Authors - Nitin Varshney, Harsh Nagar, Dhaval Pambhar, Krunal Vaghela Abstract - Federated Learning (FL) lets multiple devices work together to train a model while keeping data private. However, it has problems with managing trust, keeping the model’s integrity, and finding malicious participants in cloud environments. This article suggests TrustFLChain, a block-chain based FL framework that combines a decentralized trust management system with a scheme for collecting models based on deep learning. TrustFLChain uses a consortium blockchain to make sure that model updates can’t be changed, that participants’ trust is evaluated in a strong way using a hybrid identity-behavior trust model, and that the Proof-of-Trust (PoT) consensus mechanism works well. Trust scoring and the fraudulent detection updates are both automated by the use of smart contracts. Testing done on variety of datasets like the CIFAR-10, MNIST, and ImageNet shows that TrustFLChain is 6.5% more accurate, 38% faster to identify harmful updates, 28% faster at reaching a consensus, and 22% less energy-hungry than the current best methods. Significant improvements are supported by statistical studies (p < 0.01). TrustFLChain provides a flexible, safe, and private way to use trusted AI in cloud systems, perfect for a wide range of uses.
Authors - Ivan Blekanov, Svetlana S. Bodrunova, Li Jing, Mohsin Hassan Khan Abstract - Traditional data mining techniques, while effective for structured nu-merical data, struggle with the complexity, ambiguity, and dynamic nature of natural language. To address these challenges, topic models have emerged as a powerful tool for uncovering latent topic structures in text, enabling applications such as trend analysis, recommendation systems, and decision support. These models are particularly valuable in social network content analysis, where they help reveal user behavior, information dissemination patterns, and social dynam-ics by identifying implicit topic distributions. The linguistic diversity of text data lowers the quality of the topic models. To overcome this shortcoming, Trans-former-based text encoding is applied. However, benchmarks for text encoding are not set, and the models have not been properly compared in terms of dimen-sionality/noise reduction. We conduct comparative analysis of five neural-net-work encoding models based on the Transformer architecture, integrating them with clustering methods for efficient topic detection. We employ a dataset of COVID-related discussions from Twitter collected between November 24, 2021, and January 23, 2022. The methodology pipeline includes text encoding, dimen-sionality reduction, and clustering, with detailed steps and results discussed in the respective sections. The results show that the encoding models differ substan-tially in how they help in topic detection, with the general text embedding (GTE) model providing for the best quality. Our findings highlight the models’ differing efficiency in topic detection, offering insights for future research and practical applications in text analysis and knowledge discovery.
Authors - Truong Cong Hau, Nguyen Quoc Cuong, Tran Tat Dat, Duong Ngoc Anh, Nguyen Son Duong Abstract - In an era of increasing environmental awareness and social accountability, ESG (Environment, Social, and Governance) practices have become a strategic priority for logistics enterprises in Southeast Asia. This study aims to model the multivariate impacts of ESG implementation on firm sustainability, with a particular focus on the mediating role of Time-Critical Logistics (TCL). ESG integration is expected to enhance environmental performance, social responsibility, and governance transparency, while TCL supports the efficiency of time-critical logistics operations. Using a quantitative approach and Structural Equation Modeling (SEM), the study analyzes data from 369 from major logistics enterprises in Southeast Asia. Findings are anticipated to confirm the positive influence of ESG on sustainability, with TCL playing a key mediating role.
Authors - Palash Sontakke, Pankaj Chandre, Prashant Dhotre, Ganesh Pathak Abstract - The dyeing segment of textile manufacturing faces pressing demands to curb water, energy and chemical consumption while maintaining colour con-sistency and fast throughput. This paper presents a layered edge‑to‑cloud archi-tecture that employs artificial‑intelligence techniques to manage resources dy-namically across the entire dyeing supply chain. IoT sensors on each dyeing machine stream high‑frequency telemetry to an AI cloud where data are curated in a scalable lake and enriched through feature engineering. Deep‑learning models forecast short‑term demand, yields and process drifts, enabling proac-tive recipe adjustments. A digital‑twin simulation engine mirrors every dye bath and tank, permitting insilico experimentation of eco‑friendly formulas without risking live production. Reinforcement‑learning agents, trained against the twin, generate near‑optimal job schedules and set‑points that minimise water and chemical footprints while respecting delivery constraints. All recommendations pass through an explainable‑AI module that surfaces the key factors driving each decision to foster operator trust and regulatory compliance. A blockchain ledger records batch‑level resource transactions, ensuring tamper‑proof tracea-bility for audits and sustainability certifications. The architecture integrates seamlessly with existing ERP/MES systems, closing the loop between predic-tive intelligence and shop‑floor actuation. Proof‑of‑concept results from a mid‑scale dye house show up to 18 % water savings and 12 % energy reduction, with payback achieved in under nine months. Collectively, the proposed framework demonstrates how advanced AI and Industry 4.0 technologies can deliver both economic and environmental gains in dyeing operations.
Authors - Harsh Nagar, Nitin Varshney, Twinkal Chavda, Krunal Vaghela Abstract - Machine learning (ML) produce a huge impact in the Fourth Industrial Revolution that will change everything. ML makes systems very precise and efficient in many sectors like as cyber security, healthcare, smart cities, and farming that is good for the environment. This article examines the different aspects and advancements in machine learning since 2021. It cover wide area which gives more details and fill gaps in crucial fields like ethical AI, real-time processing, energy efficiency, explainability, federated learning, and adversarial stability. We investigate supervised, unsupervised, semi-supervised, reinforcement, and deep learning algorithms, supported by solid theoretical frameworks, mathematical formulations, and empirical evaluations on extensive benchmark datasets (e.g., MNIST, CIFAR-10, NSL-KDD, UCI datasets). These contributions include deep study of performance evaluations, visual representations crafted with Python, and architectural frameworks for hybrid machine learning systems. These diverse results shows that how things work and implement in the real world and mark the difficulties like bias, scalability, and latency. The future will be about ML solutions that are precise, accurate, adaptable, and durable. This publication offers scholars and practitioners a technological framework that fosters innovation in the Fourth Industrial Revolution (4IR).
Authors - Irappa Alagur, Prayag Gokhale Abstract - Managing finance is an important skill that differs across the generations, influenced by their investment preference and risk-taking ability. This study is an explorative study that reveals the investment preference, awareness, participation and risk tolerance among Generation Z and Generation Y. Thes research is undertaken with the objectives to examine the investment awareness amongst Gen Z and Gen Y investors, their future investment choices and assess their risk tolerance level. For the study, convenience sampling technique is used with structured questionnaire for data collection from 100 respondents confined to Bangalore, the silicon city of India. The questionnaire is designed to include 15 questions; all are set in google form and distributed amongst the intended audience on selective bases fulfilling the criteria and requirement. The responses are captured and presented in pictorial diagrams. The authors analyzed all the responses separately. The findings of the study revealed that Generation Zs are risk-taking investors, and they prefer to have investment in high liquid funds and unfamiliar markets where outcome is hard to predict to leverage risk with return. It is also found that Gen Zs are very volatile in keeping their investment in a particular fund and rollover frequently to satisfy their short-term requirements. In contrast, it is observed from the analysis that Generation Y investors are risk-avoidable and prefer to invest in stable and long-term assets like fixed deposits and commodities. They prefer to invest in a familiar market with low volatility where risk is minimum with constant return.
Authors - Tam Nguyen Minh, Tai Vu Thanh, Quynh Chi Truong, Thi Ai Thao Nguyen Abstract - The growing reliance of enterprises on internal and information systems has led to an increased risk of cyber attacks, which pose serious threats to the confidentiality, integrity and availability of data. Intrusion Detection Systems (IDS) are essential for identifying malicious activities; however, conventional IDS approaches often struggle with evolving and sophisticated attack vectors. Recent advances in machine learning (ML) offer new opportunities to enhance IDS capabilities through adaptive and data-driven models. This study proposes a hybrid architecture that integrates convolutional neural networks (CNN), long-short-term memory (LSTM), and gradient boosting machines (GBM), leveraging both supervised learning and advanced feature representation techniques, addressing key challenges such as limited labeled data, diverse traffic patterns, and resource constraints in small and medium enterprises (SMEs). The proposed approach includes an end-to-end pipeline for data collection, preprocessing, feature extraction, and data labeling, combined with aug-mentation techniques to improve model generalization. Experimental evaluation across different network scales demonstrates the effectiveness of the method in detecting both known and novel attack types, while maintaining computational efficiency. The findings contribute to a practical and scalable solution for enter-prise network security, with implications for real-world IDS deployment and fu-ture research in ML-driven cybersecurity.
Authors - Princessa Natasya Kwang, Yanthi Hutagaol-Martowidjojo Abstract - This research analyzes the effect of ESG disclosure scores on stock price synchronicity among Australian mining companies, exploring each pillar's contribution. The final sample consists of 275 firm-year observations of Australian listed mining companies covering the period from 2020 to 2024. Data was collected from Bloomberg and Factset. This study adopts the price synchronicity model proposed by Hutagaol-Martowidjojo et al. (2023) and panel data regression is employed to analyse and test the research hypotheses. The study concludes that ESG disclosure is significantly associated with higher price synchronicity, implying that while ESG disclosure scores enhance overall market visibility, they may simultaneously reduce the uniqueness of firm-specific information.
Authors - Mayur Rajendra Badiger, Tejasvi Bellubbi, Aditya Holla, Jayanth H T, Kavitha Devi CS Abstract - India, as the world’s largest democracy, faces the ongoing challenge of low voter turnout, with recent national elections recording a participation rate of just 65.79%. This issue is exacerbated by the existing electoral requirement that voters be physically present in their registered constituencies, effectively disenfranchising millions of migrant workers and citizens residing away from home. The proposed Smart and Secure Electronic Voting System addresses this critical gap by enabling inter-state voting, allowing eligible voters to cast ballots for their home constituencies from any location across the country. Built on an Arduino Uno platform, the system integrates biometric fingerprint authentication to ensure secure and unique voter identification, while an LCD interface displays constituency-specific candidate lists. Votes are securely transmitted and stored in a cloud-based database via a WiFi module, using the ThingSpeak server for real-time, tamper-resistant data management. The system prevents multiple voting attempts by locking out voters after a successful ballot submission, thereby upholding electoral integrity. By combining IoT technologies and robust biometric verification, this solution not only simplifies the voting process for the floating population but also strengthens the inclusivity, accessibility, and representativeness of the Indian democratic process.
Authors - Trilochan Jena, Pradipta Kumar Sanyal Abstract - A key role of mergers and acquisitions (M&A) is to help businesses grow rapidly in competitive markets. Foreign companies entering the Indian market have made it tough for small businesses. Using mergers and acquisitions (M&A) and restructuring has become a standard practice to ensure a company’s survival, advancement, and competitiveness. A significant number of bank mergers have occurred in India over the past decade, prompting many to wonder whether they have been efficient in adding value for bank owners. The analysis pairs four public sector banks post-merger—SBI, PNB, BOB, and Canara Bank—with four other public sector banks that did not merge—IOB, UCB, BOI, and CBI—all based on their market capitalization. To measure organic growth, Current Ratio, Advance to Deposit Ratio, NPA to Advance Ratio, Capital Adequacy Ratio, Operating Profit Ratio, Net Profit Ratio, Interest Coverage Ratio, EPS, and Dividend Payout Ratio are reviewed. We analyze inorganic growth using the Standard Event Study Methodology in a period from -200 to +30 days. Financial and operational results were better for merged banks than for non-merged banks following the merger. Although the AR and CAR results for mergers were mainly positive, they did not reach a level of statistical significance. Each merged bank displayed sound financial performance based on its Altman Z-score (>2.6). Overall, M&As help shareholders, and yet banks that haven’t merged take care of the remaining issues proactively.
Authors - Niranjan C Kundur, Anil B C, Sreenatha M, Jayasimha S R Abstract - A hybrid machine learning framework designed to predict burnout levels and employee retention among IT professionals in urban India a sector increasingly challenged by mental health issues, high attrition, and work-life imbalance. The proposed framework integrates Gradient Boosting Regression for continuous burnout score prediction and Random Forest Classification for binary retention outcomes. Data were collected from 300 IT employees across five metropolitan firms, encompassing cross-sectional and temporal variables related to work conditions, wellness policies, and demographic profiles. Rigorous preprocessing, feature encoding, and 5-fold cross-validation ensured robust model performance. The burnout prediction model achieved an R² score of 0.87 and a Mean Absolute Error (MAE) of 4.12, while the retention classifier yielded an accuracy of 85%, F1-score of 0.82, and AUC-ROC of 0.88. Key predictors included flexible hours, remote work options, and job satisfaction, with gender emerging as a significant moderating factor—female employees demonstrated 12% greater sensitivity to burnout-related outcomes. The findings highlight the utility of predictive analytics in identifying high-risk employees and guiding personalized wellness and retention strategies. This hybrid framework offers HR leaders a scalable, data-driven tool to optimize workforce well-being and reduce attrition in the evolving landscape of Indian IT workplaces.
Authors - Thejan Dulara, Indra Mahakalanda, Prasanga Jayathunga Abstract - Media budget allocation remains a major challenge in the advertising industry. Inefficient spending and biased budgeting decisions often cause un-derperforming campaigns. It is a challenge for advertisers to strike the right balance between traditional media like TV, radio, press and the digital media. This not only wastes resources but reduces campaign impact. Media mix problem revolves around media performance and return on investment. This study develops a data-driven media mix determination model using machine learning and genetic algorithms. The goal is to maximize audience reach while minimizing costs. The model focuses on key quantitative factors such as cost-effectiveness, media efficiency, and saturation points. The use of data collected from the Sri Lankan market ensures the practical relevance of the study. Supervised machine learning models such as decision trees, random forests, XGBoost, and LightGBM are tested to understand the complex, non-linear behavior of media performance. The above models predict how different channels respond to increased spending. Curve smoothing enables the identification of saturation point and efficiency levels. A genetic algorithm deployed to identify the optimal budget allocation across media platforms. The result provides a practical media mix for the Sri Lankan advertising industry where advertising planners can allocate budgets more effectively with minimum overspends to achieve higher campaign success. Although the models were learned using a country specific data set, they can be used for similar scale markets. This study contributes to the existing literature by developing an efficient method for me-dia advertising planning.
Authors - Niranjan Kulkarni, Suma MN Abstract - This paper introduces an integrated model that couples financial literacy training with financial therapy to enhance financial knowledge as well as behavioural results. Basing its argument on existing literature, this study employs a mixed-methods methodology to assess the effectiveness of pilot programs that blend therapeutic interventions like cognitive-behavioural therapy (CBT) and financial counselling with standard financial education. The study unveils the need for an integrated financial education approach, providing a model for the development of more effective financial literacy programs that consider cognitive as well as affective dimensions of financial well-being.
Authors - Wirote Jongchanachavawat, Noppon Mingmuang, Chayut Ployjirapas, Kwanchai Nanan, Kamonwan Oiumekha, Noppong Cheychuen, Wannatham Noyklay, Polaphat Laima, Suphat Bunyarittikit Abstract - This research presents the development of a low-cost obstacle avoidance prototype designed for mobile robotic applications, with a potential use case in autonomous wheelchairs. The system utilizes a single ultrasonic sensor mounted on a servo motor to perform multi-directional distance scanning, allowing the robot to detect and avoid obstacles in real time. An Arduino-based control algorithm interprets distance measurements at four predefined angles (30°, 60°, 120°, and 150°), enabling the robot to make navigation decisions including forward movement, turns, and retreating actions.The system was tested under various conditions: with obstacles in front, in front-left, and in all directions (front, left, and right). Results showed a 100% success rate in the simple frontal obstacle scenario, 80% in the front - left obstacle case, and 60% in the most complex environment with obstacles on three sides. The primary cause of failure was the sensor's limitation in detecting very close objects (less than 2 cm).The findings confirm the feasibility of implementing this single-sensor approach in low-cost assistive mobility devices. The prototype demonstrates effective navigation capabilities and provides a practical foundation for future development of intelligent obstacle-avoidance systems for autonomous wheelchairs.
Authors - Albrecht Kati, Vilko Jyri Abstract - Restaurants and their customers value natural food products (NFPs), and demand for them is growing steadily due to product qualities such as taste and freshness, as well as support for sustainable development. However, the availability of natural food products from suppliers can be challenging. Availa-bility challenges mean that the market for natural food products is inefficient. This also makes it difficult for restaurants to define their competitive strategies. Local restaurants are often small, entrepreneur-driven businesses with a few dozen employees. In small restaurants, resources are spent on daily operations, and systematic long-term development is often given less attention. However, systematic operations require clear, planned customer segmentation and, through this, the development of competitive strategies as a means of creating value. The main objective of the study is to increase understanding of the link between cus-tomer segmentation and competitive strategies in business and the added value they generate. In addition, the study aims to guide restaurants towards more sys-tematic business development. The data was collected through qualitative re-search and in-depth interviews with restaurant owners and managers in Finland. The research was based on thematic analysis, and the results were documented using NVivo software. Restaurants were found to have insufficient knowledge of how NFTs can be used to create value-added business and how customers can be segmented using competitive strategies.
Authors - Thejan Dulara, Indra Mahakalanda, Prasanga Jayathunga Abstract - Efficient media scheduling plays a vital role in advertising campaign success. Among media platforms, television remains a key channel for audience engagement. However, allocating advertisements across programs, times, and channels is a complex task. The number of possible combinations exceeds human evaluation capacity. Advertisers often face challenges in allocating spots effectively while minimizing plan cost. This study implements a Mixed Integer Linear Programming (MILP) model to optimize spot allocation across TV programs. The objective is to minimize the Cost Per Rating Point (CPRP), a key efficiency metric. The model maximizes the normalized gross rating point (GRP), subject to constraints such as total budget, program slot availability, and fair commercial distribution. By transforming a nonlinear objective into a solvable MILP framework, the model ensures practical feasibility and scalability. The results demonstrate improved CPRP performance and significant time savings under realistic constraints. This approach supports advertisers in making data-driven, cost-effective media scheduling decisions. The study offers a replicable framework for optimizing television advertising plans in dynamic markets.
Authors - W Saib, T Moodley Abstract - In modern football, smart recruitment is essential in building successful teams. Traditional scouting methods, though effective in identifying player mentalities, often fall short due to the team’s budget restrictions and the need to fit the head coach’s strategy. Teams frequently lose top targets to wealthier clubs, sign players who do not fit with the coach’s strategy and overlook affordable and stylistically similar players. To address this, we propose a novel player recommendation system, which first clusters players and then leverages the Graph Convolutional Networks (GCNs) ability to generate rich node embeddings from a player-similarity graph constructed via cosine distance. Using data from FBref, we refine the scope to only central midfielders and on the Graph Convolutional Network where the target variables are the labels from K-Means clustering of which we obtained 49% accuracy with all neighbours but a perfect 100% with shared-label aggregation introduced in this paper. It was observed that there were significant visual differences (obtained via t-SNE) in the clusters formed. Graph Convolutional Networks are primarily used for node classification on academic citation datasets, and the proposed method in this research outperformed on the Cora (88%) and Pubmed (84%) Datasets, respectively.
Authors - Bimlendu Shahi, V. Pushparajesh Abstract - The rise of Software defined network-based containerized applications has driven the need for efficient resource management and network optimization, especially in constrained environments for Raspberry Pi. This paper highlights the AI driven approach in optimizing Raspberry Pi-based container setups using Strongly typed genetic programming (STGP). This generative AI driven approach is followed by the prompt engineering aspects for implementation of adaptive approach in SDN Network. The proposed approach improves task success rates, reduces latency, and min-imizes resource contention based on real-time network metrics using CPU usage, Memory utilization and Network consumption. Experimental results demonstrate the effectiveness of STGP in maintaining optimal performance in highly dynamic network environments. The proposed model allows more precise and adaptable solutions for resource-constrained SDN environments on distributed systems of Raspberry Pi.
Authors - Ervine de Vasconcellos, Tapiwa Gundu Abstract - The rising acceptance of digital technology to improve patient care has made cybersecurity one of the biggest issues for healthcare workers. Having an urgent need to fully understand accepted cybersecurity standards and the main causes of non-compliance. Knowing how healthcare workers see cybersecurity policies becomes essential as a result of the following interruptions in services and more complex assaults that target hospitals and clinical environments. The objective of the research was to provide guidelines for addressing the non-com-pliance with cybersecurity policies by healthcare workers in South Africa. A lit-erature review was carried out to determine the current status of cybersecurity policies in healthcare and a systematic literature review was done to determine the causes of healthcare workers non-compliance with cybersecurity policies. The systematic literature review provided some themes which were then analysed and guidelines were created based on them.
Authors - Aishwarya Anand Arora, Charu Gupta Abstract - The explosive growth of artificial intelligence (AI), particularly generative AI, poses opportunities and challenges gender equality. AI has the capacity to shatter cultural boundaries and build inclusive systems, yet latent algorithmic bias and gender inequality in its composition can exacerbate existing divisions. This overview delves into the ways generative AI can both perpetuate or decrease gender bias, contingent upon how responsibly it is created and deployed. AI systems tend to reflect the biases of the society they are designed from. For instance, AI recruitment tools have tended to select more male candidates because of gender-biased historical data. Generative AI, too, tends to underrepresent women in leadership positions and perpetuate stereotypes. If unregulated, these systems stand a chance of perpetuating gender imbalance across industries. In this paper, we have discussed how AI also has the potential to advance fairness. Resume-anonymizing tools, huge data set analysis to detect biased tendencies, and individualized learning plans can promote gender inclusiveness. AI can help bridge STEM access disparities for women and provide supportive mentoring networks in education. To harness these benefits, responsible AI governance is critical. Fairness audits, diverse datasets, transparency, and accountability should guide AI development. Increasing women’s participation in AI research and policymaking is also key to creating more equitable systems. Ethical AI guidelines must ensure that AI use is inclusive, fair, and non-discriminatory. Generative AI has the potential to be an effective catalyst of gender equality when coupled with ethical governance, representative data, and representation diversity, leading towards a more equitable, AI-powered world.
Authors - Precious Magodi, Tevin Moodley Abstract - Vision-based sign language recognition significantly advances communication within the deaf community, enhancing accessibility and inclusion for those who are deaf or hard of hearing. This paper presents a system developed for real-time recognition of South African Sign Language (SASL) using Google’s MediaPipe framework for spatial feature extraction and a long short-term memory (LSTM) network for temporal modelling.We utilise a subset of the ASL Citizen dataset, focusing on five classes: “SCHOOL,” “TIMEOUT,” “MORNING,” “THANK YOU,” and “I LOVE YOU,” which serve as proxies for SASL vocabulary. Keypoint sequences from both hands and body pose are extracted via MediaPipe and fed into a two-layer LSTM for classification. Trained with a Tensor- Flow TFRecord pipeline, our model achieves a test accuracy of 35.5% and highlights the challenges posed by limited data and variability among signers. This work demonstrates the potential of combining MediaPipe and LSTM for real-time sign recognition and emphasises the need for larger, language-specific datasets to improve accuracy.
Authors - Rohan Anantapur, Pranav Rao Pernankil, Animesh Giri Abstract - The emergence of smart carts in the retail and shopping industry has introduced questions regarding the safety and security of these autonomous guided vehicles. While smart carts enhance the shopping experience through automation and real-time transaction processing, they are susceptible to various risks that can compromise their functionality and user data. Many existing cyberattack detection systems fail to consider a well-rounded set of features, leaving smart cart networks exposed to sophisticated threats. This approach enhances the resilience of smart cart systems by detecting and mitigating security breaches effectively. In this paper, we introduce DeepCart, a cyberattack detection and classification system that focuses on violations in smart cart networks. DeepCart leverages Generative Adversarial Networks (GAN) to identify cyberattack data patterns and employs Deep Belief Networks (DBN) for accurate classification of detected threats.
Authors - Jonalyn Echano, Carla Dayne N. Ferreras, Jhaniella Anne T. Ganuelas, Maria Angela P. Obsuna, Regienald G. Obina Abstract - As digital commerce continues to thrive, the Philippine government has implemented the Creditable Withholding Tax on Electronic Marketplace Transactions to ensure tax compliance among online sellers. This study explores how online sellers in Quezon City cope with the challenges brought by this regulation. Specifically, it examines their coping mechanisms in relation to the complexity of tax laws, perceived fairness of the tax system, quality of tax admin-istration, effectiveness of enforcement measures, and the level of penalties and sanctions. A quantitative research design was employed, using a structured survey distributed via email and social media. The study gathered responses from 113 online sellers operating within Quezon City. Statistical tools such as frequency distribution, weighted mean, and ANOVA were used to analyze the data. Findings revealed that while most sellers perceived the tax system as generally fair and the administration as responsive, they struggled with the complexity of the laws. Many sellers acknowledged the effectiveness of enforcement and the influence of penalties in motivating compliance. However, differences in coping mechanisms were significantly evident only when sellers were grouped by busi-ness experience and perceived fairness—while factors like capitalization and business category showed no major influence. The results highlight the need for clearer guidelines, simplified tax processes, and continuous education efforts. This research contributes to a deeper understanding of how small digital entre-preneurs adapt to evolving tax policies, offering insights for policy improvements that support voluntary compliance and fairness in the growing e-commerce sec-tor.
Authors - Pujari Suresh Kumar, Sushama Rani Dutta Abstract - Image Inpainting is the field that reconstructs the missing regions with high-quality image restoration. The image restoration addresses the loss of conditional details and distortion of visual quality in damaged images. In this paper, a Scale-Variant Learning (SVL) model is presented that combines super-resolution and deep image inpainting for the restoration of missing or damaged regions, resulting in increased image clarity and high resolution. The proposed SVL consists of a super-resolution network that first recovers high-frequency details from low-quality input and an inpainting module that fills in missing re-gions by leveraging both contextual and structural information. To generate photo-realistic output, a multi-scale feature fusion, attention mechanisms, and adversarial learning are used to enable the model learns the global semantics and local texture consistency. The pre-trained model DeepFill v1, with transfer learning applied to large-scale high-resolution datasets (CelebA-HQ and Plac-es2), shows competitive performance compared to existing techniques in both quantitative evaluations and visual appearance. This pre-trained model fills the gap between missing content and accurate regions, from image restoration and editing to historical image repair and computer vision tasks that require fine-grained representation.
Authors - Yuya Ieiri, Tengfei Shao, Osamu Yoshie Abstract - Social capital is recognized as an important concept for revitalizing commercial districts. However, the dynamics of social capital within these dis-tricts remain largely unexplored. As an initial step toward addressing this gap, this study conceptualizes changes in the social network of a commercial district community as shifts in social capital. Furthermore, it investigates the impact of information sharing within the community on this social capital. The study developed a framework to examine the relationship between social capital and so-cial networks. An empirical investigation involving ten participants and three experiments was conducted over three weeks. Results indicated that participants' subjective evaluations of store importance are influenced by the mode of information sharing within the community. Furthermore, the findings suggest that structured, repeated information sharing can strengthen interpersonal rela-tionships within the network. From a social-capital perspective, these findings imply that information sharing within interactive groups can potentially foster its development.
Authors - Ryo Itokawa, Eisuke Ito Abstract - With the widespread adoption of smartphones, digital credential presentation systems such as the EUDIWallet and ISO-compliant mobile driver’s licensesare being deployed worldwide. In contrast, human access control at data centers still primarily relies on a combination of physical IC cards and biometric authentication. This creates a considerable burden for engineers who frequently need to access multiple facilities, as they must manage several physical IC cards. To address this issue, this study investigates the feasibility of introducing a digital access pass based on the Verifiable Credentials (VC) framework, currently being standardized by the W3C. Building on the experience gained through the development of a VC-based digital student ID system at Kyushu University, we propose a conceptual system that enables the issuance, presentation, and verification of credentials via smartphones. In this paper, we outline the current operational practices and challenges of human access control in data centers. We also present a conceptual model of a VC-based digital access pass, followed by a discussion of future directions and challenges for implementation.
Authors - Anand Ghugare, Atharva Rajoba, Dinesh Kumar Saini Abstract - Quantum computers poses a significant threat to traditional cryptography systems, which depend on integer factorization. Theoretically, Shor’s algorithm, a quantum polynomial-time algorithm, allows quick factorization of huge semiprimes, compromising the RSA protocol. This paper shows hardware-based execution by implementing Shor’s algorithm using IBM’s quantum resource and Qiskit framework to factor the number 221. The study examines the success probability and performance limitations of implementation on noisy quantum hardware. Our results provide valuable insights into effective quantum cryptanalysis and pave the path for scaling such approaches for larger numbers.
Authors - Tapiwa Gundu, Nangamso Mmango Abstract - Small and Medium Enterprises (SMEs) in South Africa face signifi-cant cybersecurity challenges due to poor password hygiene practices. Employees and managers frequently experience password fatigue, leading to dangerous security shortcuts such as password reuse, weak credential creation, and physical recording of passwords. While comprehensive cybersecurity frameworks exist for large enterprises, SMEs lack practical, tailored solutions that account for their limited resources and technical expertise. This study conducts a systematic literature review (SLR) to analyze existing research on password security challenges in SMEs, with particular focus on the South African context. The review identifies key vulnerabilities and synthesizes evidence-based recommendations into actionable password hygiene guidelines specifically designed for SME environ-ments. The proposed guidelines emphasize usability alongside security, offering realistic strategies to improve authentication practices without overwhelming staff. Findings highlight the critical need for simplified policies, appropriate tech-nological tools, and continuous security awareness training in resource-constrained SME settings.
Authors - Nirel Marie M. Ibarra Abstract - The fast changes in front-end web development technologies have widened the gap between what schools teach and what businesses need in the Philippines. This paper offers the first systematic study of developer job postings in the country, using a new approach that combines web scraping, LLM-based classification, and statistical analysis. By examining hiring needs across small, mid-sized, and large companies, the study highlights apparent differences in technology preferences, range of skills, and business practices. The findings indicate that smaller firms look for adaptable generalists, while larger organizations focus on specialized skills and organized processes. There are also early signs of a demand for AI knowledge in various settings. These insights form a Minimum Viable Skill Set (MVSS) that includes technical skills like React, JavaScript/TypeScript, HTML, CSS, Git/GitHub workflows, and basic DevOps. It also includes the ability to adjust to different work environments. The results aim to guide curriculum changes in Philippine universities and act as a model for other ASEAN countries.
Authors - Keishin Asakura, Yuya Ieiri, Hiroki Sasayama, Osamu Yoshie Abstract - Recently, the importance of designing tourism routes based on a com-prehensive evaluation of tourist experiences has been increasingly recognized. One common approach for such an evaluation involves the use of electrodermal activity (EDA) data, a physiological indicator of emotional arousal. However, owing to the high cost and complexity associated with collecting and analyzing EDA data, their use in real-world tourism settings remains limited. Consequently, this study focused on the individual excitement level (IEL) curve as a subjective and cost-effective alternative for visualizing emotional transitions during sight-seeing. Building on previous studies, we developed a web-based application that allows tourists to self-report their emotional responses with greater granularity. Unlike previous methods that use only three levels, the proposed system supports both a five-level positive scale (1 to 5) and an extended ten-level scale (-5 to +5) that incorporate negative emotions. We conducted a field experiment in Mojiko, Kitakyushu City, where participants used the application while engaging in actual sightseeing. The results demonstrated that IEL curves based on five- and ten-point evaluations exhibited stronger alignment with the EDA data than those based on a three-point evaluation. In particular, the inclusion of negative evalua-tions on a ten-point scale enabled a more comprehensive representation of emo-tional fluctuations. These findings suggest that the proposed method enhances the expressive capacity for emotional self-reporting and supports the practical implementation of data-driven tourism route planning.
Authors - Alma Delia Torres-Rivera, Laura Alma Diaz-Torres, Mario Leonardo Nieto Antolinez Abstract - This study proposes a theoretical framework for integrating artificial intelligence into sustainable business models for urban public transport. Drawing on a literature review and two in-depth expert interviews (in data analytics and operations), it identifies key structural challenges in the sector, including fragmented concession models, rising costs, declining demand, environmental pressures, and weak alignment with national policies such as the National Policy for Urban Collective Public Transport. The findings indicate that artificial intelligence alone is insufficient to achieve sustainability; it must be integrated with robust enterprise architecture and adaptive strategic planning. To support this integration, the study presents a six-phase roadmap: structural diagnosis, enterprise architecture redesign, strategic planning, AI integration, training and change management, and continuous evaluation. This roadmap offers a practical and ethical pathway for digital transformation aligned with the Sustainable Development Goals. Ultimately, artificial intelligence can improve efficiency, resilience, and sustainability—provided its deployment is context-sensitive and supported by institutional leadership, organizational capacity, and cross-sector collaboration.
Authors - Shruthi S, Manjula Y Abstract - Automated emotion detection through facial analysis represents a cru-cial technological advancement for interpreting human expressions from digital images. Current classification approaches face challenges in achieving precise accuracy because they extract insufficient distinguishing characteristics needed to differentiate various emotional states. To address these issues, we introduce a Parallel Deep Convolutional Neural Network (PDCNN) incorporating Gaussian Error Linear Unit (GELU) activation for enhanced emotion classification performance. Our methodology utilizes two established benchmark collections: FER-2013 and Japanese Female Facial Expression (JAFFE) databases, which undergo preprocessing through Contrast Limited Adaptive Histogram Equalization (CLAHE) and dataset balancing via Generative Adversarial Network (GAN) based augmentation techniques. Subsequently, the enhanced dataset undergoes feature extraction using DenseNet-121 architecture, which captures representa-tions through densely connected layers before processing through our dual-stage classification framework. This system leverages both localized and comprehen-sive facial characteristics, integrating them via a fusion mechanism for precise emotional categorization. Our experimental validation demonstrates that the PDCNN with GELU approach achieves superior performance with 94.67% ac-curacy on FER-2013 and 99.10% on JAFFE datasets, outperforming traditional CNN, Convolutional Relational Network (CRN), ResNet-50, Wavelet DCNN, and Three Channel-CNN methodologies.
Authors - Suthawan Prukumpai, TzeHoung Lee, Patrick Ghali Abstract - Traditional correlation metrics like Pearson correlation capture only linear and symmetric relationships between variables, potentially obscuring meaningful dependencies in financial systems where nonlinearities and lead-lag effects are common. This paper introduces SVMBased Predictive Correlation (S2C), a novel approach that redefines correlation in terms of predictive power rather than mere association. S2C accommodates nonlinearities and directional structures within data, allowing practitioners to better gauge risk and properly size allocations. We develop the mathematical foundations of S2C within the context of kernel methods and reproducing kernel Hilbert spaces (RKHSs), then present an empirical study involving financial and macroeconomic time series with different update frequencies. Our analysis demonstrates that S2C can recover both linear and nonlinear relationships, is more robust to irregular sampling than standard correlation measures, and captures directionality by revealing how one variable can predict another. We conclude with implications for portfolio construction and risk management, particularly addressing the ”volatility washing” problem in portfolios containing illiquid alternative investments.
Authors - Victor Edwin Reyes, Joele Althea Manansala, Wilson M. Tan Abstract - The process of document notarization in the Philippines is vulnerable to institutional corruption due to a lack of a centralized source of truth. Recent initiatives by the Philippine government to introduce a digital-ready national ID system allow for an e-government-based approach to tackle this problem. This paper proposes an institutional and technical framework for such an approach, describes the implementation of a minimal viable system, and provides recommendations based on its performance under test loads. Such a framework must minimally comprise of institutional support, a storage for documents and notarization records, a mechanism for identity validation, and a physical information format along with a reader of this format. This proposed framework was implemented minimally and tested. Recommendations based on these tests were made with an emphasis on improving performance and technical rigor.
Authors - Markus Heikkila, Alisa Misukka, Ilkka Kero, Kati Albrecht, Jyri Vilko Abstract - Entrepreneurship in the natural product field is growing, founded in the utiliza-tion of sustainable natural resources and entrepreneur’s personal values and motives. Natural product field offers interesting perspectives for entrepreneurship where business activity is shaped by financial targets, personal value system and relationships with nature. The field’s immatureness, heterogeneity, and undeveloped supply chains highlight the decisions independent entrepreneurs make regarding their business strategy. This research explores the path towards entrepreneurship of two entrepreneurs within the natural product field regarding entre-preneurship motivation and commercialization strategies in the form of an extreme case study. It addresses that entrepreneurship within natural product field is driven by passion, customer entered approach, and willingness to combine per-sonal values with business activity. Case companies differ from one another re-garding their willingness to grow, educational background, and brand building. However, similarities can be found regarding valuing quality, customer feedback, and self-directed information seeking. The results expand previous understanding about entrepreneurship motives, indicating how strategic make or buy decisions are tied into entrepreneur’s identity, values and resource acquisition. Specifically in natural product entrepreneurship, commercialization is not only a technical process but rather based on entrepreneur’s value system, covering product origin, authenticity and ethical grounds.
Authors - Sneha Warrier, Umesh Mahtani, Smitha Rao Abstract - This study makes a novel attempt using ensemble Machine Learning (ML) techniques to analyze the impact of various Environmental, Social, and Governance (ESG) indicators on the financial performance of publicly listed entities in India. The findings highlight the importance of looking beyond the ESG score and assessing the most important ESG indicators that impact firms’ finan-cial performance. The main findings establish a relationship between Tobin’s Q (firm value) and individual ESG indicators. The study shows that ESG indicators have comparatively less impact on the internal accounting measures of Return on Total Assets (ROA) and Return on Net Worth (RONW). The results list the following key ESG indicators: energy intensity and consumption, equal and mini-mum wages to employees, turnover rate, as those having impact on Tobin’s Q across the various ML models explored. These research findings would assist corporations, investors, and policymakers in identifying key ESG indicators that impact financial performance of companies.
Authors - Gokulraj G, Bose S, Danya S, Maheswaran N, Illakiya Varshini C, Pradeep Kumar M Abstract - Cloud computing environments increasingly face sophisticated cyber threats due to their distributed and open-access nature, demanding robust security solutions for data integrity. To address these challenges, this work proposes a Hybrid Multi-Model Ensemble System that uses advanced hypergraph techniques for comprehensive intrusion detection and prevention. The system combines models such as Hypergraph Neural Networks (HNN), Variational Autoencoders (VAE), and Graph Attention Networks (GAT) to boost detection precision for complex attack patterns. An Adversarial Module with ZOO Model (Zeroth Order Optimization) boosting generates challenging attack samples, strengthening the pipeline’s resilience against evolving threats. Real-time protection is reinforced through an SNORT-powered Intrusion Prevention Module that blocks intrusions proactively with adaptive policies. Experiments show that the proposed ensemble achieves detection accuracy above 90%, surpassing single-model approaches. This strong accuracy, along with reliable recall and precision, confirms the hybrid architecture minimizes false positives while accurately classifying diverse intrusion types. Overall, the system’s advanced modeling and adaptability offer a scalable solution for securing cloud infrastructures against known and novel attacks.
Authors - Monu Bhagat, Sunil Kumar Abstract - Recently, the identification and classification of illnesses from images of plant leaves have been an ongoing problem in agricultural research. There is a dearth of proper dataset to be able to use modern deep learning-based disease detection algorithms for plant disease detection. We may rely less on farmers to take precautions to ensure the safety of their crops if they can use image-processing techniques to identify plant illnesses. For better use of these advancements mobile applications need to be developed, where farmers directly can upload the images and get desired feedback for his crop/plant. In this work we have developed such a solution where we attempted to solve the dataset crisis by using cycleGAN and used the generated synthetic dataset for leaf disease detection. For classification, we used transfer learning model EfficientNetB3 and achieved classification accuracy 93.33%. Finally, these developments are implemented in a mobile application for easy and scalable use for farmers.
Authors - Nasir Ansari, Amit Kumar Sharma Abstract - A significant challenge in human-computer interaction is enabling effective communication for individuals with hearing impairments. This research addresses the need for accessible solutions by implementing a neural network-based system for recognizing American Sign Language (ASL) letters from images captured via a standard webcam. The primary objective is to reduce the communication barrier between the deaf and hearing communities by leveraging machine learning techniques for hand gesture classification. A Convolutional Neural Network (CNN) was utilized for both feature extraction and classification tasks. The model was trained on a publicly available Kaggle dataset comprising 87,000 images across 29 ASL alphabet classes. Experimental results demonstrate that the proposed model achieves high classification accuracy, indicating its potential applicability in real-time ASL translation systems. When we sit down to plan the next phase of the project, well add real-time gesture tracking, mix in voice and touch data, and shrink the whole model so it runs smoothly on phones and tablets.
Authors - Siham Beloualid, Abderrahim BAJIT, Hicham Essamri, Youness Zahid, Nabil Srifi, Rachid Elbouayadi, Aya Essafini, Salaheddine Zezaan Abstract - The growing demand for intelligent healthcare systems emphasizes the need for advanced technologies that support continuous, non-intrusive patient monitoring in clinical environments. This paper presents a comprehensive solution that integrates both static and mobile IoT nodes, coupled with AI-driven perception and analytics, to enhance monitoring capabilities within hospital settings. The proposed system incorporates three core components: autonomous navigation, computer vision–based health assessment, and machine learning–enabled sensor analysis. Static nodes are deployed at each patient’s bedside to collect physiological and environmental data in real time using embedded sensors, while simultaneously capturing visual data through fixed cameras. Sensor data is analyzed using machine learning models that predict missing values in case of sensor malfunction or loss, ensuring reliable and uninterrupted monitoring. In addition to static setup, a mobile robot navigates autonomously through hospital wards, executing monitoring routines based on user-defined schedules or clinical priorities. During its rounds, the robot collects visual data of patients and surgical sites. Deep learning models, applied to extract subjective information, are employed to analyze patient posture, wound healing progress, and to detect essential items such as medicine containers and water bottles. These models also support autonomous navigation by enabling path recognition and action planning. The system integrates insights from both static and mobile nodes into structured, real-time reports that assist in the early detection of clinical issues and timely informed medical decisions. This solution provides a scalable and objective approach to continuous patient assessment. It improves monitoring quality services, reduces reliance on subjective manual evaluations, enhances staff efficiency, and fosters a more responsive, data-informed hospital environment.
Authors - Patil Pratima, Deshpande Deepa Abstract - This paper presents a real-time thermal face detection and recogni-tion system based on an enhanced Multi-task Cascaded Convolutional Neural Network (MTCNN) framework. Unlike visible-light methods, thermal imaging introduces domain-specific challenges such as low spatial resolution, high noise, and intensity variance due to temperature fluctuations. To address these, we propose a dedicated preprocessing pipeline including normalization, contrast enhancement, and channel replication to adapt single-channel thermal images for CNN-based processing. The modified MTCNN is fine-tuned on thermal datasets to accurately detect facial regions and landmarks. Aligned faces are then processed through a thermal-optimized feature embedding network trained with tri-plet loss to produce identity-preserving descriptors. Recognition is performed us-ing a lightweight classifier over the feature space. The system is optimized for real-time performance using GPU acceleration and quantized inference. Experi-mental results on publicly available thermal face datasets demonstrate the effec-tiveness of our approach in terms of detection accuracy, recognition rate, and processing speed, making it suitable for surveillance and biometric applications under low-light or no-light conditions.
Authors - Laila D. Malabanan, Apolinar P. Datu, Annaliza C. Sinfuego, Dawn Nari S. Condez, Jessica Rose P. Enriquez, Lexus P. Mon-tenegro, Ana Celine G. Esquierdo, Chona S. Lajom Abstract - Bridging the Gap: Perceptual Differences Between Physical and Vir-tual Tours in 360 Maynila takes a closer look at how people experience culture and history in today’s digital age. With virtual tours becoming more accessible through platforms like 360 Maynila, this study compares how audiences perceive traditional, in-person tours versus immersive virtual ones. Using surveys, the re-searchers gathered insights from individuals who experienced both formats. Re-sults show that while physical tours create a stronger emotional connection and allow for richer sensory engagement, virtual tours offer convenience, accessibil-ity, and a modern twist that appeals to tech-savvy audiences. Interestingly, many participants found that virtual tours sparked curiosity but lacked the depth and atmosphere of being physically present. The study suggests that instead of re-placing one with the other, a blend of both can offer a more inclusive and dynamic cultural experience. By understanding these perceptual differences, cultural in-stitutions and tourism organizers can create more engaging and adaptable ways for people to connect with heritage, no matter where they are. This research high-lights the growing role of technology in storytelling and encourages thoughtful innovation in how we share and preserve our cultural identity.
Authors - Saptarshi Paul, Pratul Kalita, Abu Ahmed Waliullah Mazumder, Saurav Paul Abstract - With the rise of multilingual technology and the growing demand for inclusive language tools, there remains a significant gap when it comes to resources and research dedicated to Assamese, one of the major languages spoken in North east India. The core objective is to bridge that gap by leveraging recent advances in deep learning—specifically the Transformer architecture—to build a translation model that is both accurate and adaptable. The system is implemented using the OpenNMT-py framework which supports flexible training of encoder- decoder models with attention mechanisms. To train the model, a parallel corpus consisting of approximately 124,000English-Assamese sentence pairs was sourced from the Samanantar dataset available on Kaggle. The data was prepared using a machine translation (MT) preprocessing script, which utilizes Sentence Piece to perform sub word tokenization. This step ensures that rare and compound words are broken down into more frequently occurring subunits, thereby improving the model’s ability to learn patterns in low-resource language settings. The trained model was evaluated using the BLEU score, which is used to compare the overlap between machine-generated outputs and human reference translations. The evaluation results indicated that the Transformer-based approach provides promising performance, particularly in producing fluent and contextually relevant translations, despite the limited size of the dataset.
Authors - Siham BELOUALID, Abderrahim BAJIT, Alae ELFOURCHI, Youness ZAHID, Emile SEMAKO, Hicham ESSAMRI Abstract - The increasing complexity of greenhouse agriculture requires integrated, scalable platforms capable of precise monitoring, real-time decision-making, and sustainable management. This work presents an intelligent greenhouse system that transitions from static IoT networks to a multi-agent architecture combining mobile sensing units, autonomous robots, and deep learning-powered computer vision. Environmental parameters such as temperature, humidity, and soil moisture are continuously collected through embedded sensors, while high-resolution visual data enables detailed plant health assessment. Machine learning models analyze these multimodal datasets to predict crop conditions, detect anomalies, and enable early intervention. A tri-modal vision system ensures complete coverage: static wide-angle cameras for global monitoring, mobile units with CNN-based analysis for close-range inspections, and robot-mounted cameras for real-time tasks. Autonomous robots, equipped with SLAM and path planning algorithms, perform precision operations such as targeted harvesting and disease removal. The fusion of robotics, AI, and sensor networks provides high-resolution monitoring, optimizes resource usage, and enhances crop management. Additionally, onboard edge computing enables fast, localized data processing, reducing latency and improving system autonomy.
Authors - Asma Shahin, Deepa Deshpande Abstract - The prevalence of stress in modern life demands innovative solutions to monitor and mitigate its effects on individual well-being. This study explores stress detection through a robust dataset derived from wearable devices, analysing physiological signals, perceived stress scores, and task performance metrics. Given the widespread impact of stress across diverse populations, this research seeks to unravel the complexities of stress responses, paving the way for personalized interventions and enhancing our understanding of the physiological mechanisms underlying stress. On the Stress Predict dataset, the accuracy by Random Forest was the highest at 83% as compared to Logistic regression - 54% and SVM - 82%.
Authors - Jhon Eric D. Punzalan, Apolinar P. Datu, Jonas A. Jaro, Andro Isao T. Aquino, Jubilee Anne C. Del Rosario, Khen Karlo A. Ocampo, Paulo M. Gabagat, Earl John Z. Alba, Marivic P. Mojica, Rizza May G. Tandog Abstract - This study examines the promotional strategies employed by Philippine festivals to attract both local and international tourists. Festivals in the Philippines are not only vibrant expressions of cultural heritage but also vital drivers of tourism and economic activity. With increasing global competition and changing tourist behavior, effective promotion is essential to maintaining their relevance and appeal. The research gathered responses from a diverse group of participants, analyzing demographics, engagement patterns, and perceptions of various promotional approaches. Findings reveal that festival attendees are predominantly young adults, male, students, and largely international tourists, particularly from Asia and Europe. Respondents strongly agree that festivals across national, regional, and city levels are widely attended and culturally significant. Promotional efforts using a mix of traditional media, experiential marketing, and digital platforms such as YouTube, TikTok, and social media are seen as highly effective, especially among younger, tech-savvy audiences. Promotional content is perceived as credible and culturally authentic, contributing to high satisfaction and repeat attendance. However, key challenges such as budget constraints, inconsistent branding, and limited digital marketing expertise persist. Respondents support strategies focused on enhancing digital engagement, extending festival durations, and maintaining cultural authenticity. The study concludes that a well-integrated, inclusive, and globally oriented marketing approach is essential for sustaining and expanding the appeal of Philippine festivals. It recommends strategic investments in capacity building, digital tools, and culturally grounded storytelling to strengthen the Philippines’ position as a leading cultural tourism destination in Southeast Asia.
Authors - Homayoun Rabiei Pour, Jyri Vilko Abstract - Non-timber forest products (NTFPs) are wild products harvested from the forest, except timber, there’s a significant potential for application in the food supply chains. This systematic literature review evaluates the process potential of various NTFPs based on the feasibility and technological aspects of these un-derutilized natural resources for food processing. By using Web of Science, pub-lications were retrieved with a specific search strategy of keywords mainly con-sisting of food, non-timber forest products, processing, and cost. After screening based on defined inclusion criteria, relevant articles were selected for analysis. The results contained different applications of NTFPs such as wild fruits, shea butter, bamboo shoots, and plant-derived polysaccharides in food manufacturing, preservation, and nutritional enhancement. Different processing methods such as drying, extraction, fermentation, and enzyme treatment were documented with corresponding evaluations of safety, functional properties, and economic viabil-ity. While interest in sustainable and local foods is increasing, there are also large gaps related to scale-up feasibility, market integration, and cost analysis. The re-view concludes with recommendations for future research, particularly empha-sizing innovation in food-grade processing and value-added product develop-ment from NTFPs.
Authors - Irna Hamzah, Ely Salwana, Hameedur Rahman Abstract - Virtual reality (VR) is swiftly evolving into a transformative tool in education, offering immersive environments that facilitate social-emotional learning (SEL) and enhance emotional regulation, particularly among adolescents. This study intends to explore the application of a VR design framework specifically customized for the Malaysian context, with the objective of strengthening social-emotional learning and establishing emotional regulation skills in adolescents. The study collects and analyses data through the VR application named mVR-REAL utilizing a VRSEL framework, which encompasses essential design principles such as user interface (UI), presentation layer (PL), and brain activity (BA) in the execution of VR-based social-emotional learning (SEL) interventions, highlighting the opportunities and constraints within Malaysian educational settings. The data analysis is performed utilizing SPSS. A total of 127 students from four secondary schools were enrolled in this study. Majority of the respondents were female (51.2%, n=65). All respondents answered usability instrument and the emotional questionnaire. Overall, the data suggests that the system has strong usability, with most users rating it as good. The mean score above 86% and the high proportion of good ratings reflect positively on the user experience. However, the presence of some users with scores below 80% highlights opportunities to further enhance usability for all users.
Authors - Ornurai Sangsawang Abstract - Industrial chemical emergencies, such as leaks, fires, and explosions, are major risks that affect life, property, the environment, and infrastructure security, especially in areas with high factory density. This research aims to develop a spatial emergency response station placement model by applying the Maximal Covering Location Problem (MCLP) model in two case studies: (1) the placement of the Industrial Emergency Response Center (I-ERC) using factory location data in Rayong Province, and (2) the placement of the Chemical Emergency Response Station (CERS) using historical chemical accidents. The results of the study compared the locations of 21 existing EMS stations and found that the MCLP model can significantly increase the coverage of the risk areas. In the I-ERC case, the coverage level increased from 87.09% to 99.46%, and in the CERS case, the risk points can be covered 100% with an appropriate number of stations. The results of this study can be applied to support strategic planning for emergency response systems in high-risk industrial areas.
Authors - Takashi Miyata, Noriaki Takemura, Takumi Kato, Kazuhiko Tsuda Abstract - In the field of internal marketing, concern exists that advanced technology may be perceived as a negative target in employee attitudes. This is because new technology will completely change the processes that employees have accumulated and put their employment at risk. Therefore, to help employees understand the value of advanced technology, the technology concept is important. By targeting an organization’s big data analysis infrastructure, we verified a concept that is attractive to potential job-changers. A randomized controlled trial of 500 people in Japan revealed that potential job-changers are attracted to a workplace through the appeal of the presence of high-speed internal processes rather than high technical performance. This effect was more pronounced than concepts that promoted risk management such as personal information leaks, or that promoted management of business domain knowledge. The background to this is that close collaboration with business departments is essential for data scientists to function effectively. The factors that cause data science projects to fail are more prominent in the aspects of internal processes and organizational friction than in technical aspects. Having an internal environment that solves these problems is very attractive to employees. By analyzing employees’ needs and developing a concept, employees will have a positive attitude toward advanced technology.
Authors - R. Kowsalya, S. Ravi, C. Manusha, A. Saranya, T. Kalaichelvi Abstract - A significant obstacle to early skin cancer detection is the diversity of skin types and colors. Compared to convolutional neural networks (CNNs), Vision Transformers (ViTs) are a powerful alternative. By applying self-attention mechanisms to model global dependencies within an image, ViTs can capture long-range contextual information more effectively than traditional CNNs that use local convolutions to capture spatial patterns. A study describes how Vision Transformers perform better on large-scale image datasets than CNNs when trained with enough training data to achieve maximum performance. Additionally, hybrid architectures are investigated, which combine the advantages of CNNs and transformers strategies to improve generalization and training efficiency. It will help researchers learn about the latest deep-learning techniques and comparative analysis. It will also be helpful to know which type of Transformer is most suitable for accurately detecting the early stage of skin cancer classification and detection.
Authors - Rajneeshkaur Sachdeo Bedi, Pankaj Chandre, Pallavi Bhujbal, Bhagyashree Shendkar Abstract - Transforming healthcare with Natural Language Processing (NLP) is revolutionizing how medical data is analyzed, interpreted, and utilized. This paradigm shift is fueled by NLP's ability to process diverse healthcare data sources such as medical research articles, imaging reports, electronic health records, clinical notes, and patient feedback. Key NLP tasks like text summarization, information extraction, named entity recognition, sentiment analysis, and question answering are at the core of enabling advanced applications in healthcare. These include medical research acceleration, administrative task automation, clinical decision support systems (CDSS), and patient care enhancement. Despite its promise, challenges such as limited annotated datasets, biases in models, integration with legacy systems, and ensuring data privacy and security persist. The integration of NLP-driven solutions into healthcare systems has immense potential to enhance efficiency, improve patient outcomes, and optimize decision-making processes. Addressing these challenges through innovation and collaboration will ensure the sustainable growth of NLP in smart healthcare systems.
Authors - Arnold Aguilar, Ronaldo Polancos Abstract - Multilingual IT contact centers serve as vital operational structures for global corporations, facilitating engagement with geographically dispersed clientele across diverse languages, temporal zones, and technical complexities. Excluding their strategic significance, the mechanisms for scheduling and task allocation within these contexts have remained inadequately investigated within the classical project scheduling literature. Conventional frameworks addressing the resource-constrained project scheduling problem (RCPSP) neglect to incorporate dynamic constraints such as agent fatigue, linguistic alignment, shift-based availability, or the demands of strategic escalation. This systematic literature review integrates more than twenty years of advancements in RCPSP, leveraging hybrid metaheuristic methodologies—specifically Genetic Algorithms (GA) and Constraint Programming (CP)—to propose an innovative trajectory tailored to multilingual service operations. A case study is employed to corroborate the proposed model, demonstrating its potential to enhance SLA compliance, agent workload distribution, and language-specific support efficacy. This research provides a dedicated conceptual and algorithmic foundation for multilingual support scheduling—an area that has been predominantly preoccupied from the mainstream RCPSP discourse—thereby establishing a basis for forthcoming empirical validation and implementation in high-demand support environments.
Authors - Luay Jum’a Abstract - This study examined the impact of digitalization on total quality management (TQM) practices and examines how both digitalization and TQM practices influ-ence supply chain performance (SCP) within the manufacturing sector in Jordan, a developing country. Using the resource-based view and dynamic capabilities theory, the study conceptualizes digitalization as a dynamic enabler that rein-forces internal quality capabilities. Data were collected through a self-adminis-tered survey targeting managers in Jordanian manufacturing firms, resulting in 74 valid responses. Established measurement scales were used, and the data were analyzed using multiple linear regression via SPSS. The findings reveal that dig-italization significantly enhances the implementation of TQM practices, particu-larly by improving process visibility, data integration, and quality control. Amongst the six TQM dimensions examined, only process management and em-ployee involvement demonstrated a significant positive impact on SCP. Addi-tionally, digitalization was found to have a direct and positive effect on SCP, reinforcing its strategic role in enhancing responsiveness and efficiency in supply chains. The study contributes to literature by incorporating digital transformation with quality and supply chain in the context of Jordan as a developing economy. It additionally offers actionable suggestions for managers in pursuit of aligning digital initiatives with quality-driven practices to improve supply chain out-comes.
Authors - Shane Maluleke, Tebatso Gorgina Moape, Ernest Mnkandla Abstract - The exponential growth of consumer and service provider reviews on digital platforms has generated substantial big data online, creating both opportunities and challenges for business analytics. Businesses often use these reviews to evaluate customer satisfaction, service quality, and overall brand perception. Due to the vast amount of data generated, traditional analysis methods are often inadequate for efficient processing. Hence, most companies employ sentiment analysis techniques to analyze substantial volumes of data from reviews. Sentiment analysis is a subset of natural language processing that enables the automatic classification of text-based feedback according to the emotional tone expressed. In this paper, sentiment analysis is conducted on the Uber driver app, a ride e-hailing service, within the South African context. This study intentionally focused on driver reviews instead of customer reviews, as most research predominantly focuses on passenger satisfaction, service quality, and pricing strategies, while driver perspectives remain understudied. The methodology employed in the paper involved a systematic data mining process, followed by text pre-processing, thematic code analysis of the collected data, and the application of Naïve Bayes and Random Forest algorithms to classify the Uber driver app reviews. The Random Forest model outperformed the Naïve Bayes classifier, with an accuracy of 0.9023, while Naïve Bayes achieved an accuracy of 0.8333.
Authors - Khalid BOUALI, Abderrahim BAJIT, Hamza BENZZINE, Ibtissam EL AOUNI, Hicham ESSAMRI, Siham BELOUALID, Rachid EL BOUAYADI Abstract - The transition towards intelligent greenhouse agriculture is driven by the need to optimize resource efficiency and manage climate variability. Classical control methods, such as PID and open-loop control systems, have shown limi-tations in precision and in handling the nonlinearities. To address these chal-lenges, advanced automation and predictive control strategies like Model Predic-tive Control (MPC) have gained attention. However, achieving accurate forecasts of meteorological parameters remains critical for maintaining optimal growing conditions and reducing energy consumption. This paper proposes a hybrid deep learning model that integrates Long Short-Term Memory (LSTM) networks with Transformer architecture within an MPC framework to improve forecasting of key meteorological parameters, including temperature, humidity, and solar irra-diance. By combining memory and attention mechanisms, the model captures both short- and long-term dependencies in time series data. Experiments were conducted with varying input window sizes, and performance was evaluated us-ing mean absolute error (MAE), root mean squared error (RMSE), and symmetric mean absolute percentage error (SMAPE). Results show that the proposed hybrid model outperforms standard LSTM models in both accuracy and inference time, highlighting its potential to support intelligent greenhouse climate management and promote sustainable agriculture.
Authors - Kayode Daniel Akilo, Rhulani Maluleka, Abelwe Maluleka Abstract - The introduction of Artificial Intelligence (AI) in revolutionizing e-business environments has considerably automated operational efficiency with ease. The induction of AI has increased consumer engagement and business suc-cess across the e-commerce landscape. Concerning this, this research examines the application, operation, and various impacts and challenges of the adoption of artificial intelligence across e-commerce operations and platforms. Primarily focusing on Shopify as a case study, this allows for an effective and efficient analysis of AI adoption. This research utilizes SWOT analysis and comprehensive academic literature in evaluating AI environments and AI adoption, such as intelligent chatbots, personalization engines, and security systems. Through this analysis, this research extends to how these implementations transform both small and medium-sized enterprises (SMEs). The research identifies the barriers to implementation, strategic approaches in effective AI adoption, and factors that are to be attributed to success. Additionally, this research contributes to the competitive advantages through an established platform, such as Shopify, for a more grounded approach. This paper evaluates the AI adoption in the e-commerce landscape and addresses the economic infrastructure. Allowing effective solu-tions for SMEs in practical, technical, and ethical ways.
Authors - M.Akashi, M.Nagano, Y.Ieiri, O.Yoshie Abstract - Recently, the number of tourists engaging in walking tourism at various destinations has increased, presenting new opportunities for local economic activity. However, the mechanisms underlying consumer behavior in walking tourism remain unclear, and effective methods for designing such tourism have not been established. This study aims to elucidate the mechanism of consumer behavior by integrally analyzing eye-tracking data, conversation data, and electrodermal activity (EDA) data collected during walking tours. Empirical experiments were conducted in Otaru City and Atami City, with data analyzed from multiple perspectives. The analysis revealed that eye-tracking data, conversation data, and EDA data can effectively identify triggers of consumer behavior during walking tourism. Furthermore, the increase in EDA highlights the potential to extract consumer behavior in walking tourism.
Authors - Mathew Philip, Ruksana Banu, Amala Nirmal Doss Savari, Mimy Mathew, Ahmed Aboualam Abstract - The rapid progress of Internet of Things (IoT) technology and digitalisation is transforming the logistics sector into more efficient operational processes and data-informed decision-making. This shift is driven by evolving market demands, sustainability imperatives, and the emergence of innovative business models. This study aims to identify and analyse current research trends in the application of IoT in smart logistics management, and to understand how these technologies address existing research gaps in traditional logistics systems. The study presents a bibliometric analysis and examines the concept of smart logistics. It also reviews and analyses IoT-based smart Logistics Management (SLM) research, demonstrating how IoT influences smart logistics. The study reveals that the most prominent area, based on Scopus research from 2017 to 2025, was IoT, which is regarded as a key revolution. Terms like efficiency, visibility, and responsiveness highlight the operational priorities IoT technologies seek to optimise within logistics and supply chain contexts.
Authors - Khalid BOUALI, Abderrahim BAJIT, Hamza BENZZINE, Siham BELOUALID, Youness ZAHID, Mohamed Nabil SRIFI, Rachid EL BOUAYADI Abstract - With the rapid advancement of the Internet of Things (IoT), smart de-vices have become integral to various sectors, including healthcare, transporta-tion, smart homes, and industrial systems. In agriculture, these technologies have driven a shift toward automation and data-driven decision-making through the adoption of smart sensing systems. However, most existing systems remain con-strained by their reliance on centralized cloud infrastructure, resulting in latency, increased computational costs, and limited real-time capabilities. This work pro-poses an optimized microclimate sensor node architecture that incorporates edge computing abilities to enable real-time processing of sensor data and localized decision-making. These nodes are enhanced with Edge Artificial Intelligence to offer prediction analysis capacities at the edge. In this study, we focused on the prediction of missing sensor data using the intercorrelation between microclimate features, including temperature, humidity, CO₂, and light intensity. The study evaluates three supervised regression models, including Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Artificial Neural Network (ANN), based on R², RMSE, and MAE metrics. Experimental results demonstrate the superior performance of the RF model in learning the patterns between the mi-croclimate parameters, achieving R² scores of 98.88 % in predicting temperature, 95.60 % for humidity, 94.67 % for CO₂, and 97.40 % for light intensity. The results present the effectiveness of the model in predicting the missing parameters using the available ones. By enabling predictive inference at the edge, this ap-proach optimizes the monitoring systems, reduces the dependency on the cloud servers, and contributes to sustainable agriculture, generally offering a scalable solution for resilient, intelligent, and real-time monitoring in precision agricul-ture.
Authors - Balebetse H. Skele, Partson Paradza, Benita G. Zulch, Joseph A. Yacim Abstract - In South Africa, Section 2 of the Sectional Title Schemes Management Act of 2011 (the Act) requires developers to attend the First General Meeting (FGM) and present necessary documentation to the corporate body. However, non- compliance with standards and incomplete submissions by developers often lead to the postponement of the FGM. This results in financial burdens for the body corporate and the signing of long-term contracts without proper oversight. The impact of this non-compliance has not been investigated, highlighting the need for further investigation to improve handover procedures under the Act. Thus, this study aims to inform current policies and contribute to the literature on the handover process of residential sectional title properties. Adopting a case study approach, the research integrates mixed methods to collect data from seven sectional title schemes in the Western Cape and Gauteng Provinces. Findings reveal that developers' non-attendance at FGMs causes communication breakdowns with Body Corporate, rendering FGMs ineffective. This paper provides valuable insights for policy on sectional title purchases in South Africa. It also contributes to the litera-ture by examining the challenges in the handover processes of sectional title properties in South Africa.
Authors - Anthony Garces L, Pablo Flores-Siguenza, Lorena Siguenza-Guzman, Piera Maresca, Rodrigo Guaman Abstract - In a global landscape increasingly driven by competitiveness and sus-tainability, manufacturing companies face significant challenges in adopting sustainable practices—often due to financial limitations, limited technical training, and inadequate policy support. This study presents a systematic literature review focused on methodologies, tools, and performance indicators used to optimize industrial plant layout, with a particular emphasis on enhancing operational efficiency and environmental sustainability. Using Fink’s methodology, 46 peer-reviewed articles published between 2014 and 2024 were rigorously analyzed through a three-tier bibliometric approach: meta-analysis, keyword clustering, and descriptive sample analysis. The findings highlight the effectiveness of hybrid strategies that integrate systematic layout planning (SLP), advanced simulation platforms (FlexSim, Arena, ProModel), and multi-criteria decision-making techniques (AHP, NSGA-III). These approaches demonstrate clear improvements in workflow efficiency, bottleneck reduction, and environmental impact mitigation. Key performance indicators identified include material flow, travel distance, cycle time, inventory levels, and carbon footprint. The study under-scores the importance of integrated methodologies that align operational and sus-tainability objectives, offering valuable insights for decision-making in industrial engineering and facility planning goals.
Authors - Pornpimol Chaiwuttisak Abstract - This study developed predictive models for the closing prices of five leading technology stocks: GOOGL, MSFT, AAPL, NVDA, and META by employing five advanced machine learning and deep learning techniques: Light Gradient Boosting Machine (LightGBM), Extreme Gradient Boosting (XGBoost), Recurrent Neural Network (RNN), Gated Recurrent Unit (GRU), and Long Short-Term Memory (LSTM). The modeling framework integrated sentiment scores derived from financial news articles specific to each stock us-ing the VADER Sentiment Analysis tool, in conjunction with a range of macro-economic indicators. Model performance was evaluated separately for each stock using Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE) as primary metrics. To determine whether statistically significant dif-ferences existed among the predictive performance of the models across all stocks, the Friedman test was employed, followed by the Wilcoxon signed-rank test for post-hoc pairwise comparisons. The empirical results indicated that XGBoost achieved superior predictive accuracy for MSFT and AAPL, GRU outperformed other models for NVDA and META, while RNN yielded the most accurate forecasts for GOOGL.
