Authors - E. C. Nwokorie, D. O. Njoku, M. E. Nwanga, S. A. Okolie, C. D. Anyiam, J. E. Jibiri, C. G. Onukwugha, I. H. Ajunwa, C. O. Amadi, F. O. Nwokoma, A. I. Otuonye, U. C. Onyemauche Abstract - This research investigates the application of TabNet, a deep learning model optimized for tabular data, for binary classification of Software Defined Networking (SDN) traffic. Using a combination of normal and Open vSwitch (OVS) traffic datasets, the model was trained to differentiate between benign and potentially anomalous traffic patterns. The preprocessing pipeline included feature selection, normalization, and encoding, followed by model training using PyTorch TabNet. The classifier achieved a high validation accuracy of 99.51%, with strong precision and recall, highlighting its capability for real-time anomaly detection in SDN environments. Visualizations such as ROC curves, precision-recall plots, confusion matrices, and PCA projections further validated the model’s effectiveness and interpretability.
Authors - Tiurida Lily Anita, Arif Zulkarnain, Abdul Rauf Ridzuan Abstract - The integration of blockchain technology into digital tourism platforms has sparked interest in how such innovations influence user trust and behavioral intentions. This study investigates the impact of digital value, smart contracts, and security-transparency on users’ intention to use blockchain-based services, with perceived trust as a mediating variable. A quantitative survey involving 200 Traveloka users was conducted using structured questionnaires. The analysis employed Partial Least Squares Structural Equation Modeling (PLS-SEM) to validate the measurement and structural models. Results reveal that digital value and perceived trust significantly influence users’ intention to use Traveloka's blockchain-enabled services. Moreover, digital value and smart contracts positively affect perceived trust. However, the direct impact of security-transparency on perceived trust was found to be statistically insignificant. The mediation effect of perceived trust is confirmed only in the relationship between digital value and intention to use, while its mediating roles between smart contract and intention, and between security-transparency and intention, are not supported. These findings suggest that enhancing digital value and reinforcing trustworthy smart contract features are key to fostering trust and increasing user adoption. This study offers practical insights for digital tourism platforms aiming to deploy blockchain technology and contributes to the theoretical understanding of trust-based technology acceptance in the tourism domain.
Authors - Zainab Shalehah, Santy Abstract - Small and Medium Enterprises (SMEs) face increasing pressure to remain competitive in rapidly evolving markets. Business Intelligence (BI) has emerged as a strategic tool that supports data-driven decision-making and improves organizational performance. This study aims to explore the impacts, benefits, and challenges of BI implementation in SMEs through a systematic literature review (SLR) of relevant academic sources. Literature was collected from databases such as Scopus and Google Scholar and analyzed using thematic categorization based on BI usage and its performance outcomes in SMEs. The findings highlight that BI positively contributes to decision-making quality, operational efficiency, and financial performance. However, SMEs often face challenges such as high implementation costs, lack of skilled personnel, and integration difficulties. The success of BI adoption is highly influenced by contextual factors, including data quality, financial capacity, and strategic planning. This review concludes that while BI offers significant advantages for SMEs, a careful, well-planned approach is necessary to overcome adoption barriers. Further research is recommended to explore industry-specific BI solutions that address the unique needs of SMEs.
Authors - Sadhana Mishra, Poonam Dang Abstract - Automatic speech recognition (ASR) is increasingly being applied in various fields such as healthcare, Education and accessibility. However, ASR of mathematical expressions presents a unique challenge due to the symbolic, structured and hierarchical nature of math language. Accurate transcription of such expressions is essential for digital learning, documentation and computational processing. This paper presents a comparative study of four open-source ASR tools— Whisper, DeepSpeech, Vosk and PocketSphinx — focusing on their ability to recognize spoken mathematical expressions accurately. The study uses a dataset of several mathematical categories, such as algebra, trigonometry, calculus, and vectors, recorded by six speakers, to assess each tool's performance based on Word error rate (WER) and processing time. According to the results, Vosk processes information the quickest, whereas Whisper performs better in terms of accuracy. The findings provide insights into tool selection for educational or assistive technology applications involving math speech transcriptions.
Authors - Serhii Kozlov, Nazar Matsko, Yaroslava Chopa, Volodymyr Dubinin, Dmytro Nishchemenko Abstract - This article proposes a solution to the problem of free decentralized protocol usage for a group of users who want to participate in the protocol without paying transaction fees and/or do not have a wallet with a key pair (Externally Owned Account). The proposed solution is a public donation pool that enables users to interact with any decentralized protocol during a specific event without owning a wallet and/or incurring blockchain gas fees.
Authors - Andrea Dannielle Mayuga, KC A. Berdin, Mary Faith F. Lagmay, Love Joyce A. Mortel, Lovely M. Penafiel, Ashley D. Sacayanan, Manuel J. Logatoc, Steven C. Jocson Abstract - This study evaluates the level of satisfaction with digital payment systems among residents in the Philippines. In an era where rapid technological advancement reshapes business transactions, digital payment platforms have emerged as critical drivers of efficiency and convenience. Employing data from survey questionnaires and pertinent digital‐literacy studies, the research applies Davis’s Technological Acceptance Model (TAM), with perceived usefulness (PU) and perceived ease of use (PEOU) as central predictors of users’ behavioral intentions toward mobile payments. The analysis explores three dimensions: users’ overall satisfaction, the most frequently used digital payment platforms, and variations across socio‐demo-graphic profiles. Findings indicate that respondents maintain a uniformly positive attitude toward digital payment systems, deeming them useful for everyday trans-actions and expressing strong willingness to recommend these platforms over traditional methods. Ease of use emerged as a key factor driving continued adoption intentions. Among socio‐demographic variables, gender and monthly in-come show significant correlations with satisfaction levels; in contrast, age, civil status, and highest educational attainment exhibit no notable influence. These results suggest that while digital payment systems enjoy broad acceptance across diverse user groups, targeted strategies that address gender, and income‐based preferences may further enhance user satisfaction. Policymakers and service providers can leverage these insights to refine platform design, optimize user education initiatives, and foster more inclusive adoption of digital payment technologies.
Authors - Sarvani Kocherlakota, Poojitha Panchakarla, Ajay Amjuri, Sannakalla Sai Sree Charan Abstract - Economic, Social and Governance is playing a predominant role in the capital markets to increase the awareness Global investments and to acquire knowledge on the investment avenues available across the world. To investigate its current research landscape and emerging trends, we conduct a bibliometric analysis by using R software 4.5.0, and VOSviewer to identify the research trend, emerging topics, and collaborations among countries, authors, documents and the contributing academic journals during the study period. Finance research letters is having the highest publications and Review of Accounting Studies is having the most cited document. Li Y is the most contributing author and Christensen HB, Hail L and Leuz C are the most cited author. China is the most cited country. Further research may happen in this area from the perspective of various countries like BRICS, various quantative techniques and scope of the study may be limited to individual country and so on.
Authors - Rajkumar Patil, Vivek S. Deshpande, Nilesh P. Sable Abstract - Pests pose a significant threat to cotton yields, leading to economic losses for farmers. This paper conducted a comprehensive literature review, examining the various types of pests affecting cotton crops both globally and specifically in India. We analyzed the actual yield losses ascribed to these pests as well. Furthermore, we reviewed a variety of literature on pesticide recommendations and cotton disease detection. In this paper we have chosen four Deep Learning (DL) models—VGG19, ResNet50, ResNet152V2, and Incep-tionV3 selection of this model was based on literature review. These models were trained and tested on a dataset of 2,293 images comprising affected and non-affected cotton plants and leaves. The output of our evaluation demonstrates how useful these models are in detecting diseases in cotton plants. Ultimately, the AI-based automated recommendation system allows farmers to use this information to make informed decisions about using pesticides resulting in better crop health and higher yield of cotton.
Authors - Ronil Manohar, Melita Simoes, Arogyaswamy Karadi Abstract - Today’s competitive jobs demand a sturdy balance between personal and professional life. Women are an integral part of the current workforce including academics wherein achieving a sustainable work-life integration is a critical challenge in the ever evolving dynamic workplaces despite institutional reforms, growing attention to gender equity and women empowerment. This study highlights the role of work-life balance, mental well-being, and organizational support structures among 103 women professionals that include teaching and non teaching fraternity in educational institutions across Hubli-Dharwad. According to reports, a substantial proportion of respondents, mostly Millennials and Generation Z, struggle to maintain balance, resulting in medical illnesses, stress, burnout, and disturbances in family life. These issues frequently result in lower productivity, job satisfaction and can hamper career progression and leadership aspirations, emphasizing the critical need for effective measures to help women achieve a sustainable work-life balance. This study employs a quantitative approach that made use of a structured data collection through a well drafted questionnaire which aims to explore the perception of women on work-life balance, mental health, and personal empowerment along with understanding the role of equitable policies, anti-harassment frameworks, as well as the implementation of flexible and inclusive work environments that promote a gender-balanced leadership wherein the needs and voice of women employees are addressed.
Authors - Usman Ali, Tariq Hussain, Muhammad Mujeeb Akbar, Shahzad Ali, Sajid Abstract - In Pakistan, crime is always a significant economic and social issue affecting governance and public safety. Religious issues, poverty, and political instability have a very high contribution to increasing crime in the country. Despite highly effective efforts of authorities and prevention techniques, crimes are often inconsistent and lack effectiveness in determining crimes across the country. This study aims to analyze national crimes in Pakistan using machine learning and structured datasets to support more effective decision-making and understanding of crime rates across the country. Through the proposed framework, linear regression, the Decision Tree, and the Random Forest are applied to historical data obtained from the Kaggle repository. With different evaluation matrices and cost functions, the proposed model is interpreted and evaluated. The Evaluation metric includes R², and the cost functions include MSE, MAE, and RMSE. Linear Regression works effectively in comparison to others, providing the highest R², i.e., 99.9%. By using this framework, crimes from 2030 to 2050 are predicted with a difference of 5 years. These algorithms help to identify different types of crimes across the country based on different factors. Unlike traditional methods and black-box models, this research underscores the comprehensibility, making insights understandable for both law and policy makers. The study explains how interpretable frameworks can help authorities to find high-risk area predictions. In the future, the aim is to use deep learning techniques with explainable AI (XAI) for enhancement in this study, which can support the development of more public safety systems across the country.
