Authors - D. S. Vangao, Pallavi Khatri Abstract - Image forgeries have become much more common due to the widespread use of sophisticated digital image manipulation tools, which makes it difficult to independently confirm authenticity in domains like social media, digital forensics, and journalism. This survey study paper offers a thorough analysis of the most recent methods for identifying image modifications including copy-move and splicing forgeries, with an emphasis on combining Convolutional Neural Networks (CNNs) with Error Level Analysis (ELA). We evaluate important approaches from recent literature based on their architectures, datasets, and performance metrics. We do so via methodically analyzing both contemporary deep learning techniques and traditional methods that rely on handcrafted features. Our investigation shows that hybrid ELA-CNN techniques routinely beat alternative techniques, attaining accuracy rates exceeding 90% on common datasets such as CASIA. More reliable, real-time solutions are required, nevertheless, as problems like identifying subtle tampering and increasing computational effectiveness continue to arise. We wrap up by discussing the present state of the field's limits and potential avenues for future research in digital image forensics.
Authors - Chethana R.M., S.P. Manikandan Abstract - Organisations around the world face never-before-seen difficulties as a result of the quickly changing cybersecurity landscape, which calls for advanced analytical techniques to recognise and anticipate threat trends. In order to analyse current cyberthreats and their organisational impact, this study uses sophisticated statistical techniques such as ANOVA, regression analysis, machine learning classification, and clustering algorithms. We examine threat distribution patterns, financial impact correlations, and predictive modeling capabilities for ten key threat categories malware, phishing, social engineering, ransomware, insider threats, supply chain attacks, DoS/DDoS attacks, zero-day exploits, credential theft, and AI-powered attacks by thoroughly analysing 360 cyber security incidents that occurred across several Indian cities between 2019 and 2024. The most significant predictor of financial impact, according to our statistical analysis, is incident type (F=4.58, p
Authors - GGS Pradeep, Thrilok. Kolla, Rajesh Sharma R, Akey Sungheetha, U Ananthanagu, Pellakuri Vidyullatha Abstract - This paper outlines a holistic framework for improving query comprehension in information retrieval (IR) systems through deep contextual embeddings. Using Sentence-BERT, we transform the queries and documents into dense semantic representations and then calculate cosine similarity for the relevance measure. We especially emphasize interpretability by adding various statistical and visualization techniques, like heatmaps, KDE plots, UMAP projection, dendrograms, and box plots, to identify and analyze latent semantic patterns and keep close tabs on the inner workings of how different documents relate to such varied query formulations. We also follow an avenue of the interquartile dispersion and distributional behavior of similarity scores to understand the embedding consistency and discriminative power. This methodology, therefore, encompasses both retrieval accuracy and explainability as it provides visible insights into improving query reformulation, semantic search, and content recommendation. Experimental visualizations have further demonstrated their effectiveness towards deep semantic alignment, especially during the processing of complex multi-topic corpora. The abstract is technically solid and easily comprehensible because it is rationally structured and clearly states the research’s methodology, instruments, and objectives.
Authors - GGS Pradeep, Thrilok. Kolla, U Ananthanagu, Akey Sungheetha, Rajesh Sharma R Abstract - Predicting non-stationary time series is still a tough nut to crack: the statistical properties may vary, and so will the temporal dynamics. In this context, a robust and interpretable approach involving the integration of a Takagi–Sugeno neuro-fuzzy inference system and evolutionary multi-objective optimization is proposed. The NSGA-II optimization procedure minimizes prediction accuracy alongside model complexity, evolving the fuzzy rule base and membership parameters and the linear consequents. Contrary to the conventional opaque models, a neuro-fuzzy architecture affords some degree of transparency, letting one see how the functional temporal patterns have been learned. Results of the experiments conducted demonstrate the ability of the system to adapt to structural changes in the data, with a corresponding better capability of reducing residual errors and increasing model compactness using a synthetic non-stationary dataset. Further, residual oscillations and fuzzy rule surfaces, alongside the convergence behavior and the Pareto optimality, present powerful evidence in support of the proposed model’s effectiveness and interpretability. The proposed framework represents a potent alternative for real-time adaptive forecasting in dynamic environments where precision and explainability are both crucial. Simulated non-stationary time series will be good enough to justify the approach of lag-embedding. Thoughtful integration of interpretable fuzzy logic and adaptive learning via evolutionary optimization would strengthen the contribution.
Authors - Ritu Raut, Sudhir Agarmore Abstract - The kick to stride the new era in wireless communication begins once 5G technologies holding the promises of speeds previously unheard of and extremely low latency with the capacity to connect a large number of devices at once [4]. This article reviews the potential of 5G in transforming such industries as healthcare, driverless cars, smart cities, and the Internet of Things. It discusses enabling technologies such as millimeter waves, massive MIMO (Multiple Input Multiple Output), and network slicing [1], among others, and also its infrastructure, security, and the possibility of availability of the frequency spectrum. For this purpose, this research aimed to provide an inclusive overview of how this new generation of wireless technology may impinge upon the future of worldwide communication and connectivity by assessing both the benefits and challenges that emanate from 5G.
Authors - D. S. Vangao, Pallavi Khatri, Diya Khatri Abstract - In the digital age, the proliferation of image manipulation has raised significant concerns regarding the authenticity and integrity of visual content. This study, explores the critical role of image forensic tools in detecting digital forgeries and ensuring the credibility of photographic evidence. A comprehensive evaluation of a range of widely used image forensic tools—including but not limited to FotoForensics, JPEG snoop, Izitru, Forensically, and Amped Authenticate—assessing their performance in identifying various types of tampering, such as splicing, cloning, resampling, and compression artifacts is done in this work. Each tool is evaluated on the basis of criteria such as detection accuracy, supported forgery type, user interface, automation capabilities, and analysis depth. The comparative analysis reveals strengths and limitations unique to each tool, offering insights into their suitability for different investigative scenarios. Our findings highlight that no single tool excels universally; rather, a combination of tools often yields more reliable results. This study underscores the necessity for cybersecurity professionals, digital investigators, and media analysts to adopt a multitool strategy for robust image authentication.
Authors - GGS Pradeep, Thrilok. Kolla, Rajesh Sharma R, Akey Sungheetha, N Vijayalakshmi, Pellakuri Vidyullatha Abstract - The early identification of neurodegenerative diseases, like Alzheimer’s and Parkinson’s disease, is crucial for their management, although difficult due to subtle, heterogeneous, and evolutionarily conditioned clinical patterns. In this paper, we present a fuzzy-neural hybrid that incorporates the beneficial properties of fuzzy inference systems and temporal deep learning toward improved early diagnosis. Our model analyzes longitudinal multimodal medical data (neuroimaging and clinical scores), combining fuzzy rule-based feature encoding with Long Short- Term Memory (LSTM) networks for temporal pattern extraction. Interpretability is provided by assigning Gaussian membership functions, while the LSTM component encodes the dynamics of disease progression. The proposed system is validated on synthetic and benchmark datasets, showing robust classification performance and excellent temporal tracking of patient trajectories. Interpretations of internal representations are provided through visualizations such as confusion matrices, t-SNE embeddings, and 3D PCA trajectories. The results indicate that the hybrid approach provides both powerful predictions and transparent operation, making it an excellent option for clinical decision support in neurodegenerative diagnostics. The authors propose a hybrid diagnostic system that uses Gaussian fuzzy membership functions for interpretable feature encoding and LSTM networks for temporal sequence modeling of multimodal medical data. The authors validated their method with synthetic data as well as benchmark datasets, achieving perfect binary classification in their experimental results.
Authors - Agus Timan, Maisyaroh, Maulana Amirul Adha, Indra Lesmana, Anabelie Villa Valdez, Arum Sri Banowati Abstract - The urgency of climate change, environmental degradation, and the need for sustainable development has placed education at the forefront of global transformation. As schools evolve into eco-conscious institutions, there is growing interest in integrating digital technologies to enhance sustainability-driven governance. This has led to the emergence of Green Digital School Management (GDSM), a model that synergizes environmental responsibility with technology-based school leadership. This study aims to systematically explore the core com-ponents, implementation challenges, and effective strategies of GDSM by con-ducting a Systematic Literature Review (SLR) based on PRISMA guidelines. An initial pool of 892 articles was screened, 87 high-quality studies were selected for thematic analysis. The findings indicate that GDSM encompasses digital environmental policies, IoT-based monitoring, and participatory platforms that engage school communities in green practices. Despite significant barriers, including infrastructure gaps, limited digital-environmental literacy, and policy frag-mentation, several innovative strategies have emerged, such as digital teacher training, cross-sector partnerships, and gamified environmental education tools. This review contributes to the conceptual development of GDSM and provides actionable recommendations for policymakers, educators, and technology providers seeking to build smart, green, and sustainable school ecosystems.
Authors - Tsunenori Inakura, Shotaro Imai, Kunihiko Takamatsu, Sayaka Matsumoto, Masao Mori Abstract - Institutional Research (IR) in universities needs data from many different systems, but it is often hard to know what data is stored and where. To solve this, it is important to design both databases and business processes together. In this study, categorical databases, ontology logs (ologs), and event driven process chains (EPCs) are used to connect institutional documents with data and process design. Ologs describe concepts and their functional relations in a formal but also readable way, while EPCs show how events and functions go step by step in the real processes. Generative AI was used to support both tasks. The AI helps to read documents, to extract concepts and functions, and to check consistency. By comparing ologs and EPCs, both sides can be improved and give a unified view of data and processes. This makes it possible to design information systems for IR with more consistency and less effort.
Authors - Vijay Siva, Vijayakumar Ponnusamy Abstract - According to the United Nations, global population will rise from 7 billion currently to 9 billion in 2050. The world will need far more food, and agriculture will face remarkable pressure to meet demand. Emerging application of deep learning in agriculture includes ripeness detection of tomato which harvest tomato in appropriate time and prevents rotten of tomato. This saves the framer from loss. Tomato was classified as ripe, half-ripe, and unripe, based on maturity stage of fruit. Various deep learning methodologies were analyzed for maturity detection of tomato. Multimodal approach for maturity detection is suggested for enhanced accuracy in ripeness detection.
