Authors - Kunam Subba Reddy, Mangavarapu Jahnavi, Kotte Hima Teja, Shaik Kathamma Basheerun, Nama Adarsh Abstract - Proper estimation of battery state of charge (SOC), state of health (SOH) and state of power (SOP) are vital to safe and efficient operation of photovoltaic (PV)-battery energy storage systems, particularly at highly dynamic profiles in which both charging and discharging is taking place. In this paper, a clear comparative analysis of classical, model-based, and machine-learning-based estimation techniques is performed in terms of a similar 24-h ultra-challenging PV + load current profile, simulating realistic residential microgrids operation. The test profile involves strong directions of current swings, partial charging, and long constant-power discharge, and temperature change. The estimators are implemented and benchmarked such as open-circuit-voltage (OCV)-based SOC estimation, linear Kalman filter (KF), extended Kalman filter (EKF), unscented Kalman filter (UKF), basic machine learning (ridge regression) and support vector machine (SVM). Each of the methods is compared to a high-fidelity model of an electro-thermal battery with capacity degradation and resistance increase with age and temperature. The accuracy of SOC tracking, SOH estimation error, and SOP tracking capability are discussed. It is found that the OCV-based method fails when the loading is dynamic which makes the SOC about constant and SOP highly conservative. KF and EKF are much better SOC trackers but they have greater deviation at high SOC and near bottom-of-discharge. ML and SVM estimators based on Ridge-regression show high SOC accuracy in the entire profile and UKF shows the best overall trade off between SOC accuracy, SOH tracking as well as SOP estimation strength when resistance varies with temperature and with age. The paper discusses the relevance of the collaborative consideration of SOC, SOH, and SOP and shows the advanced filters and ML models can significantly increase the performance of PV-battery applications that require tough operating conditions.
Authors - Asmit Patil, Smita Shedbale, Sneha Kumbhar, Ashwini Athawale, Smita Arude, Rohan S. Sapkal, Priya Sharma, Dhanaraj Jadhav Abstract - The rapid growth of Internet of Things (IoT) deployments in 5G Enhanced Ma-chine-Type Communication (eMTC) networks has significantly increased the network at-tack surface. A major challenge for Network Anomaly Detection Systems (NADS) in this environment is severe class imbalance, where dominant benign traffic obscures rare but high-impact attacks, leading to poor minority-class detection. This paper presents Conf-Gate XGBoost-RF, a two-stage hybrid anomaly detection architecture designed to address this limitation without compromising real-time performance. The framework employs a high-speed XGBoost classifier for initial screening and a confidence-gated mechanism that selectively routes low-confidence predictions to a specialist Random Forest trained on synthetically balanced data. Evaluation on the large-scale CICIoT2023 dataset shows that the proposed model achieves 99.32% accuracy and a Macro F1-score of 0.80, sub-stantially outperforming single-stage baselines. Notably, recall for critical low-volume at-tacks, such as Command Injection, improves by over 34%. With an average inference latency of 0.87 ms, the proposed approach remains compatible with the stringent low-latency requirements of 5G eMTC control signaling, demonstrating a practical balance between computational efficiency and rare-attack sensitivity.
Authors - Nguyen Thanh Minh Tam, Mai Nhu Yen, Nguyen Quang Huy, Nguyen Thi Nhung, Nguyen Thi Huyen Chau, Nguyen Hoang Phuong, Dong Van He, Bui Xuan Cuong, Vladik Kreinovich Abstract - The rapid emergence of smart apps in smart environments, industrial automation and cyber-physical systems has demonstrated the intrinsic limitations of conventional design of information and communication technologies. The existing ICT systems are very rigid, centrally controlled and dependent on fixed operation logic and this restricts their dynamism to changing environments and complex system dynamics. Intelligent systems are already urgently in need of architectural paradigms that offer self-education, decentralized intelligence, and autonomous scale-based decision making. The following paper proposes a next-generation Edge-Cloud-AI integrated ICT architecture, which is supposed to service self-learnings and autonomous intelligent systems. The proposed architecture gives a layered intelligence design that utilizes edge level real-time learning, cloud level global optimization, and an autonomy orchestration layer balancing the adaptive behavior in the distributed elements. The architecture enables systems to create operational policies in an autonomous way through the provision of continuous learning feedback and autonomous controls directly within the ICT infrastructure although still be scaled and be reliable. Significant contributions of this work are the definition of a single Edge-Cloud intelligence system, the incorporation of self-learner’s mechanisms along structural layers, and an autonomy-based orchestration model that may be applied to diverse fields of intelligent systems. The proponent architecture is not platform specific and can be applied in a wide range of future intelligent applications that may require resilience, versatility and autonomy.
Authors - Nethika Alagarathnam, Dhanushka Jayasinghe, WU Wickramaarachchi Abstract - Social media platforms, especially Twitter, have become trending sources for public health monitoring, as individuals often share personal experiences related to symptoms, diagnoses, and health concerns. However, detecting personal health mentions (PHMs) in such noisy, short text environments remains challenging. This study investigates about evaluating and comparing three neural architectures including Long Short-Term Memory with word embeddings, a fine tuned Bidirectional Encoder Representations from Transformer model (BERT) and a compact TinyBERT model distilled from BERT. Using a labeled corpus of health related tweets, all models were trained under identical preprocessing, optimization, and evaluation conditions with accuracy, precision, recall, and F1- score assessed on a test set. The results reveal clear performance differences across three architectural paradigms. LSTM baseline demonstrated strong learning on the training set but found significant overfitting and failed to perform on unseen data. But in contrast, the transformer models BERT and TinyBERT delivered a decent balanced performance reflecting the good ability to capture contextual semantics noise in tweets. While BERT achieved the highest overall performance. Notably, TinyBERT provided a competitive and alternate suite for deployment in constrained environment. These findings highlight the effectiveness of transformer architectures for Personal Health Mention detection and practical insights for building efficient and accurate public health monitoring system using social media data.
Authors - Michael David, Chekwas Ifeanyi Chikezie, Abra-ham Usman Usman, Sulieman Zubair, Henry Ohiani Ohize, Joseph Ojeniyi Abstract - With the rapid growth of digital communication and multimedia applications, secure transmission and storage of digital images have become critical challenges. Conventional text-based encryption algorithms are often inadequate for image data due to its high redundancy, strong pixel correlation, and large data volume. These characteristics necessitate specialized encryption mechanisms that can provide strong security while maintaining computational efficiency. This paper proposes a robust image encryption framework designed to ensure confidentiality, resistance to cryptographic attacks, and suitability for real-time applications. The proposed approach integrates advanced permutation–diffusion operations with chaos-based key generation to effectively disrupt statistical characteristics inherent in digital images. Chaotic maps with high sensitivity to initial conditions are employed to generate dynamic encryption keys, enhancing key space complexity and resistance against bruteforce and differential attacks. Pixel-level scrambling is combined with nonlinear diffusion operations to eliminate spatial correlations and achieve uniform cipher text distribution. The encryption process is further optimized to support grayscale and color images while preserving computational feasibility. Extensive experimental evaluation is conducted using standard benchmark images to assess security and performance. Statistical analyses, including histogram uniformity, correlation coefficients, information entropy, NPCR, and UACI metrics, demonstrate strong resistance against statistical and differential attacks. Key sensitivity and key space analysis confirm robustness against bruteforce attempts. Performance results indicate that the proposed scheme achieves a favorable balance between security strength and execution efficiency, making it suitable for real-time image protection. The experimental findings validate that the proposed image encryption framework provides enhanced security, scalability, and practicality, offering an effective solution for secure image communication in modern digital environments.
Authors - Vinod B. Maniyat, Arun Kumar B. R, Shreyas A Abstract - Stealthy rogue components pose as legitimate nodes and progressively deteriorate services, take over flows, or taint network topology, posing serious scalability and security threats to modern SDN networks. High false positive rates, poor interpretability, and static threat assumptions make it difficult for current rule-based and signature-driven detection systems to detect such contextual threats. Based on the Dynamic Containment Score (DCS), a mathematically modelled, context-sensitive metric that measures each network node’s disruptive potential, this work offers a comprehensive behavioural defence paradigm. The framework integrates graph theoretic features, protocol specific entropy, and temporal volatility to compute real time DCS rankings, refined through SHAP based explainability and confidence bounded feature attribution for adaptive detection under concept drift. A multi strategy containment engine, including deception based mitigation, redirects attackers toward synthetic vulnerabilities. Validation on hybrid real world and adversarial traffic demonstrates superior early detection, explainable risk attribution, and efficient mitigation with minimal service disruption.
Authors - Saurabh Nimje, Anup Bhitre, Sudhir Agarmore, Utkarsha Pacharaney Abstract - Insider threat is a great danger to business security because of trust rights granted insiders, it is not easy to notice their malicious or careless work through the available security programs. This paper is going to examine how Natural Language Processing (NLP) can be used to detect insider threats proactively by analyzing the communication of employees such as emails, chat messages, and internal reports. Applying the CERT Insider Threat Dataset and simulated logs, a multi-level system was created, which includes text preprocessing, feature extraction based on sentiments and semantics, and classification of machine learning models- Random Forest Mean Square Error, SVM, and LSTM. Out of them, LSTM model performed best (92.6% accuracy and overall performance) since it was able to capture contextual and sequential patterns of communication. The most notable indicators of behaviors were sentiments of negativity, passively aggressive language, and frequency of communication efficiency, which indicated a high relationship with insider threat. SHAP (Shapley Additive Explanations) was also used in the given research to allow enhancing insights into model decisions. The results prove the viability of NLP-based solutions as scalable, context-sensitive, and explainable systems to detect insider threats extending the understanding of organizations to perceive behavioral anomalies and reduce the risks to a minimum.
Authors - Maria Jihan Sangil, John Raymond Barajas, Ramnick Lim Abstract - Government Identity documents have become groundwork for citizen verification, financial inclusion and public service. However unauthorized dis-closure, fraudulent access and frequent misuse of individual's personal information expose gaps in routine verification and wrongful disbursement of welfare benefits which asks the immediate need for a more secure privacy holding approach. Existing infrastructure like DigiLocker takes care of the secure transmission but a factor of privacy exposure is still compromised. The pro-posed model introduces TrustChain based on blockchain framework for decentralized identify verification and secure access. The inducement shifts focus from submission of identity information to authentication by the means of DID (Decentralized Identifiers) ensuring that some personal information will be hid-den to the document requestor. By integrating self sovereign identity principles, distributed storage and cryptographic operations the model enables users to au-thenticate without revealing personal parameters minimizing the risks of identity compromise. Pilot findings are particular not to mention that identity expo-sure is mitigated by such a representation and offers scalability towards integration into the current infrastructures such as Aadhaar connected services and Digital locker. A safe identity space where individuals retain ownership to per-sonal information as organizations and governments achieve acceptable validation.
Authors - K. Subba Reddy, Pasulammagari Jahnavi, Devasam Hema Keerthana, Katreddy Jaswanth Reddy, Dudhekula Abdul Gaffar Abstract - The investigation of events that have taken place is the foundation of the current law enforcement that uses surveillance videos extensively to identify suspects and the motives of criminals. Wherein, it becomes slow, tiresome, and liable to error when video data is being monitored manually due to the enormously large volumes of data being monitored. To cope with this, it is a need to witness a transition toward the use of automated technologies that are led by AI and deep learning. These systems are able to detect faces, masks, gaits, and ab-normal behavior systematically in adverse environments. The survey will re-view the information about each of the methods that involve face recognition using videos, gait analysis and anomaly detection systems. In addition, efforts are put in direction to present a standardized AI-based surveillance framework of legal multimodal multitask biometric and behaviour identification. The system proposed will focus on a radical reduction of false alarms and offer adequate and prompt intelligence to the law enforcement agencies to speed up investigations.
Authors - Keerin Nopanitaya, Luo Xiaoyu, Zhu Chunping, Pratya Nuankaew Abstract - This study examines Generative AI use and ethical guidelines in graduate education at Payap University, Thailand. As large language models increasingly support learning, research, and academic writing, they boost efficiency but raise concerns about accuracy, transparency, and integrity. Using mixed methods, the study gathered questionnaire data and conducted interviews and focus groups with master’s and doctoral students. Results show broad AI use for literature reviews, writing, idea generation, and research, with more advanced use expected to grow. While students report moderate to high skills, many lack strong critical evaluation of AI outputs and practical understanding of ethics. Consistent with international research, key risks stem from limited AI literacy, unclear disclosure, and lack of oversight rather than the technology itself. The study recommends developing an AI literacy framework, clear disclosure standards, and process evaluation for ethical, responsible AI integration while protecting academic quality and integrity.
Authors - K.Surya Teja, Immanuel Anupalli, P.Sudheer Abstract - Maximum power point tracking (MPPT) is a vital module of photovoltaic (PV) systems. Traditional maximum power MPPT techniques struggle in a complex and ever-changing scenarios, and the solar system's output characteristic curve shows multi-peak phenomena owing to dissimilarities in temperature and light concentration. This paper proposes an adaptive hybrid RIME optimization technique which enhances the exploratory capabilities of the method during the initialization phase by integrating tent mapping. The goal is to improve feature selection tasks and MPPT for PV systems under partial shading condition. It uses piecewise mapping to optimize the algorithm's parameters and attack a fair steadiness amongst global exploration and local exploitation. The search method is dynamically adjusted with an adaptive inertia weight introduced, which further increases convergence speed, search efficiency and algorithm's adaptability. In order to reduce computational costs and increase classification accuracy, the hybrid method employs natural-inspired metaheuristics for feature selection, resulting in optimal subsets. When it comes to tracking speed, precision, and stability in the PV MPPT environment, the method beats PSO-BOA, conventional RIME, IRIME and HRIME approaches.
Authors - Gauree Prabhakar Sayam, Supriya Narad Abstract - Chronic non-communicable diseases like diabetes, heart disease, and obesity continue to increase globally, comprising 74% of all deaths, even as noted by the World Health Organization in the 2025 progress monitor on non-communicable diseases. This work describes the design and deployment of Health Risk Advisor, an AI (artificial intelligence) web application powered by machine learning that predicts early risks and provides personalized recommendations on disease prevention. The integration of ensemble models such as Random Forest and XG-Boost into a rule-based advisory engine allows the application to achieve more than 90% accuracy in making risk classifications, addressing access barriers to healthcare in underserved regions, such as rural India. From architecture and design, healthcare applications and benefits, to ethical AI challenges and considerations, this work discusses every aspect of the new technology using diverse sets of datasets that inform practices as well as recommend ethical AI. Evaluations showed reductions of the burden from NCDs between 20-30% by engaging the application in a preventive healthcare intervention, which is aligned to global health equity goals.
Authors - Saurabh Nimje, Reena Satpute, Utkarsha Pacharaney, Anup Bhitre Abstract - Breast cancer is considered as one of the top causes of mortality on women across the world making early and accurate diagnosis a key element in addressing patient outcomes. The work introduces artificial breast instances of cancer detection techniques in ultrasound imaging by means of Contrast Limited Adaptive Histogram Equalization (CLAHE) and ensemble deep learning framework. Data used was a balanced data set comprising of 200 ultrasound images that are made to be benign, malignant, and normal. The CLAHE preprocessing was quite useful in terms of image quality as it provided edge and local contrast enhancement and profited letting the lesions be seen more effectively. A number of the convolutional neural network (CNN) architectures were tuned collectively in an ensemble arrangement with soft voting and weighted averaging, and this produced an improved classification performance. The proposed model returned an accuracy of 93.7%, sensitivity of 92.5%, specificity of 94.5% and AUC of 0.97 even better than the baseline general CNN models and the single CNN models with CLAHE. The findings are indicative of the fact that CLAHE-enhanced ensemble learning is a robust, reproducible, and promising tool in breast cancer detection within ultrasound imaging that holds a great promise in clinical.
Authors - Naga Sujitha Vummaneni, Srilakshmi Bharadwaj, Himani Varshney Abstract - The global healthcare landscape is currently undergoing a radical transformation, driven by the dual catalysts of the post-pandemic necessity for remote care and the rapid proliferation of digital infrastructure in developing economies. This research paper presents a comprehensive study on the design, development, and strategic positioning of a desktop-based "Healthcare Management System with Telemedicine." Developed using the Java ecosystem—specifically Java Swing for the graphical user interface (GUI) and Java Database Connectivity (JDBC) for persistence—the system integrates third-party WebRTC services via Jitsi Meet to facilitate real-time virtual consultations. Unlike purely administrative Hospital Management Systems (HMS), this solution integrates clinical workflows with administrative tasks, offering a unified platform for patient authentication, appointment scheduling, and remote video consultation. This report goes beyond technical implementation to provide an exhaustive analysis of the Indian digital health market, projected to reach USD 106.97 billion by 2033. It critically evaluates market leaders such as Practo, Zocdoc, and Teladoc to identify structural gaps in service delivery, particularly regarding cost-barriers and infrastructure dependency in Tier-2 and Tier-3 cities. By adopting the Prototyping Model of software engineering, the research iteratively addresses requirements for security, usability, and legacy hardware compatibility. The findings suggest that while cloud-native SaaS models dominate the current market, lightweight Java-based desktop solutions offer distinct advantages in data sovereignty, offline capability, and operational stability for resource-constrained healthcare settings. The paper concludes with a roadmap for integrating Artificial Intelligence (AI) for predictive diagnostics and expanding into mobile ecosystems, positioning the developed system as a viable component of the emerging Global Initiative on Digital Health (GIDH).
Authors - Nevil Dhinoja, Shubh Patel, Binal Kaka Abstract - Gradient conflicts, computational complexity, and optimization instability are some of the issues with model-agnostic meta-learning, or MAML. We introduce a methodical methodology that integrates three improvement techniques: meta-level regularization, adaptive optimization management, and taskaware gradient. By combining three complimentary mechanisms—task-aware gradient modulation, meta-level regularization, and adaptive optimization management—this work suggests an organized design framework to increase the stability and robustness of MAML-based optimization. The paradigm provides a solid basis for the methodical creation of more reliable and scalable meta-learning systems, even while empirical evaluation is saved for later research.
Authors - Liyan Grace Shaji, Lakshmi K.S, Shazil Mohammad Iqbal, Don Basil Saj, Tom Thomas Abstract - Autism Spectrum Disorder (ASD) is a neurodevelopmental condition that affects skills related to social interaction and communication. Of late, this is estimated to be prevalent in 1 among 100 children, across the world. Unfortunately, our present, diagnostic methods, like ADI-R and ADOS, rely on questionnaires, which render them to be time-consuming, expensive, and skill-dependent. Hence, to address these challenges, FaceIt is developed, which is a Deep Learning-based diagnostic tool that integrates real-time image capture and classification for rapid and accessible ASD screening. The tool efficiently processes facial images captured or uploaded by users, by performing preprocessing steps like cropping and alignment. A Convolutional Neural Network (CNN) extracts facial features to detect ASD, while a Bayesian CNN captures uncertainty in predictions. Its user-friendly interface allows self administration, devoid of professional supervision. The faster and more accessible preliminary screening even facilitates timely follow-up diagnostics if needed, thus making this an optimum solution for widespread use.
Authors - Nabeela Kausar, Ramiza Ashraf, Naila Ashraf, Romana Ali Abstract - The conventional way of preparing an advertisement is an elaborate process incorporating human subjectivity and human resources heavily dependent on creativity. Making advertisements by human effort can be regarded as an inefficient utilization of capital for small to medium-scale businesses due to increased cost of production. Even in current advancements in the development of generative techniques including LLM-based strategies for Advertisement Generation with Prompts, creating apt prompts for the depiction of products requires human expertise, making them less accessible. In order to overcome the challenges presented by the current models, we introduce a fast, affordable, and scalable platform for the automation of advertisement generation for products leveraging the capabilities of pre-trained diffusion models. The proposed system requires no training or fine-tuning since everything is performed at the inference level. The AI-aware system for designing assists in the identification of color schemes and attributes from the images of the products, whereas the descriptions and categories of the items help identify the theme and pattern recommendations for advertisements. These recommendations are channeled through a pre-trained Stable diffusion model guided by the LLaMA language model.
Authors - Naga Sujitha Vummaneni, Ishan Kumar, Adarsh Mittal Abstract - Digital evidence is now central to cyber investigations, legal trials, and organizational audits. However, traditional evidence management systems rely heavily on centralized storage, making them vulnerable to unauthorized modifications, insider attacks, and in complete audit trails. This research introduces a Blockchain-Based Evidence Management System designed to secure digital evidence through immutability, transparent verification, and tamper proof storage of evidence hashes. The proposed solution integrates Java FX as a user-friendly interface, MongoDB for storing meta data, SHA-256 for generating unique evidence fingerprints, and the Polygon Mumbai blockchain for permanent registration of hash values. Users can upload evidence, verify its authenticity, and review all actions through a detailed activity log. Experimental results show that blockchain-backed verification reliably identifies tampered evidence and significantly strengthens the chain of custody. The system offers an efficient, scalable, and secure enhancement to traditional evidence-handling methods.
Authors - Naga Sujitha Vummaneni, Adarsh Mittal, Ishan Kumar Abstract - The rapid growth of digital platforms has transformed the way individuals buy and sell goods. However, college students still largely depend on informal and unorganized methods for peer-to-peer trading. This paper presents UNIBID, a Java-based online marketplace designed specifically for college students to enable secure, reliable, and efficient product trading within the campus community. The system allows users to register, authenticate, list products, browse products, search and filter items, and perform secure purchase transactions. The backend is implemented using Java [1], while database operations are handled using a reliable database management system. The proposed system eliminates the drawbacks of manual trading such as lack of trust, delay in communication, and absence of product verification. Experimental results show that UNIBID significantly improves transaction speed, transparency, and user convenience compared to traditional methods. The system is scalable, secure, and suitable for deployment in real academic environments.
Authors - Nishu, Kajal, Pavitra Jangir, Ayush Kumar Gupta, Kiran Dikshit, Ajay, Vishal Shrivastava, Akhil Pandey, Ram Babu Buri, Harveer Choudhary Abstract - Despite the availability of digital voting systems, prior studies continue to identify gaps such as weak or voter authentication, security vulnerabilities and insufficient fraud prevention mechanisms. This paper presents BotoSafe, a secure and user-centered electronic voting (e-voting) platform developed for student government elections within educational institutions. The system implements multifactor authentication (MFA) using one-time password (OTP) verification and facial recognition with an anti-spoofing mechanism. To ensure the confidentiality and integrity of the voting process we employ the Advanced Encryption Standard in Galois/Counter Mode (AES-GCM). A developmental research design with a quantitative approach was used for the system development and evaluation. A mock election involving 84 students from Western Mindanao State University–Pagadian Campus was conducted, followed by a post-assessment survey. Results from the System Usability Scale (SUS) yielded a score of 72.08, indicating acceptable usability. User responses further showed that the system is easy to use, safe, and trustworthy for student elections. These findings indicate that BotoSafe is a viable e-voting solution for student government elections and may be further enhanced in future studies.
Authors - Banda Rithija, MV Parth, Haripriya L, Skandan SS, Manju Abstract - The task of identifying Cryptographic Algorithms from ciphertext is a challenge within digital forensics and security auditing, when there is no knowledge of either the plaintext or the key used. As modern encryption algorithms increase in sophistication, their output becomes indistinguishable from random noise, rendering traditional pattern recognition techniques ineffective. This paper proposes a two-stage Hierarchical Cipher Classifiers, the first stage discriminates among three major Cryptographic Families: Symmetric, Asymmetric, and Hash; the second stage identifies the specific algorithm within those families in the context of six Modern Encryption Standards: Advanced Encryption Standard, Triple Data Encryption Standard, Blowfish, Rivest–Shamir–Adleman, ElGamal, and Secure Hash Algorithm 256-bit. In order to achieve high accuracy, we developed a hybrid feature space consisting of 167 attributes that included both Statistical and Transform- Domain Features.We incorporated SHapley Additive exPlanations (SHAP) into our classifiers to address the concern of the black-box nature of Deep Learning. Empirical Results indicate that the Hierarchical Classifier Structure has produced a substantial reduction in the rate of misclassifications compared to flat classifiers, offering a transparent and effective tool for automated cryptanalysis.
Authors - Megha Potdar Abstract - This paper delineates a compact microstrip patch antenna that operates within the frequency range of 6.5 to 8.5 THz and exhibits a resonance frequency of 7.344 THz. The antenna maintains a flat, compact shape that is well-suited for terahertz circuit integration and also incorporates circular and U-shaped patch modifications that enhance radiation efficiency, gain, and band-width. According to the simulation results, the device has a gain of 7.042 dBi, a VSWR of 1.1329, a low return loss of –24.109 dB, and a wide impedance bandwidth of 1.119 THz. It demonstrates consistent radiation patterns and effective impedance matching across the operating frequency range, indicating that the proposed design outperforms conventional THz patch antennas and rep-resents a highly efficient solution for high-speed terahertz communication, im-aging, and sensing applications.
Authors - Babatunde David Ikudehinbu, Atefeh Khazaei, Hamidreza Khaleghzadeh Abstract - In this paper, we outline the design and implementation of a novel electronic voting kiosk, dubbed BlockVote, which helps counter identity-related fraud and data tampering via biometric and blockchainbased approaches. The proposed system is a standalone embedded system running on an ESP32-S3 SoC-based microcontroller. The system includes a touchscreen display for user input and an optical fingerprint sensor for identity checking. This collected bio-data and voting selection are then integrated in such a manner that a secure transaction is created through cryptography. This is then sent through the Node.js gateway, which leads it to the secure Ethereum-based blockchain network. Such an application of physical verification technologies with blockchain technology ensures that the proposed voting system is more secure than the traditional e-voting machines or e-voting websites. Block-vote is a hybrid security system in which hardware-based verification techniques are combined with blockchain-based data management in a power-saving, compact format. The prototype has shown proof of its functional viability, its module-based construction, and its reliability, particularly in the field of embedded systems. The experimental results demonstrate the system’s high precision, low latency, and robustness against illegitimate use. The suggested framework demonstrates the practical feasibility of blockchain and biometric technology in the creation of trustworthy electronic voting systems that can be used in both urban and rural areas.
Authors - Deepika K M, Girish Gowda J, Ravi Honnalli, Nikhil S G Abstract - Cloud computing environments face increasingly sophisticated cyber threats that demand advanced detection mechanisms capable of identifying anomalous behavior in real-time. This study introduces an innovative hybrid temporal anomaly modeling system that integrates Autoregressive Integrated Moving Average (ARIMA) with Long Short-Term Memory (LSTM) networks, augmented by meta-learning fusion strategies. Our method solves the difficult problem of getting high recall rates (>95%) that are needed to keep operational efficiency while reducing missed critical threats. We tested five meta-learning architectures—Logistic Regression, Random Forest, XG-Boost, Gradient Boosting, and Neural Network—along with four rule-based fusion strategies on a large Cloud Anomaly Dataset with 249,595 samples taken from 11 virtual machines over 30 days. The Hybrid-RF (Random Forest) model had the best balance, with a recall of 95.75%, an accuracy of 10.59%, and an F1-score of 11.37%. This was much better than the average in the literature (75-85% recall). We set up the system as a production-ready Flask REST API on Google Cloud Platform, with response times of less than 200 milliseconds. This shows that it is possible to use real-time cloud security monitoring. Our findings demonstrate that metalearning fusion of statistical and deep learning temporal models yields enhanced threat detection capabilities relative to single-model approaches, achieving recall improvements of 10-20% over state-of- the-art methods while adhering to real-time performance constraints.
Authors - Anup Bhitre, Saurabh Nimje, Utkarsha Pacharaney, K. T. Reddy Abstract - Cervical Spinal Stenosis (CSS) is a progressive spinal disorder caused by narrowing of the spinal canal in the neck, potentially leading to severe neurological damage if undiagnosed. Due to rising CSS cases and the limitations of manual MRI analysis—such as subjectivity, time consumption, and inter-observer variation—there is a growing need for automated, reliable diagnostic tools. This study evaluates and compares four AI models—CNN, ResNet50, SVM, and Random Forest—using 1,200 T2-weighted MRI images processed through normalization, segmentation, and augmentation. Performance was measured using accuracy, precision, recall, F1-score, and AUC-ROC. ResNet50 achieved the highest accuracy (93.6%) and AUC-ROC (0.97), demonstrating superior diagnostic performance. SHAP was used for interpretability, highlighting spinal canal diameter and ligamentum flavum thickening as key diagnostic features. The findings confirm that deep learning, especially ResNet50, offers a scalable, interpretable, and clinically effective method for early CSS detection.
Authors - C Ashik Poojary, Chirag B Jogi, Sanath Shetty, Sandhya P, Mahitha G Abstract - Image inpainting plays an important role in restoring and reconstructing degraded or damaged images by filling in missing regions. This work proposes a gated convolutional neural network based on a U-Net architecture to achieve perceptually accurate and high-resolution restoration. The model was trained on a large-scale dataset of over 20,000 images generated with the CelebA dataset along with extensive enhancement using artificial damages such as scratches, cracks, random patches, blurring, sepia-toning, and grayscale degradation. The proposed method performs two phases of restoration: context-aware inpainting, followed by resolution enhancement while preserving both global structure and local texture. Quantitative metrics such as PSNR and SSIM were evaluated, and qualitative comparisons demonstrate faithful texture synthesis and tone-consistent fills across color, grayscale, and sepia domains.
Authors - D.Nagaraju, Padinjaroot Monesh Raj, G .Likith, K .Kavitha, Thella Muni Chandrika Abstract - This Gesture recognition technology is studied in this article as it pertains to controlling music wirelessly via a music controller de-vice. The gesture recognition system highlighted in this study is an innovative advancement in this area. In addition to providing the user with an easy-to-use interface for controlling the volume of music with hand motions, This provides a no-contact way to play percussion instruments where users can play from anywhere, either they have good eyesight or not! In addition to providing users with visual experience while using the application, the application also provides users with 3D graphics and animations that dynamically reflect the user’s movement on the screen as they create percussion music through the application. The entire system is created using JavaScript and thus, is completely platform-independent and will work on any recent web browser.
Authors - Aditya Ajitrao Kulkarni, Mayuri Shelke, Saurabh Babasaheb Gonte, Kalpak Sanjay Kedari, Parikshit Balasaheb Jadhav Abstract - Image inpainting is a basic problem in image restoration that focuses on recovering the missing or damaged areas of an image in a visually plausible and semantically consistent way. However, in practical image restoration tasks like historical photo restoration, images are often degraded by complex damages like cracks, scratches, fading, stains, and tone changes. Conventional image restoration methods relying on interpolation or diffusion have limitations in restoring high-frequency details and global semantic information. This paper presents a gated convolutional neural network with a U-Net structure for effective image inpainting and restoration with resolution enhancement. The proposed network is trained on a large-scale dataset of more than 20,000 synthetically degraded images created from the CelebA dataset, considering various damage patterns like scratches, cracks, random occlusions, blurring, grayscale conversion, and sepia tone transformation. The image restoration process involves two steps: context-aware image inpainting and resolution refinement. The proposed framework is extensively evaluated using PSNR and SSIM metrics for its effectiveness in color, grayscale, and sepia image restoration.
Authors - G Venkata Suresh Reddy, Immanuel Anupalli, P.Sudheer Abstract - Solar photovoltaic (PV) systems require robust and intelligent problem detection systems to guarantee they continue producing energy effectively as they gain traction as a renewable energy source. In order to detect various defects in photovoltaic (PV) systems operating under nonlinear and noisy conditions, this research presents a data-driven fault classification framework that employs machine learning techniques. Electrical data from photovoltaic (PV) panels, including current-voltage (I-V) and power-voltage (P-V) curves recorded in three distinct operating circumstances (Healthy, Shading, and Open-Circuit), formed the basis of the dataset used for training and testing the model. For each condition, crucial electrical characteristics have been used to characterize the system's electrical behavior, including open-circuit voltage, short-circuit current, maximum power point voltage and current, fill factor, and a handful of statistical statistics. Logistic Regression, Naïve Bayes, and k-Nearest Neighbors (KNN) are the three supervised machine learning methods that were employed to detect various errors. Each model was fine-tuned using hyper parameter tweaking and k-fold cross-validation. The classification performance in the comparative performance analysis was greatest for Logistic Regression (96.09% accuracy, 96.25% precision, 96.49% recall, and 96.36% F1-score). Second place went to the KNN model, which had a 95.47% accuracy rate. In contrast, the Naïve Bayes model maintained its reliability, with an accuracy rate of 94.13%. This demonstrates that it is still effective when dealing with nonlinear data that contains noise. According to the overall results, many machine learning algorithms, especially Logistic Regression, do a great job of finding PV problems in real time. The suggested framework is both efficient and useful for real-world PV monitoring systems because it just needs to measure electrical parameters that are easy to get (I-V and P-V data). Using this strategy for preventative maintenance makes solar systems more reliable and increases their production, which in turn cuts down on power losses.
Authors - Premanand Ghadekar, Utkarsh Patil, Niraj Ukare, Vansh Bhatt, Rohan Uplenchwar, Shreya Sidnale Abstract - Traditional multi-agent communication systems rely on fixed security protocols and static message processing pipelines, leaving them vulnerable to advancing cyberattacks and dependent on expensive infrastructure. This paper introduces a Secure Multi-Agent Communicational Protocol designed as a lightweight, affordable framework for small and medium-scale systems to communicate safely without enterpriselevel costs. The current setup depends heavily on predictable session keys, making systems prone to impersonation, replay attacks, token alterations, and man-in-the-middle interceptions. This framework stimulates agentto- agent interactions through three primary components: a predictive security model, a dual-token authentication mechanism, and a protocolaware attack engine. The infrastructure utilizes WebSocket connections integrated with Redis Pub/Sub for real-time messaging. A dynamic session key generation process works alongside a rotating refresh-token system, ensuring that even if a session key is compromised, attackers still require a valid refresh token. The predictive component features a Protocol-Aware XLNet model with a dual-thread structure to examine message sequences and statistical irregularities. A fusion layer integrates these analyses, reporting a Dual-Thread Consistency Score of 0.87 and a 31% gain in early-warning capability. Experimental evaluations demonstrate 93.5% violation sensitivity, 91.7% replay detection accuracy, and 89.3% attack-type classification accuracy. This approach enables timely identification of replay incidents, interceptions, and protocol tampering. Additionally, an independent XGBoost model filters fraudulent links. These enhancements provide substantial gains in early warning capabilities and consistent classification accuracy across various attack categories.
