Pillar College

With the rapid expansion of the Internet of Things (IoT) networks, ensuring secure, efficient, and high-performance device communication has become increasingly critical. Existing lightweight authentication protocols struggle to balance security, performance, and efficiency. To address this, we propose OPP (Our Proposed Protocol), a lightweight authentication protocol integrating session-specific AEAD encryption and ECC-based Schnorr signatures to strengthen security without degrading performance and efficiency. OPP is rigorously evaluated against SELAP and ELWSCAS through formal (Scyther) and informal security analyses, and performance simulations in NS-3 using metrics such as delay, packet delivery ratio (PDR), throughput, energy, computation, and communication cost. Results demonstrate that OPP achieves mutual authentication, session key freshness, and best attack resistance while outperforming counterparts in performance, achieving the lowest handshake delay (11.53–29.50 ms), highest PDR (91.20–98.40%), and best throughput (72–412 authentications). It also sustains minimal energy consumption (0.320J at 50 nodes), low communication overhead (960 bits), and efficient computation (705 µs). Since SELAP and ELWSCAS previously outperformed earlier schemes, OPP’s superiority implies a transitive improvement over existing IoT authentication protocols, establishing it as a robust and scalable solution for secure communication in constrained IoT networks.

Identifying duplicate questions is essential for maintaining quality and reducing redundancy on question-answering platforms like Quora. While it is relatively easy for humans to detect semantic similarity between questions, automating this task poses a challenge due to the diversity in language expression. With the advancement of Natural Language Processing and deep learning, it has become possible to capture deeper semantic meaning in text. This study proposes a duplicate question detection method that leverages Sentence-BERT embeddings to understand semantic similarity between question pairs. The proposed method is evaluated on a sampled subset of the Quora Question Pairs dataset comprising 30,000 instances. Various features such as cosine similarity, absolute embedding differences, length differences, and common word counts are engineered from these embeddings. These features are then used to train multiple machine learning classifiers, including XGBoost, Random Forest, SVM, and Logistic Regression. To improve performance, an ensemble approach using majority voting is employed. This method effectively combines the power of deep semantic representation and classical machine learning to enhance prediction accuracy.

The invasive Crown-of-Thorns starfish (COTS) poses a significant threat to coral reef ecosystems. Early detection and removal are crucial to mitigating their impact. This research proposes a YOLOv5-based object detection system to accurately identify and locate COTS in underwater images. By fine-tuning the YOLOv5 model with a dataset of COTS images, the system can effectively detect and classify COTS with high precision and recall. The output of the system includes bounding boxes and confidence scores for each detected COTS, enabling timely intervention and removal efforts. This research contributes to the conservation of coral reefs by providing a valuable tool for monitoring and controlling COTS populations. The proposed system can be integrated into underwater drones or diveroperated devices to facilitate efficient and accurate COTS detection and removal.

Using artificial intelligence (AI), machine learning (ML), deep learning (DL), and conversational models like ChatGPT, smart farming is revolutionizing the agricultural industry by increasing productivity, cutting down on resource usage, and improving decision-making. Critical agricultural problems including crop monitoring, pest identification, weather forecasting, and soil analysis can be resolved with the help of these technologies. Predictive analytics is made possible by AI and ML algorithms, which enhance crop yield by foreseeing disease outbreaks and maximizing planting schedules. With sophisticated image processing, deep learning models (DL models) enable real-time monitoring of livestock and crops, providing detailed information for precision farming. Smart farming is being further enhanced by ChatGPT and other AI-driven conversational agents. These agents offer real-time advisory services, make it possible for farmers to communicate with AI tools using natural language, and streamline difficult tasks like supply chain management, market analysis, and crop selection. Future developments in smart farming include the integration of AI with IoT devices, blockchain technology for traceability, and improved edge computing capabilities to facilitate localized, real-time decision-making.

Industry 4.0 brought with it by the next-gen Industry 5.0 and Society 5.0 paradigms, catalysed by Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) technologies. These advances have the benefit of encouraging sustainability, improving output, and updating manufacturing. By enabling self-decision, continuous monitoring, and predictive maintenance with the processing of large data, AI is dramatically reducing downtime and associated costs of system downtime. As a result, ML algorithms, in light of their applicability for continuous learning and adaptation, have contributed to enriching product quality, streamlining supply networks and okaying personalized customer experiences. Neural networks are also being leveraged to improve computer vision and speech capabilities, for applications such as smart automation and human-robot cooperation in challenging industrial contexts. Industry 5.0 truly puts humans back at the centre of innovation. It is aimed to create an evolved society in which AI, ML, and DL are fused with the digital and physical world Society 5.0. The integration aims to address a plethora of societal challenges: environmental sustainability, health and ageing population, among others. It is a convergence of these said technologies that lead to a paradigm shift towards more resilient, adaptive, and sustainable industrial ecosystems. This paper aims to address these questions in a systematic way to offer a comprehensive view of what the future industrial landscape could look like leveraging the promise of Industry 4.0 and Industry 5.0 thus, and more opportunities to embrace intelligent and sustainable industries of tomorrow.

The swift progression of artificial intelligence (AI), machine learning (ML), and deep learning (DL) has transformed different industries, offering unprecedented efficiency and innovation. Nevertheless, the growing intricacy and lack of transparency of these technologies have led to important worries about their reliability and ethical consequences. This research explores the growing area of Explainable Artificial Intelligence (XAI) that seeks to improve the clarity, comprehensibility, and responsibility of AI, ML, and deep learning models. XAI helps to increase trust and acceptance by making these technologies easier to understand for users and stakeholders, therefore tackling the "black box" issue. This research provides a thorough examination of the most recent approaches and structures in XAI, with a focus on important strategies like model-agnostic explanations, interpretable models, and post-hoc interpretability techniques. It also examines the important function of XAI in guaranteeing adherence to regulatory standards and ethical guidelines, which are becoming stricter globally. Moreover, the review assesses how XAI is incorporated into different fields such as healthcare, finance, and autonomous systems, illustrating its ability to reduce biases, enhance decision-making, and increase user confidence. This research highlights the significance of XAI in creating AI systems that are both strong and ethical by discussing current trends and developments.

Abstract: The "Bus Pass with Barcode Scan Project" aims to enhance the efficiency and security of bus transportation services by implementing a barcode-based pass system. This theoretical project focuses on the conceptual framework and key components required for the successful implementation of such a system. Implementing a secure and convenient bus pass system using barcode technology. Improves the accuracy and speed of passenger boarding by automating the pass verification process. Enhancing data management and analytics for better service planning and passenger experience. Developing a system for generating unique barcodesfor each bus pass holder. Ensures that the generated barcodes are tamper-proof and secure against duplication. Installing barcode scanners on buses to read the passenger's bus pass barcode. Ensures compatibility with various barcode types (e.g., QR codes, traditional barcodes). Creates a centralized database that store passenger information, including name, pass details, and barcode data. Implementing data encryption and security protocols to protect passenger information. Developing a mobile application for passengers to purchase, renew, or display their bus pass on their smartphones. Enabling easy scanning of the mobile app's barcode at the bus entry point.