Financial stock market trend decision systems support the investment decisions by predicting future price movements and analyzing large-scale market data. Despite, IoT enabled trading systems continuously collects and exchange sentiment and market information are exposed to adversarial attacks, which misleads automated trading algorithms and results in inaccurate investment decision systems. To face this challenge, this study proposes an adversarial-resilient explainable artificial intelligence for sentiment-driven stock trading (ARXAI-SST) architecture. The proposed framework combines graph neural networks (GNN) for adversarial attack detection, FinBERT based sentiment representation, BiLSTM with attention (BiLSTM-Att) for the sentiment analysis, and SHAP-based explainable artificial intelligence for enhancing model interpretability. The experimentation outcomes show that the proposed framework accomplishes higher accuracy and robustness compared with the existing approaches while providing transparent insights into the trading decisions. The proposed model offers an efficient and reliable solution for secure sentiment driven stock trading in IoT enabled financial environments.
Learning management systems (LMSs) are widely adopted in engineering education to support content delivery, foster collaboration, and develop digital competencies. However, existing platforms often prioritize functionality over user engagement and accessibility. There is limited research that holistically evaluates LMS usability, persuasive design, and accessibility in the context of technical education, particularly during high-frequency tasks such as assignment submission. This study aims to evaluate and compare the usability, persuasive elements, and accessibility of blackboard, canvas, and Google Classroom during the assignment submission process from the perspective of engineering students. An experimental, between-subjects design was employed with engineering students who each interacted with one of the three LMS platforms. We evaluated usability, persuasiveness and accessibility. Canvas was the most efficient platform, with shorter task completion times and fewer errors. However, it received lower scores in satisfaction and persuasive design compared to Google Classroom, which stood out in credibility and user guidance but showed more variability in efficiency. None of the platforms fully complied with key accessibility criteria, such as keyboard operability and proper form labeling. These findings highlight the importance of designing LMS platforms that balance us ability, persuasion, and accessibility to better support engagement and equity in engineering education.
There are still a huge demand for safe and sustainable modes of transport which has led to the creation of autonomous self-balancing bicycles. The design and analysis of the self-balancing bicycle with flywheel mechanism assisted by gyroscope is presented in this study. A Lagrangian approach was used to model the tilt dynamics; it includes kinetic energy, potential energy, damping and actuator torque generated by the BLDC motors. The nonlinear system was linearized around the upright equilibrium for control implementation and simulated in MATLAB. Results indicate that an initial lean disturbance is stabilized within about 1 s, and that the motor current also reaches steady state values, thus signifying efficient use of energy. The gyroscopic response trends corroborate the realistic tilt sensing and the effectiveness of the proposed stabilization framework is confirmed for autonomous operation on straight and curved paths.
This article introduces VigilNet, a personal safety system powered by internet of things (IoT) and machine learning (ML) that identifies environmental irregularities instantaneously through intelligent wearable gadgets. In contrast to solutions dependent on extensive datasets and reactive alert systems VigilNet employs a few-shot learning (FSL) strategy utilizing siamese neural networks (SNNs) to achieve precise anomaly recognition, with limited training data. In the information and communication technology (ICT) realm, VigilNet is a smart IoT sensing and communication network with interconnected wearable sensor nodes continuously collecting physiological and environmental data for real-time processing. The SNNs based FSL module then fuses these multiple modal streams of sensor information and extracts the similarity-based threat assessment, which in turn drives an intelligent decision support system to alarm the operator to take timely action for any abnormal situations. VigilNet, thus, combines IoT connectivity, real-time data analytics, and machine-learning-driven decision support into a single personal safety system. The framework was tested on an IoT wearable dataset encompassing heart rate, body temperature, ambient noise and proximity data. Experimental results demonstrate that VigilNet achieves a threat detection rate (TDR) of 0.85, false alarm rate (FAR) of 0.10, and a response time (RT) of 3.5 seconds, outperforming conventional IoT–ML safety models. These findings validate the feasibility, efficiency, and robustness of the proposed architecture and confirm the potential of FSL-based techniques for next-generation women’s safety technologies.
Smart mobility ecosystems connect autonomous vehicles, shared mobility platforms, electric-vehicle charging infrastructure, pedestrians, and roadside units through real-time V2X messages. This paper redesigns PPT-CLAMA, a privacy-preserving and traceable certificateless anonymous mutual authentication scheme, for high-speed internet of vehicles (IoV) and smart mobility environments. The proposed SmartMob-PPT-CLAMA introduces mobility-adaptive pseudonym pools, RSU-assisted handover caching, lightweight V2X authentication headers, hierarchical traceability, and Sybil aware regional trust filtering. The protocol preserves the original security objectives of anonymity, unlinkability, perfect forward secrecy, known session-specific temporary information security, and lawful traceability, while addressing mobility-specific weaknesses such as long-lived pseudonym tracking, handover re-authentication delay, centralized trace authority failure, high-speed Sybil attacks, and broadcast replay. In the evaluated Raspberry Pi 4B and SUMO/NS-3 workload, the proposed design reduces authentication delay from 1.10 ms to 0.82 ms, reduces communication overhead from 470 bits to 312 bits, and achieves 99.1% handover re-authentication success. The design is mapped to ETSI ITS security, IEEE 1609.2, ISO/SAE 21434, and GDPR Article 32 requirements.
