Urban road traffic congestion poses significant challenges to sustainable mobility in smart cities. Traditional traffic light systems, reliant on static or semi-fixed timers, fail to adapt to dynamic traffic conditions, exacerbating congestion and limiting inclusivity. To address these limitations, this paper proposes H-ATLM (a hybrid adaptive traffic lights management), a system utilizing the deep deterministic policy gradient (DDPG) reinforcement learning algorithm to optimize traffic light timings dynamically based on real-time data. The system integrates advanced sensing technologies, such as cameras and inductive loops, to monitor traffic conditions and adaptively adjust signal phases. Experimental results demonstrate significant improvements, including reductions in congestion (up to 50%), increases in throughput (up to 149%), and decreases in clearance times (up to 84%). These findings open the door for integrating accessibility-focused features such as adaptive signaling for accessible vehicles, dedicated lanes for paratransit services, and prioritized traffic flows for inclusive mobility.

Breast cancer (BC) remains a leading cause of cancer-related mortality among women worldwide, necessitating advancements in diagnostic methodologies to improve early detection and treatment outcomes. This study proposes a novel twin-stream approach for histopathological image classification, utilizing both histopathologically inherited and vision-based features to enhance diagnostic precision. The first stream utilizes Virchow2, a deep learning model designed to extract high-level histopathological features, while the second stream employs Nomic, a vision-based transformer model, to capture spatial and contextual information. The fusion of these streams ensures a comprehensive feature representation, enabling the model to achieve state-of-the-art performance on the BACH dataset. Experimental results demonstrate the superiority of the twin-stream approach, with a mean accuracy of 98.60% and specificity of 99.07%, significantly outperforming single-stream methods and related studies. Statistical analyses, including paired t-tests, ANOVA, and correlation studies, confirm the robustness and reliability of the model. The proposed approach not only improves diagnostic accuracy but also offers a scalable and efficient solution for clinical applications, addressing the challenges of resource constraints and increasing diagnostic demands.

As the global population ages, robust technological solutions are increasingly necessary to support and enhance elderly autonomy in-home or care settings. This paper presents a novel computer vision-based activity monitoring system that uses cameras and infrared sensors to detect and analyze daily activities of elderly individuals in care environments. The system integrates a frame differencing algorithm with adjustable sensitivity parameters and an anomaly detection model tailored to identify deviations from individual behavior patterns without relying on large volumes of labeled data. The system was validated through real-world deployments across multiple care home rooms, demonstrating significant improvements in emergency response times and ensuring resident privacy through anonymized frame differencing views. Upon detecting anomalies in daily routines, the system promptly alerts caregivers and family members, facilitating immediate intervention. The experimental results confirm the system’s capability for unobtrusive, continuous monitoring, laying a strong foundation for scalable remote elderly care services and enhancing the safety and independence of vulnerable older individuals.

Sound-based early fault detection for vehicles is a critical yet underexplored area, particularly within Intelligent Transportation Systems (ITSs) for smart cities. Despite the clear necessity for sound-based diagnostic systems, the scarcity of specialized publicly available datasets presents a major challenge. This study addresses this gap by contributing in multiple dimensions. Firstly, it emphasizes the significance of sound-based diagnostics for real-time detection of faults through analyzing sounds directly generated by vehicles, such as engine or brake noises, and the classification of external emergency sounds, like sirens, relevant to vehicle safety. Secondly, this paper introduces a novel dataset encompassing vehicle fault sounds, emergency sirens, and environmental noises specifically curated to address the absence of such specialized datasets. A comprehensive framework is proposed, combining audio preprocessing, feature extraction (via Mel Spectrograms, MFCCs, and Chromatograms), and classification using 11 models. Evaluations using both compact (52 features) and expanded (126 features) representations show that several classes (e.g., Engine Misfire, Fuel Pump Cartridge Fault, Radiator Fan Failure) achieve near-perfect accuracy, though acoustically similar classes like Universal Joint Failure, Knocking, and Pre-ignition Problem remain challenging. Logistic Regression yielded the highest accuracy of 86.5% for the vehicle fault dataset (DB1) using compact features, while neural networks performed best for datasets DB2 and DB3, achieving 88.4% and 85.5%, respectively. In the second scenario, a Bayesian-Optimized Weighted Soft Voting with Feature Selection (BOWSVFS) approach is proposed, significantly enhancing accuracy to 91.04% for DB1, 88.85% for DB2, and 86.85% for DB3. These results highlight the effectiveness of the proposed methods in addressing key ITS limitations and enhancing accessibility for individuals with disabilities through auditory-based vehicle diagnostics and emergency recognition systems.