This paper proposes a standard applications of Radio Frequency Identification (RFID) system to manage vehicles at electronic toll gate system without compromising the vehicle speed. The existing electronic toll gate system has low latency as each car needs to wait in a queue for passing the gate. Installation of reader antenna at each lane makes the system expensive. We propose a two-ray ground model for using minimal reader antenna to define required antenna height and downtilt angle to cover the total gate area. We estimate that reader antenna at a height of 15 m and 45.4° downtilit angle are required for optimal signal reception from the car at a distance of 35–38 m. Modified Pulse Protocol algorithm is suggested for mitigating reader collision and increase throughput and utilization of the system by 14.71% and 15.2% respectively. The probability distribution function of the contention window is modified to triangular function. The M-ary Trimming Q-tree protocol is suggested to resolve the tag collision by trimming the idle nodes from the query tree, which reduces identification time. The total time slot decreases with higher elements, and the total throughput also increases to 98%. The “no-lane” strategy established a fast, efficient and cost effective vehicle toll collection system.
Real-time object detection in adverse weather and low-light conditions is crucial for applications such as autonomous driving and intelligent surveillance. This paper presents MDAT-YOLO, a novel object detection framework designed to balance accuracy and efficiency in challenging environments. The model integrates multi-dimensional attention mechanisms and transformer-based enhancements to strengthen feature extraction and adaptability. It introduces two core modules: DWConv_O, an optimized depthwise separable convolution layer, and ODConv++, an omni-dimensional dynamic convolution module that enhances spatial, channel, and kernel-level interactions for improved feature selectivity and dynamic response. A lightweight C3 Transformer (C3TR) block further reduces computational overhead while maintaining strong representational capacity. MDAT-YOLO is evaluated on four benchmark datasets, including RTTS, VOC-Foggy, ExDark, and a custom foggy VOC-PASCAL subset, achieving accuracy improvements of 70.50%, 65.14%, 77.40%, and 49.00%, respectively. The model sustains real-time speeds up to 145 FPS, demonstrating robustness and practicality for real-world deployment under diverse environmental conditions.
Alzheimer’s disease (AD) is the most prevalent form of dementia and a major cause of mortality among older adults. Magnetic resonance imaging (MRI) and positron emission tomography (PET) are commonly used for AD diagnosis. Despite extensive research, the accuracy of automated detection methods remains limited. This study proposes a highly accurate AD classification model by integrating complementary information from MRI and PET scans. The images are fused using a discrete wavelet transform (DWT), augmented, and subsequently classified using a Vision Transformer (ViT). Comprehensive evaluation across nine performance metrics shows that the proposed ViT-based framework achieves 97.68\% accuracy, surpassing benchmark transfer learning models and state-of-the-art methods. Ablation studies and comparative analysis further confirm the robustness and reliability of the proposed approach for AD detection.