Premier University

In Bangladesh, where a burgeoning population strains limited road networks, wrong-way driving (WWD) exacerbates traffic congestion and elevates accident risks, posing a critical public safety challenge. We present a pioneering real-time WWD detection system that integrates cutting-edge image processing and deep learning to transform traffic monitoring. Our methodology combines the Hough line transform for precise road boundary extraction with the state-of-the-art YOLOv5 algorithm for high-fidelity, real-time vehicle detection. Vehicle direction is inferred from single-frame orientation (distinguishing front/rear views) without multi-frame tracking, ensuring lightweight operation and scalable deployment. Tested on a novel, region-specific dataset from Chattogram, the system achieves an impressive 96% vehicle detection accuracy (mAP@0.5) during training and validation. Real-world evaluations on 20 diverse test videos yield an overall 60.6% recall for wrong-way vehicles, with a representative subset of 10 videos reaching 75% recall (and 41% precision). This research advances computer vision applications in traffic safety, providing an effective and deployable framework for reducing WWD incidents in high congestion urban regions and paving the way for enhanced intelligent transportation systems.

Automated interpretation of wafer maps is central to manufacturing quality monitoring. Identifying rare defects with less detailed wafer maps is a challenging task. Moreover, class imbalance, heavyweight backbones, and limited model transparency are constraints for the real-world deployment of defective wafer identification. However, a nine-class wafer-map classifier is required that maintains high accuracy under tight parameter and compute budgets and provides decision-level interpretability, despite long-tailed class distributions. To address this issue, a compact convolutional network is presented for wafer-map classification on standardized low-resolution inputs. The architecture uses two convolution-pooling stages, followed by a modified convolutional block attention module (CBAM). Channel attention is realized via a shared multilayer perceptron with batch normalization for stable reweighting, while spatial attention uses a multi-scale gate to emphasize ring-like, edge-localized, and streak patterns. A compact dense head with softmax produces nine class probabilities, with a total footprint of approximately 0.15M parameters. Class imbalance is mitigated through a training-only convolutional autoencoder that generates minority samples via latent feature variation, together with a controlled reduction in the dominant None class. Validation and test sets remain unchanged. A fixed-seed protocol ensures reproducibility, and performance is evaluated using accuracy and macro-averaged precision, recall, and F1. On a balanced benchmark derived from the WM-811K dataset, the model achieves 99.88% test accuracy with near-ceiling macro-F1 while using a small fraction of the parameters required by transfer learning and transformer baselines and consistently outperforming conventional convolutional neural network (CNN) backbones. Post-training interpretability analyses with Grad-CAM, integrated gradients (IG), and occlusion show alignment between salient regions and physically meaningful defect morphology. Ablation studies indicate complementary gains from latent feature augmentation and attention mechanisms, while robustness checks with input noise and reduced training support show graceful degradation. The resulting pipeline is accurate, lightweight, and transparent, making it suitable for inline screening scenarios.

Mobile Ad Hoc Networks (MANETs) stand out for supporting connectivity in fluid, infrastructure-free scenarios, though they grapple with issues like broadcast storms, inefficient data retrieval, signal overload, and resource constraints due to frequent topology changes. Named Data Networking (NDN) offers content-centric benefits such as in-network caching but suffers from redundant transmissions and mobility-induced disruptions in MANETs. This paper presents PDAF, an SDN-assisted performance-driven adaptive forwarding framework that improves data delivery while suppressing redundant transmissions in NDN-MANETs. PDAF leverages SDN controller to rank candidate routes using multiple performance metrics, incorporating both data caches and source nodes to guide packets along optimal paths in highly dynamic scenarios. An adaptive identifier-driven suppression scheme cancels pending requests network-wide after successful delivery, halting further packet dissemination. Extensive simulations under varying mobility, traffic load, catalogue size, and network density show that PDAF outperforms existing forwarding schemes, achieving, on average, a 25–86% improvement in packet delivery ratio, a 63–96% reduction in end-to-end latency, and a 48-79% reduction in traffic load, while maintaining low control overhead, demonstrating its effectiveness in reliable and efficient content delivery.

Agriculture consumes 70% of global freshwater, yet over half is lost to inefficient irrigation. Existing IoT based smart systems prioritize full automation, marginalizing farmers' experiential knowledge. Here we proposed a hybrid human in the loop IoT architecture that balances algorithmic precision with farmer driven control. The system integrates an ESP32 microcontroller with real time sensing of soil moisture, pH, and water reservoir levels. A heuristic control algorithm, formalized through pseudo code, governs irrigation decisions while an intuitive mobile interface provides real time telemetry and manual override capabilities. A 7-day prototype validation demonstrated significant water conservation, achieving 382.9 mL mean daily consumption versus 570.0 mL for conventional fixed schedules, a 32.8% reduction (cumulative 37.5% savings). The system maintained optimal soil moisture within ±5% of crop specific set points, and manual override functionality proved 100% reliable (42/42 attempts). Total prototype cost was 2,460 BDT (approximately $23 USD). This work establishes three contributions: a formal hybrid control algorithm with farmer confirmation protocols, a low cost multi parameter sensing platform, and empirical validation that farmer expertise enhances automated irrigation decisions, providing a scalable framework for sustainable agriculture in water stressed regions.