Uneven roads pose significant challenges to vehicle stability, passenger comfort, and safety, especially in snowy and mountainous regions. These problems are often complex and challenging to resolve with traditional detection and stabilization methods. This paper presents a dual-method approach to improving vehicle stability by identifying road irregularities and dynamically adjusting the balance. The proposed solution combines YOLOv8 for real-time road anomaly detection with a GY-521 sensor to track the speed of servo motors, facilitating immediate stabilization. YOLOv8 achieves a peak precision of 0.99 at a confidence threshold of 1.0 rate in surface recognition, surpassing conventional sensor-based detection. The vehicle design is divided into two sections: an upper passenger seating area and a lower section that contains the engine and wheels. The GY-521 sensor is strategically placed to monitor road conditions, while the servomotor stabilizes the upper section, ensuring passenger comfort and reducing the risk of accidents. This setup maintains stability even on uneven terrain. Furthermore, the proposed solution significantly reduces collision risk, vehicle wear, and maintenance costs while improving operational efficiency. Its compatibility with various vehicles and capabilities makes it an excellent candidate for enhancing road safety and driving experience in challenging environments. In addition, this work marks a crucial step towards a safer, more sustainable, and more comfortable transportation system.

Manual inspection of onba earing casting defects is not realistic and unreliable, particularly in the case of some micro-level anomalies which lead to major defects on a large scale. To address these challenges, we propose BearFusionNet, an attention-based deep learning architecture with multi-stream, which merges both DenseNet201 and MobileNetV2 for feature extraction with a classification head inspired by VGG19. This hybrid design, figuratively beaming from one layer to another, extracts the enormity of representations on different scales, backed by a pre-preprocessing pipeline that brings defect saliency to the fore through contrast adjustment, denoising, and edge detection. The use of multi-head self-attention enhances feature fusion, enabling the model to capture both large and small spatial features. BearFusionNet achieves an accuracy of 99.66% and Cohen’s kappa score of 0.9929 in Kaggle’s Real-life Industrial Casting Defects dataset. Both McNemar’s and Wilcoxon signed-rank statistical tests, as well as five-fold cross-validation, are employed to assess the robustness of our proposed model. To interpret the model, we adopt Grad-Cam visualizations, which are the state of the art standard. Furthermore, we deploy BearFusionNet as a web-based system for near real-time inference (5–6 s per prediction), which enables the quickest yet accurate detection with visual explanations. Overall, BearFusionNet is an interpretable, accurate, and deployable solution that can automatically detect casting defects, leading to significant advances in the innovative industrial environment.

The rapid advancement of deep learning in medical image analysis has greatly enhanced the accuracy of skin cancer classification. However, current state-of-the-art models, especially those based on transfer learning like ResNet50, come with significant computational overhead, rendering them impractical for deployment in resource-constrained environments. This study proposes a custom CNN model that achieves a 96.7\% reduction in parameters (from 23.9 million in ResNet50 to 692,000) while maintaining a classification accuracy deviation of less than 0.022\%. Our empirical analysis of the HAM10000 dataset reveals that although transfer learning models provide a marginal accuracy improvement of approximately 0.022\%, they result in a staggering 13,216.76\% increase in FLOPs, considerably raising computational costs and inference latency. In contrast, our lightweight CNN architecture, which encompasses only 30.04 million FLOPs compared to ResNet50's 4.00 billion, significantly reduces energy consumption, memory footprint, and inference time. These findings underscore the trade-off between the complexity of deep models and their real-world feasibility, positioning our optimized CNN as a practical solution for mobile and edge-based skin cancer diagnostics.

A Content Delivery Network (CDN) is a powerful system of distributed caching servers that aims to accelerate content delivery, like high-definition video, IoT applications, and ultra-low-latency services, efficiently and with fast velocity. This has become of paramount importance in the post-pandemic era. Challenges arise when exponential content volume growth and scalability across different geographic locations are required. This paper investigates data-driven evaluations of CDN algorithms in dynamic server selection for latency reduction, bandwidth throttling for efficient resource management, real-time Round Trip Time analysis for adaptive routing, and programmatic network delay simulation to emulate various conditions. Key performance metrics, such as round-trip time (RTT) and CPU usage, are carefully analyzed to evaluate scalability and algorithmic efficiency through two experimental setups: a constrained edge-like local system and a scalable FABRIC testbed. The statistical validation of RTT trends, alongside CPU utilization, is presented in the results. The optimization process reveals significant trade-offs between scalability and resource consumption, providing actionable insights for effectively deploying and enhancing CDN algorithms in edge and distributed computing environments.

Visual-Inertial Odometry (VIO) supports immersive Virtual Reality (VR) by fusing camera and Inertial Measurement Unit (IMU) data for real-time pose. However, current trend of offloading VIO to edge servers can lead server-side threat surface where subtle pose spoofing can accumulate into substantial drift, while evading heuristic checks. In this paper, we study this threat and present an unsupervised, label-free detection and recovery mechanism. The proposed model is trained on attack-free sessions to learn temporal regularities of motion to detect runtime deviations and initiate recovery to restore pose consistency. We evaluate the approach in a realistic offloaded-VIO environment using ILLIXR testbed across multiple spoofing intensities. Experimental results in terms of well-known performance metrics show substantial reductions in trajectory and pose error compared to a no-defense baseline.