The domain of object detection was revolutionized with the introduction of Convolutional Neural Networks (CNNs) in the field of computer vision. This article aims to explore the architectural intricacies, methodological differences, and performance characteristics of three CNN-based object detection algorithms, namely Faster Region-Based Convolutional Network (R-CNN), You Only Look Once v3 (YOLO), and Single Shot MultiBox Detector (SSD) in the specific domain application of vehicle detection. The findings of this study indicate that the SSD object detection algorithm outperforms the other approaches in terms of both performance and processing speeds. The Faster R-CNN approach detected objects in images with an average speed of 5.1 s, achieving a mean average precision of 0.76 and an average loss of 0.467. YOLO v3 detected objects with an average speed of 1.16 s, achieving a mean average precision of 0.81 with an average loss of 1.183. In contrast, SSD detected objects with an average speed of 0.5 s, exhibiting the highest mean average precision of 0.92 despite having a higher average loss of 2.625. Notably, all three object detectors achieved an accuracy exceeding 99%.
Most motor vehicles have historically utilized Internal Combustion Engines powered by a fossil fuel. Despite the technological advancements in fuel-efficient engines, further improvements are required to reduce the effect of fuel costs and global warming. This study models and simulates Hybrid Electric Vehicles (HEVs) to evaluate their potential for fuel cost savings and emissions reduction compared to traditional vehicles. Using MATLAB® version R2023a Update 5 (9.14.0.2337262) Simulink version 10.7 (R2023a) and the Advanced Vehicle Simulator (ADVISOR) version 2003-00-r0116, the research examines Series and Parallel HEV configurations. The simulation explores various battery configurations, engine capacities, and power unit models to analyze their impact on energy utilization. The data, collected from the simulations, show significant fuel savings and emissions reduction with HEVs. The Parallel HEV configuration consistently saves fuel with fewer battery modules, while the Series HEV configuration performs better but requires more modules to maintain the system’s State of Charge.
The rising demand to efficiently acquire live production data has added more significance to automated monitoring and reporting within the industrial manufacturing sector. Real-time parts screening requiring repetitive human intervention for data input may not be a feasible solution to meet the demands of modern industrial automation. The objective of this study is to automatically classify and report on manufactured metal sheet parts. The metal components are mechanically suspended on an enamel paint-coating conveyor line in a household appliance manufacturing plant. At any given instant, the parts may not be in the exact coordinates within the desired area of interest and the classes of objects vary based on changing production requirements. To mitigate these challenges, this study proposes the use of a trained Mask R-CNN model to detect the objects and their associated class. Images are acquired in real-time using a video camera located next to the enamel coating line which are subsequently processed using the object detection algorithm for automated entry into the plant management information system. The highest achieved average precision obtained from the model was 98.27% with an overall accuracy of 98.24% using the proposed framework. The results surpassed the acceptable standard for the average precision of 97.5% as set by the plant production quality engineers.
The advent of the Internet of Things (IoT) has contributed to an increase in the production volume of RF-featured equipment. According to statistics from the literature, the IoT industry will soon deploy billions of products. While the concept behind these applications seems exciting, this paper sought to assess the effects the radio emissions produced by IoT products would have on the ambient radio noise levels within the unlicensed frequency bands of 433 MHz, 868 MHz, and 2.4 GHz. The study extended to three environments: industrial, urban, and suburban. This study developed an IoT noise generator (ING) device to emulate RF noise signals in the desired IoT radio transmission band. The paper presents a simplified radio noise surveying system (RNSS) for data collection of ambient radio noise from five South African candidate sites. The statistical and empirical analysis agree that the level of ambient radio noise was directly proportional to the rate of IoT radio activities. The slopes of the regression lines demonstrate that 80% of the analyzed data developed augmenting trends. Approximately 20% of the data show declining trends.
Valve stiction remains a persistent nonlinear phenomenon in industrial control loops, often inducing limit-cycle oscillations that degrade control performance, compromise stability, and reduce process efficiency. Reliable detection of stiction is therefore essential for condition-based maintenance and improved operational performance. This study proposes a Hybrid Wavelet–Convolutional Neural Network (HW-CNN) framework for the detection of valve stiction in closed-loop systems. The approach employs the continuous wavelet transform (CWT) to generate time–frequency scalograms that preserve localized energy distributions associated with stick–slip behavior, including transient release events and sustained oscillatory patterns. These representations are subsequently processed using a fine-tuned deep residual neural network to enable automated feature extraction and classification. Unlike conventional signal-based or generic time–frequency learning approaches, the proposed framework is designed to retain control system-specific dynamics within the feature representation, thereby improving the separability of stiction-induced signatures under varying operating conditions. The methodology is evaluated using both simulated control loop data and real industrial datasets obtained from the International Stiction Database (ISDB), ensuring evaluation under controlled and practical conditions. To enhance reliability, performance metrics are reported as averages over repeated experimental runs. The results demonstrate that the proposed HW-CNN framework achieves an accuracy of 96.1% and an F1-score of 96.0% on simulated datasets, and 90.4% accuracy with an F1-score of 90.0% on industrial data. Additional analysis indicates that the model maintains consistent detection capability despite increased variability in real-world conditions. Furthermore, interpretability is supported through Grad-CAM analysis, which shows that the network focuses on physically meaningful regions within the scalograms corresponding to known stiction dynamics. The findings confirm that the integration of wavelet-based feature encoding with deep residual learning provides a robust and interpretable framework for valve stiction detection.
This article presents a computer vision-based approach to switching electric locomotive power supplies as the vehicle approaches a railway neutral section. Neutral sections are defined as a phase break in which the objective is to separate two single-phase traction supplies on an overhead railway supply line. This separation prevents flashovers due to high voltages caused by the locomotives shorting both electrical phases. The typical system of switching traction supplies automatically employs the use of electro-mechanical relays and induction magnets. In this paper, an image classification approach is proposed to replace the conventional electro-mechanical system with two unique visual markers that represent the ‘Open’ and ‘Close’ signals to initiate the transition. When the computer vision model detects either marker, the vacuum circuit breakers inside the electrical locomotive will be triggered to their respective positions depending on the identified image. A Histogram of Oriented Gradient technique was implemented for feature extraction during the training phase and a Linear Support Vector Machine algorithm was trained for the target image classification. For the task of image segmentation, the Circular Hough Transform shape detection algorithm was employed to locate the markers in the captured images and provided cartesian plane coordinates for segmenting the Object of Interest. A signal marker classification accuracy of 94% with 75 objects per second was achieved using a Linear Support Vector Machine during the experimental testing phase.