SJEE

Implementation of Serial Peripheral Interface Slave Device Based on Uncommitted Logic Arrays

Alexander Sinyukin — 2025-03-11

Microcontrollers and microprocessors link to peripheral devices (sensors, converters, transceivers, memory modules) via communication interfaces. One of the most widespread interfaces is the Serial Peripheral Interface (SPI), characterized by simplicity, energy efficiency, and high-speed performance. The purpose of the study was to design an SPI bus Slave device based on uncommitted logic arrays technology. Uncommitted logic arrays are integrated circuit technology that is intermediate between full-custom integrated circuits and programmable logic devices in terms of power consumption, dimensions, development, and manufacturing cost. The SPI Slave device was designed using the computer-aided design system Kovcheg dedicated to the chosen technology. Layout synthesis using Kovcheg can be executed based on a circuit developed with a built-in graphics editor or based on structural descriptions in the Verilog hardware description language. A technique of digital device design using Kovcheg based on behavioral descriptions is proposed to optimize the design process. The SPI Slave device was manufactured, and experimental results of the fabricated microchip agree well with simulation results. The device is able to work properly at clock frequency up to 5 MHz. Tests of speed performance, interference resistance, and ability to operate at different voltage levels were carried out. Attained results imply that the proposed device can function as an SPI Slave unit to communicate control devices with embedded peripherals.

Scheduling of Home Energy Management Systems for Price-Based Demand Response and End-Users Discomfort Reduction

Gholam-Reza Kamyab — 2025-03-12

The home energy management system (HEMS) can effectively participate in price-based demand response programs, significantly reducing electricity costs by optimizing the usage times of shift-able household appliances such as washing machines, dishwashers, and others. However, this optimization may compromise the comfort of the residents. In this paper, a discomfort index is proposed based on the time intervals between the start and end of the operation periods of these shift-able appliances relative to their residents' preferred usage times. The problem of optimal scheduling for these appliances is then modeled as an optimization problem aimed at minimizing the weighted sum of the daily household electricity bill and the discomfort index. A constraint is imposed to restrict the discomfort index to a maximum allowable level. This optimization problem is solved using a simulated annealing algorithm across various scenarios with different maximum allowable values for the discomfort index. The simulation results indicate that, among the optimal schedules across the scenarios, the most cost-effective demand response schedule can be identified based on the marginal reductions in the daily household electricity bill. This approach ensures substantial decreases in electricity expenses while avoiding unnecessary increases in the discomfort index.

Enhanced SEP Protocol Based on Fuzzy Logic with Dynamic Threshold to Improve the Lifetime of WSNs

Mohammed Adnan Altaha — 2025-03-12

: Stability and energy efficiency are the key factors that determine how well a Wireless Sensor Networks (WSNs) can perform and last. A Static Election Protocol (SEP) was developed to tackle this problem by selecting stable nodes as cluster heads; however, this protocol depends on random selection, which may cause an uneven energy distribution in the network. To address this problem, a new and improved version of SEP called SEP-FLDT is proposed. In order to optimize the cluster head decision and allow for cluster head switching over time, SEP-FLDT uses fuzzy logic coupled with a dynamic threshold mechanism. Comparison experiments are carried out with existing protocols like LEACH and SEP to prove the efficacy of SEP-FLDT. It is shown that the use of fuzzy logic combined with a dynamic threshold mechanism will lead to better evaluations for optimal clusters, therefore ensuring periodic changes in their selection as well as identifying a set of optimal cluster heads that maximize stability in terms of connectivity. Experimental results from performance evaluations demonstrate improvements in all aspects, such as energy efficiency, connectivity, stability and overall network performance, compared to other methods such as the LEACH and SEP protocols.

Advancing Road Maintenance with EfficientDet-based Pothole Monitoring

Archpaul Jenefa — 2025-03-12

Effective road maintenance is crucial for ensuring safe and efficient transportation but is often compromised by the widespread occurrence of potholes. This study introduces a novel approach using an EfficientDet-based model for sophisticated pothole monitoring. Potholes pose a significant hazard that requires proactive detection and timely resolution. Traditional detection methods frequently fall short in terms of accuracy and real-time capability. Addressing these limitations, our research leverages the EfficientDet architecture, known for its optimal balance of accuracy and computational efficiency, to enhance the detection and monitoring of potholes. We utilized a carefully curated dataset from Kaggle, which includes 1,500 training images, 1,000 validation images, and 500 test images, encompassing a variety of real-world pothole scenarios. This diversity enables the model to generalize effectively across different conditions. Our experimental evaluations demonstrate that the EfficientDet-based model achieves an impressive average precision of 0.90 and a robust recall of 0.92, highlighting its capacity for accurate and swift pothole detection-an essential component for improving road maintenance. Moreover, we provide a comparative analysis with five contemporary pothole detection algorithms: YOLOv5, RetinaNet, CenterNet, SSD, and Faster R-CNN, among which EfficientDet consistently shows superior performance in terms of precision, recall, F1-Score, and average precision. These findings highlight the significant advancements in road safety, infrastructure management, and resource optimization. By adopting sophisticated deep learning techniques like EfficientDet, we promote a transformative improvement in road maintenance practices, paving the way for more resilient, safe, and disruptionminimized transportation networks.

Energy Efficient Design and Implementation of Approximate Adder for Image Processing Applications

Jatothu Brahmaiah Naik — 2025-03-12

Approximate computing is a new technique that promises to speed up computations while preserving a level of precision suitable for error-tolerant systems such as neural networks and graphics. At the edge, a lot of computationally complex methods are now in use. As such, designing quick and low-energy circuits is crucial. This work presents a novel approximate full adder approach that lowers power consumption and delay at the expense of some output mistakes. To achieve these objectives, the proposed full adder architecture makes use of fundamental gate logic reduction techniques. Evaluations based on the Intel FPGA synthesis tool indicate that the suggested adder surpasses state-of-the-art techniques in terms of power, speed, and propagation delay. The design parameters – area, power dissipation, and latent characteristics of proposed adder are verified by simulation using EDA tools. The results demonstrate that our proposed approximate adder runs faster and requires fewer logic components than earlier equivalent systems. The synthesis reports testify to the fact that compared to other adders currently in use, the suggested adder used less logic elements. Furthermore, suggested approximation adders were used to execute image additions. Using image addition, the image quantitative statistics are used to application-level accuracy metrics analysis. Quantitative results confirm the superior functioning of the full adder cell approximation over comparable models.

Machine Learning for Early Diabetes Screening: A Comparative Study of Algorithmic Approaches

Adem Korkmaz — 2025-03-12

Diabetes mellitus, a chronic metabolic disorder, poses a significant global health challenge. Early screening and risk assessment are crucial for effective management and prevention. This study evaluates the performance of various machine learning models – Artificial Neural Networks (ANNs), Random Forest (RF), k-nearest Neighbors (k-NN), and Support Vector Machine (SVM) – in screening diabetes risk using a dataset based on patient-reported symptoms such as age, gender, polyuria, polydipsia, and sudden weight loss. The dataset, comprising self-reported data from 520 individuals, highlights the potential association of specific symptoms and demographics with diabetes risk. Rigorous analysis demonstrates the superior performance of the RF model in terms of accuracy and F1 Score. Feature importance analysis further emphasizes the critical role of patient-reported symptoms in assessing predisposition to diabetes. The findings suggest that with its robust predictive capability, RF is particularly suitable for early screening, offering valuable insights into symptom-based diabetes risk assessment. This research advances non-invasive, symptom-based screening tools, paving the way for early interventions and tailored prevention strategies.

Designing a New Tomato Leaf Disease Classification Framework using RAN-based Adaptive Fuzzy C-Means with Heuristic Algorithm Model

Rongali Divya Kanti — 2025-03-12

In tomato production, one of the most significant problems is the identification of Tomato Leaf Disease (TLD). Plant leaf disease is the primary factor that influences both the quality and quantity of crop production. India holds the second position in tomato making. However, multiple diseases contribute to the decline in the quality of tomatoes and the decrease in crop yield. Hence, it is important to accurately categorize and diagnose the tomato plant leaf infection. The productions of tomatoes are impacted by many leaf diseases. Early recognition of the diseases helps to reduce the disease infection and improve the yield of crops. Certain diseases are identified and шlassified using several methods. Therefore, the TLD classification and identification model is developed to solve the above problems. The images related to tomato leaves are aggregated in the initial phase through online sources. Then, the images are forwarded to the pre-processing phase. Further, the pre-processed image is given to the segmentation process, where the Adaptive Fuzzy C-Means (AFCM) technique is utilized. Meanwhile, the parameters of the AFCM algorithm complicate the cluster assignment in the presence of outliers or noise, thus resulting in reduced clustering performance. So, the parameters of AFCM are tuned by utilizing the new improved algorithm named Dingo Optimization Algorithm (DOA) to improve the clustering accuracy. It is done by assuming the AFCM parameters as a population of Dingoes and the maximum classification accuracy as its fitness function. Finally, the segmented images are fed to the classification process, where the Residual Attention Network (RAN) is used to attain the classified outcomes. Therefore, the investigated system shows a more efficient TLD prediction rate compared to traditional techniques in the experimental investigation. The results from the experiments indicate that the suggested models exhibit exceptional classification performance, achieving an accuracy rate of 95.22%. Therefore, the model suggests advancement in predictive capabilities over traditional methods.

Corrigendum on: Enhancing Heart Disease Prediction Accuracy by Comparing Classification Models Employing Varied Feature Selection Techniques

Alenka Milovanović — 2025-02-28