Nov 2026· Computer Science and Information Technology· 0 citations· 22 references
TL;DR
The proposed YOLOv5 detection and translation system can reliably automate circuit image-to-Boolean translation, bridging image recognition and symbolic computation, and demonstrates that the proposed system can reliably automate circuit image-to-Boolean translation, bridging image recognition and symbolic computation.
Abstract
Artificial intelligence (AI) has become an essential tool in solving complex problems effectively and efficiently. In digital electronics, translating logic gate circuits into Boolean functions can be challenging, especially for more complex structures. This study presents the design of a detection and translation system for logic gate images into Boolean functions using the You Only Look Once (YOLOv5) object detection model. A dataset of 800 images was collected using a smartphone camera under varied lighting conditions and preprocessing to ensure robustness. The dataset was divided into 70% for training, 20% for validation, and 10% for testing. Training was conducted using YOLOv5s with batch size 32, 100 epochs, and pre-trained weights. The trained model achieved strong results with an overall mean average precision (mAP@0.5) of 0.922, precision of 0.98, and recall of 0.984. The confusion matrix confirmed accurate detection across all classes, with minimal misclassification. Furthermore, the translator system successfully converted recognized objects into correct Boolean expressions, with results validated in multiple test cases. This demonstrates that the proposed system can reliably automate circuit image-to-Boolean translation, bridging image recognition and symbolic computation.
Handwritten character recognition is vital for document digitization and autonomous reading systems. This study focuses on enhancing handwritten Devanagari character recognition using deep learning models, specifically fine-tuned Convolutional Neural Networks (CNNs), combined with hybrid mathematical methods for image enhancement. Devanagari script, used for several South Asian languages, presents challenges due to its complexity and structural variations. To improve recognition accuracy, we propose a fuzzy-enabled Power-Law transformation for image enhancement, along with other techniques like Grunwald- Letnikov Fractional Differentiation (GLFD) and Atangana-Baleanu-Riemann (ABR). Experimental results show that the CNN model with Power-Law+ Fuzzy enhancement achieves the highest accuracy (98.02%), surpassing even MobileNetV2 (92.86%). The same method also yields impressive performance on the MNIST dataset (99.15% accuracy), demonstrating its effectiveness across different scripts. These findings highlight the benefits of integrating advanced preprocessing with deep learning for improved handwriting recognition, offering practical applications in multilingual document processing and OCR-based automation.
Akshara Sreenivasan, Vinodkumar Vinodkumar Arumugam, Sriramakrishnan Pathmanaban et al.· Chaos and Fractals· 0 citations
This study presents an easy-to-use system that can recognize and solve handwritten polynomial equations using a Convolutional Neural Network (CNN). To achieve this, we began by collecting digits and math symbols from various publicly available sources. We began with a dataset of around 30,000 samples, then converted the images to grayscale, inverted them, applied binary thresholding, and removed noise to clean them up. Individual symbols are then separated using OpenCV, and a custom-trained CNN model classifies each symbol. We used 16 classes to classify our data. To ensure the model’s ability to detect symbols increases and produces efficient results, we expanded our data set through data augmentation to over 100, 000 images. CNN, built using Keras, achieved an impressive 98.99% classification accuracy, reliably identifying each character during training. Once the symbols are recognized, they are combined to form a complete equation. For normal equations, the system uses the eval () function to evaluate expression, providing quick, dynamic solutions . For polynomial equations of up to the third degree, SymPy is utilized for symbolic computation, providing accurate and detailed solutions. The solution is presented through a PyQt5-based user interface, that allows users to upload their handwritten equations and view the solved results. The proposed method supports polynomial equations with variables and basic mathematical operators, providing an accurate and user-friendly educational tool. The system supports basic mathematical symbols (+, –, ×, =, x, y). It can handle polynomial equations up to the third degree, which will be beneficial for students learning algebra or for quick problem solving.
Anupa Gaire, Rohisha Shrestha, Rosha Prajapati et al.· Journal of Sciences and Engi...· 0 citations
Handwritten digit recognition remains useful for studying compact image-classification models, although the MNIST (Modified National Institute of Standards and Technology) benchmark is no longer sufficient for claiming state-of-the-art novelty. Accordingly, this study frames MNIST as a controlled setting for analyzing accuracy-efficiency behavior in lightweight convolutional neural networks (CNNs). It examines how optimizer choice, epoch count, data augmentation, and convolutional parameter settings jointly affect classification accuracy and execution time. The experimental design covers two 5-layer CNN configurations, five parameter-varying cases, eight named optimizer settings, one baseline control setting, five epoch values, and two augmentation conditions. In total, 540 paired observations of accuracy and execution time are analyzed. The results show that peak accuracy and practical efficiency lead to different conclusions. The best observed accuracy was 99.50% for the standard CNN-5LS configuration with Nadam at 120 epochs after augmentation, but this required 1,011 s. RMSprop reached 99.47% after augmentation at both 15 and 120 epochs in the standard configuration, while the 15-epoch setting required only 114 s. In the parameter-varied CNN-5L model, Case-1 was generally the most efficient and stable configuration, while wider dilation and stride combinations frequently reduced reliability. Data augmentation improved weak or unstable settings more strongly than already stable configurations, and Ftrl did not produce meaningful learning in these experiments. These findings suggest that lightweight CNN design for handwritten digit recognition should be evaluated through accuracy-time trade-offs, not only through maximum accuracy. The scope is practical configuration guidance within the MNIST experimental setting.
Muhammad Munsarif, Richmond Ampah-Mensah· Cureus Journal of Computer S...· 0 citations
Detecting out-of-distribution (OoD) data is a critical process in artificial intelligence models that specialize in critical systems that require accurate results, such as medical systems, air navigation systems, and financial transaction systems. Therefore, researchers in the field of neural network programming place great importance on OoD handling. OoD detection approaches aim to identify inputs that deviate from a model’s training distribution, preventing the overconfident and false predictions that neural networks suffer from. In this paper using Post-hoc scoring approaches which as selective classification gates to handle OoD in a classification convolutional neural networks CNN model. That model is supposed to implemented in a vending machine, it’s trained on a label dataset of the Iraqi currency, that model suffers from OoD because of the convergent probabilities of the mathematical model of the neural network. With this approach, test four types; four methods were chosen to prevent out-of-distribution for the CNN model, which are: Confidence, Entropy, Cosine similarity, and Mahalanobis distance. Mathematical calculations were performed for each method with the tested data for the model and found threshold value to make as gate to pass currency classes and reject non-currency classes. Then the results of these gates comparing and analysis, it was concluded that the most accurate method of handling OoD is the Mahalanobis distance, which handled the OoD in model on real data from 85.29% to achieve a high prediction accuracy of this model.
Shaymaa A. Hantoosh· Zanco Journal of Pure and Ap...· 0 citations
Handwritten digit recognition on the MNIST dataset routinely achieves near-perfect accuracy. However, deploying these models on edge platforms introduces new challenges where predictive accuracy is no longer the only metric that matters. For constrained systems, memory footprint, computational overhead, and inference latency are equally critical. In this work, they propose a multi-dimensional evaluation framework for deployment-oriented assessment. The authors introduce the Edge Suitability Score (ESS), a composite metric that combines normalized accuracy, model size, and inference speed into a single value, weighted at 0.40, 0.35, and 0.25, respectively, to reflect their relative importance for microcontroller deployment. By comparing two lightweight architectures, a scaled-down CNN (L-CNN) and a depthwise-separable L-MobileNet, against a deeper Baseline CNN, the results show that compact networks can maintain near-99% accuracy while drastically reducing storage and computation requirements: L-MobileNet achieves 99.10% accuracy with only 12,186 parameters and roughly 48 KB of weight memory, compared with 99.45% accuracy and over 1 MB for the baseline. This framework offers a practical methodology for selecting neural networks in real-world edge environments, bridging the gap between theoretical performance and actual deployability on resource-constrained hardware such as the STM32 and ESP32.
This study explores methods for combining fuzzy logic and convolutional neural networks (CNN) to improve image analysis when images are blurry, noisy, or have low contrast. Fuzzy logic is used to represent areas of imprecision in an image by assigning each pixel a degree of membership to different sets, while convolutional neural networks automatically detect important features and identify objects present. Thus, the paper proposes a hybrid Fuzzy-CNN method: pixels or visual features are first «fuzzified» in a logical sense to account for uncertainties, and then fed into the neural network. A defuzzification stage is then applied to the output to obtain a clear and interpretable final result. This approach enhances the reliability of tasks such as segmentation, classification, or image enhancement, particularly in medical or industrial contexts where image quality may be degraded. Tests conducted demonstrate that this hybrid strategy outperforms classical approaches based solely on fuzzy logic or CNN alone, providing higher accuracy and robustness to visual variations and uncertainties. Thus, it represents a solid foundation for more intelligent and adaptive image processing in challenging conditions.
L. Kruglova, R. Samb, F. Sisej· ИНФОРМАЦИОННЫЕ СИСТЕМЫ И ТЕХ...· 0 citations
