AUTOMATIC CONTROL AND COMPUTER SCIENCES最新文献

{"title":"Development of Centralized Multivariable Cascade Control Strategy for Quadcopter System","authors":"Vasanthakumar Sekar,&nbsp;K. Srinivasan","doi":"10.3103/S0146411626700409","DOIUrl":"10.3103/S0146411626700409","url":null,"abstract":"<p>In this article proposes a novel centralized cascade control framework for quadcopter attitude and trajectory tracking that explicitly suppresses secondary cross-coupling effects commonly observed in multivariable UAV dynamics. The nonlinear quadcopter model is transformed into a set of region-dependent linear MIMO state-space representations using a piecewise affine (PWA) formulation, and each region model is converted into a MIMO transfer-function form to support systematic multivariable controller synthesis. To avoid ad hoc loop selection, a hybrid loop-pairing method is introduced to identify feasible pairings and reduce unfavourable inner-loop interactions across operating regions. Based on this pairing, an IMC-based switching enhanced cascade PID/PI design is developed, employing an enhanced PID controller in the outer loop and an enhanced PI controller in the inner loop, with regionwise scheduling to maintain performance over the operating envelope. The proposed method (Ce) achieves the lowest ISE in both Simulation-1 and Simulation-2 for roll <span>(left( phi right))</span> and pitch <span>(left( theta right))</span>, showing consistent improvement over both De and Ge. The ISE reductions are 14.34 and 11.29% over De in Simulation-1, and 12.91 and 16.83% over De in Simulation-2 for roll and pitch, respectively, with even larger improvements over Ge. Extensive simulations demonstrate improved tracking accuracy with reduced coupling effects while satisfying state and input constraints. Comparisons with a decentralized cascade controller and a conventional cascade controller further confirm the effectiveness and efficiency of the proposed approach.</p>","PeriodicalId":46238,"journal":{"name":"AUTOMATIC CONTROL AND COMPUTER SCIENCES","volume":"60 2","pages":"143 - 163"},"PeriodicalIF":0.5,"publicationDate":"2026-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149023036","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Detection and Classification of Diabetic Retinopathy Using 3D Squeeze Net Architecture","authors":"D. Umamaheswari,&nbsp;N. Nachammai,&nbsp;S. Anita","doi":"10.3103/S0146411626700422","DOIUrl":"10.3103/S0146411626700422","url":null,"abstract":"<p>Large number of people is affected by the diabetic retinopathy disease. It results in vision impairment. Deep learning (DL) techniques are widely used nowadays for the screening and research of diabetic retinopathy (DR). Researchers have been utilizing the convolutional neural network (CNN) technique to detect the fundus in retinal images. The application of CNN helps to improving the accuracy to make things automated. Accurate classification of the affected part is a little tedious compared to the existing methods since accurate annotations are expensive. A notable success has been observed when using the squeeze net architecture to detect and classify diabetic retinopathy. A novel 3D squeezenet architecture has been proposed in this paper. Gaussian blurring and random shifting have been used to support the proposed 3D squeezenet method in classifying the affected part. A trustworthy classification can be obtained by reducing the excess fitting in the beginning itself by using data augmentation. This technique has the advantage of having less complexity and cost without compromising the results' accuracy. The findings demonstrate the high efficacy of the proposed methodology in the automated identification of diabetic retinopathy. Consequently, this contributes to a higher degree of prevention of visual impairment.</p>","PeriodicalId":46238,"journal":{"name":"AUTOMATIC CONTROL AND COMPUTER SCIENCES","volume":"60 2","pages":"176 - 190"},"PeriodicalIF":0.5,"publicationDate":"2026-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149023240","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Attention-Enhanced Deep Learning Framework for Automated Tea Bud Detection","authors":"Ranjithkumar Sakthivel,&nbsp;Ajith Nagaraj,&nbsp;Parthasarathy Velusamy,&nbsp;Saravana Kumar Ganesan,&nbsp;Manikandan Bose","doi":"10.3103/S0146411626700495","DOIUrl":"10.3103/S0146411626700495","url":null,"abstract":"<p>The tea industry faces persistent challenges from labor shortages and nonselective plucking, which affect both yield and quality. This study presents a computer vision framework for precise tea bud detection using a YOLOv9s architecture enhanced with a convolutional block attention module (CBAM). The research employed the teaRob dataset and implemented extensive data augmentation to overcome limited annotated images, increasing the training set by a factor of 2.95. The proposed model achieved 99% precision, 85.3% recall, an F1-score of 92.0%, and a mean Average Precision (mAP@50) of 80.6% under field conditions with complex backgrounds. The lightweight model, with 7.2 million parameters and an inference time of 10.2 ms per image on RTX A2000 GPU, demonstrates suitability for real-time agricultural applications. Robust evaluation through five-fold cross-validation confirmed model stability and generalization. These results indicate that integrating attention mechanisms into YOLOv9s significantly improves discrimination of fine-grained objects such as tea buds. The system enables practical deployment in automated harvesting, where accurate identification of pluckable buds is critical for operational efficiency and crop quality. The novelty of this work is demonstrated through the targeted integration of CBAM into the YOLOv9s backbone, which enhanced feature selectivity while maintaining computational efficiency. In addition, the implementation of a systematic augmentation pipeline effectively addressed the limitation of data scarcity by generating realistic variations without compromising semantic accuracy. The study further contributes by applying a rigorous evaluation protocol that combined cross-validation with complex field imagery, ensuring robustness and generalization.</p>","PeriodicalId":46238,"journal":{"name":"AUTOMATIC CONTROL AND COMPUTER SCIENCES","volume":"60 2","pages":"260 - 271"},"PeriodicalIF":0.5,"publicationDate":"2026-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149023241","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Indian Sign Language Recognition System Using GAN and Ensemble Based Approach","authors":"Rhuchita Shirude,&nbsp;Soumya Khurana,&nbsp;R. Sreemathy,&nbsp;Mousami Turuk,&nbsp;Jayashree Jagdale,&nbsp;Saurabh Chidrewar","doi":"10.3103/S0146411626700045","DOIUrl":"10.3103/S0146411626700045","url":null,"abstract":"<p>Sign language is the most prominent mode of communication for people who have hearing problems. Continuous sign language recognition is a poorly supervised job that involves identifying sign gestures with no prior knowledge of the temporal boundaries between consecutive signs. Most modern techniques focus on the extraction of visual features, with no use of text or contextual information to boost recognition accuracy. Furthermore, in the field of sign language recognition, the potential of deep generative models to generate realistic sign language images has not been examined in depth. To achieve that aim, the recognition system for Indian Sign Language is a novel approach for continuous sign language recognition using a generative adversarial network architecture. The system is trained on the self-created dataset, which includes numbers from 0 to 9, alphabets from A to Z, and 50 distinct words with static gestures. The proposed approach is based on the idea of using a generative adversarial network (GAN) to generate realistic sign language gestures, which are then used to train a recognition model. By training these networks together, the generator learns to produce increasingly realistic gestures, while the discriminator learns to distinguish between real and synthetic generators with increasing accuracy. The network architecture involves the use of deep convolutional generative adversarial network (DCGAN) and superresolution generative adversarial network (SRGAN), while the transfer learning algorithms used are ResNet-50, VGG-19, and AlexNet. The transfer learning algorithms enable the network to learn from pretrained models and achieve better accuracy in sign language recognition. Overall, the recognition system for Indian Sign Language is a promising approach for continuous sign language recognition. By using a combination of deep generative models and transfer learning algorithms, the network can accurately detect and translate sign language gestures into textual language. The proposed approach shows recognition accuracy of 92.5% and robustness, and it has the potential to improve the recognition of sign language gestures in real-world scenarios. This has the potential to greatly improve communication for individuals who are speech and hearing impaired.</p>","PeriodicalId":46238,"journal":{"name":"AUTOMATIC CONTROL AND COMPUTER SCIENCES","volume":"60 1","pages":"33 - 47"},"PeriodicalIF":0.5,"publicationDate":"2026-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148292374","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Studies on the Use of 5G RedCap Technology for Electric Power Communication Services","authors":"Gang Ma,&nbsp;Min Lu,&nbsp;Yawei Cao","doi":"10.3103/S014641162670001X","DOIUrl":"10.3103/S014641162670001X","url":null,"abstract":"<p>As 5G technology advances, particularly with the adoption of 3GPP Rel-16/Rel-17 standards, there is a growing need for terminal equipment in the field of power communication that has low power consumption, cheap cost, and high reliability. In order to meet the demands of medium- and low-speed IoT application scenarios, 5G RedCap (reduced capability) technology is a new type of 5G terminal defined in the Rel-17 version. It is especially suitable for industrial IoT, wearable devices, and other scenarios. By reducing terminal design complexity and system cost, 5G RedCap technology meets the needs of medium- and low-speed IoT application scenarios. In this context, this paper thoroughly studies the application of 5G RedCap technology based on 5G RedCap technology in electric power communication services, and explores its ability to support electric power business scenarios. This article first examines the communication needs of the power business and how well they align with 5G network slicing. It next suggests a 5G network slicing coupling model that is tailored to various power business scenarios. Second, the complexity reduction technology, power saving technology, and its identification method of 5G RedCap terminals are examined, and their power consumption optimization effect is evaluated, based on the current scenario of 1800 MHz spectrum allotment. In conclusion, this paper presents the particular needs for the integration of the 5G RedCap and the 4G electric power network along with the future access requirements of large-scale electric power terminals. It also designs multimode communication terminal equipment to enhance the security and efficiency of network access for the electric power system’s end equipment. The study’s findings demonstrate that terminal equipment’s energy economy and communication performance may be significantly enhanced by implementing 5G RedCap technology in electric power communication.</p>","PeriodicalId":46238,"journal":{"name":"AUTOMATIC CONTROL AND COMPUTER SCIENCES","volume":"60 1","pages":"1 - 10"},"PeriodicalIF":0.5,"publicationDate":"2026-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148292358","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hazard Identification Method for Distribution Networks Based on Generative Adversarial Networks","authors":"Donglai Tang,&nbsp;Yu Li,&nbsp;Peng He,&nbsp;Qiang Zhang,&nbsp;Yuan Ou,&nbsp;Lei Wu","doi":"10.3103/S0146411626700033","DOIUrl":"10.3103/S0146411626700033","url":null,"abstract":"<p>Addressing the issues of untimely discovery and low identification accuracy of hazards in China’s distribution networks, this paper introduces a hazard identification method for distribution networks based on generative adversarial networks (GANs). The method employs a modular design comprising three parts: hazard traveling wave acquisition, hazard location, and hazard type identification. The hazard traveling wave acquisition part uses wavelet transform to extract the waveform of the initial hazard wave and records the arrival time at the device. The hazard location part improves the dual-end traveling wave location method to determine the hazard location, enhancing location accuracy. The hazard type identification part uses affinity propagation to cluster the hazard traveling waves, obtaining classification features of the hazard traveling waves, and then identifies distribution network hazards through GANs. Finally, the method was applied to a distribution network in a certain region, achieving a hazard identification accuracy of 81.3%. The identification results validate the effectiveness of the proposed method.</p>","PeriodicalId":46238,"journal":{"name":"AUTOMATIC CONTROL AND COMPUTER SCIENCES","volume":"60 1","pages":"24 - 32"},"PeriodicalIF":0.5,"publicationDate":"2026-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148292372","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Robust Identification Algorithm of Network Communication Signals via Machine Learning Model","authors":"XinMing Fan,&nbsp;Lijie Zhou,&nbsp;Weihai Yu,&nbsp;Peng Sun","doi":"10.3103/S0146411626700112","DOIUrl":"10.3103/S0146411626700112","url":null,"abstract":"<p>The identification of network signals is one of the important factors that affect the communication processing and control effect, but anomalies and errors often occur in applications. With the development of artificial intelligence technology, this paper automatically identifies computer network communication based on a machine learning model. We use the support vector machine model for simulation and solve the problem of overlearning through parameter optimization. Using the feature parameters obtained, the support vector machine and radial basis function neural network model are used to classify the modulated signals. The experimental results show that the performance of the support vector machine is better than that of the radial basis function neural network. The network communication signal has good performance under high SNR. However, at low SNR, the former still has a high accuracy, while the latter has a serious performance degradation. Therefore, the support vector machine model is considered to be more robust when applied to computer network communication signals.</p>","PeriodicalId":46238,"journal":{"name":"AUTOMATIC CONTROL AND COMPUTER SCIENCES","volume":"60 1","pages":"105 - 119"},"PeriodicalIF":0.5,"publicationDate":"2026-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148292359","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analysis Model of Students Learning Behavior Based on Extreme Random Forest Classification Algorithm","authors":"Yan Yang,&nbsp; Yi Qu","doi":"10.3103/S0146411626700124","DOIUrl":"10.3103/S0146411626700124","url":null,"abstract":"<p>With the continuous development of information technology, under the existing teaching environment and the degree of informationization, relying only on teachers to pay attention to each student’s learning situation is not able to accurately analyze the students' status. To solve this issue, the study suggests a hierarchical multilabel classification technique based on clustering relationships. Using the integration principle, the clustered clustering tree is built as a random forest classification model after the labels in the sample set are clustered using the K-mean clustering method. Moreover, the random forest classification model is improved to address the problem of reduced classification effect caused by the increased randomness of the decision tree. The outcomes indicated that the accuracy of the multilabel classification algorithm with clustered relationships was 95.6%, the false alarm rate was 2.3%, the F1 value was 0.97, and the root-mean-square error value was 0.12 at a training set size of 800. The accuracy of the random forest algorithm, the K-nearest neighbor algorithm, and the adaptive extreme random forest classification algorithm models were 0.49, 0.61, and 0.75 at a training set size of 1000, respectively. At a validation set size of 500, the accuracy of the three algorithm models was 0.41, 0.47, and 0.64, respectively. The outcomes demonstrated that the proposed improved algorithmic model has a better performance compared to other methods, which can improve the level of education informatization and promote the intelligent development of education and teaching.</p>","PeriodicalId":46238,"journal":{"name":"AUTOMATIC CONTROL AND COMPUTER SCIENCES","volume":"60 1","pages":"120 - 131"},"PeriodicalIF":0.5,"publicationDate":"2026-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148292371","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Traditional Chinese Medicine Tongue Image Intelligent Recognition Model Combining Attention Mechanism and Convolutional Neural Network","authors":"Hongbo Chu,&nbsp;Qihang Wu,&nbsp;Ming Xu,&nbsp;Dongmei Li","doi":"10.3103/S0146411626700069","DOIUrl":"10.3103/S0146411626700069","url":null,"abstract":"<p>To solve the issues of low recognition efficiency and high feature extraction error rate in the current intelligent recognition models of tongue images in traditional Chinese medicine, this study uses attention mechanism to improve the convolutional neural network algorithm. Moreover, based on an improved algorithm, it constructs a new intelligent recognition model for traditional Chinese medicine tongue images to improve the accuracy of tongue image recognition. In the comparative experiment of the improved algorithm, the algorithm had the highest classification accuracy, the fastest calculation speed of 6.3bps, and the lowest space occupancy rate of only 23.1%. The overall performance was much higher than that of the comparative algorithm. The experimental results on the intelligent recognition model of traditional Chinese medicine tongue images based on improved algorithms validated that the recognition error rate was the lowest at only 1.2%, and the recognition time was also the shortest at only 1.2 s. Additionally, after recognition by the model, the diagnostic accuracy of doctors reached 97.5%. The above experiments indicate that the proposed intelligent recognition model for tongue images can improve the recognition efficiency and accuracy of tongue image feature extraction, thereby enhancing the diagnostic accuracy of doctors for patients’ diseases.</p>","PeriodicalId":46238,"journal":{"name":"AUTOMATIC CONTROL AND COMPUTER SCIENCES","volume":"60 1","pages":"48 - 59"},"PeriodicalIF":0.5,"publicationDate":"2026-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148292356","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hybrid Machine Learning Approach for Phishing URL Detection","authors":"Pachipala Yellamma,&nbsp;Vijaya Chandra Jadala,&nbsp;Penugonda Mohan Krishna,&nbsp;D. Srinivasa Rao,&nbsp;V. V. R. Maheswara Rao,&nbsp;Prakash Bethapudi","doi":"10.3103/S0146411626700021","DOIUrl":"10.3103/S0146411626700021","url":null,"abstract":"<p>As phishing attacks on unsuspecting online users become a high priority task and recognition of phishing URLs has become a critical concern now. Although machine learning (ML) methods have shown potential in detecting phishing URLs, deep learning (DL) algorithms offer the added benefit of automatically extracting features and handling large datasets more efficiently. The Proposed work analyzed various deep learning algorithms, including decision tree, CNN, RNN, NLP, and ANN. A goal of the suggested approach is to integrate recurrent neural networks (RNN) with decision tree techniques to attain high precision in detecting Phishing URLs. Phishing attacks pose a major risk by tricking users into disclosing confidential information on websites that appear legitimate, leading to possible data breaches and financial damage An Identifying the need for robust and accurate detection methods, our study aimed to develop an effective approach to distinguish between trustworthy and fraudulent URLs, protecting consumers from becoming targets of phishing scams. Our comparison of several deep learning algorithms found that the RNN-decision tree hybrid model determined better results in correctness and effectiveness. This model attained high recall, F1-score, accuracy, and precision. The proposed work results demonstrate its efficacy, identify phishing URLS, and explain how it can be applied to lessen the danger of phishing scams.</p>","PeriodicalId":46238,"journal":{"name":"AUTOMATIC CONTROL AND COMPUTER SCIENCES","volume":"60 1","pages":"11 - 23"},"PeriodicalIF":0.5,"publicationDate":"2026-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148292357","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}