Automation and Remote Control最新文献

{"title":"Analysis of Multiview Integration Deep Learning Framework for Early Lung Disease Detection and Classification","authors":"Ashwini C. Gote,&nbsp;Mrudul Arkadi,&nbsp;Nilesh Ghavate,&nbsp;Pallavi V. Baviskar","doi":"10.1134/S0005117925601460","DOIUrl":"10.1134/S0005117925601460","url":null,"abstract":"<p>Detecting lung diseases through clinical diagnosis, particularly pneumonia, tuberculosis and COVID-19, a health problem of international importance, is one of the most important tasks for the detection of lung diseases. Current deep learning (DL) approaches have been effective in such scenarios, but at the same time have some drawbacks, like difficulty in capturing the location of illness through AI and others. In order to promote the widespread application of lung disorder diagnostics in medical facilities, the researchers present a novel MVIDL algorithm that takes advantage of multiview CXR images to obtain an extremely high accuracy level in lung disease detection and classification. The suggested approach incorporates the edges of the multiview CXR image into a deep convolutional network, thus enabling the acquisition of rich spatial or contextual information for a more comprehensive understanding of lung diseases, by the already existing methods. Besides, the use of multiview imaging in training gives rise to more generalized models, lowers the number of wrong predictions, and increases the robustness over a wider range of lung disease types. In addition, the proposed framework provides XAI mechanisms as part of its features to facilitate interpretability and build up clinical trust by making the decision process transparent with visual representations. The MVIDL system tackles the limitations of traditional single-view and nonexplainable deep learning methods, thus providing a scalable, interpretable, and clinically relevant pathway for lung disease detection and classification. The experimental outcomes confirmed that the MVIDL model really excelled all the other state-of-the-art representations very much, obtaining 99.72% test accuracy, 99.75% precision, 98.25% recall, and an F1-score of 98.97%. This study is a step towards the development of highly efficient, smart, and understandable diagnostic tools that will enable radiologists to make timely clinical decisions for the early detection of lung disorders.</p>","PeriodicalId":55411,"journal":{"name":"Automation and Remote Control","volume":"87 3","pages":"341 - 360"},"PeriodicalIF":0.5,"publicationDate":"2026-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148782605","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Research and Application of Ecological Logistics Model Based on System Dynamics","authors":"Ye Zhou,&nbsp;Chao Zhou,&nbsp;Hui Mao","doi":"10.1134/S0005117925601290","DOIUrl":"10.1134/S0005117925601290","url":null,"abstract":"<p>In response to the severe impact of energy consumption and carbon emissions on the ecological environment in the current logistics transportation process, a system dynamics-based ecological logistics model is developed based on the logistics transportation system of province H in China. Firstly, the current situation of the logistics industry in province H is analyzed, and the parameters and system boundaries of the ecological logistics model are determined. Secondly, ecological logistics models related to highways, railways, and waterways are constructed. Verification showed that the maximum difference between the ecological logistics model proposed in the study and the historical value simulation of province H was only 8.37%. Case analysis showed that reducing the proportion of road transportation and fuel use, increasing the use of clean energy, and investing in environmental protection could significantly improve the energy conservation and emission reduction efficiency of the logistics transportation industry. Under the optimal solution obtained by the model, the energy consumption and carbon emissions of logistics transportation in province H in 2026 would be reduced by 42.5 and 33.7%, respectively, compared to maintaining the current situation. The results indicated that optimizing the transportation structure, reducing the use of fuel energy, and increasing the application of clean energy could reduce the energy consumption and carbon emissions of the logistics transportation industry. The ecological logistics model constructed on the basis of system dynamics has great practical significance for the green, ecological, and environmentally friendly development of the logistics transportation industry.</p>","PeriodicalId":55411,"journal":{"name":"Automation and Remote Control","volume":"87 3","pages":"510 - 525"},"PeriodicalIF":0.5,"publicationDate":"2026-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148783037","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"BrainMorphNet (BMN): Multistage Hierarchical Attention Framework for Robust Brain Tumor Detection in MRI","authors":"Veena Janardhan Jadhav,&nbsp;Namita Kale,&nbsp;Deepali Pankaj Javale,&nbsp;Ranjana Gore","doi":"10.1134/S0005117925601423","DOIUrl":"10.1134/S0005117925601423","url":null,"abstract":"<p>The development of effective treatments and the improvement of patient survival rates depend heavily on the timely and precise diagnosis of brain tumors. Nevertheless, the current deep-learning methods have trouble generalizing, are prone to overfitting with small datasets, and are imprecise in identifying the subtle boundaries of tumors, all of which could limit their application in clinical settings. To tackle these concerns, this paper has introduced an innovative BrainMorphNet (BMN) structure which can automatically detect and categorize brain tumors on MRI images completely, hence overcoming these problems. The first step of the approach is the application of data-specific preprocessing to clear the images of artifacts and improve their quality. Afterwards, the multilevel feature extraction generates the global and local structures of the tumor regions simultaneously. Lastly, the framework applies adaptive attention mechanisms to spatial and contextual features and thus improve them. There is a very strong multiclass separation between gliomas, meningiomas, pituitary tumors, and nontumor cases, and the whole setup is such that cancers can be diagnosed at a particular place. Our rigorous testing on the Brain Tumor MRI and Figshare datasets gave a model accuracy of 0.993, precision of 0.985, and F1 score of 0.988. The system is a very effective and time-saving tool for brain tumor analysis automation, and it is a significant step towards more intelligent medical imaging and diagnostic systems. These impressive numbers show that BMN has good generalization and clinical reliability.</p>","PeriodicalId":55411,"journal":{"name":"Automation and Remote Control","volume":"87 3","pages":"361 - 383"},"PeriodicalIF":0.5,"publicationDate":"2026-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148783125","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analysis of Compiler-Level Static and Dynamic Features for Automated Bug Prediction Using Transformer Models","authors":"Veena Janardhan Jadhav,&nbsp;Prakash R. Devale,&nbsp;Nischal Puri,&nbsp;Priya Parkhi","doi":"10.1134/S0005117925601058","DOIUrl":"10.1134/S0005117925601058","url":null,"abstract":"<p>The rapid evolution of software systems has increased the complexity of codebases, making traditional bug detection and debugging techniques inefficient and resource-intensive. Automated bug prediction systems using cutting-edge machine learning (ML) and deep learning (DL) architectures have drawn a lot of attention in an effort to overcome this difficulty. However, the majority of current approaches rely on historical datasets or static code features, which fail to capture runtime behaviors and intermodule interactions that frequently result in failures. Many frameworks show severe computational overheads, lack scalability across big heterogeneous projects, and are restricted to particular programming languages or benchmark datasets. This paper suggests an integrated method that uses dynamic runtime features and static compiler-level features for thorough bug prediction to get over these restrictions. In this work, transformer-based hybrid models for automated bug prediction are used to analyze compiler-level static and dynamic information in depth. To examine their prediction skills across a variety of datasets, three frameworks: Rust-IR-BERT, nature-based ensemble prediction model, and hybrid CNN-LSTM were compared. To improve the accuracy of bug discovery, the suggested DynastBug framework combines static and dynamic analysis with transformer encoders and hybrid ensemble learning. It captures semantic relationships between code components, monitors execution flow, and leverages attention-based mechanisms to enhance feature representation. Experimental results demonstrated that DynastBug outperformed existing models with an accuracy of 99.2%, precision of 97.8%, recall of 97.3%, and F1-score of 99.3%. The results confirm that integrating compiler-level semantics with runtime behavior significantly improves generalization, reliability, and scalability in automated software bug prediction.</p>","PeriodicalId":55411,"journal":{"name":"Automation and Remote Control","volume":"87 2","pages":"198 - 215"},"PeriodicalIF":0.5,"publicationDate":"2026-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148614603","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Parameter-Variable Backstepping Control for a Mobile Robot with Two Time-Scale Filter","authors":"Haesong Ham,&nbsp;Hyok Jo,&nbsp;Juchon Han,&nbsp;Taechol Paek,&nbsp;Myonghak Jong,&nbsp;JongNam Kim","doi":"10.1134/S0005117925601319","DOIUrl":"10.1134/S0005117925601319","url":null,"abstract":"<p>Tracking the desired trajectory for mobile robots has been an important research topic. Trajectories are of different shapes and all the tracking of them are affected by the noises and disturbances. The robots should track such trajectories rapidly, but with no velocity jumps. In this paper, we used unscented Kalman filter (UKF) to reduce noises and proposed a parameter-variable backstepping controller (PVBC) with two time-scale (TTS) filter to avoid velocity jumps and reject disturbances. The unscented Kalman filter (UKF) effectively estimated postures of a mobile robot in noisy environments. The conventional backstepping controller (CBC), due to parameters fixed in no relation to its trajectory, had low responsiveness in transient-time tracking in case of rapid changes in the trajectory and often led to velocity jumps. The PVBC that can vary parameters along the trajectory improved the responsiveness of trajectory tracking and avoided velocity jumps compared to CBC. Combining PVBC and the TTS filter enabled more accurate tracking and disturbance rejection. The convergence of tracking error was guaranteed by Lyapunov stability analysis. Results showed that tracking trajectories for a mobile robot by using PVBC and TTS filter with UKF had improved both transient and steady-state performance in noisy environments.</p>","PeriodicalId":55411,"journal":{"name":"Automation and Remote Control","volume":"87 2","pages":"179 - 197"},"PeriodicalIF":0.5,"publicationDate":"2026-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148614598","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Droop Control-Based Optimization of Hybrid Renewable Energy Systems: Combining Node-Level Capsule Graph Neural Network with Artificial Protozoa Optimizer","authors":"D. Viji,&nbsp;D. Saranya,&nbsp;A. Srinivasan,&nbsp;B. Rajani","doi":"10.1134/S0005117925601204","DOIUrl":"10.1134/S0005117925601204","url":null,"abstract":"<p>Optimization of hybrid renewable energy systems (HRES) using droop control (DC): This research proposes the combination of node-level capsule graph neural network and artificial protozoa optimizer (NLCGNN-APO). First, data from the “Dataset for renewable energy systems” dataset is collected. The success of the proposed method is assessed using performance metrics such as rise time, settling time, and overshoot in contrast to other existing methods, such as droop control combined with a proportional-integral (Droop+PI) controller. Droop control with particle swarm optimization (droop+pso) tuned fractional order proportional-integral (fopi) controller, droop control with fractional order proportional-integral (Droop+FOPI) controller, artificial neural network-based adaptive proportional-integral controller (ANN-APIC), and conventional PI controller. The proposed APO-NLCGNN method achieves 0.078 s rise time, 0.052 s settling time and 0.98% overshoot. Overall, adaptive and optimized controllers outperform traditional droop-based solutions in reducing overshoot and enhancing system stability.</p>","PeriodicalId":55411,"journal":{"name":"Automation and Remote Control","volume":"87 2","pages":"261 - 278"},"PeriodicalIF":0.5,"publicationDate":"2026-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148614604","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Parameter Tuning of Quadrotor UAV Attitude Controller Based on Adaptive Catch Fish Optimization Algorithm","authors":"Wangwang Chen,&nbsp;Anjing Wei,&nbsp;Yue Wu,&nbsp;Liang Tao,&nbsp;Yaocong Hu,&nbsp;Bingyou Liu","doi":"10.1134/S0005117925601162","DOIUrl":"10.1134/S0005117925601162","url":null,"abstract":"<p>This paper proposes a novel adaptive catch fish optimization algorithm (ACFOA) for efficient tuning of controller parameters in the active disturbance rejection control (ADRC) system of quadrotor UAV. Firstly, a cascade ADRC attitude control architecture is constructed. Secondly, an improved fish optimization algorithm integrating adaptive weight and dynamic iteration count threshold is proposed. This algorithm enriches the exploitation strategy by introducing Cauchy distribution while realizing efficient exploration of parameter space through population diversity evaluation. Finally, to verify the stability and robustness of the tuned attitude controller, simulation comparisons of control performance before and after optimization are conducted. Experimental results demonstrate that the adaptive catch fish optimization algorithm not only enhances the step response speed and disturbance rejection capability of the attitude controller but also significantly improves parameter tuning efficiency.</p>","PeriodicalId":55411,"journal":{"name":"Automation and Remote Control","volume":"87 2","pages":"160 - 178"},"PeriodicalIF":0.5,"publicationDate":"2026-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148614599","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Study on the Realization of an Improved Adaptive Blend Station Ratio Control in PVA Production Process","authors":"Yong So,&nbsp;Jong Nam Kim,&nbsp;Song Min Kim,&nbsp;Song Il Pak,&nbsp;Song Il Ji","doi":"10.1134/S0005117925601265","DOIUrl":"10.1134/S0005117925601265","url":null,"abstract":"<p>Unlike other polymers, polyvinyl alcohol (PVA) is produced not by the polymerization of monomers, but by the saponification of polyvinyl acetate (PVAc). In PVA production process, precisely controlling the ratio of the raw material PVAc and the catalyst sodium hydroxide (NaOH) is a critical issue for improving product quality. This paper proposes an improved adaptive blend station ratio control method that accurately maintains a setting ratio even during transients due to changes in setpoint and external disturbances, as well as during dynamic changes in main and auxiliary loops. The effectiveness of the proposed method is verified through simulations and experiments applying it to a PVA production process.</p>","PeriodicalId":55411,"journal":{"name":"Automation and Remote Control","volume":"87 2","pages":"235 - 248"},"PeriodicalIF":0.5,"publicationDate":"2026-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148614311","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advanced Energy Distribution Management Using Droop Control: A Multiсomponent Attention GNN-GWO Approach","authors":"K. M. Vijayalakshmi,&nbsp;B. Rajani,&nbsp;Nancy Acharya,&nbsp;Jogendra Kumar","doi":"10.1134/S0005117925601307","DOIUrl":"10.1134/S0005117925601307","url":null,"abstract":"<p>Microgrids are increasingly embracing a wide range of sustainable power sources, like storage devices and energy sources like solar, wind, and tidal, to provide long-term and steady electricity delivery. However, because renewable energy sources are sporadic and unpredictable, voltage regulation and frequency stability are severely hampered, and efficient power distribution. To address these challenges, this study suggests an enhanced energy distribution management system that combines hybrid technology and droop control graph neural network-grey wolf optimization (GNN-GWO) technique. Microgrids are progressively incorporating several different types of renewable energy, such as wind, solar, and tidal power, as well as storage devices, to ensure long-term and consistent electricity supply. However, the erratic and sporadic character of renewable energy sources presents significant challenges for effective power distribution, frequency stability, and voltage management. To solve these issues, this paper presents a more effective energy distribution management system that includes droop control and a hybrid graph neural network-grey wolf optimization (GNN-GWO) technique.</p>","PeriodicalId":55411,"journal":{"name":"Automation and Remote Control","volume":"87 2","pages":"279 - 296"},"PeriodicalIF":0.5,"publicationDate":"2026-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148614601","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dynamic Analysis of Positional Errors in Free-Floating Space Robots Incorporating Joint Clearance and Backlash Phenomena","authors":"Kumar Abhishek,&nbsp;Vijay Kumar Dalla,&nbsp;Vitalram Rayankula","doi":"10.1134/S0005117925600806","DOIUrl":"10.1134/S0005117925600806","url":null,"abstract":"<p>The performance of space robot manipulators is strongly influenced by positional accuracy, structural integrity, and mechanical tolerances. Joint clearances in revolute and prismatic joints significantly affect both kinematic and dynamic behavior, leading to reduced accuracy. This study analyses the impact of joint clearance and backlash on the dynamic performance of a six-DOF free-floating space robot (FFSR). A numerical experimental model is developed incorporating clearances in all joints, and its end-effector positional deviations are compared with an ideal, clearance-free model. Additionally, joint torque variations and end-effector force fluctuations are evaluated. The results highlight how joint clearance and backlash degrade positional accuracy and overall dynamic performance.</p>","PeriodicalId":55411,"journal":{"name":"Automation and Remote Control","volume":"87 2","pages":"137 - 159"},"PeriodicalIF":0.5,"publicationDate":"2026-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148614160","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}