Computers & Electrical Engineering最新文献

{"title":"Hardware architecture of efficient image dehazing technique for advanced driving assistance system","authors":"Harish Babu Gade ,&nbsp;Appala Raju Uppala ,&nbsp;Purushotam Naidu Karri ,&nbsp;Renuka Devi Sinduvala Mallesh ,&nbsp;Venkata Krishna Odugu ,&nbsp;Janardhana Rao B","doi":"10.1016/j.compeleceng.2025.110493","DOIUrl":"10.1016/j.compeleceng.2025.110493","url":null,"abstract":"<div><div>Advanced Driving Assistance Systems (ADAS) rely on clear visual input, making robust image dehazing essential for safety and reliability. This paper presents a low-complexity, hardware-efficient image dehazing solution based on the Dark Channel Prior (DCP). The proposed architecture includes three key modules: Approximate Transmission Map Estimation (TME), Atmospheric Light Estimation (ALE), and Scene Recovery Module (SRM). Each component is optimized for real-time processing and implemented in Verilog Hardware Description Language (HDL). The complete system is synthesized and validated on the Zynq 7000 series Field Programmable Gate Array (FPGA) platform. Furthermore, the design is synthesized using 45 nm Complementary Metal Oxide Semiconductor (CMOS) technology via Cadence Genus to evaluate actual chip-level parameters such as area, power consumption, and delay. Experimental results demonstrate that the proposed design achieves high image quality with improved Structural Similarity Index (SSIM), Peak Signal-to-Noise Ratio (PSNR), and lower Mean Square Error (MSE) compared to existing methods. Furthermore, the hardware architecture offers substantial efficiency gains, with Area-Delay Product (ADP) reductions ranging from 0.801 % to 91.16 %, and Power-Delay Product (PDP) reductions from 6.67 % to 93.56 % over prior works. These results indicate that the proposed solution is well-suited for integration in real-time embedded vision applications such as ADAS.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"126 ","pages":"Article 110493"},"PeriodicalIF":4.0,"publicationDate":"2025-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144231544","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"A weighted Gompertz fuzzy ranking-based ensemble model for diabetic foot ulcer detection in skin and thermal imagery","authors":"Kamran Amjad ,&nbsp;Sohaib Asif ,&nbsp;Zafran Waheed ,&nbsp;Muhammad Ali Khalid ,&nbsp;Ying Guo","doi":"10.1016/j.compeleceng.2025.110475","DOIUrl":"10.1016/j.compeleceng.2025.110475","url":null,"abstract":"<div><div>Diabetic Foot Ulcers (DFUs) pose a significant health risk, often leading to severe complications in diabetic patients. Early and accurate detection of DFUs is crucial for effective intervention and management. This paper introduces an innovative ensemble methodology that leverages a weighted Gompertz function-based fuzzy ranking strategy for accurate and reliable DFU detection. The proposed technique adopts an ensemble framework where the weighted Gompertz function forms fuzzy rankings for the three fundamental classifiers, and their decision scores are integrated to yield final predictions on test cases. The ensemble model is constructed using three transfer learning-based models: InceptionV3, MobileNet, and InceptionResNetV2, which generate decision scores that are subsequently fused. The method showcases remarkable enhancements in classification accuracy, thoroughly evaluated on a dataset of 1055 foot images. Grad-CAM analysis showcases the models' focus on relevant regions, while ablation studies and comparison with the traditional ensemble method confirm our approach's reliability. These results highlight the crucial significance of hyperparameter tuning in enhancing model performance. Furthermore, our ensemble's efficacy extends to thermal imagery domains, validated by experiments on a diverse dataset comprising thermal images of diabetic foot cases. This adaptability across imaging modalities positions our methodology as a useful diagnostic tool, potentially aiding medical practitioners in efficiently detecting diabetic foot ulcers in both skin and thermal imagery domains. The proposed approach achieves an accuracy of 99.53 % on the initial dataset of foot images and attains a remarkable accuracy of 93.60 % on a separate dataset comprising thermal images. By improving diagnostic accuracy and adaptability, this approach can facilitate early DFU detection, reducing the risk of complications and enhancing patient outcomes.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"126 ","pages":"Article 110475"},"PeriodicalIF":4.0,"publicationDate":"2025-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144222307","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"Hybrid medical image encryption with compression framework for Internet of Medical Things","authors":"Anandbabu Gopatoti ,&nbsp;James Stephen Meka ,&nbsp;Poornaiah Billa","doi":"10.1016/j.compeleceng.2025.110443","DOIUrl":"10.1016/j.compeleceng.2025.110443","url":null,"abstract":"<div><div>Patient medical data’s security, storage, and transmission are critical challenges in healthcare systems, especially in the Internet of Medical Things (IoMT) environments. The vulnerability to attacks, higher computational costs, and loss of diagnostic quality are most often failures of the conventional encryption methods due to an imbalance between security and imperceptibility. This work focuses on developing a hybrid medical image encryption and compression (HMIEC) framework that uniquely integrates encryption, compression, and watermarking to address these issues. Initially, Improved Henon Chaotic Map Encryption (IHCME) was applied on the source image, which provides higher security. Then, the preprocessing operation is performed on the cover image, which converts the color space of the cover image. Further, the Discrete Karhunen–Loève Transform (DKLT) is applied to preprocessed and encrypted images. Moreover, a naturally inspired gray wolf optimization (GWO) algorithm selects the optimal embedding coefficients. Further, medical image embedding is performed using a GWO-based optimal embedding strength factor, where the preprocessed image hides the encrypted image and generates a watermarked image. Finally, a post-processing operation is performed on the watermarked image to generate a smoother watermarked image. The proposed HMIEC system resulted in improved peak signal-to-noise ratio (PSNR) by 77.04 dB, entropy of 41.923, mean square error (MSE) of 0.001283, structural similarity index metric (SSIM) of 0.991, normalizer correlation coefficient (NCC) of 0.992, compression ratio (CR) of 21.955%, the unified average change in intensity (UACI) of 99.60%, and the number of pixels change rate (NPCR) of 33.46% as compared to existing watermarking and security systems.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"126 ","pages":"Article 110443"},"PeriodicalIF":4.0,"publicationDate":"2025-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144222309","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"Multi objective framework for optimal allocation of electrical fast charging stations using enhanced slime mould algorithm","authors":"Abdelmonem Draz,&nbsp;Ahmed M. Othman,&nbsp;Attia A. El-Fergany","doi":"10.1016/j.compeleceng.2025.110489","DOIUrl":"10.1016/j.compeleceng.2025.110489","url":null,"abstract":"<div><div>In this paper, a novel optimization methodology based on single and multi-objective formulation is proposed for optimal allocation of electric fast charging stations (EFCSs). The suggested methodology is planned for selecting the optimal candidate buses to supply the EFCSs in mesh transmission networks. Moreover, the algorithm locates the EFCSs geographically by determining the service line length of the connecting cable between the EFCS and the candidate bus. Afterwards, this problem is solved using the enhanced slime mould algorithm (ESMA) characterized by a novel searching technique, adaptive grouping strategy, and efficient learning operator. The adapted objective aims to minimize the summation of voltage deviations at all buses due to the high-power demand of EFCSs. Additionally, another objective is formulated concerning the line stability aspect and solved using the multi-objective version of SMA (called MOSMA). Finally, the problem gets more comprehensive by incorporating an economic perspective of minimizing the total running energy cost during the whole charging process. It is worth mentioning that the proposed ESMA’s performance is validated and compared with other competitors such as the traditional SMA, particle swarm optimizer, and osprey optimization algorithm. In all cases, the ESMA outperforms all other competitors by attaining the minimum objective function values satisfying all the operational constraints. Using the computed metrics for each simulation set, the outcomes of the multi-objective particle swarm optimizer and the multi-objective water cycle algorithm are compared to the proposed MOSMA. Highlighting some results, the MOSMA achieves total voltage deviations of 14.9 % and energy cost of $4109.55 in the IEEE 14-bus benchmark test case. Undoubtedly, the MOSMA establishes its superiority in solving this complicated optimization problem either in 2-D or 3-D objective formulations.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"126 ","pages":"Article 110489"},"PeriodicalIF":4.0,"publicationDate":"2025-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144213045","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"Fire hawks optimized radial basis function neural network based feature extraction and ON/OFF detection of household appliances","authors":"Deepika Rohit Chavan,&nbsp;Dagadu Shankar More","doi":"10.1016/j.compeleceng.2025.110441","DOIUrl":"10.1016/j.compeleceng.2025.110441","url":null,"abstract":"<div><div>Accurate ON/OFF detection of household appliances is essential for smart energy monitoring, lowering costs, and improving energy efficiency in smart homes. However, existing ON/OFF detection methods have several challenges, such as high computational complexity, overfitting and overlapping power usage patterns, which lead to false classifications and reduced performance. This study proposes a novel hybrid method combining a Fire Hawks optimized radial basis function neural network (FH_RBFNN) in order to extract and detect ON/OFF status at the source end of a residential building. The Fire Hawks Optimization Algorithm (FHO) is employed to fine-tune Radial Basis Function Neural Network (RBFNN) layer parameters, which ensures effective feature extraction by reducing redundancy. Subsequently, the Xtreme Gradient Boosting (XGBoost) technique is employed to classify the extracted features in order to identify the ON/OFF stage of house appliances. The proposed FH_RBFNN+ XGBoost model achieves high detection performance in terms of accuracy of 0.995, Precision of 0.99324, Recall of 0.99606, F1-Score of 0.99465, and Specificity of 0.99067, respectively.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"126 ","pages":"Article 110441"},"PeriodicalIF":4.0,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144213046","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"Optimal allocation of distributed power in adaptive droop controlled isolated DC microgrid under renewable energy intermittency and uncertainty using fuzzy logic controllers","authors":"Alankrita,&nbsp;Avadh Pati,&nbsp;Nabanita Adhikary","doi":"10.1016/j.compeleceng.2025.110445","DOIUrl":"10.1016/j.compeleceng.2025.110445","url":null,"abstract":"<div><div>This study presents an innovative adaptive droop control framework based on Interval Type-2 Fuzzy Logic Control (IT2FLC) for co-ordinated control and DC link stability of multiple Renewable Energy Systems (RES) during heavy transient in varying operating conditions in DC Microgrid (DC MG). The proposed method integrates voltage and current loop in primary layer into one unit based on adaptive droop characteristics, reducing controller complexity and tuning requirements. Voltage and current error are simultaneously used to restore DC link voltage and correct current sharing errors. Additionally, uncertainties in system parameters are incorporated as uncertainty in the degree of membership of FLC. The system integrates different RES namely, Photo-Voltaic (PV) array, Wind Turbine (WT), and Energy Storage System (ESS), and carries out comparative study against traditional PI through multiple case studies. Simulation results demonstrate superior performance of the proposed IT2FLC, achieving up to 14.5% improvement in power regulation under environmental variations and 15.5% better resilience to communication errors compared to PI control. Further testing on an OPAL-RT real-time simulator confirms that the controller maintains robust power delivery across varying operational scenarios, consistently outperforming conventional controllers in stability and precision.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"126 ","pages":"Article 110445"},"PeriodicalIF":4.0,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144204051","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"Ownership protection of deep learning models using watermarking","authors":"Md. Ishfaque Ahmed ,&nbsp;Kedar Nath Singh ,&nbsp;Himanshu Kumar Singh ,&nbsp;Amit Kumar Singh ,&nbsp;Amrit Kumar Agrawal","doi":"10.1016/j.compeleceng.2025.110481","DOIUrl":"10.1016/j.compeleceng.2025.110481","url":null,"abstract":"<div><div>Deep learning (DL) models have achieved remarkable success in the multimedia domain. However, the potential misuse of these powerful models poses significant challenges in many security-sensitive domains. To address this issue, digital watermarking schemes have emerged, aiming to embed watermark information into DL models to prove copyright ownership. In this paper, we propose a copyright protection scheme for DL models to resolve ownership conflicts and enhance overall system security. Initially, we generate two different watermarks using chaotic and Gold sequences. The generated watermarks are then embedded into selected layers of the DL model using redundant discrete wavelet transform and singular value decomposition. After the watermarking process, we shuffle the model’s weights before sharing it with a third party. On the receiver’s side, the inverse of the embedding process, followed by watermark verification, ensures secure access to authentic and unaltered model data. Ownership analysis shows that the proposed scheme is robust against pruning and fine-tuning attacks. Experimental results further validate the effectiveness of the proposed scheme compared to other competitive approaches.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"125 ","pages":"Article 110481"},"PeriodicalIF":4.0,"publicationDate":"2025-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144195577","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"Attentive deep learning with Randomized Vector Energy Least Square Twin Support Vector Machine for Alzheimer’s Disease diagnosis","authors":"Manish Kumar ,&nbsp;Bambam Kumar ,&nbsp;Prabhat Sharma ,&nbsp;Rahul Sharma ,&nbsp;Mujahed Al-Dhaifallah ,&nbsp;Adnan Shakoor","doi":"10.1016/j.compeleceng.2025.110412","DOIUrl":"10.1016/j.compeleceng.2025.110412","url":null,"abstract":"<div><div>Alzheimer’s Disease (AD), the most common form of dementia, progressively deteriorates cognitive functions, emphasizing the importance of early and accurate diagnosis for effective treatment and management. This study proposes an advanced framework combining neuroimaging and machine learning to enhance the diagnostic precision of AD. Leveraging T1-weighted structural Magnetic Resonance Imaging (MRI) scans, the model employs a 10-layer Residual Network (ResNet) integrated with a multi-head attention mechanism to extract high-resolution features from sagittal slices, focusing on critical regions such as the hippocampus and amygdala. These features are classified using the Randomized Vector Energy Least Square Twin Support Vector Machine (RV-ELSTSVM), a novel classifier designed to improve generalization by employing randomized feature transformations and energy-based regularization. Tested on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset, the proposed framework demonstrates superior performance, achieving classification accuracies of 94.38% for CN vs AD, 88.88% for CN vs MCI, and 92.88% for MCI vs AD. By surpassing existing state-of-the-art methods, this approach highlights the efficacy of combining advanced feature extraction with robust classification techniques for early AD diagnosis. These findings pave the way for impactful clinical applications, offering healthcare professionals a powerful tool for timely intervention and management of AD. The source code of the proposed model is available at <span><span>https://github.com/rsharma2612/Randomised-SVM</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"126 ","pages":"Article 110412"},"PeriodicalIF":4.0,"publicationDate":"2025-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144196353","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"Frequency and voltage stability improvement in a two-area thermal power system using a novel controller and RIME optimizer","authors":"Özay Can ,&nbsp;Mustafa Şinasi Ayas ,&nbsp;Emre Çelik","doi":"10.1016/j.compeleceng.2025.110434","DOIUrl":"10.1016/j.compeleceng.2025.110434","url":null,"abstract":"<div><div>This work presents a novel method for integrating the Load Frequency Control (LFC) and Automatic Voltage Regulator (AVR) processes to enhance frequency and voltage stability in two-area non-reheat thermal power systems. In this study, we present a novel Proportional Derivative-(1+Double Integral) (PD-(1+II)) controller, which is optimized through the utilization of the recently created Rime Optimization Algorithm (RIME). This represents the first time that the RIME algorithm and the PD-(1+II) controller are used in the context of coupled LFC-AVR systems. Our comprehensive research encompasses six distinct scenarios, including AVR system tuning, LFC system tuning, combined LFC-AVR system tuning, disturbance analysis, nonlinearity analysis, and parameter sensitivity analysis. A comparative analysis is conducted between the proposed RIME-tuned PD-(1+II) controller and established techniques such as the Nonlinear Threshold Accepting (NLTA) algorithm and its multi-objective version (MONLTA) tuned PID controllers, i.e. MONLTA-PID and NLTA-PID controllers. The simulation results demonstrate that the RIME-tuned PD-(1+II) controller consistently outperforms existing techniques. It exhibits superior performance in terms of overshoot reduction (100 % decrease in frequency deviation and 30 % decrease in terminal voltage) and faster settling times (50 % decrease in frequency control and 30 % decrease in voltage control) when compared to current methods. Furthermore, the controller demonstrates resilience in the presence of a diverse range of disturbances, nonlinearities, and parameter variations, highlighting its adaptability and reliability in a multitude of operational scenarios. The efficacy and reliability of the proposed methodology are further substantiated by statistical analysis, which demonstrates that it outperforms existing optimization algorithms, including the Gorilla Troops Optimizer (GTO) and the Whale Optimization Algorithm (WOA), with the RIME algorithm achieving an average ITSE value of 0.0881 compared to 0.1023 for GTO and 0.1057 for WOA.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"125 ","pages":"Article 110434"},"PeriodicalIF":4.0,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144190120","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"Adaptive virtual inertia emulation based on policy gradient clipping for low-inertia microgrids with phase-locked loop dynamics","authors":"Ming Chang ,&nbsp;Mohamed Salem ,&nbsp;Faisal A. Mohamed","doi":"10.1016/j.compeleceng.2025.110477","DOIUrl":"10.1016/j.compeleceng.2025.110477","url":null,"abstract":"<div><div>The high-penetration of sustainable energy resources in the hybrid microgrids necessitates deploying the power electronic interface systems (e.g., rectifiers, inverters, and converters) for conversion purposes. However, the utilization of such technologies reduces the inertia of microgrids which highly threaten their stability. The stability challenges of microgrids are heightened when the phase-locked loop devices are installed in the converter-based systems. In this work, a fractional order disturbance-observer-based control (FO-DOBC) is developed for advanced virtual inertia control (AVIC) of microgrids with sustainable resources, electric vehicles, and storage units. In particular, the effect of phase-locked loop’s dynamics on the stability of microgrid is investigated. To dynamically respond to the disturbances in the microgrid and phase-locked loop’s dynamics, the coefficients embedded in the FO-DOBC are adaptively adjusted by the stochastic policy gradient clipping. By training the neural networks of SPGC, the FO-DOBC controller is designed in such a way that maximizes a reward function defined based on the system requirements. The comprehensive examinations based on the Arduino testbed are carried out to appraise the feasibility of the suggested virtual-based controller in a real-time framework. The real-time outcomes of the microgrid reveal that the AVIC based on FO-DOBC controller (designed by the stochastic policy gradient clipping) provides better responses than conventional virtual inertia control. Moreover, the suggested AVIC controller provides a higher level of stability against the reduction of inertia (between 1 % to 10 %) from its nominal value.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"125 ","pages":"Article 110477"},"PeriodicalIF":4.0,"publicationDate":"2025-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144178423","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}