检索结果-内蒙古大学图书馆

International Conference on Control and Automation (ICCA)

作者： Guanpu Chen Kun Cao Karl Henrik Johansson Yiguang Hong Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Digital Futures Stockholm Sweden Department of Control Science and Engineering Research Institute for Intelligent Autonomous Systems Tongji University Shanghai China

ISBN: (数字)9798350354409

ISBN: (纸本)9798350354416

We study the computation of the global generalized Nash equilibrium (GNE) for a class of non-convex multi-player games, where players' actions are subject to both local and coupling constraints. Due to the non-convex payoff functions, we employ canonical duality to reformulate the setting as a complementary problem. Under given conditions, we reveal the relation between the stationary point and the global GNE. According to the convex-concave properties within the complementary function, we propose a continuous-time mirror descent to compute GNE by generating functions in the Bregman divergence and the damping-based design. Then, we devise several Lyapunov functions to prove that the trajectory along the dynamics is bounded and convergent.

关键词： Couplings Damping Automation Games Nash equilibrium Trajectory Mirrors

来源：评论

学校读者我要写书评

暂无评论

Machine learning algorithms for predicting the risk of chronic kidney disease in type 1 diabetes patients: a retrospective longitudinal study

引用

Neural Computing and Applications 2024年第26期36卷 16545-16565页

作者： Chowdhury, Md Nakib Hayat Reaz, Mamun Bin Ibne Ali, Sawal Hamid Md Crespo, María Liz Cicuttin, Andrés Ahmad, Shamim Haque, Fahmida Bakar, Ahmad Ashrif A. Razak, Mohd Ibrahim Bin Shapiai Abd Bhuiyan, Mohammad Arif Sobhan Department of Electrical Electronic and Systems Engineering Universiti Kebangsaan Malaysia UKM Selangor Bangi43600 Malaysia Saidpur Cantonment Saidpur Nilphamari5310 Bangladesh Department of Electrical and Electronic Engineering Independent University Bangladesh Dhaka Bashundhara Bangladesh Department of Electrical Electronic and Systems Engineering Centre of Advanced Electronic and Communication Engineering Universiti Kebangsaan Malaysia UKM Selangor Bangi43600 Malaysia Malaysia-Japan International Institute of Technology Universiti Teknologi Malaysia Jalan Sultan Yahya Petra Kuala Lumpur54100 Malaysia Trieste34151 Italy Department of Computer Science and Engineering University of Rajshahi Rajshahi6205 Bangladesh Artificial Intelligence Resource Molecular Imaging Branch National Cancer Institute BethesdaMD United States Department of Electrical and Electronics Engineering Xiamen University Malaysia Selangor Bandar Sunsuria Sepang43900 Malaysia

Chronic kidney disease (CKD) is a significant concern for individuals with type 1 diabetes (T1D), impacting their quality of life and healthcare costs. Identifying T1D patients at greater risk of developing CKD is crucial for preventive measures. However, it is challenging due to the asymptomatic progression of CKD and limited nephrologist availability in many countries. This study explores machine learning algorithms to predict CKD risk in T1D patients using ten years of retrospective data from the Epidemiology of Diabetes Interventions and Complications clinical trial. Eleven machine learning algorithms were applied to twenty-two readily available features from T1D patients’ routine check-ups and self-assessments to develop 10-year CKD risk prediction models. In addition, we also proposed a heterogeneous ensemble model (STK) using a stacking generalization approach. The models’ performance was evaluated using different evaluation metrics and repeated stratified k-fold cross-validation. Several predictive models showed reliable performance in CKD risk prediction, with the proposed ensemble model being the best performing with an average accuracy of 0.97, specificity of 0.98, sensitivity/recall of 0.96, precision of 0.98, F1 score of 0.97, Kappa and MCC score of 0.94, AUROC of 0.99, and Precision-Recall curve of 0.99. The proposed machine learning approach could be applicable for CKD risk prediction in T1D patients to ensure the necessary precautions to overcome the risk. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Fuzzy-Based Weighted Federated Machine Learning Approach for Sustainable Energy Management with IoE Integration

Fuzzy-Based Weighted Federated Machine Learning Approach for...

引用

IEEE Symposium on systems and Information engineering Design, SIEDS

作者： Taher M. Ghazal Jamshaid Iqbal Janjua Sagheer Abbas Areej Fatima Muhammad Saleem Muhammad Adnan Khan Abdulrahman Alqarafi Computer Science Department Centre for Cyber Physical Systems Khalifa University Abu Dhabi UAE Center for Cyber Security Faculty of Information Science and Technology Universiti Kebangsaan Malaysia Selangor Malaysia School of Computer Sciences National College of Business Administration & Economics Lahore Pakistan Al-Khawarizmi Institute of Computer Science University of Engineering & Technology (UET) Lahore Pakistan Department of Computer Science Bahria University Lahore Pakistan Department of Computer Science LGU Lahore Pakistan School of Computer Science Minhaj University Lahore Pakistan School of Computing Skyline University College Sharjah UAE Riphah School of Computing and Innovation Riphah International University Lahore Pakistan College of Computer Science and Engineering Taibah University Medina Saudi Arabia

ISBN: (数字)9798350385144

ISBN: (纸本)9798350385151

The considerable surge in energy consumption due to population growth and the use of new technology has posed significant challenges to energy security and the environment. Managing energy consumption on the consumer side is crucial as the demand for energy continues to increase. Consumers need to monitor their daily usage and understand consumption standards to prepare themselves for energy efficiency and cost savings. To address these challenges, a Smart Energy Management System (SEMS) based on the Internet of Energy (IoE) has been developed. This system uses day-ahead planning and accurate energy availability forecasting to manage energy demand in a smart environment with high sustainable energy penetration. The Fuzzy based Weighted Federated Learning (FWFML) approach is integrated into the system to optimize energy management. The SEMS system monitors energy usage at the user level, and a review of management plans has been introduced to improve energy efficiency in terms of 93.5% accuracy, and 6.5% miss-rate. This research work also highlights future challenges in developing SEMS to increase energy efficiency in a more robust manner.

关键词： Energy consumption Costs Smart buildings Sociology Energy efficiency Energy management systems Surges

来源：评论

学校读者我要写书评

暂无评论

Modified Aquila Optimization based Route Planning Model for Unmanned Aerial Vehicles Networks 1

Modified Aquila Optimization based Route Planning Model for ...

引用

1st IEEE International Conference on Automation, Computing and Renewable systems, ICACRS 2022

作者： Chaudhari, Sachin Vasant Dhipa, M. Ayoub, Shahnawaz Gayathri, B. Siva, M. Banupriya, V. Department of Electronic and Computer Engineering Sanjivani College of Engineering Kopargaon Maharashtra Ahmednagar India Department of Biomedical Engineering Nandha Engineering College Perundurai Main Road Erode India Shri Venkateshwara University NH-24 Venkateshwara Nagar Rajabpur Gajraula Dist Uttar Pradesh Amroha India Department of Computer Science Bishop Heber College Affiliated to Bharathidasan University Trichy India Department of Civil Engineering Easwari Engineering College Tamilnadu Chennai India Department of Computer Science and Business Systems M. Kumarasamy College of Engineering Tamilnadu Karur India

ISBN: (纸本)9781665460842

Unmanned aerial vehicles (UAVs) are deliberated as a potential example of automated emergency tasks in dynamic marine environments. But the maritime transmission performances among UAVs and offshore platform becomes a crucial problem. The task planning problems of numerous UAVs are classified into two parts, route planning and task allocation problems, are different and interrelated from one another. Because of the complicated marine environments, both efficiencies of UAVs in an intelligent ocean are not acceptable. This study presents a Modified Aquila Optimization Algorithm based Route Planning Scheme (MAOA-RPS) for UAV networks. The presented MAOA-RPS technique is majorly concentrated on the detection of optimal routes for UAV data transmission. To attain this, the MAOA-RPS technique involves the incorporation of Levy flight (LF) with the traditional AOA. In addition, the optimal routes are chosen by the MAOA-RPS technique via a fitness value, which can be determined by many input parameters. For assessing the enhanced outcomes of the MAOA-RPS technique, we have performed a series of experiments. The comparison study revealed the improved performance of the MAOA-RPS technique under distinct metrics. © 2022 IEEE

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

A preliminary study about gender gap perception in informatics studies in Spain 12

A preliminary study about gender gap perception in informati...

引用

12th International Conference on Virtual Campus, JICV 2022

作者： Garcia-Holgado, Alicia Gonzalez-Gonzalez, Carina S. Fernandez, Inmaculada Garcia Lopez, Lourdes Moreno Barrenechea, Edurne Rueda, Silvia Navarro, Angeles G. Martinez, Paloma Masia, Belen Navarro, Elena Fornes, Alicia Grial Research Group Universidad DeSalamanca Computer Science and Automation Department Salamanca Spain University of la Laguna Computer Engineering Department San Cristobal de La Laguna Spain Universidad de Málaga Computer Architecture Department Málaga Spain Universidad Carlos Iii de Madrid Computer Science and Engineering Department Madrid Spain Universidad Pública de Navarra Departamento de Estadística Informática y Matemáticas Pamplona Spain Universitat de València Departament of Computer Science Valencia Spain Universidad de Zaragoza Computer Science Department Zaragoza Spain Universidad de Castilla la Mancha Departament of Computing Systems Albacete Spain Computer Vision Center Universitat Autónoma de Barcelona Barcelona Spain

ISBN: (数字)9781665451062

ISBN: (纸本)9781665451062

The gender gap in STEM is an issue that affects regions and countries worldwide. Furthermore, the percentage of women in these areas depends on a range of different factors. In particular, the gender gap is critical in technology in general and, more specifically, in informatics. This problem affects not only the business sector but also society. Informatics is part of our lives;however, 50% of the world population is not represented in the teams that are developing solutions for solving society's problems. In Spain, the number of women with informatics degrees is around 15%. This work describes a case study developed by the committee of Women in Informatics at the Scientific Society of Spanish Informatics (SCIE) to analyse the perception of informatics scientists on the gender gap in informatics. © 2022 IEEE.

关键词： computers

来源：评论

学校读者我要写书评

暂无评论

Weighted Sampled Split Learning (WSSL): Balancing Privacy, Robustness, and Fairness in Distributed Learning Environments

Weighted Sampled Split Learning (WSSL): Balancing Privacy, R...

引用

International Conference on Parallel and Distributed systems (ICPADS)

作者： Manish Osti Aashray Thakuri Basheer Qolomany Aos Mulahuwaish Department of Computer Science and Information Systems Saginaw Valley State University University Center MI USA College of Engineering and Computer Science University of Michigan - Dearborn Dearborn USA Cyber Systems Department University of Nebraska at Kearney Kearney USA

This study presents Weighted Sampled Split Learning (WSSL), an innovative framework tailored to bolster privacy, robustness, and fairness in distributed machine learning systems. Unlike traditional approaches, WSSL disperses the learning process among multiple clients, thereby safeguarding data confidentiality. Central to WSSL’s efficacy is its utilization of weighted sampling. This approach ensures equitable learning by tactically selecting influential clients based on their contributions. Our evaluation of WSSL spanned various client configurations and employed two distinct datasets: Human Gait Sensor and CIFAR-10. We observed three primary benefits: heightened model accuracy, enhanced robustness, and maintained fairness across diverse client compositions. Notably, our distributed frameworks consistently surpassed centralized counterparts, registering accuracy peaks of 82.63% and 75.51% for the Human Gait Sensor and CIFAR-10 datasets, respectively. These figures contrast with the top accuracies of 81.12% and 58.60% achieved by centralized systems. Collectively, our findings champion WSSL as a potent and scalable successor to conventional centralized learning, marking it as a pivotal stride forward in privacy-focused, resilient, and impartial distributed machine learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

IoT sensor data retrieval and analysis through cloud environment for effective power management

引用

Measurement: Sensors 2024年 31卷

作者： Ch, Srilakshmi K, Uma Yadav, Rakesh Kumar Sagar, K.V Daya N.P, Dharani Sharma, Priyanka Department of Computer Science and Business Systems R.M.D Engineering College Tamil Nadu Kavaraipettai India VIT University Tamilnadu Vellore India Department of Computer Science and Engineering Ajay Kumar Garg Engineering College Uttar Pradesh Ghaziabad India Department of Electronics and Computer Science Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh Guntur India Andhra Pradesh Tirupati India Department of Electrical Engineering Graphic Era HIllUniversiy Graphic Era Deemed to Be University Dehradun R/S Dehradun India

The Internet of Things (IoT) brings new products to everyone to improve daily life. Other newly created techniques, including Big Data, Cloud Services, and surveillance, can participate through these technological advances. In this study, the researchers look at the four systems mentioned above to identify their shared functions and integrate them to create useful potential applications. Despite the limitations of the smart city concept, researchers would seek innovative methods to collect and process sensor information within an IoT-enabled smart building. A cloud service would have been used as the foundation technology for the proposed schema management platform, collecting the information generated by each sensor in the smart factory. It was easy to manage and manipulate remotely using IoT technology and a mobile device with a network connection. Here, to enhance safety of the entire building by installing multiple IoT devices in a smart building. The proposed systems were designed in a simulated Cooja simulator environment. The proposed approaches to the collection and manipulation of sensor information in smart cities can help us create a green, resource-efficient project. © 2023 The Authors

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Dynamic Multi-Objective Optimization Based on Multi-Scale Perturbation Prediction and Regional Search

SSRN

引用

SSRN 2024年

作者： Hu, Yaru Zheng, Zhi Ou, Junwei Zou, Juan Wang, Rui Yang, Shengxiang Zheng, Jinhua Zhang, Bo Peng, Jiankang The School of Computer Science and Cyberspace Science Xiangtan University Xiangtan411105 China The College of Systems Engineering National University of Defense Technology China School of Computer Science and Informatics De Montfort University LeicesterLE1 9BH United Kingdom

In recent years, many distinguished dynamic multiobjective optimization evolutionary algorithms (DMOEAs) have been derived based on prediction strategies. Prediction-based strategies have shown their superiority in tracking the new POS/POF. However, prediction-based strategies will be poor if the distribution of the Pareto optimal solutions has drastic changes with environmental ***, we propose a hybrid of multi-scale perturbation prediction and regional search (PPRS) to solve DMOPs. The regional search strategy contains two sub-methods of autonomous evolutionary complementation and bi-directional route ***, the multi-scale perturbation prediction strategy is based on the prediction of the centroid and generates a disturbance area to assist the population in quickly converging after environmental changes. Second, the autonomous evolutionary complementary strategy can effectively solve the problem of poor convergence when the predicted trajectory of the population is inconsistent with the direction of self-evolution by supplementing the good individuals generated by self-evolution into the population obtained by perturbation prediction. Third, the bi-directional route sampling strategy can facilitate the population distribution with forward search and backward search of the population in the disturbance area. The experimental comparison results on all kinds of selected benchmark suits have given evidence that more excellent performance in MIGD and MHV of PPRS. © 2024, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Object Detection as Gram Positive Cocci in Gram Stained Smear Images 12

Object Detection as Gram Positive Cocci in Gram Stained Smea...

引用

12th International Congress on Advanced Applied Informatics, IIAI-AAI 2022

作者： Sugimoto, Hitoshi Hirata, Kouichi Kyushu Institute of Technology Graduate School of Computer Science and Systems Engineering Iizuka820-8502 Japan Kyushu Institute of Technology Department of Artificial Intelligence Iizuka820-8502 Japan

In this paper, we detect Gram positive cossi in Gram stained smear images as object detection. As detectors, we adopt Faster R-CNN, RetinaNet and YOLOv5. Then, we give experimental results for detecting Gram positive ... 详细信息

ISBN: (数字)9781665497558

ISBN: (纸本)9781665497558

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Strategies For Rare Drug Mechanism of Action Prediction

Deep Learning Strategies For Rare Drug Mechanism of Action P...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Gonçalo Ferreira Marco Teixeira Raquel Belo Wilson Silva Jaime S. Cardoso FEUP - Faculty of Engineering University of Porto Porto Portugal INESC TEC - Institute for Systems and Computer Engineering Technology and Science Porto Portugal

The application of machine learning algorithms to predict the mechanism of action (MoA) of drugs can be highly valuable and enable the discovery of new uses for known molecules. The developed methods are usually evaluated with small subsets of MoAs with large support, leading to deceptively good generalization. However, these datasets may not accurately represent a practical use, due to the limited number of target MoAs. Accurate predictions for these rare drugs are important for drug discovery and should be a point of focus. In this work, we explore different training strategies to improve the performance of a well established deep learning model for rare drug MoA prediction. We explored transfer learning by first learning a model for common MoAs, and then using it to initialize the learning of another model for rarer MoAs. We also investigated the use of a cascaded methodology, in which results from an initial model are used as additional inputs to the model for rare MoAs. Finally, we proposed and tested an extension of Mixup data augmentation for multilabel classification. The baseline model showed an AUC of 73.2% for common MoAs and 62.4% for rarer classes. From the investigated methods, Mixup alone failed to improve the performance of a baseline classifier. Nonetheless, the other proposed methods outperformed the baseline for rare classes. Transfer Learning was preferred in predicting classes with less than 10 training samples, while the cascaded classifiers (with Mixup) showed better predictions for MoAs with more than 10 samples. However, the performance for rarer MoAs still lags behind the performance for frequent MoAs and is not sufficient for the reliable prediction of rare MoAs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：