检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Zheng, Shaifeng Zhu, Qingling Lin, Qiuzhen Liu, Songbai Wong, Ka-Chun Li, Jianqiang College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Computer Science City University of Hong Kong Hong Kong

Personalized federated learning (PFL) has garnered attention due to its capability to address statistical heterogeneity among clients. Typically, prevailing PFL methods aggregate a single global model for personalization, which may be inadequate for clients with diverse data distributions. Furthermore, in the local update, each private dataset is used to optimize the model independently, which increases the risk of overfitting the current data distribution and losing previously acquired knowledge, resulting in knowledge forgetting. In this study, personalized federated learning with multiple classifier aggregation is proposed. The method involves splitting the client model into its head and base, then optimizing them respectively using an alternating optimization strategy that first optimizes the head and then the base. Initially, to address the suboptimal model problem, the proposed approach aggregates multiple classifiers using data distribution and employs knowledge distillation to impart positive and negative classifier knowledge for learning the most suitable personalized model head. Additionally, to mitigate knowledge forgetting, a learnable personalization layer is introduced, and hidden loss is utilized to learn the knowledge of the global base and prevent overfitting of the model base. Empirical results demonstrate that the proposed method achieves competitive performance across various benchmarks, outperforming the majority of state-of-the-art PFL algorithms. The source code is publicly available at \href{https://***/xiaye-maker/FedMCA}{https://***/xiaye-maker/FedMCA} © 2024, The Authors. All rights reserved.

关键词： Aggregates

来源：评论

学校读者我要写书评

暂无评论

Thy-Sys: A Preliminary Thyroid Wellness Assessment Through Machine Learning Using Pathological Factors 1

Thy-Sys: A Preliminary Thyroid Wellness Assessment Through M...

引用

1st International Conference in Information and Computing Research, iCORE 2021

作者： Francisco, Ismael R. Ferolin, Mary Bernadette J. Pena, Christine F. Ferolin, Rosana J. University of San Carlos Department of Computer Information Sciences and Mathematics Cebu City Philippines University of San Carlos Graduate Engineering Program School of Engineering Department of Computer Engineering Cebu City Philippines

ISBN: (纸本)9781665402101

The thyroid gland is a butterfly-shaped organ located lower front of the neck that plays a critical role in one's overall well-being. According to survey, thyroid dysfunction is observed in 8.53% of Filipino adults aged 42 to 62 years old, implying that 1 out of 12 Filipino adults has some form of thyroid function abnormality. To promote awareness of thyroid health, the researchers developed the Thyroid System for Wellness Assessment (Thy-Sys) which aims to determine the wellness of a person's thyroid through machine learning. The system assesses the user's thyroid wellness based on their responses to questions related to observable characteristics of the more common thyroid diseases like hypothyroidism and hyperthyroidism. Prior to the development, four machine learning models, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Decision Tree, and SVM-KNN were evaluated in classifying the state of the thyroid through pathological factors. Training and testing of the machine were done over a dataset with 1,464 entries and a total of 18 pathological attributes. 10-fold cross-validation was performed to verify the models' accuracy while observing other metric scores. The SVM-KNN model garnered the highest accuracy of 99.55% with 98.75% precision, and 98.61 % recall and F1 scores, and was integrated into the system. © 2021 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

AI-Powered Smart and Personalized Education Platform

AI-Powered Smart and Personalized Education Platform

引用

2023 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2023

作者： Dunusinghe, A.V. Ranasinghe, T.K.S.A. Gamage, J.G.A.C.H. Perera, K.G.D.T. Thelijjagoda, Samantha Gunatilake, Poojani Sri Lanka Institute of Information Technology Department of Computer Science and Software Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Department of Information Technology Malabe Sri Lanka Research and International Sri Lanka Institute of Information Technology Malabe Sri Lanka

ISBN: (纸本)9798350319200

An AI assistant addresses online education's shortcomings, focusing on personalized learning and career guidance. It provides tailored recommendations, assesses performance, suggests subjects, and crafts learning plans. Objectives include accurate grade prediction, subject stream advice, customized assessments, and personalized strategies. The study shows data analytics and machine learning forecast grades, while multi-tenancy architecture improves data handling. Personalized assessments consider both academics and soft skills. Machine learning promises accurate subject stream predictions, and engagement detection aids in optimal learning. This AI system holds potential in reshaping online education, but ongoing improvements are vital for enhanced learning. © 2023 IEEE.

关键词： career guidance learning strategies Machine learning multi-tenancy Online education personalized assessment personalized learning subject stream recommendation

来源：评论

学校读者我要写书评

暂无评论

Optimizing MEMS Optical Arrays with Silicon Micro Mirrors using Machine Learning Techniques

Optimizing MEMS Optical Arrays with Silicon Micro Mirrors us...

引用

Computational Modelling, Simulation and Optimization (ICCMSO), International Conference on

作者： Vilas Ramrao Joshi Surender Kumar Sharma Vijay Agatrao Galande Pallavi Sachin Patil Ushadevi Patil Hussain Suttarwala Deepak K. Sharma Department of Computer Engineering Savitribai Phule Pune University Pune India Department of Electrical Engineering Poornima University Jaipur India Department of Engineering Science KJEI’s Trinity Academy of Engineering Pune India Department of Civil Engineering Genba Sopanrao Moze College of Engineering Pune India Senior Software Engineer American Express Phoenix AZ USA University of Technology Jaipur India

ISBN: (数字)9798350361391

ISBN: (纸本)9798350361407

In the rapidly evolving landscape of optical microsystems, the infusion of Machine Learning (ML) techniques stands out as a catalyst for unprecedented progress. This research paper delves into the intricate interplay between Micro-Electro-Mechanical Systems (MEMS), optical arrays, and silicon micro mirrors, shedding light on the transformative prowess unleashed by Machine Learning in optimizing these intricate components. Focusing on the limitations posed by conventional designs, the paper not only illuminates the challenges encountered but also presents a compelling narrative of how ML algorithms emerge as formidable allies, poised to surmount these hurdles with ingenuity and precision. The exploration extends beyond a mere technical discourse; it unfolds as a narrative of innovation, where the convergence of MEMS, optical arrays, and silicon micro mirrors, guided by the intelligence of Machine Learning, transcends traditional boundaries, propelling optical microsystems into an era of unparalleled efficiency and adaptability. This research beckons a new epoch, where the intricate dance of silicon micro mirrors and the intricate mechanics of MEMS find harmony through the symphony of Machine Learning, reshaping the landscape of optical microsystems and inspiring future possibilities that were once deemed beyond reach.

关键词： Micromechanical devices Integrated optics Technological innovation Machine learning Optical computing Optical fiber networks Silicon

来源：评论

学校读者我要写书评

暂无评论

Binary Code Similarity Detection

arXiv

引用

arXiv 2023年

作者： Liu, Zian Department of Computer Science and Software Engineering Swinburne University of Technology Data61 CSIRO Melbourne Australia

Binary code similarity detection is to detect the similarity of code at binary (assembly) level without source code. Existing works have their limitations when dealing with mutated binary code generated by different compiling options. In this paper, we propose a novel approach to addressing this problem. By inspecting the binary code, we found that generally, within a function, some instructions aim to calculate (prepare) values for other instructions. The latter instructions are defined by us as key instructions. Currently, we define four categories of key instructions: calling subfunctions, comparing instruction, returning instruction, and memory-store instruction. Thus if we symbolically execute similar binary codes, symbolic values at these key instructions are expected to be similar. As such, we implement a prototype tool, which has three steps. First, it symbolically executes binary code;Second, it extracts symbolic values at defined key instructions into a graph;Last, it compares the symbolic graph similarity. In our implementation, we also address some problems, including path explosion and loop handling. © 2023, CC BY.

关键词： Binary codes

来源：评论

学校读者我要写书评

暂无评论

Diagnostic of an Aircraft by Different Dynamics of Operating Conditions

Diagnostic of an Aircraft by Different Dynamics of Operating...

引用

2022 International Conference on Control, Automation and Diagnosis, ICCAD 2022

作者： Al Mamun, Abdullah Shahin, Kamrul Islam Simon, Christophe Weber, Philippe Department of Computer Science and Engineering United International University Dhaka Bangladesh The Mærsk Mc-Kinney Møller Institute Department of Software Engineering University of Southern Denmark Odense Denmark Université de Lorraine CNRS CRAN NancyF-54000 France

ISBN: (数字)9781665497947

ISBN: (纸本)9781665497947

This paper proposes an Input-Output Hidden Markov Model (IOHMM) to describe how the diagnostic of aircraft gas turbine engines can be estimated under multiple operating conditions. The PHM data challenge 2008 is used to model the system under the uncertainties of model parameters, operating dynamics, and the initial health situation. In this paper, multiple inputs are considered respective to the operating conditions. The thermodynamic simulation model generated the data of all sensors as a function of variations of flow and the efficiency of the modules concerned. The exponential rate of flow variation and efficiency loss was established in each data set, starting at a randomly selected initial deterioration set point. Well-known algorithms dedicated to Hidden Markov Model (HMM) are adapted to train different versions of IOHMM with the operating conditions. Finally, the best version of the model based on the most appropriate operating conditions for the system operation is selected to perform the diagnostic of the engine. The proposed method is validated by the cross-validation method to provide confidence over the model performance. © 2022 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

High-Accuracy Hand Segmentation for Palmprint Biometric Systems Improving Auto-Encoder Techniques

High-Accuracy Hand Segmentation for Palmprint Biometric Syst...

引用

Innovative Approaches in Smart Technologies (ISAS), International Symposium on

作者： Kadir Yalcin Ramazan Ozgur Dogan Hulya Dogan Ozkan Bingol Department of Artificial Intelligence and Intelligent Systems Graduate Education Institute Gumushane University Gumushane Türkiye Department of Artificial Intelligence Engineering Faculty of Computer and Information Sciences Trabzon University Trabzon Türkiye Department of Software Engineering Faculty of Engineering Karadeniz Technical University Trabzon Türkiye Department of Software Engineering Faculty of Eng. and Natural Sciences Gumushane University Gumushane Türkiye

ISBN: (数字)9798331540104

ISBN: (纸本)9798331540111

Biometric technologies have been widely adopted in various commercial products, ranging from security systems to personal devices, due to their exceptional reliability and user-friendliness. Among these, palmprint biometrics has gained increasing attention for its advantages, such as ease of use, a larger surface area, and the ability to capture more features compared to other biometric methods. A typical palmprint biometric system involves five key stages: (a) Image Acquisition, (b) Hand Segmentation, (c) Pattern Generation, (d) Feature Extraction, and (e) Verification/Identification. The overall success of the system depends on the effectiveness of each stage, with hand segmentation being crucial for identifying the most relevant features for accurate verification. This study aims to achieve high-accuracy biometric recognition by segmenting hands from images captured in uncontrolled environments with complex backgrounds. Accuracy (ACC), Intersection over Union (IoU), F1-Score, and Dice Coefficient are the four critical metrics used to assess the performance of segmentation techniques. The findings demonstrate that the U-Net + ViT and MA-Net + ResNet34 techniques outperform traditional auto-encoder methods in both quantitative performance metrics and visual analysis, leading to significantly improved hand segmentation for biometric systems.

关键词： Biometrics Hands Image segmentation Visualization Accuracy Image recognition Biological system modeling Feature extraction Reliability Security

来源：评论

学校读者我要写书评

暂无评论

Design, Modeling and Simulation of Cybercriminal Personality-Based Cyberattack Campaigns

Design, Modeling and Simulation of Cybercriminal Personality...

引用

Simulation Winter Conference

作者： Jeongkeun Shin Geoffrey B. Dobson L. Richard Carley Kathleen M. Carley Department of Electrical and Computer Engineering Carnegie Mellon University Pittsburgh PA USA Software and Societal Systems Department Carnegie Mellon University Pittsburgh PA USA

ISBN: (数字)9798331534202

ISBN: (纸本)9798331534219

Cybersecurity challenges are inherently complex, characterized by both advanced technical elements and complex aspects of human cognition. Although extensive research has explored how victims' human factors affect their susceptibility to cyberattacks, the influence of cybercriminals' personalities on the pattern of cyberattack campaigns and the resulting damage to organizations has not received equivalent attention. To bridge this research gap through computer simulation, we introduce a cyberattack campaign designer that enables modelers to construct cyberattack campaigns. This tool allows modelers to define how the process or pattern of the cyberattack campaign can change based on the cybercriminal's personality and simulates how these personality differences influence the magnitude of cyberattack damage on the target organization. In this paper, through computer simulation, we demonstrate how cautious and reckless personalities result in variations in the cyberattack pattern and, consequently, affect the magnitude of cyberattack damage, despite identical cyberattack objectives and techniques used at each step.

关键词： Bridges Computational modeling computer simulation Organizations Human factors Cognition computer crime

来源：评论

学校读者我要写书评

暂无评论

A Bi-Directional Inductive Power Transfer System with Zero Voltage Switching and Unity Power Factor for a Wide Operating Range

A Bi-Directional Inductive Power Transfer System with Zero V...

引用

Wireless Power Week (WPW)

作者： Bharat Vardani Duleepa J. Thrimawithana Zhihao He Grant A. Covic Martin Neuburger Department of Electrical Computer and Software Engineering University of Auckland Auckland New Zealand Department of Electrical Drives University of Applied Sciences Esslingen am Neckar Germany

ISBN: (数字)9798350349139

ISBN: (纸本)9798350349146

A conventional bi-directional inductive power transfer (Bd-IPT) system is required to accommodate a wide range of loads due to variations in the magnetic coupling factor and battery voltage of electric vehicles (EVs). To address this challenge, the system adjusts both internal and relative phase shifts of the H-Bridge converter to achieve the desired power transfer. However, altering the internal phase shift may lead to a loss of zero-voltage switching (ZVS) in the converters, while changing the relative phase shift can introduce reactive power into the system, resulting in increased losses in the coil and the converter. This article presents a novel Bd-IPT system that utilizes an integrated boost multilevel converter (IBMC) with a digitised modulation scheme. The primary objectives of the proposed Bd-IPT system are to maintain the desired power transfer, operate both the primary and secondary converters within the ZVS range, and achieve zero reactive power for a wide range of loading conditions. Additionally, the article compares the efficiency and cost of the proposed Bd-IPT system to a conventional IPT system.

关键词： Coils Wireless communication Reactive power Multilevel converters Costs Loading Modulation

来源：评论

学校读者我要写书评

暂无评论

Enhancing Pulmonary Nodule Classification performance with TriCaps-RL: A Capsule Network Reinforcement Learning Approach

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第3期9卷 1441-1459页

作者： Zheng, Guang-Yuan Zhang, Fu-Quan Cheng, Chen Shan, Hong-Tao Soomro, Nouman Qadeer Liu, Yi College of Information Technology Shanghai Jian Qiao University Shanghai201306 China School of Mathematics and Computer Science Yanan University Shaanxi 716000 China School of Computer and Data Science Minjiang University No.200 Xiyuangong Road Fuzhou University Town Fuzhou350108 China Digital Media Art Key Laboratory of Sichuan Province Sichuan Conservatory of Music Chengdu610021 China Fuzhou Technology Innovation Center of intelligent Manufacturing information System Minjiang University Fuzhou350108 China Fujian Province University Fuzhou350300 China College of Business Shanghai Jian Qiao University Shanghai201306 China College of Electronic and Electrical Engineering Shanghai University of Engineering Science Shanghai201620 China Software Department Mehran University of Engineering & Technology Sindh 76062 Pakistan

Distinguishing the manifestations of pulmonary nodules poses a significant challenge in the medical field, demanding the expertise of experienced radiologists. This complexity results in the high cost and inadequacy of sample labeling. In response, this study introduces a reinforcement learning approach, denoted as TriCaps-RL, for the classification of pulmonary nodules based on CT signs. This approach initially employs the Q-value loss to train a single CapsNet. When the performance of the CapsNet plateaus and further enhancement becomes challenging, the loss function is progressively replaced by a triplet metric to augment performance. Consequently, a more nuanced differentiation among various types of pulmonary nodules is achieved. The proposed method can improve its performance through interactions with radiologists during their CT image reading process, thereby mitigating the shortage of radiologists and addressing the time-consuming issue of training sample labeling in medical image research. This paper delves into the fine-grained classification of pulmonary nodules using deep reinforcement learning based on CT imaging signs. In comparison to previous studies that primarily concentrate on the benign/malignant classification of lung nodules, this fine-grained classification of nodules founded on CT imaging signs proves to be more valuable for medical practitioners in making accurate diagnostic decisions. © 2024, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Lung cancer

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：