检索结果-内蒙古大学图书馆

Multi-objective Feature Attribution Explanation for Explainable Machine Learning

ACM Transactions on Evolutionary Learning and Optimization 2024年第1期4卷 1-32页

作者： Wang, Ziming Huang, Changwu Li, Yun Yao, Xin Research Institute of Trustworthy Autonomous Systems Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Departmentof Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China The Advanced Cognitive Technology Lab Huawei Technologies Co. Ltd Shanghai201206 China School of Computer Science University of Birmingham BirminghamB15 2TT United Kingdom

The feature attribution-based explanation (FAE) methods, which indicate how much each input feature contributes to the model's output for a given data point, are one of the most popular categories of explainable machine learning techniques. Although various metrics have been proposed to evaluate the explanation quality, no single metric could capture different aspects of the explanations. Different conclusions might be drawn using different metrics. Moreover, during the processes of generating explanations, existing FAE methods either do not consider any evaluation metric or only consider the faithfulness of the explanation, failing to consider multiple metrics simultaneously. To address this issue, we formulate the problem of creating FAE explainable models as a multi-objective learning problem that considers multiple explanation quality metrics simultaneously. We first reveal conflicts between various explanation quality metrics, including faithfulness, sensitivity, and complexity. Then, we define the considered multi-objective explanation problem and propose a multi-objective feature attribution explanation (MOFAE) framework to address this newly defined problem. Subsequently, we instantiate the framework by simultaneously considering the explanation's faithfulness, sensitivity, and complexity. Experimental results comparing with six state-of-The-Art FAE methods on eight datasets demonstrate that our method can optimize multiple conflicting metrics simultaneously and can provide explanations with higher faithfulness, lower sensitivity, and lower complexity than the compared methods. Moreover, the results have shown that our method has better diversity, i.e., it provides various explanations that achieve different tradeoffs between multiple conflicting explanation quality metrics. Therefore, it can provide tailored explanations to different stakeholders based on their specific requirements. © 2024 Copyright held by the owner/author(s). Publication rights licensed

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

CNN-LSTM: Development of Offline Signature Authentication 1

CNN-LSTM: Development of Offline Signature Authentication

引用

1st IEEE International Conference on Emerging Research in Computational Science, ICERCS 2023

作者： Ganapathy, Revathy Lingeshwaran, D. Suthanthiradevi, P. Harish Kumar, M.V. Vels Insitute of Science Technology and Advanced Studies Department of Computer Science and Engineering Chennai India Srm Institute of Science and Technology Department of Data Science and Business Systems Chennai India

ISBN: (纸本)9798350359756

Offline Signature Authentication is a critical task in the field of document authentication, and its accuracy is essential for ensuring security while transactions. This research proposes two approaches: Initially Pre-trained CNN models are used to extract features from signature images, which are then combined with handcrafted features such as HOG and some other geometric features of signature. Such combined features are passed to bidirectional LSTM model in which drop out layer undergoes classification which differentiate real and forgery signature. The proposed system has potential applications in document authentication and security, subsequently combination of CNN models and additional features provides more comprehensive representation of signature images resulting in improved accuracy. Three signature datasets are utilized namely GDPS, CEDAR, and BHSig-Bengali each with varying signature styles and image quality. Our experimental outcomes reveal that Bidirectional Convolutional LSTM along with handcraft features attained maximum accuracy in offline signature verification system. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

CoDPoC IP: A Configurable Data Protection Circuit to Support Multiple Key Agreement Scheme 26th

CoDPoC IP: A Configurable Data Protection Circuit to Suppor...

引用

26th International Conference on Information and Communications Security, ICICS 2024

作者： Peng, Yijing Wang, Junhui Wang, Zhenyu Guo, Zhenbin Wang, Yaohua Deng, Ding Li, Shaoqing Guo, Yang Key Laboratory of Advanced Microprocessor Chips and Systems National University of Defense Technology Changsha China School of Computer National University of Defense Technology Changsha China College of Electronic Science and Technology National University of Defense Technology Changsha China College of Semiconductors Hunan University Changsha China

ISBN: (纸本)9789819788002

Physical Unclonable Function(PUF)-based security protocols are effective in mitigating various security threats, including eavesdropping, interception, and cloning. Nevertheless, most existing protocols are implemented in software, with the primary drawback being their inability to integrate with actual PUF and their inefficiency. Although some strategies incorporate PUF into their design, these systems do not allow for configuration changes and are deficient in flexibility. In this paper, we propose the CoDPoC IP, a configurable data protection circuit that supports PUF-based various key agreement authentication schemes and allows for flexible scheme design adjustments through configurable registers. The CoDPoC IP offers two advantages: 1) hardware-level implementation incorporates PUF, leading to higher resource utilization, efficiency, and security;and 2) the IP supports flexible configuration of schemes. Experimental results indicate that the hardware execution time is 0.03504 milliseconds. The proposed scheme is successfully implemented and verified with low-overhead hardware. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

An Empirical Comparison of Machine and Deep Learning Algorithms for Predicting Maternal Health Risk 5th

An Empirical Comparison of Machine and Deep Learning Algorit...

引用

5th EAI International Conference on Cognitive Computing and Cyber Physical systems, IC4S 2024

作者： N, Srinivasa Gupta Valarmathi, B. Kavitha, A. Gopini, Sai Bhuvan Seela, Hari Kumar Department of Manufacturing Engineering School of Mechanical Engineering Vellore Institute of Technology Tamil Nadu Vellore India Department of Software and Systems Engineering School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore India Department of Mathematics School of Advanced of Sciences Vellore Institute of Technology Tamil Nadu Vellore India

ISBN: (纸本)9783031770777

Maternal health is among the greatest challenges in the world, especially in rural areas as there lack medical practitioners, they do not have easily accessible publics clinics and transport is difficult. Therefore, high rates of maternal as well as infant morbidity and mortalities are recorded. This research utilizes Artificial Intelligence (AI) with machine learning algorithms to forecast and address maternal health hazards right at their onset stage. The current research utilizes the concept of AI along with many Machine Learning (ML) methods like the Ensemble Learning Model (ELM), Random Forest (RF), K-Nearest Neighbour (KNN), Decision-Tree (DT), XG-Boost (XGB), Cat Boost (CB), and Gradient Boosting (GB), along with Synthetic Minority Over-sampling Technique (SMOTE) algorithm used for dealing with the problem class imbalance within the data set. SMOTE algorithm is utilized for the dataset balancing process. The handling system involves refining data preprocessing with the help of feature engineering and robust data cleaning which makes sure that anomalies do not erode the reliability of the predictive model. The existing methods [1] used RF (90%), DT (87%), XGB (85%), CB (86%), and GB (81%) algorithms and were compared with the accuracies of the proposed models like Logistic Regression (LR), Ensemble Learning Bagging (ELB), Ensemble Learning Stacking (ELS), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU). The existing methods used only imbalance dataset. The accuracies of the proposed models with using SMOTE algorithm (balanced dataset) are LR (61.33%), KNN (81%), ELB (92.33%), ELS (90.66%) CNN (40.67%), RNN (59.67%), LSTM (54%), GRU (56%) respectively. Among these methods, ELB achieved 92.33% of accuracy with using SMOTE algorithm using imbalanced dataset. Whereas the accuracies of the proposed models without using SMOTE algorithm (imbalanced dataset) are LR (66.09%), KNN (68.47%)

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Anthropomorphism for improving user tolerance to system errors in environmental behavior change 12

Anthropomorphism for improving user tolerance to system erro...

引用

12th IEEE Global Conference on Consumer Electronics, GCCE 2023

作者： Hu, Yiduan Tsuji, Airi Fujinami, Kaori Tokyo University of Agriculture and Technology Grad. School of Bio-Functions and Systems Science Tokyo Japan Tokyo University of Agriculture and Technology Div. of Advanced Information Technology and Computer Science Tokyo Japan

ISBN: (纸本)9798350340181

Technologies that support behavior change are often implemented in systems such as health advice and social support in daily life. However, users might distrust the systems and eventually cease using them if there is a measurement or judgment error, which would go against the goal of behavior improvement. Based on the assumption that failures are inevitable, this study proposes a strategy to prevent withdrawal from the system by making the system reliable and empathetic. An anthropomorphic garbage-disposal system that has the capability of revealing vulnerability is introduced, to increase the users' awareness of trash reduction. © 2023 IEEE.

关键词： Behavioral research

来源：评论

学校读者我要写书评

暂无评论

Investigating the Determinants of Compliance Intention in Behavior Change Support systems 29

Investigating the Determinants of Compliance Intention in Be...

引用

29th Annual Americas Conference on Information systems: Diving into Uncharted Waters, AMCIS 2023

作者： Ekpezu, Akon Obu Oinas-Kukkonen, Harri Wiafe, Isaac Faculty of Information Technology and Electrical Engineering Oulu Advanced Research on Service and Information Systems University of Oulu Finland Department of Computer Science University of Ghana Ghana

ISBN: (纸本)9781713893592

The effectiveness of behavior change support systems (BCSS) in promoting health and well-being is unflinching. However, its long-term effectiveness is hindered by non-compliance. Research in BCSS that focuses on compliance is scarce, particularly the determinants of compliance intention are not well established. To address this gap, this study investigated the determinants of compliance intention in BCSS by extending the persuasive system design model to include competence, effectiveness, enjoyment, and persuasiveness. By surveying a sample of prospective BCSS users (N=234), partial least squares structural equation modeling was used to evaluate the proposed model. The findings suggest that the prospective users’ perceptions of primary task support and dialogue support, as well as social support and credibility support significantly influenced their perceptions of self-competence and system effectiveness respectively. These perceptions influenced enjoyment, then persuasiveness, and finally compliance intention. Future studies will validate these findings on the compliance behavior of BCSS. © 2023 29th Annual Americas Conference on Information systems, AMCIS 2023. All rights reserved.

关键词： Behavior Change Support systems Compliance Intention Persuasive systems Design Persuasive technology Physical Activity

来源：评论

学校读者我要写书评

暂无评论

Study on Landslide Susceptibility Evaluation Based on Improved Multivariable Weighted Model: A Case Study of Lushan County, China 3

Study on Landslide Susceptibility Evaluation Based on Improv...

引用

3rd IEEE International Conference on Software Engineering and Artificial Intelligence, SEAI 2023

作者： Zhao, Li Duan, Gonghao Wuhan Institute of Technology School of Computer Science and Engineering Wuhan China Automation for Complex Systems Hubei Key Laboratory of Advanced Control and Intelligent Wuhan China

ISBN: (纸本)9798350337952

The evaluation of regional geological hazard susceptibility is of great significance to the prevention and control of geological hazard. In this paper, the "4-20"Lushan earthquake disaster area as the research area, combined with GIS and characteristics of the research area, through correlation analysis, selected 9 influencing factors as the evaluation factors. The study was conducted using a weighted information volume-logistic regression model (WI-LR). The results were classified into five sensitivity levels: very low, low, medium, high and very high. The results show that the landslide prone areas in Lushan County are concentrated in the area below the middle of the county seat, mostly near rivers, faults and areas with peak acceleration greater than 0.4. Among them, WI-LR model (AUC=0.918) > deterministic factor model (CF =0.908) > weighted information quantity model (WI) (AUC=0.896) > information quantity model I (AUC=0.853) > information quantity logistic regression model I-LR (AUC=0.799). It indicates that WI-LR model has high evaluation accuracy. © 2023 IEEE.

关键词： Hazards

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study on Edge-to-Cloud Continuum for Smart Applications: Performance, Design Patterns, and Key Factors 8

An Empirical Study on Edge-to-Cloud Continuum for Smart Appl...

引用

8th IEEE International Conference on Edge Computing and Communications, EDGE 2024

作者： Chen, Norman Toosi, Adel N. Javadi, Bahman Alqahtani, Daghash Aslanpour, Mohammad S. Xu, Minxian Monash University Department of Software Systems and Cybersecurity Clayton Australia Western Sydney University School of Computer Data and Mathematical Sciences Australia Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China

ISBN: (纸本)9798350368499

The rapid evolution of cloud-native technologies has facilitated seamless application deployment and execution across the entire edge-to-cloud continuum. This continuum offers a myriad of benefits, including reduced latency, optimized bandwidth utilization, enhanced data privacy, improved reliability, scalability, and flexibility. However, realizing a coherent edge-to-cloud continuum poses challenges especially in resource management, due to the heterogeneous and dynamic nature of computing resources such as resource scheduling and load balancing. This paper focuses on the Container-as-a-Service model enabling independent execution of functions/microservices anywhere on the continuum. We propose an architectural design for constructing a practical edge-to-cloud infrastructure and conduct comprehensive performance evaluations using a real edge-to-cloud testbed. Through an empirical study, we aim to identify key factors impacting application performance and resource management within the continuum, with a specific focus on AI-based IoT applications. Our experiments explore various design patterns including load balancing techniques, scheduling algorithms, invocation methods, gateway and data source location, and factors such as bandwidth and delay, providing practical insights for practitioners and researchers alike. © 2024 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Cabin: A Compressed Adaptive Binned Scan Index

引用

Proceedings of the ACM on Management of Data 2024年第1期2卷 1-26页

作者： Yiyuan Chen Shimin Chen SKLP and Center for Advanced Computer Systems Institute of Computing Technology CAS & University of Chinese Academy of Sciences Beijing China

Scan is a fundamental operation widely used in main-memory analytical database systems. To accelerate scans, previous studies build either record-order or sort-order structures known as scan indices. While achieving good performance, scan indices often incur significant space overhead, limiting their use in main-memory databases. For example, the most recent and best performing scan index, BinDex, consists of a sort-order position array, which is an array of rowIDs in the value order, and a set of record-order bit vectors, representing records in pre-defined value intervals. The structures can be much larger than the base data column *** this paper, we propose a novel scan index, Cabin, that exploits the following three techniques for better time-space tradeoff. 1) filter sketches that represent every 2^w-2 value intervals with a w-bit sketched vector, thereby exponentially reducing the space for the bit vectors; 2) selective position array that removes the rowID array for a fraction of intervals in order to lower the space overhead for the position array; and 3) data-aware intervals that judiciously select interval boundaries based on the data characteristics to better support popular values in skewed data distributions or categorical attributes. Experimental results show that compared with state-of-the-art scan solutions, Cabin achieves better time-space tradeoff, and attains 1.70 -- 4.48x improvement for average scan performance given the same space budget.

关键词： data awareness filter sketches scan index time-space tradeoff

来源：评论

学校读者我要写书评

暂无评论

Project Assessment in Offshore Software Maintenance Outsourcing Using Deep Extreme Learning Machines

引用

computers, Materials & Continua 2023年第1期74卷 1871-1886页

作者： Atif Ikram Masita Abdul Jalil Amir Bin Ngah Saqib Raza Ahmad Salman Khan Yasir Mahmood Nazri Kama Azri Azmi Assad Alzayed Faculty of Ocean Engineering Technology and Informatics University Malaysia TerengganuKuala NerusMalaysia Department of Computer Science&Information Technology Faculty of Information TechnologyThe University of LahoreLahore54000Pakistan Department of Software Engineering Faculty of Information TechnologyThe University of LahoreLahore54000Pakistan Advanced Informatics Department Razak Faculty of Technology and InformaticsUniversiti Teknologi Malaysia54100Kuala LumpurMalaysia Computer Science and Information Systems Department College of Business Studies Public Authority for Applied Education and Training(PAAET)AdailiyahKuwait Department of Computer Science Sharif College of Engineering&TechnologyLahore54000Pakistan

Software maintenance is the process of fixing,modifying,and improving software deliverables after they are delivered to the *** can benefit from offshore software maintenance outsourcing(OSMO)in different ways,including time savings,cost savings,and improving the software quality and *** of the hardest challenges for the OSMO vendor is to choose a suitable project among several clients’*** goal of the current study is to recommend a machine learning-based decision support system that OSMO vendors can utilize to forecast or assess the project of OSMO *** projects belong to OSMO vendors,having offices in developing countries while providing services to developed *** the current study,Extreme Learning Machine’s(ELM’s)variant called Deep Extreme Learning Machines(DELMs)is used.A novel dataset consisting of 195 projects data is proposed to train the model and to evaluate the overall efficiency of the proposed *** proposed DELM’s based model evaluations achieved 90.017%training accuracy having a value with 1.412×10^(-3) Root Mean Square Error(RMSE)and 85.772%testing accuracy with 1.569×10^(-3) RMSE with five DELMs hidden *** results express that the suggested model has gained a notable recognition rate in comparison to any previous *** current study also concludes DELMs as the most applicable and useful technique for OSMO client’s project assessment.

关键词： Software outsourcing deep extreme learning machine(DELM) machine learning(ML) extreme learning machine assessment

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：