检索结果-内蒙古大学图书馆

4th International Conference on Intelligent Technologies, CONIT 2024

作者： Guru Prasad, M.S. Devadas, Raghavendra M Hiremani, Vani Jahan, Afsar Praveen Gujjar, J. Dahiya, Aryan Department of Computer Science and Engg Dehradun India Manipal Institute of Technology Department of Information Technology Bengaluru India Manipal Academy of Higher Education Manipal India University Pune India Department of Computer Applications Dehradun India Faculty of Management Studies Bengaluru India

ISBN: (纸本)9798350349900

This innovative study utilizes machine learning techniques to analyze facial microbiome data, drawing inspiration from the metaphorical representation of microbial information through facial features. Leveraging the Olivetti Faces dataset as a model for facial microbiome data, the research introduces the Metagenomic Face framework. This framework facilitates the translation of microbial information into facial features, enabling the application of machine learning algorithms such as Random Forests or Neural Networks for pattern recognition. The investigation focuses on identifying correlations between facial features and underlying microbial compositions, aiming to assess the feasibility of classifying health and disease states based on these patterns. Preliminary results demonstrate promising outcomes, with precision, recall, and accuracy metrics reaching 0.94, 0.91, and 0.91, respectively, and support for the model encompassing 80 instances. These findings underscore the potential of Metagenomic Face as an innovative approach to microbiome analysis, shedding light on the intricate relationship between facial features and microbial communities. Furthermore, a comparative analysis involving Support Vector Machine, Logistic Regression, and Random Forest classifiers reveals compelling performance metrics. The Support Vector Machine Classifier attained an accuracy rate of 85%, the Logistic Regression Classifier showed an accuracy of 91%, and the Random Forest Classifier displayed a matching accuracy of 91%. These additional insights contribute to a comprehensive understanding of the Metagenomic Face framework's efficacy compared to alternative machine learning approaches, emphasizing its potential in advancing precision medicine through microbiome analysis. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

RFECV-DT: Recursive Feature Selection with Cross Validation using Decision Tree based Android Malware Detection

RFECV-DT: Recursive Feature Selection with Cross Validation ...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Naimisha Awasthi Prateek Raj Gautam Anuj Kumar Sharma Department of Computer Science and Engineering Centre for Advanced Studies AKTU Lucknow India School of Computer Science UPES Dehradun India Department of Mechatronics Centre For Advanced Studies AKTU Lucknow India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

The internet is extremely valuable, but it is also vulnerable to assault. Malware is a persistent and dynamic danger. Malware assaults entail introducing malicious code into software. The task was handled using a variety of machine learning approaches. Previous research utilized various methods, such as chi-square, Fisher’s score, and Forward/Backward methods. A recent work used a wrapper strategy of Recursive Feature Elimination with Cross-Validation using the nonlinear Support Vector Machine (SVM) as an estimator. This lowered the number of features from 215 to 74, yielding an accuracy percentage of 95.58%. Our solution improves on the previous strategy by using the same dataset and a decision tree with Recursive Feature Elimination with Cross-Validation using Decision Tree to identify 53 out of 215 feature. Classifiers other than Naive Bayes and Logistic Regression are all obtaining the highest accuracy of 98 %. This paper decreases the number of features by using Gini Impurity and Cross Validation for detection of Android Malware.

关键词： Support vector machines Logistic regression Accuracy Impurities Machine learning Feature extraction Malware Bayes methods Decision trees

来源：评论

学校读者我要写书评

暂无评论

MPEC: Manifold-Preserved EEG Classification via an Ensemble of Clustering-Based Classifiers

MPEC: Manifold-Preserved EEG Classification via an Ensemble ...

引用

International CSI computer Conference, CSICC

作者： Shermin Shahbazi Mohammad–Reza Nasiri Majid Ramezani Department of Electrical and Computer Engineering University of Zanjan Zanjan Iran Department of Computer Science and Information Technology Institute for Advanced Studies in Basic Sciences (IASBS) Zanjan Iran

ISBN: (数字)9798331523114

ISBN: (纸本)9798331523121

Accurate classification of EEG signals is crucial for brain-computer interfaces (BCls) and neuroprosthetic applications, yet many existing methods fail to account for the non-Euclidean, manifold structure of EEG data, resulting in suboptimal performance. Preserving this manifold information is essential to capture the true geometry of EEG signals, but traditional classification techniques largely overlook this need. To this end, we propose MPEC (Manifold-Preserved EEG Classification via an Ensemble of Clustering-Based Classifiers), that introduces two key innovations: (1) a feature engineering phase that combines covariance matrices and Radial Basis Function (RBF) kernels to capture both linear and non-linear relationships among EEG channels, and (2) a clustering phase that employs a modified K-means algorithm tailored for the Riemannian manifold space, ensuring local geometric sensitivity. Ensembling multiple clustering-based classifiers, MPEC achieves superior results, validated by significant improvements on the BCI Competition IV dataset 2a.

关键词： Manifolds Geometry Support vector machines Technological innovation Accuracy Sensitivity Brain modeling Electroencephalography Brain-computer interfaces Reliability

来源：评论

学校读者我要写书评

暂无评论

Beyond Deterrence: A Systematic Review of the Role of Autonomous Motivation in Organizational Security Behavior studies 25

Beyond Deterrence: A Systematic Review of the Role of Autono...

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI 2025

作者： Chen, Xiaowei Schöni, Lorin Distler, Verena Zimmermann, Verena Institute for Advanced Studies University of Luxembourg Esch-sur-Alzette Luxembourg Security Privacy & Society ETH Zurich Zurich Switzerland Department of Computer Science Aalto University Espoo Finland Department of Humanities Social and Political Sciences ETH Zürich Zürich Switzerland

ISBN: (纸本)9798400713941

What drives employees to ensure security when handling information assets in organizations? There is growing interest from the security behavior community in how autonomous motivators shape employees' security-related behaviors. To reconcile the scattered viewpoints on autonomous motivation and synthesize findings from studies utilizing various theoretical frameworks, we systematically reviewed relevant publications. We present a preregistered literature review that investigated (a) what forms of autonomous motivation have been examined in organizational security contexts, (b) which behaviors/behavioral intentions are related to autonomous motivators, and (c) how autonomous motivation affects employees' security behaviors. Based on an initial set of 432 papers, filtered down to 45 studies, we identified 17 unique autonomous motivators and three types of related security behaviors. This review not only develops a refined taxonomy of autonomous motivation related to security behaviors but also charts a path forward for future research on autonomous motivation in human-centered security. © 2025 Copyright held by the owner/author(s).

关键词： Motivation

来源：评论

学校读者我要写书评

暂无评论

Enhanced Bayesian Optimized Support Vector Machine (BO-SVM) Classification and Prediction of Heart Disease

Enhanced Bayesian Optimized Support Vector Machine (BO-SVM) ...

引用

Sentiment Analysis and Deep Learning (ICSADL), International Conference on

作者： P. Chairmadurai P. Kavitha S. Kamalakkannan Department of Computer Science School of Computing Sciences Vels Institute of Science Technology & Advanced Studies (VISTAS) Pallavaram Chennai India Department of Computer Applications School of Computing Sciences Vels Institute of Science Technology & Advanced Studies (VISTAS) Pallavaram Chennai India Department of Information Technology School of Computing Sciences Vels Institute of Science Technology & Advanced Studies (VISTAS) Pallavaram Chennai India

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

Medical data analysis is increasingly used to plan, improve research techniques, and explain diagnoses. The allocation of medical resources is based on the prevalence of specific pathologies. Artificial intelligence (AI) offers robust software solutions to analyze existing data and provide optimal predictions of medical outcomes. The dataset for heart disease prediction consists missing values in important features like cholesterol, ECG results and lifestyle factors. This research focuses to solve the issues in the traditional machine learning algorithm and designing a system model incorporating multiple data processing algorithms to classify heart disease. The classification process allows for the generation of a predictive model from training and testing datasets. These datasets are processed using an algorithm for classification to create a new model that can analyze detailed data, potentially with these same classes, by combining computational techniques with mathematical tools. This study uses optimization strategies to improve this model's performance and maximize prediction outcomes. This study aims to provide a framework to forecast cardiac problems based on significant risk using various classifier techniques, including the Bayesian Optimized SVM, to variables. The UCI repository is the source of the dataset utilized in this investigation. Linear Discriminant Analysis is used for feature extraction to decrease dimensionality and enhance the model's capacity to identify relevant patterns in the data. To generate the results as a precision, Recall, f1 score and accuracy.

关键词： Support vector machines Heart Accuracy Feature extraction Prediction algorithms Data models Bayes methods Optimization Medical diagnostic imaging Diseases

来源：评论

学校读者我要写书评

暂无评论

Enhancing Video Anomaly Detection Using Spatio-Temporal Autoencoders and Convolutional LSTM Networks

引用

SN computer science 2024年第1期5卷 190页

作者： Almahadin, Ghayth Subburaj, Maheswari Hiari, Mohammad Sathasivam Singaram, Saranya Kolla, Bhanu Prakash Dadheech, Pankaj Vibhute, Amol D. Sengan, Sudhakar Department of Networks and Cybersecurity Faculty of Information Technology Al Ahliyya Amman University Country Amman Jordan School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Chennai 600127 India Department of Networks and Cybersecurity Information Technology Al Ahliyya Amman University Amman Jordan Department Computing Technology School of Computing SRM Institute of Science and Technology Kattankulathur Campus Tamil Nadu Chennai 603203 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Guntur 522302 India Department of Computer Science and Engineering Swami Keshvanand Institute of Technology Management and Gramothan (SKIT) Rajasthan Jaipur 302017 India Symbiosis Institute of Computer Studies and Research (SICSR) Symbiosis International (Deemed University) MH Pune 411016 India Department of Computer Science and Engineering PSN College of Engineering and Technology Tamil Nadu Tirunelveli 627152 India

Identifying suspicious activities or behaviors is essential in the domain of Anomaly Detection (AD). In crowded scenes, the presence of inter-object occlusions often complicates the detection of such behaviors. Therefore, developing a robust method capable of accurately detecting and locating anomalous activities within video sequences becomes crucial, especially in densely populated environments. This research initiative aims to address this challenge by proposing a novel approach focusing on AD behaviors in crowded settings. By leveraging a spatio-temporal method, the proposed approach harnesses the power of both spatial and temporal dimensions. This enables the method to effectively capture and analyze the intricate motion patterns and spatial information embedded within the continuous frames of video data. The objective is to create a comprehensive model that can efficiently detect and precisely locate anomalies within complex video sequences, specifically those featuring human crowds. The efficacy of the proposed model will be rigorously evaluated using a benchmark dataset encompassing diverse scenarios involving crowded environments. The dataset is designed to simulate real-world conditions where millions of video footage need to be continuously monitored in real time. The focus is on identifying anomalies, which might occur within short time frames, sometimes as brief as five minutes or even less. Given the challenges posed by the massive volume of data and the requirement for rapid AD, the research emphasizes the limitations of traditional Supervised Learning (SL) methods in this context. © 2024, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Anomaly detection Autoencoders LSTM Machine learning Spatio-temporal features Suspicious activities

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Crime Monitoring and Alerting System using Hybrid Feature Engineering technique with IoT Technology

Deep Learning Crime Monitoring and Alerting System using Hyb...

引用

Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering (RMKMATE), International Conference on

作者： S. Arul. P. Kavitha S. Kamalakkannan Department of Computer Science School of Computing Sciences Vels Institute of Science Technology & Advanced Studies (VISTAS) Pallavaram Chennai India Department of Computer Applications School of Computing Sciences Vels Institute of Science Technology & Advanced Studies (VISTAS) Pallavaram Chennai India Department of Information Technology School of Computing Sciences Vels Institute of Science Technology & Advanced Studies (VISTAS) Pallavaram Chennai India

ISBN: (数字)9798331598488

ISBN: (纸本)9798331598495

This paper presents a Deep Learning-based Crime Monitoring and Alerting System that integrates IoT technology with a Hybrid Feature Engineering technique using Vision Transformer and Bidirectional Gated Recurrent Units. The system employs IoT devices, such as surveillance cameras, motion sensors, and microphones, to collect real-time environmental data. The HFE technique extracts spatial and temporal features, where ViT captures intricate spatial patterns from visual data, while BiGRU analyses time series sensor data to detect sequential anomalies indicative of criminal activities. By combining these deep learning models, the system identifies suspicious behaviours like unauthorized access, physical altercations, or disturbances with high accuracy and triggers immediate alerts to law enforcement for timely intervention. The integration of ViT for spatial feature extraction and BiGRU for temporal modelling enhances crime detection with minimal human intervention. This approach demonstrates the potential of IoT and Deep Learning to improve public safety, making crime monitoring more efficient, adaptive, and responsive.

关键词： Deep learning computer vision Accuracy Transformers Feature extraction Real-time systems Motion detection Internet of Things Monitoring Microphones

来源：评论

学校读者我要写书评

暂无评论

Weighting Heart Disease Criteria Using Multi-Criteria Decision-Making

Weighting Heart Disease Criteria Using Multi-Criteria Decisi...

引用

2023 Al-Sadiq International Conference on Communication and Information Technology, AICCIT 2023

作者： Muhammed, Saleh Mahdi Abdul-Majeed, Ghassan Mahmoud, Mahmoud Shuker Informatics Institute for Postgraduate Studies Iraqi Commission for Computers and Informatics Department of Computer Science Baghdad Iraq University of Baghdad College of Engineering Department of Computer Science Baghdad Iraq Al-Mansour University College Department of Communications Baghdad Iraq

ISBN: (纸本)9798350341881

Heart disease describes a group of conditions that affect the heart and there are many different factors including lifestyle, medical history, family history, and so on that may cause this complex disease. It is therefore important to consider multiple criteria, such as smoking status, blood pressure, and cholesterol levels to make informed decisions about patient priority management and treatment of HD. Multicriteria Decision Making (MCDM) allows us to identify and weigh the importance of each criterion. This approach can enhance the quality of patient care and improve clinical outcomes. Therefore, weighting HD criteria using MCDM is an essential step in achieving better healthcare outcomes in the management of HD. The FWZIC method was used in this study to weigh 11 heart disease parameters with the assistance of four cardiologists. The results of the criterion weights were without any difference in the preferences of the respective expert. Therefore, this method is flexible, robust, and useful in complex real-world problems. © 2023 IEEE.

关键词： Blood pressure

来源：评论

学校读者我要写书评

暂无评论

Improving Alpha-Beta Pruning Efficiency in Chess Engines 2

Improving Alpha-Beta Pruning Efficiency in Chess Engines

引用

2nd International Conference on IT Innovations and Knowledge Discovery, ITIKD 2024

作者： Nair, Rekha R Babu, Tina Kishore, S. Pavithra, K. Sumana, S.G. Alliance School of Advanced Computing Alliance University Department of Computer Science and Engineering Bengaluru India Nitte Institute of Professional Education Nitte (Deemed to Be University Department of Computer Applications Mangalore India Dayananda Sagar University Department of Computer Applications Bengaluru India

ISBN: (纸本)9798350355468

Alpha-Beta Pruning is a critical optimization technique in chess engines, helping them make fast, accurate decisions by reducing unnecessary calculations. This paper focuses on enhancing its efficiency to improve search depth and speed with-out compromising accuracy. This investigation examines current challenges in traditional implementations, such as inefficiencies in move ordering and redundant computations, especially in complex game scenarios. The proposed innovative strategies include dynamic move ordering powered by machine learning and improved transposition table management. These techniques streamline the pruning process, ensuring the most promising moves are evaluated first and avoiding repetitive calculations. Adaptive depth control is explored to make the algorithm more responsive to the game's context. Extensive testing on various chess positions demonstrated clear improvements in pruning efficiency. The enhanced algorithm can analyze deeper game trees with reduced computational costs, making chess engines faster and smarter. These advancements not only benefit chess engines but also have broader implications for Artificial Intelligence (AI) systems requiring efficient decision-making in dynamic environments. Improved Alpha-Beta Pruning methods make chess engines smarter and faster, allowing them to analyze deeper strategies while using less computing power. © 2025 IEEE.

关键词： Adaptive Depth Control Alpha-Beta Pruning Chess Engines Game Tree Analysis Move Ordering Optimization Transposition Table

来源：评论

学校读者我要写书评

暂无评论

Abnormal Mutations Evolution Strategies Don’t Require Gaussianity

arXiv

引用

arXiv 2025年

作者： de Nobel, Jacob Vermetten, Diederick Wang, Hao Kononova, Anna V. Rudolph, Günter Bäck, Thomas Leiden Institute for Advanced Computer Science Leiden Netherlands TU Dortmund University Department of Computer Science Dortmund Germany

The mutation process in evolution strategies has been interlinked with the normal distribution since its inception. Many lines of reasoning have been given for this strong dependency, ranging from maximum entropy arguments to the need for isotropy. However, some theoretical results suggest that other distributions might lead to similar local convergence properties. This paper empirically shows that a wide range of evolutionary strategies, from the (1+1)-ES to CMA-ES, show comparable optimization performance when using a mutation distribution other than the standard Gaussian. Replacing it with, e.g., uniformly distributed mutations, does not deteriorate the performance of ES, when using the default adaptation mechanism for the strategy parameters. We observe that these results hold not only for the sphere model but also for a wider range of benchmark problems. Copyright © 2025, The Authors. All rights reserved.

关键词： Evolutionary algorithms

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：