检索结果-内蒙古大学图书馆

A Comparative Study of Machine Learning Algorithms on Datasets of Varying Sizes 1

9th Future Technologies Conference, FTC 2024

作者： Huang, Xiaoting Xi, Xuelian Wang, Siqi Sadeghi, Zahra Samir, Asif Matwin, Stan Department of Electrical and Computer Engineering Dalhousie University HalifaxNSB3H4R2 Canada Department of Computer Science Dalhousie University HalifaxNSB3H1W5 Canada

ISBN: (数字)9783031731259

ISBN: (纸本)9783031731242

This research investigates the nuanced performance dynamics of machine learning algorithms across datasets of varying sizes. Employing three distinct datasets characterized by different sample sizes, we implement four machine learning algorithms—Logistic Regression, K Nearest Neighbors (KNN), Naïve Bayes, and Random Forest. This paper delineates the application methodologies, hyperparameter tuning procedures, and the resultant performance outcomes. Our findings reveal that Logistic Regression and Naïve Bayes exhibit relatively minor sensitivity to dataset size fluctuations. In stark contrast, KNN is markedly influenced by dataset size, showcasing significant performance variations. Notably, Random Forest demonstrates consistently superior performance across the four machine learning models considered, particularly excelling with the largest datasets. The implications of these observations are discussed, contributing to a comprehensive understanding of the interplay between machine learning algorithms and dataset characteristics. The effectiveness of a machine learning algorithm does not rely solely on expanding the dataset size. Our research indicates that once a certain threshold is reached, merely increasing the dataset size does not proportionally improve performance. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Graph-Based Deep Learning Model for the Anti-Money Laundering Task of Transaction Monitoring 16th

A Graph-Based Deep Learning Model for the Anti-Money Launder...

引用

16th International Joint Conference on Computational Intelligence, IJCCI 2024

作者： Bakhshinejad, Nazanin Nguyen, Uyen Trang Ghahremani, Shahram Soltani, Reza Department of Electrical Engineering and Computer Science York University 4700 Keele St TorontoONM3J 1P3 Canada

ISBN: (纸本)9789897587214

Anti-money laundering (AML) refers to a comprehensive framework of laws, regulations, and procedures to prevent bad actors from disguising illegally obtained funds as legitimate income. The AML framework encompasses customer identity verification and risk assessment, monitoring transactions to detect suspicious money laundering activities, and reporting suspicious transactions to regulators. In this paper, we focus on the transaction monitoring task of the AML framework. We propose a graph convolutional networks (GCN) model to classify transactions as legitimate or suspicious of money laundering. We tested and evaluated the model on a publicly available large dataset to promote reproducibility. The proposed model was trained and evaluated using the classification objectives for AML transaction monitoring per industry standard. We describe in detail our solutions to the class imbalance problem typical of AML datasets. We present comprehensive experiments to demonstrate and justify how the important parameters of the model were optimized and selected. This helps to support reproducibility and comparison with future work. © 2024 by SCITEPRESS – science and Technology Publications, Lda.

关键词： Laundering

来源：评论

学校读者我要写书评

暂无评论

PR-FCNN: a data-driven hybrid approach for predicting PM2.5 concentration

引用

Discover Artificial Intelligence 2024年第1期4卷 1-22页

作者： Inam, Syed Azeem Khan, Abdullah Ayub Mazhar, Tehseen Ahmed, Noor Shahzad, Tariq Khan, Muhammad Amir Saeed, Mamoon M. Hamam, Habib Department of Artificial Intelligence and Mathematical Sciences Sindh Madressatul Islam University Karachi74000 Pakistan Department of Computer Science Bahria University Karachi Campus Sindh Karachi75000 Pakistan Department of Computer Science and information Technology School Education Department Government of Punjab Layyah 31200 Pakistan Department of Computer Science Shaheed Zulfiqar Ali Bhutto Institute of Science and Technology Karachi Pakistan Department of Computer Science COMSATS University Islamabad Sahiwal Campus Sahiwal57000 Pakistan School of Computing Sciences College of Computing Informatics and Mathematics Universiti Teknologi MARA Selangor Shah Alam40450 Malaysia Sana’a Yemen Faculty of Engineering Uni de Moncton MonctonNBE1A3E9 Canada School of Electrical Engineering University of Johannesburg Johannesburg 2006 South Africa Av. Grandes Ecoles Libreville BP 1989 Gabon Bridges for Academic Excellence Spectrum Tunis Tunisia

The atmosphere’s fine articulate Matter (PM2.5) poses various health-related risks. Even though multiple efforts have been made to lower the emissions of these substances, the mortality rate is continuously increasing, requiring immediate inclination of the scientific community towards the design and development of advanced predictive models. Conventional statistical approaches have become dormant due to their limitations in capturing the innate relationships between the pollutants, particularly for predicting PM2.5 concentrations. In contrast, machine and deep learning techniques have shown great potential for forecasting air quality, providing more accuracy than its predecessor techniques. The present study investigates the utilization of hybrid approaches by integrating machine learning models with deep learning models to improve the prediction capabilities of PM2.5 concentration. It uses datasets from the World Air Quality Index (WAQI) and the State of Global Air (SOGA) to analyze the performance of the models on both the daily and annual data, respectively. This ensures the model’s effectiveness on a diversified dataset. The present study implements Random Forest (RF), Polynomial Regression (PR), XGBoost, and Extra Tree Regressor (ETR) coupled with Fully Connected Neural Network (FCNN), Long Short-Term Memory (LSTM), and Bi-directional LSTM (Bi-LSTM) for obtaining optimized results. Finally, after a thorough investigation, the hybrid PR model coupled with FCNN (PR-FCNN) is found to be the best model with improved R-squared (R2) values, portraying its potential for predicting PM2.5 concentration accurately. Based on the experimentation, the preset study recommends implementing hybrid approaches, offering better predictive accuracy in forecasting air pollutants, especially PM2.5. © The Author(s) 2024.

关键词： Health risks

来源：评论

学校读者我要写书评

暂无评论

AI-Navigated Fog Computing based Portable Ambient Particulate Matter Sensor Calibration

AI-Navigated Fog Computing based Portable Ambient Particulat...

引用

2023 International Conference on Sustainable Communication Networks and Application, ICSCNA 2023

作者： Sahaya Sakila, V. Manohar, S. College of Engineering and Technology Srm Institute of Science and Technology Department of Computer Science and Engineering Vadapalani Campus No. 1 Jawaharlal Nehru Road TamilNadu Vadapalani India

ISBN: (纸本)9798350313987

Bull Trench Kilns, shortly referred as BTK are one of the major sources of emitting Particulate Matter (PM) pollutants in air, which is harmful to the environment, and it has the capability to remain suspended in the air for very long duration. As conventional fixed pollution monitoring stations are sparsely located, and Brick industries are generally located in remote locations, BTK's pollutant emission rate is not exactly been recorded/monitored. In this study, portable PM sensor along with a reference sensor are mounted near the Brick Kilns and the pollutant's concentration in air along with the atmospheric temperature and humidity are measured. Since PM sensors are sensitive to atmospheric factors, its readings are calibrated using Machine Learning (ML) techniques, with the help of data collected from reference sensor, to provide more reliable data. The proposed AI-navigated three phase architecture is used to calibrate the readings obtained from the sensor, where Linear Support Vector Regression (LSVR) obtained best results. © 2023 IEEE.

关键词： Artificial Intelligence Bull Trench Kiln Calibrated Sensor Readings Machine Learning Particulate Matter

来源：评论

学校读者我要写书评

暂无评论

SyREC: A Symbolic-Regression-Based Ensemble Combiner 36

SyREC: A Symbolic-Regression-Based Ensemble Combiner

引用

36th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2024

作者： Fong, Kei Sen Motani, Mehul Department of Electrical and Computer Engineering Singapore College of Design and Engineering Singapore Institute of Data Science Singapore N.1 Institute for Health Singapore National University of Singapore Singapore

ISBN: (纸本)9798331527235

Symbolic Regression (SR) is the task of finding a concise white-box mathematical expression that fulfills a given machine learning (ML) objective. In this work, we introduce the first-of-its-kind SR-based ensemble combiner (SyREC) for ML which utilizes the quasi-arithmetic mean (parameterized by a function f) as an ensemble combiner and discovers f via SR. Our Sy REC demonstrates advantages over existing ensemble combiners, i.e., averaging methods and meta-learners. Compared to averaging methods, Sy REC allows for increased combiner complexity via exploring a large function class and provides a learning process to tune the ensemble combiner to the specific dataset. Compared to meta-learners, SyREC preserves important ensemble properties, like idempotency, monotonicity and boundedness, which produce predictions more consistent with the base models. We note SyREC produces a white-box ensemble combiner that lies in the intersection of both categories of existing combiners, addressing the weaknesses while capturing the strengths of each category. To evaluate Sy REC, we present experiments on 16 open-source PMLB datasets and commonly used base models, including a large variety of experiments and analyses across different settings: (i) regression and classification tasks, (ii) equally weighted combiners and custom-weighted combiners, (iii) homogeneous and heterogeneous ensembles, (iv) sequential and parallel ensembles. We find that in all these settings, SyREC shows consistent improvement over existing ensembling approaches. This indicates that SyREC is a robust ensemble combiner, which produces explainable and consistent ensemble predictions. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Memory Allocation Scheme for Batch Jobs with Intel Optane DC Persistent Memory and DRAM 9

Heterogeneous Memory Allocation Scheme for Batch Jobs with I...

引用

9th International Conference on Applied System Innovation, ICASI 2023

作者： Chang, Che-Wei Zhang, Kai-Jie Chang Gung University School of Electrical and Computer Engineering College of Engineering Department of Computer Science and Information Engineering No.259 Wenhua 1st Rd. Guishan Dist. Taoyuan333 Taiwan

ISBN: (纸本)9798350398380

It is a promising approach to include Non-Volatile Memory (NVM) and DRAM together as the main memory to provide huge memory space for large objects and guarantee short access latency for frequent writes and reads. To provide feasible and suitable memory allocation for all applications on a sever, our solution analyzes applications to derive the read-write ratio, memory footprint, and access pattern of each application. Heterogenous memory allocation scheme is then developed to reduce the makespan of batch jobs. © 2023 IEEE.

关键词： Dynamic random access storage

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Model for Predicting Individual Substance Abuse with Associated Risk-Factors

引用

Annals of Data science 2023年第6期10卷 1607-1634页

作者： Islam, Uwaise Ibna Haque, Enamul Alsalman, Dheyaaldin Islam, Muhammad Nazrul Moni, Mohammad Ali Sarker, Iqbal H. Department of Computer Science and Engineering Chittagong University of Engineering & Technology Chittagong4349 Bangladesh University of Waterloo WaterlooONN2L 3G1 Canada School of Engineering Computing and Informatics Dar Al-Hekma University Jeddah Saudi Arabia Department of Computer Science and Engineering Military Institute of Science and Technology Dhaka1216 Bangladesh School of Health and Rehabilitation Sciences Faculty of Health and Behavioural Sciences The University of Queensland St LuciaQLD4072 Australia

Substance abuse is the unrestrained and detrimental use of psychoactive chemical substances, unauthorized drugs, and alcohol that can ultimately lead a human to disastrous consequences. As patients with this behavior display a high value of relapse, the best intervention approach is to prevent it at the very beginning. In this paper, we propose a framework based on machine learning techniques to identify individual vulnerability towards substance abuse by analyzing socio-economic aspects. We have carefully assessed the commonly involved causes to form the questionnaire for collecting data from healthy people and patients suffering from substance abuse. Using Pearson’s chi-squared test of independence, feature importance is measured to eliminate less significant features using backward elimination. Popular machine learning classification algorithms (Random Forest, Decision Tree, Logistic Regression, Support Vector Machine, K-Nearest neighbors, and Gaussian Naive Bayes) are used to build the predictive classifier. To identify the key risk-factors of individual substance abuse, we extract association rules from the significant features and subsequent factors. Experimental results on real data-set support the effectiveness of the proposed framework. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

Hands and Palms Recognition by Transfer Learning for Forensics: A Comparative Study 23

Hands and Palms Recognition by Transfer Learning for Forensi...

引用

23rd International Conference on New Trends in Intelligent Software Methodologies, Tools and Techniques, SoMeT 2024

作者： Fattahi, Jaouhar Fkiri, Obeb Mejri, Mohamed Ghayoula, Ridha Department of Computer Science and Software Engineering Laval University 2325 rue de l'Université QuebecQCG1V 0A6 Canada Department of Computer Science National School of Engineers of Carthage University of Carthage Tunis Tunisia Faculty of Engineering Information Systems Department University of Moncton New Brunswick Canada

ISBN: (纸本)9781643685380

In the realm of forensic science, precise identification of individuals holds paramount importance in both investigative procedures and legal proceedings. Hands and palms recognition has emerged as a valuable biometric modality within forensic applications, owing to the distinct and intricate features inherent to these anatomical regions. The elaborate patterns of veins, creases, and ridges present on palms and fingers serve as rich sources of biometric data, crucial for accurate identification purposes. Furthermore, given the frequent involvement of hands and palms in criminal activities such as theft and assault, their recognition becomes imperative for establishing links between suspects and crime scenes. However, developing robust recognition systems tailored for forensic applications poses notable challenges, including variations in hand poses, lighting conditions, and image quality. To address these hurdles, sophisticated deep learning techniques, notably transfer learning, have been employed. By harnessing pre-trained deep learning models namely NasNetLarge, NasNetMobile, and EfficientNet, initially trained on expansive datasets for general image recognition tasks, we can adapt these models to the specific task of hands and palms recognition in forensic contexts. Our findings reveal that all three models consistently achieved over 92% accuracy across all metrics evaluated, demonstrating their efficacy as strong contenders for the hands-and-palms recognition task. Notably, the EfficientNet model exhibited superior performance compared to its counterparts, boasting more than 95.8% accuracy, precision, F1-score and recall, along with more than 98.6% specificity and 99.4% AUC. © 2024 IOS Press. All rights reserved.

关键词： Palmprint recognition

来源：评论

学校读者我要写书评

暂无评论

Socialized Learning: A Survey of the Paradigm Shift for Edge Intelligence in Networked Systems

引用

IEEE Communications Surveys and Tutorials 2024年第3期27卷 2085-2128页

作者： Wang, Xiaofei Zhao, Yunfeng Qiu, Chao Hu, Qinghua Leung, Victor C. M. Tianjin University College of Intelligence and Computing Tianjin300072 China Shenzhen518000 China Shenzhen MSU-BIT University Artificial Intelligence Research Institute Shenzhen518172 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China The University of British Columbia Department of Electrical and Computer Engineering VancouverV6T 1Z4 Canada

Amidst the robust impetus from artificial intelligence (AI) and big data, edge intelligence (EI) has emerged as a nascent computing paradigm, synthesizing AI with edge computing (EC) to become an exemplary solution for unleashing the full potential of AI services. Nonetheless, challenges in communication costs, resource allocation, privacy, and security continue to constrain its proficiency in supporting services with diverse requirements. In response to these issues, this paper introduces socialized learning (SL) as a promising solution, further propelling the advancement of EI. SL is a learning paradigm predicated on social principles and behaviors, aimed at amplifying the collaborative capacity and collective intelligence of agents within the EI system. SL not only enhances the system's adaptability but also optimizes communication, and networking processes, essential for distributed intelligence across diverse devices and platforms. Therefore, a combination of SL and EI may greatly facilitate the development of collaborative intelligence in the future network. This paper presents the findings of a literature review on the integration of EI and SL, summarizing the latest achievements in existing research on EI and SL. Subsequently, we delve comprehensively into the limitations of EI and how it could benefit from SL. Special emphasis is placed on the communication challenges and networking strategies and other aspects within these systems, underlining the role of optimized network solutions in improving system efficiency. Based on these discussions, we elaborate in detail on three integrated components: socialized architecture, socialized training, and socialized inference, analyzing their strengths and weaknesses. Finally, we identify some possible future applications of combining SL and EI, discuss open problems and suggest some future research, with the hope of arousing the research community's interest in this emerging and exciting interdisciplinary field. © 1

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

6G service-oriented space-air-ground integrated network: A survey

引用

Chinese Journal of Aeronautics 2022年第9期35卷 1-18页

作者： Nan CHENG Jingchao HE Zhisheng YIN Conghao ZHOU Huaqing WU Feng LYU Haibo ZHOU Xuemin SHEN School of Telecommunications Engineering Xidian UniversityXi’an 710071China School of Cyber Engineering Xidian UniversityXi’an 710071China Department of Electrical and Computer Engineering University of WaterlooWaterloo N2L 3G1Canada School of Computer Science and Engineering Central South UniversityChangsha 410083China School of Electronic Science and Engineering Nanjing UniversityNanjing 210023China

As an indispensable component of the emerging 6G networks,Space-Air-Ground Inte-grated Networks(SAGINs)are envisioned to provide ubiquitous network connectivity and services by integrating satellite networks,aerial networks,and terrestrial *** 6G SAGINs,a wide variety of network services with the features of diverse requirements,complex mobility,and multi-dimensional resources will pose great challenges to service provisioning,which urges the develop-ment of service-oriented *** this paper,we conduct a comprehensive review of 6G SAGINs from a new perspective of service-oriented ***,we present the requirements of service-oriented networks,and then propose a service-oriented SAGINs management *** categories of critical technologies are presented and discussed,i.e.,heterogeneous resource orchestration technologies and the cloud-edge synergy technologies,which facilitate the interoperability of different network segments and cooperatively orchestrate heterogeneous resources across different domains,according to the service features and *** addition,the potential future research directions are also presented and discussed.

关键词： Mobile Edge Computing(MEC) Network Function Virtual-ization(NFV) Network slicing Service-oriented network Software Defined Network-ing(SDN) Space-Air-Ground Inte-grated Networks(SAGINs)

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：