检索结果-内蒙古大学图书馆

Multi-Level and Multi-Segment Learning Multitask Optimization via a Niching Method

IEEE Transactions on Evolutionary Computation 2024年

作者： Xue, Zhao-Feng Wang, Zi-Jia Jiang, Yi Zhan, Zhi-Hui Kwong, Sam Zhang, Jun Guangzhou University School of Computer Science and Cyber Engineering Guangzhou510006 China South China University of Technology School of Computer Science and Engineering Guangzhou510006 China Nankai University College of Artificial Intelligence Tianjin300350 China Lingnan University Department of Data Science Hong Kong Hong Kong Nankai University China ERICA Hanyang University Korea Republic of

Knowledge transfer (KT) has been regarded as an efficient method in evolutionary multitask optimization (EMTO) by utilizing the information of other tasks to promote the optimization of the current task. Most KT methods achieve information communication across index-aligned dimensions. However, the index-aligned dimensions are not always similar or related, which is not always suitable for communication and causes the low efficiency in KT. Moreover, when the KT occurs in the heterogeneous tasks with different dimensions, the task with lower dimensions often pads the extra dimensions to make their dimensions equal. However, the dimension-padding often involves the redundant or useless information, which may mislead the KT process. In this paper, a novel multi-level and multi-segment learning multitask optimization (MMLMTO) algorithm based on niching technique is proposed to achieve high-quality KT. Firstly, a multi-level learning strategy is proposed to divide the population into three levels according to fitness values for better selecting the individuals for KT. Secondly, a multi-segment learning strategy is proposed to split some top individuals in each level into several segments, and each segment will find its closest segment to form a niche, where the KT is executed. This ensures that KT occurs in the similar or related dimensions and avoids the dimension-padding to eliminate the influence of the redundant information. Experimental results on IEEE CEC2017 and IEEE CEC2022 multitask benchmarks fully demonstrate the effectiveness of MMLMTO, which can significantly outperform other state-of-the-art multitask algorithms. Finally, MMLMTO is applied to a real-world multitask rover navigation application problem to further demonstrate its applicability. © 1997-2012 IEEE.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Phishing Web Page Detection using Web Scraping

Phishing Web Page Detection using Web Scraping

引用

IEEE Southeastcon

作者： Mallika Boyapati Ramazan Aygun School of Data Science and Analytics Kennesaw State University Kennesaw GA USA Department of Computer Science Kennesaw State University Kennesaw GA USA

In today’s Internet era, webpages act as major user interfaces for the applications hosted by the organizations. One of the most common security attacks on the web page applications is phishing attacks. Phishing is a social engineering attack in which an adversary tries to steal user credentials by tricking them to believe that they are on a legitimate web page. Adversaries are using sophisticated and new ways to forge the web page designs craftily to trick the users into visiting the malicious links. The phishing webpages are used as a medium to carry out the art of phishing attacks. Web scraping is a methodology to extract features of each webpage. In this paper, web scraping is employed to extract hybrid feature set to implement Machine Learning (ML) models. The machine learning models like XGBoost, Multilayer Perceptron, Logistic Regression, SVM, Auto Encoder, Random Forest, Decision Trees, K-means, and Naive Bayes are built. All the models are tested with and without applying principal component analysis (PCA), a feature reduction technique. Extracting hybrid features by employing web scraping to train the ML models and finding the key features contributing to phishing detection on Phishpedia, Kaggle, and PhishTank datasets is the key contribution of this paper. Results show that XGBoost algorithm outperformed the all other classifiers with 98% accuracy or higher on the web scraped features on all the datasets. The model achieved higher precision and recall when compared to other approaches like CANTINA+, URL based approaches, SenseInput, Knowing Thy Domain, and Phishpedia on the Phishpedia dataset.

关键词： Uniform resource locators Visualization Machine learning algorithms Web page design Phishing Virtual assistants Web pages

来源：评论

学校读者我要写书评

暂无评论

A Multi-faceted Vulnerability Searching Website Powered by Aspect-level Vulnerability Knowledge Graph

A Multi-faceted Vulnerability Searching Website Powered by A...

引用

International Conference on Software Engineering - Companion, ICSE, Companion

作者： Jiamou Sun Zhenchang Xing Qinghua Lu Xiwei Xu Liming Zhu Data61 Eveleigh CSIRO Sydney Australia Research School of Computer Science CECS Australian National University Canberra Australia School of Computer Science University of New South Wales Sydney Australia

Vulnerabilities can cause damages to users. With heavy dependencies among software, it is particularly important to safely select the dependent libraries and maintain security of software in a targeted manner, which require deep understanding of potential weakness of third-party libraries. Current vulnerability advisories only support rough-level description-based vulnerability information searching, which cannot cater the needs of in-depth investigation and understanding of vulnerabilities. Driven by the real needs, we propose a vulnerability aspect-level vulnerability knowledge graph integrating diversified vulnerability key aspect information from heterogeneous vulnerability databases. Based on the knowledge graph, we implement a multi-faceted vulnerability searching website for statistics and details acquiring of vulnerabilities. Our use cases demonstrate the usefulness of our knowledge graph and website to the software security. Demo Video https://***/vYSy7MYIU48 Source Code: https://***/sjmsjmdsg/Multi_faceted_Web Website: see GitHub repository

关键词：

来源：评论

学校读者我要写书评

暂无评论

What Makes Good In-context Demonstrations for Code Intelligence Tasks with LLMs?

arXiv

引用

arXiv 2023年

作者： Gao, Shuzheng Wen, Xin-Cheng Gao, Cuiyun Wang, Wenxuan Zhang, Hongyu Lyu, Michael R. School of Computer Science and Technology Harbin Institute of Technology Shenzhen China Department of Computer Science and Engineering The Chinese University of Hong Kong China School of Big Data and Software Engineering Chongqing University China

Pre-trained models of source code have gained widespread popularity in many code intelligence tasks. Recently, with the scaling of the model and corpus size, large language models have shown the ability of in-context learning (ICL). ICL employs task instructions and a few examples as demonstrations, and then inputs the demonstrations to the language models for making predictions. This new learning paradigm is training-free and has shown impressive performance in various natural language processing and code intelligence tasks. However, the performance of ICL heavily relies on the quality of demonstrations, e.g., the selected examples. It is important to systematically investigate how to construct a good demonstration for code-related tasks. In this paper, we empirically explore the impact of three key factors on the performance of ICL in code intelligence tasks: the selection, order, and number of demonstration examples. We conduct extensive experiments on three code intelligence tasks including code summarization, bug fixing, and program synthesis. Our experimental results demonstrate that all the above three factors dramatically impact the performance of ICL in code intelligence tasks. Additionally, we summarize our findings and provide takeaway suggestions on how to construct effective demonstrations, taking into account these three perspectives. We also show that a carefully-designed demonstration based on our findings can lead to substantial improvements over widely-used demonstration construction methods, e.g., improving BLEU-4, EM, and EM by at least 9.90%, 175.96%, and 50.81% on code summarization, bug fixing, and program synthesis, respectively. © 2023, CC BY.

关键词： Demonstrations

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approaches for Battery Capacity and State of Charge Estimation with the NASA B0005 dataset

引用

computers, Materials & Continua 2025年第6期83卷 4795-4813页

作者： Zeyang Zhou Zachary James Ryan Utkarsh Sharma Tran Tien Anh Shashi Mehrotra Angelo Greco Jason West Mukesh Prasad School of Computer Science Faculty of Engineering and Information TechnologyUniversity of Technology SydneyUltimoNSW 2007Australia School of Data Science and Engineering Indian Institute of Science Education and ResearchBhopal462066India Research Institute of Marine Systems Engineering Seoul National UniversitySeoul08826Republic of Korea Department of Computer Science and Engineering Faculty of Engineering and TechnologySRM Institute of Science and TechnologyDelhi NCR CampusGhaziabad201204India Battery System Modelling Department CLARIOS VARTA Hannover GmbHHanover30419Germany Science and Innovation Group Bureau of MeteorologyBrisbane4000Australia

Accurate capacity and State of Charge(SOC)estimation are crucial for ensuring the safety and longevity of lithium-ion batteries in electric *** study examines ten machine learning architectures,Including Deep Belief Network(DBN),Bidirectional Recurrent Neural Network(BiDirRNN),Gated Recurrent Unit(GRU),and others using the NASA B0005 dataset of 591,458 *** indicate that DBN excels in capacity estimation,achieving orders-of-magnitude lower error values and explaining over 99.97%of the predicted variable’s *** computational efficiency is paramount,the Deep Neural Network(DNN)offers a strong alternative,delivering near-competitive accuracy with significantly reduced prediction *** GRU achieves the best overall performance for SOC estimation,attaining an R^(2) of 0.9999,while the BiDirRNN provides a marginally lower error at a slightly higher computational *** contrast,Convolutional Neural Networks(CNN)and Radial Basis Function Networks(RBFN)exhibit relatively high error rates,making them less viable for real-world battery *** of error distributions reveal that the top-performing models cluster most predictions within tight bounds,limiting the risk of overcharging or deep *** findings highlight the trade-off between accuracy and computational overhead,offering valuable guidance for battery management system(BMS)designers seeking optimal performance under constrained *** work may further explore advanced data augmentation and domain adaptation techniques to enhance these models’robustness in diverse operating conditions.

关键词： Battery capacity estimation state of charge deep learning prediction efficiency energy storage systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Personalized Healthcare via Capturing Disease Severity, Interaction, and Progression

Enhancing Personalized Healthcare via Capturing Disease Seve...

引用

IEEE International Conference on data Mining (ICDM)

作者： Yanchao Tan Zihao Zhou Leisheng Yu Weiming Liu Chaochao Chen Guofang Ma Xiao Hu Vicki S Hertzberg Carl Yang College of Computer and Data Science Fuzhou University Fuzhou China Department of Computer Science Rice University Houston United States College of Computer Science Zhejiang University Hangzhou China School of Computer Science Zhejiang Gongshang University Hangzhou China Nell Hodgson Woodruff School of Nursing Emory University Atlanta United States Department of Computer Science Emory University Atlanta United States

Personalized diagnosis prediction based on electronic health records (EHR) of patients is a promising yet challenging task for AI in healthcare. Existing studies typically ignore the heterogeneity of diseases across different patients. For example, diabetes can have different complications across different patients (e.g., hyperlipidemia and circulatory disorder), which requires personalized diagnoses and treatments. Specifically, existing models fail to consider 1) varying severity of the same diseases for different patients, 2) complex interactions among syndromic diseases, and 3) dynamic progression of chronic diseases. In this work, we propose to perform personalized diagnosis prediction based on EHR data via capturing disease severity, interaction, and progression. In particular, we enable personalized disease representations via severity-driven embeddings at the disease level. Then, at the visit level, we propose to capture higher-order interactions among diseases that can collectively affect patients’ health status via hypergraph-based aggregation; at the patient level, we devise a personalized generative model based on neural ordinary differential equations to capture the continuous-time disease progressions underlying discrete and incomplete visits. Extensive experiments on two real-world EHR datasets show significant performance gains brought by our approach, yielding average improvements of 10.70% for diagnosis prediction over state-of-the-art competitors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of an IoT-Based Sensor for Indirect Measurement of Underwater CO2 Levels in Aquascape Environments

Development of an IoT-Based Sensor for Indirect Measurement ...

引用

computer sciences, Engineering, and Technology Innovation (ICoCSETI), International Conference on

作者： Ivan Diryana Sudirman Boby Siswanto Entrepreneurship Department Binus Business School Undergraduate Program Bina Nusantara University Bandung Indonesia School of Computer Science Bina Nusantara University Bandung Indonesia

ISBN: (数字)9798331508616

ISBN: (纸本)9798331508623

This research develops and tests a modified air pocket chamber with a Non-Dispersive Infrared (NDIR) sensor monitoring aquarium CO 2 levels. While conventional drop checkers offer delayed and non-digital CO 2 data, this work aimed to create a more responsive and affordable aquascaping tool. The device catches and analyzes CO 2 emitted into an air pocket in a partially submerged chamber to estimate indirect CO 2 using an MH-Z19B sensor. Initial tests revealed water pressure and CO 2 buildup in the chamber producing inaccurate readings. Subsequently, a modified chamber was designed to address these issues. The altered gadget detected variations in CO 2 content, stabilizing at 800–900 ppm without aeration and declining to 400–500 ppm with aeration, according to tests. With a mean concentration of 677.56 ppm and a standard deviation of 167.76 ppm, CO 2 data revealed modest variability in response to aeration conditions. The results verify that the modified chamber provides a less expensive substitute for digital measurement tools since it can track aquascaping CO 2 levels.

关键词： Technological innovation Monitoring Standards

来源：评论

学校读者我要写书评

暂无评论

Attention guided filter for jointly extracting entities and classifying relations 33

Attention guided filter for jointly extracting entities and ...

引用

33rd International Conference on Software Engineering and Knowledge Engineering, SEKE 2021

作者： Chen, Shaoze Wang, Su Hu, Wenxin School of Computer Science and Technology East China Normal University Shanghai China School of Data Science Engineering East China Normal University Shanghai China

ISBN: (纸本)1891706527

Jointly extracting entities and classifying relations aims to detect all possible triples from unstructured text with a single model. Tagging-based method effectively improves the performance of jointly relation extraction. However, some tagging-based approaches ignored that one entity pair may exist multiple relations and others set an empirical threshold value for selecting one or more relevant relations, which becomes the bottlenecks of the model. As a solution, we propose the attention guided filter, namely, AGFRel, which introduces transformer blocks to learn the number of relations for every entity pair to filter out irrelevant relations. Moreover, each module of the model has a multi-head attention guided layer to highlight valuable information. Extensive experimental results show that AGFRel is capable of gaining better performance on various tasks including overlapping triples extraction and multiple triples extraction. On NYT and WebNLG public datasets, our model obtains F1 score 90.8 and 91.9 respectively and achieves a new state-of-the-art performance. © 2021 Knowledge Systems Institute Graduate school. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Twenty years of e-learning in health science: A bibliometric

引用

Procedia computer science 2023年 216卷 604-612页

作者： Fairuz Iqbal Maulana M. Aldiki Febriantono Dwi Risza Budi Raharja Khaeruddin Ridho Herasmara Computer Science Department School of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Diploma III Electronic Technology Vocational Study Program University of Muhammadiyah Malang Indonesia Electrical Engineering Faculty of Science and Technology Raden Rahmat Islamic University Malang Indonesia

Education about health sciences has historically been limited in the curriculum of health professionals and largely inaccessible to the public. In practice, most of the health science education is still running conventionally. Supposedly with the advancement of technology and the use of the internet everywhere, learning such as e-learning can be important, especially in the health sector. Until this research was conducted, only 514 academic documents about e-learning in health sciences were found for 20 years from 2001 to 2020, obtained in searching on the Scopus database. This study presents a comprehensive overview of studies related to E-learning in the Health sciences sector. This study uses bibliometric analysis and indexed digital methods to map scientific publications throughout the world. This research employs the Scopus database to gather information, as well as the Scopus online analysis tool and Vosviewer to show the bibliometric network. The method consists with five stages: determining search keywords, initial search results, refinement of search results, initial compilation, and data analysis. Among the most published and indexed articles by Scopus, papers published by researchers in the United States have the highest number of publications (80), followed by United Kingdom (63) and Australia with 45 academic publications. The processed data shows the pattern and trend of increasing the number of international publications in E-learning in Health sciences field, which Scopus index.

关键词： e-learning health science bibliometric vosviewer education

来源：评论

学校读者我要写书评

暂无评论

XC-NAS: A New Cellular Encoding Approach for Neural Architecture Search of Multi-path Convolutional Neural Networks

arXiv

引用

arXiv 2023年

作者： Londt, Trevor Gao, Xiaoying Andreae, Peter Mei, Yi Centre for Data Science and Artificial Intelligence School of Engineering and Computer Science Victoria University of Wellington PO Box 600 Wellington6140 New Zealand

Convolutional Neural Networks (CNNs) continue to achieve great success in classification tasks as innovative techniques and complex multi-path architecture topologies are introduced. Neural Architecture Search (NAS) aims to automate the design of these complex architectures, reducing the need for costly manual design work by human experts. Cellular Encoding (CE) is an evolutionary computation technique which excels in constructing novel multi-path topologies of varying complexity and has recently been applied with NAS to evolve CNN architectures for various classification tasks. However, existing CE approaches have severe limitations. They are restricted to only one domain, only partially implement the theme of CE, or only focus on the micro-architecture search space. This paper introduces a new CE representation and algorithm capable of evolving novel multi-path CNN architectures of varying depth, width, and complexity for image and text classification tasks. The algorithm explicitly focuses on the macro-architecture search space. Furthermore, by using a surrogate model approach, we show that the algorithm can evolve a performant CNN architecture in less than one GPU day, thereby allowing a sufficient number of experiment runs to be conducted to achieve scientific robustness. Experiment results show that the approach is highly competitive, defeating several state-of-the-art methods, and is generalisable to both the image and text domains. Copyright © 2023, The Authors. All rights reserved.

关键词： Convolutional neural networks

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：