检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 2456-2457页

作者： Cheng, Ran Escalante, Hugo Jair Tu, Wei-Wei Rijn, Jan N. Van Wang, Shuo Yang, Yun Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen518055 China Instituto Nacional de Astrofísica Óptica y Electrónica Computer Science Department Puebla72840 Mexico 4Paradigm Inc. Beijing100089 China RA Leiden2300 Netherlands The University of Birmingham School of Computer Science BirminghamB15 2TT United Kingdom Yunnan University National Pilot School of Software Kunming650504 China

The five papers in this special section address different aspects of automated machine learning (AutoML) from fundamental algorithms to real-world applications. Developing high-performance machine learning models is a difficult task that usually requires expertise from data scientists and knowledge from domain experts. To make machine learning more accessible and ease the labor-intensive trial-and-error process of searching for the most appropriate machine learning algorithm and the optimal hyperparameter setting, AutoML was developed and has become a rapidly growing area in recent years. AutoML aims at automation and efficiency of the machine learning process across domains and applications. Nowadays, data is commonly collected over time and susceptible to changes, such as in Internet-of-Things (IoT) systems, mobile phone applications and healthcare data analysis. It poses new challenges to the traditional AutoML with the assumption of data stationarity. Interesting research questions arise around whether, when and how to effectively and efficiently deal with non-stationary data in AutoML. © 2020 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

A Survey on Masked Facial Detection Methods and Datasets for Fighting Against COVID-19

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2022年第3期3卷 323-343页

作者： Wang, Bingshu Zheng, Jiangbin Chen, C. L. Philip Northwestern Polytechnical University School of Software Taicang Campus Suzhou215400 China South China University of Technology School of Computer Science and Engineering Guangzhou510641 China

Coronavirus disease 2019 (COVID-19) continues to pose a great challenge to the world since its outbreak. To fight against the disease, a series of artificial intelligence (AI) techniques are developed and applied to real-world scenarios such as safety monitoring, disease diagnosis, infection risk assessment, and lesion segmentation of COVID-19 CT scans. The coronavirus epidemics have forced people wear masks to counteract the transmission of virus, which also brings difficulties to monitor large groups of people wearing masks. In this article, we primarily focus on the AI techniques of masked facial detection and related datasets. We survey the recent advances, beginning with the descriptions of masked facial detection datasets. A total of 13 available datasets are described and discussed in detail. Then, the methods are roughly categorized into two classes: conventional methods and neural network-based methods. The conventional methods are usually trained by boosting algorithms with hand-crafted features, which accounts for a small proportion. Neural network-based methods are further classified as three parts according to the number of processing stages. Representative algorithms are described in detail, coupled with some typical techniques that are described briefly. Finally, we summarize the recent benchmarking results, give the discussions on the limitations of datasets and methods, and expand future research directions. To our knowledge, this is the first survey about masked facial detection methods and datasets. Hopefully our survey could provide some help to fight against epidemics. © 2020 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Research on the Application of Binary Classification Dataset Based on Integrated Learning Model 2

Research on the Application of Binary Classification Dataset...

引用

2nd IEEE International Conference on Image Processing and computer Applications, ICIPCA 2024

作者： Huang, Jiaqi Zheng, Chongyang Feng, Guohuan Artificial Intelligence School Wuchang University of Technology Wuhan China Software College Northeastern University Shenyang China School of Engineering and Computer Science Oakland University Auburn Hills United States

ISBN: (纸本)9798350360240

The binary classification problem is a fundamental and core problem type in machine learning, and many machine learning algorithms, such as logistic regression and tree models, are widely used to solve binary classification problems. Based on the Kaggle open-source binary classification dataset, a prediction model for binary classification data was established using five different machine learning algorithms, namely KNN, decision tree, gradient boosting tree, random forest, and extreme random decision tree integration. The parameters of the models were determined through relevant theoretical analysis cross-validation methods, and the test accuracy of the five integrated learning models were compared, and the experimental results showed that the test accuracy of the gradient boosting tree and random forest models reached 93.23%, which indicated that these two models had the best prediction performance in solving the binary classification problem. In addition, these two models also have high stability. Therefore, this study provides strong support to the field of machine learning and demonstrates the potential of gradient boosted trees and random forests in solving real-world problems. © 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

Considerations in Prioritizing for Efficiently Refactoring the Data Clumps Model Smell: A Preliminary Study 19

Considerations in Prioritizing for Efficiently Refactoring t...

引用

19th International Conference on Evaluation of Novel Approaches to software engineering, ENASE 2024

作者： Baumgartner, Nils Iyenghar, Padma Pulvermüller, Elke Software Engineering Research Group School of Mathematics/Computer Science/Physics Osnabrück University Osnabrück49090 Germany innotec GmbH Hornbergstrasse 45 Filderstadt70794 Germany Faculty of Engineering and Computer Science HS Osnabrueck Osnabrück49009 Germany

ISBN: (纸本)9789897586965

This paper delves into the importance of addressing the data clumps model smell, emphasizing the need for prioritizing them before refactoring. Qualitative and quantitative criteria for identifying data clumps are outlined, accompanied by a systematic, simple but effective approach involving a weighted attribute system with threshold-based priority assignment. The paper concludes with an experimental evaluation of the proposed method, offering insights into critical areas for developers and contributing to improved code maintenance practices and overall quality. The approach presented provides a practical guide for enhancing software system quality and sustainability. © 2024 by SCITEPRESS – science and Technology Publications, Lda.

关键词： software design

来源：评论

学校读者我要写书评

暂无评论

CTNet:A Convolutional Transformer Network for Color Image Steganalysis

引用

Journal of computer science & Technology 2025年第2期40卷 413-427页

作者： Kang-Kang Wei Wei-Qi Luo Shun-Quan Tan Ji-Wu Huang School of Computer Science and Engineering Sun Yat-sen UniversityGuangzhou 510006China Guangdong Key Laboratory of Information Security Technology Sun Yat-sen UniversityGuangzhou 510006China College of Computer Science and Software Engineering Shenzhen UniversityShenzhen 518060China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen UniversityShenzhen 518060China Shenzhen Key Laboratory of Media Security Shenzhen UniversityShenzhen 518060China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen 518129China

Compared with convolutional neural network(CNN),Transformer can obtain global receptive field features more effectively and has recently achieved great success in natural language processing and computer *** to the particularity of steganography,however,almost all existing steganalytic networks just employ CNN with local receptive fields to detect embedding *** this paper,we propose a novel convolutional Transformer network for color image ***,we firstly obtain various image residuals for each color channel of an input image in the pre-processing *** capture more comprehensive steganalytic features,the truncated residuals after channel concatenation will pass through a feature extraction module composed of a CNN group and a Transformer *** CNN group aims to extract local receptive fields features,while the Transformer group with multi-head self-attention as the key tries to extract global steganalytic ***,we employ a global covariance pooling(GCP)and two fully-connected(FC)layers with dropout for *** comparative experiments demonstrate that the proposed method can significantly improve the detection performances in color image steganalysis and achieve state-of-the-art *** the proposed method is originally designed for color images,it can also obtain competitive results for grayscale images compared with the current best *** addition,we provide numerous ablation studies to verify the rationality of the proposed network architecture.

关键词： steganalysis steganography convolutional neural network Transformer color image

来源：评论

学校读者我要写书评

暂无评论

ProCQA: A Large-scale Community-based Programming Question Answering Dataset for Code Search 30

ProCQA: A Large-scale Community-based Programming Question A...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Li, Zehan Zhang, Jianfei Yin, Chuantao Ouyang, Yuanxin Rong, Wenge State Key Laboratory of Complex & Critical Software Environment Beihang University China Sino-French Engineer School Beihang University China School of Computer Science and Engineering Beihang University China

ISBN: (纸本)9782493814104

Retrieval-based code question answering seeks to match user queries in natural language to relevant code snippets. Previous approaches typically rely on pretraining models using crafted bi-modal and uni-modal datasets to align text and code representations. In this paper, we introduce ProCQA, a large-scale programming question answering dataset extracted from the StackOverflow community, offering naturally structured mixed-modal QA pairs. To validate its effectiveness, we propose a modality-agnostic contrastive pre-training approach to improve the alignment of text and code representations of current code language models. Compared to previous models that primarily employ bimodal and unimodal pairs extracted from CodeSearchNet for pre-training, our model exhibits significant performance improvements across a wide range of code retrieval benchmarks. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

MFN: Explainable DNA triple helixes Stabilized Design based on mCGR and flow network

MFN: Explainable DNA triple helixes Stabilized Design based ...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Wen, Xiaoru Sun, Lijun Xie, Lei Zheng, Yanfen Cao, Ben Wang, Bin Dalian University Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian China Dalian University of Technology School of Computer Science and Technology Dalian China

ISBN: (纸本)9798350386226

DNA triple helix structure, as a highly specific gene targeting tool, enable gene regulation by precisely identifying and binding to target DNA sequences. However, the limits of design quality and efficiency affect their wide application in gene therapy. Therefore, in this paper, we propose an antiparallel DNA triple helixes design method-MFN based on matrix chaotic game representation (mCGR) and flow network. Leveraging the structural characteristics of DNA sequences, this method employs the mCGR algorithm to construct an initial matrix, generating a set of DNA sequences that conform to foundational constraints. Then, these sequences are mapped as stream network nodes to screen crosstalk structures by path search, and the whole process is observable and interpretable. Experimental results show that MFN significantly improves the design efficiency of triple helix structure and reduces crosstalk phenomenon. Wet experiments further verify the effectiveness of the method. In summary, MFN achieves an efficient and high-quality design of DNA triple helixes and provides a new idea for targeted gene therapy. © 2024 IEEE.

关键词： Crosstalk

来源：评论

学校读者我要写书评

暂无评论

software Defect Prediction Using Ensemble Technique 9

Software Defect Prediction Using Ensemble Technique

引用

9th International Conference on Information Management and Technology, ICIMTech 2024

作者： Wicaksono, Pandu Arisaputra, Panji Yunanda, Rezky Kristian, Willy Mujhid, Almuzhidul School of Computer Science Bina Nusantara University Software Engineering Department Jakarta11480 Indonesia School of Information Systems Bina Nusantara University Information Systems Department Jakarta11480 Indonesia

ISBN: (纸本)9798350390025

software defect prediction is the methodical process of identifying code segments that are likely to have problems. This is done by analyzing software metrics and using categorization algorithms. This work introduces an alternate approach that utilizes ensemble learning techniques to improve the effectiveness of fault detection models. The models utilized in this study are CodeGPT and CodeBERT, both of which are transformer-based deep learning models that can extract code features from source code. The models are trained using the PROMISE dataset, which consists of Java projects that have been labeled with defects. The test results show that using ensemble learning methods can improve the accuracy, precision, recall, and F1 score of a single model by around 1-3%. This study contributes to the progress of software dependability and quality by utilizing advanced software fault prediction algorithms. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Domain Contrastive Learning for Multi-Site Alzheimer's Disease Classification 20

Domain Contrastive Learning for Multi-Site Alzheimer's Disea...

引用

20th International computer Conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2023

作者： Fiasam, Linda Delali Rao, Yunbo Sey, Collins Aggrey, Esther Stacy E. B. Kodjiku, Seth Larweh Browne, Judith Ayekai Danso, Juliana Mantebea Ukwuoma, Chiagoziem C. Gyarteng, Emmanuel S. A. School of Information and Software Engineering University of Electronic Science and Technology of China China School of Computer Science and Technology Zhejiang Gongshang University China School of Computer Science and Technology University of Electronic Science and Technology of China University China College of Nuclear Technology and Automation Engineering Chengdu University of Technology China

ISBN: (纸本)9798350318982

In the field of medical imaging, accurately classifying Alzheimer's Disease (AD) poses a substantial challenge, primarily due to the inherent variability in imaging data across different clinical sites. This paper introduces a novel approach, Domain Contrastive Learning (DCL), to address this challenge by enhancing the robustness and transferability of AD classification models using multi-site Magnetic Resonance Imaging (MRI) data. DCL leverages a unique contrastive learning technique within an autoencoder's latent space, enabling the extraction of domain-invariant features essential for accurate diagnosis. We rigorously evaluate the proposed network on brain images from three distinct imaging sites, employing a Domain Generalization (DG) training protocol to ensure robustness and generalizability across varying data sources. Our model is evaluated on three binary classification tasks: AD vs. Normal Control (NC), AD vs. Mild Cognitive Impairment (MCI), and MCI vs. NC. Results demonstrate that DCL outperforms existing methods, especially in AD vs. NC classification, achieving higher accuracy, sensitivity, and specificity with 0.51%, 1.54% and 1.68% increments respectively. This underscores DCL's potential as a robust and generalizable method for enhanced AD diagnosis, marking a significant step forward in medical imaging challenges in a multi-site context. © 2023 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Flexibility and Privacy: A Multi-Head Federated Continual Learning Framework for Dynamic Edge Environments 11

Flexibility and Privacy: A Multi-Head Federated Continual Le...

引用

11th International Symposium on Computing and Networking, CANDAR 2023

作者： Chen, Chunlu Wang, Kevin I-Kai Li, Peng Sakurai, Kouichi Kyushu University Graduate School of Information Science and Electrical Engineering Fukuoka Japan The University of Auckland Dept. of Electrical Computer and Software Engineering Auckland New Zealand The University of Aizu School of Computer Science and Engineering Aizuwakamatsu Japan Kyushu University Faculty of Information Science and Electrical Engineering Fukuoka Japan

ISBN: (纸本)9798350306705

Federated Learning (FL) and the Internet of Things (IoT) have revolutionized data processing and analysis, overcoming the traditional limitations of cloud computing. However, traditional machine learning strategies lead to increased costs and catastrophic forgetting due to model retraining with new datasets. Continual learning has been proposed to counter this, enabling models to adapt to new data while preserving previous knowledge, which is beneficial for dynamic edge environments. Despite these advantages, the retention of previous knowledge during the continual learning process may lead to the information leakage. To address the inherent challenges of multitask scenarios, we present a Federated Continual Learning (FCL) framework that integrates the privacy-preserving benefits of Federated Learning (FL) into a continual learning system, ensuring both continual learning and privacy preservation in edge computing data processing and analysis. Specifically, our architecture introduces dedicated fully-connected layers for each task. This architecture ensures that distinctive features pertinent to each task are not only captured but also preserved throughout the model's lifespan. Within our framework, data is processed via task-specific layers. Subsequently, the final label is determined by associating it with the paramount prediction value, thus capitalizing on the model's comprehensive knowledge reservoir to bolster prediction accuracy. We subjected our FCL framework to rigorous validation using two benchmark datasets: MNIST and CFAR-10. Experimental outcomes unequivocally substantiate the efficacy of our proposed methodology. © 2023 IEEE.

关键词： Learning systems

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：