检索结果-内蒙古大学图书馆

A Multiform Many-objective Evolutionary Algorithm for Multi-label Feature Selection in Classification

IEEE Transactions on Evolutionary Computation 2024年

作者： Hancer, Emrah Xue, Bing Zhang, Mengjie Victoria University of Wellington Center for Data Science and Artificial Intelligence School of Engineering and Computer Science Wellington6140 New Zealand Burdur Mehmet Akif Ersoy University Department of Software Engineering Burdur15039 Turkey

Multi-label classification (MLC) deals with instances associated with multiple labels simultaneously and often includes high dimensional data with noisy, irrelevant, and redundant features. Feature selection for MLC is crucial for achieving successful classification performance. However, no unified metric exists for evaluating learning performance in MLC tasks. Instead, multiple metrics exist, each assessing a different aspect of the classification process, and these metrics are often inconsistent with one another. Consequently, multi-label feature selection (MLFS) becomes a many-objective optimization problem (MaOP) when optimizing three or more classification metrics and the number of selected features simultaneously. Evolutionary computation (EC) techniques have shown great promise in addressing many-objective tasks due to their ability to effectively explore large and complex search spaces. EC techniques can handle multiple objectives concurrently, making them well-suited for the challenges posed by MLFS. Despite this potential, research on EC-based MLFS methods remains limited, with few studies treating it as a MaOP. To address this gap, this paper proposes a new many-objective evolutionary algorithm within a multiform framework. The proposed algorithm leverages distinct sub-populations to address specific MLFS tasks, incorporates a strategy to exchange information between MLFS tasks, employs a local density-based selection mechanism to maintain diverse high-quality solutions, and uses an adaptive parameter scheme inspired by stochastic gradient descent to guide the search towards new regions in the objective space. Experimental results demonstrate the superiority of the proposed algorithm across a diverse range of high-dimensional datasets, outperforming both recently introduced many-objective and conventional MLFS algorithms. © 1997-2012 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Snapshot boosting: a fast ensemble framework for deep neural networks

引用

science China(Information sciences) 2020年第1期63卷 77-88页

作者： Wentao ZHANG Jiawei JIANG Yingxia SHAO Bin CUI Center for Data Science Peking University National Engineering Laboratory for Big Data Analysis and Applications Department of Computer Science Beijing Key Lab of Intelligent Telecommunications Software and Multimedia School of Computer ScienceBeijing University of Posts and Telecommunications Key Lab of High Confidence Software Technologies Department of Computer SciencePeking University

Boosting has been proven to be effective in improving the generalization of machine learning models in many fields. It is capable of getting high-diversity base learners and getting an accurate ensemble model by combining a sufficient number of weak learners. However, it is rarely used in deep learning due to the high training budget of the neural network. Another method named snapshot ensemble can significantly reduce the training budget, but it is hard to balance the tradeoff between training costs and diversity. Inspired by the ideas of snapshot ensemble and boosting, we propose a method named snapshot boosting. A series of operations are performed to get many base models with high diversity and accuracy, such as the use of the validation set, the boosting-based training framework, and the effective ensemble strategy. Last, we evaluate our method on the computer vision(CV) and the natural language processing(NLP) tasks, and the results show that snapshot boosting can get a more balanced trade-off between training expenses and ensemble accuracy than other well-known ensemble methods.

关键词： ensemble learning deep learning boosting neural network snapshot ensemble

来源：评论

学校读者我要写书评

暂无评论

How to Select Pre-Trained Code Models for Reuse? A Learning Perspective

arXiv

引用

arXiv 2025年

作者： Bi, Zhangqian Wan, Yao Chu, Zhaoyang Hu, Yufei Zhang, Junyi Zhang, Hongyu Xu, Guandong Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Wuhan China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Big Data and Software Engineering Chongqing University Chongqing China School of Computer Science University of Technology Sydney Sydney Australia

Pre-training a language model and then fine-tuning it has shown to be an efficient and effective technique for a wide range of code intelligence tasks, such as code generation, code summarization, and vulnerability detection. However, pre-training language models on a large-scale code corpus is computationally expensive. Fortunately, many off-the-shelf Pre-trained Code Models (PCMs), such as CodeBERT, CodeT5, CodeGen, and Code Llama, have been released publicly. These models acquire general code understanding and generation capability during pre-training, which enhances their performance on downstream code intelligence tasks. With an increasing number of these public pre-trained models, selecting the most suitable one to reuse for a specific task is essential. In this paper, we systematically investigate the reusability of PCMs. We first explore three intuitive model selection methods that select by size, training data, or brute-force fine-tuning. Experimental results show that these straightforward techniques either perform poorly or suffer high costs. Motivated by these findings, we explore learning-based model selection strategies that utilize pre-trained models without altering their parameters. Specifically, we train proxy models to gauge the performance of pre-trained models, and measure the distribution deviation between a model's latent features and the task's labels, using their closeness as an indicator of model transferability. We conduct experiments on 100 widely-used open-source PCMs for code intelligence tasks, with sizes ranging from 42.5 million to 3 billion parameters. The results demonstrate that learning-based selection methods reduce selection time to 100 seconds, compared to 2,700 hours with brute-force fine-tuning, with less than 6% performance degradation across related tasks. © 2025, CC BY-NC-SA.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Deep Wavelet Frequency Laplacian Pyramid Network for Vehicle Logo Super-Resolution 5

Deep Wavelet Frequency Laplacian Pyramid Network for Vehicle...

引用

5th International Conference on Pattern Recognition and Artificial intelligence, PRAI 2022

作者： Yu, Yue She, Kun Kang, Jian Jackson, Jehoiada Shaukat, Hayat Li, Yang University of Electronic Science and Technology of China Information and Software Engineering Chengdu China Sichuan Provincial Big Data Technology Services Center Chengdu China Iqra National University Department of Computer Science Peshawar Pakistan

ISBN: (数字)9781665499163

ISBN: (纸本)9781665499163

In intelligent transportation systems, generated high-resolution images promote high-level version tasks compared to captured low-resolution vehicle logo images, which lack adequate details. However, the resolution of vehicle logo images is restricted by factors like hardware. Few attempts have been made with the Laplacian pyramid structure, while images can be represented on multi-scale in the wavelet domain. This paper proposes a progressive reconstruction network with a Laplacian pyramid (WLapsrn) structure to predict the sub-bands of wavelet transformed images. Firstly, we adopted a suitable network architecture for feature extraction using residual blocks for the advanced reconstruction network in the wavelet domain. Then, the Texture-Charbonnier loss function is used to achieve highfrequency sub-bands reconstruction. Ultimately, the inverse 2D discrete stationary wavelet transform is applied to generate predicting HR images from mapped coefficients. Extensive objective and subjective evaluations using benchmark datasets demonstrate that the proposed algorithm achieves superior visual effects compared with the state-of-the-art Laplacian-based algorithms. © 2022 IEEE.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

How to Select Pre-Trained Code Models for Reuse? A Learning Perspective

How to Select Pre-Trained Code Models for Reuse? A Learning ...

引用

IEEE International Conference on software Analysis, Evolution and Reengineering (SANER)

作者： Zhangqian Bi Yao Wan Zhaoyang Chu Yufei Hu Junyi Zhang Hongyu Zhang Guandong Xu Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Wuhan China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Big Data and Software Engineering Chongqing University Chongqing China School of Computer Science University of Technology Sydney Sydney Australia

ISBN: (数字)9798331535100

ISBN: (纸本)9798331535117

Pre-training a language model and then fine-tuning it has shown to be an efficient and effective technique for a wide range of code intelligence tasks, such as code generation, code summarization, and vulnerability detection. However, pre-training language models on a large-scale code corpus is compu-tationally expensive. Fortunately, many off-the-shelf Pre-trained Code Models (PCMs), such as CodeBERT, CodeT5, CodeGen, and Code Llama, have been released publicly. These models acquire general code understanding and generation capability during pre-training, which enhances their performance on downstream code intelligence tasks. With an increasing number of these public pre-trained models, selecting the most suitable one to reuse for a specific task is essential. In this paper, we systematically investigate the reusability of PCMs. We first explore three intuitive model selection methods that select by size, training data, or brute-force fine-tuning. Experimental results show that these straightforward techniques either perform poorly or suffer high costs. Motivated by these findings, we explore learning-based model selection strategies that utilize pre-trained models without altering their parameters. Specifically, we train proxy models to gauge the performance of pre-trained models, and measure the distribution deviation between a model's latent features and the task's labels, using their closeness as an indicator of model transferability. We conduct experiments on 100 widely-used open-source PCMs for code intelligence tasks, with sizes ranging from 42.5 million to 3 billion parameters. The results demonstrate that learning-based selection methods reduce selection time to 100 seconds, compared to 2,700 hours with brute-force fine-tuning, with less than 6% performance degradation across related tasks.

关键词： Phase change materials Analytical models Adaptation models Codes Costs Computational modeling Training data Machine learning software software development management

来源：评论

学校读者我要写书评

暂无评论

Medical Image Fusion Solid Works Supporting Multiple Techniques with Feature-Level Transforms 2

Medical Image Fusion Solid Works Supporting Multiple Techniq...

引用

2nd International Conference on Sustainable Computing and data Communication Systems, ICSCDS 2023

作者： Mutha, Rakhi Pathak, Devendra Nath Ahuja, Vandana Bhandari, Prabhakar Ramesh Rahi, Pankaj Mamodiya, Udit Lovely Professional University Department of Computer Application Punjab India Poornima College of Engineering Department of Computer Science and Engineering Rajasthan Jaipur India Swami Vivekanand Institute of Engineering and Technology Department of Computer Science and Engineering Punjab India Sevadal Mahila Mahavidyalaya Department of Microbiology Umred Road Maharashtra Nagpur India Poornima Institute of Engineering and Technology Department of Artificial Intelligence & Data Science Rajasthan Jaipur India Piet Aicte Idea Lab Poornima Institute of Engineering and Technology Department of Electrical Engineering Rajasthan Jaipur India

ISBN: (纸本)9781665491990

The use of group classifiers on similar features has resulted in computationally expensive and tedious, making them unsuitable for online applications. The clustering techniques are evaluated for both inter-subject and intra-subject variations, and it is discovered that intra-subject order execution is superior. Another approach to dealing with object recognition from medical images is considered. This is known as similarity matching, and it is a computationally simple process as compared to costly and complex characterization computations. The major challenges that occur in the image processing are high noise levels, limited image resolution, and geometric deformations throughout the image. © 2023 IEEE.

关键词： Image resolution

来源：评论

学校读者我要写书评

暂无评论

Agile Ontology: A Dynamic Framework for E-Business Evolution

Agile Ontology: A Dynamic Framework for E-Business Evolution

引用

Emerging Smart Technologies and Applications (eSmarTA), International Conference on

作者： Mohammad Mustafa Taye Rawan Abulail Belal Al-Ifan Software Engineering Department Philadelphia University Amman Jordan Computer Science Department Philadelphia University Amman Jordan Data Science and Artificial Intelligence Department Philadelphia University Amman Jordan

ISBN: (数字)9798350354133

ISBN: (纸本)9798350354140

In this work, a progressed version of Extreme Programming (XP) for e-business is provided. In an effort to efficiently address the precise troubles of this dynamic industry, the strategy promotes iterative procedures and more functions. By including new elements that guide growth, independence, and fine manipulation, Enhanced XP for E-business (EXPe) builds upon the fundamental XP concepts of continuous feedback and collaboration. The e-business enterprise faces challenges such as rapidly evolving marketplace needs and the want for scalable, adaptive solutions. EXPe targets to cope with these by using selling iterative development and incorporating more suitable functionalities to help non-stop adaptation and scalability. The layout prioritizes user standards, adds more scalability mechanisms, and employs iterative improvement techniques to help development teams adapt quickly and efficaciously to changing E-enterprise desires. This study indicates that EXPe is a great choice for quickly and efficaciously growing E-business solutions due to its many benefits and capabilities. This technique aims to provide a strong foundation for engaging in non-intrusive studies on agile methods. Enhanced XP for E-Business (EXPe) uniquely integrates ontology-unique requirements and semantic research into the agile framework, extensively enhancing the adaptability and scalability of e-commercial enterprise solutions. Furthermore, listed for this purpose are applicable files and XP artifacts, including user stories.

关键词： Scalability Layout User centered design Semantics Collaboration Ontologies Programming

来源：评论

学校读者我要写书评

暂无评论

Container lifecycle-aware scheduling for serverless computing

Container lifecycle-aware scheduling for serverless computin...

引用

作者： Wu, Song Tao, Zhiheng Fan, Hao Huang, Zhuo Zhang, Xinmin Jin, Hai Yu, Chen Cao, Chun National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University Nanjing China

Elastic scaling in response to changes on demand is a main benefit of serverless computing. When bursty workloads arrive, a serverless platform launches many new containers and initializes function environments (known as cold starts), which incurs significant startup latency. To reduce cold starts, platforms usually pause a container after it serves a request, and reuse this container for subsequent requests. However, this reuse strategy cannot efficiently reduce cold starts because the schedulers are agnostic of container lifecycle. For example, it may ignore soon available containers or evict soon needed containers. We propose a container lifecycle-aware scheduling strategy for serverless computing, CAS. The key idea is to control distribution of requests and determine creation or eviction of containers according to different lifecycle phases of containers. We implement a prototype of CAS on OpenWhisk. Our evaluation shows that CAS reduces 81% cold starts and therefore brings a 63% reduction at 95th percentile latency compared with native scheduling strategy in OpenWhisk when there is worker contention between workloads, and does not add significant performance overhead. © 2021 John Wiley & Sons Ltd.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

A big data Analytic and IoT-Based Approach for Addressing Water Scarcity in Jordan

A Big Data Analytic and IoT-Based Approach for Addressing Wa...

引用

Computational intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Abdelraouf Ishtaiwi Nuha El-Khalili May Alnashashibi Mohammad Abu Arqoub Dept. of Data Science and Artificial Intelligence University of Petra Amman Jordan Department of Software Engineering University of Petra Amman Jordan Department of Computer Science University of Petra Amman Jordan

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

Water scarcity critically threatens agricultural sus-tainability in Jordan, necessitating innovative technological solutions. This study presents a comprehensive framework that integrates Internet of Things (IoT) sensors with big data Analytics to optimize water usage in agriculture. Employing a multi-stage approach, we conducted real-time data acquisition from diverse farms, processed the data using clustering algorithms, and implemented intelligent decision-making systems. Our analysis focused on key parameters such as soil moisture, temperature, rainfall, and wind speed across various farming locations. The methodology encompassed extensive field data collection, advanced analytics, and the deployment of smart irrigation systems. Results demonstrated a significant 25 % reduction in water consumption while maintaining optimal crop yields. Additionally, clustering identified three distinct farm categories, each requiring tailored water management strategies. This research contributes to the field of smart agriculture by providing practical, scalable solutions for regions facing severe water scarcity. The findings highlight the potential of advanced technologies to enhance agricultural sustainability and address critical water management challenges.

关键词： Temperature sensors Smart agriculture Irrigation Wind speed Soil moisture big data Real-time systems Internet of Things Sustainable development Water resources

来源：评论

学校读者我要写书评

暂无评论

Drone Stereo Vision for Radiata Pine Branch Detection and Distance Measurement: Utilizing Deep Learning and YOLO Integration

arXiv

引用

arXiv 2024年

作者： Lin, Yida Xue, Bing Zhang, Mengjie Schofield, Sam Green, Richard Centre for Data Science and Artificial Intelligence Victoria University of Wellington Wellington New Zealand Department of Computer Science and Software Engineering Canterbury University Canterbury New Zealand

This research focuses on the development of a drone equipped with pruning tools and a stereo vision camera to accurately detect and measure the spatial positions of tree branches. YOLO is employed for branch segmentation, while two depth estimation approaches, monocular and stereo, are investigated. In comparison to SGBM, deep learning techniques produce more refined and accurate depth maps. In the absence of ground-truth data, a fine-tuning process using deep neural networks is applied to approximate optimal depth values. This methodology facilitates precise branch detection and distance measurement, addressing critical challenges in the automation of pruning operations. The results demonstrate notable advancements in both accuracy and efficiency, underscoring the potential of deep learning to drive innovation and enhance automation in the agricultural sector. Copyright © 2024, The Authors. All rights reserved.

关键词： Drones

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：