检索结果-内蒙古大学图书馆

Carrying Out CNN Channel Pruning in a White Box

IEEE Transactions on Neural Networks and Learning Systems 2023年第10期34卷 7946-7955页

作者： Zhang, Yuxin Lin, Mingbao Lin, Chia-Wen Chen, Jie Wu, Yongjian Tian, Yonghong Ji, Rongrong Xiamen University Media Analytics and Computing Laboratory Department of Artificial Intelligence School of Informatics Xiamen361005 China Youtu Laboratory Tencent Shanghai200233 China National Tsing Hua University Department of Electrical Engineering The Institute of Communications Engineering Hsinchu30013 Taiwan Peng Cheng Laboratory Shenzhen518000 China Peking University Department of Computer Science and Technology Beijing100871 China School of Informatics and the Institute of Artificial Intelligence Xiamen University Media Analytics and Computing Laboratory Department of Artificial Intelligence Xiamen361005 China

Channel pruning has been long studied to compress convolutional neural networks (CNNs), which significantly reduces the overall computation. Prior works implement channel pruning in an unexplainable manner, which tends to reduce the final classification errors while failing to consider the internal influence of each channel. In this article, we conduct channel pruning in a white box. Through deep visualization of feature maps activated by different channels, we observe that different channels have a varying contribution to different categories in image classification. Inspired by this, we choose to preserve channels contributing to most categories. Specifically, to model the contribution of each channel to differentiating categories, we develop a class-wise mask for each channel, implemented in a dynamic training manner with respect to the input image's category. On the basis of the learned class-wise mask, we perform a global voting mechanism to remove channels with less category discrimination. Lastly, a fine-tuning process is conducted to recover the performance of the pruned model. To our best knowledge, it is the first time that CNN interpretability theory is considered to guide channel pruning. Extensive experiments on representative image classification tasks demonstrate the superiority of our White-Box over many state-of-the-arts (SOTAs). For instance, on CIFAR-10, it reduces 65.23% floating point operations per seconds (FLOPs) with even 0.62% accuracy improvement for ResNet-110. On ILSVRC-2012, White-Box achieves a 45.6% FLOP reduction with only a small loss of 0.83% in the top-1 accuracy for ResNet-50. Code is available at https://***/zyxxμWhite-Box. © 2012 IEEE.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

The use of long short-term memory models to estimate soybean pricing: a regional climate data evaluation from Brazil

引用

IEEE Access 2025年 13卷 101869-101884页

作者： Oliva, Jefferson Tales Martelli, Otavio Pigozzo Barbosa, Marco Antonio De Castro Molin, Viviane Dal Casanova, Dalcimar Teixeira, Marcelo Federal University of Technology-Paraná Graduate Program in Electrical and Computer Engineering Pato Branco Brazil Federal University of Technology-Paraná Department of Academic Informatics Pato Branco Brazil Federal University of Technology-Paraná Graduate Program in Production and Systems Engineering Pato Branco Brazil

This work uses machine learning methods to analyze the influence of the Brazilian climate on international soybean price variability. For this purpose, climatic data, historical series of the extended national consumer price index, dollar price historical series, soybean harvest historical series, and international soybean price historical series are collected from different data sources. The data is then preprocessed and grouped by state. Afterward, data from the five most productive Brazilian states, Mato Grosso (MT), Mato Grosso do Sul (MS), Goiás (GO), Paraná (PR), and Rio Grande do Sul (RS), which together correspond to 74.9% of total production, are chosen. Then, predictive models were built using the long short-term memory (LSTM) method, which is applied to each state dataset considering two different settings: with and without climatic data. Thus, two models were built for each Brazilian state, totaling ten predictors. These models are evaluated using 10-fold sequential split cross-validation, whose predictive results are used for performance comparison through statistical hypothesis testing. In the experimental evaluation, when trained with climatic data, the PR model achieved the lowest average values of root mean squared error (RMSE) and mean absolute error (MAE), which are 20.90 and 16.72, respectively. Regarding predictors trained without climate data, the RS and PR obtained the lowest averaged values of RMSE (20.84) and MAE (16.81), respectively. After performing statistical hypothesis tests, no significant differences were found between the models, stating, with certainty 95%, that the Brazilian climatic data did not influence soybean prices in our study. © 2013 IEEE.

关键词： Brazilian Climatic Data Long-Short Term Memory Machine Learning Soybean Time Series

来源：评论

学校读者我要写书评

暂无评论

Chaotic binary reptile search algorithm and its feature selection applications

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第10期14卷 13931-13947页

作者： Abualigah, Laith Diabat, Ali Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman19328 Jordan Faculty of Information Technology Middle East University Amman11831 Jordan Division of Engineering New York University Abu Dhabi Saadiyat Island Abu Dhabi129188 United Arab Emirates Department of Civil and Urban Engineering Tandon School of Engineering New York University BrooklynNY11201 United States Faculty of Computer Sciences and Informatics Amman Arab University Amman11953 Jordan School of Computer Sciences Universiti Sains Malaysia Pulau Pinang11800 Malaysia

Feature selection (FS) is known as the most challenging problem in the Machine Learning field. FS can be considered an optimization problem that requires an efficient method to prepare its optimal subset of relative features. This article introduces a new FS method-based wrapper scheme that mixes chaotic maps (CMs) and binary Reptile Search Algorithm (RSA) called CRSA, employed to address various FS problems. In this method, different chaotic maps are included with the main ideas of the RSA algorithm. The objective function is revealed to combine three objectives: maximizing the classification accuracy, the number of chosen features, and the complexity of produced wrapper models. To assess the achievement of the proposed methods, 20 UCI datasets are applied, and the results are compared with other well-known methods. The results showed the superiority of the introduced method in bettering other well-known techniques, particularly when applying binary RSA with Tent CM. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

An Explainable Machine Learning-Based Phishing Website Detection using Gradient Boosting

An Explainable Machine Learning-Based Phishing Website Detec...

引用

2024 International Conference on Information technology Research and Innovation, ICITRI 2024

作者： Prayogo, Rizal Dwi Alfisyahrin, Alvin Rizqi Gambetta, Windy Karimah, Siti Amatullah Nambo, Hidetaka Kanazawa University Division of Electrical Engineering and Computer Science Graduate School of Natural Science and Technology Kanazawa Japan Telkom University School of Computing Bandung Indonesia Kanazawa University Faculty of Transdisciplinary Sciences Institute of Philosophy in Interdisciplinary Sciences Kanazawa Japan Institut Teknologi Bandung School of Electrical Engineering and Informatics Bandung Indonesia

ISBN: (纸本)9798350376210

As the need for achieving optimal performance in prediction models, several recent and complex models have been developed. However, many of these models operate as black boxes, providing little insight into their predictive results. In recent years, three gradient-boosting methods based on Decision Trees have been recommended, i.e., XGBoost, CatBoost, and LightGBM. These methods have proven to deliver competitive performance with fast training times. Nevertheless, in critical domains like security, there is a growing need for increased transparency among stakeholders. One pressing concern in the security field is the proliferation of phishing websites. To address this issue, we propose an explainable machine learning-based approach using gradient-boosting methods with hyperparameter optimization on three phishing website datasets. Our best methods surpass the state-of-the-art phishing website detection methods, achieving accuracy rates of 97.45%, 99.16%, and 97.85% for the UCI (2015), Mendeley (2018), and Mendeley (2020) datasets, respectively. Subsequently, we implement posthoc explainability using SHAP and LIME for the selected dataset. The experimental results indicate that three features, i.e., length_url, directory_length, and time_domain_activation, are consistently identified as the most influential features in the dataset. Moreover, our proposed approach demonstrates promising results for detecting phishing websites with both high accuracy and explainability. © 2024 IEEE.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

Machine Learning based Classification Algorithm for Classification of Dengue (Dengue Fever -DF, Dengue Harmonic Fever -DHF & Serve Dengue -SD) 1

Machine Learning based Classification Algorithm for Classifi...

引用

1st International Conference on Technologies for Smart Green Connected Society 2021, ICTSGS 2021

作者： Kapoor, Rajeev Ahuja, Sachin Kadyan, Virender Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Department of Informatics School of Computer Science University of Petroleum and Energy Studies Dehradun India

ISBN: (纸本)9781607685395

Dengue is becoming a burden for society worldwide and become challenge for the world. The main objective of this research paper is to classify dengue at an early stage. The author has adopted a methodology that is divided into five phases namely Data Collection, Transmission of Raw Data in Structural data format, Data Preprocessing, Model building with Train & Test Datasets and Prediction. Further, the proposed prediction model has been trained with the help of 250 data samples from primary sources namely clinical labs and 1000 data sample in the form of synthetic datasets adopted from 20 research papers. The proposed prediction Model has been tested and validated with the help of comparative study of different machine learning algorithms namely Decision Tree, Logistical Regression, Support Vector Machine (SVM), Gaussian Naïve Bayes etc. The proposed model has achieved 97.39% accuracy, 0.98 Precision, 0.97 Recall, 0.97 F1 Score, 0.02 MS and 0.14 RMSE. © The Electrochemical Society

关键词： Dengue Prediction Model Machine Learning Prediction Model Vector Borne Disease

来源：评论

学校读者我要写书评

暂无评论

UAV-RIS-Aided Energy-Efficient and QoS-Aware Emergency Communications Based on DRL 100

UAV-RIS-Aided Energy-Efficient and QoS-Aware Emergency Commu...

引用

100th IEEE Vehicular technology Conference, VTC 2024-Fall

作者： Hu, Jiawei Ju, Ying Wang, Haoyu Liu, Lei Pei, Qingqi Shee, Y.G. Zhu, Xiaojie Wu, Celimuge University of California Department of Electrical Engineering and Computer Science IrvineCA92697 United States Xidian University Guangzhou Institute of Technology Guangzhou510555 China Xi'an University of Posts Telecommunications Shaanxi Key Laboratory of Information Communication Network and Security Xi'an710121 China Universiti Tunku Abdul Rahman Department of Electrical and Electronic Engineering Kajang43000 Malaysia King Abdullah University of Science and Technology Department of Computer Electrical and Mathematical Sciences and Engineering Thuwal239556900 Saudi Arabia The University of Electro-Communications Graduate School of Informatics and Engineering Tokyo182-8585 Japan

ISBN: (纸本)9798331517786

Ensuring reliable communication can be incredibly challenging in emergencies due to the breakdown of conventional infrastructure. However, a promising solution is on the horizon: the integration of reconfigurable intelligent surfaces (RIS) onto unmanned aerial vehicles (UAV), known as UAV-RIS. This innovative approach holds the potential to offer agile and adaptable communication services during crises, overcoming the limitations of traditional systems. This paper establishes an innovative UAV-RIS system with an active RIS to enhance the uplink communication between ground devices (GDs) and the air base station (ABS). We present an advanced communication strategy utilizing deep reinforcement learning (DRL) for UAV-RIS-supported uplink communication in dynamic emergencies. This scheme is designed to optimize the energy efficiency of the UAV-RIS communication system while adhering to quality of service (QoS) constraints for all GDs. It achieves this by jointly optimizing the trajectory of the UAV-RIS and the phase of the active RIS, ensuring efficient and reliable communication in challenging environments. To optimize the performance of the system, we propose a hierarchical Proximal Policy Optimization (H-PPO) algorithm and the upper and lower layers of H-PPO optimize the trajectory and phase control, respectively. Simulation results demonstrate that our scheme can effectively learn the communication strategy to enhance the performance of dynamic emergency communication networks. © 2024 IEEE.

关键词： active reconfigurable intelligent surface deep reinforcement learning quality of service UAV trajectory

来源：评论

学校读者我要写书评

暂无评论

Accurate Multi-view Clustering by Exploiting Within-view High-order Affinities through Tensor Self-representation

Accurate Multi-view Clustering by Exploiting Within-view Hig...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Wang, Haiyan Chen, Jiazhou Zhang, Bin Cai, Hongmin South China Agricultural University College of Mathematics and Informatics Guangzhou China South China University of Technology School of Computer Science and Engineering Guangzhou China

ISBN: (纸本)9781665468190

Multi-view clustering divides data into their under-lying partitions by exploiting multiple views information. Popular approaches leverage cross-view information by self-expressive tensor learning and then learn a low-rank or sparse essential representation tensor for capturing the global structure of multi-view data. However, this process may encounter instability due to the lack of protection for local within-view structures. To overcome this problem, this paper proposes a unified L ow-rank and HyperGraph Laplacian regularized Tensor learning (LHGT) method for multi-view clustering, which aims to integrate within-view high-order affinities in self-expressive tensor learning for capturing inherent clustering structure. LHGT effectively extracts global cross-view and local within-view high-order statistics. An effective optimization procedure is tailored for the proposed model. Experimental results on six real-world datasets illustrate the efficacy of LHGT, where a clear advance over nine state-of-the-art approaches. © 2022 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Theoretical analysis of QBER for Quantum Key Distribution in 5G multi-site networks 15

Theoretical analysis of QBER for Quantum Key Distribution in...

引用

2022 IEEE Congress on Cybermatics: 15th IEEE International Conferences on Internet of Things, iThings 2022, 18th IEEE International Conferences on Green Computing and Communications, GreenCom 2022, 2022 IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2022 and 8th IEEE International Conference on Smart Data, SmartData 2022

作者： Batalla, Jordi Mongay Sujecki, Slawomir Song, Houbing Mavromoustakis, Constandinos X. Wichary, Tomasz Institute of Telecommunications Warsaw University of Technology Warsaw Poland Military University of Technology Wroclaw University of Technology Wroclaw Poland Embry-Riddle Aeronautical University Department of Electrical Engineering and Computer Science Daytona BeachFL United States University of Nicosia Department of Computer Science Nicosia Cyprus

ISBN: (数字)9781665454179

ISBN: (纸本)9781665454179

This paper presents theoretical analysis of Quantum Bit Error Rate (QBER) for Quantum Key Distribution (QKD) in mobile networks (5G/6G). The considered configuration of the underlying optical fiber network that is available for the establishment of the QKD in multi-site 5G networks assumes that the 5G sites are connected by a single optical fiber. Thus, multiplexing of both quantum and classical channels in a single optical fiber is thus necessary. This, in turn, results in a cross talk between classical and quantum channels, which increases QBER and imposes limitations on the maximum distance that can be reached. The approach followed in this paper provides an estimate of the maximum quantum link budget for the targeted QBER. The results of the analysis show that the QKD solution considered here can be potentially deployed using current Operators' 5G infrastructures to replace currently used asymmetric key exchange algorithms if needed. © 2022 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Efficient Resource Management in IoTs Using Evolutionary and Swarm Intelligence Algorithms 7

Efficient Resource Management in IoTs Using Evolutionary and...

引用

7th International Symposium on Innovative Approaches in Smart Technologies, ISAS 2023

作者： Gupta, Keshav Dev Cengiz, Korhan Awasthi, Charu Ramini, Siva Akash Chatterjee, Shyamapriya Pavithra, M. Poornima College of Engineering Department of Computer Science Engineering Jaipur India University of Fujairah College of Information Technology United Arab Emirates Istinye University Department of Computer Engineering Istanbul Turkey University of Hradec Kralove Faculty of Informatics and Management Department of Information Technologies Hradec Kralove500 03 Czech Republic JSS Academy of Technical Education Department of Information Technology Noida India Andhra Pradesh Amaravati India Narula Institute of Technology Department of Information Technology West Bengal Kolkata India Jansons Institute of Technology Karumathampatti Department of Computer Science and Engineering Coimbatore641659 India

ISBN: (纸本)9798350383065

The proliferation of the Internet of Things (IoT) has ushered in a transformative era of connected devices, emphasizing the critical need for effective resource management. This study introduces an innovative approach that harnesses Evolutionary and Swarm Intelligence algorithms for IoT Task Scheduling, addressing resource optimization challenges. The approach offers superior resource utilization through advanced optimization techniques, reducing energy consumption and enhancing efficiency. Furthermore, it significantly reduces task scheduling execution time, enabling prompt decision-making in dynamic IoT environments. This results in improved task allocation quality, meeting application-specific requirements, and prioritizing critical tasks. Notably, the approach excels in minimizing completion time, making it particularly advantageous for real-time IoT applications. This research contributes to the advancement of IoT resource management, offering an adaptive, efficient, and intelligent solution with broad applicability. In the evolving landscape of IoT, the findings presented here lay a solid foundation for future research and practical implementations, ultimately promoting more responsive, sustainable, and intelligent IoT ecosystems. © 2023 IEEE.

关键词： Swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

Trustworthy and Load-Balancing Routing Scheme for Satellite Services with Multi-Agent DRL

Trustworthy and Load-Balancing Routing Scheme for Satellite ...

引用

2023 IEEE INFOCOM Conference on computer Communications Workshops, INFOCOM WKSHPS 2023

作者： Song, Jiaxin Ju, Ying Liu, Lei Pei, Qingqi Wu, Celimuge Jan, Mian Ahmad Mumtaz, Shahid School of Telecommunications Engineering Xidian University Xi'an710071 China Graduate School of Informatics and Engineering The University of Electro-Communications Chofu182-8585 Japan Abdul Wali Khan University Mardan Department of Computer Science Mardan23200 Pakistan Silesian University of Technology Department of Applied Informatics Akademicka16 44-100 Poland Nottingham Trent University Engineering Department Nottingham999020 United Kingdom

ISBN: (纸本)9781665494274

Massive computing tasks of various applications have been generated in 6G space-air-ground integrated networks, and need to be transmitted securely and reliably. Nevertheless, the mobility of satellites and the untrusted nodes bring new challenges to the routing scheme design in low earth orbit (LEO) satellite networks. To improve the system trust and elevate the service quality, this paper proposes a fully distributed trustworthy load-balancing routing scheme for satellite services with a multi-agent dueling double deep Q network (D3QN)-based learning algorithm. Our scheme organizes multiple agents to generate hop-by-hop routes and makes decisions based on the trust value of the nodes, which has good scalability to deploy on various satellite constellations and can meet the trust requirements of the services. Besides, we add a variable delay constraint into the load minimization objective to meet various delay-sensitive satellite quality of service (QoS) requirements. We demonstrate that the proposed scheme dramatically reduces the link queue utilization rate and enhances the system capability of handling delay-sensitive services. The packet loss rate of our scheme is 24% lower than that of the benchmark scheme when the system has 30% malicious nodes. © 2023 IEEE.

关键词： Satellites

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：