检索结果-内蒙古大学图书馆

Optimisation of sparse deep autoencoders for dynamic network embedding

CAAI Transactions on Intelligence Technology 2024年第6期9卷 1361-1376页

作者： Huimei Tang Yutao Zhang Lijia Ma Qiuzhen Lin Liping Huang Jianqiang Li Maoguo Gong College of Computer Science and Software Engineering Shenzhen UniversityShenzhenChina Institute for Infocomm Research Agency for Science Technology and ResearchSingaporeSingapore Key Laboratory of Collaborative Intelligence Systems Ministry of EducationXidian UniversityXi'anChina

Network embedding(NE)tries to learn the potential properties of complex networks represented in a low-dimensional feature ***,the existing deep learningbased NE methods are time-consuming as they need to train a dense architecture for deep neural networks with extensive unknown weight parameters.A sparse deep autoencoder(called SPDNE)for dynamic NE is proposed,aiming to learn the network structures while preserving the node evolution with a low computational *** tries to use an optimal sparse architecture to replace the fully connected architecture in the deep autoencoder while maintaining the performance of these models in the dynamic ***,an adaptive simulated algorithm to find the optimal sparse architecture for the deep autoencoder is *** performance of SPDNE over three dynamical NE models(*** architecture-based deep autoencoder method,DynGEM,and ElvDNE)is evaluated on three well-known benchmark networks and five real-world *** experimental results demonstrate that SPDNE can reduce about 70%of weight parameters of the architecture for the deep autoencoder during the training process while preserving the performance of these dynamical NE *** results also show that SPDNE achieves the highest accuracy on 72 out of 96 edge prediction and network reconstruction tasks compared with the state-of-the-art dynamical NE algorithms.

关键词： deep autoencoder dynamic networks low-dimensional feature space network embedding sparse structure

来源：评论

学校读者我要写书评

暂无评论

Transformative Technology in Poultry Management: 3D CNNs for Broiler Chicken Weight Prediction 1

Transformative Technology in Poultry Management: 3D CNNs for...

引用

1st IEEE International Conference on Cognitive Robotics and Intelligent systems, ICC - ROBINS 2024

作者： Anuprabha, K. Kaliappan, Vishnu Kumar Baniekal Hiremath, Gangadhar Kpr Institute of Engineering and Technology Department of Computer Science Engineering Tamilnadu Coimbatore641407 India Wasp Autonomous Systems Pvt Ltd Karnataka Ballari India

ISBN: (纸本)9798350372748

In global food production, broiler chickens hold significant importance, which are traditionally managed through manual labour for both meat and egg production. However, the poultry farming industry has increasingly turned to automation to address challenges associated with manual labour and enhance efficiency. This research introduces a novel methodology for estimating chicken weight utilizing top-view videos as input and leveraging 3D Convolutional Neural Networks (CNNs). Accurate weight assessment is a critical aspect of poultry farming, influencing feeding strategies and resource allocation. Traditional manual weighing methods are laborious and time-intensive, necessitating the exploration of automated alternatives. The methodology involves dataset collection, preprocessing, and employing 3D CNNs for effective feature extraction. 3D CNN architecture, adept at capturing spatial and temporal features, consists of convolutional and pooling layers, followed by flatten and dense layers for weight prediction. The model achieves a remarkable accuracy of 95%, as evidenced in the experimental results. Experimental validation showcases the potential of this method as a non-invasive and efficient tool for estimating chicken weight. It contributes to the growing field of automated livestock management in agriculture. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Large Language Model-Based Optimization for System-Level Test Program Generation 37

Large Language Model-Based Optimization for System-Level Tes...

引用

37th IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology systems, DFT 2024

作者： Schwachhofer, Denis Domanski, Peter Becker, Steffen Wagner, Stefan Sauer, Matthias Pfluger, Dirk Polian, Ilia Institute of Computer Engineering and Computer Architecture University of Stuttgart Stuttgart Germany Institute of Software Engineering University of Stuttgart Stuttgart Germany Institute for Parallel and Distributed Systems University of Stuttgart Stuttgart Germany Technical University of Munich Heilbronn Germany Advantest Europe Boeblingen Germany

ISBN: (纸本)9798350366884

System-Level Test (SLT) is essential for testing integrated circuits, focusing on functional and non-functional properties of the Device under Test (DUT). Traditionally, test engineers manually create tests with commercial software to simulate the DUT's end-user environment. This process is both time-consuming and offers limited control over non-functional properties. This paper proposes Large Language Models (LLMs) enhanced by Structural Chain of Thought (SCoT) prompting, a temperature schedule, and a pool of previously generated snippets to generate high-quality code snippets for SLT. We repeatedly query the LLM for a better snippet using previously generated snippets as examples, thus creating an iterative optimization loop. This approach can automatically generate snippets for SLT that target specific non-functional properties, reducing time and effort. Our findings show that this approach improves the quality of the generated snippets compared to unstructured prompts containing only a task description. © 2024 IEEE.

关键词： Functional Test Large Language Models Optimization System-Level Test Test Generation

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Intrusion Detection System Using Convolutional Neural Network and Long Short-Term Memory in Fog Computing

引用

computers, Materials & Continua 2024年第9期80卷 4703-4728页

作者： Hawazen Alzahrani Tarek Sheltami Abdulaziz Barnawi Muhammad Imam Ansar Yaser Computer Engineering Department Interdisciplinary Research Center of Smart Mobility and LogisticsKing Fahd University of Petroleum and MineralsDhahran31261Saudi Arabia Computer Engineering Department Interdisciplinary Research Center for Intelligent Secure SystemsKing Fahd University of Petroleum and MineralsDhahran31261Saudi Arabia Transportation Research Institute(IMOB) Hasselt UniversityHasselt3500Belgium

The Internet of Things(IoT)links various devices to digital services and significantly improves the quality of our ***,as IoT connectivity is growing rapidly,so do the risks of network vulnerabilities and *** interesting Intrusion Detection systems(IDSs)are presented based on machine learning(ML)techniques to overcome this *** the resource limitations of fog computing environments,a lightweight IDS is *** paper introduces a hybrid deep learning(DL)method that combines convolutional neural networks(CNN)and long short-term memory(LSTM)to build an energy-aware,anomaly-based *** test this system on a recent dataset,focusing on reducing overhead while maintaining high accuracy and a low false alarm *** compare CICIoT2023,KDD-99 and NSL-KDD datasets to evaluate the performance of the proposed IDS model based on key metrics,including latency,energy consumption,false alarm rate and detection rate *** findings show an accuracy rate over 92%and a false alarm rate below 0.38%.These results demonstrate that our system provides strong security without excessive resource *** practicality of deploying IDS with limited resources is demonstrated by the successful implementation of IDS functionality on a Raspberry Pi acting as a Fog *** proposed lightweight model,with a maximum power consumption of 6.12 W,demonstrates its potential to operate effectively on energy-limited devices such as low-power fog nodes or edge *** prioritize energy efficiency whilemaintaining high accuracy,distinguishing our scheme fromexisting *** experiments demonstrate a significant reduction in false positives,ensuring accurate identification of genuine security threats while minimizing unnecessary alerts.

关键词： Intrusion detection fog computing CNN LSTM energy consumption

来源：评论

学校读者我要写书评

暂无评论

Ship Platform Access Control Method Based on Zero Trust 7

Ship Platform Access Control Method Based on Zero Trust

引用

7th IEEE Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2024

作者： Wei, Renlong Li, Guobing Beijing University of Posts and Telecommunications Beijing China Beihang University School of Computer Science and Engineering Beijing China Cssc Systems Engineering Research Institute China

ISBN: (纸本)9798350370782

With the digital transformation of the shipbuilding industry, the interaction between ship platform systems and intelligent equipment has become closer, which has led to the increasingly blurred security boundaries of ship platform systems and increased the risk of illegal access to ship platform resources. At present, ship platforms still mainly rely on static access control methods to protect sensitive resources, which can no longer meet the growing access control needs in a de-bordered environment. In order to meet this challenge, this paper introduces the zero-trust concept into the ship platform access control system. By designing a trust evaluation algorithm and a dynamic access control algorithm, the ship platform permissions can be managed more finely, and experiments are designed to verify the effectiveness of the scheme in access control. © 2024 IEEE.

关键词： Shipyards

来源：评论

学校读者我要写书评

暂无评论

Differentially Private Online Federated Learning with Correlated Noise 63

Differentially Private Online Federated Learning with Correl...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Zhang, Jiaojiao Zhu, Linglingzhi Johansson, Mikael Kth Royal Institute of Technology Division of Decision and Control Systems School of Electrical Engineering and Computer Science StockholmSE-100 44 Sweden Chinese University of Hong Kong Department of Systems Engineering and Engineering Management Hong Kong

ISBN: (纸本)9798350316339

We introduce a novel differentially private algorithm for online federated learning that employs temporally correlated noise to enhance utility while ensuring privacy of continuously released models. To address challenges posed by DP noise and local updates with streaming non-iid data, we develop a perturbed iterate analysis to control the impact of the DP noise on the utility. Moreover, we demonstrate how the drift errors from local updates can be effectively managed under a quasi-strong convexity condition. Subject to an (, δ) DP budget, we establish a dynamic regret bound over the entire time horizon, quantifying the impact of key parameters and the intensity of changes in dynamic environments. Numerical experiments confirm the efficacy of the proposed algorithm. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

State of Health Estimation of Lithium-Ion Batteries Based on Relaxation Voltage Reconstruction and AM-LSTM Method

引用

IEEE Transactions on Transportation Electrification 2025年第3期11卷 7261-7273页

作者： Wei, Liangliang Xu, Hongzhang Sun, Yiwen Diao, Qi Tan, Xiaojun Fan, Yuqian Liu, Han School of Intelligent Systems Engineering Shenzhen518107 China Henan Institute of Science and Technology School of Computer Science and Technology Henan Xinxiang453003 China Dongguan Institute Sun Yat-sen University Guangdong Dongguan523808 China Hong Kong Polytechnic University Department of Building and Energy Engineering Hong Kong

It is essential to accurately estimate the state of health (SOH) for lithium-ion batteries from the perspectives of safety and reliability. Most existing data-driven methods are, however, based on charging or discharging data, which is relatively difficult to apply. This article proposes a novel SOH estimation approach based on the relaxation voltage reconstruction and a long short-term memory network with an attention mechanism (AM-LSTM) method. First, based on the relaxation voltage data, a complete relaxation curve is reconstructed with a gated recurrent unit (GRU) neural network. Next, health feature (HF) extraction is carried out on the reconstructed data, and the correlation is analyzed based on Pearson correlation analysis. Then, the SOH estimation is performed based on the AM-LSTM model. Various comparative studies have been conducted to verify the effectiveness of the proposed method by comparing it with relaxation voltage reconstruction and different SOH estimation methods. The experimental results demonstrate that the proposed method can effectively reconstruct the relaxation voltage and have good accuracy in estimating the SOH with a partial relaxation voltage curve. © 2015 IEEE.

关键词： Voltage Batteries Estimation Feature extraction Long short term memory Logic gates Data models Integrated circuit modeling Data mining Transportation

来源：评论

学校读者我要写书评

暂无评论

Predicting Aesthetic Outcomes in Breast Cancer Surgery: A Multimodal Retrieval Approach 1st

Predicting Aesthetic Outcomes in Breast Cancer Surgery: A M...

引用

1st Deep Breast Workshop on AI and Imaging for Diagnostic and Treatment Challenges in Breast Care, Deep-Breath 2024

作者： Zolfagharnasab, Mohammad Hossein Freitas, Nuno Gonçalves, Tiago Bonci, Eduard Mavioso, Carlos Cardoso, Maria J. Oliveira, Hélder P. Cardoso, Jaime S. University of Porto Porto Portugal Institute for Systems and Computer Engineering Technology and Science Porto Portugal Breast Unit Champalimaud Foundation Lisbon Portugal

ISBN: (纸本)9783031777882

Breast cancer treatments often affect patients’ body image, making aesthetic outcome predictions vital. This study introduces a Deep Learning (DL) multimodal retrieval pipeline using a dataset of 2,193 instances combining clinical attributes and RGB images of patients’ upper torsos. We evaluate four retrieval techniques: Weighted Euclidean Distance (WED) with various configurations and shallow Artificial Neural Network (ANN) for tabular data, pre-trained and fine-tuned Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs), and a multimodal approach combining both data types. The dataset, categorised into Excellent/Good and Fair/Poor outcomes, is organised into over 20K triplets for training and testing. Results show fine-tuned multimodal ViTs notably enhance performance, achieving up to 73.85% accuracy and 80.62% Adjusted Discounted Cumulative Gain (ADCG). This framework not only aids in managing patient expectations by retrieving the most relevant post-surgical images but also promises broad applications in medical image analysis and retrieval. The main contributions of this paper are the development of a multimodal retrieval system for breast cancer patients based on post-surgery aesthetic outcome and the evaluation of different models on a new dataset annotated by clinicians for image retrieval. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Intelligent Optimization Under Multiple Factories: Hybrid Flow Shop Scheduling Problem with Blocking Constraints Using an Advanced Iterated Greedy Algorithm

引用

Complex System Modeling and Simulation 2023年第4期3卷 282-306页

作者： Yong Wang Yuting Wang Yuyan Han Junqing Li Kaizhou Gao Yusuke Nojima School of Computer Science Liaocheng UniversityLiaocheng 252000China School of Computer Science Shandong Normal UniversityJinan 252000China Macao Institute of Systems Engineering Macao University of Science and TechnologyMacao 999078China Department of Computer Science and Intelligent Systems Osaka Prefecture UniversityOsaka 599-8531Japan

The distributed hybrid flow shop scheduling problem(DHFSP),which integrates distributed manufacturing models with parallel machines,has gained significant ***,in actual scheduling,some adjacent machines do not have buffers between them,resulting in *** paper focuses on addressing the DHFSP with blocking constraints(DBHFSP)based on the actual production *** solve DBHFSP,we construct a mixed integer linear programming(MILP)model for DBHFSP and validate its correctness using the Gurobi ***,an advanced iterated greedy(AIG)algorithm is designed to minimize the makespan,in which we modify the Nawaz,Enscore,and Ham(NEH)heuristic to solve blocking *** balance the global and local search capabilities of AIG,two effective inter-factory neighborhood search strategies and a swap-based local search strategy are ***,each factory is mutually independent,and the movement within one factory does not affect the *** view of this,we specifically designed a memory-based decoding method for insertion operations to reduce the computation time of the ***,two shaking strategies are incorporated into the algorithm to mitigate premature *** advanced algorithms are used to conduct comparative experiments with AIG on 80 test instances,and experimental results illustrate that the makespan and the relative percentage increase(RPI)obtained by AIG are 1.0%and 86.1%,respectively,better than the comparative algorithms.

关键词： blocking distributed hybrid flow shop neighborhood search iterated greedy algorithm

来源：评论

学校读者我要写书评

暂无评论

IDENTIFYING POLICY GRADIENT SUBSPACES 12

IDENTIFYING POLICY GRADIENT SUBSPACES

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Schneider, Jan Schumacher, Pierre Guist, Simon Chen, Le Häufle, Daniel Schölkopf, Bernhard Büchler, Dieter Max Planck Institute for Intelligent Systems Tübingen Germany Hertie Institute for Clinical Brain Research Tübingen Germany Institute for Computer Engineering University of Heidelberg Germany

Policy gradient methods hold great potential for solving complex continuous control tasks. Still, their training efficiency can be improved by exploiting structure within the optimization problem. Recent work indicates that supervised learning can be accelerated by leveraging the fact that gradients lie in a low-dimensional and slowly-changing subspace. In this paper, we conduct a thorough evaluation of this phenomenon for two popular deep policy gradient methods on various simulated benchmark tasks. Our results demonstrate the existence of such gradient subspaces despite the continuously changing data distribution inherent to reinforcement learning. These findings reveal promising directions for future work on more efficient reinforcement learning, e.g., through improving parameter-space exploration or enabling second-order optimization. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Reinforcement learning

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：