检索结果-内蒙古大学图书馆

Scale adaptive fitness evaluation‐based particle swarm optimisation for hyperparameter and architecture optimisation in neural networks and deep learning

引用

CAAI Transactions on Intelligence technology 2023年第3期8卷 849-862页

作者： Ye‐Qun Wang Jian‐Yu Li Chun‐Hua Chen Jun Zhang Zhi‐Hui Zhan School of Computer Science and Engineering South China University of TechnologyGuangzhouChina School of Software Engineering South China University of TechnologyGuangzhouChina Hanyang University AnsanSouth Korea

Research into automatically searching for an optimal neural network(NN)by optimi-sation algorithms is a significant research topic in deep learning and artificial ***,this is still challenging due to two issues:Both the hyperparameter and ar-chitecture should be optimised and the optimisation process is computationally *** tackle these two issues,this paper focusses on solving the hyperparameter and architecture optimization problem for the NN and proposes a novel light‐weight scale‐adaptive fitness evaluation‐based particle swarm optimisation(SAFE‐PSO)***,the SAFE‐PSO algorithm considers the hyperparameters and architectures together in the optimisation problem and therefore can find their optimal combination for the globally best ***,the computational cost can be reduced by using multi‐scale accuracy evaluation methods to evaluate ***,a stagnation‐based switch strategy is proposed to adaptively switch different evaluation methods to better balance the search performance and computational *** SAFE‐PSO algorithm is tested on two widely used datasets:The 10‐category(i.e.,CIFAR10)and the 100−cate-gory(i.e.,CIFAR100).The experimental results show that SAFE‐PSO is very effective and efficient,which can not only find a promising NN automatically but also find a better NN than compared algorithms at the same computational cost.

关键词： deep learning evolutionary computation hyperparameter and architecture optimisation neural networks particle swarm optimisation scale‐adaptive fitness evaluation

来源：评论

学校读者我要写书评

暂无评论

Novel Darknet traffic data synthesis using Generative Adversarial Networks enhanced with oscillatory Growing Cosine Unit activated convolution layers

引用

International Journal of Cognitive Computing in engineering 2024年第1期5卷 58-65页

作者： Pradeep C, Antony Amali D, Geraldine Bessie Noel, Mathew Mithra Ghalib, Muhammad Rukunuddin Subramaniam, Prabhakar Rontala Venugopal, Chitra School of Computer Science and Engineering Vellore Institute of Technology Vellore India School of Electrical Engineering Vellore Institute of Technology Vellore India School of Computing De Montfort University Dubai United Arab Emirates Information Systems and Technology Westville South Africa Electrical Engineering & Renewable Energy Oregon Institute of Technology United States

The Darknet is an anonymous, encrypted collection of websites, with a passive listening nature - accepting incoming packets, while not supporting outgoing packets. Thus, it can potentially host criminal or malicious activity and software, becoming a cyber security threat. Network Detection Systems are effective in identifying dark net traffic and mitigating its ill effects. However, capturing and extracting data from raw network traffic for training these systems can be time-intensive and costly. Using the CIC-Darknet 2020 dataset, this paper proposes using a Novel Generative Adversarial Networks (GAN) Architecture generating the required training and testing data for these systems. This uses a combination of Growing Cosine Unit (GCU) activated convolution layers and Dense layers for the Generator. Feature selection with statistical correlation methods is used to select the most relevant features. An independently trained Evaluator network is used to evaluate the generated data. The proposed system is compared to other established Tabular data GANs like Conditional Tabular GAN (CTGAN) and Copula GAN with similar parameters and on the same data. The Proposed GAN architecture outperforms CTGAN and CopulaGAN by 20 % and 10 % in ters of accuracy while also taking 90 % and 30 % less time to train respectively. Results from measuring similarity of data using the Inverted Kolmogorov - Smirnov D statistic also show significantly better results for the Proposed GAN Architecture. This shows significant promise in using Generative models to reduce the time and effort costs associated with collecting and formatting data to use in research and for training detection systems. © 2024

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Collective Diagnostic Prototypical in Internet of Medical Things for Depression Identification using Deep Learning Algorithm

引用

Recent Patents on engineering 2024年第9期18卷 24-33页

作者： Selvarajan, Shitharth Thirumalaisamy, Manikandan Manoharan, Hariprasath Devendiran, Ramkumar Lakshmi Narayanan, S. Kumar, Ashwani Department of Computer Science Kebri Dehar University Kebri Dehar250 Ethiopia School of Computer Science Engineering and technology Bennett University U.P India Department of Artificial Intelligence and Machine Learning Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai India Department of Electronics and Communication Engineering Panimalar Engineering College Poonamallee Tamil Nadu Chennai600 123 India School of Computer Science and Engineering VIT-AP UNIVERSITY Andhra Pradesh Amaravathi522237 India Gojan School of Business and Technology Chennai India Department of Computer Science and Engineering School of Engineering and Technology Sharda University Greater Noida India

Background: The majority of wearable technology that is present in various patents for Internet of Medical Things (IoMT) health monitoring systems is introduced to recognize various bodily indicators. The enumerated patents indicate that monitored values are sent to a central server, where they are all treated by experts at the appropriate moment. Therefore, a new patent technique by expanding the use of wireless devices, has been discovered that such communication technologies can recognize specific depression traits and mood swings. Objectives: The major objective of the proposed method is to analyze the disputes that arise in the characteristics of an individual by observing the leveling periods that are identified from the processed image. In addition, the rate of data transfer in case of any dispute is maximized therefore recognition problem is solved at a minimized distance. Further, the steady state probability values are achieved at low delay thus minimizing the dropout packets in the monitored system using IoMT and LSTM. Methods: A balanced record with four distinct parameters—such as livelihood, self-reliance, correlation, and precision—is employed with the projected model on IoMT for depression identification. As a result, high data transfer rates and low distance separation are used to process the identification framework. Additionally, by combining an original matrix representation with the input feature set using LSTM, a novel framework with great efficiency is created. Results: In order to assess the results of IoMT using LSTM, four situations are split apart and their probability ratios are calculated. The results of each situation are then contrasted with the current methodology, and it is found that when there is a low dropout ratio, depression in a person is quickly diagnosed. Conclusion: The comparison analysis demonstrates that the proposed method, when compared to the current method, offers the best-compromised outcomes at roughly 64%. © 2024 B

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

Automatic Transportation Mode Classification Using a Deep Reinforcement Learning Approach With Smartphone Sensors

引用

IEEE Access 2024年 12卷 514-533页

作者： Taherinavid, Siavash Moravvej, Seyed Vahid Chen, Yen-Lin Yang, Jing Ku, Chin Soon Yee, Por Lip Iran University of Science and Technology School of Civil Engineering Tehran13114-16846 Iran Isfahan University of Technology Department of Electrical and Computer Engineering Isfahan84156-83111 Iran National Taipei University of Technology Department of Computer Science and Information Engineering Taipei106344 Taiwan Universiti Malaya Faculty of Computer Science and Information Technology Department of Computer System and Technology Kuala Lumpur50603 Malaysia Universiti Tunku Abdul Rahman Department of Computer Science Kampar31900 Malaysia

The increasing dependence on smartphones with advanced sensors has highlighted the imperative of precise transportation mode classification, pivotal for domains like health monitoring and urban planning. This research is motivated by the pressing demand to enhance transportation mode classification, leveraging the potential of smartphone sensors, notably the accelerometer, magnetometer, and gyroscope. In response to this challenge, we present a novel automated classification model rooted in deep reinforcement learning. Our model stands out for its innovative approach of harnessing enhanced features through artificial neural networks (ANNs) and visualizing the classification task as a structured series of decision-making events. Our model adopts an improved differential evolution (DE) algorithm for initializing weights, coupled with a specialized agent-environment relationship. Every correct classification earns the agent a reward, with additional emphasis on the accurate categorization of less frequent modes through a distinct reward strategy. The Upper Confidence Bound (UCB) technique is used for action selection, promoting deep-seated knowledge, and minimizing reliance on chance. A notable innovation in our work is the introduction of a cluster-centric mutation operation within the DE algorithm. This operation strategically identifies optimal clusters in the current DE population and forges potential solutions using a pioneering update mechanism. When assessed on the extensive HTC dataset, which includes 8311 hours of data gathered from 224 participants over two years. Noteworthy results spotlight an accuracy of 0.88±0.03 and an F-measure of 0.87±0.02, underscoring the efficacy of our approach for large-scale transportation mode classification tasks. This work introduces an innovative strategy in the realm of transportation mode classification, emphasizing both precision and reliability, addressing the pressing need for enhanced classification mechanisms in an eve

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Combining neural network-based method with heuristic policy for optimal task scheduling in hierarchical edge cloud

引用

Digital Communications and Networks 2023年第3期9卷 688-697页

作者： Zhuo Chen Peihong Wei Yan Li College of Computer Science and Engineering Chongqing University of TechnologyChongqing200433China School of Artificial Intelligence Chongqing University of TechnologyChongqing200433China

Deploying service nodes hierarchically at the edge of the network can effectively improve the service quality of offloaded task requests and increase the utilization of *** this paper,we study the task scheduling problem in the hierarchically deployed edge *** first formulate the minimization of the service time of scheduled tasks in edge cloud as a combinatorial optimization problem,blue and then prove the NP-hardness of the *** from the existing work that mostly designs heuristic approximation-based algorithms or policies to make scheduling decision,we propose a newly designed scheduling policy,named Joint Neural Network and Heuristic Scheduling(JNNHSP),which combines a neural network-based method with a heuristic based *** takes the Sequence-to-Sequence(Seq2Seq)model trained by Reinforcement Learning(RL)as the primary policy and adopts the heuristic algorithm as the auxiliary policy to obtain the scheduling solution,thereby achieving a good balance between the quality and the efficiency of the scheduling ***-depth experiments show that compared with a variety of related policies and optimization solvers,JNNHSP can achieve better performance in terms of scheduling error ratio,the degree to which the policy is affected by re-sources limitations,average service latency,and execution efficiency in a typical hierarchical edge cloud.

关键词： Edge cloud Task scheduling Neural network Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Crafting Captivating Narratives: Enhancing Image Captioning Through Encoder-Decoder Architectures 2

Crafting Captivating Narratives: Enhancing Image Captioning ...

引用

2nd IEEE International Conference on Data Science and Network Security, ICDSNS 2024

作者： Sahaaya Arul Mary, S.A. Pandey, Adamya Kumar Jha, Aadarsh Sharma, Kartikay Shohel, Mohmad Natarajan, B. School of Computer Science and Engineering Vellore Institute of Technology Vellore India School of Information Technology Vellore Institute of Technology Vellore India School of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9798350373110

This research work aims to develop an image captioning system utilizing deep learning techniques. The pre-trained VGG-16 model is employed to extract image features, while an innovative encoder-decoder architecture is used to generate descriptive captions. To ensure compatibility with the model, pre-processing techniques are applied to the dataset, which comprises images and their corresponding descriptions. Tokenization, vocabulary generation, and effectively utilizing a data generator are integral parts of the training process, facilitating the handling vast datasets. Multiple training epochs are employed to optimize the model's ability to associate captions with specific picture attributes. The model's performance is evaluated using BLEU-1 and BLEU-2 scores on a designated test set, providing quantitative insights into the quality of the generated captions. Additionally, this work includes a visualization component enabling users to input names of specific images, generating captions in real-time for comparative analysis with actual captions. This comprehensive approach integrates methodologies from computer vision and natural language processing, showcasing how deep learning can enhance the interpretability and comprehension of images akin to human perception. BLEU is a widely used, automated metric for evaluating image captioning models, offering objective and quantitative comparisons. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Multi-scale network for single image deblurring based on ensemble learning module

引用

Multimedia Tools and Applications 2025年第11期84卷 9045-9064页

作者： Wu, WenBo Pan, Yun Su, Na Wang, JingTao Wu, ShaoChuan Xu, ZeKun Yu, YouJian Liu, YaPeng State Key Laboratory of Media Convergence and Communication Communication University of China Beijing100024 China School of Computer and Cyberspace Security Communication University of China Beijing100024 China School of Electronics and Information Engineering Harbin Institute of Technology Harbin150080 China College of Computer and Control Engineering Northeast Forestry University Harbin150040 China School of Computer and Information Engineering Tianjin Chengjian University Tianjin300384 China School of Computer Science and Technology Anhui University Hefei230601 China

In this paper, we have identified two primary issues with current multi-scale image deblurring methods. On the one hand, the blurring scale is ignored. On the other hand, the context information of images is not fully utilized, and the spatial detail information of images is lost. To better solve the above problems, on top of that, this paper proposes a multi-scale network for single image deblurring. The designed network contains two parts: 1) Ensemble Learning Model: The Weak Learning Model in this module connects multiple weak learners in series to increase network depth. Moreover, through multi-scale feature ensemble module, the output features and intermediate features of different weak learner are integrated, and finally strong learner is used to enhance the features with semantic information at different scales;2) Spatial Feature Enhancement Module: This module can preserve spatial detail information of images and compensate for the disadvantages of losing image spatial details due to continuous downsampling in the Ensemble Learning Model structure. Our proposed deblurring model has been extensively evaluated on several benchmark datasets, and the model achieves superior performance compared to the most advanced deblurring methods. In particular, the peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) values are 33.57 dB and 0.965 on the GoPro dataset, respectively, with PSNR and SSIM improving by 0.49 dB and 0.002 over NAFNet, and 0.65 dB and 0.004 over Restormer. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

DD-SPP: Dynamic and Distributed Service Placement Policy for Optimal Scheduling in Fog-Edge Computing

引用

SN computer Science 2024年第7期5卷 801页

作者： Kaur, Navjeet Bhardwaj, Vivek Department of Computer Science and Engineering Apex Institute of Technology Chandigarh University School of Computer Science and Engineering Manipal University Jaipur

The existing cloud model unable to handle abundant amount of Internet of Things (IoT) services placed by the end users due to its far distant location from end user and centralized nature. The edge and fog computing are the latest technologies for developing smart cities that are becoming popular to efficiently support latency-sensitive IoT application services. But these advanced technologies suffer from limited size and computation capabilities;therefore, optimal placement of services among available resources is an open issue. Therefore, the proposed work target the stated issue and presents a Dynamic and Distributed Service Placement Policy (DD-SPP) considering the edge and fog devices. The model is divided into three main phases, that is, the Service Type Estimator (STE), the Service Dependency Estimator & Resolution (SDER), and Resource Demand Estimator & Scheduling (RDES). STE and RDES modules depend on each other to perform optimal service placement. The results of the implementation showed satisfactory improvement with respect to present state-of-the-art policy where delay is improved by around 41%, energy is improved by 27%, response time by 28% and overall cost by 28%. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Cloud computing DD-SPP Edge computing Fog computing IoT Scheduling Service placement policy

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Offloading Optimization in MEC and Vehicular-Fog Systems: A Distributed-TD3 Approach

引用

IEEE Transactions on Intelligent Transportation Systems 2024年第11期25卷 16897-16909页

作者： Wakgra, Frezer Guteta Kar, Binayak Tadele, Seifu Birhanu Shen, Shan-Hsiang Khan, Asif Uddin The Department of Computer Science and Information Engineering National Taiwan University of Science and Technology Taipei106 Taiwan The School of Computer Engineering KIIT Deemed to be University Odisha Bhubaneswar751024 India

The emergence of 5G networks has enabled the deployment of a two-tier edge and vehicular-fog network. It comprises Multi-access Edge Computing (MEC) and Vehicular-Fogs (VFs), strategically positioned closer to Internet of Things (IoT) devices, reducing propagation latency compared to cloud-based solutions and ensuring satisfactory quality of service (QoS). However, during high-traffic events like concerts or athletic contests, MEC sites may face congestion and become overloaded. Utilizing offloading techniques, we can transfer computationally intensive tasks from resource-constrained devices to those with sufficient capacity, for accelerating tasks and extending device battery life. In this research, we consider offloading within a two-tier MEC and VF architecture, involving offloading from MEC to MEC and from MEC to VF. The primary objective is to minimize the average system cost, considering both latency and energy consumption. To achieve this goal, we formulate a multi-objective optimization problem aimed at minimizing latency and energy while considering given resource constraints. To facilitate decision-making for nearly optimal computational offloading, we design an equivalent reinforcement learning environment that accurately represents the network architecture and the formulated problem. To accomplish this, we propose a Distributed-TD3 (DTD3) approach, which builds on the TD3 algorithm. Extensive simulations, demonstrate that our strategy achieves faster convergence and higher efficiency compared to other benchmark solutions. © 2024 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

An intrusion attack classification using bio-inspired optimization technique and ensemble learning model for edge computing environments

引用

Multimedia Tools and Applications 2024年 1-28页

作者： Rahamathulla, Mohemmed Yousuf Ramaiah, Mangayarkarasi School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamilnadu Vellore India

The phenomenal rise in network traffic across various sectors, driven by advancements in network communication, has led to an explosion of connected devices. While internet-based service providers have enhanced smart environments, these environments remain highly vulnerable to security risks. Due to their resource- constrained nature, Internet of Things (IoT) systems rely on edge servers for processing. Cutting-edge machine learning algorithms have significantly improved the security of edge computing systems by enabling early intrusion detection. However, the dynamic nature of our society demands more sophisticated Network Intrusion Detection Systems (NIDS) that can balance the challenge of managing the explosive growth of network traffic data with effectively responding to attacks. This paper proposes a novel NIDS that can train and learn from massive amounts of data in a centralized environment. To identify the best subset of features for improved data representation and classification, a bio-inspired algorithm, the Improved Firefly Optimization Algorithm (IFOA), is employed. Furthermore, a hyper-tuned Extremely Randomized Trees (ERT) attack detection model is developed to accurately identify malicious behavior while minimizing false positives. The experimental results demonstrate that the proposed approach achieves superior accuracy and execution speed compared to alternative solutions and its baseline versions. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Network intrusion

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：