检索结果-内蒙古大学图书馆

17th China Conference on Wireless Sensor Networks, CWSN 2023

作者： Wei, Lian-Suo Ma, Long-Yu Huang, Shen-Hao School of Information Engineering Suqian University Jiangsu Suqian223800 China College of Computer and Control Engineering Qiqihar University Heilongjiang Qiqihar161006 China

ISBN: (纸本)9789819710096

In response to the insufficient small-scale feature extraction capabilities of traditional SSD object detection algorithms, which lead to missed detections and false alarms in the detection of small underwater targets, this paper proposes a new underwater object detection algorithm. The algorithm first uses a Dual Reverse Dehazing (DRDM) module for image enhancement. Then, on the basis of the backbone network of the SSD algorithm, a channel attention mechanism and feature extraction convolution are introduced to construct a SE-Feature-Enhancement Module (SFEM) to integrate high-resolution shallow feature maps and deep feature maps with high semantic information. This fusion method preserves the context information of the feature maps, learns the necessary features, and suppresses redundant information, thereby improving the network’s learning ability. The experimental results show that the proposed algorithm achieves a detection accuracy of 94.62% on the Wilder_fish_new dataset. Compared with the current commonly used SSD (VGG) and SSD (Mobilenetv2) algorithms, the proposed algorithm improves the accuracy by 2.7 and 3.13 percentage points, respectively. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Weighted syncmer sampling improves long-read mapping

Weighted syncmer sampling improves long-read mapping

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Quan, Wei Kang, Jinjun Deng, Yanfei Liu, Zhuang Zhu, Xiao Quan, Guangri Yantai University School of Computer and Control Engineering Yantai China Xinjiang University of Political Science and Law School of Information and Network Security Tumxuk China

ISBN: (纸本)9798350386226

Syncmers represent a novel class of methods for selecting k-mers that exhibit robustness against mutations in flanking sequences and demonstrate superior conservation in mutated sequences. Nevertheless, syncmers may generate a higher frequency of repetitive seed matches compared to alternative techniques, such as minimizers, which can result in increased computational time. In this article, we introduce weighted minimizer sampling, which integrates weighted minimizer sampling and syncmer sampling to enhance the sensitivity and accuracy of long-read mapping. We modified two state-of-the-art long-read mappers, Minimap2 and Winnowmap, by substituting the sketching sampling methods with weighted minimizer sampling. We assessed their sensitivity and accuracy using simulated and real datasets. The experimental results indicate that weighted minimizer sampling significantly improves the sensitivity and accuracy of long-read mapping. The source code is available at GitHub: https://***/hexinkaoan/weighted-syncmer. © 2024 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Equalizer Zero-Determinant Strategy in Discounted Repeated Stackelberg Asymmetric Game

引用

Journal of Systems Science & Complexity 2024年第1期37卷 184-203页

作者： CHENG Zhaoyang CHEN Guanpu HONG Yiguang Key Laboratory of Systems and Control Academy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China School of Mathematical Sciences University of Chinese Academy of SciencesBeijing 100049China School of Electrical Engineering and Computer Science KTH Royal Institute of Technology10044 StockholmSweden. Department of Control Science and Engineering Tongji UniversityShanghai 201804China Shanghai Research Institute for Intelligent Autonomous Systems Tongji UniversityShanghai 210201China

This paper focuses on the performance of equalizer zero-determinant(ZD)strategies in discounted repeated Stackelberg asymmetric *** the leader-follower adversarial scenario,the strong Stackelberg equilibrium(SSE)deriving from the opponents’best response(BR),is technically the optimal strategy for the ***,computing an SSE strategy may be difficult since it needs to solve a mixed-integer program and has exponential complexity in the number of *** this end,the authors propose an equalizer ZD strategy,which can unilaterally restrict the opponent’s expected *** authors first study the existence of an equalizer ZD strategy with one-to-one situations,and analyze an upper bound of its performance with the baseline SSE *** the authors turn to multi-player models,where there exists one player adopting an equalizer ZD *** authors give bounds of the weighted sum of opponents’s utilities,and compare it with the SSE ***,the authors give simulations on unmanned aerial vehicles(UAVs)and the moving target defense(MTD)to verify the effectiveness of the proposed approach.

关键词： Discounted repeated Stackelberg asymmetric game equalizer zero-determinant strategy strong Stackelberg equilibrium strategy

来源：评论

学校读者我要写书评

暂无评论

Efficient-Learning Grasping and Pushing in Dense Stacking via Mask Function and Pixel Overlap Rate 7

Efficient-Learning Grasping and Pushing in Dense Stacking vi...

引用

7th International Symposium on Autonomous Systems, ISAS 2024

作者： Lian, Jie Jiang, Juncheng Qiu, Chaochao Pan, Qinghui Dong, Yongxiang Wang, Zhao Wang, Dong Dalian University of Technology School of Control Science and Engineering Dalian China University of Science and Technology Liaoning Shool of Computer Science and Software Engineering China

ISBN: (纸本)9798350363173

In the field of robotic grasping, grasping tightly stacked objects is a formidable challenge. The presence of non-target objects significantly increases the risk of grasping failure. To solve this problem, the aim is to take action while grasping, reduce clutter, and effectively complete grasping tasks. Based on deep reinforcement learning, the Efficient Learning Grasping(ELG) framework is proposed that integrates pushing actions alongside grasping to efficiently pick up objects from cluttered environments with reduced training time. However, in the process of grasping, the agent is rewarded only when the grasp is successful, so the data collection is extremely inefficient and spends a lot of time on the training of grasping strategy. In our work, two strategies are proposed to improve the training efficiency. First, two mask functions are introduced as prior knowledge to enable the agent to focus on more meaningful regions while ignoring some unnecessary regions, aiming at effective learning. Second, The Pixel Overlap Rate (POR) is introduced to quantify the environment clutter level, and set a new push action reward function based on the POR. The implementation of the above ideas in a simulation environment and transferred the learned models to the real world and verified them in practice. Compared with existing method, our method improves the training efficiency of the initial algorithm while having a higher success rate of grasping. Detailed grasping video at https://***/CqtSvaVl60M. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Dynamic Multi-Task Interactive Evolutionary Optimization Algorithm with Search Space Alignment 13

Dynamic Multi-Task Interactive Evolutionary Optimization Alg...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Wu, Weidong Sun, Xiaoyan Zhang, Yong Song, Wei School of Information and Control Engineering China University of Mining and Technology Xuzhou China School of Artifical Intelligence and Computer Science Jiangnan University Wuxi China

ISBN: (纸本)9798350308365

The interactive evolutionary multi-task optimization approach assisted by surrogate models has proven successful in enhancing individualized recommendation performance. However, in light of the dynamically changing user preferences, it becomes imperative to further develop more powerful knowledge sharing strategy to improve the interactive multi-task optimization efficiency. A probability model-assisted search space alignment among multiple tasks method is proposed for knowledge transfer across multi-task environment. Additionally, a diversity maintaining mechanism of the transferred population is proposed to improve the quality and diversity of the initial population in a preference varied multi-task environment. The research demonstrates the effectiveness of the proposed approach in achieving effective knowledge transfer across multi-task environmen. Furthermore, the utilization of a high-quality initial population not only enhances the evolutionary search efficiency of the algorithm but also significantly improves the accuracy, diversity., and novelty of personalized recommendation. © 2024 IEEE.

关键词： Dynamic optimization Interactive evolutionary algorithm Multi-task optimization Personalized recommendation Subspace alignment

来源：评论

学校读者我要写书评

暂无评论

Combined CNN-LSTM Deep Learning Algorithms for Recognizing Human Physical Activities in Large and Distributed Manners:A Recommendation System

引用

computers, Materials & Continua 2024年第4期79卷 351-372页

作者： Ameni Ellouze Nesrine Kadri Alaa Alaerjan Mohamed Ksantini Control and Energy Management Laboratory National Engineering SchoolPreparatory Institute for Engineering StudiesUniversity of SfaxSfax3029Tunisia Higher Institute of Computer Science and Communication Technologies University of SousseSousseBN19RHTunisia College of Computer and Information Sciences Jouf UniversityPO Box 2014SakakahSaudi Arabia

Recognizing human activity(HAR)from data in a smartphone sensor plays an important role in the field of health to prevent chronic *** and weekly physical activities are recorded on the smartphone and tell the user whether he is moving well or ***,smartphones and their associated sensing devices operate in distributed and unstable ***,collecting their data and extracting useful information is a significant *** this context,the aimof this paper is twofold:The first is to analyze human behavior based on the recognition of physical *** the results of physical activity detection and classification,the second part aims to develop a health recommendation system to notify smartphone users about their healthy physical behavior related to their physical *** system is based on the calculation of calories burned by each user during physical *** this way,conclusions can be drawn about a person’s physical behavior by estimating the number of calories burned after evaluating data collected daily or even weekly following a series of physical *** identify and classify human behavior our methodology is based on artificial intelligence models specifically deep learning techniques like Long Short-Term Memory(LSTM),stacked LSTM,and bidirectional *** human activity data contains both spatial and temporal information,we proposed,in this paper,to use of an architecture allowing the extraction of the two types of information *** Convolutional Neural Networks(CNN)has an architecture designed for spatial information,our idea is to combine CNN with LSTM to increase classification accuracy by taking into consideration the extraction of both spatial and temporal *** results obtained achieved an accuracy of 96%.On the other side,the data learned by these algorithms is prone to error and *** overcome this constraint and improve performance(96%),we proposed to use the

关键词： Human physical activities smartphone sensors deep learning distributed monitoring recommendation system uncertainty healthy calories

来源：评论

学校读者我要写书评

暂无评论

Improving Security and Performance of Databases Through Single Cache System 4

Improving Security and Performance of Databases Through Sing...

引用

4th International Conference on Blockchain Technology and Information Security, ICBCTIS 2024

作者： Ul Haq, Ikram Khan, Salabat Khan, Mansoor Tamsal, Saher School of Computer Science and Technology Southwest University of Science and Technology Mianyang China School of Computer and Information Engineering Qilu Institute of Technology Jinan China School of Intelligent Manufacturing and Control Engineering Qilu Institute of Technology Jinan China University of Agriculture Department of Computer Science Faisalabad Pakistan

ISBN: (纸本)9798331528324

In today's world, connectivity and performance-driven technology are rapidly advancing each year, and new platforms and mechanisms are being utilized to enhance the security and performance of databases and cloud computing, which are trending in the global market. This examination focused on customer information security in cloud computing, i.e., information stockpiling security issues and how to control unapproved access to data by proposing access control;valuable measures were characterized subsequently, and an entrance control show was prescribed. Cloud computing can be described as an innovation that depends on the web and the sharing of resources. It has an adaptable foundation that customers can use with much of a stretch. With its wide event relationship, there are numerous obstacles to continuing with cloud computing because of security issues, mostly considering customer data security. The proposed study helped hesitant clients sensibly continue forward in the cloud while understanding the dangers of cloud computing. The research objective is to examine the security techniques employed in cloud technology to improve its performance by utilizing data mining within a unified cache system. We will apply the Apriori algorithm as a proposed solution to be used in a single cache while considering the security measures in the cloud. The study expects to apply this method to all cloud providers and vendors by entering data into a single cache mechanism that can be extended into different components and implemented using SPSS modelers to improve the security of the database. © 2024 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

Salinity sensing by the radio-frequency power based on the Michelson interferometer

Salinity sensing by the radio-frequency power based on the M...

引用

2024 Asia Communications and Photonics Conference, ACP 2024 and International Conference on Information Photonics and Optical Communications, IPOC 2024

作者： Gui, Lin Chen, Xuhui Mao, Chengxin Li, Qiankun Peng, Yu Wu, Mengmeng School of Computer and Information Engineering Shanghai Polytechnic University Shanghai China School of Intelligent Manufacturing and Control Engineering Shanghai Polytechnic University Shanghai China School of Resources and Environmental Engineering Shanghai Polytechnic University Shanghai China

ISBN: (纸本)9798350379266

The salinity sensing technology based on the microwave photonic method is proposed and experimentally verified. The microwave photonic filter is formed by the microwave photonic interferometry of the Michelson interferometer. Contrast to the traditional method based on the optical spectrum measurement, the salinities information can be measured by extracting the minimum values of radio frequency(RF) response curves of microwave photonic filter(MPF). Due to amount of noise and the nonlinearity in the MPF, the minimum values of RF response of MPF vary with time, so the averaged values of several measurements are utilized in data analyzing process. Experimental results show that the salinity sensitivity of 0.284dB/% is achieved with the brine concentration in the range of 31%-40% and the value of R-square can reach 0.88 by linearity fitting for salinity sensing, and the value can be improved to 0.979 by Cubic fitting. © 2024 IEEE.

关键词： Michelson interferometers

来源：评论

学校读者我要写书评

暂无评论

FAB-D2PIM: A Full Anonymous Blockchain-based Distributed Privacy-Preserving Incentive Mechanism for Crowdsensing 5

FAB-D2PIM: A Full Anonymous Blockchain-based Distributed Pri...

引用

5th International Conference on Industrial Artificial Intelligence, IAI 2023

作者： Cheng, Jiameng Zhang, Hongwei Tianjin University of Technology School of Computer Science and Engineering Tianjin China National Engineering Laboratory for Computer Virus Prevention and Control Technology Tianjin China

ISBN: (纸本)9798350325294

Privacy-preserving incentive mechanism in crowd-sensing systems is an ongoing research challenge, partly due to the untrusted centralized servers and sensitive data leakage. In this paper, we focus on a secure incentive way with blockchain. First, we analyze the limitations in traditional crowdsensing systems with a trusted third party (TTP) and identify three ways privacy in the incentive mechanism (IM) of crowdsensing: identity, data, and revenues. Then, we propose a novel decentralized system for IM based on a full anonymous blockchain called FAB-D2PIM. In the proposed system, we use a one-way aggregate signature scheme (Boneh et al. EUROCRYPT 2003) for identity privacy and homomorphic Public Key Encryption (Boneh et al. TCC 2005) for sensing data and reward privacy. The proposed scheme not only protects the privacy of the workers but also decreases the operation rate of the task publishing center. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

ViT lightweight training at IoT edge based on transfer learning

ViT lightweight training at IoT edge based on transfer learn...

引用

2024 International Conference on Optics, Electronics, and Communication engineering, OECE 2024

作者： Li, Zhixin Long, Yang Miao, Jiahao School of Computer Technology and Engineering Changchun Institute of Technology Jilin Changchun130012 China School of Information and Control Engineering Jilin Institute of Chemical Technology Jilin Jilin132022 China

ISBN: (纸本)9781510685437

Recently, the vision transformer (ViT) model of deep learning has achieved surprising performance in the field of computer vision and has been widely used in IoT edge devices. However, the training of ViT models requires a large amount of data and computing resources, which is a challenge for resource-constrained edge IoT devices. To solve the above problems, this paper proposed a lightweight ViT method based on transfer learning. The primary concept of this method is to train large-scale ViT models in the cloud (CloudViT) and deploying small-scale ViT models at the edge (EdgeViT). Firstly, through the method of transfer learning, some underlying parameters of CloudViT were utilized to construct EdgeViT. The purpose is to enable EdgeViT to learn from CloudViT, acquiring knowledge and improving its performance. Secondly, adding a randomly initialized LayerNorm layer before the MLPHead during the training process of EdgeViT, it can improve further model performance. Finally, Experiment results demonstrated that EdgeViT could achieve 91.3% of CloudViT’s performance with only half the parameters and floating-point operations (FLOPs). Moreover, finetuning EdgeViT with a 60% reduction in training time still allows it to achieve 81.3% of CloudViT’s performance. Relevant conclusions can provide technical support for the proposed method. © 2024 SPIE.

关键词： Data modeling Clouds Internet of things Performance modeling Instrument modeling Neural networks Head Visual process modeling Image classification

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：