检索结果-内蒙古大学图书馆

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Sibo Qiao Zhiyuan Zhao Pengfei Xie Wenjing Yin Min Wang Yuanyuan Zhang Shanchen Pang The College of Software Tiangong University Tianjin China The College of Computer Science and Technology China University of Petroleum Qingdao China The Department of Electrical Engineering and Computer Science Khalifa University of Science and Technology Abu Dhabi United Arab Emirates The College of Life Sciences Tiangong University Tianjin China The College of Information and Control Engineering Qingdao University of Technology Qingdao China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

In the rapidly advancing landscape of intelligent medical technology, high-precision and widely applicable medical image segmentation techniques are pivotal in advancing personalized treatment plans and enhancing patient experiences. To address inherent obstacles, such as complex structures and features that are difficult to capture in segmentation tasks, we first propose a CMH module that merges convolutional neural networks (CNNs) with state space models (e.g., Mamba). This module hierarchically integrates CNN’s local priors into the Mamba layer, adeptly capturing specific details of target objects and broader contextual information from different perspectives. Subsequently, we introduce an information fusion module based on Mamba (MIH), aimed at dynamically fusing feature information from different paths and levels to enhance feature expression and discrimination. Building upon the abovementioned modules, we develop an unexplored segmentation model, CMHNet, capable of flexibly capturing feature maps of varying scales and angles from medical images. In the experiments, we present CMHNet’s distinguished performance in segmentation tasks through massive experiments on four medical datasets.

关键词： Image segmentation Sensitivity Anatomical structure Medical services Robustness Real-time systems Lesions Medical diagnostic imaging Optimization Testing

来源：评论

学校读者我要写书评

暂无评论

SensoryT5: Infusing Sensorimotor Norms into T5 for Enhanced Fine-grained Emotion Classification

arXiv

引用

arXiv 2024年

作者： Xia, Yuhan Zhao, Qingqing Long, Yunfei Xu, Ge Wang, Jia School of Computer Science and Electronic Engineering University of Essex United Kingdom Institute of Linguistics Chinese Academy of Social Sciences China College of Computer and Control Engineering Minjiang University China Department of Intelligent Science Xi’an Jiaotong-Liverpool University China

In traditional research approaches, sensory perception and emotion classification have traditionally been considered separate domains. Yet, the significant influence of sensory experiences on emotional responses is undeniable. The natural language processing (NLP) community has often missed the opportunity to merge sensory knowledge with emotion classification. To address this gap, we propose SensoryT5, a neuro-cognitive approach that integrates sensory information into the T5 (Text-to-Text Transfer Transformer) model, designed specifically for fine-grained emotion classification. This methodology incorporates sensory cues into the T5’s attention mechanism, enabling a harmonious balance between contextual understanding and sensory awareness. The resulting model amplifies the richness of emotional representations. In rigorous tests across various detailed emotion classification datasets, SensoryT5 showcases improved performance, surpassing both the foundational T5 model and current state-of-the-art works. Notably, SensoryT5’s success signifies a pivotal change in the NLP domain, highlighting the potential influence of neuro-cognitive data in refining machine learning models’ emotional sensitivity. © 2024, CC BY-SA.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Optimal control of Constrained Trajectory Optimization Problem of UAV with Limited Sensing

Optimal Control of Constrained Trajectory Optimization Probl...

引用

Chinese Automation Congress (CAC)

作者： Long Xiao Miao Liu Xialai Wu Shaopan Guo Benyun Shi Wenyan Ci College of Computer and Information Engineering (College of Artificial Intelligence) Nanjing Tech University Nanjing China Huzhou Key Laboratory of Intelligent Sensing and Optimal Control for Industrial Systems Huzhou University Huzhou China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

Optimal control of constrained unmanned aerial vehicle (UAV) trajectory optimization problem is one of the frontiers and hotspots of UAV research. The various constraints generated by physical limitations and obstacles in the environment increase the difficulties of solving the trajectory optimization problem, especially when the limited sensing ability is taken into consideration. This paper presents the receding horizon optimization method to obtain optimal control for the UAV with limited sensing range in a complex environment with obstacles. To improve efficiency, a path constraint processing method is proposed to reduce the number of constraints in the nonlinear programming problem (NLP). The proposed main structure and detailed algorithm are also given. The numerical results demonstrate the effectiveness of the proposed method compared with the classical Gauss pseudospectral method.

关键词： Automation Computational modeling Optimal control Optimization methods Programming Autonomous aerial vehicles Sensors Finite element analysis Time factors Trajectory optimization

来源：评论

学校读者我要写书评

暂无评论

Security Issues in Software-Defined Networking (SDN) Environments

Security Issues in Software-Defined Networking (SDN) Environ...

引用

Roedunet International Conference (RoEduNet)

作者： Khirota Gorgees Yalda Diyar Jamal Hamad Nicolae Tapus Ibrahim Taner Okumus Faculty of Automatic Control and Computer Science Politehnica University of Bucharest Bucharest Romania IT department Soran Technical college Erbil Polytechnic University Kurdistan Region Erbil Iraq Computer Engineering Faculty of engineering Kahramanmaras Sutcu Imam University Kahramanmaras Turkey

ISBN: (数字)9798331540388

ISBN: (纸本)9798331540395

Software-Defined Networking (SDN) represents a significant shift in network architecture, providing exceptional programmability, flexibility, and simplified management. However, this paradigm shift introduces a unique set of security challenges that must be addressed to fully realize the potential of SDN. This paper examines the security issues in SDN environments, detailing the threats and vulnerabilities at various layers of the SDN architecture, including the control plane, data plane, and application plane. Through an extensive review of current literature, critical security challenges such as controller attacks, data plane breaches, and vulnerabilities in inter-plane communications are identified. Existing security solutions and mitigation strategies, such as authentication and authorization mechanisms, encryption techniques, and intrusion detection systems, are also explored. Furthermore, the paper discusses recent advances and emerging trends in SDN security, offering insights into ongoing research and future directions. The findings underscore the importance of robust security measures in ensuring the reliability and integrity of SDN deployments, providing a foundation for future innovation and development in this dynamic field.

关键词： Technological innovation Prevention and mitigation Intrusion detection Distributed databases Organizations Robustness Encryption Security Software defined networking computer crime

来源：评论

学校读者我要写书评

暂无评论

The prognostic impact of pathogenic stromal cell-associated genes in lung adenocarcinoma

引用

computers in Biology and Medicine 2024年 178卷 108692-108692页

作者： Zhou, Murong Li, Hongfei Gao, Bo Zhao, Yuming College of Computer and Control Engineering Northeast Forestry University Harbin150040 China College of Life Science Northeast Forestry University Harbin150040 China Department of Radiology The Second Affiliated Hospital Harbin Medical University Harbin150040 China

Background: Lung adenocarcinoma (LUAD) stands as the most prevalent subtype among lung cancers. Interactions between stromal and cancer cells influence tumor growth, invasion, and metastasis. However, the regulatory mechanisms of stromal cells in the lung adenocarcinoma tumor microenvironment remain unclear. This study seeks to elucidate the regulatory connections among critical pathogenic genes and their associated expression variations within distinct stromal cell subtypes. Method: Analysis and investigation were conducted on a total of 114,019 single-cell RNA data and 346 The Cancer Genome Atlas (TCGA) LUAD-related samples using bioinformatics and statistical algorithms. Differential gene expression analysis was performed for tumor samples and controls, followed by Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis. Differential genes between stromal cells and other cell clusters were identified and intersected with the differential genes from TCGA. We employed a combination of LASSO regression and multivariable Cox regression to identify the ultimate set of pathogenic gene. Survival models were trained to predict the relationship between patient survival and these pathogenic genes. Analysis of transcription factor (TF) cell specificity and pseudotime trajectories within stromal cell subpopulations revealed that vascular endothelial cells (ECs) and matrix cancer-associated fibroblasts (CAFs) are key in regulation of the prognosis-associated genes CAV2, COL1A1, TIMP1, ETS2, AKAP12, ID1 and COL1A2. Results: Seven pathogenic genes associated with LUAD in stromal cells were identified and used to develop a survival model. High expression of these genes is linked to a greater risk of poor survival. Stromal cells were categorized into eight subtypes and one unannotated cluster. Mesothelial cells, vascular endothelial cells (ECs), and matrix cancer-associated fibroblasts (CAFs) showed cell-specific regulation of the pathogenic genes. Conclusions: The seven

关键词： Fibroblasts

来源：评论

学校读者我要写书评

暂无评论

Falcon Optimized CNN for the Detection of Alzheimer's Disease in MRI Image

Falcon Optimized CNN for the Detection of Alzheimer's Diseas...

引用

Smart Systems for applications in Electrical Sciences (ICSSES), International Conference on

作者： S. Febeena Ezhil Jothi L. Mahalakshmi P. Elamurugan Naveenkumar Kaliyan J. Swapna R. Rajeshwari Department of Artificial Intelligence and Data Science Adhi College of Engineering And Technology Kanchipuram Department of Biomedical Engineering Kongunadu College of Engineering and Technology Trichy Department of Instrumentation and Control Engineering Sri Manakula Vinayagar Engineering College Puducherry Department of Computer science and Engineering Veltech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai Tamilnadu India Department of Electrical and Electronics Engineering J.P. College of Engineering Ayikudi Tenkasi

ISBN: (数字)9798331507671

ISBN: (纸本)9798331507688

Degenerative illnesses that lead to the eventual death of brain neurons afflict a large number of people. Compared to the traditional Machine Learning (ML) approach, the recent success in the medical community of classifying Alzheimer's Disease (AD) utilized a Deep Learning (DL) technique eliminates the necessity for manual feature extraction techniques. Although DL methods are widely used, there is currently a dearth of trustworthy and comprehensive research on the quantitative analysis of brain Magnetic Resonance Image (MRI) data. In this paper, an effective AD classification approach is proposed that use MRI to classify brain structure and diagnose AD. Gaussian filter is used to eliminate noises at different degrees of complexity, noisy backgrounds, low contrast, and partial volume effect in the original input image. Next, K-Means clustering segmentation is useful for dividing image into different regions based on pixel intensity values. Key features for categorization are extracted using the Gray Level Co-Occurrence Matrix (GLCM) method. A Convolutional Neural Network (CNN), enhanced by Falcon Optimization Algorithm (FOA), is employed for AD categorization. The proposed system, implemented on the Python platform using the best Alzheimer's MRI dataset, demonstrates an enhanced accuracy of 93.21 %. Additionally, this model-based approach provides a capable avenue for advancing research in the early detection of AD and holds substantial potential in differentiating AD patients from healthy individuals.

关键词： Training Accuracy Magnetic resonance imaging Neurons Magnetic resonance Feature extraction Convolutional neural networks Alzheimer's disease Optimization Testing

来源：评论

学校读者我要写书评

暂无评论

Mixed Strategy PSO for Global Optimization

Mixed Strategy PSO for Global Optimization

引用

2021 IEEE International Conference on Space-Air-Ground Computing, SAGC 2021

作者： Pang, Jinwei Li, Xiaohui Han, Shuang School of Computer and Control Engineering Yantai University Yantai China Harbin Vocational & Technical College Harbin China Harbin Engineering University Department of Computer Science and Technology Harbin China

ISBN: (纸本)9781665400114

Particle Swarm Optimization (PSO) is an evolutionary algorithm for solving global optimization problems. In recent two decades, a lot of researches have been working on improving the performance of PSO and numerous PSO variants have been presented. According to a recent theory, the hardest problem to one evolutionary algorithm may be the easiest to another algorithm, and vice versa. Thus, mixed strategy PSO algorithms might be more efficient than pure strategy algorithms. A mixed strategy PSO algorithm (MSPSO) was proposed which integrates five different PSO variants. In MSPSO, an adaptive selection strategy is used to adjust the probability of selecting different variants according to the rate of the fitness value change between offspring generated by each variant and the personal best position of particles to guide the selection probabilities of variants. The rate of the fitness value change is a more effective indicator of good strategies than the number of previous successes and failures of each variant. The proposed algorithm is tested on CEC 2014 benchmark suites with 10 variables. Experimental results demonstrate that the solution accuracy of the proposed algorithm is overall better than those of comparative algorithms. © 2021 IEEE.

关键词： Global optimization

来源：评论

学校读者我要写书评

暂无评论

Distributed Event-Triggered Adaptive Cooperative Circumnavigation control of Networked Unmanned Aerial Vehicles

Distributed Event-Triggered Adaptive Cooperative Circumnavig...

引用

IEEE SSD International Multi-Conference on Systems, Signals and Devices

作者： Jawhar Ghommam Raouf Fareh Ibrahim Al Naimi Department of Electrical and Computer Engineering College of Engineering Sultan Qaboos University Laboratory of Control Energy Management ENIS Tunisa Electrical Engineering Dept. University of Sharjah UAE

In this paper, the objective for a group of unmanned aerial vehicle agents (UAVs) to achieve three dimensional circumnavigation around a moving target which information is made available to all agents in the group. The cooperative circumnavigation is to drive the UAVs to orbit around the target according to a given elliptical desired spatial formation. Due to the thrust limitation needed to fly the drone, existing cyclic pursuit algorithms cannot be extended directly to achieve this objective. Thus the proposed algorithm is worked out to take into account this constraint in order to achieve such objective. The drones are subject to unknown external disturbance, also the masses of those agent drones are assumed to be unknown. Furthermore, the communication cost can be decreased and the Zeno behavior is shown to be excluded. The proposed controller guarantees the bounded control effort irrespective of the external disturbance and model uncertainties of the drone. Numerical simulations are conducted to illustrate the efficacy of the approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Which Policy is Used by the CNS to control Human Standing Posture: Intermittent or Impulsive control?

Which Policy is Used by the CNS to Control Human Standing Po...

引用

Iranian Conference of Biomedical engineering (ICBME)

作者： Neda Bayat Fariba Bahrami Mohammad Javad Yazdanpanah Human Motor Control and Computational Neurosience Lab Advanced Control Systems Lab School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran

The aim of this research is to model the function of the Central Nervous System (CNS) when controlling human standing posture which paves the way for designing external skeletal structures for rehabilitation or in an industrial direction, for building human-like biped robots. We used a simple inverted pendulum with one degree of freedom to model body skeletal dynamics. Three different feedback control policies were used to describe the function of the CNS, and the stability of the whole closed-loop model under each policy was studied. The policies we considered for the CNS as a controller are: 1) intermittent control, 2) impulsive control, and 3) hybrid control, which is a combination of intermittent and impulsive. The stability of the closed-loop model under each policy was evaluated numerically using Lyapunov stability criteria. Our simulation results indicate that while the intermittent policy results in a stable system, impulsive control is more efficient in terms of energy consumption. Consequently, a hybrid control strategy will result in a system that compromises between stability and energy efficiency.

关键词： Service robots Computational modeling Simulation Stability criteria control systems Energy efficiency Numerical models

来源：评论

学校读者我要写书评

暂无评论

Client Selection Based on Channel Capacity for Federated Learning Under Wireless Channels

Client Selection Based on Channel Capacity for Federated Lea...

引用

Asia-Pacific Conference on Communications

作者： Satoshi Yamazaki Takuma Furuki Dept. of Control and Computer Engineering National Institute of Technology Numazu College Numazu Japan Systems Innovation Faculty of Engineering Tokyo University Tokyo Japan

This paper proposes a user selection scheme for federated learning (FL) over wireless networks to reduce communication time based on channel capacity. In particular, the edge server calculates the Shannon channel capacity of each client for each round, and clients with a certain threshold capacity are randomly selected to participate in FL. We show that the convergence time of the proposed scheme outperformed that of the conventional scheme through computer simulation based on an image processing task under a wireless channel with pass-loss, shadowing, and Rician flat-fading. Moreover, the superiority of FL to centralized learning (CL) regarding total time is demonstrated theoretically and validated through computer simulation.

关键词：

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：