检索结果-内蒙古大学图书馆

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Mingwang Xu Wei Wang Kuanquan Wang Suyu Dong Pengzhong Sun Jinwei Sun Gongning Luo Faculty of Computing Harbin Institute of Technology Harbin China School of Computer Science and Technology Harbin Institute of Technology Shenzhen China College of Computer and Control Engineering Northeast Forestry University Harbin China School of Instrumentation Science and Engineering Harbin Institute of Technology Harbin China

Breast cancer continues to be a pressing global health concern, emphasizing the essential need for effective diagnostic techniques. Automated Breast Ultrasound Systems (ABUS) provide a promising advance in breast tumor detection, yet they require significant expertise in interpreting 3D ABUS images, a task fraught with distinctive challenges. Although Vision Transformers (ViT) display remarkable potential for image processing, their low inductive bias and significant data requirements pose obstacles, particularly in the data-constrained medical field. To mitigate these issues, we introduce a Mask-Recover strategy for pretraining Transformer models on 3D ABUS images, enhancing model adaptability and reducing the data demands of the ViT model. Moreover, recognizing the risk that ViTs’ average pooling approach may unintentionally mask small but vital features, we propose Dual-CapsViT, an inventive model combining Transformers and Capsule Networks. This integration affords efficient token routing while preserving fine-grained details. To reconcile potential inconsistencies between capsules and tokens, we engineer a novel dual-channel routing algorithm, strengthening the decoder’s performance. We benchmarked our models against well-known standards such as ResNet and ViT for classifying breast tumors in ABUS images. Our models exhibited superior performance, as evidenced by improved accuracy, specificity, and Area Under the Receiver Operating Characteristic Curve (AUC) metrics, thereby affirming Dual-CapsViT’s potential to enhance breast cancer diagnostics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Triple IRS-Aided Communications: Row-Column Sparsity Enhanced Bayesian Tensor Learning for Channel Estimation

引用

IEEE Transactions on Communications 2025年

作者： Hu, Limei Shao, Xiaodan Qiu, Tingzhi Chen, Feng Cheng, Lei Wu, Qingqing Southwest University College of Artificial Intelligence College of Electronic and Information Engineering Brain-Inspired Computing and Intelligent Control of Chongqing Key Laboratory National and Local Joint Engineering Laboratory of Intelligent Transmission and Control Technology Chongqing400715 China University of Waterloo Department of Electrical and Computer Engineering WaterlooONN2L 3G1 Canada Zhejiang University College of Information Science and Electronic Engineering Hangzhou310058 China Shanghai Jiao Tong University Department of Electronic Engineering Shanghai China

Channel acquisition presents a major challenge in deploying intelligent reflecting surfaces (IRS) aided communication systems, due to massive reflective elements that create a complex multi-path channel and increase channel dimensions. For an IRS-aided communication system, complete channel includes three parts: From the users to IRS, from the IRS to BS, and from the BS back to the IRS. Thus, a generalized multi-IRS cascaded communication system with three cascaded IRSs is considered. Unfortunately, existing channel estimation methods focus on single or double IRS cascades, which is not applicable to the case of triple cascaded IRS channel estimation directly. In this paper, we study the uplink channel estimation for triple cascaded IRSs aided single-user single-input single-output (SISO) systems. Specifically, the triple IRS cascaded channel is typically sparse. It permits us to characterize the channel estimation as a problem of sparse matrix recovery. Then, the sparse learning is explored to achieve robust channel estimation with limited training overhead. Particularly, the sparse channel matrices of the cascaded triple IRS channels have a common row-column block sparsity structure. However, a unique challenge lies in characterizing and enhancing such a common row-column sparsity. To tackle this issue, we apply a random matrix prior to promote the common row-column-wise sparsity of the channel matrix, and then an efficient Bayesian tensor inference algorithm is proposed to estimate the IRS channel. Finally, simulation results confirm that the proposed scheme outperforms traditional counterparts in terms of accuracy. © 1972-2012 IEEE.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

Cross-Layer Optimization for Fault-Tolerant Deep Learning

arXiv

引用

arXiv 2023年

作者： Zhang, Qing Liu, Cheng Liu, Bo Huang, Haitong Wang, Ying Li, Huawei Li, Xiaowei Both State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100190 China Beijing Institite of Control Engineering Beijing100190 China

Fault-tolerant deep learning accelerator is the basis for highly reliable deep learning processing and critical to deploy deep learning in safety-critical applications such as avionics and robotics. Since deep learning is known to be computing- and memory-intensive, traditional fault-tolerant approaches based on redundant computing will incur substantial overhead including power consumption and chip area. To this end, we propose to characterize deep learning vulnerability difference across both neurons and bits of each neuron, and leverage the vulnerability difference to enable selective protection of the deep learning processing components from the perspective of architecture layer and circuit layer respectively. At the same time, we observe the correlation between model quantization and bit protection overhead of the underlying processing elements of deep learning accelerators, and propose to reduce the bit protection overhead by adding additional quantization constrain without compromising the model accuracy. Finally, we employ Bayesian optimization strategy to co-optimize the correlated cross-layer design parameters at algorithm layer, architecture layer, and circuit layer to minimize the hardware resource consumption while fulfilling multiple user constraints including reliability, accuracy, and performance of the deep learning processing at the same time. © 2023, CC BY.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Integrated Energy-Efficient Distributed Link Stability Algorithm for UAV Networks

引用

Computers, Materials & Continua 2024年第11期81卷 2357-2394页

作者： Altaf Hussain Shuaiyong Li Tariq Hussain Razaz Waheeb Attar Farman Ali Ahmed Alhomoud Babar Shah School of Computer Science and Technology Chongqing University of Posts and TelecommunicationsChongqing400065China Key Laboratory of Industrial Internet of Things and Networked Control Ministry of EducationChongqing University of Posts and TelecommunicationsChongqing400065China School of Computer Science and Information Engineering Zhejiang Gongshang UniversityHangzhou310018China Management Department College of Business AdministrationPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Applied AI School of ConvergenceCollege of Computing and InformaticsSungkyunkwan UniversitySeoul03063Republic of Korea Department of Computer Science College of ScienceNorthern Border UniversityArar91431Saudi Arabia College of Technological Innovation Zayed UniversityDubai19282United Arab Emirates

Ad hoc networks offer promising applications due to their ease of use,installation,and deployment,as they do not require a centralized control *** these networks,nodes function as senders,receivers,and *** such network is the Flying Ad hoc Network(FANET),where nodes operate in three dimensions(3D)using Unmanned Aerial Vehicles(UAVs)that are remotely *** the integration of the Internet of Things(IoT),these nodes form an IoT-enabled network called the Internet of UAVs(IoU).However,the airborne nodes in FANET consume high energy due to their payloads and low-power *** optimal routing approach for communication is essential to address the problem of energy consumption and ensure energy-efficient data transmission in *** paper proposes a novel energy-efficient routing protocol named the Integrated Energy-Efficient Distributed Link Stability Algorithm(IEE-DLSA),featuring a relay mechanism to provide optimal routing with energy efficiency in *** energy efficiency of IEE-DLSA is enhanced using the Red-Black(R-B)tree to ensure the fairness of advanced energy-efficient *** link stability,transmission loss avoidance,delay awareness with defined threshold metrics,and improving the overall performance of the proposed protocol are the core functionalities of *** simulations demonstrate that the proposed protocol performs well compared to traditional FANET routing *** evaluation metrics considered in this study include network delay,packet delivery ratio,network throughput,transmission loss,network stability,and energy consumption.

关键词： FANET UAV internet of UAVs relay mechanism energy consumption routing IEE-DLSA

来源：评论

学校读者我要写书评

暂无评论

Towards efficient implementation of MLP-ANN classifier on the FPGA-based embedded system

引用

IFAC-PapersOnLine 2022年第4期55卷 207-212页

作者： Rijad Sarić Nejra Beganović Dejan Jokić Edhem Čustović School of Computing Engineering and Mathematical Sciences La Trobe University 3086 Victoria Melbourne Australia Chair of Dynamics and Control University of Duisburg-Essen 47057 Duisburg Germany Department of Electrical and Electronics Engineering International Burch University 71000 Sarajevo Bosnia and Herzegovina

Epilepsy is a widely known neurological disease, causing atypical brain activity such as seizures. Apparently, it is critical to analyse possible triggers as well as establish appropriate medical treatment based on the seizure type. In general, diagnosis of epilepsy is usually conducted by applying various state-of-the-art algorithms to extract useful information from electroencephalography (EEG) signals. For effective real-time epilepsy diagnosis, the biomedical device integrated with the best performing machine learning algorithm is needed. Multilayer Perceptron (feed-forward) Artificial Neural Network (MLP-ANN) has proven to be a much better choice over traditional supervised machine learning algorithms in achieving high accuracy diagnosis. Challenges exist in handling extremely long data processing time in the case of many features in EEG signals plus complex MLP-ANN structure and computations. This research proposes the 5-12-3 MLP-ANN configuration to classify different types of epileptic seizures using Field Programmable Gate Array (FPGA) as a real-time embedded system.

关键词： MLP-ANN FPGA Epileptic seizure Real-time diagnosis

来源：评论

学校读者我要写书评

暂无评论

A Sub-mother UAV System Capable of Autonomous Aerial Docking

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年

作者： Li, Gang Lu, Yi He, Bin Pang, Tao Cheng, Bin Zhang, Pengpeng College of Electronics and Information Engineering Tongji University Shanghai201804 China Shanghai Research Institute for Intelligent Autonomous Systems Shanghai200120 China Shanghai Sunshine Rehabilitation Center Shanghai201613 China National Key Laboratory of Autonomous Intelligent Unmanned Systems Shanghai200120 China East China Institute of Computing Technology Shanghai201822 China Department of Control Science and Engineering College of Electronics and Information Engineering Tongji University Shanghai China College of Electronic and Information Engineering Tongji University Shanghai China

Completing the docking between two multi-rotor unmanned aerial vehicles (UAVs) in the air has great significance for expanding the application scenarios of multiple UAVs and improving their endurance capability. In this regard, this paper first designs a safe and autonomous docking scheme and constructs a sub-mother UAV *** address the issue of unstable flight in downwash airflow, this paper designs a high-performance control method suitable for the sub-mother UAV system based on Incremental Nonlinear Dynamic Inversion (INDI) and achieves robust attitude control with strong disturbance rejection capability. A UWB-based Ortho-UWB 3D positioning method is proposed in this paper with orthogonal installation, which, after being integrated with visual methods, enables high-precision 3D relative positioning during the docking process of the sub-mother UAV ***, the paper designs a complete docking process for the sub-mother UAVs and incorporates safety constraints into the docking process to ensure the safety of the docking process for both UAVs. Experiments of successfully docking the sub UAV to the mother UAV from bottom to top prove the feasibility and effectiveness of this scheme. © 2024 IEEE.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

Attention-Driven Graph Convolutional Networks for Deadline-Constrained Virtual Machine Task Allocation in Edge computing

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Ali, Ahmad Ullah, Inam Singh, Sushil Kumar Jiang, Weiwei Alturise, Fahad Bai, Xiaoshan Shenzhen University College of Mechatronics and Control Engineering Shenzhen518060 China Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen518060 China Beijing University of Posts and Telecommunications Beijing China Qassim University College of Computer Department of Cybersecurity Buraydah Saudi Arabia

Effective load balancing is critical in contemporary mobile computing environments to ensure optimal resource utilization and adherence to strict deadlines. This study presents a novel framework for deadline-constrained load balancing, termed DCLD-net, which leverages the integration of Graph Convolutional Networks (GCN) and an attention-based Bidirectional Gated Recurrent Unit (BiGRU). The proposed framework utilizes the spatial modeling capabilities of GCNs to capture intricate network topologies, while the temporal dynamics and attention mechanisms of BiGRU enable the identification of critical patterns in traffic flow data. By incorporating key factors such as sticky sessions, load distribution, content-based factors such as videos or file downloads, instance health checks, and other relevant parameters, the DCLD-net model achieves high accuracy in predicting task schedules. These schedules allocate tasks to virtual machines (VMs), enabling dynamic traffic routing through a load balancer that efficiently assigns tasks. Extensive experimental evaluations demonstrate that the proposed attention-based BiGRU-GCN model significantly outperforms traditional methods in both deadline compliance and load balancing efficiency, offering a robust solution to the challenges of modern cloud computing. Experimental results demonstrate that DCLD-net outperforms traditional methods by 27% in deadline compliance and 29.3% in load balancing efficiency. © 1975-2011 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

A new model to correlate solubility of drug compounds in supercritical carbon dioxide

引用

Chemical Thermodynamics and Thermal Analysis 2025年 18卷

作者： Raghavan, Amrithaa Alwi, Ratna Surya M, Geetha Devi Garlapati, Chandrasekhar Centre for Pollution Control and Environmental Engineering Pondicherry University Puducherry 605014 India Research Center for Computing National Research and Innovation Agency (BRIN) Jl. Raya Jakarta-Bogor KM 46 Cibinong Indonesia Department of Mechanical & Industrial Engineering College of Engineering National University of Science & Technology Oman Department of Chemical Engineering Puducherry Technological University Puducherry 605014 India

A new solubility model based on enhancement factor concept is proposed to correlate solubility of drug compounds in supercritical carbon dioxide (SCCO2). The correlating ability of the new model is compared with exist... 详细信息

A new solubility model based on enhancement factor concept is proposed to correlate solubility of drug compounds in supercritical carbon dioxide (SCCO₂). The correlating ability of the new model is compared with existing solubility model. The proposed model and existing models were tested with twenty nine drug-supercritical carbon dioxide systems reported in the literature. The proposed model correlating performance is indicated in terms of absolute relative deviation percentage. Additionally, Akaike's Information Criterion (AIC) was used to assess the model's performance compared with existing solubility model. The results show the compared to existing solubility model, the proposed model accurately correlates the *** global absolute average relative deviation percentage for the existing model and proposed new model are 22.17 % and 16.11 % respectively. © 2025

关键词： Akaike's information criterion Enhancement factor Solubility Supercritical carbon dioxide

来源：评论

学校读者我要写书评

暂无评论

Stress Severity Detection in College Students Using Emotional Pulse Signals and Deep Learning

引用

IEEE Transactions on Affective computing 2025年

作者： Li, Mi Li, Junzhe Chen, Yanbo Hu, Bin School of Information Science and Technology Beijing University of Technology Beijing International Collaboration Base on Brain Informatics and Wisdom Services Engineering Research Center of Intelligent Perception and Autonomous Control Ministry of Education China Engineering Research Center of Digital Community Ministry of Education Beijing China Beijing University of Technology School of Information Science and Technology Beijing China Beijing Institute of Technology Institute of Engineering Medicine Beijing China Lanzhou University Gansu Provincial Key Laboratory of Wearable Computing School of Information Science and Engineering Lanzhou China

College students face increasing stress from difficulties with studies, employment, and social interactions, which, if left unaddressed, may lead to depression and physical illnesses. Currently, the detection of stress severity relies on self-assessment scales, while machine learning or deep learning-based approaches primarily focus on classification. This study proposes an approach using pulse signals containing emotional cues and deep learning to automatically detect the severity of stress in college students. Firstly, pulse signals of 177 college students were collected using photoplethysmography (PPG) during they watched five virtual reality (VR) emotional scenes, including calm, sadness, happiness, fear, and tension. Pulse rate variability (PRV) and discrete PPG (dPPG) were extracted from these signals as input for detecting stress severity. Then, the proposed stress detection framework, 1DCNN-BiLSTM + Cross-Attention + XGBoost, was employed to detect stress severity, incorporating an emotional Cross-Attention mechanism. The impact of induced emotions on stress severity detection performance was examined. The results indicated that stress severity detection in emotional scenes outperformed in calm. Furthermore, the detection performance that integrates multiple emotions surpassed single emotions. The fusion of PRV and dPPG signals yielded the best detection performance. This study provides an end-to-end automated approach for detecting stress severity in college students. © 2010-2012 IEEE.

关键词： Photoplethysmography

来源：评论

学校读者我要写书评

暂无评论

Few-shot Object Detection Algorithm Based on YOLOv8-Mamba-Like Linear Attention

Few-shot Object Detection Algorithm Based on YOLOv8-Mamba-Li...

引用

International Conference on Communication Software and Networks, ICCSN

作者： Hongliang Wang Kaizhu Wang Binglong Ji Changyi Deng Liaoning Province Human- Computer Interaction System Engineering Research Center Based on DigitTwin Shenyang Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Shenyang China Shenyang Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Shenyang China Industrial Control Systems Cyber Emergency Response Team Institute of Software China Beijing China

ISBN: (数字)9798331506322

ISBN: (纸本)9798331506339

In the production and assembly process, the accuracy of detection is usually low due to limited resources and small quantities. In this paper, we propose a few-shot learning method for object detection based on the combination of YOLOv8 and Mamba-Like Linear Attention (MLLA) module. This method utilizes a high-pixel camera to capture the shape and size of the workpiece. By consistency-based mutual augmentation structure for few-shot samples data augmentation. By introducing the efficient and lightweight MLLA module, the model’s speed and accuracy in object detection and segmentation tasks on mobile devices are significantly improved. Specifically, MLLA mainly integrates the two key elements of “forget gate” and “block design” in Mamba, and MLLA replaces forget gate by using position coding (RoPE) to provide necessary location information while maintaining parallel computation and fast inference speed. This makes MLLA improves the accuracy of detection and segmentation recognition. Experimental results show that compared to the original YOLOv8 model, the model with the MLLA module exhibits improvements in segmentation precision and recognition accuracy. This method demonstrates high accuracy and robustness in workpiece recognition, making it suitable for real-time industrial applications.

关键词： Accuracy Shape Computational modeling Object detection Production Logic gates Feature extraction Robustness Software Real-time systems

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：