检索结果-内蒙古大学图书馆

2022 International Conference on Networking and Network Applications, NaNA 2022

作者： Wang, Aiguo Meng, Yue Zhao, Liang Liu, Jinjun Chen, Guilin School of Electronic Information Engineering Foshan University Foshan China School of Computer Science and Technology Donghua University Shanghai China School of Computer and Information Engineering Chuzhou University Chuzhou China

ISBN: (数字)9781665461313

ISBN: (纸本)9781665461313

Ambient sensor-based in-home activity recognition plays a crucial role in the design and development of a smart home to better and actively respond to population aging. From the perspective of machine learning, how to extract features from sensor data largely determines the power of a data-driven human activity recognizer. However, few studies systematically investigate how to encode streaming sensor events. To this end, we herein conduct a comparison of different feature extraction techniques for activity recognition. Specifically, we explore two types of feature representations (i.e., statistical features and structural features) and evaluate their single use and joint use. Besides, we experimentally analyze the impact of window size on prediction accuracy. Finally, we perform experiments on three public datasets with 15 different feature encodings and 6 classifiers. Results show that the joint use of different features generally obtains enhanced accuracy and that the interval 60s of window size achieves a better accuracy-speed tradeoff. © 2022 IEEE.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

GraphFed: A Personalized Subgraph Federated Learning Framework for Non-IID Graphs 20

GraphFed: A Personalized Subgraph Federated Learning Framewo...

引用

20th IEEE International Conference on Mobile Ad Hoc and Smart systems, MASS 2023

作者： Deng, Pan Liu, Xuefeng Niu, Jianwei Hu, Chunming Zhongguancun Laboratory Beijing China Zhengzhou University Research Institute of Industrial Technology School of Information Engineering Zhengzhou University Zhengzhou China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China

ISBN: (纸本)9798350324334

Recently, federated graph learning has attracted significant attention, as subgraphs of a global graph may often distribute across different institutions and are subject to privacy restrictions. However, inevitable data heterogeneity among sub-graphs can lead to poor performance of Graph Neural Networks (GNNs) trained by vanilla federated learning algorithm, which has been neglected before. To address this problem we look at subgraphs and find that there are usually overlapping nodes among them. Inspired by the common overlapping nodes among subgraphs, we propose GraphFed, a subgraph federated learning framework which solve the challenge in terms of both data augmentation and personalized federated learning. GraphFed uses common overlapping nodes among subgraphs to locate lost node information and applies data augmentation by retrieving lost nodes and forming common node sets that mitigates data distribution difference. Furthermore, GraphFed treats the overlapping nodes as bridges to calculate the distance among different subgraphs, which implies the similarity of the graph data distribution. Then, we use the distance to perform personalized federated learning. Empirical results and analysis on three real-world graph datasets with graph federated learning settings demonstrate the effectiveness of our proposed framework. © 2023 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Imputation of incomplete medical data using missing neighborhood perturbation denoising autoencoder

Imputation of incomplete medical data using missing neighbor...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Qi, Huamei Yang, Wenhui Fu, Sen Deng, Lei Central South University Department of Electronic Information Changsha China Ningxia University School of Economics and Management Yinchuan China Central South University School of Computer Science and Engineering Changsha China

ISBN: (纸本)9798350386226

The problem of missing data in the clinical environment is a common one. However, the presence of these missing values or incorrect processing can affect downstream tasks. Imputation is the most effective way to solve the missing problem. Combining deep generative models and multiple imputation idea provides new ideas for the imputation of data, but some methods do not apply to mixed-type tabular data such as clinical data. The missing types of tabular data in real-world scenarios are varied and unpredictable, so it is necessary to construct a generalized imputation method. In this paper, we propose a multiple imputation architecture for missing neighborhood perturbation denoising autoencoder (MI-NPDAE) for imputing mixed types of incomplete medical tabular data for different missing mechanisms. In MI-NPDAE, the neighborhood information of the data is searched to find the best set of donors to be used as the input layer of the network, and the learning of the neighborhood features of the missing locations is ensured by reconstructing new inputs, while the addition of additive noise exposes the model to different missing mechanisms. The experiments were respectively conducted on a public dataset Breast and one lung cancer nutrition dataset from the Chinese Anti-Cancer Society. The experiments on the datasets show that the proposed model shows better results under different missing mechanisms and can maintain a low error on the comparison experiments on data with different missing ratios. In addition, the imputed results also show significant advantages in downstream prediction tasks. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Feature Selection for Disease Prediction in Medical Diagnosis Using Machine Learning 2

Feature Selection for Disease Prediction in Medical Diagnosi...

引用

2nd IEEE International Conference on IoT, Communication and Automation Technology, ICICAT 2024

作者： Devendran, K. Keerthika, P. Sagana, C. Abinaya, A. Sangeetha, M. Karuppuchamy, R. Bhuvaneshwari, R. Kongu Engineering College Department of Computer Science and Engineering Tamil Nadu Erode India Vellore Institute of Technology School of Computer Science and Engineering Tamil Nadu Vellore India Dr. N.G.P.Institute of Technology Department of Information Technology Tamil Nadu Coimbatore India

ISBN: (纸本)9798350368109

Feature selection is the technique widely used when experimented with huge dataset that can be used for dimensionality reduction to extract most recognizable features from the huge dataset and it also improves the performance of classification methods and helps in selecting relevant features. The most common method utilized in this work to extract the important characteristics from the COVID-19 dataset is feature selection, after which the derived dataset is utilized for disease prediction. The outcomes aim to offer nuanced insights into the applicability of these techniques for disease prediction, aiding healthcare professionals and researchers in selecting suitable models tailored to specific scenarios. © 2024 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Human action recognition in immersive virtual reality based on multi-scale spatio-temporal attention network

Human action recognition in immersive virtual reality based ...

引用

作者： Xiao, Zhiyong Chen, Yukun Zhou, Xinlei He, Mingwei Liu, Li Yu, Feng Jiang, Minghua School of Computer Science and Artificial Intelligence Wuhan Textile University Wuhan China School of Electrical and Electronic Engineering Nanyang Technological University Singapore Singapore Engineering Research Center of Hubei Province for Clothing Information Wuhan China

Wearable human action recognition (HAR) has practical applications in daily life. However, traditional HAR methods solely focus on identifying user movements, lacking interactivity and user engagement. This paper proposes a novel immersive HAR method called MovPosVR. Virtual reality (VR) technology is employed to create realistic scenes and enhance the user experience. To improve the accuracy of user action recognition in immersive HAR, a multi-scale spatio-temporal attention network (MSSTANet) is proposed. The network combines the convolutional residual squeeze and excitation (CRSE) module with the multi-branch convolution and long short-term memory (MCLSTM) module to extract spatio-temporal features and automatically select relevant features from action signals. Additionally, a multi-head attention with shared linear mechanism (MHASLM) module is designed to facilitate information interaction, further enhancing feature extraction and improving accuracy. The MSSTANet network achieves superior performance, with accuracy rates of 99.33% and 98.83% on the publicly available WISDM and PAMPA2 datasets, respectively, surpassing state-of-the-art networks. Our method showcases the potential to display user actions and position information in a virtual world, enriching user experiences and interactions across diverse application scenarios. © 2024 John Wiley & Sons Ltd.

关键词： human activity recognition multi-scale feature spatio-temporal feature virtual reality

来源：评论

学校读者我要写书评

暂无评论

Towards imbalanced motion:part-decoupling network for video portrait segmentation

引用

science China(information sciences) 2024年第7期67卷 197-210页

作者： Tianshu YU Changqun XIA Jia LI State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang University Peng Cheng Laboratory

Video portrait segmentation(VPS), aiming at segmenting prominent foreground portraits from video frames, has received much attention in recent years. However, the simplicity of existing VPS datasets leads to a limitation on extensive research of the task. In this work, we propose a new intricate large-scale multi-scene video portrait segmentation dataset MVPS consisting of 101 video clips in 7 scenario categories,in which 10843 sampled frames are finely annotated at the pixel level. The dataset has diverse scenes and complicated background environments, which is the most complex dataset in VPS to our best *** the observation of a large number of videos with portraits during dataset construction, we find that due to the joint structure of the human body, the motion of portraits is part-associated, which leads to the different parts being relatively independent in motion. That is, the motion of different parts of the portraits is imbalanced. Towards this imbalance, an intuitive and reasonable idea is that different motion states in portraits can be better exploited by decoupling the portraits into parts. To achieve this, we propose a part-decoupling network(PDNet) for VPS. Specifically, an inter-frame part-discriminated attention(IPDA)module is proposed which unsupervisedly segments portrait into parts and utilizes different attentiveness on discriminative features specified to each different part. In this way, appropriate attention can be imposed on portrait parts with imbalanced motion to extract part-discriminated correlations, so that the portraits can be segmented more accurately. Experimental results demonstrate that our method achieves leading performance with the comparison to state-of-the-art methods.

关键词： video portrait segmentation imbalanced motion unsupervised part decoupling motion correlation inter-frame attention

来源：评论

学校读者我要写书评

暂无评论

Semantic-Aware Prompt Learning for Multimodal Sarcasm Detection

Semantic-Aware Prompt Learning for Multimodal Sarcasm Detect...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Wang, Guangjin Wang, Bao Xu, Fuyong Zhu, Zhenfang Wang, Peipei Wang, Ru Liu, Peiyu School of Information Science and Engineering Shandong Normal University Jinan China School of Information Science and Electrical Engineering Shandong Jiao Tong University Jinan China Qilu University of Technology Shandong Academy of Sciences Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (纸本)9798350368741

Multimodal sarcasm detection aims to identify whether utterances express sarcastic intentions contrary to their literal meaning based on multimodal information. However, existing methods fail to explore the model's "ability to understand" the semantics expressed by sentences in the image context from semantic diversity perspectives. In this paper, we propose a multi-view semantic awareness method, which concretizes semantics from multiple perspectives to improve the model's ability to capture different semantic features. Specifically, two learnable prefixes are attached to the text representation respectively to construct semantic representations from both the literal meaning and sarcastic intention perspectives. Then, image-text information is further fused through cross-attention to guide the semantic representation of different perspectives in the image context. Finally, the semantics expressed by prefixes are strengthened through KL divergence, thereby encouraging the model to capture two distinctive semantic features. Experiments on benchmark datasets demonstrate the effectiveness of our method. © 2025 IEEE.

关键词： KL divergence multi-view semantic representation multimodal sarcasm detection semantic representation enhancement

来源：评论

学校读者我要写书评

暂无评论

IoT Based Drip Infusion Monitoring System

IoT Based Drip Infusion Monitoring System

引用

2022 IEEE Delhi Section Conference, DELCON 2022

作者： Maniktalia, Riddhi Tanwar, Satwik Billa, Ritvik Deepa, K. School of Computer Science and Engineering Vellore Institute of Technology Vellore India School of Computer Science and Engineering Vellore Institute of Technology Department of Software Systems Vellore India

ISBN: (纸本)9781665458832

During recent years, we have seen many technological advancements which help to take better care of patient's health and assure them fast and safe recovery. The most basic item necessary is competent patient care in hospitals, as well as proper management of fluid and electrolytes. In hospital almost all patients, mainly ICU patients, have to regulate the volume of fluids and electrolyte into the bloodstream 247 which is done using drip. These drips need regular monitoring or changing to maintain constant flow of fluids or to prevent any infection to patients. Though this system is simple, overcrowded hospitals and the risk of deficiency of nurses can put patients at health risk which can deteriorate patients' health more aggressively or in worse case it can lead to death. Almost in all hospitals, nurses or the hospital staff are responsible for monitoring the drip level. But unfortunately, because of their hectic schedule, the observer may forget to change the bottle at the appropriate time. During the pandemic, hospitals were overrun with patients, and nurses were unable to do manual regular checks on the drip conditions and drip level of every patient, even after working extra shifts. Many patients even died due to not being able to get proper care from nurses. The next step in providing more effective and easy healthcare is to automate such vital procedures. To overcome this critical situation, we are proposing an IoT (Internet of Things) based Drip Monitor System using Arduino UNO which eases the process of measuring and solves the issues of bubble formation in drips. © 2022 IEEE.

关键词： Health risks

来源：评论

学校读者我要写书评

暂无评论

A Novel Approximate Message Passing Detection for Massive MIMO 5G System

引用

computer systems science & engineering 2023年第6期45卷 2827-2835页

作者： Nidhi Gour Rajneesh Pareek Karthikeyan Rajagopal Himanshu Sharma Mrim M.Alnfiai Mohammed A.AlZain Mehedi Masud Arun Kumar Department of Computer Science&Engineering JECRC UniversityJaipurIndia Centre for Nonlinear Systems Chennai Institute of TechnologyChennaiIndia Department of Electronics and Communication Engineering and University Centre for Research&Development Chandigarh UniversityMohaliIndia Department of Information Technology College of Computer and Information TechnologyTaif UniversityP.O.Box 11099Taif21994Saudi Arabia Department of Computer Science College of Computers and Information TechnologyTaif UniversityP.O.Box 11099TaifSaudi Arabia Department of Electronics and Communication Engineering JECRC UniversityJaipurIndia

Massive-Multiple Inputs and Multiple Outputs(M-MIMO)is considered as one of the standard techniques in improving the performance of Fifth Generation(5G)radio.5G signal detection with low propagation delay and high throughput with minimum computational intricacy are some of the serious concerns in the deployment of *** evaluation of 5G promises a high quality of service(QoS),a high data rate,low latency,and spectral efficiency,ensuring several applications that will improve the services in every *** existing detection techniques cannot be utilised in 5G and beyond 5G due to the high complexity issues in their *** the proposed article,the Approximation Message Passing(AMP)is implemented and compared with the existing Minimum Mean Square Error(MMSE)and Message Passing Detector(MPD)*** outcomes of the work show that the performance of Bit Error Rate(BER)is improved with minimal complexity.

关键词： AMP MMSE MPD 5G

来源：评论

学校读者我要写书评

暂无评论

Multiple occurrence point recognition method for unsafe traffic driving behavior based on YOLOv5 visual perception

Advances in Transportation Studies

引用

Advances in Transportation Studies 2023年第Special Issue期1卷 51-62页

作者： Guo, Y.R. Wu, R.N. Patnaik, S. School of Mathematics and Information Engineering Longdong University Qingyang745000 China Lanzhou Big Data Administration Bureau 122 Gannan Middle Road Lanzhou730000 China Department of Computer Science and Engineering SOA University Bhubaneswar751030 India

Reducing the risk behaviors of drivers during driving is of great significance to improve the level of road traffic safety. Using intelligent technology to monitor unsafe behaviors of drivers can effectively reduce and control the occurrence of unsafe events of drivers, and avoid and reduce casualties and property losses. In this paper, we propose a multiple occurrence point recognition method for traffic unsafe driving behavior based on YOLOv5 visual perception. This method uses media filtering to remove the noise of driving image, divides the image in YOLOv5 network structure, objectifies the image features;uses visual perception to obtain the true aspect ratio, calculates the fatigue coefficient;uses threshold value to judge unsafe driving behavior, and determines the frequent occurrence of unsafe driving through low function. The results show that the data SNR of this method can reach ***, the recall rate can reach 99.0%, and the recognition time is less than 8s, indicating that this method has stronger recognition performance. © 2023, Aracne Editrice. All rights reserved.

关键词： Aspect ratio

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：