检索结果-内蒙古大学图书馆

1st ieee International Conference on Applied Intelligence and Sustainable Computing, ICAISC 2023

作者： Luo, Junyou Gong, Xinyue Tan, Hao Chen, Chunguang Kang, Yu Fu, Taoran Hunan Institute of Engineering School of Computational Science and Electronics Xiangtan China Hunan Institute of Engineering School of Computer and Communication Xiangtan China

ISBN: (纸本)9798350323795

Compared to traditional business activities, e-commerce activities are more susceptible to the impact of logistics networks and various emergency situations. Therefore, in the event of a special situation, e-commerce operators urgently need an optimized emergency response plan. This article aims to establish a logistics network scheduling model to help operators cope with emergencies and improve operational efficiency in emergency situations. The article establishes a path planning model that considers how the logistics network can quickly plan when a warehouse or road suddenly closes, which can meet the logistics transportation requirements and minimize the number of logistics adjustments required. The article focuses on the classification integration and visualization of logistics network data, evaluates the importance of each logistics location and road, determines the workload and efficiency, dynamically adjusts the logistics sites, and discusses the impact of logistics site closures and the feasibility of this research method. The planning model developed in this article has strong reference value for the mobilization plan of real logistics. © 2023 ieee.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

TAMFN: Time-Aware Attention Multimodal Fusion Network for Depression Detection

引用

ieee TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING 2023年 31卷 669-679页

作者： Zhou, Li Liu, Zhenyu Shangguan, Zixuan Yuan, Xiaoyan Li, Yutong Hu, Bin Lanzhou Univ Gansu Prov Key Lab Wearable Comp Lanzhou 730000 Peoples R China

In recent years, with the widespread popularity of the Internet, social media has become an indispensable part of people's lives. People regard online social media as an essential tool for interaction and communication. Due to the convenience of data acquisition from social media, mental health research on social media has received a lot of attention. The early detection of psychological disorder based on social media can help prevent further deterioration in at-risk people. In this paper, depression detection is performed based on non-verbal (acoustics and visual) behaviors of vlog. We propose a time-aware attention-based multimodal fusion depression detection network (TAMFN) to mine and fuse the multimodal features fully. The TAMFN model is constructed by a temporal convolutional network with the global information (GTCN), an intermodal feature extraction (IFE) module, and a time-aware attention multimodal fusion (TAMF) module. The GTCN model captures more temporal behavior information by combining local and global temporal information. The IFE module extracts the early interaction information between modalities to enrich the feature representation. The TAMF module guides the multimodal feature fusion by mining the temporal importance between different modalities. Our experiments are carried out on D-Vlog dataset, and the comparative experimental results report that our proposed TAMFN outperforms all benchmark models, indicating the effectiveness of the proposed TAMFN model.

关键词： Depression Feature extraction Social networking (online) Convolution data mining visualization Kernel vlog non-verbal behaviors automatic detection time-aware attention-based multimodal fusion depression detection network (TAMFN)

来源：评论

学校读者我要写书评

暂无评论

data Mining and Analysis of Video Barrage By AI Algorithm 5

Data Mining and Analysis of Video Barrage By AI Algorithm

引用

5th ieee Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2023

作者： Gong, Daoqing Gan, Xinyan Tang, Xiaonian Li, Hua Gao, Xiang School of Public Health and Management Guangxi University of Chinese Medicine Nanning530200 China School of Computer Science and Engineering Yulin Normal University Yulin537000 China Guangxi College for Preschool Education Department of Special Education Nanning530022 China

ISBN: (纸本)9798350320978

The barrage is an important form for the audience to express their emotions and opinions. It runs through the entire video and feeds back audience's overall evaluation of the plot type, characters, and even actors of the videos. Mining such information from massive barrages not only has important academic value but also provides a reference for relevant business decisions to increase film traffic and revenue. We crawled the bullet screen information of 5 different types of recommended movies in the Bilibili bullet screen network in 2021 and performed statistical analysis on the data in a graphical visualization manner. The user's attention is analyzed through the word cloud map. The distribution of the number of bullet screens was used to reflect the changes in the number of viewers every week and every day, and the degree of attention during the film screening process was analyzed. Sentiment analysis is performed on the obtained bullet screen data based on artificial intelligence algorithms. First, the Word2vec model generated the word vector of the bullet screen text and input it into the machine learning model SVM and the deep learning model TextCNN for classification. The experimental results show that the deep learning model is higher than the traditional model in accuracy. © 2023 ieee.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Beyond CNNs: Exploiting Further Inherent Symmetries in Medical Image Segmentation

引用

ieee TRANSACTIONS ON CYBERNETICS 2023年第11期53卷 6776-6787页

作者： Pang, Shuchao Du, Anan Orgun, Mehmet A. Wang, Yan Sheng, Quan Z. Wang, Shoujin Huang, Xiaoshui Yu, Zhenmei Nanjing Univ Sci & Technol Sch Cyber Sci & Engn Nanjing 210094 Peoples R China Macquarie Univ Sch Comp Sydney NSW 2109 Australia Univ Technol Sydney Sch Elect & Data Engn Ultimo NSW 2007 Australia Univ Technol Sydney Data Sci Inst Ultimo NSW 2007 Australia Shanghai AI Lab Shanghai 200433 Peoples R China Shandong Womens Univ Sch Data & Comp Sci Jinan 250014 Peoples R China

Automatic tumor or lesion segmentation is a crucial step in medical image analysis for computer-aided diagnosis. Although the existing methods based on convolutional neural networks (CNNs) have achieved the state-of-the-art performance, many challenges still remain in medical tumor segmentation. This is because, although the human visual system can detect symmetries in 2-D images effectively, regular CNNs can only exploit translation invariance, overlooking further inherent symmetries existing in medical images, such as rotations and reflections. To solve this problem, we propose a novel group equivariant segmentation framework by encoding those inherent symmetries for learning more precise representations. First, kernel-based equivariant operations are devised on each orientation, which allows it to effectively address the gaps of learning symmetries in existing approaches. Then, to keep segmentation networks globally equivariant, we design distinctive group layers with layer-wise symmetry constraints. Finally, based on our novel framework, extensive experiments conducted on real-world clinical data demonstrate that a group equivariant Res-UNet (called GER-UNet) outperforms its regular CNN-based counterpart and the state-of-the-art segmentation methods in the tasks of hepatic tumor segmentation, COVID-19 lung infection segmentation, and retinal vessel detection. More importantly, the newly built GER-UNet also shows potential in reducing the sample complexity and the redundancy of filters, upgrading current segmentation CNNs, and delineating organs on other medical imaging modalities.

关键词： Image segmentation Task analysis Medical diagnostic imaging Computational modeling Kernel Solid modeling Context modeling Control across kernels group equivariant segmentation framework medical image segmentation neural networks visualization analysis

来源：评论

学校读者我要写书评

暂无评论

DrawingInStyles: Portrait Image Generation and Editing With Spatially Conditioned StyleGAN

引用

ieee TRANSACTIONS ON visualization AND COMPUTER GRAPHICS 2023年第10期29卷 4074-4088页

作者： Su, Wanchao Ye, Hui Chen, Shu-Yu Gao, Lin Fu, Hongbo City Univ Hong Kong Sch Creat Media Kowloon Tong Hong Kong Peoples R China Chinese Acad Sci Beijing Key Lab Mobile Comp & Pervas Device Inst Comp Technol Beijing 100045 Peoples R China Chinese Acad Sci Beijing Key Lab Mobile Comp & Pervas Device Inst Comp Technol Beijing 100045 Peoples R China Univ Chinese Acad Sci Beijing 101408 Peoples R China

The research topic of sketch-to-portrait generation has witnessed a boost of progress with deep learning techniques. The recently proposed StyleGAN architectures achieve state-of-the-art generation ability but the original StyleGAN is not friendly for sketch-based creation due to its unconditional generation nature. To address this issue, we propose a direct conditioning strategy to better preserve the spatial information under the StyleGAN framework. Specifically, we introduce Spatially Conditioned StyleGAN (SC-StyleGAN for short), which explicitly injects spatial constraints to the original StyleGAN generation process. We explore two input modalities, sketches and semantic maps, which together allow users to express desired generation results more precisely and easily. Based on SC-StyleGAN, we present DrawingInStyles, a novel drawing interface for non-professional users to easily produce high-quality, photo-realistic face images with precise control, either from scratch or editing existing ones. Qualitative and quantitative evaluations show the superior generation ability of our method to existing and alternative solutions. The usability and expressiveness of our system are confirmed by a user study.

关键词： Faces Semantics Image synthesis Codes Training Transforms Spatial resolution Sketch-based portrait generation suggestive interfaces data-driven approaches StyleGAN conditional generation

来源：评论

学校读者我要写书评

暂无评论

Super-Resolution of Wireless Channel Characteristics: A Multitask Learning Model

引用

ieee TRANSACTIONS ON ANTENNAS AND PROPAGATION 2023年第10期71卷 8197-8209页

作者： Wang, Xiping Guan, Ke He, Danping Zhang, Zhao Zhang, Haoyang Dou, Jianwu Zhong, Zhangdui Beijing Jiaotong Univ State Key Lab Adv Rail Autonomous Operat Beijing 100044 Peoples R China Beijing Engn Res Ctr High Speed Railway Broadband Beijing 100044 Peoples R China China Key Lab Railway Ind Broadband Mobile Informa Beijing 100044 Peoples R China Beijing Engn Res Ctr High Speed Broadband Mobile C Beijing 100044 Peoples R China ZTE Corp State Key Lab Mobile Network andMobile Multimedia Shenzhen 518055 Peoples R China

Channel modeling has always been the core part of the design and development of communication system, especially in the sixth-generation (6G) era. Traditional approaches like stochastic channel modeling and ray-tracing (RT)-based channel modeling depend heavily on measurement data or simulation, which are usually expensive and time-consuming. In this article, we propose a super-resolution (SR) model for recovering high-resolution (HR) channel characteristics from sparse sampling data. The model is based on multitask learning (MTL) convolutional neural networks (CNNs) with attention mechanism and residual connection. Experiments demonstrate that the proposed MTL SR model could achieve fairly good performances in terms of mean absolute error (MAE) and standard deviation of error (STDE). The advantages of the proposed model are demonstrated in comparison with other state-of-the-art deep learning (DL) models and visualization of SR performances. The ablation study also proved the necessity of data augmentation and the techniques in the model design. The good generalizability of the proposed MTL SR model leads to discussions of potential applications. The contribution of this article could be helpful in channel modeling, network optimization, positioning, and other wireless channel characteristics-related work by largely reducing the workload of simulation or measurement.

关键词： data models Wireless communication Training Deep learning Channel estimation Urban areas Three-dimensional displays Convolutional neural network (CNN) multitask learning (MTL) ray-tracing (RT) super-resolution (SR) wireless channel modeling

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal Self-Attention Network for Video Saliency Prediction

引用

ieee TRANSACTIONS ON MULTIMEDIA 2023年 25卷 1161-1174页

作者： Wang, Ziqiang Liu, Zhi Li, Gongyang Wang, Yang Zhang, Tianhong Xu, Lihua Wang, Jijun Shanghai Univ Shanghai Inst Adv Commun & Data Sci Shanghai 200444 Peoples R China Shanghai Univ Sch Commun & Informat Engn Shanghai 200444 Peoples R China Nanyang Technol Univ Sch Comp Sci & Engn Singapore 639798 Singapore Univ Manitoba Dept Comp Sci Winnipeg MB R3T 2N2 Canada Shanghai Jiao Tong Univ Sch Med Shanghai Mental Hlth Ctr Shanghai Key Lab Psychot Disorders Shanghai 200030 Peoples R China

3D convolutional neural networks have achieved promising results for video tasks in computer vision, including video saliency prediction that is explored in this paper. However, 3D convolution encodes visual representation merely on fixed local spacetime according to its kernel size, while human attention is always attracted by relational visual features at different time. To overcome this limitation, we propose a novel Spatio-Temporal Self-Attention 3D Network (STSANet) for video saliency prediction, in which multiple Spatio-Temporal Self-Attention (STSA) modules are employed at different levels of 3D convolutional backbone to directly capture long-range relations between spatio-temporal features of different time steps. Besides, we propose an Attentional Multi-Scale Fusion (AMSF) module to integrate multi-level features with the perception of context in semantic and spatio-temporal subspaces. Extensive experiments demonstrate the contributions of key components of our method, and the results on DHF1K, Hollywood-2, UCF, and DIEM benchmark datasets clearly prove the superiority of the proposed model compared with all state-of-the-art models.

关键词： Three-dimensional displays Computational modeling visualization Solid modeling Task analysis Semantics Computer vision Attention mechanism self-attention spatio-temporal feature video saliency prediction

来源：评论

学校读者我要写书评

暂无评论

Mahalanobis Distance Based DBSCAN For Vessel Near Collision Detection 7

Mahalanobis Distance Based DBSCAN For Vessel Near Collision ...

引用

7th International Conference on Information Technology, Information Systems and Electrical Engineering, ICITISEE 2023

作者： Asana, I Made Dwi Putra Widyantara, I Made Oka Linawati Wiharta, Dewa Made Udayana University Engineering Science Department Badung Indonesia Udayana University Electrical Engineering Department Badung Indonesia Udayana Unversity Electrical Engineering Department Badung Indonesia

ISBN: (纸本)9798350382266

Mahalanobis Distance-based DBSCAN is a method for detecting potential near-collision among ship using AIS data. In general, the detection of near-collision is very important in preventing ship accidents. DBSCAN plays a critical role in detecting potential collision between maritime ship. Furthermore, its clustering method identifies ship that is in close proximity, showing potential collision risks. The distance between these objects is a fundamental aspect of DBSCAN clustering method. The attributes of latitude, longitude, and heading in AIS data showed correlations and diverse distributions. However, Euclidean distance measurement failed to consider these correlations and variations. To address this limitation, the current study proposed Mahalanobis distance-based DBSCAN clustering to recognize potential near-collision scenarios. The method incorporated receiving AIS data, cleaning the data to remove docked ship, calculating the covariance matrix, computing Mahalanobis distance, performing DBSCAN clustering, and visualizing cluster outcomes. visualization of cluster, measurement of distance variables, and assessment of silhouette coefficient scores were used to analyze near-collision detection results. Mahalanobis-based DBSCAN effectively generated cluster associated with near-collision scenarios, as shown by the Dr, DCP A, and TCP A values of the ship pairs. Mahalanobis distance showed superior cluster quality compared to Euclidean distance, with scores of 0.291 and 0.125, respectively. © 2023 ieee.

关键词： Ships

来源：评论

学校读者我要写书评

暂无评论

Exploratory Investigation and Alzheimer's Disease Classification Utilizing Ensemble Models in Machine Learning 1

Exploratory Investigation and Alzheimer's Disease Classifica...

引用

1st ieee International Conference on Ambient Intelligence, Knowledge Informatics and Industrial Electronics, AIKIIE 2023

作者： Chandralekha, E. Prem M, Vigilson Cyndhiya J, Janet Gokila, E. Vasudevan, I. Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Dept.of Cse Chennai India R.M.K. College of Engineering and Technology Dept.of Cse Chennai India

ISBN: (纸本)9798350316469

The Alzheimer's disease (AD) is a highly prevalent neurodegenerative disorder that affects an estimated 20 million people worldwide. It is characterized by changes in behavior, deteriorated cognitive abilities, and memory loss. For prompt intervention and efficient treatment of Alzheimer's disease (AD), it is imperative to identify and diagnose the disease as early as possible. In recent years, machine learning methods have become increasingly popular for detecting Alzheimer's disease (AD), with clinical data being used as the main source of information. This paper provides a comprehensive analysis of the detection of Alzheimer's disease using machine learning techniques. In this research, several key components are included, including data preprocessing, visualization of feature relevance, and evaluation of performance for five ensemble classifiers: Random Forest, AdaBoost, Gradient Boosting, Extra Trees, and Bagging. Principal Component Analysis (PCA) is used to reduce the number of attributes of a model and better understand the importance of particular features within the dataset. In addition, the research rigorously evaluates the efficacy of the classifier by utilizing a distinct test dataset. The models' prediction powers are assessed by calculating and reporting various metrics, including accuracy, precision, recall, and Fl-score. © 2023 ieee.

关键词： AdaBoost Alzheimer's disease data preprocessing Ensemble classifiers Machine learning Random Forest

来源：评论

学校读者我要写书评

暂无评论

A Novel Framework to Generate Synthetic Video for Foreground Detection in Highway Surveillance Scenarios

引用

ieee TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2023年第6期24卷 5958-5970页

作者： Li, Xuan Duan, Haibin Liu, Bingzi Wang, Xiao Wang, Fei-Yue Peng Cheng Lab Shenzhen 518000 Peoples R China Beihang Univ Sch Automat Sci & Elect Engn Key Lab Virtual Real Technol & Syst Beijing 100083 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

Foreground detection (FD) plays an important role in the domain of video surveillance for highway. The design of advanced FD algorithms requires large-scale and diverse video dataset. However, collecting and labeling real dataset is still time-consuming, labor-intensive, and highly subjective. To address this issue, we first use computer graphics (CG) to clone real highway scenarios (HS) and generate synthetic multi-challenge video datasets, called "Synthetic-HS (CG)", automatically labeled with accurate pixel-level ground truth. The Synthetic-HS (CG) dataset contains eight imaging condition sequences for computer vision research. Then, we design an image translation (IT) model that translates source domain (Synthetic-HS (CG)) to target domain (real). This model uses skip connections and attention module to generate realistic synthetic images "Synthetic-HS (IT)". We use publicly available Synthetic-HS in combination with the corresponding real video sequence to conduct experiments. The experiment results suggest that: 1) The Synthetic-HS (CG) dataset enables us to provide precise quantitative evaluation of the drawbacks of foreground detection methods 2) The realistic Synthetic-HS (IT) images can be used to promote the visual perception in highway video surveillance.

关键词： Computational modeling Surveillance Road transportation Generative adversarial networks Synthetic data Solid modeling visualization Foreground detection highway surveillance parallel intelligent synthetic dataset scenarios engineering

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：