检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Liu, Hongyu Cong, Runmin Li, Hua Xu, Qianqian Huang, Qingming Zhang, Wei Institute of Information Science Beijing Jiaotong University Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing China School of Control Science and Engineering Shandong University Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Computer Science and Technology Hainan University Hainan China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

Preserving details and avoiding high computational costs are the two main challenges for the High-Resolution Salient Object Detection (HRSOD) task. In this paper, we propose a two-stage HRSOD model from the perspective of evolution and succession, including an evolution stage with Low-resolution Location Model (LrLM) and a succession stage with High-resolution Refinement Model (HrRM). The evolution stage achieves detail-preserving salient objects localization on the low-resolution image through the evolution mechanisms on supervision and feature;the succession stage utilizes the shallow high-resolution features to complement and enhance the features inherited from the first stage in a lightweight manner and generate the final high-resolution saliency prediction. Besides, a new metric named Boundary-Detail-aware Mean Absolute Error (MAEBD) is designed to evaluate the ability to detect details in high-resolution scenes. Extensive experiments on five datasets demonstrate that our network achieves superior performance at real-time speed (49 FPS) compared to state-of-the-art methods. Our code is publicly available at: https://***/rmcong/ESNet_ICML24. Copyright 2024 by the author(s)

关键词： Miocene

来源：评论

学校读者我要写书评

暂无评论

Biometric individual identification system based on the ECG signal 19th

Biometric individual identification system based on the ECG ...

引用

19th International Conference on Intelligent systems Design and Applications, ISDA 2019

作者： Hamza, Sihem Ben Ayed, Yassine Higher Institute of Computer Science and Multimedia ISIMS University of Sfax Sfax Tunisia Multimedia InfoRmation Systems and Advanced Computing Laboratory MIRACL University of Sfax Sfax Tunisia

ISBN: (纸本)9783030493417

Human biometric identification based on the ElectroCardioGram (ECG) is relatively new. This domain is intended to recognize individuals since the ECG has unique characteristics for each individual. These features are robust against forgery. In this study, feature extraction from ECG signals was performed using a combination of three new types of characteristics: MFCC, ZCR, and entropy. We proposed to apply classification methods: K Nearest Neighbors (KNN) and support vector machines (SVM) for human biometric identification. For evaluation we used two bases, namely MIT-BIH arrhythmia and normal sinus rhythm obtained from the Physionet database. For the MIT-BIH database, we used 47 individuals, each recording contains ECG data recorded for 15 s and in the SNR database, we used 18 individuals, the duration of each recording is 10 s. The analysis of the results obtained shows that the combination of all the features proposed makes it possible to improve the efficiency of our identification system to reach a performance rate equal to 100% for the two bases. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

New Dynamic Bayesian Network for Time-to-Event Prediction

New Dynamic Bayesian Network for Time-to-Event Prediction

引用

ACS/IEEE International Conference on Computer systems and Applications

作者： Walid Ben Abdallah Hasna Njah Salma Jamoussi National Engineering School of Gabes Gabes University Tunisia Multimedia InfoRmation systems and Advanced Computing Laboratory Sfax University Tunisia Higher institute of Computer sciences and multimedia of Gabes Gabes University Tunisia Higher institute of Computer sciences and multimedia of Sfax Sfax university Tunisia

ISBN: (数字)9798331518240

ISBN: (纸本)9798331518257

Time-to-event prediction is an important analytical approach in medical research and personalized medicine that aims to predict the timing of clinically relevant occurrences and find associated risk variables. In the context of chronic diseases such as multiple sclerosis (MS), precisely modelling time to disease progression, adverse events, or therapeutic responses can have a significant impact on patient management strategies and clinical results. This study investigate the use of Bayesian networks(BN), augmented with a temporal factor, for time-to-event prediction in predicting disease progression in MS patients. We suggest using dynamic Bayesian networks (DBNs) as a versatile temporal modeling framework to capture the complex dynamics and inter-dependencies found in time-to-event processes.

关键词： Multiple sclerosis Accuracy Precision medicine Probabilistic logic Bayes methods Timing Medical diagnostic imaging Context modeling

来源：评论

学校读者我要写书评

暂无评论

Swin Transformer-Based CSI Feedback for Massive MIMO 23

Swin Transformer-Based CSI Feedback for Massive MIMO

引用

23rd IEEE International Conference on Communication Technology, ICCT 2023

作者： Cheng, Jiaming Chen, Wei Xu, Jialong Guo, Yiran Li, Lun Ai, Bo Beijing Jiaotong University State Key Laboratory of Advanced Rail Autonomous Operation China School of Electronic and Information Engineering Beijing Jiaotong University Beijing China Frontiers Science Center for Smart High-speed Railway System China State Key Laboratory of Mobile Network and Mobile Multimedia Technology Shenzhen518055 China Zte Corporation Shenzhen518055 China Key Laboratory of Railway Industry of Broadband Mobile Information Communications China

ISBN: (纸本)9798350325959

For massive multiple-input multiple-output systems in the frequency division duplex (FDD) mode, accurate downlink channel state information (CSI) is required at the base station (BS). However, the increasing number of transmit antennas aggravates the feedback overhead of CSI. Recently, deep learning (DL) has shown considerable potential to reduce CSI feedback overhead. In this paper, we propose a Swin Transformer-based autoencoder network called SwinCFNet for the CSI feedback task. In particular, the proposed method can effectively capture the long-range dependence information of CSI. Moreover, we explore the impact of the number of Swin Transformer blocks and the dimension of feature channels on the performance of SwinCFNet. Experimental results show that SwinCFNet significantly outperforms other DL-based methods with comparable model sizes, especially for the outdoor scenario. © 2023 IEEE.

关键词： autoencoder CSI feedback deep learning Massive MIMO Swin Transformer

来源：评论

学校读者我要写书评

暂无评论

Semantic Heads Segmentation and Counting in Crowded Retail Environment with Convolutional Neural Networks Using Top View Depth Images

引用

SN Computer Science 2023年第1期4卷 61页

作者： Abed, Almustafa Akrout, Belhassen Amous, Ikram Department of Computer Science College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University Alkharj 11942 Saudi Arabia Multimedia Information Systems and Advanced Computing Laboratory (MIRACL) Sfax University Sfax 3021 Tunisia ENET’COM University of Sfax National School of Electronics and Telecommunications of Sfax Road Tunis City El Ons Sfax 3018 Tunisia

In recent years, researchers have developed several techniques to accurately count the number of people in a crowded retail environment for human behavior analysis, ranging from vision and feature based approaches to machine-learning and deep learning approaches. Due to the availability and affordability of recent advanced technologies such as depth sensors and high computing powers as well as the availability of big data, the need for building accurate models to detect and count people in crowded environments arises. Deep learning approaches has proven to be highly accurate especially when there is enough data to train the model and high computation powers. People detection and counting is a challenging problem. due to several issues such as occlusion, light variations, complex backgrounds to name a few. To cope with these issues, we utilize a top-view configuration depth data to train our model. We propose a convolutional encoder decoder architecture consisting of a resnet50 encoder trained on the ImageNet dataset as a transfer learning technique and we built the decoder part of the model as a novel contribution, for segmenting and counting customers heads in a crowded retail stores where there are more than 6 individuals per square meter without compromising people privacy because the camera does not record people’s faces. The objective of our method is to segment and count people using the publicly available TV-Head Dataset and People Counting DataSet (PCDS). The results demonstrate that our model is robust and can be used for real time people counting with accurate results. © 2022, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Computer vision Convolutional neural networks Intelligent retail environment People counting Top-view configuration

来源：评论

学校读者我要写书评

暂无评论

E-health Application In IoMT Environment Deployed in An Edge And Cloud computing Platforms

引用

Procedia Computer Science 2024年 246卷 1019-1028页

作者： Ahlem Ayari Hassen Hamdi Khlil Ahmad Alsulbi Business Computing Department Higher Institute of Management of Sousse Sousse 4037 Tunisia Miracl (Multimedia InfoRmation systems and Advanced Computing Laboratory) FSEGS University of Sfax Sfax 3000 Tunisia Computers Department College of Engineering and Computers in Al-Qunfodah Umm Al-Qura University Makka 24211 Saudi Arabia

Different countries may use E-health in Health systems that include all the institutions, organizations, and resources that are devoted to promote, sustain, or restore health. The basic goal of E-health projects is to enhance the delay of the service. Healthcare data now are being moved and collected from Internet of Medical Things (IoMT) environment. Different researches shows that recent E-health application is deployed in distributed computing and especially cloud computing is being used more frequently. Most of these applications are based on intelligent algorithm’s such as KNN, SVM and deep learning algorithms etc… Which require more height power computing and storage capacity, but cloud computing with this delicate algorithm and with the sensitive health domain has some tradeoffs in handling the large amount of data from different IoMT devices, so it effects the delay which can cause risk. We propose Edge computing to address the limitations of cloud. By transferring some of the computing to the network’s edge, edge computing can significantly increase processing efficiency. In order to accomplish our goal, we first deploy our health application based on IoMT environment in a cloud. Then, we run it in an edge, and we analyze the response times in each of these situations. The experimental study proves that the proposed approach reduces delay in response time compared to the use of clouds.

关键词： E-health Cloud computing Edge computing IoMT

来源：评论

学校读者我要写书评

暂无评论

Deep support vector machines for speech emotion recognition 19th

Deep support vector machines for speech emotion recognition

引用

19th International Conference on Intelligent systems Design and Applications, ISDA 2019

作者： Aouani, Hadhami Ben Ayed, Yassine National School of Engineers ENIS University of Sfax Sfax Tunisia Multimedia InfoRmation Systems and Advanced Computing Laboratory MIRACL University of Sfax Sfax Tunisia

ISBN: (纸本)9783030493417

Speech Emotions recognition has become the active research theme in speech processing and in applications based on human-machine interaction. In this work, our system is a two-stage approach, namely feature extraction and classification engine. Firstly, two sets of feature are investigated which are: the first one is extracting only 13 Mel-frequency Cepstral Coefficient (MFCC) from emotional speech samples and the second one is applying features fusions between the three features: zero crossing rate (ZCR), Teager Energy Operator (TEO), and Harmonic to Noise Rate (HNR) and MFCC features. Secondly, we use two types of classification techniques which are: the Support Vector Machines (SVM) and the k-Nearest Neighbor (k-NN) to show the performance between them. Besides that, we investigate the importance of the recent advances in machine learning including the deep kernel learning. A large set of experiments are conducted on Surrey Audio-Visual Expressed Emotion (SAVEE) dataset for seven emotions. The results of our experiments showed given good accuracy compared with the previous studies. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Graph Reasoning Model Based on Multiple Types of Nodes 7

A Graph Reasoning Model Based on Multiple Types of Nodes

引用

7th International Conference on Big Data and information Analytics, BigDIA 2021

作者： Liu, Yibing Huo, Lijun Zhou, Gang Information Engineering University State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China National University of Defense Technology Key Laboratory of Information System Engineering Changsha China

ISBN: (纸本)9781665424660

Multi-hop machine reading comprehension (MRC) depends on the model to answer a semantically related question based on the given supporting text. In this study, inspired by previous research about Graph Neural Network(GNN), we develop a new graph covering three kinds of nodes: Sentence, Entity, Candidate. A corresponding MRC method based on graph inference is proposed, called SEC reasoner. The advantage of SECr is that it adopts different granular information as graph nodes, which can execute a more comprehensive reasoning. Our proposed model first initialize the node representations by co-Attention, multi-head attention and self-Attention based on context embedding. SECr then employs GNN based information transfer algorithms to collect evidences from the node encoding, and calculates a score for choosing the answer. In experiments, we evaluate the model on two popular benchmark datasets-WikiHop and MedHop. SECr reachs accuracy rates of 71.6%, 63.1% respectively, which is a competitive result. In addition, a comprehensive analysis proves the effectiveness and interpretability of the SECr. © 2021 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

CrossViT Wide Residual Squeeze-and-Excitation Network for Alzheimer's disease classification with self attention ProGAN data augmentation

引用

International Journal of Hybrid Intelligent systems 2021年第3-4期17卷 163-177页

作者： Kadri, Rahma Bouaziz, Bassem Tmar, Mohamed Gargouri, Faiez Multimedia InfoRmation Systems and Advanced Computing Laboratory Miracl University of Sfax Tunisia Sfax Tunisia Faculty of Economics and Management of Sfax Fseg Sfax University of Sfax Tunisia Sfax Tunisia

Efficient and accurate early prediction of Alzheimer's disease (AD) based on the neuroimaging data has attracted interest from many researchers to prevent its progression. Deep learning networks have demonstrated an optimal ability to analyse large-scale multimodal neuroimaging for AD classification. The most widely used architecture of deep learning is the Convolution neural networks (CNN) that have shown great potential in AD detection. However CNN does not capture long range dependencies within the input image and does not ensure a good global feature extraction. Furthermore, increasing the receptive field of CNN by increasing the kernels sizes can cause a feature granularity loss. Another limitation is that CNN lacks a weighing mechanism of image features;the network doesn't focus on the relevant features within the image. Recently,vision transformer have shown an outstanding performance over the CNN and overcomes its main limitations. The vision transformer relies on the self-attention layers. The main drawbacks of this new technique is that it requires a huge amount of training data. In this paper, we combined the main strengths of these two architectures for AD classification. We proposed a new method based on the combination of the Cross ViT and Wide Residual Squeeze-and-Excitation Network. We acquired MRI data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and the Open Access Series of Imaging Studies (OASIS). We also proposed a new data augmentation based on the self attention progressive generative adversarial neural network to overcome the limitation of the data. Our proposed method achieved 99% classification accuracy and outperforms CNN models. © 2021 - IOS Press. All rights reserved.

关键词： AD classification CNN CrossViT self attention ProGAN wide residual squeeze-and-excitation network

来源：评论

学校读者我要写书评

暂无评论

High-Fidelity Editable Portrait Synthesis with 3D GAN Inversion

High-Fidelity Editable Portrait Synthesis with 3D GAN Invers...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Jindong Xie Jiachen Liu Yupei Lin Jinbao Wang Xianxu Hou Linlin Shen Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University School of Information Engineering Guangdong University of Technology Guangzhou China Guangdong Provincial Key Laboratory of Intelligent Information Processing School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The 3D generative adversarial network (GAN) inversion converts an image into 3D representation to attain high-fidelity reconstruction and facilitate realistic image manipulation within the 3D latent space. However, previous approaches face challenges regarding the trade-off between the reconstruction ability and editability. That is, reversing a real-world image to a low-dimensional latent code would inevitably lead to information loss, and achieving a near-perfect reconstruction using high-rate triplane representation often limits the ability to manipulate the image freely in the latent space. To address these issues, we propose a novel latent conditioning encoder-based framework with the alignment between the low-dimensional latent and high-dimensional triplane. A non-semantic guided editing strategy bridges the intrinsic relation between the latent condition and triplane generation, making it possible to edit the high-dimensional representation by latent manipulation. As a result, our method can achieve high-fidelity reconstruction and editing simultaneously by directly controlling the latent code. Experimental results demonstrate that our approach excels in reconstruction and editing quality compared to previous 3D inversion methods. Furthermore, our method can also edit even real faces with large poses and out-of-domain cases.

关键词： Bridges Three-dimensional displays Codes Signal processing Generative adversarial networks Vectors Acoustics Speech processing Image reconstruction Faces

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：