检索结果-内蒙古大学图书馆

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

作者： Guanghao Meng Tao Dai Bin Chen Naiqi Li Yong Jiang Shu-Tao Xia Tsinghua Shenzhen International Graduate School Tsinghua University Peng Cheng Laboratory Shenzhen China College of Computer Science and Software Engineering Shenzhen University Department of Computer Science and Technology Harbin Institute of Technology Shenzhen

Deep neural network (DNN) based scene text recognition (STR) methods usually require a large amount of annotated data for training, which is time-consuming and cost-expensive in practice. To address this issue, many data augmentation methods have been developed to train recognizers by improving the diversity of training samples. However, most existing methods neglect the difficulty inherent in samples, and easily suffer from the problem of over-diversity, i.e., the distribution of the augmented data significantly deviates from that of clean data. In this paper, we propose a novel difficulty-aware data augmentation framework for scene text recognition, which jointly considers the difficulty of samples and the strength of augmentations. Specifically, our framework first predicts the sample difficulty, followed by an adaptive data augmentation strategy. Furthermore, we build a more diverse set of augmentation methods for STR and integrate it into our augmentation framework. Extensive experiments on scene text recognition benchmarks show that our augmentation framework significantly improves the performance of recognizers.

关键词： Training Measurement Deep learning Text recognition Neural networks Speech recognition Signal processing

来源：评论

学校读者我要写书评

暂无评论

Anonymous Authentication Without Home Server in Mobile Roaming Networks

引用

Chinese Journal of Electronics 2023年第2期22卷 382-386页

作者： Chunlin Jiang Weijia Jia Ke Gu Ning Xu School of Information Science and Engineering Central South University Changsha China China Standard Software Co. Ltd Shanghai China Department of Computer Science City University of Hong Kong Kowloon Hong Kong

In this paper, we propose an anonymous authentication protocol based on group signature under Canetti-Krawczyk (CK) model for mobile roaming networks. The protocol involves only a mobile user and the user's visited server, without the involvement of the user's home server until the user's identity (ID) needs to be revealed. In order to reduce the computational burden on the mobile terminals, the protocol gives a method that minimizes expensive pairing operations. Then, its performance as well as efficiency is analyzed. It is shown that the proposed protocol greatly reduces the average authentication latency while security and anonymity are still preserved. Therefore, it can be applicable in practical applications.

关键词： Technological innovation Protocols Computational modeling Authentication Servers Security Research and development

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Approach to Identify Stroke based on Real-time Medical Data

A Comprehensive Approach to Identify Stroke based on Real-ti...

引用

Cognitive Robotics and Intelligent Systems (ICC - ROBINS), International Conference on

作者： M. Maragatharajan Shanmugapriya S M. B. Sudhan Deeptha R. Sankar Muthu Paramasivam School of Computing Science and Engineering VIT Bhopal University Kothrikalan Madhya Pradesh India Department of Computer Science and Engineering School of Computing Kalasalingam Academy of Research and Education Srivilliputhur Tamilnadu India Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai Tamilnadu Department of Information Technology SRM Institute of Science and Technology Ramapuram Chennai Tamilnadu India Distinguished Software Engineer Palo Alto Networks Inc Santa Clara California USA

ISBN: (数字)9798350372748

ISBN: (纸本)9798350372755

Strokes or cardiovascular disorders continue to be a major global health concern. Proactive intervention and timely detection greatly reduce the morbidity and death related to strokes. The goal of this research is to build a prediction model using machine learning techniques to assess a person’s risk of stroke based on a variety of sociodemographic and health characteristics. The dataset used in this study consists of a large collection of medical records. It contains important details including age, gender, BMI, smoking habits, heart disease, hypertension, and the type of residential property. Using this information, a Decision Tree Classifier is trained to predict the likelihood of strokes, enabling early detection and customized treatment plans. A Decision Tree Classifier with a predetermined maximum depth is used in the proposed methodology’s rigorous data preprocessing, which includes handling missing values, encoding categorical features, and developing models. Both the training and testing datasets are used to evaluate the model’s performance using evaluation measures including accuracy, precision, and recall. The model’s insights provide important characteristics that influence the prediction of stroke risk, assisting medical professionals in focused risk assessment and preventive intervention. The proposed method has the potential to improve healthcare practices by facilitating prompt interventions and personalized treatment for stroke risk individuals. The proposed model has resulted in 86.78% accuracy for this dataset by using the traditional machine learning algorithms. This work highlights the value of predictive modelling in the healthcare industry by demonstrating how it may improve early detection techniques and lessen the impact of strokes on public health.

关键词： Training Machine learning algorithms Machine learning Predictive models Stroke (medical condition) Real-time systems Risk management

来源：评论

学校读者我要写书评

暂无评论

Selecting and Evaluating Key MDS-UPDRS Activities Using Wearable Devices for Parkinson's Disease Self-Assessment

IEEE Journal of Selected Areas in Sensors

引用

IEEE Journal of Selected Areas in Sensors 2024年 1卷 177-189页

作者： Zhao, Yuting Wang, Xulong Peng, Xiyang Li, Ziheng Nan, Fengtao Zhou, Menghui Qi, Jun Yang, Yun Zhao, Zhong Xu, Lida Yang, Po Yunnan University National Pilot School of Software Kunming650106 China University of Sheffield Department of Computer Science SheffieldS10 2TN United Kingdom Northwest A&F University College of Information Engineering Xianyang712100 China Xi'an JiaoTong-Liverpool University Department of Computing Suzhou215000 China Yunnan First People's Hospital Yunnan650021 China Old Dominion University NorfolkVA23529 United States

Parkinson's disease (PD) is a complex neurodegenerative disease in the elderly. This disease has no cure, but assessing these motor symptoms will help slow down that progression. Inertial sensing-based wearable devices, such as mobile phones and smartwatches have been widely employed to analyze the condition of PD patients. However, most studies purely focused on a single activity or symptom, which may ignore the correlation between activities and complementary characteristics. In this article, a novel technical pipeline is proposed for fine-grained classification of PD severity grades, which identify the most representative activities. We also propose a multiactivities combination scheme based on MDS-UPDRS. Utilizing this scheme, symptom-related and complementary activities are captured. We collected 85 PD subjects of different severity grades using a single wrist sensor. Our best results demonstrate F1 scores of 95.75% for PD diagnosis and the fine-grained classification accuracy of PD disease grade is 82.41% when combing four activities which improved by 11.02% over a single activity. The experiments and theoretical analyses can serve as a useful foundation for future investigations into the effect of proposed solutions for PD diagnosis in uncontrolled environment setup, ultimately leading to self-PD assessment in the home environment. © 2024 IEEE.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approach for COVID-19 Identification 18

Deep Learning Approach for COVID-19 Identification

引用

18th International computer Conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2021

作者： Ul Haq, Amin Li, Jian Ping Khan, Riaz Ullah Mawuli, Cobbinah Bernard Agbley, Bless Lord Y. Raj, Mordecai F. Zhou, Wang Khan, Jalaluddin Haq, Abdul Saboor, Abdus Habib, Faiza Khan, Zafar University of Electronic Science and Tech. of China School of Computer Science and Engineering Chengdu China 313000 China Xihua University School of Computer and Software Engineering Chengdu Sichuan China University of Electronic Science and Tech. of China School of Computer Science and Engineering Chengdu China Gomal University Department of Computer Science D.I. Khan29220 Pakistan Hazzra University Department of Computer Science and IT Manshera KPK 21120 Pakistan Northern University Faculty of Engineering and I.T Nowshera Pakistan

ISBN: (纸本)9781665413640

Accurate diagnostic system is significantly important for timely COVID-19 identification. Diagnosing COVID-19 from chest x-ray images employing the CNN model is recommended for accurate recognition of COVID-19. The existing diagnosis techniques of COVID-19 still lack high accuracy. To handle this problem in this work, we have proposed accurate detection method for COVID-19. In the proposed method, a CNN is incorporated for the diagnosis of COVID-19 using chest x-ray images data. The experimental results illustrate that our technique is good for COVID-19 accurate diagnosis and can be easily implemented in health care systems. © 2021 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Amplifying the Music Listening Experience through Song Comments on Music Streaming Platforms

arXiv

引用

arXiv 2023年

作者： Chen, Longfei Liu, Qianyu Zhang, Chenyang Huang, Yangkun Peng, Zhenhui Zeng, Haipeng Sun, Zhida Ma, Xiaojuan Li, Quan The School of Information Science and Technology ShanghaiTech University Shanghai Engineering Research Center of Intelligent Vision and Imaging China The Department of Computer Science University of Illinois Urbana-Champaign United States Tandon School of Engineering New York University United States The School of Artificial Intelligence Sun Yat-Sen University China The School of Intelligent Systems Engineering Sun Yat-Sen University China The College of Computer Science and Software Engineering Shenzhen University China The Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong

Music streaming services are increasingly popular among younger generations who seek social experiences through personal expression and sharing of subjective feelings in comments. However, such emotional aspects are often ignored by current platforms, which affects the listeners' ability to find music that triggers specific personal feelings. To address this gap, this study proposes a novel approach that leverages deep learning methods to capture contextual keywords, sentiments, and induced mechanisms from song comments. The study augments a current music app with two features, including the presentation of tags that best represent song comments and a novel map metaphor that reorganizes song comments based on chronological order, content, and sentiment. The effectiveness of the proposed approach is validated through a usage scenario and a user study that demonstrate its capability to improve the user experience of exploring songs and browsing comments of interest. This study contributes to the advancement of music streaming services by providing a more personalized and emotionally rich music experience for younger generations. © 2023, CC BY.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

DevFlair: A Framework to Automate the Pre-screening Process of software engineering Job Candidates 4

DevFlair: A Framework to Automate the Pre-screening Process ...

引用

4th International Conference on Advancements in Computing, ICAC 2022

作者： Jayasekara, R.T.R. Kariyawasam, K.G.S.S.K. Jayasinghe, S.L. Kudarachchi, K.A.N.D. Rajapaksha, Dilini Thelijjagoda, Samantha Department of Computer Science and Software Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka School of Computing Technologies Royal Melbourne Institute of Technology Melbourne Australia SLIIT Business School Sri Lanka Institute of Information Technology Malabe Sri Lanka

ISBN: (纸本)9798350398090

The HR department of a technology company receives hundreds of job applications for each software engineering related vacancy. Evaluating a candidate by looking at the curriculum vitae may appear to be easy during the pre-screening process. However, an automated pre-screening process using Natural Language Processing and Machine Learning methodologies would help the recruiter to obtain a more accurate and deeper understanding of the candidate. In this paper we propose "DevFlair", a framework to automate pre-screening software engineering job candidates. DevFlair uses data from social media, GitHub, and open-ended questionnaires to predict the Big-Five personality traits, analyze technical skill expertise, and analyze the experience in using industry-related online platforms. After analysis, the candidates are ranked according to their personality and technical skill levels. We conduct the personality prediction experiments using a social media posts dataset annotated with gold-standard Big-Five personality labels. We train FastText classification models and compare their accuracy against other state of the art classification models. The comparisons conclude that the FastText classification models substantially outperform the state of the art classification models when predicting Openness, Conscientiousness, and Agreeableness personality traits. © 2022 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

xLSTM-UNet can be an Effective 2D & 3D Medical Image Segmentation Backbone with Vision-LSTM (ViL) better than its Mamba Counterpart

arXiv

引用

arXiv 2024年

作者： Chen, Tianrun Ding, Chaotao Zhu, Lanyun Xu, Tao Ji, Deyi Wang, Yan Zang, Ying Li, Zejian College of Computer Science and Technology Zhejiang University China Tech. Co. LTD China School of Information Engineering Huzhou University China Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore School of Software Technology Zhejiang University China School of Information Science and Technology University of Science and Technology of China China School of Instrumentation and Optoelectronic Engineering State Key Laboratory of Software Development Environment Beihang University China

Convolutional Neural Networks (CNNs) and Vision Transformers (ViT) have been pivotal in biomedical image segmentation. Yet, their ability to manage long-range dependencies remains constrained by inherent locality and computational overhead. To overcome these challenges, in this technical report, we first propose xLSTM-UNet, a UNet structured deep learning neural network that leverages Vision-LSTM (xLSTM) as its backbone for medical image segmentation. xLSTM has recently been proposed as the successor of Long Short-Term Memory (LSTM) networks and has demonstrated superior performance compared to Transformers and State Space Models (SSMs) like Mamba in Neural Language Processing (NLP) and image classification (as demonstrated in Vision-LSTM, or ViL implementation). Here, xLSTM-UNet we designed to extend the success in the biomedical image segmentation domain. By integrating the local feature extraction strengths of convolutional layers with the long-range dependency-capturing abilities of xLSTM, xLSTM-UNet offers a robust solution for comprehensive image analysis. We validate the efficacy of xLSTM-UNet through experiments. Our findings demonstrate that xLSTM-UNet consistently surpasses the performance of leading CNN-based, Transformer-based, and Mamba-based segmentation networks in multiple datasets in biomedical segmentation including organs in abdomen MRI, instruments in endoscopic images, and cells in microscopic images. With comprehensive experiments performed, this technical report highlights the potential of xLSTM-based architectures in advancing biomedical image analysis in both 2D and 3D. The code, models, and datasets are publicly available at http://***/xLSTM-Unet/. © 2024, CC BY-NC-ND.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Towards a global machine learning model to fill gaps in flood frequency: Random Forest to estimate MNDWI in Bangladesh

Towards a global machine learning model to fill gaps in floo...

引用

Machine Intelligence for GeoAnalytics and Remote Sensing (MIGARS), International Conference on

作者： James Houghton Carolynne Hultquist James Atlas Andrew Zimmer Computer Science and Software Engineering University of Canterbury Christchurch NZ School of Earth and Environment University of Canterbury Christchurch NZ Department of Earth Sciences Montana State University Bozeman MT USA

ISBN: (数字)9798350389678

ISBN: (纸本)9798350389685

An understanding of historical trends of flooding is essential to capture current risk as more people are exposed to flood hazards than ever before. Flood modeling relies on accurate and frequent remote sensing inputs to produce reliable flood risk results. However, remote sensing datasets are limited by temporal resolution which, in the case of Landsat, leaves 87% of days without observation. This study aims to address these gaps in observation using a Random Forest model to predict the Modified Normalized Difference Water Index (MNDWI) in Landsat images by fusing gridded precipitation and elevation data. The trained model is then used to estimate MNDWI for when there are no Landsat observations. The model was evaluated on a 50 by 50 pixel test patch achieving a residual squared error between the true average MNDWI and the estimated average MNDWI of 0.48.

关键词： Time-frequency analysis Precipitation Predictive models Market research Data models Floods Reliability

来源：评论

学校读者我要写书评

暂无评论

Positive Sample Augmentation with Graph Mixup for DDI Prediction

Positive Sample Augmentation with Graph Mixup for DDI Predic...

引用

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Hailong Yu Xinyu Ma Xu Chu Yasha Wang Rengyu Wu Qiang Zhou School of Computer Science Peking University Beijing China Department of Computer Science and Technology Tsinghua University Beijing China National Engineering Research Center for Software Engineering Peking University Beijing China Shenzhen Center for Prehospital Care Shenzhen China

Unexpected drug-drug interactions (DDIs) may occur when drugs are taken at the same time. Harmful DDIs can reduce drug efficacy and even increase unintended toxicity, putting patients treated with different drugs at risk. Previous works on DDI prediction mainly rely on hand-engineered domain knowledge, which is laborious to obtain and cannot handle the problem of sparse positive samples in DDI prediction. Even though some works attempt to handle data sparsity from the perspective of data distribution to improve the generalization ability of the model, they are limited to negative samples distribution. To address these limitations, we propose a novel method, Graph Mixup for Positive Sample Augmentation (GMPSA), to effectively combine positive drug molecule graphs and extend the training distribution to alleviate the problem of sparse positive samples. To model the graph signals and graph structures jointly, we map source graphs to the fused gromov-wasserstein metric space, then minimizes the weighted sum of transportation distances between the distributions of the source graphs and the objective graph in this metric space. By doing so, interpolated positive samples improve the the generalization error of the model. Experiments results on a real-word dataset show that our method effectively improve the perfomermance in DDI prediction on a state-of-the-art architecture. Further studies also verify the robustness and generalizability of GMPSA under different GNN backbones and parameter settings.

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：