检索结果-内蒙古大学图书馆

2021 International Conference of Technology, Science and Administration, ICTSA 2021

作者： Alawi, Abdulfattah E. Ba Al-Basser, Amer Sallam, Amer Al-Sabaeei, Amr Al-Khateeb, Hesham Taiz University Software Engineering Dept. Taiz Yemen Taiz University Mechatronics and Robotics Engineering Dept. Taiz Yemen Taiz University Computer Networks and Distributed System Dept. Taiz Yemen

ISBN: (纸本)9781665428620

Tuberculosis disease has a big concern and it is spreading quickly across the world. The secret for managing the condition is an accurate diagnosis. Acid quick staining, conventional approaches such as tuberculin skin test (TST), yield findings are unreliable or require more time to detect. This paper presents an automated solution that uses chest radiographs to diagnose tuberculosis. Chest radiographic images are used for tuberculosis diagnosis. Tuberculosis in chest radiographs is difficult to investigate under the current system of cavity identification, ribs, and diaphragm removal. By using a CNN-based model, the lung area is separated to resolve the problems. The proposed technique can classify chest x-ray (CXR) images as Tuberculosis (TB) infected or not. We analyzed 3500 CXR cases and 3500 normal cases with exposure to tuberculosis. Then, we built and trained our own CNN and found that the features map or heat-map generated from this network performed a slightly better job. The implementation was done in Tensorflow and Keras library. An accuracy of 98.71%, a sensitivity of 98.86%, and a specificity of 98.57% were achieved. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Cloud-Based Framework for Data Exchange to Enhance Global Healthcare

引用

Procedia computer Science 2024年 241卷 570-575页

作者： Ammerha Naz Muhammad Ali Sehrish Munawar Cheema Ivan Miguel Pires Dept. of Computer Science University of Sialkot Sialkot Punjab Dept. of Software Engineering Superior University Lahore Pakistan Dept. of Computer Science University of Management and Technology Lahore Pakistan Instituto de Telecomunicações Escola Superior de Tecnologia e Gestão de Águeda Universidade de Aveiro Águeda Portugal

Healthcare is a global pillar, with a surge in the adoption of information technology, particularly in hospital information systems (HIS). However, global protocols are needed to meet the growing demand for data interchange, practical implementations for sharing healthcare data among facilities, and a pressing need for processing and storage infrastructure to handle the escalating volume of healthcare data. This study proposes a solution for efficient data transmission using electronic health records (EHR) and Platform-as-a-Service (PaaS) to leverage cloud computing resources. This framework's architecture boasts robustness and adaptability, providing all registered software programs access to data interchange services. Through a comprehensive examination of the framework's structure, the essay also explores the most effective data-sharing methods. It identifies the healthcare system's optimal EHR data model. According to multiple healthcare experts, the operational building of this framework is expected to catalyze the growth of healthcare institutions both nationally and within specific industries.

关键词： Healthcare Hospital information systems (HIS) Electronic health records (EHRs) Cloud computing. Data transmission

来源：评论

学校读者我要写书评

暂无评论

XAI for Understanding the Success in Curbing COVID-19

XAI for Understanding the Success in Curbing COVID-19

引用

Intelligent Systems and computer Vision (ISCV)

作者： Salah Bouktif Nimmi Kunnath Ali Ouni Dept. of Computer Science and Software Engineering CIT United Arab Emirates University Al Ain UAE École de Technologie Supérieure University of Quebec Montreal Canada

ISBN: (数字)9798350350180

ISBN: (纸本)9798350350197

The Covid-19 pandemic has prompted governments worldwide to implement various non-pharmaceutical interventions (NPIs) in an effort to curb the pandemic to attenuate the harmness of the pandemic. However, there is a debate about how to assess the effectiveness of these interventions. A set of indicators has been used to monitor the outbreak such as case counts, infection rates, death rate, hospitalization. In this study, we contribute to the debate by firstly proposing a definition of the success in managing the pandemic in terms of mortality rate, socio-demographic and epidemiological factors. Secondly, we propose a modeling framework based on (1) analysing the time series pandemic data and (2) employing eXplainable Artificial Intelligence (XAI) to provide interpretability of the successfulness of countries in responding to the pandemic. By using a rich dataset collected by Oxford COVID-19 Government Response Tracker (OxCGRT), we built a success model based on Random Forest Regressor for time series analysis and we identified the major factors/practices/measures/protocols. Our findings indicate a significant relationship between policy compliance levels and death counts, highlighting the importance of considering mortality outcomes in evaluating the efficacy of interventions. Additionally, we discovered that socio-demographic and epidemiological factors such as elderly populations aged (65+), prevalent cardiovascular disease, high diabetes prevalence, increased smoking rates, and reduced life expectancy based on the person correlation coefficient are key determinants of success in managing the pandemic.

关键词： COVID-19 Analytical models Pandemics Explainable AI Time series analysis Government Sociology

来源：评论

学校读者我要写书评

暂无评论

Analysis and Research on Students' Learning Behavior Based on Lag Sequence Analysis 4

Analysis and Research on Students' Learning Behavior Based o...

引用

4th International Conference on computer Information Science and Artificial Intelligence, CISAI 2021

作者： Han, Jiazheng Wei, Zhengang Ocean University of China Dept. of Computer Application Technology Qingdao China Ocean University of China Dept. of Software Engineering Qingdao China

ISBN: (纸本)9781665406925

with the effective practical application of data mining technology in other fields, many researchers have used data mining technology to analyze the learning process data in the field of education and teaching, and explore the hidden and potentially valuable information and knowledge. This paper mainly mines the association in students' learning behavior data through lag sequence analysis algorithm (LSA), and shows learners' learning trajectory, willingness and cognitive process in the learning process. Help to grasp the potential behavior mode of students' learning and effectively guide the development and implementation of follow-up teaching work. © 2021 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

引用

14th International Conference on Education Technology and computers, ICETC 2022

作者： Segarra-Faggioni, Veronica Ratté, Sylvie De Jong, Frank Dept. Software and IT Engineering École de Technologie Supérieure Montreal Canada Dept. Computer Science and Electronics Universidad Tecnica Particular de Loja Loja Ecuador Dept. Learning and Innovation Aeres Wageningen Applied University Wageningen Netherlands

ISBN: (纸本)9781450397766

Knowledge Building as a pedagogy supports collaborative work between students to improve ideas. The result of knowledge-building discourse in student communities is the development of academic artifacts. Student reports are academic artifacts that can result from a knowledge-building process during their learning. However, the automatic analysis of student reports is quite challenging due to the documents' length and written language. Given this context, our goal is to analyze the semantic similarity between student reports and curriculum literature using the information coverage measure based on the Skip-gram word2vec model. Word2vec is a well-known set of techniques that provides a way to create a representation of words to predict the nearby words between every word and its context to capture the internal semantic and syntactic information. In this work, through the experimental comparison between the vocabulary list, the best similarity value is 0.90 using word2vec. The results show that each student report was aligned with each document in the curriculum literature using the information coverage measure based on word2vec. © 2022 ACM.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Breast Cancer: A Machine Learning Approach 3

Performance Analysis of Breast Cancer: A Machine Learning Ap...

引用

3rd International Conference on Inventive Research in Computing Applications, ICIRCA 2021

作者： Khatun, Tania Utsho, Md. Mahfuzur Rahman Islam, Md. Ashiqul Zohura, Mst. Fatematuz Hossen, Md. Sagar Rimi, Robaiya Akter Anni, Sabiha Jannat Daffodil International University Dept. of Computer Science and Engineering Dhaka Bangladesh Daffodil International University Dept. of Software Engineering Dhaka Bangladesh Shahabuddin Medical College Gulshan-2 Dhaka Bangladesh

ISBN: (纸本)9780738146270

Nowadays, breast cancer is the most emerging diseaseamong women both in developed as well as developing countries. Due to increased life prospects, increased urbanization, and therelinquishment of western societies, the rareness of breast cancer is supersizing in the developing world. Even it became a second popular cause of cancer that has already been announced. It's very hard to identify the early symptom of this type of cancer for reducing numerous death. Different methods of machine learning and data mining techniques are using for medical diagnosis. In this study, four machine-learning algorithms are applying to analyze breast cancer in the inflammation stage and dig up the most cabbalistic and non-cabbalistic risk factors. To analyze breast cancer data from the Coimbra dataset from the UCI machine learning repository to create accurate prediction models for breast cancer. For getting better performance and to get higher accuracy Naïve Bayes (NB), Random Forest (RF), Multilayer Perceptron (MLP), Simple Logistic Regression (SLR) are using to find out some higher accuracy sequentially 70%, 68%, 85%, and 75%. Among all the above algorithms a better accuracy was achieved using Multi-layer Perceptron. Linear Regression (LiR) models are applying to dig up the most cabbalistic and non-cabbalistic risk factors of breast cancer. These results will help the doctor to detect breast cancer easily in the early stage and take the necessary steps. © 2021 IEEE.

关键词： Developing countries

来源：评论

学校读者我要写书评

暂无评论

An Efficient GPU-based Implementation for Noise Robust Sound Source Localization

arXiv

引用

arXiv 2025年

作者： Lin, Zirui Takigahira, Masayuki Terakado, Naoya Gulzar, Haris Busto, Monikka Roslianna Eda, Takeharu Itoyama, Katsutoshi Nakadai, Kazuhiro Amano, Hideharu Dept. of Systems and Control Engineering School of Engineering Tokyo Institute of Technology Tokyo Japan Honda Research Institute Japan Co. Ltd. Saitama Japan NTT Software Innovation Center Tokyo Japan Dept. of Information and Computer Science Keio University Kanagawa Japan

Robot audition, encompassing Sound Source Localization (SSL), Sound Source Separation (SSS), and Automatic Speech Recognition (ASR), enables robots and smart devices to acquire auditory capabilities similar to human hearing. Despite their wide applicability, processing multi-channel audio signals from microphone arrays in SSL involves computationally intensive matrix operations, which can hinder efficient deployment on Central Processing Units (CPUs), particularly in embedded systems with limited CPU resources. This paper introduces a GPU-based implementation of SSL for robot audition, utilizing the Generalized Singular Value Decomposition-based Multiple Signal Classification (GSVD-MUSIC), a noise-robust algorithm, within the HARK platform, an open-source software suite. For a 60-channel microphone array, the proposed implementation achieves significant performance improvements. On the Jetson AGX Orin, an embedded device powered by an NVIDIA GPU and ARM®Cortex™-A78AE v8.2 64-bit CPUs, we observe speedups of 4645.1× for GSVD calculations and 8.8× for the SSL module, while speedups of 2223.4× for GSVD calculation and 8.95× for the entire SSL module on a server configured with an NVIDIA A100 GPU and AMD EPYC™ 7352 CPUs, making real-time processing feasible for large-scale microphone arrays and providing ample capacity for real-time processing of potential subsequent machine learning or deep learning tasks. © 2025, CC BY-NC-ND.

关键词： Acoustic generators

来源：评论

学校读者我要写书评

暂无评论

Transformer-Based Human Action Recognition with Dynamic Feature Selection

Transformer-Based Human Action Recognition with Dynamic Feat...

引用

Canadian Conference on computer and Robot Vision, CRV

作者： Soufiane Lamghari Guillaume-Alexandre Bilodeau Nicolas Saunier Dept. of Computer and Software Engineering LITIV Polytechnique Montreal Montreal Canada Dept. of Civil Geological and Mining Eng. Polytechnique Montreal Montreal Canada

Human action recognition in videos is an important task of computer vision that aims to automatically recognize and classify human actions in video sequences. However, accurately recognizing human actions can be challenging due to the complexity and variability of human motion and appearance. In this paper, we propose ActiViT, a novel approach for human action recognition in videos based on a Transformer architecture. Unlike existing methods that rely on convolutional or recurrent layers, our model is entirely based on the Transformer encoder, enabling us to leverage valuable information in action image patches features. We demonstrate that by dynamically selecting key patches guided by specific human poses, our model learns informative features useful for distinguishing between different actions. Our experimental results on real-world datasets convincingly demonstrate the effectiveness of our model and the importance of selecting discriminative key poses for action recognition.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RNN-based Model for an Optimal COVID-19 Cases Detection using Clinical Reports

RNN-based Model for an Optimal COVID-19 Cases Detection usin...

引用

International Conference on Optimization and Applications (ICOA)

作者： Akib Khanday Salah Bouktif Ali Ouni dept. Computer Science and Software Engineering CIT UAE University Al Ain UAE ETS Montreal University of Quebec Montreal QC Canada

The global impact of COVID-19 has been significant due to its rapid spread and high transmission rate. A large number of individuals have been exposed to this dangerous virus, emphasizing the importance of early detection to potentially save numerous lives. This research paper introduces an enhanced method for COVID-19 detection, utilizing a Recurrent Neural Network (RNN) and leveraging early clinical reports. Specifically, a Long Short Term Memory (LSTM) model is trained using data obtained from the metadata of the available dataset published by the World Health organisation, specifically focusing on extracting clinical reports and labels. Several pre-processing techniques and word embedding are applied to train an LSTM-based classifier that accurately identifies positive COVID-19 cases. The implementation of this proposed approach yielded superior results compared to traditional machine learning algorithms. The model achieved a testing accuracy of 87%, and future works include expanding the dataset to enhance the efficiency of the model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EvoSL: A Large Open-Source Corpus of Changes in Simulink Models & Projects

EvoSL: A Large Open-Source Corpus of Changes in Simulink Mod...

引用

ACM/IEEE International Conference on Model Driven engineering Languages and Systems (MODELS)

作者： Sohil Lal Shrestha Alexander Boll Shafiul Azam Chowdhury Timo Kehrer Christoph Csallner Computer Science & Eng. Dept. University of Texas at Arlington Arlington TX USA Software Engineering Group University of Bern Bern Switzerland

Having readily available corpora is crucial for performing replication, reproduction, extension, and verification studies of existing research tools and techniques. MAT-LAB/Simulink is a de-facto standard tool in several safety-critical industries for system modeling and analysis, compiling models to code, and deploying code to embedded hardware. There is no commonly used corpus for large-scale model change studies because there is no readily available corpus. EvoSL is the first large corpus of Simulink projects that includes model and project changes and allows redistribution. EvoSL is available under a permissive open-source license and contains its collection and analysis tools. Using a subset of EvoSL, we replicated a case study of model changes on a single closed-source industrial project.

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：