检索结果-内蒙古大学图书馆

International conference of Electronics, Communication and Aerospace technology (ICECA)

作者： Deepa S Praveenkumar G D R Suguna Vivek Duraivelu C Jamunadevi S G Sundhar Department of Computer Technology-PG Kongu Engineering College Perundurai Erode Tamilnadu Department of computer science Vet institute of Arts and Science (Co-Education) College Erode Tamilnadu Department of Computer science and Engineering Bannari Amman Institute of Technology Sathyamangalam Department of Computer Science and Engineering B V Raju Institute of Technology Narsapur Telangana Department of Computer Technology PG Kongu Engineering College Perundurai Erode Tamilnadu Final M.Sc(Software Systems) Kongu Engineering College Perundurai Erode Tamilnadu

COVID-19, caused by the new coronavirus SARS-Co V-2, has turned into a worldwide health emergency, needing speedy and precise diagnostic techniques. This abstract provides a thorough evaluation of research works focusing on COVID-19 identification using DenseNet, a cutting-edge convolutional neural network architecture. DenseNet is notable for its innovative design, which fosters feature reuse while relieving the vanishing gradient problem and enhancing network information flow. Researchers have created novel ways for COVID-19 identification using medical imaging, such as chest X-rays and CT scans, by harnessing the capabilities of DenseNet. The analyzed studies demonstrate DenseNet's efficiency in recognizing COVID-19-specific patterns and distinguishing them from other lung diseases. These investigations have shown remarkable accuracy, sensitivity, and precision, exceeding established machine learning approaches and even professional radiologists. This research study also highlights the difficulties and constraints experienced while using DenseNet to identify COVID-19. Issues such as dataset quantity, class imbalance, and model decision-making process interpretability are addressed. Furthermore, future research paths and prospective enhancements, such as multi-modal data integration and the development of explainable AI systems, are investigated. The experimental results indicate that the proposed approach achieves high accuracy, sensitivity, and precision in the identification of COVID - 19. The proposed methodology achieved an accuracy of 89.74%, sensitivity of 87.25 % , and precision of 79.56%, which outperforms the existing state-of-the-art methods. The proposed approach is robust and can effectively differentiate between COVID-19 positive and negative cases, which is essential for early detection and prompt treatment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive watermark generation mechanism based on time series prediction for stream processing

引用

Frontiers of computer Science 2021年第6期15卷 59-73页

作者： Yang SONG Yunchun LI Hailong YANG Jun XU Zerong LUAN Wei LI Sino-German Joint Software Institute Beihang UniversityBeijing 100191China School of Computer Science and Engineering Beihang UniversityBeijing 100191China Science and Technology on Space System Simulation Laboratory Beijing Simulation Center Beijing 100854China College of Life Sciences and Bioengineering Beijing University of TechnologyBeijing 100083China

The data stream processing framework processes the stream data based on event-time to ensure that the request can be responded to in *** reality,streaming data usually arrives out-of-order due to factors such as network *** data stream processing framework commonly adopts the watermark mechanism to address the data *** is a special kind of data inserted into the data stream with a timestamp,which helps the framework to decide whether the data received is late and thus be *** watermark generation strategies are periodic;they cannot dynamically adjust the watermark distribution to balance the responsiveness and *** paper proposes an adaptive watermark generation mechanism based on the time series prediction model to address the above *** mechanism dynamically adjusts the frequency and timing of watermark distribution using the disordered data ratio and other lateness properties of the data stream to improve the system responsiveness while ensuring acceptable result *** implement the proposed mechanism on top of Flink and evaluate it with realworld *** experiment results show that our mechanism is superior to the existing watermark distribution strategies in terms of both system responsiveness and result accuracy.

关键词： data stream processing watermark time series based prediction dynamic adjustment

来源：评论

学校读者我要写书评

暂无评论

Career Aura-Smart Resume and Employment Recommender 3

Career Aura-Smart Resume and Employment Recommender

引用

3rd International Conference on Advancements in Computing, ICAC 2021

作者： Dissanayake, Kavindi Mendis, Senidu Subasinghe, Randula Geethanjana, Dineth Lunugalage, Dilani Kasthurirathna, Dharshana Sri Lanka Institute of Information Technology Computer Systems Engineering Department Malabe Sri Lanka Sri Lanka Institute of Information Technology Information Technology Department Malabe Sri Lanka Sri Lanka Institute of Information Technology Computer Science and Software Engineering Department Malabe Sri Lanka

ISBN: (纸本)9781665408622

Recruitment and Job seeking are two major factors that are directly proportional to each other. Due to the competitive nature of the present world, the process of acquiring the best resource effectively and efficiently has become a challenging aspect for the companies. As a result, modern job portals have become increasingly popular to address the challenges identified in the early recruitment and job search process. The purpose of this research is to introduce an optimal solution to address the ineffective areas identified in the job and recruitment domain which can further enhance the recruitment and job seeking decisions by utilizing deep learning and sentiment analytic approach along with descriptive analysis. The proposed system recommends the relevant job opportunities by omitting the irrelevant job advertisements for job hunters who are interested in the IT job domain while they input their resume to the system and additionally, they can improve their career decisions by adhering to the prediction schemes. Moreover, the system facilitates recruiters to headhunt top talents efficiently once they input job requirements to the system and candidate suggestions are not only made depending on their resume information but also analyzing their LinkedIn endorsements. © 2021 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Motorbike Driving Activity Recognition Using Smartphone Motion Sensors

Motorbike Driving Activity Recognition Using Smartphone Moti...

引用

IEEE International Conference on Multi Topic

作者： Aasim Raheel Aamir Arsalan Sadam Hussain Noorani Sheharyar Khan Muhammad Ehatisham-Ul-Haq Zohaib Ali Department of Computer Engineering University of Engineering & Technology Taxila Pakistan Department of Software Engineering Fatima Jinnah Women University Rawalpindi Pakistan Department of Creative Technologies Air University Islamabad Pakistan Department of Computer Science Bahria University Islamabad Pakistan

Motorbike driving activity recognition plays a crucial role in various domains, including rider safety, vehicle diagnostics, and driver behavior analysis. Traditional methods for activity recognition often rely on dedicated sensors or on-board systems, which can be expensive, cumbersome, or limited in terms of availability. In recent years, the widespread use of smartphones with built-in motion sensors has opened up new possibilities for activity recognition in a more cost-effective and accessible manner. This paper presents a novel approach for motorbike driving activity recognition using smartphone motion sensors. Motorcyclist are inquired to take after a predefined way for recording accelerometer and gyroscope data. Twelve factual features are extricated to classify four driving events i.e., right turn, left turn, U-turn, and a straight path. Four machine learning classifiers i.e., Bayes Net, K-nearest neighbor, support vector machine, and random forest is utilized to classify motorbike driving events. The findings indicate that fusing of a gyroscope and accelerometer can significantly improve the detection of bike driving occurrences, achieving a noteworthy precision rate of 92.13%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Diagnosing Spinal Abnormalities Using Machine Learning: A Data-Driven Approach

Diagnosing Spinal Abnormalities Using Machine Learning: A Da...

引用

Artificial Intelligence (ICAI), International Conference on

作者： Zia Ul Islam Nasir Khalil Khan Momna Asghar School of Interdeciplanary Engineering & Sciences(SINES) National University of sciences & Technology (NUST) Isamabad Pakistan Department of Computer Software Engineering & Computer Science Pak-Austria Institute of Applied Science & Technology Haripur Pakistan Department of Electrical Engineering University of Azad Jammu & Kashmir Muzaffarabad A.K

Low back pain is a predominant condition which can affects people from different diaspora. The goal of this work is to use machine learning approach to forecast spinal abnormalities. Extratreesclassifier is utilized as a data preprocessing stage to choose the dataset's most prominent features. On a dataset of 310 samples, spinal anomalies are diagnosed using machine learning algorithms like the Support Vector Machine (SVM) and the multilayer perceptron (MLP). The purpose of this study is to determine the most crucial factors that produce backbone abnormalities and to predict them using supervised machine learning techniques. The classification of normal and abnormal spinal patients is investigated in terms of various aspects, including testing and training accuracy, precision, and recall. The observed accuracies for SVM and MLP with 80% training data are 92% and 90%, respectively. The result shows that these models can achieve high accuracy in predicting spinal abnormalities, with the SVM model performing the better. The result suggest that this approach has the potential to significantly improve the efficiency and accuracy of spinal abnormality diagnosis, leading to better patient outcomes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A software Execution Data Component Identification Algorithm Based on Spectral Clustering

A Software Execution Data Component Identification Algorithm...

引用

International Conference on Dependable Systems and Their Applications (DSA)

作者： Yahui Tang Mengqi Rao Qingjie Wei Feng Chen Xin Liu School of Software Engineering Chongqing University of Posts and Telecommunications ChongQing China College of Computer Science and Technology Chongqing University of Posts and Telecommunications ChongQing China

In order to understand the architecture of software system and facilitate the future maintenance of the software, we can reconstruct the software system as a component-based software system. To obtain the component information of the software, it is necessary to identify components based on the information contained in the software execution data. This paper presents a software Execution data component identification algorithm based on Spectral Clustering (SESC). The input of the algorithm is the software execution event log, and the output is an evaluation report on the quality of the identified components, yielding the log of software execution events with component information. By using four software execution event logs, we compare the proposed SESC with five component identification algorithms based on the community detection algorithm. SESC takes the number of calls between classes into consideration, so it can identify components more accurately, and has certain advantages in time performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Vehicle Re-Identication Model Based on Optimized DenseNet121 with Joint Loss

引用

computers, Materials & Continua 2021年第6期67卷 3933-3948页

作者： Xiaorui Zhang Xuan Chen Wei Sun Xiaozheng He Jiangsu Engineering Center of Network Monitoring Engineering Research Center of Digital ForensicsMinistry of EducationSchool of Computer and SoftwareNanjing University of Information Science&TechnologyNanjing210044China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Nanjing University of Information Science&TechnologyNanjing210044China Department of Civil and Environmental Engineering Rensselaer Polytechnic InstituteTroyNY12180USA

With the increasing application of surveillance cameras,vehicle re-identication(Re-ID)has attracted more attention in the eld of public *** Re-ID meets challenge attributable to the large intra-class differences caused by different views of vehicles in the traveling process and obvious inter-class similarities caused by similar *** existing methods focus on local attributes by marking local ***,these methods require additional annotations,resulting in complex algorithms and insufferable computation *** cope with these challenges,this paper proposes a vehicle Re-ID model based on optimized DenseNet121 with joint *** model applies the SE block to automatically obtain the importance of each channel feature and assign the corresponding weight to it,then features are transferred to the deep layer by adjusting the corresponding weights,which reduces the transmission of redundant information in the process of feature reuse in *** the same time,the proposed model leverages the complementary expression advantages of middle features of the CNN to enhance the feature expression ***,a joint loss with focal loss and triplet loss is proposed in vehicle Re-ID to enhance the model’s ability to discriminate difcult-to-separate samples by enlarging the weight of the difcult-to-separate samples during the training *** results on the VeRi-776 dataset show that mAP and Rank-1 reach 75.5%and 94.8%,***,Rank-1 on small,medium and large sub-datasets of Vehicle ID dataset reach 81.3%,78.9%,and 76.5%,respectively,which surpasses most existing vehicle Re-ID methods.

关键词： Vehicle re-identication densenet joint loss focal loss SE block

来源：评论

学校读者我要写书评

暂无评论

Crack Detection Method for Asphalt Pavement Combining Multi-scale Features and Attention Mechanism

Crack Detection Method for Asphalt Pavement Combining Multi-...

引用

Advances in Electrical engineering and computer Applications( AEECA), 2020 IEEE International Conference on

作者： Zijian Xu Lili Wang School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China School of Software Engineering Chongqing University of Posts and Telecommunications Chongqing China

Crack, as one of the common diseases of asphalt pavements, seriously affects the health of asphalt pavements. To cope with the demand of crack detection in the context of complex pavements, an improved network model with an encoder-decoder structure is proposed. First, dense long and short connections are combined with full-scale jump connections, and the jump connection structure yields fullscale feature information to each node of the decoding layer. Second, spatial and channel attention modules are incorporated into the proposed network. The former is used at the low level of the network to improve the ability to capture crack detail information, and the latter is applied at the high level of the proposed network to obtain the semantic information. Finally, improve network performance by building deep supervision network. The proposed network is compared with on three datasets, DeepCrack, CFD, and Crack500, and the F-score reaches 86.79%. In this paper, the network is effective in crack detection and plays a certain role in maintaining road safety.

关键词：

来源：评论

学校读者我要写书评

暂无评论

G2Pxy: Generative Open-Set Node Classification on Graphs with Proxy Unknowns

arXiv

引用

arXiv 2023年

作者： Zhang, Qin Shi, Zelin Zhang, Xiaolin Chen, Xiaojun Fournier-Viger, Philippe Pan, Shirui Big Data Institute College of Computer Science and Software Engineering Shenzhen University China School of Information and Communication Technology Griffith University Queensland Australia

Node classification is the task of predicting the labels of unlabeled nodes in a graph. State-of-the-art methods based on graph neural networks achieve excellent performance when all labels are available during training. But in real-life, models are often applied on data with new classes, which can lead to massive misclassification and thus significantly degrade performance. Hence, developing open-set classification methods is crucial to determine if a given sample belongs to a known class. Existing methods for open-set node classification generally use transductive learning with part or all of the features of real unseen class nodes to help with open-set classification. In this paper, we propose a novel generative open-set node classification method, i.e., G2Pxy, which follows a stricter inductive learning setting where no information about unknown classes is available during training and validation. Two kinds of proxy unknown nodes, inter-class unknown proxies and external unknown proxies are generated via mixup to efficiently anticipate the distribution of novel classes. Using the generated proxies, a closed-set classifier can be transformed into an open-set one, by augmenting it with an extra proxy classifier. Under the constraints of both cross entropy loss and complement entropy loss, G2Pxy achieves superior effectiveness for unknown class detection and known class classification, which is validated by experiments on benchmark graph datasets. Moreover, G2Pxy does not have specific requirement on the GNN architecture and shows good generalizations. Copyright © 2023, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Long Short Term Memory (LSTM)-based Cuffless Continuous Blood Pressure Monitoring

Long Short Term Memory (LSTM)-based Cuffless Continuous Bloo...

引用

International Conference on VLSI Design

作者： Vijay Kumar Goldy Kolin Paul Mahesh Chowdhary Amar Nath and Shashi Khosla School of Information Technology Indian Institute of Technology Delhi India Department of Computer Science and Engineering Indian Institute of Technology Delhi India MEMS Software Solutions ST Microelectronics Santa Clara California United States

Continuously monitoring blood pressure (BP) is crucial for individuals at high risk of cardiac diseases. However, existing BP measurement techniques lack the ability to provide non-invasive and continuous monitoring. To address this challenge, researchers have recently explored accelerometer-based systems for BP estimation. These systems rely on signal processing algorithms that often necessitate extensive feature engineering, making updates and calibration difficult. In this paper, we propose a novel device for non-invasive continuous BP monitoring. The device consists of a patch with two inertial measurement units (IMUs) attached to the skin in the user’s neck region, specifically along the carotid artery. A control unit connected to the patch receives sensor data from these IMU units. It employs a machine learning (ML) model based on Long Short Term Memory (LSTM) to estimate BP using the sensor data. The model undergoes two general ML processes. The first ML process involves training the analysis model using a training set comprised of data from various individuals. Subsequently, the second machine learning process re-trains a portion of the analysis model using an individualized training set gathered from the specific user. This approach enhances the accuracy and personalization of the BP estimation, providing a promising solution for continuous monitoring of BP in high-risk *** BP monitoring device’s analysis model is also trained and tested on 11 volunteers. The BP monitoring device can measure an individual’s BP every 5 seconds. Additionally, the best root mean squared error (RMSE) loss obtained with our model is less than 2.932 mmHg for systolic BP and 2.231 mmHg for diastolic BP.

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：