检索结果-内蒙古大学图书馆

Comparison of Persian Handwritten Digit Recognition in Three Color Modalities Using Deep Neural Networks 1

2nd International Conference on Pattern Recognition and Artificial Intelligence, ICPRAI 2020

作者： Zohrevand, Abbas Sattari, Mahdi Sadri, Javad Imani, Zahra Suen, Ching Y. Djeddi, Chawki Department of Computer Engineering Kosar University of Bojnord Bojnord Iran Department of Computer Engineering University of Tabriz Tabriz Iran Department of Computer Science and Software Engineering Faculty of Engineering and Computer Science Concordia University MontrealQC Canada Department of Electrical and Computer Engineering Babol Noshirvani University of Technology Babol Iran Department of Mathematics and Computer Science Larbi Tebessi University Tebessa Algeria

ISBN: (数字)9783030598303

ISBN: (纸本)9783030598297

Most of the methods on handwritten digit recognition in the literature are focused and evaluated on black and white image databases. In this paper we try to answer a fundamental question in document recognition. Using Convolutional Neural Networks (CNNs), we investigate to see whether color modalities of handwritten digits affect their recognition rate? To the best of our knowledge, so far this question has not been answered due to the lack of handwritten digit databases that have all three color modalities of handwritten digits. To answer this question, we select 13,330 isolated digits from novel Persian handwritten database, which have three different color modalities and are unique in term of size and variety. Our selected dataset are divided into training, validation, and testing sets. Afterward, similar conventional CNN models are trained with the samples of our training set. While the experimental results on the testing set show that CNN on the black and white digit images has a better performance compared to the other two color modalities, in general there are no significant differences for network accuracy in different color modality. Also, comparisons of training times in three color modalities show that recognition of handwritten digits in black and white using CNN is much more efficient. © 2020, Springer Nature Switzerland AG.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

COVID TCL:A Joint Metric Loss Function for Diagnosing COVID-19 Patient in the Early and Incubation Period

引用

computer Systems science & engineering 2023年第10期47卷 187-204页

作者： Rui Wen Jie Zhou Zhongliang Shen Xiaorui Zhang Sunil Kumar Jha Department of Electromechanical Engineering Zhejiang Business Technology InstituteNingbo315012China Engineering Research Center of Digital Forensics Ministry of EducationJiangsu Engineering Center of Network MonitoringSchool of Computer and SoftwareNanjing University of Information Science&TechnologyNanjing210044China Wuxi Research Institute Nanjing University of Information Science&TechnologyWuxi214100China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET) Nanjing University of Information Science&TechnologyNanjing210044China Department of Physics Faculty of ScienceAdani UniversityAhmedabadIndia

Convolution Neural Networks(CNN)can quickly diagnose COVID-19 patients by analyzing computed tomography(CT)images of the lung,thereby effectively preventing the spread of ***,the existing CNN-based COVID-19 diagnosis models do consider the problem that the lung images of COVID-19 patients in the early stage and incubation period are extremely similar to those of the non-COVID-19 *** reduces the model’s classification sensitivity,resulting in a higher probability of the model misdiagnosing COVID-19 patients as non-COVID-19 *** solve the problem,this paper first attempts to apply triplet loss and center loss to the field of COVID-19 image classification,combining softmax loss to design a jointly supervised metric loss function COVID Triplet-Center Loss(COVID-TCL).Triplet loss can increase inter-class discreteness,and center loss can improve intra-class ***,COVID-TCL can help the CNN-based model to extract more discriminative features and strengthen the diagnostic capacity of COVID-19 patients in the early stage and incubation ***,we use the extreme gradient boosting(XGBoost)as a classifier to design a COVID-19 images classification model of CNN-XGBoost architecture,to further improve the CNN-based model’s classification effect and operation *** experiment shows that the classification accuracy of the model proposed in this paper is 97.41%,and the sensitivity is 97.61%,which is higher than the other 7 reference *** COVID-TCL can effectively improve the classification sensitivity of the CNN-based model,the CNN-XGBoost architecture can further improve the CNN-based model’s classification effect.

关键词： Covid-19 diagnose convolutional neural networks XGBoost COVID triplet-center loss early and incubation COVID-19 patients

来源：评论

学校读者我要写书评

暂无评论

Parallel Global Sequence Alignment with Arbitrary Scoring Scheme: Algorithm Formulation and Evaluation

SSRN

引用

SSRN 2022年

作者： Sadiq, Muhammad Umair Yousaf, Muhammad Murtaza Department of Computer Science Government College University Lahore54000 Pakistan Department of Software Engineering Faculty of Computing and Information Technology University of the Punjab Lahore54000 Pakistan Faculty of Computing and Information Technology University of the Punjab Lahore54000 Pakistan

Alignment of the sequences is useful in many biological and non-biological domains. Needleman-Wunsch algorithm is deemed as the basic algorithm for finding the optimal alignment between two sequences. It is a dynamic programming based algorithm which has quadratic time and space requirement. Nonetheless, as a result of increase in the capacity of sequence databases in recent years, sizes of sequences may contain billions of characters for computationally intensive problems. Comparison of such large sequences using sequential methods is avoided as it takes unacceptable amount of time for producing the results. In this paper, we proposed a parallel variation of the Needleman-Wunsch algorithm by reformulating the dependencies in the prevalent dynamic programming solution. Proof of correctness of the proposed algorithm is established. It evinces certain characteristics such as it allows arbitrary linear scoring scheme when comparing the sequences which is important to obtain peerless alignment. Moreover, it ensures load balancing among the computational units and maximizes the utilization of resources. It is compared with various state-of-the-art approaches. Experimental results using the real DNA and user trajectories sequences over graphic processing units (GPUs) suggest that the proposed algorithm is notably superior to the existing approaches that allow arbitrary linear scoring schemes. It achieved the GCUPs up to 14.06 and maximum speedup of 48.18x compared to the sequential implementation. © 2022, The Authors. All rights reserved.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

ACOCA-G: scenario-based context query generation for evaluating performance of context management platforms

Discover Internet of Things

引用

Discover Internet of Things 2025年第1期5卷

作者： De Silva, Ravindi Zaslavsky, Arkady Loke, Seng W. Jayaraman, Prem Prakash Faculty of Information Technology Deakin University Melbourne Australia Department of Computer Science and Software Engineering Swinburne University Melbourne Australia

Context-awareness is a pivotal trend within the Internet of Things research area, facilitating the near real-time processing and interpretation of relevant sensor data to enhance data processing efficiency. Context Management Platforms (CMPs), as advanced IoT middleware platforms offer promising solutions to IoT applications by offering seamless interoperability between different IoT silos. However, significant gaps still remain in evaluating the performance of CMPs, especially the data retrieval aspect of CMPs. Existing IoT middleware evaluation approaches lack flexible, user-friendly approaches to generate query loads to address aforementioned limitation. This paper introduces ACOCA-G (Adaptive COntext CAching-Generator), a configurable automated framework designed to generate scenario-based context queries to evaluate data retrieval of CMPs. ACOCA-G transforms real-world scenarios into scene descriptions in a specified format, which are then converted into Context-aware Scene Graphs (CSGs). ACOCA-G framework introduces a novel situation reasoning approach that integrates concepts of Context Spaces Theory (CST) and enhanced Situation State Machines (SSM). CSG reasoning identifies situations, facilitating the generation of dynamic and context-specific query loads. The framework produces template-based queries of varied complexities, demonstrating ACOCA-G’s flexibility and adaptability in generating queries closely aligning with real-world query complexities. Empirical evaluations using real-world IoT datasets and scenes of diverse complexities assess ACOCA-G in terms of query completeness, volume, and generation efficiency, providing insights into accuracy, scalability, and effectiveness. As a pioneering solution for systematically evaluating CMP performance, ACOCA-G serves as a robust tool for addressing gaps in CMP data retrieval assessment. © The Author(s) 2025.

关键词： Middleware

来源：评论

学校读者我要写书评

暂无评论

Towards Gait Analysis and Rehabilitation of Parkinson's Disease Patients 23

Towards Gait Analysis and Rehabilitation of Parkinson's Dise...

引用

23rd IEEE International Multi-Topic Conference, INMIC 2020

作者： Ul Haq, Inam Ali, Ghulam Ul Ghani, M. Ahmad Nawaz Nadeem, Amna University of Okara Pakistan Faculty of Computing Department of Computer Science Lahore Pakistan University of Management and Technology Department of Software Engineering Lahore Pakistan

ISBN: (纸本)9781728198934

This paper aims at designing an efficient real-time gait analysis algorithm to detect a possible fall. Four-meter Go and Back (4G) scale has been designed for taking measurements of experiments. Two wireless accelerometers are put on waist positions of 17 subjects suffering from Parkinson's disease. Based on information captured, a real-time gait analysis algorithm is implemented to detect an ambulatory deviation. Furthermore, the proposed method is flexible to adjust to respond to the gait-related movements. Other researchers can use this algorithm in their gait-related studies. In this paper, different gait-related parameters are also discussed and represented through a 4GB scale. © 2020 IEEE.

关键词： Gait analysis

来源：评论

学校读者我要写书评

暂无评论

Towards a Deep Learning Pain-Level Detection Deployment at UAE for Patient-Centric-Pain Management and Diagnosis Support: Framework and Performance Evaluation

arXiv

引用

arXiv 2023年

作者： Ismail, Leila Waseem, Muhammad Danish Lab School of Computing and Information Systems Faculty of Engineering and Information Technology The University of Melbourne Australia Research Laboratory Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University United Arab Emirates National Water and Energy Center United Arab Emirates University United Arab Emirates

The outbreak of the COVID-19 pandemic revealed the criticality of timely intervention in a situation exacerbated by a shortage in medical staff and equipment. Pain-level screening is the initial step toward identifying the severity of patient conditions. Automatic recognition of state and feelings help in identifying patient symptoms to take immediate adequate action and providing a patient-centric medical plan tailored to a patient's state. In this paper, we propose a framework for pain-level detection for deployment in the United Arab Emirates and assess its performance using the most used approaches in the literature. Our results show that a deployment of a pain-level deep learning detection framework is promising in identifying the pain level *** Codes 68T07 © 2023, CC BY-NC-ND.

关键词： eHealth

来源：评论

学校读者我要写书评

暂无评论

Local Weighted Generalized Multigranulation Neighborhood Rough Set

Local Weighted Generalized Multigranulation Neighborhood Rou...

引用

International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)

作者： Yanting Guo Eric C.C. Tsang Meng Hu College of Computer Science and Software Engineering Shenzhen University Shenzhen China Faculty of Information Technology Macau University of Science and Technology Taipa Macau

ISBN: (纸本)9781665466127

Local neighborhood rough set is an emerging rough set model, which provides more efficient knowledge representation for weakly labeled data with real-valued attributes in big data. It mainly studies knowledge representation under single granulation, but it cannot effectively and comprehensively represent knowledge of multiple granulations. In this paper, having considered the importance of different granulations for knowledge representation and decisions, we propose a Local Weighted Generalized Multigranulation Neighborhood Rough Set (LWGMNRS) model by using a novel weighted granulation method for knowledge representation of weakly labeled data with multiple granulations. Meanwhile, we discuss the relationships among LWGMNRS and the existing rough set models in detail, as well as its advantages and significances. Finally, theoretical analysis and case study show that the sig-nificance of LWGMNRS in knowledge representation.

关键词： Rough sets Knowledge representation Big Data Wavelet analysis Data models Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

An Improved ${k}$-Means Algorithm with Spatial Constraints for Image Segmentation

An Improved ${k}$-Means Algorithm with Spatial Constraints f...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Meng Hu Eric C.C. Tsang Yanting Guo Qingshuo Zhang Faculty of Information Technology Macau University of Science and Technology Taipa Macau College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (纸本)9781665466097

The ${k}$ -means is sensitive to the initial center and noise in image segmentation. To reduce the sensitivity of k-means to the initial center, we use the equidistant strategy to segment the cumulative sum of histogram to initialize centers. Then we introduce local spatial information into objective function of k-means to reduce the impact of noise in image segmentation and improve the robustness of segmentation algorithm. We combine the equidistant segmentation strategy and k-means with spatial constraints to propose an improved k-means algorithm (I- ${k}$ -means_S). I- ${k}$ -means_S solves the problem that traditional ${k}$ -means is easy to be affected by initial center and noise in image segmentation. To test the performance of I- ${k}$ -means, we create two synthetic images and add Gaussian and Salt & Pepper noises to the two images. We compare I- ${k}$ -means_S with 5 classical cluster algorithms on the two noisy images. From the results, we know that the proposed algorithm is more robust than the other algorithms. Meanwhile, we apply I- ${k}$ -means_S to natural image processing. The results show that it still has high robustness.

关键词： Image segmentation Histograms Machine learning algorithms Sensitivity Clustering algorithms Machine learning Linear programming

来源：评论

学校读者我要写书评

暂无评论

Enhancing Adults' Online Course Learning Behavior Performance through Live Class in Distance and Open Education: Learning Analysis Based on a Course 22

Enhancing Adults' Online Course Learning Behavior Performanc...

引用

6th International Conference on Education and Multimedia Technology, ICEMT 2022

作者： Shu, Fengfang Zhao, Chengling Liu, Qingtang Li, Hongxia Huang, Yan Faculty of Artificial Intelligence in Education Central China Normal University Hubei Wuhan430079 China Wuhan Open University Wuhan Software Engineering Vocational College Hubei Wuhan430030 China School of Computer Science Si Chuan Normal University Sichuan Chengdu610068 China Institute of Education Wisdom Education Research Center Guizhou Normal University Guizhou Guiyang550001 China

ISBN: (纸本)9781450396455

The open and distance education is a hybrid of synchronous and asynchronous learning. This study examines the impact of synchronous live class on online course learning behavior from the perspective of learning data analysis to offer insight to further guide the integrated learning design and implementation of adult learners' synchronous and asynchronous learning. Using online course learning log data and the interactive text generated from the course learning interaction at an Open University School in central China, this study analyzes descriptive statistics of live class learning and mines learners' emotions and attitudes towards it. In particular, this study uses participation in the live class as the classification variable, analyzes the depth, breadth and persistence of learners' online course learning behavior performance, and examines the correlation between these learning behavior performance and grades. The analyses demonstrate that learners have a positive attitude towards live class learning and have learning disabilities. Moreover, participation in live class has a positive effect on asynchronous learning performance. Participation in live class promotes the occurrence of learners' online course learning behavior, and correlation between learning behavior performance and grades. Chinese instant messaging program Tencent QQ and other Instant messenger tools were useful for the adult learners' smoothly online learning. © 2022 ACM.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

A fast and effective maximum power point tracking method under various weather conditions for grid-connected photovoltaic systems

A fast and effective maximum power point tracking method und...

引用

IEEE Conference on Power Electronics and Renewable Energy (CPERE)

作者： Karam Khairullah Mohammed Saad Mekhilef Muhyaddin Rawa Control and Mechatronics Engineering Department School of Electrical Engineering Universiti Teknologi Malaysia Johor Bahru Malaysia School of Software and Electrical Engineering Faculty of Science Engineering and Technology Swinburne University of Technology Hawthorn VIC Australia Smart Grids Research Group Center of Research Excellence in Renewable Energy and power Systems King Abdulaziz University Jeddah Saudi Arabia Department Of Electrical and computer Engineering Faculty of engineering K. A Care Energy Research and Innovation Center King Abdulaziz University Jeddah Saudi Arabia

Photovoltaic systems (PV) are exposed to various weather conditions during the day and getting the maximum power of a PV system is one of its major challenges. While the conventional methods take time to track the maximum power accompanying the fluctuation around the maximum power. Consequently, several metaheuristic algorithms have been presented to overcome the fluctuating around the maximum power. On the other hand optimization methods will search into entire the PV curve to extract the maximum power. This leads to unnecessary search points during the uniform shading conditions which decrease the convergence speed towards the maximum power. In overcoming the tracking time issues as well as the capacity to distinguish between uniform and partial shading conditions, a quick and efficient tracking technique connected to the grid system was presented in this paper. The proposed system, has been tested using MATLAB/SIMULINK, which includes a boost converter to track the maximum power with a sampling time of 0.05 seconds, While a voltage source converter (VSC) is used to transfer the power generated by solar panels to the grid. The simulation results demonstrated that the proposed method was successfully implemented, with an average tracking time of 0.412 s for different weather conditions. Moreover, the comparison with the conventional method of perturb and observe (P& O) has been presented to evaluate the proposed method’s efficiency.

关键词： Maximum power point trackers Renewable energy sources Fluctuations Simulation Optimization methods Power electronics Solar panels

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：