检索结果-内蒙古大学图书馆

Performance Comparison of Deep and Machine Learning Approaches Toward COVID-19 Detection

Intelligent Automation & Soft Computing 2023年第8期37卷 2247-2261页

作者： Amani Yahyaoui Jawad Rasheed Shtwai Alsubai Raed M.Shubair Abdullah Alqahtani Buket Isler Rana Zeeshan Haider Department of Software Engineering Istanbul Sabahattin Zaim UniversityIstanbul34303Turkey Department of Software Engineering Nisantasi UniversityIstanbul34398Turkey Department of Computer Science College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia Department of Electrical and Computer Engineering New York University(NYU)Abu Dhabi129188United Arab Emirates College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia Department of Computer Engineering Istanbul Topkapi UniversityIstanbul34087Turkey Baqai Institute of Hematology Baqai Medical UniversityKarachi75340Pakistan

The coronavirus(COVID-19)is a disease declared a global pan-demic that threatens the whole *** then,research has accelerated and varied to find practical solutions for the early detection and correct identification of this *** researchers have focused on using the potential of Artificial Intelligence(AI)techniques in disease diagnosis to diagnose and detect the *** paper developed deep learning(DL)and machine learning(ML)-based models using laboratory findings to diagnose *** different methods are used in this study:K-nearest neighbor(KNN),Decision Tree(DT)and Naive Bayes(NB)as a machine learning method,and Deep Neural Network(DNN),Convolutional Neural Network(CNN),and Long-term memory(LSTM)as DL *** approaches are evaluated using a dataset obtained from the Israelita Albert Einstein Hospital in Sao Paulo,*** data consists of 5644 laboratory results from different patients,with 10%being Covid-19 positive *** dataset includes 18 attributes that characterize *** used accuracy,f1-score,recall and precision to evaluate the different developed *** obtained results confirmed these approaches’effectiveness in identifying COVID-19,However,ML-based classifiers couldn’t perform up to the standards achieved by DL-based *** all,NB performed worst by hardly achieving accuracy above 76%,Whereas KNN and DT compete by securing 84.56%and 85%accuracies,*** these,DL models attained better performance as CNN,DNN and LSTM secured more than 90%*** LTSM outperformed all by achieving an accuracy of 96.78%and an F1-score of 96.58%.

关键词： Artificial intelligence COVID-19 deep learning diagnosis machine learning

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Scheduling Meeting System Using Mobile Agent 8

Design and Implementation of a Scheduling Meeting System Usi...

引用

8th International Conference on Contemporary Information Technology and Mathematics, ICCITM 2022

作者： Hammo, Asma'A Y. Al-Jawaherry, Marwa Adeeb Altaie, Atica M. University of Mosul College of Computer Science and Mathematics Department of Software Engineering Mosul Iraq Tikrit University College of Computer Science and Mathematics Department of Computer Science Tikrit Iraq

ISBN: (纸本)9798350334869

In recent years, as a result of rapid development, the scheduling of meetings has become costly and time-consuming. Many systems that support the scheduling of meetings have been developed and they are independently finding the appropriate scheduling date and duration of the meeting. In this research, the Multi-Agent Systems (MAS) is used to find out the appropriate time for meeting since agent is able to cooperate and execute autonomy. An algorithm was proposed to deal with the participants' leisure time and to make the appropriate decision to determine the date and duration of the meeting. The scheduling system collects free time from several persons (every person has an agent) and decides the appropriate meeting date, duration, and time for holding the meeting and publishing it to all attenders. The number of attenders in the designed system is between (4-7), with the presence of the manager (The manager Agent) who is responsible for organizing the meeting. The system was developed using multi-agent systems. JADE (Java Agent Development Framework) is used under java language to design the system for its capabilities. The system provides easy and clear interfaces for users. The system is compared with other previous work and shows that its lightness to the network. Also, the proposed system provides an interface with no need to send messages using SMS or any other media. © 2022 IEEE.

关键词： Mobile agents

来源：评论

学校读者我要写书评

暂无评论

Category-Prompt Refined Feature Learning for Long-Tailed Multi-Label Image Classification 24

Category-Prompt Refined Feature Learning for Long-Tailed Mul...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Yan, Jiexuan Huang, Sheng Mu, Nankun Huangfu, Luwen Liu, Bo School of Big Data & Software Engineering Chongqing University Chongqing China College of Computer Science Chongqing University Chongqing China Fowler College of Business San Diego State University San DiegoCA United States School of Computer Science and Information Engineering Hefei University of Technology Hefei China

ISBN: (纸本)9798400706868

Real-world data consistently exhibits a long-tailed distribution, often spanning multiple categories. This complexity underscores the challenge of content comprehension, particularly in scenarios requiring Long-Tailed Multi-Label image Classification (LTMLC). In such contexts, imbalanced data distribution and multi-object recognition pose significant hurdles. To address this issue, we propose a novel and effective approach for LTMLC, termed Category-Prompt Refined Feature Learning (CPRFL), utilizing semantic correlations between different categories and decoupling category-specific visual representations for each category. Specifically, CPRFL initializes category-prompts from the pretrained CLIP's embeddings and decouples category-specific visual representations through interaction with visual features, thereby facilitating the establishment of semantic correlations between the head and tail classes. To mitigate the visual-semantic domain bias, we design a progressive Dual-Path Back-Propagation mechanism to refine the prompts by progressively incorporating context-related visual information into prompts. Simultaneously, the refinement process facilitates the progressive purification of the category-specific visual representations under the guidance of the refined prompts. Furthermore, taking into account the negative-positive sample imbalance, we adopt the Asymmetric Loss as our optimization objective to suppress negative samples across all classes and potentially enhance the head-to-tail recognition performance. We validate the effectiveness of our method on two LTMLC benchmarks and extensive experiments demonstrate the superiority of our work over *** code is available at https://***/jiexuanyan/CPRFL. © 2024 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Message Verification Protocol Based on Bilinear Pairings and Elliptic Curves for Enhanced Security in Vehicular Ad Hoc Networks

引用

computers, Materials & Continua 2024年第10期81卷 1029-1057页

作者： Vincent Omollo Nyangaresi Arkan A.Ghaib Hend Muslim Jasim Zaid Ameen Abduljabbar Junchao Ma Mustafa A.Al Sibahee Abdulla J.Y.Aldarwish Ali Hasan Ali Husam A.Neamah Department of Computer Science and Software Engineering Jaramogi Oginga Odinga University of Science and TechnologyBondo40601Kenya Department of Applied Electronics Saveetha School of EngineeringSIMATSChennaiTamilnadu602105India Information Technology Department Management Technical CollegeSouthern Technical UniversityBasrah61004Iraq Department of Computer Science College of Education for Pure SciencesUniversity of BasrahBasrah61004Iraq College of Big Data and Internet Shenzhen Technology UniversityShenzhen518118China Huazhong University of Science and Technology Shenzhen InstituteShenzhen518000China National Engineering Laboratory for Big Data System Computing Technology Shenzhen UniversityShenzhen518060China Computer Technology Engineering Department Iraq University CollegeBasrah61004Iraq Department of Mathematics College of Education for Pure SciencesUniversity of BasrahBasrah61004Iraq Institute of Mathematics University of DebrecenDebrecenH-4002Hungary Department of Electrical Engineering and Mechatronics Faculty of EngineeringUniversity of DebrecenDebrecen4028Hungary

Vehicular ad hoc networks(VANETs)provide intelligent navigation and efficient route management,resulting in time savings and cost reductions in the transportation ***,the exchange of beacons and messages over public channels among vehicles and roadside units renders these networks vulnerable to numerous attacks and privacy *** address these challenges,several privacy and security preservation protocols based on blockchain and public key cryptography have been proposed ***,most of these schemes are limited by a long execution time and massive communication costs,which make them inefficient for on-board units(OBUs).Additionally,some of them are still susceptible to many *** such,this study presents a novel protocol based on the fusion of elliptic curve cryptography(ECC)and bilinear pairing(BP)*** formal security analysis is accomplished using the Burrows–Abadi–Needham(BAN)logic,demonstrating that our scheme is verifiably *** proposed scheme’s informal security assessment also shows that it provides salient security features,such as non-repudiation,anonymity,and ***,the scheme is shown to be resilient against attacks,such as packet replays,forgeries,message falsifications,and *** the performance perspective,this protocol yields a 37.88%reduction in communication overheads and a 44.44%improvement in the supported security ***,the proposed scheme can be deployed in VANETs to provide robust security at low overheads.

关键词： Attacks bilinear elliptic curve cryptography(ECC) privacy security vehicular ad hoc network(VANET)

来源：评论

学校读者我要写书评

暂无评论

Deep Semi-Supervised Learning with Fine-Grained Dynamic Weights and Pseudo-Label Constraints

Deep Semi-Supervised Learning with Fine-Grained Dynamic Weig...

引用

2023 International Conference on Communications, Computing and Artificial Intelligence, CCCAI 2023

作者： Li, Kuan Lian, Qianzhi Gao, Can Dongguan University of Technology School of Cyberspace Security Dongguan China Shenzhen University College of Computer Science and Software Engineering Shenzhen China

ISBN: (纸本)9798350311297

Semi-supervised learning is comonly trained using a large amount of unlabeled data and a small amount of labeled data. Existing works have achieved excellent results through consistent regularization methods. However, when designing the loss function, they set a loss function for labeled and unlabeled data separately, ignoring the connection between labeled and unlabeled data. Furthermore, unlabeled data all share the same weight, but the weights of different unlabeled data should be different. Based on these observations, a pair loss is proposed in this paper to strengthen the connection between labeled and unlabeled data;in addition, a dynamic weight is designed for each unlabeled data based on EMA (Exponential Moving Average) when calculating the loss function. Finally, a deep semi-supervised learning method called DWPC is proposed by combining dynamic weighting and pair loss. Experimental results on several datasets show that the proposed method improves performance in many scenarios. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

News-Driven Stock Price Forecasting in Indian Markets: A Comparative Study of Advanced Deep Learning Models 3

News-Driven Stock Price Forecasting in Indian Markets: A Com...

引用

3rd International Conference for Advancement in Technology, ICONAT 2024

作者： Attaluri, Kaushal Tripathi, Mukesh Kumar Reddy, Srinithi Shivendra Software Engineer-Machine Learning and AI Pegasystems India Worldwide Pvt Ltd Hyderabad India Vardhaman College of Engineering Department of Computer Science and Engineering Hyderabad India Vasavi College of Engineering Department of Information Technology Hyderabad India D. K. College Department of Computer Application Bihar Dumraon India

ISBN: (纸本)9798350354171

Forecasting stock market prices is a challenging task for traders, analysts, and engineers due to the myriad of variables influencing stock prices. However, the advent of artificial intelligence (AI) and natural language processing (NLP) has significantly advanced stock market forecasting. AI's ability to analyze complex data sets allows for more informed predictions. Despite these advancements, stock price forecasting remains an area where AI has not yet achieved optimal results. In this paper, we forecast stock prices using 30 years of historical data from various national banks in India sourced from the National Stock Exchange. We employ advanced deep learning models, including multivariate multi-step Long Short-Term Memory (LSTM), Facebook Prophet with LightGBM and Optuna, and Seasonal Auto-Regressive Integrated Moving Average (SARIMA). Additionally, we analyze news data from tweets and reliable sources like Business Standard and Reuters, recognizing their significant impact on stock price movements. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Three-Dimensional Real-Time Gait-Based Age Detection System Using Machine Learning

引用

computers, Materials & Continua 2023年第4期75卷 165-182页

作者： Muhammad Azhar Sehat Ullah Khalil Ullah Habib Shah Abdallah Namoun Khaliq Ur Rahman Department of Computer Science&IT University of MalakandChakdara18800Pakistan Department of Software Engineering University of MalakandChakdara18800Pakistan College of Computer Science King Khalid UniversityAbha62529Saudi Arabia Faculty of Computer and Information Systems Islamic University of MadinahMadinah42351Saudi Arabia Department of Statistics Abdul Wali Khan UniversityMardan23200Pakistan

Human biometric analysis has gotten much attention due to itswidespread use in different research areas, such as security, surveillance,health, human identification, and classification. Human gait is one of the keyhuman traits that can identify and classify humans based on their age, gender,and ethnicity. Different approaches have been proposed for the estimation ofhuman age based on gait so far. However, challenges are there, for which anefficient, low-cost technique or algorithm is needed. In this paper, we proposea three-dimensional real-time gait-based age detection system using a machinelearning approach. The proposed system consists of training and testingphases. The proposed training phase consists of gait features extraction usingthe Microsoft Kinect (MS Kinect) controller, dataset generation based onjoints’ position, pre-processing of gait features, feature selection by calculatingthe Standard error and Standard deviation of the arithmetic mean and bestmodel selection using R2 and adjusted R2 techniques. T-test and ANOVAtechniques show that nine joints (right shoulder, right elbow, right hand, leftknee, right knee, right ankle, left ankle, left, and right foot) are statisticallysignificant at a 5% level of significance for age estimation. The proposedtesting phase correctly predicts the age of a walking person using the resultsobtained from the training phase. The proposed approach is evaluated on thedata that is experimentally recorded from the user in a real-time *** (50) volunteers of different ages participated in the experimental *** the limited features, the proposed method estimates the age with 98.0%accuracy on experimental images acquired in real-time via a classical generallinear regression model.

关键词： Age estimation gait biometrics classical linear regression model

来源：评论

学校读者我要写书评

暂无评论

A New Secure Encryption Algorithm Based on RC4 Cipher and 4D Hyperchaotic Sprott-S System 5

A New Secure Encryption Algorithm Based on RC4 Cipher and 4D...

引用

5th college of science International Conference on Recent Trends in Information Technology, CSCTIT 2022

作者： Mohammed, Nadia M. Al-Kateeb, Zeena N. College of Computer Science and Mathematics University of Mosul Department of Software Engineering Mosul Iraq College of Computer Science and Mathematics University of Mosul Department of Computer Science Mosul Iraq

ISBN: (纸本)9798350334920

The widespread exchange of data in various formulas such as text and images via multimedia has created a great need for encryption techniques development, that can protect sharing of important secure data from untrusted or unauthorized access. In this paper, a two-level encryption method is proposed, the first level involves the use of an RC4 algorithm with several different length keys. The number of used keys depends on the length of the input original text. The keys are extracted from a 4D hyperchaotic Sprott_S system. The first encryption process is followed by the second encryption using the XOR gate for the first encryption output, with another key chain extracted from the same hyperchaotic system, that is pre-processed differently. Several measurements were used to measure the efficiency of the algorithm, including the time of application of the algorithm, histogram, bit error rate, and correlation. The experiments that were conducted on texts of different sizes showed the efficiency of the algorithm's performance, its high level of security, and the lack of time it needs, which confirms its quality. © 2022 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Recognition of Urdu Handwritten Alphabet Using Convolutional Neural Network (CNN)

引用

computers, Materials & Continua 2022年第11期73卷 2967-2984页

作者： Gulzar Ahmed Tahir Alyas Muhammad Waseem Iqbal Muhammad Usman Ashraf Ahmed Mohammed Alghamdi Adel A.Bahaddad Khalid Ali Almarhabi Department of Computer Science University of South AsiaLahore54000Pakistan Department of Computer Science Lahore Garrison UniversityLahore54000Pakistan Department of Software Engineering Superior UniversityLahore54000Pakistan Department of Computer Science GC Women UniversitySialkot53310Pakistan Department of Software Engineering College of Computer Science and EngineeringUniversity of Jeddah21493Saudi Arabia Department of Information System Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Computer Science College of Computing in Al-QunfudahUmm Al-Qura UniversityMakkah24381Saudi Arabia

Handwritten character recognition systems are used in every field of life nowadays,including shopping malls,banks,educational institutes,*** is the national language of Pakistan,and it is the fourth spoken language in the ***,it is still challenging to recognize Urdu handwritten characters owing to their cursive *** paper presents a Convolutional Neural Networks(CNN)model to recognize Urdu handwritten alphabet recognition(UHAR)offline and online *** research contributes an Urdu handwritten dataset(aka UHDS)to empower future works in this *** offline systems,optical readers are used for extracting the alphabets,while diagonal-based extraction methods are implemented in online ***,our research tackled the issue concerning the lack of comprehensive and standard Urdu alphabet datasets to empower research activities in the area of Urdu text *** this end,we collected 1000 handwritten samples for each alphabet and a total of 38000 samples from 12 to 25 age groups to train our CNN model using online and offline ***,we carried out detailed experiments for character recognition,as detailed in the *** proposed CNN model outperformed as compared to previously published approaches.

关键词： Urdu handwritten text recognition handwritten dataset convolutional neural network artificial intelligence machine learning deep learning

来源：评论

学校读者我要写书评

暂无评论

Lift: Exploiting Hybrid Stacked Memory for Energy-Efficient Processing of Graph Convolutional Networks 23

Lift: Exploiting Hybrid Stacked Memory for Energy-Efficient ...

引用

Proceedings of the 60th Annual ACM/IEEE Design Automation Conference

作者： Jiaxian Chen Zhaoyu Zhong Kaoyi Sun Chenlin Ma Rui Mao Yi Wang College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (纸本)9798350323481

Graph Convolutional Networks (GCNs) are powerful learning approaches for graph-structured data. GCNs are both computing- and memory-intensive. The emerging 3D-stacked computation-in-memory (CIM) architecture provides a promising solution to process GCNs efficiently. The CIM architecture can provide near-data computing, thereby reducing data movement between computing logic and memory. However, previous works do not fully exploit the CIM architecture in both dataflow and mapping, leading to significant energy *** paper presents Lift, an energy-efficient GCN accelerator based on 3D CIM architecture using software and hardware co-design. At the hardware level, Lift introduces a hybrid architecture to process vertices with different characteristics. Lift adopts near-bank processing units with a push-based dataflow to process vertices with strong re-usability. A dedicated unit is introduced to reduce massive data movement caused by high-degree vertices. At the software level, Lift adopts a hybrid mapping to further exploit data locality and fully utilize the hybrid computing resources. The experimental results show that the proposed scheme can significantly reduce data movement and energy consumption compared with representative schemes.

关键词： 3D-stacked memory

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：