检索结果-内蒙古大学图书馆

A Deep Learning for Alzheimer’s Stages Detection Using Brain Images

computers, Materials & Continua 2023年第1期74卷 1457-1473页

作者： Zahid Ullah Mona Jamjoom Department of Information Systems Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddahSaudi Arabia Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadhSaudi Arabia

Alzheimer’s disease(AD)is a chronic and common form of dementia that mainly affects elderly *** disease is dangerous because it causes damage to brain cells and tissues before the symptoms appear,and there is nomedicinal or surgical treatment available yet *** loss of memory and functionality control in multiple degrees according to AD’s progression ***,early diagnosis of AD can hinder its *** imaging tools such as magnetic resonance imaging(MRI),computed tomography(CT)scans,positron emission tomography(PET),*** help in medical diagnosis of ***,computer-aided diagnosis(CAD)such as deep learning applied to brain images obtained with these tools,has been an established strategic methodology that is widely used for clinical assistance in prognosis of *** this study,we proposed an intelligent methodology for building a convolutional neural network(CNN)from scratch to detect AD stages from the brain MRI images dataset and to improve patient *** is worth mentioning that training a deep-learning model requires a large amount of data to produce accurate results and prevent the model from overfitting ***,for better understanding of classifiers and to overcome the model overfitting problem,we applied data augmentation to the minority classes in order to increase the number of MRI images in the *** experiments were conducted using Alzheimer’s MRI dataset consisting of brain MRI scanned *** performance of the proposed model determines detection of the four stages of *** results show high performance of the proposed model in that the model achieved a 99.38%accuracy rate,which is the highest so ***,the proposed model performance in terms of accuracy,precision,sensitivity,specificity,and f-measures is promising when compared to the very recent state-of-the-art domain-specific models existing in the literature.

关键词： Dementia MRI images CNN model detection data augmentation decision support system

来源：评论

学校读者我要写书评

暂无评论

Web Application to predict Skin Disease: An Approach Using Deep Learning Algorithm 6

Web Application to predict Skin Disease: An Approach Using D...

引用

6th International Congress on Human-computer Interaction, Optimization and Robotic Applications, HORA 2024

作者： Thayalan, Eelanila Arumugavel, Ayingaran Ganeshan, Sharujan Dalaxshan, Makenthiran Fernando, Harinda Rajapakse, Kaushalya Department of Information Technology Faculty of computing Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Computer Systems Engineering Faculty of computing Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Computer Science and Software Engineering Faculty of computing Sri Lanka Institute of Information Technology Malabe Sri Lanka

ISBN: (纸本)9798350394634

The Disease Prediction system revolutionizes healthcare with advanced machine learning techniques for early detection of skin diseases, notably focusing on skin cancer. Through image processing and Transfer Learning, it excels in identifying potential malignancies, enabling timely interventions. Its capabilities extend to benign tumors and growth disorders, utilizing the ResNet50 Model for precise identification. Additionally, it predicts skin reactions associated with various dermatological conditions, such as Urticaria Hives and Warts, leveraging the efficientnetB0 Model. Integration of the VGG16 Model enhances diagnostic accuracy for inflammatory skin conditions. This holistic approach prioritizes patient-centric care, leveraging diverse datasets and intricate pattern recognition in medical images. The system's proactive nature embodies personalized solutions for early detection, timely intervention, and improved patient outcomes. Its versatility and accuracy underscore itstransformative potential in healthcare delivery. By harnessing diverse datasets and recognizing intricate patterns within medical images, it heralds a new era of personalized healthcare solutions. In essence, the Disease Prediction system exemplifies the transformative potential of machine learning in healthcare, ensuring the highest standards of diagnostic accuracy and efficacy, while prioritizing patient well-being and quality oflife. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Lossless Compression Technique in Quantum Secure Direct Communication 1

A Comparative Study of Lossless Compression Technique in Qua...

引用

1st International Conference on Cyber Security and Computing, CyberComp 2024

作者： Ishak, Izlin Zuriani Wooi, Liew Seow Harun, Nur Ziadah Azahari, Nur Shahirah Ramli, Sofia Najwa Ghazali, Osman Politeknik Seberang Perai Department of Information Technology and Communication Pulau Pinang Malaysia Universiti Putra Malaysia Faculty of Computer Science and Information Technology Department of Computer Science Selangor Malaysia Raffles University Faculty of AI and Robotics Johor Malaysia Universiti Tun Hussein Onn Malaysia Faculty of Computer Science and Information Technology Department of Information Security and Web Technology Johor Malaysia School of Computing Universiti Utara Malaysia Kedah Malaysia

ISBN: (纸本)9798350387728

This is a comparative study to explore the performance of three lossless compression techniques, namely Run Length Encoding (RLE), Shannon-Fano Coding (SFC), and Huffman Coding (HC) in the context of a Hybrid M-Ary in Braided Single Stage (HMBSS) protocol communication scheme. The previous study on HMBSS using HC found that HC's compression technique has drawbacks, i.e., it is sensitive to errors and noise in the transmission channel and limited to certain data types. These drawbacks did affect the value of the compression rate limit. In this study, we evaluate the effectiveness of RLE, SFC, and HC in terms of data size reduction, coding efficiency, and data transmission time by comparing their results arising from the simulation experiments using Python coding in Jupiter Notebook and developed based on the HMBSS protocol algorithm. This simulation experiment starts with an initial six randomly generated datasets. Each dataset is tested using three compression techniques, which resulted in 18 different datasets. The results from the experiments reveal that SFC and HC consistently achieved a higher compression ratio and coding efficiency than RLE. These two compression techniques' algorithms effectively reduce the data size while preserving the original information. In our study, we also find that the data transmission time is increased with larger text sizes for all three compression techniques. This indicates that the larger the data size, the more transmission time is required with regard to what the compression technique's algorithm is. © 2024 IEEE.

关键词： Quantum communication

来源：评论

学校读者我要写书评

暂无评论

A Conceptual Model e-Collaboration for Rural Tourism - Combining Soft system Methodology and UML 7

A Conceptual Model e-Collaboration for Rural Tourism - Combi...

引用

7th information systems International Conference, ISICO 2023

作者： Purwaningsih, Mardiana Purwandari, Betty Hidayanto, Achmad Nizar Faculty of Computer Science Universitas Indonesia Indonesia Faculty of Information Technology Perbanas Institute Indonesia

Through the IT utilization, stakeholders in rural tourism can engage in e-collaboration to develop tourism products and services together. While existing literature has not extensively addressed the e-collaboration model specifically tailored for rural tourism, this research sheds light on the emerging role of IT and its value within this context. To effectively model the intricate and less-structured environment of e-collaboration in rural tourism, the SSM is deemed the most suitable approach. Nonetheless, one limitation of SSM is the absence of explicit references during the implementation stage, requiring an additional methodological approach to realize the e-collaboration conceptual model within a system. To overcome this limitation, the present study applies both SSM and UML an e-collaboration system for rural tourism. The findings of this research can serve as a valuable reference for the development of an e-collaboration tool. © 2023 The Authors. Published by Elsevier B.V.

关键词： information services

来源：评论

学校读者我要写书评

暂无评论

Automatic emotion recognition using deep neural network

引用

Multimedia Tools and Applications 2025年 1-30页

作者： Sujatha, R. Chatterjee, Jyotir Moy Pathy, Baibhav Hu, Yu-Chen School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India Department of CSE Graphic Era University Dehradun India School of Electrical Engineering Vellore Institute of Technology Vellore India Department of Computer Science Tunghai University Taichung City Taiwan

Emotions are a vital semantic part of human correspondence. Emotions are significant for human correspondence as well as basic for human–computer cooperation. Viable correspondence between people is possibly achieved when both the importance and the emotion of the correspondence are perceived by all groups included. Understanding the significance of language has generally been concentrated on in natural language processing (NLP) as a semantic examination. In NLP, the text can be handled appropriately for classification. Emotion detection from facial emotion is the subfield of social signal processing applied in a wide assortment of regions, explicitly for human and PC collaboration. Many researchers have proposed various approaches, generally utilizing machine learning concepts. Automatic emotion recognition (AER) is significant for working with consistent intuitiveness between a person and a smart device toward fully acknowledging an intelligent society. Many researchers examined cross-lingual and multilingual speech emotion as a stage toward language-free emotion acknowledgment in natural speech. In the present work, we are proposing a deep learning-based AER system using four openly accessible datasets, namely Basic Arabic Vocal Emotions Dataset (BAVED), Acted Emotional Speech Dynamic Database (AESDD), Urdu written in Latin/Roman Script (URDU), and Toronto Emotional Speech Set (TESS), by utilizing the Jupyter notebook and a Python library for music and audio synthesis named Librosa. The experimental results exhibited that the proposed approach achieves better than the existing approaches, i.e., the accuracy of the proposed system with the URDU dataset is 96.24%, the TESS dataset is 99.10%, the AESDD dataset is 65.97%, and the BAVED dataset is 73.12%. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Recognition Model Depending on Optimized Support Vector Machine

引用

computers, Materials & Continua 2023年第7期76卷 499-515页

作者： Amel Ali Alhussan Fatma M.Talaat El-Sayed M.El-kenawy Abdelaziz A.Abdelhamid Abdelhameed Ibrahim Doaa Sami Khafaga Mona Alnaggar Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Machine Learning&Information Retrieval Department Faculty of Artificial IntelligenceKafrelsheikh UniversityKafrelsheikh33516Egypt Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia Department of Computer Science Faculty of Computer and Information SciencesAin Shams UniversityCairo11566Egypt Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Robotics and Intelligent Machines Department Faculty of Artificial IntelligenceKafrelsheikh UniversityKafrelsheikh33516Egypt

In computer vision,emotion recognition using facial expression images is considered an important research *** learning advances in recent years have aided in attaining improved results in this *** to recent studies,multiple facial expressions may be included in facial photographs representing a particular type of *** is feasible and useful to convert face photos into collections of visual words and carry out global expression *** main contribution of this paper is to propose a facial expression recognitionmodel(FERM)depending on an optimized Support Vector Machine(SVM).To test the performance of the proposed model(FERM),AffectNet is *** uses 1250 emotion-related keywords in six different languages to search three major search engines and get over 1,000,000 facial photos *** FERM is composed of three main phases:(i)the Data preparation phase,(ii)Applying grid search for optimization,and(iii)the categorization *** discriminant analysis(LDA)is used to categorize the data into eight labels(neutral,happy,sad,surprised,fear,disgust,angry,and contempt).Due to using LDA,the performance of categorization via SVM has been obviously *** search is used to find the optimal values for hyperparameters of SVM(C and gamma).The proposed optimized SVM algorithm has achieved an accuracy of 99%and a 98%F1 score.

关键词： Facial expression recognition machine learning linear dis-criminant analysis(LDA) support vector machine(SVM) grid search

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Calibration Approaches for Single-Beam and Multiple-Beam Distance Sensors

引用

IEEE Sensors Journal 2024年第1期24卷 975-983页

作者： Syu, Jia-Hao Lin, Jerry Chun-Wei Biernacki, Piotr Ziebinski, Adam National Taiwan University Department of Computer Science and Information Engineering Taipei10617 Taiwan Silesian University of Technology Faculty of Automatic Control Electronics and Computer Science Department of Distributed Systems and Informatics Devices Gliwice44-100 Poland Silesian University of Technology Department of Distributed Systems and Informatic Devices Gliwice44-100 Poland

Sensors are the foundation to facilitate smart cities, smart grids, and smart transportation, and distance sensors are especially important for sensing the environment and gathering information. Researchers have developed various methods to calibrate distance sensors;however, they mainly focus on using external information for calibration, which is inefficient and computationally expensive. To alleviate the above problems, we propose machine learning (ML)-based calibration approaches for distance sensors. We develop two calibration mechanisms, where the naive mechanism directly predicts the true distance, while the residual mechanism predicts the residual for calibration. The conventional ML regression algorithms are then adopted to predict the true distance or calibration residual. Experimental results show that the designed residual calibration mechanism outperforms the naive mechanism by reducing the root mean square error (RMSE) by 92.2% and mean absolute error (MAE) by 93.3% in the fitting task. In prediction, the proposed 2-D-residual mechanism achieves an improvement of 78.6% and 65.7% compared to the state-of-the-art method. The experimental results show the effectiveness and generalization of the proposed ML-based calibration method, especially for the 2-D mechanism, which achieves the highest robustness in all fitting and prediction tasks. © 2001-2012 IEEE.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Abnormal Events Detection in Surveillance Environments using Machine Learning

Abnormal Events Detection in Surveillance Environments using...

引用

2024 International Conference on science, technology, Engineering and Management, ICSTEM 2024

作者： Priya, D. Divya Theam, Lim Jit Vinisha, J. Krishnan, Kesavan Ayyasamy, Ramesh Kumar Subramaniam, Suthashini Department of Computer Science Engineering MLR Institue of Technology Hyderabad India Kampar Perak Malaysia Department of Information Technology St.Joseph's Institute of Technology Tamilnadu India Faculty of Computer Science and Information Technology Universiti Malaya Kuala Lumpur Malaysia

ISBN: (纸本)9798350376913

The ability of intelligent CCTV systems to detect unusual events, detect human behaviour and recognize objects is essential. This system enables the detection of anomalous events in the environment, anomalous human behaviour and the level of alertness in the environment. The system uses machine learning and machine vision capabilities to detect and identify specific anomalies in CCTV video feeds. This system often uses frames through frame processing, and supervised learning is often used as a training method. However, unsupervised and semi-supervised learning replace supervised learning in the system learning process due to the large variety of anomalies and the impossibility of predicting and preparing for all of them. This system can decrease or do away with the amount of labour-intensive human work needed to manually spot anomalies in the live CCTV feed and provide alerts. The initial monitoring of unusual events and low-quality archiving of typical scenarios also increases the efficiency of the system’s storage. In addition, this system provides an extension for developing a distributed anomaly classification system so that only abnormal events are directed to different unique systems for categorization. Regular recordings, on the other hand, will be archived with low quality. Furthermore, this approach offers a distributed anomaly classification system development path. © 2024 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Enhancing intrusion detection in IIoT: optimized CNN model with multi-class SMOTE balancing

引用

Neural Computing and Applications 2024年第24期36卷 14643-14659页

作者： Eid, Abdulrahman Mahmoud Soudan, Bassel Nassif, Ali Bou Injadat, MohammadNoor Department of Computer Engineering College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Department of Data Science and AI Faculty of Information Technology Zarqa University Zarqa Jordan

This work introduces an intrusion detection system (IDS) tailored for industrial internet of things (IIoT) environments based on an optimized convolutional neural network (CNN) model. The model is trained on a dataset that was balanced using a novel multi-class implementation of synthetic minority over-sampling technique (SMOTE) that ensures equal representation of all classes. Additionally, systematic optimization will be used to fine tune the hyperparameters of the CNN model and mitigate the effects of the increased size of the training dataset. Evaluation results will demonstrate substantial improvement in performance when the optimized CNN model is trained on the balanced dataset. The proposed IDS will be evaluated using the IIoT-specific WUSTL-IIOT-2021 dataset, and then its generalization capability will be verified using the non-domain specific UNSW_NB15 dataset. The model’s performance will be evaluated using accuracy, precision, recall, and F1-score metrics. The results will demonstrate that the proposed IDS is highly effective with performance exceeding 99.9% on all performance metrics. The IDS is also highly effective in detecting intrusion for generic IT networks achieving improvements in excess of 30% compared to the default baseline model. The results emphasize the versatility and effectiveness of the proposed IDS model, making it a reliable and adaptable solution for enhancing network security across diverse network environments. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Cluster-preserving sampling algorithm for large-scale graphs

引用

science China(information sciences) 2023年第1期66卷 60-76页

作者： Jianpeng ZHANG Hongchang CHEN Dingjiu YU Yulong PEI Yingjun DENG National Digital Switching System E&T Research Center Information Engineering University Network Systems Department of the Strategic Support Force School of Computer Science and Technology Eindhoven University of Technology Center for Applied Mathematics Tianjin University

Graph sampling is a very effective method to deal with scalability issues when analyzing largescale graphs. Lots of sampling algorithms have been proposed, and sampling qualities have been quantified using explicit properties(e.g., degree distribution) of the sample. However, the existing sampling techniques are inadequate for the current sampling task: sampling the clustering structure, which is a crucial property of the current networks. In this paper, using different expansion strategies, two novel top-leader sampling methods(i.e., TLS-e and TLS-i) are proposed to obtain representative samples, and they are capable of effectively preserving the clustering structure. The rationale behind them is to select top-leader nodes of most clusters into the sample and then heuristically incorporate peripheral nodes into the sample using specific expansion strategies. Extensive experiments are conducted to investigate how well sampling techniques preserve the clustering structure of graphs. Our empirical results show that the proposed sampling algorithms can preserve the population's clustering structure well and provide feasible solutions to sample the clustering structure from large-scale graphs.

关键词： graph sampling clustering structure top-leader nodes expansion strategies large-scale graphs

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：