检索结果-内蒙古大学图书馆

4th International Conference on Advancements in Computing, ICAC 2022

作者： Weerasinghe, D.N.H. Thiwanka, K.A.T. Jayasith, H.B.C. Onella Natalie, P.A.D. Samantha Rajapaksha, U.U. Karunasena, Anuradha Department of Computer Science and Software Engineering Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Information Technology Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka

ISBN: (纸本)9798350398090

The great majority of manual processes have been automated in the current day. Nonetheless, there is no reliable approach for evaluating UML diagrams for plagiarism and correctness. Unified Modeling Language (UML) provides the basis for UML diagrams. UML Diagrams are typically used to graphically express a system's stakeholders, activities, objects, and classes to get a deep knowledge of a particular system. UML diagrams are widely used by industry experts as well as beginners. Class diagrams and use case diagrams are the most commonly used diagrams in UML. Though most computer science-related students get assessed in UML modelling, diagram plagiarism isn't considered in most exams since it's a tedious task to perform. The proposed system automates capturing details in UML diagram components and generating a model answer from the given question scenario to compare the diagrams and calculate the plagiarism percentage with the correction percentage. © 2022 IEEE.

关键词： Unified Modeling Language

来源：评论

学校读者我要写书评

暂无评论

Development of Low Resource Machine Learning Models for Child Cognitive Ability Assessments 4

Development of Low Resource Machine Learning Models for Chil...

引用

4th International Conference on Advancements in Computing, ICAC 2022

作者： Kahawanugoda, Adithya Gnanarathna, Kulanika Meegoda, Nilan Monarawila, Randika Samarasinghe, Pradeepa Lindamulage, Asiri Gawesha Department of Computer Science and Software Engineering Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Information Technology Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka

ISBN: (纸本)9798350398090

Automated cognitive assessment tools are state-of-the-art in assessing cognition development. Due to the low availability of resources, building automated cognitive ability evaluation tools is challenging. This study focuses on developing machine learning models using a limited amount of data to assess Reasoning IQ, Knowledge IQ, Mental Chronometry and Attention-levels of Sinhala-speaking children between the age of 7 to 9 years. Our solution includes Sinhala speech recognition systems, image classification models, gaze estimation, blink count detection and facial expression recognition models to evaluate the above four cognitive ability measuring factors. Open domain speech recognition has been used to evaluate complex Sinhala child verbal responses and limited vocabulary responses were assessed using an end-to-end speech recognition system, respectively achieving 40.1% WER and 97.14% accuracy. Additionally, the image classification models for handwritten Sinhala letter recognition and two shape recognition models have gained 97%, 89% and 99% accuracy. The linear regression model for attention level evaluation that utilizes the inputs from a combination of eye-gaze estimation, facial expression recognition and blink rate detection models has gained 85% accuracy. © 2022 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Modeling of Sensor Enabled IrrigationManagement for Intelligent Agriculture Using Hybrid Deep Belief Network

引用

computer systems science & engineering 2023年第8期46卷 2319-2335页

作者： Saud Yonbawi Sultan Alahmari B.R.S.S.Raju Chukka Hari Govinda Rao Mohamad Khairi Ishak Hend Khalid Alkahtani JoséVarela-Aldás Samih M.Mostafa Department of Software Engineering College of Computer Science and EngineeringUniversity of JeddahJeddahSaudi Arabia King Abdul Aziz City for Science and Technology RiyadhKingdom of Saudi Arabia Aditya Engineering College Affiliated to JNTUK(Kakinada) SurampalemIndia Department of MBA Vignan’s Institute of Information and Technology(A)DuvvadaVisakhapatnamAP530049India School of Electrical and Electronic Engineering Engineering CampusUniversiti Sains Malaysia(USM)Nibong TebalPenang14300Malaysia Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11564Saudi Arabia SISAu Research Group Universidad Tecnológica IndoaméricaAmbato180103Ecuador Faculty of Computers and Information South Valley UniversityQena83523Egypt

Artificial intelligence(AI)technologies and sensors have recently received significant interest in intellectual *** the application of AI technologies and agriculture sensors in intellectual agriculture is urgently required for the growth of modern agriculture and will help promote smart *** irrigation scheduling systems were highly required in the agricultural field due to their capability to manage and save water deficit irrigation *** learning systems devise an alternative to conventional irrigation management through the automatic elaboration of predictions related to the learning of an *** this motivation,this study develops a modified black widow optimization with a deep belief network-based smart irrigation system(MBWODBN-SIS)for intelligent *** MBWODBN-SIS algorithm primarily enables the Internet of Things(IoT)based sensors to collect data forwarded to the cloud server for examination ***,the MBWODBN-SIS technique applies the deep belief network(DBN)model for different types of irrigation classification:average,high needed,highly not needed,and not *** MBWO algorithm is used for the hyperparameter tuning process.A wideranging experiment was conducted,and the comparison study stated the enhanced outcomes of the MBWODBN-SIS approach to other DL models with maximum accuracy of 95.73%.

关键词： Agriculture smart farming hyperparameter tuning artificial intelligence irrigation management sensors deep learning

来源：评论

学校读者我要写书评

暂无评论

Path Selection Optimization Algorithms for Mobile Agent Based on Push-All-Data Strategy

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2025年第10期19卷 112-128页

作者： Alzyoud, Faisal Tarawneh, Monther Al-Shrouf, Faiz Almaghthawi, Ahmed Alrehaili, Meaad Kanaker, Hasan Department of Computer Science Isra University Amman Jordan Department of Information Technology College of Information Technology and Communications Tafila Technical University Tafila Jordan Department of Software Engineering Faculty of Information Technology Isra University Amman Jordan Department of Computer Science College of Science & Art at Mahayil King Khalid University Abha62529 Saudi Arabia Department of Computer Sciences and Artificial Intelligence Collège of Computer Science and Engineering University of Jeddah Jeddah Saudi Arabia Department of Information Security Faculty of Information Technology Petra University Amman Jordan

With the advent of 5G and 6G technologies and the growing ubiquity of the Internet, the Mobile Agent (MA) paradigm is increasingly seen as a promising alternative to the conventional client-server model. MAs, which are software entities capable of moving and processing data across different systems, offer potential efficiencies in data management. However, their operation in dynamic and mobile environments can lead to challenges, such as incomplete or delayed tasks. This study addresses these issues by focusing on reducing the relocation time of MAs. A numerical procedure and a streamlining strategy were developed to expedite the transfer of an agent from the source to the target hub. Utilizing the itinerary design pattern and the Ant Colony Optimization (ACO) algorithm, implemented via the Java Agent Development Framework (JADE), this study sought the most efficient path for the MA. The proposed algorithm demonstrated a significant improvement, selecting the optimal path in just 271.511 seconds. This performance represents a substantial enhancement over previous approaches using the master-slave design pattern with either the Genetic Algorithm (GA) or the Node Compression Algorithm (NCA). The implications of this improvement are far-reaching, potentially enhancing the efficiency and reliability of data management systems in a variety of applications. © 2025 by the authors of this article. Published under CC-BY.

关键词： information management

来源：评论

学校读者我要写书评

暂无评论

FGRL-Net: Fine-Grained Personalized Patient Representation Learning for Clinical Risk Prediction Based on EHRs

FGRL-Net: Fine-Grained Personalized Patient Representation L...

引用

2023 IEEE International Conference on systems, Man, and Cybernetics, SMC 2023

作者： Chio, KaKit Zhu, Wenhao He, Lihua Zhang, Dian Yang, Xu Luo, Wuman Macao Polytechnic University Faculty of Applied Sciences S.A.R Macao China School of Information and Communication Engineering University of Electronic Science and Technology of China Sichuan Province China Shenzhen University Department of Computer Science and Software Engineering Shenzhen China

ISBN: (纸本)9798350337020

Personalized patient representation learning (PPRL) is a critical element in clinical risk prediction. It aims to obtain a complete portrait of each patient based on Electronic Health Records (EHR). Although existing works have achieved remarkable progress in healthcare prediction, there are still three major issues. First, feature correlation is crucial for risk prediction, but it has not yet been fully exploited by existing works. Second, variation pattern of dynamic feature contains useful information about patient's physical status, but adaptive pattern recognition is still a challenge. Third, existing works usually adopt a two-stage embedding process to process each dimension of the EHR data. However, some useful low-level information for PPRL will be lost. To address these issues, in this paper, we propose a fine-grained PPRL architecture named FG RL- N et for clinical risk prediction based on EHR. Specifically, we propose a Medical Feature Correlation Detection Module (FCM) to effectively learn the feature correlations for each patient and a Temporal Variation Pattern Recognition Module (TVM) to effectively detect the variation patterns of each dynamic feature. Moreover, we design a Fine-Grained Representation Mechanism (FGRM) to preserve the low-level information (from both feature and visit dimensions) useful for risk prediction. In addition, in the stage of data preprocessing, We utilize generic medical classification knowledge to classify numerical dynamic data. We conduct the in-hospital mortality experiment and the decompensation experiment on a real-world dataset. The experiment results show that the FGRL-Net outperforms state-of-the-art approaches. The source code is provided in github https://***/JackyChio/FGRL-Net. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based multi-head self-attention model for human epilepsy identification from EEG signal for biomedical traits

引用

Multimedia Tools and Applications 2024年第33期83卷 80201-80223页

作者： Dutta, Ashit Kumar Raparthi, Mohan Alsaadi, Mahmood Bhatt, Mohammed Wasim Dodda, Sarath Babu Prashant, G.C. Sandhu, Mukta Patni, Jagdish Chandra Department of Computer Science and Information Systems College of Applied Sciences AlMaarefa University Ad Diriyah Riyadh13713 Saudi Arabia Alphabet Life Science DallasTX7506 United States Department of Computer Science Al-Maarif University College Al Anbar31001 Iraq Model Institute of Engineering and Technology J&K Jammu India Software Engineer Central Michigan University DallasTX75009 United States Department of Computer Science Texas Tech University Lubbock79409 United States Skill Faculty of Engineering & amp Technology Shri Vishwakarma Skill University Haryana Palwal India CSE School of advance Computing Alliance University Bengaluru India

The neurological condition epilepsy is demanding and even fatal. Electroencephalogram (EEG)-based epilepsy detection still faces various difficulties. EEG readings fluctuate, and different patients have various seizure activity patterns. EEG signal detection is time-consuming and labour-intensive, which puts a strain on medical staff and raises the possibility of erroneous detections. Usually, electrodes are inserted into the scalp or inside the brain for a brief period of time in order to obtain EEG data. It is essential to research efficient cross-patient automatic epilepsy detection techniques. The multi-head self-attention mechanism recognises long-distance dependencies with the same proficiency as it does temporal dynamic correlations between short-term temporal pattern characteristics and sequential relationships. The contextual representations are inputted into a bidirectional long short-term memory network (BiLSTM) so that information can be extracted in both directions. Classification and training are carried out utilising the log SoftMax algorithm. The experiments utilised scalp EEG data from the CHB-MIT database. Sensitivity, specificity, F1-score, and accuracy were computed to be 96.5 percent, 97.04 percent, 96.6 percent, and 96.2 percent, respectively. The results of the experiment show how well the technique works for detecting seizures in several patients utilising multi-channel EEG recordings. The results also demonstrate the method's improved generalisation capabilities and resilience and consistency in collecting seizure patterns. This is particularly critical for the tertiary diagnosis of epilepsy, and the findings indicate that the proposed method significantly improves the accuracy of detection. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Prediction of Dental Fluorosis Infection based on Particle Optimized Scored KNN Approach 1

Prediction of Dental Fluorosis Infection based on Particle O...

引用

1st International Conference of Intelligent Methods, systems and Applications, IMSA 2023

作者： Montasser, Reem Kadry Ismael, Osama El-Kholy, Moataz October University for Modern Sciences and Arts Faculty of Computer Science Software Engineering Department Giza Egypt Cairo University Faculty of Computers and Artificial Intelligence Information Systems Department Giza Egypt October University for Modern Sciences and Arts Faculty of Dentistry Oral Pathology Department Giza Egypt

ISBN: (纸本)9798350335569

Due to its simplicity of usage across a variety of applications, the K-Nearest Neighbor algorithm is usually utilized as a classification approach. The K-Nearest Neighbor algorithm's accuracy is greatly impacted by the occurrence of multidimensional and outlier data. This research uses a novel hybrid technique known as Particle Optimized Scored K-Nearest Neighbor (POSKNN) to build a model to predict the emergence of dental fluorosis. The proposed novel approach is implemented in two phases: the first phase helps in the resolution of multidimensional data by performing selection of feature using the Modified Particle Swarm Optimization algorithm, and the second phase helps in the resolution of the presence of outliers by making use of the results of the first phase and applying the newly proposed scored KNN technique to them. The suggested approach was tested using a real-world dataset acquired from three dentistry clinics in Egypt's El Baharia Oasis, which has 56 attributes, two classes, and 328 records. 10-fold cross validation was implemented to the model. The experimental evaluation was divided into two parts;evaluation for modified particle swarm optimization, evaluation for scored K nearest neighbor, and the hybrid particle optimized scored K nearest neighbor. The experiment's results demonstrated that the suggested approach outperformed the traditional KNN and the modified KNN. POSKNN achieved an accuracy of 94.5% when K value is 11. © 2023 IEEE.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Hybrid Multi-Strategy Aquila Optimization with Deep Learning Driven Crop Type Classification on Hyperspectral Images

引用

computer systems science & engineering 2023年第10期47卷 375-391页

作者： Sultan Alahmari Saud Yonbawi Suneetha Racharla ELaxmi Lydia Mohamad Khairi Ishak Hend Khalid Alkahtani Ayman Aljarbouh Samih M.Mostafa King Abdulaziz City for Science and Technology P.O Box 6086Riyadh 11442Saudi Arabia Department of Software Engineering College of Computer Science and EngineeringUniversity of JeddahJeddahSaudi Arabia Department of AIML Aditya Engineering CollegeSurempallemAndhra PradeshIndia Department of Computer Science and Engineering Vignan’s Institute of Information TechnologyVisakhapatnam530049India School of Electrical and Electronic Engineering Engineering CampusUniversiti Sains Malaysia(USM)Nibong TebalPenang14300Malaysia Department of Information Systems College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh 11671Saudi Arabia Department of Computer Science University of Central AsiaNaryn722600Kyrgyzstan Faculty of Computers and Information South Valley UniversityQena83523Egypt

Hyperspectral imaging instruments could capture detailed spatial information and rich spectral signs of observed *** spatial information and spectral signatures of hyperspectral images(HSIs)present greater potential for detecting and classifying fine *** accurate classification of crop kinds utilizing hyperspectral remote sensing imaging(RSI)has become an indispensable application in the agricultural *** is significant for the prediction and growth monitoring of crop *** the deep learning(DL)techniques,Convolution Neural Network(CNN)was the best method for classifying HSI for their incredible local contextual modeling ability,enabling spectral and spatial feature *** article designs a Hybrid Multi-Strategy Aquila Optimization with a Deep Learning-Driven Crop Type Classification(HMAODL-CTC)algorithm *** proposed HMAODL-CTC model mainly intends to categorize different types of crops on *** accomplish this,the presented HMAODL-CTC model initially carries out image preprocessing to improve image *** addition,the presented HMAODL-CTC model develops dilated convolutional neural network(CNN)for feature *** hyperparameter tuning of the dilated CNN model,the HMAO algorithm is ***,the presented HMAODL-CTC model uses an extreme learning machine(ELM)model for crop type classification.A comprehensive set of simulations were performed to illustrate the enhanced performance of the presented HMAODL-CTC *** comparison studies reported the improved performance of the presented HMAODL-CTC algorithm over other compared methods.

关键词： Crop type classification hyperspectral images agricultural monitoring deep learning metaheuristics

来源：评论

学校读者我要写书评

暂无评论

The Impact of Stuttering Event Representation on Detection Performance

The Impact of Stuttering Event Representation on Detection P...

引用

Cyber Resilience (ICCR), International Conference on

作者： Abedal-Kareem Al-Banna Hui Fang Ahmad F Shubita Mohammad Arafah Amani Eqteeshat Saif B Abuaisheh Department of AI and Data Science University of Petra Department of Computer Science Loughborough University Department of Software Engineering University of Petra Department of Computer Science University of Petra Department of Information System Malaya University

ISBN: (数字)9798350394962

ISBN: (纸本)9798350394979

Stuttering or stammering is a common neurogenic, psychogenic fluency disorder wherein people have uncontrolled blocks on the natural flow of speech. Automatic Stuttering Event Detection (SED) is a widely recognised challenge due to the heterogenic and overlapped nature of stuttering speech. Therefore, this comparative study investigates the impact of stuttering event representation on detection performance. The paper evaluates the performance of SED and shows the impact of employing ASR pre-trained feature extractions on each stuttering event. Moreover, the paper provides different groups of experiments that evaluate the impact of three acoustic features, the Zero Crossing Rate (ZCR), the Spectral Flux Onset Strength Envelope (SFO), and Fundamental Frequency (FF) features, on SED performance. The paper demonstrates that the fusion of spectral and ASR features improves SED performance across all stuttering events by 8%. The F1 score of the Block class increased by approximately 10%, from 15% to 25%, while the word repetition and interjection increased by 8%. In addition, our experiments proved that the fusion of temporal features increased the average F1 score of SED by 2% across all stuttering events. The F1 score of the prolongation and sound repetition classes increased by 6% and 3%, respectively.

关键词： Event detection Speech recognition Feature extraction Acoustics Robustness Time-domain analysis Mel frequency cepstral coefficient

来源：评论

学校读者我要写书评

暂无评论

An Efficient Intrusion Detection Framework in software-Defined Networking for Cybersecurity Applications

引用

computers, Materials & Continua 2022年第8期72卷 3529-3548页

作者： Ghalib H.Alshammri Amani K.Samha Ezz El-Din Hemdan Mohammed Amoon Walid El-Shafai Department of Computer Science Community CollegeKing Saud UniversityRiyadh28095Saudi Arabia Deanship of Scientific Research Saudi Electronic UniversityRiyadhSaudi Arabia Management Information System Department College of Business AdministrationKing Saud UniversityRiyadh28095Saudi Arabia Department of Computer Science and Engineering Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Security Engineering Lab Computer Science DepartmentPrince Sultan UniversityRiyadh11586Saudi Arabia Electronics and Electrical Communications Eng.Depart. Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt

Network management and multimedia data mining techniques have a great interest in analyzing and improving the network traffic *** recent times,the most complex task in software Defined Network(SDN)is security,which is based on a centralized,programmable ***,monitoring network traffic is significant for identifying and revealing intrusion abnormalities in the SDN ***,this paper provides an extensive analysis and investigation of the NSL-KDD dataset using five different clustering algorithms:K-means,Farthest First,Canopy,Density-based algorithm,and Exception-maximization(EM),using the Waikato Environment for Knowledge Analysis(WEKA)software to compare extensively between these five ***,this paper presents an SDN-based intrusion detection system using a deep learning(DL)model with the KDD(Knowledge Discovery in Databases)***,the utilized dataset is clustered into normal and four major attack categories via the clustering ***,a deep learning method is projected for building an efficient SDN-based intrusion detection *** results provide a comprehensive analysis and a flawless reasonable study of different kinds of attacks incorporated in the KDD ***,the outcomes reveal that the proposed deep learning method provides efficient intrusion detection performance compared to existing *** example,the proposed method achieves a detection accuracy of 94.21%for the examined dataset.

关键词： Deep neural network DL WEKA network traffic intrusion and anomaly detection SDN clustering and classification KDD dataset

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：