检索结果-内蒙古大学图书馆

Hybrid GrabCut Hidden Markov Model for Segmentation

computers, Materials & Continua 2022年第7期72卷 851-869页

作者： Soobia Saeed Afnizanfaizal Abdullah N.Z.Jhanjhi Mehmood Naqvi Mehedi Masud Mohammed A.AlZain Department of Software Engineering UniversitiTeknologi Malaysia-UTM81310Malaysia School of Computer Science and Engineering SCE Taylor’s UniversitySubang Jaya47500Malaysia Department of Engineering and Technology Mohak CollegeAlbertaCanada Department of Computer Science College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Department of Information Technology College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia

Diagnosing data or object detection in medical images is one of the important parts of image segmentation especially those data which is less effective to identify inMRI such as low-grade tumors or cerebral spinal fluid(CSF)leaks in the *** aim of the study is to address the problems associated with detecting the low-grade tumor and CSF in brain is difficult in magnetic resonance imaging(MRI)images and another problem also relates to efficiency and less execution time for segmentation of medical *** tumor and CSF segmentation using trained light field database(LFD)datasets of MRI *** research proposed the new framework of the hybrid k-Nearest Neighbors(k-NN)model that is a combination of hybridization of Graph Cut and Support Vector Machine(GCSVM)and Hidden Markov Model of k-Mean Clustering Algorithm(HMMkC).There are four different methods are used in this research namely(1)SVM,(2)GrabCut segmentation,(3)HMM,and(4)k-mean clustering *** this framework,on the one hand,phase one is to perform the classification of SVM and Graph Cut algorithm to create the maximum margin *** research use GrabCut segmentation method which is the application of the graph cut algorithm and extract the data with the help of scaleinvariant features *** the other hand,in phase two,segment the low-grade tumors and CSF using a method adapted for HMkC and extract the information of tumor or CSF fluid by GCHMkC including iterative conditional maximizing mode(ICMM)with identifying the range of *** evaluation is also performing by the comparison of existing techniques in this *** conclusion,our proposed model gives better results than *** proposed model helps to common man and doctor that can identify their condition of brain *** future,this will model will use for other brain related diseases.

关键词： SVM tumor CSF k-NN MRI grabcut segmentation HMM

来源：评论

学校读者我要写书评

暂无评论

Dynamic Visible Light Positioning Based on Enhanced Visual Target Tracking

引用

China Communications 2023年第10期20卷 276-291页

作者： Xiangyu Liu Jingyu Hao Lei Guo Song Song School of Information Science and Engineering Shenyang Ligong UniversityShenyang 110158China Department of Computer Science and Engineering Southern University of Science and TechnologyShenzhen 518055China School of Computer Science and Engineering Northeastern UniversityShenyang 110819China School of Communication and Information Engineering Chongqing University of Posts and TelecommunicationsChongqing 400065China Hangzhou Institute of Advanced Technology Hangzhou 310056China Institute of Intelligent Communications and Network Security Chongqing University of Posts and TelecommunicationsChongqing 400065China

In visible light positioning systems,some scholars have proposed target tracking algorithms to balance the relationship among positioning accuracy,real-time performance,and ***,there are still two problems:(1)When the captured LED disappears and the uncertain LED reappears,existing tracking algorithms may recognize the landmark in error;(2)The receiver is not always able to achieve positioning under various moving *** this paper,we propose an enhanced visual target tracking algorithm to solve the above ***,we design the lightweight recognition/demodulation mechanism,which combines Kalman filtering with simple image preprocessing to quickly track and accurately demodulate the ***,we use the Gaussian mixture model and the LED color feature to enable the system to achieve positioning,when the receiver is under various moving *** results show that our system can achieve high-precision dynamic positioning and improve the system’s comprehensive performance.

关键词： visible light positioning visual target tracking gaussian mixture model kalman filtering system performance

来源：评论

学校读者我要写书评

暂无评论

Digital Twin Implementation of Autonomous Planning Arc Welding Robot System

引用

Complex System Modeling and Simulation 2023年第3期3卷 236-251页

作者： Xuewu Wang Yi Hua Jin Gao Zongjie Lin Rui Yu School of Information Science and Engineering East China University of Science and TechnologyShanghai 200237China Institute for Sustainable Manufacturing and also with the Department of Electrical and Computer EngineeringUniversity of KentuckyLexingtonKY 40506USA

Industrial robots are currently applied for ship sub-assembly welding to replace welding workers because of the intelligent production and cost *** order to improve the efficiency of the robot system,a digital twin system of welding path planning for the arc welding robot in ship sub-assembly welding is proposed in this manuscript to achieve autonomous planning and generation of the welding ***,a five-dimensional digital twin model of the dual arc welding robot system is ***,the system kinematics analysis and calibration are studied for communication realization between the virtual and the actual ***,a topology consisting of three bounding volume hierarchies(BVH)trees is proposed to construct digital twin virtual entities in this *** on this topology,algorithms for welding seam extraction and collision detection are ***,the genetic algorithm and the RRT-Connect algorithm combined with region partitioning(RRT-Connect-RP)are applied for the welding sequence global planning and local jump path planning,*** digital twin system and its path planning application are tested in the actual application *** results show that the system can not only simulate the actual welding operation of the arc welding robot but also realize path planning and real-time control of the robot.

关键词： arc welding robot digital twin topology path planning

来源：评论

学校读者我要写书评

暂无评论

DeepCNN:Spectro-temporal feature representation for speech emotion recognition

引用

CAAI Transactions on Intelligence technology 2023年第2期8卷 401-417页

作者： Nasir Saleem Jiechao Gao Rizwana Irfan Ahmad Almadhor Hafiz Tayyab Rauf Yudong Zhang Seifedine Kadry Department of Electrical Engineering Faculty of Engineering and TechnologyGomal UniversityD.I.KhanPakistan Department of Computer Science University of VirginiaCharlottesvilleVirginiaUSA Department of Information Technology College of Computing and Information Technology at KhulaisUniversity of JeddahJeddahSaudi Arabia Department of Computer Engineering and Networks College of Computer and Information SciencesJouf UniversitySkaka AljoufSaudi Arabia Centre for Smart Systems AI and CybersecurityStaffordshire UniversityStoke‐on‐TrentUK School of Computing and Mathematical Sciences University of LeicesterLeicesterUK Department of Applied Data Science Noroff University CollegeKristiansandNorway Artificial Intelligence Research Center(AIRC) Ajman UniversityAjmanUnited Arab Emirates Department of Electrical and Computer Engineering Lebanese American UniversityByblosLebanon

Speech emotion recognition(SER)is an important research problem in human-computer interaction *** representation and extraction of features are significant challenges in SER *** the promising results of recent studies,they generally do not leverage progressive fusion techniques for effective feature representation and increasing receptive *** mitigate this problem,this article proposes DeepCNN,which is a fusion of spectral and temporal features of emotional speech by parallelising convolutional neural networks(CNNs)and a convolution layer-based *** parallel CNNs are applied to extract the spectral features(2D-CNN)and temporal features(1D-CNN)representations.A 2D-convolution layer-based transformer module extracts spectro-temporal features and concatenates them with features from parallel *** learnt low-level concatenated features are then applied to a deep framework of convolutional blocks,which retrieves high-level feature representation and subsequently categorises the emotional states using an attention gated recurrent unit and classification *** fusion technique results in a deeper hierarchical feature representation at a lower computational cost while simultaneously expanding the filter depth and reducing the feature *** Berlin Database of Emotional Speech(EMO-BD)and Interactive Emotional Dyadic Motion Capture(IEMOCAP)datasets are used in experiments to recognise distinct speech *** efficient spectral and temporal feature representation,the proposed SER model achieves 94.2%accuracy for different emotions on the EMO-BD and 81.1%accuracy on the IEMOCAP dataset *** proposed SER system,DeepCNN,outperforms the baseline SER systems in terms of emotion recognition accuracy on the EMO-BD and IEMOCAP datasets.

关键词： decision making deep learning

来源：评论

学校读者我要写书评

暂无评论

Using Deep Learning to Analyze Brain fMRI for Schizophrenia Diagnosis

Using Deep Learning to Analyze Brain fMRI for Schizophrenia ...

引用

2024 IEEE International Conference on Computing, Applications and Systems, COMPAS 2024

作者： Salehin, Yusuf Bhuiyan, Md. Shakil Rahman Momo, Mariya Bithea, Yeamoni Jennifer, Sanjeda Sara Ahnaf Morshed, Md. Reza, Ahmed Wasif Shamsul Arefin, Mohammad East West University Department of Computer Science and Engineering Dhaka Bangladesh Chittagong University of Engineering and Technology Department of Computer Science and Engineering Chittagong Bangladesh

ISBN: (纸本)9798331529765

This paper explores the potential of Convolutional Neural Networks (CNNs) in diagnosing schizophrenia patients through functional Magnetic Resonance Imaging (fMRI) data, as early detection of schizophrenia, is crucial for symptom management. The study evaluates the performance of five state-of-the-art CNN models (VGG16, Resnet50, Inception V3, Inception Resnet V2, EfficientNetB0) in conjunction with a custom CNN model for binary classification. By utilizing a dataset of 19,734 fMRI images, an effective approach for classifying schizophrenia patients and healthy controls with remarkable accuracy has been introduced. These approaches involve model modification, image pre-processing techniques, and hyperparameter tuning. Notably, grayscale conversion, binary thresholding, and 3-channel format conversion contribute significantly to enhanced classification accuracy. The incorporation of data augmentation and layer modification schemes further strengthens the methodology. Moreover, through meticulous layer modifications, the layer-modified VGG16 and the customized CNN model achieved more than 99.99%, while other models reached an accuracy of 99.9%. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

One_by_zero@NLU of Devanagari Script Languages 2025: Target Identification for Hate Speech Leveraging Transformer-based Approach 1

One_by_zero@NLU of Devanagari Script Languages 2025: Target ...

引用

1st Workshop on Challenges in Processing South Asian Languages, CHiPSAL 2025, co-located with the 31st International Conference on Computational Linguistics, COLING 2025

作者： Chakraborty, Dola Hossain, Jawad Hoque, Mohammed Moshiul Department of Computer Science and Engineering Chittagong University of Engineering & Technology Chattogram4349 Bangladesh

ISBN: (纸本)9798891762015

People often use written words to spread hate aimed at different groups that cannot be practically detected manually. Therefore, developing an automatic system capable of identifying hate speech is crucial. However, creating such a system in a low-resourced languages (LRLs) script like Devanagari becomes challenging. Hence, a shared task has been organized targeting hate speech identification in the Devanagari script. This work proposes a pre-trained transformer-based model to identify the target of hate speech, classifying it as directed toward an individual, organization, or community. We performed extensive experiments, exploring various machine learning (LR, SVM, MNB, GB, and ensemble), deep learning (CNN, LSTM, CNN+BiLSTM), and transformer-based models (IndicBERT, mBERT, MuRIL, XLM-R) to identify hate speech. Experimental results indicate that the IndicBERT model achieved the highest performance among all other models, obtaining a macro F1-score of 0.6785, which placed the team 6th in the task. © 2025 International Committee on Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Dermatological Disease Detection Using Image Processing and Deep Learning

Dermatological Disease Detection Using Image Processing and ...

引用

2024 IEEE International Conference on Computing, Applications and Systems, COMPAS 2024

作者： Juthi, Nafisha Nower Sabrina Mahi, Tasnima Khan, Safayet Hossain Masrura, Samiha Hossain, Md Jakir Ahnaf Morshed, Md. Reza, Ahmed Wasif Shamsul Arefin, Mohammad East West University Department of Computer Science and Engineering Dhaka Bangladesh Chittagong University of Engineering and Technology Department of Computer Science and Engineering Chittagong Bangladesh

ISBN: (纸本)9798331529765

Skin Disease is now spreading at an alarming rate. People are not aware of different types of skin diseases and for lack of treatment, it is spreading from people to people. In this study, we have tried to make skin disease detection and identification easy and simple with three different convolutional neural network architectures, namely U-Net, VGG19, and MobileNetV2, for the task of skin disease classification. Our objective is to identify the most suitable model that achieves superior accuracy in distinguishing between 7 different types of skin conditions. We have conducted experiments on a skin disease image dataset with corresponding masks. The data was preprocessed and augmented, ensuring good model training. Each architecture went under rigorous training and evaluation, with a focus on achieving high accuracy in disease classification. From our findings U-Net model emerged as the most effective, achieving an impressive accuracy of 93% on the test set. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

TRS Scheduling for Improved QoS Performance in Cloud System

引用

computers, Materials & Continua 2023年第4期75卷 1547-1559页

作者： G.John Samuel Babu M.Baskar Department of Computer Science and Engineering School of ComputingCollege of Engineering and TechnologySRM Institute of Science and TechnologyKattankulathurChengalpattuTamilnadu603203India Department of Computing Technologies School of ComputingCollege of Engineering andTechnologySRM Institute of Science and TechnologyKattankulathurChengalpattuTamilnadu603203India

Numerous methods are analysed in detail to improve task schedulingand data security performance in the cloud environment. The methodsinvolve scheduling according to the factors like makespan, waiting time,cost, deadline, and popularity. However, the methods are inappropriate forachieving higher scheduling performance. Regarding data security, existingmethods use various encryption schemes but introduce significant serviceinterruption. This article sketches a practical Real-time Application CentricTRS (Throughput-Resource utilization–Success) Scheduling with Data Security(RATRSDS) model by considering all these issues in task scheduling anddata security. The method identifies the required resource and their claim timeby receiving the service requests. Further, for the list of resources as services,the method computes throughput support (Thrs) according to the number ofstatements executed and the complete statements of the service. Similarly, themethod computes Resource utilization support (Ruts) according to the idletime on any duty cycle and total servicing time. Also, the method computesthe value of Success support (Sus) according to the number of completions forthe number of allocations. The method estimates the TRS score (ThroughputResource utilization Success) for different resources using all these supportmeasures. According to the value of the TRS score, the services are rankedand scheduled. On the other side, based on the requirement of service requests,the method computes Requirement Support (RS). The selection of service isperformed and allocated. Similarly, choosing the route according to the RouteSupport Measure (RSM) enforced route security. Finally, data security hasgets implemented with a service-based encryption technique. The RATRSDSscheme has claimed higher performance in data security and scheduling.

关键词： Cloud task scheduling TRS quality of service RSM route security data security SDE RATRSDS

来源：评论

学校读者我要写书评

暂无评论

Enhancing Object Detection Robustness in Adverse Weather Conditions 4

Enhancing Object Detection Robustness in Adverse Weather Con...

引用

4th International Conference on Evolutionary Computing and Mobile Sustainable Networks, ICECMSN 2024

作者： Yacoob, Shaik Kumar, D. Phani Harshitha, G.G.S. Teja, V.Y. Sai Veni, C.H. Satya Reddy, K. Mahidhar Department of Computer Science and Engineering Godavari Global University Rajahmahendravaram533296 India Department of Computer Science and Engineering Godavari Institute of Engineering & Technology Rajahmahendravaram533896 India

Fundamental applications in autonomous cars, robots, and surveillance systems include object detection for safety reasons such as recognizing vehicles, pedestrians, trees, street poles, and buildings. However, one of the major challenges it faces from adverse weather conditions like rain, haze, and fog through deterioration of accuracy and an increase in safety risks such as traffic accidents. This paper proposes an enhanced object detection system to improve its robustness and accuracy in challenging environments. The proposed approach effectively addresses the problem of poor image quality due to adverse weather conditions by using unsupervised domain adaptation and including a Quasi-Translation Network and Feature Calibration Network in the YOLO(You Only Look Once) framework. It attempts to leverage the success made in CNNs(Convolutional Neural Networks) and mass amounts of datasets in order to adapt YOLO-series detectors in the best possible way, achieving object detection under challenging environmental conditions with precision and speed. Experimental results demonstrate that the solution proposed outperforms existing models in terms of adaptability and accuracy, providing a scalable and reliable solution for autonomous systems to enhance overall safety and operational efficiency in real-world environments. © 2025 The Authors. Published by Elsevier B.V.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning-Based Method for Classifying Yoga Poses using Deep Convolutional Neural Networks

Transfer Learning-Based Method for Classifying Yoga Poses us...

引用

2023 Innovations in Power and Advanced Computing Technologies, i-PACT 2023

作者： Vallabhaneni, Nagalakshmi Panneer, Prabhavathy Sundaram, Venkatesan Meenakshi School of Computer Science Engineering and Information Systems VIT University Vellore India Department of Computer Science and Engineering National Institute of Technology Puducherry India

ISBN: (纸本)9798350325188

Yoga is a popular practice that aims to improve one's health and well-being through physical postures, breathing exercises, and meditation. The growing popularity of yoga has prompted researchers to focus on automating the process of classifying yoga poses. Using deep convolutional neural networks (CNNs) and transfer learning, we present a deep learning-based method for correctly categorizing yoga postures in this research. The primary goal of this study is to develop an efficient method for automatically recognizing and categorizing yoga poses in given photographs. The impressive success of deep CNNs in picture classification tasks is exploited here to accomplish this goal. We also use transfer learning, a method for customizing pre-trained CNN models for our unique yoga posture categorization task. This paper presents a Transfer Learning based Method for Yoga Poses classification using Deep Convolutional Neural Networks (TLMYPC-DCNN). The proposed model uses the Yoga Posture Dataset for classification of images. Initially, this model starts with pre-processing the input images by splitting input data into three groups such as training set, validation set and test data. The deep learning CNN model will be trained using the training data, and then its parameters will be tweaked using the validation data. Finally, the test data will be used to assess how well the data performs. A convolutional neural network (CNN) model called MobileNetV2 will be applied to the model photos. The experimental results show that the suggested TLMYPC-DCNN based technique with transfer learning is effective at accurately and reliably classifying yoga poses. © 2023 IEEE.

关键词： Deep Convolutional Neural Networks MobileNetV2 Transfer Learning Yoga Pose classification

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：