检索结果-内蒙古大学图书馆

25th International Arab Conference on Information Technology, ACIT 2024

作者： Alazaidah, Raed Nasir, Ola Hadi, Wael Samara, Ghassan Al Daoud, Essam Aljaidi, Mohammad Khouj, Mohammed Talat Elsoud, Esraa Abu Alzoubi, Haneen Zarqa University Faculty of Information Technology Department of Data Science and Ai Zarqa Jordan Zarqa University Faculty of Information Technology Department of Computer Science Zarqa Jordan Petra University Faculty of Information Technology Department of Cyber Security Amman Jordan University of Business and Technology Department of Electrical Engineering Jeddah21432 Saudi Arabia Applied Science Private University Faculty of Information Technology Department of Computer Science Amman Jordan

ISBN: (纸本)9798331540012

Multi-Label Classification (MLC) is an advanced form of traditional classification, where each data instance is simultaneously associated with multiple labels. The importance of MLC has increased significantly in recent years, due to its wide range of application areas. Modern algorithms, when faced with the challenge of multiple labels, continue to show suboptimal performance, conversely, they show significantly superior performance when processing single-label datasets. This paper proposes a new algorithm to deal with the problem of transforming datasets from multiple labels to single labels by exploiting conditional and local correlations between labels after applying the Apriori predictive algorithm to extract relationships. Six ensemble learning models: Voting Hard, Voting Soft, Voting Weighted, Stacking LR, Stacking RF, and Stacking SVM, along with four classification models: SMO, DecisionStump, Random Forest, and Random Committee, were applied to three datasets. The algorithm showed effective and good performance by comparing the results of the proposed Multi Label Classification algorithm based on Conditional Local Correlations among Labels (MLC-CLCL) with several popular algorithms for dealing with multiple labels. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Parameter Tuned Machine Learning Based Emotion Recognition on Arabic Twitter Data

引用

computer Systems science & engineering 2023年第9期46卷 3423-3438页

作者： Ibrahim M.Alwayle Badriyya B.Al-onazi Jaber S.Alzahrani Khaled M.Alalayah Khadija M.Alaidarous Ibrahim Abdulrab Ahmed Mahmoud Othman Abdelwahed Motwakel Department of Computer Science College of Science and ArtsSharurahNajran UniversityNajran55461Saudi Arabia Department of Language Preparation Arabic Language Teaching InstitutePrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Industrial Engineering College of Engineering at AlqunfudahUmm Al-Qura UniversityNajran24211Saudi Arabia Computer Department Applied CollegeNajran UniversityNajran66462Saudi Arabia Department of Computer Science Faculty of Computers and Information TechnologyFuture University in EgyptNew Cairo11835Egypt Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia

Arabic is one of the most spoken languages across the ***,there are fewer studies concerning Sentiment Analysis(SA)in *** recent years,the detected sentiments and emotions expressed in tweets have received significant *** substantial role played by the Arab region in international politics and the global economy has urged the need to examine the sentiments and emotions in the Arabic *** common models are available:Machine Learning and lexicon-based approaches to address emotion classification *** this motivation,the current research article develops a Teaching and Learning Optimization with Machine Learning Based Emotion Recognition and Classification(TLBOML-ERC)model for Sentiment Analysis on tweets made in the Arabic *** presented TLBOML-ERC model focuses on recognising emotions and sentiments expressed in Arabic *** attain this,the proposed TLBOMLERC model initially carries out data pre-processing and a Continuous Bag Of Words(CBOW)-based word embedding *** addition,Denoising Autoencoder(DAE)model is also exploited to categorise different emotions expressed in Arabic *** improve the efficacy of the DAE model,the Teaching and Learning-based Optimization(TLBO)algorithm is utilized to optimize the *** proposed TLBOML-ERC method was experimentally validated with the help of an Arabic tweets *** obtained results show the promising performance of the proposed TLBOML-ERC model on Arabic emotion classification.

关键词： Arabic language Twitter data machine learning teaching and learning-based optimization sentiment analysis emotion classification

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Feature Selection Framework for Predicting Students Performance

引用

computers, Materials & Continua 2022年第1期70卷 1893-1920页

作者： Maryam Zaffar Manzoor Ahmed Hashmani Raja Habib KS Quraishi Muhammad Irfan Samar Alqhtani Mohammed Hamdi High Performance Cloud Computing(HPC3) Department of Computer and Information SciencesUniversiti Teknologi PETRONAS32610SeriIskandarMalaysia Department of Computer Science and Information Technology University of LahorePakistan Department of Process Engineering Pakistan Institute of Engineering&Applied SciencesNiloreIslamabadPakistan Electrical Engineering Department College of EngineeringNajran UniversityNajran61441Saudi Arabia College of Computer Science and Information Systems Najran University61441NajranSaudi Arabia

Student performance prediction helps the educational stakeholders to take proactive decisions and make interventions,for the improvement of quality of education and to meet the dynamic needs of *** selection of features for student’s performance prediction not only plays significant role in increasing prediction accuracy,but also helps in building the strategic plans for the improvement of students’academic *** are different feature selection algorithms for predicting the performance of students,however the studies reported in the literature claim that there are different pros and cons of existing feature selection algorithms in selection of optimal *** this paper,a hybrid feature selection framework(using feature-fusion)is designed to identify the significant features and associated features with target class,to predict the performance of *** main goal of the proposed hybrid feature selection is not only to improve the prediction accuracy,but also to identify optimal features for building productive strategies for the improvement in students’academic *** key difference between proposed hybrid feature selection framework and existing hybrid feature selection framework,is two level feature fusion technique,with the utilization of cosine-based ***,according to the results reported in existing literature,cosine similarity is considered as the best similarity measure among existing similarity *** proposed hybrid feature selection is validated on four benchmark datasets with variations in number of features and number of *** validated results confirm that the proposed hybrid feature selection framework performs better than the existing hybrid feature selection framework,existing feature selection algorithms in terms of accuracy,f-measure,recall,and *** reported in presented paper show that the proposed approach gives more than 90%accuracy on benchmark dataset that is better tha

关键词： Educational data mining feature selection hybrid feature selection

来源：评论

学校读者我要写书评

暂无评论

Development of Virtual Reality Platform through Human computer Interaction using Artificial Intelligence 3

Development of Virtual Reality Platform through Human Comput...

引用

3rd International Conference on applied Artificial Intelligence and Computing, ICAAIC 2024

作者： Saranya, S. Channarayapriya, B. Harshavardhini, U. Nandhini, A.Sunitha Revathi, J. Venkatesan, R. New Horizon College of Engineering Department of Computer Science and Engineering Bangalore India Vel Tech Multi Tech Dr.Rangarajan Dr Sakunthala Engineering College Deparment of Information Technology Chennai India Psg Institute of Technology and Applied Research Department of Computer Science and Engineering Coimbatore India Kongu Engineering College Department of Mathematics Erode India Bannari Amman Institute of Technology Deparment of Information Technology Erode India

ISBN: (纸本)9798350375190

The development of a virtual reality platform through human-computer interaction (HCI) is obtained using deep learning with a genetic algorithm. The human-computer interaction forms a bridge between users and the VR system. This helps in providing a natural interaction experience to the users. Deep learning techniques help in obtaining the realistic nature of the physical world in the virtual platform. The personalized experiences are obtained using the integration of deep learning with VR platforms. The optimization algorithm helps in achieving user interaction in a real-time platform. The adaptive learning helps in increasing the overall immersion with a user-friendly interface. The VR development process is done using a genetic algorithm. This helps to evolve and optimize themselves within the period of time. This helps the VR platform to iteratively improve its performance and complete design through adopting successful combinations of various parameters. The proposed approach helps the VR system to evolve towards an optimal condition. This helps to satisfy the various needs and preferences of the users. Thus the proposed system helps in obtaining adaptive and intelligent virtual environments. This helps in overcoming various challenges in designing immersive VR experiences with personalized digital environments. © 2024 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Learning for Breast Cancer Diagnosis: Evaluating CNN and ANN on BreakHis_v1_400X

Hybrid Deep Learning for Breast Cancer Diagnosis: Evaluating...

引用

2024 International Conference on science, engineering and Business for Driving Sustainable Development Goals, SEB4SDG 2024

作者： Ogundokun, Roseline Oluwaseun Abdullahi, AbdulRahman Tosho Adenike, Ajiboye Raimot Awoniyi, Charles Akande, Hakeem Babalola Falajiki, Funmilola Adedayo-Ajayi, Victoria Landmark University Department of Computer Science Omu Aran Nigeria Kaunas University of Technology Department of Multimedia Engineering Lithuania Kwara State Polytechnic Institute of Information and Communication Technology Department of Computer Science Nigeria Kwara State Polytechnic Institute of Applied Sciences Department of Statistics Nigeria Bupa Insurance Services London United Kingdom Telecommunication Science University of Ilorin Nigeria

ISBN: (纸本)9798350358155

Recent medical research has significantly emphasized the need for early illness diagnosis due to the fast rise of the world's population. Since there are now more people in the world, the danger of dying from breast cancer is rising at an exponential rate. Breast cancer is currently the second deadliest form of cancer out of all the forms that are known. When it comes to illness diagnosis, having access to an automated disease detection system is very helpful to medical professionals since it enables them to provide dependable, effective, and quick reactions while also lowering the mortality rate. This research assesses the hybridization of two deep learning models, a convolutional neural network (CNN) and an artificial neural network (ANN) - the well-known BreakHis_v1_400X dataset (a dataset for breast cancer histopathological images) to work with. The performance of these approaches is evaluated based on several criteria, including accuracy, sensitivity, specificity, precision, false-positive rate, and F1 score. In addition, we evaluate these methods by calculating the area under the curve for accuracy and recall, as well as the receiver operating characteristic curve. According to the findings, the hybridized CNN-ANN achieved the most remarkable accuracy, precision, AUC, and F1 score, with respective values of 89.47%, 86.18%, 89.46%, and 89.08%. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Digital Twins for Photorealistic Event-Based Structural Dynamics 41st

Digital Twins for Photorealistic Event-Based Structural Dyna...

引用

41st IMAC, A Conference and Exposition on Structural Dynamics, 2023

作者： Davis, Allison Walker, Edward Chen, Marcus Felipe, Moises Mascareñas, David Moreu, Fernando Cattaneo, Alessandro Department of Electrical Engineering and Computer Science College of Engineering and Applied Science University of Wyoming LaramieWY United States Department of Mechanical Engineering George R. Brown School of Engineering Rice University HoustonTX United States Department of Electrical and Computer Engineering College of Engineering University of Washington SeattleWA United States Los Alamos National Laboratory Los AlamosNM United States Department of Civil Construction and Environmental Engineering University of New Mexico AlbuquerqueNM United States

ISBN: (纸本)9783031349096

Digital twins are virtual representations of real-world structures that can be used for modeling and simulation. Because of digital twins’ ability to simulate complex structural behaviors, they also have potential for structural health monitoring (SHM) applications. Video-based SHM techniques are advantageous due to the lower installation/maintenance costs, analysis in high-spatial resolution, and its non-contact monitoring features. Both digital twins and video-based techniques hold particular interest in the fields of non-destructive evaluation, damage identification, and modal analysis. An effective use of these techniques for SHM applications still poses several challenges. Neural radiance fields (NeRFs) are an emerging and promising type of neural network that can render photorealistic novel views of a complex scene using a sparse data set of 2D images. Originally, NeRF was designed to capture static scenes, but recent work has extended its capability to capture dynamic scenes which has implications for medium and long-term SHM. However, to date, most NeRFs use frame-based images and videos as input data. Frame-based video monitoring approaches result in redundant information derived from the fact that, for structural dynamics monitoring, only a small number of active pixels record the actual dynamical changes in the structure, resulting in intensive computational loads for data processing and storage. A promising alternative is event-based imaging, which only records pixel-wise changes on the illumination of a scene. Event-based imaging creates a sparse set of data, while accurately capturing the dynamics. The work proposes a method to extract the dynamics of a structure using a generated digital twin. Using Unreal Engine 5, digital twins of rigid and non-rigid structures were generated. The digital twin model was then used along with an event-based camera simulator to generate event-based data. A frequency analysis framework was then developed to extract the

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Learning Approaches for Data Security in Cloud Environments 2

Hybrid Deep Learning Approaches for Data Security in Cloud E...

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Rekha, S. Sharma, Manish Kannan, Sathish Upadhye, Vijay Jagdish Patil, Harshal Rajkumar, S. PSG College of Arts and Science Department of Computer Science Tamil Nadu Coimbatore641 014 India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun248002 India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of VLSI Microelectronics Tamil Nadu Chennai602105 India Parul Institute of Applied Sciences Parul University Research and Development Cell Department of Microbiology Gujarat Waghodia India Computer Science and Engineering Maharashtra Pune412115 India Institute of Technology Hawassa University Faculty of Manufacturing Department of Mechanical Engineering Ethiopia

ISBN: (纸本)9798350327533

More recent studies have concentrated on methods to improve the security and privacy of cloud operations for the benefit of user data. For example, in order to safeguard sensitive data kept by a cloud-deployed procedure, it is important to guarantee secure transmission of sensitive data across multiple stakeholders. Researchers have investigated deeply into the subject of cloud security concerns, which include data breaches, denial of service, data loss, service rejection, and threats from malicious users. These issues typically stem from problems like multi-tenancy, lack of control over data, and trust issues. Cloud providers are primarily responsible for ensuring the security of the cloud platform. This study proposes a CNN-BiLSTM-AM hybrid model that combines Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (Bi-LSTM), and Attention Mechanism (AM). In order to determine how well our proposed hybrid model worked, this study tested it extensively against the traditional CNN and Long Short-Term Memory (LSTM) techniques. An established standard for evaluating intrusion detection systems, the CICIDS 2017 dataset was used in the study. The experimental results demonstrated that the proposed hybrid model outperformed the competition. The proposed hybrid model delivers the highest performance measure of accuracy (99.2%), detection rate (98.807%), and precision (99.59%). © 2024 IEEE.

关键词： Cardiovascular Disease Deep Learning Electrocardiogram Heartbeat Normalization

来源：评论

学校读者我要写书评

暂无评论

Advancements in Control Systems: Sliding Motion Control, Integrating PID Control, and Machine Learning for Precision and Robustness 3

Advancements in Control Systems: Sliding Motion Control, Int...

引用

3rd IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2023

作者： Dawane, Mahendra K. Malwatkar, G.M. Deshmukh, Suhas P. Chouhan, Devendra Govt. College of Engineering Department of Instrumentation Engineering Jalgaon India Govt. College of Engineering Department of Mechanical Engineering Karad India School of Computer Science & It Symbiosis University of Applied Sciences Indore India

ISBN: (纸本)9798350343274

To improve the precision and robustness of control systems, this paper investigates the integration of three different control methodologies: Proportional-Integral-Derivative (PID) control, sliding motion control, and machine learning. The introduction starts by outlining the historical progression of control systems and highlighting their growing significance in contemporary technology. These integrated control strategies are at the centre of the research. The effectiveness of PID control as a solid foundation is first demonstrated through real-world applications and success stories, which provide insights into its principles, advantages, and disadvantages. The next step is to introduce sliding motion control to improve the adaptability of control systems, particularly in handling complex dynamics and uncertainties. It is presented as an addition to PID control, and real-world examples show how adaptable and responsive it is. The importance of machine learning's ability to learn from data and adapt to changing environments is emphasised as the role of machine learning in control systems is thoroughly examined. It is viewed as a tool for performance improvement and optimisation, supported by real-world examples that show the sophistication of control systems. The integration of these three methodologies, emphasising the theoretical underpinnings and methodologies of this approach, forms the core of the research. Through case studies spanning numerous industries, such as industrial automation, robotics, aerospace, and autonomous vehicles, it elaborates on the advantages of such integration, particularly in terms of achieving precision and robustness. © 2023 IEEE.

关键词： Motion control

来源：评论

学校读者我要写书评

暂无评论

Redefining Diagnosis: A Novel Approach to Detect Brain Hemorrhages using Modified Learning Principles with Artificial Intelligence Association 1

Redefining Diagnosis: A Novel Approach to Detect Brain Hemor...

引用

1st International Conference on Innovative Sustainable Technologies for Energy, Mechatronics and Smart Systems, ISTEMS 2024

作者： Ramakrishna G, Naga Venkata Babu, J. Jagan Shankari, R. Dilipkumar, E. Ravi, C.N. Vanaja, T. University of Technology and Applied Sciences-Al Musannah Faculty of Engineering Oman R.M.D Engineering College Department of Ece Tamil Nadu Chennai India Anna University Department of Ece Tamil Nadu Chennai India Dhanalakshmi Srinivasan College of Engineering and Technology Tamil Nadu Chennai India Cmr Engineering College Department of Computer Science and Engineering Hyderabad India Prince Shri Venkateshwara Padmavathy Engineering College Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350384246

Numerous studies have concentrated on developing computer-aided diagnostic methods. They work on the principle of fast and accurate diagnosis by processing and analysis of pictures of various human body parts. In order to determine if a brain haemorrhage is present in Computed Topography (CT) images of the brain, this research follows the aforementioned technique. In addition, the kind of haemorrhage is determined. An AI-assisted prediction scheme, AI-based Brain Haemorrhages Detection (AIBHD), is presented in this paper. In order to determine how well the suggested model works, it is cross-validated with regard to the conventional learning scheme, Random Forest Classifier (RFC). Image preprocessing, segmentation, feature extraction, and classification are some of the steps that make up the developed system. The trials that were carried out yielded really encouraging outcomes. A brain haemorrhage is a form of stroke in which blood clots form in the brain's surrounding tissues as a result of an arterial burst. This method classifies brain haemorrhages using computed tomography (CT) scans. The suggested approach, AIBHD, is used for picture segmentation after preprocessing and morphological procedures. The classification model takes this extracted picture as input and outputs details on the area and percentage of haemorrhage. The results of this study improve the likelihood of identifying haemorrhage in a picture and categorize it accordingly. On average, the system's accuracy in haemorrhage classification is determined to be 97.34%. © 2024 IEEE.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

RAFA-Net: Region Attention Network for Food Items and Agricultural Stress Recognition

IEEE Transactions on AgriFood Electronics

引用

IEEE Transactions on AgriFood Electronics 2025年第1期3卷 121-133页

作者： Bera, Asish Krejcar, Ondrej Bhattacharjee, Debotosh Birla Institute of Technology and Science Department of Computer Science and Information Systems Pilani333031 India University of Hradec Kralove Center for Basic and Applied Science Faculty of Informatics and Management Hradec Kralove50003 Czech Republic Skoda Auto University Mlada Boleslav29301 Czech Republic Universiti Teknologi Malaysia Malaysia Japan International Institute of Technology Kuala Lumpur81310 Malaysia Jadavpur University Department of Computer Science and Engineering Kolkata700032 India

Deep convolutional neural networks (CNNs) have facilitated remarkable success in recognizing various food items and agricultural stress. A decent performance boost has been witnessed in solving the agro-food challenges by mining and analyzing region-based partial feature descriptors. Also, computationally expensive ensemble learning schemes fusing multiple CNNs have been studied in earlier works. This work proposes a region attention scheme for modeling long-range dependencies by building a correlation among different regions within an input image. The attention method enhances feature representation by learning the usefulness of context information from complementary regions. Spatial pyramidal pooling and average pooling pairs aggregate partial descriptors into a holistic representation. Both pooling methods establish spatial and channelwise relationships without incurring extra parameters. A context gating scheme is applied to refine the descriptiveness of weighted attentional features, which is relevant for classification. The proposed region attention network for food items and agricultural stress recognition method, dubbed RAFA-Net, has been experimented on three public food datasets, and has achieved state-of-the-art performances with distinct margins. The highest top-1 accuracy of RAFA-Net is 91.69%, 91.56%, and 96.97% on the UECFood-100, UECFood-256, and MAFood-121 datasets, respectively. In addition, better accuracies have been achieved on two benchmark agricultural stress datasets. The best top-1 accuracies on the Insect Pest (IP-102) and PlantDoc-27 plant disease datasets are 92.36%, and 85.54%, respectively;implying RAFA-Net's generalization capability. © 2023 IEEE.

关键词： Plant diseases

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：