检索结果-内蒙古大学图书馆

2023 International Conference on Sustainable Communication Networks and Application, ICSCNA 2023

作者： Sathia Priya, M. Shamna Parveen, S. Saravanan, S. Kalaivani, R. Karpagam Institute of Technology Department of Electronics and Communication Engineering Coimbatore India Dhanalakshmi Srinivasan College of Engineering Department of Computer Science and Engineering Coimbatore India Karpagam Academy of Higher Education Department of Artificial Intelligence and Data Science Coimbatore India Sri Krishna College of Technology Department of Artificial Intelligence and Data Science Coimbatore India

ISBN: (纸本)9798350313987

The role of education is of paramount importance in influencing the cognitive development of future generations. This paper presents a novel IoT-based Behavioural Analysis (IoT -BA) Model for Smart Learning integrated with neural network technology. The Internet of Things (IoT) enables educational institutions to perform management tasks more quickly and risk- freely by analyzing organized data and acquiring insights from it to inform decisions. The significance of teaching college students in the self-directed application of effective learning strategies has evolved with various trending digital twin frameworks. The proposed IoT -BA model can collect the motion features and facial expressions of the students from the classroom video while attending classes through self-learning applications. The collected images can then be preprocessed using augmentation and a local binary pattern approach. This deep-preprocessed data has been passed to the deep learning algorithm convolutional neural network (CNN) that is trained with the preprocessed data for classification. Spatiotemporal feature extraction and selection from the preprocessed data can be performed using the preprocessing algorithm principal component analysis (PCA). The student's attention level classification for the IoT -BA uses the CNN algorithm. This experimental research uses the real-time data collected by setting the classroom environment for model training and validation. The CNN model has been trained with the data collected from the environment using the simulation platform TensorFlow and performs five-cross-validation with the realistic data. The IoT -BA model can predict the student's attention level in the classroom based on the collected features from the classroom video. The simulation results of the CNN -based IoT -BA model showed better performance in terms of 96.42% classification accuracy and a minimal error rate of 1.82%. © 2023 IEEE.

关键词： Behavioral Analysis Classroom CNN Smart Learning Spatiotemporal Features Student Attention

来源：评论

学校读者我要写书评

暂无评论

Optimal trained ensemble of classification model for satellite image classification

引用

Multimedia Tools and Applications 2025年第7期84卷 3745-3766页

作者： Singh, Sarabjeet Kundra, Harish Kundra, Sheetal Pratima, P. Venkata Devi, M. V. Anjana Kumar, Sushil Hassan, Mariya Department of Computer Science and Engineering Chandigarh College of Engineering and Technology Chandigarh160019 India Department of Computer Science and Engineering Guru Nanak Institutions Technical Campus Ranga Reddy District Telangana Ibrahimpatnam501506 India Department of Artificial Intelligence and Data Science Guru Nanak Institute of Technology Ranga Reddy District Telangana Ibrahimpatnam501506 India Department of Computer Science and Engineering Central University of Haryana Jant-Pali Mahendergarh123031 India

Satellite image classification is the most significant remote sensing method for computerized analysis and pattern detection of satellite data. This method relies on the image's diversity structures and necessitates a thorough validation of the training data using the chosen classification algorithm. The classifying of remotely sensed images refers to the process of classifying pixels into a fixed set of distinct classes based on their data values. The pixel is categorized into that class if it complies with a specific set of requirements. A new SIC scheme is suggested in this work, where, Contrast limited adaptive histogram equalization (CLAHE) is deployed for pre-processing the image. Further, statistical features, Vegetation Indices (VI) and Improved Hybrid Vegetation Index (IHVI) are extracted from the preprocessed image. Then, we deploy 2 phase classification process for classifying the image. In the first phase, Bi-Directional Gated Recurrent Unit (BI-GRU), Convolutional Neural Network (CNN) and Deep Max Out (DMO) are used. In 2nd phase, optimized RNN is used for determining the final classification result. Also, the training of the model is done by the new Chaotic Opposition Behavior Improvised Coot Algorithm (COBI-CA) optimization via tuning the optimal weights. The COOT method has been enhanced and is now the suggested algorithm. Lastly, we conduct an analysis to compare the suggested Satellite Image Classification (SIC) model's performance to the traditional approaches in terms of statistical analysis, precision, accuracy, and error measure. In comparison to other conventional methods, the accuracy of the suggested model is 97%. © This is a U.S. Government work and not under copyright protection in the US;foreign copyright protection may apply 2024.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Navigation Assistance for the Visually Impaired: An Image Segmentation-based Web Application

Navigation Assistance for the Visually Impaired: An Image Se...

引用

17th INDIACom;2023 10th International Conference on Computing for Sustainable Global Development, INDIACom 2023

作者： D'Mello, Sejal Prajapati, Vivek Vyas, Hirenkumar Arora, Naveen Mishra, Arpit Vidyavardhini's College of Engineering and Technology Dept. of Artificial Intelligence and Data Science Mumbai India

ISBN: (纸本)9789380544472

The objective of this paper is to create a mobile app that can aid visually impaired people in navigating outdoor surroundings through floor segmentation technique. The app uses phone's camera to capture live video of the user's environment, which will be analyzed to identify and segment the floor area. As a result, the user will be able to obtain audio information regarding their location and distance from nearby objects or obstacles. This proposed system is a practical and low-cost solution that can be effortlessly incorporated into existing smartphone technology, providing an easy-to-use and accessible tool for the visually impaired to navigate through outdoor environments. © 2023 Bharati Vidyapeeth, New Delhi.

关键词： Floors

来源：评论

学校读者我要写书评

暂无评论

The optimal scaling factor based on Secant Method for image watermarking using the hybrid DTCWT-DCT domain.

Iraqi Journal for Computer Science and Mathematics

引用

Iraqi Journal for Computer science and Mathematics 2024年第1期5卷 237-262页

作者： Lebcir, Mohamed Awang, Suryanti Benziane, Ali Faculty of Computing Universiti Malaysia Pahang Al-Sultan Abdullah Pahang Pekan26600 Malaysia Center of Excellence for Artificial Intelligence & Data Science Universiti Malaysia Pahang Al-Sultan Abdullah Lebuh Persiaran Tun Khalil Yaakob Pahang Kuantan26300 Malaysia Faculty of Science and Technology University of Djelfa Algeria

This paper proposes an implementation of the secant optimization method on the watermark embedding in DTCWT domain. An objective function combining PSNR and NC (The Normalized Correlation) values calculated for a set of common attacks is used in the optimization process. The aim is to enhance the tradeoff between robustness and imperceptibility against the various image processing attacks via an automatic and careful selection of the scaling factor using optimization. The watermark is inserted in the high energy bands of DCT-transformed sub-vectors, which were generated from the DTCWT coefficient decomposition of the host image. Experimental results performed on a set of 512×512 greyscale images, show better results than the existing schemes for most common image attacks such as compression, low-pass filtering and noise addition. © 2024 College of Education, Al-Iraqia University. All rights reserved.

关键词： Image watermarking

来源：评论

学校读者我要写书评

暂无评论

A Novel CAD Framework with Visual and Textual Interpretability: Multimodal Insights for Predicting Respiratory Diseases 8

A Novel CAD Framework with Visual and Textual Interpretabili...

引用

8th International artificial intelligence and data Processing Symposium, IDAP 2024

作者： Mukhlis, Raza Saleem, Saied Kwon, Hyunwook Hussain, Jamil Aydin, Ahmet Arif Al-Antari, Mugahed A. Sejong University College of Ai Convergence Department of Artificial Intelligence and Data Science Seoul05006 Korea Republic of Inonu University Faculty of Engineering Department of Computer Engineering Malatya Turkey

ISBN: (纸本)9798331531492

Generating textual interpretability using recent advancements in large language models (LLMs) is crucial for enhancing the efficiency of comprehensive computer-aided diagnosis (CAD) systems. This improves transparency between medical staff, intelligent CAD systems, and end-users by creating a trustworthy and effective intermediate medical diagnosis environment. In this paper, an innovative explainable throughout CAD system is introduced, designed to predict diseases from Chest X-rays (CXR) in a comprehensive scenario. The primary goal is to undertake multiple tasks that reduce the burden on medical staff and enrich CAD outcomes, including classification, visual explanations (heatmaps), and textual report generation. The proposed CAD system is developed through eight key steps: data Collection and Annotation, data Preparation, Text Vectorizations (Indexing), Visual Encoder, RAG-Fusion, Structural Prompt, XAI LLmTextual Reasoning (LLM Model), and Final Output (LLM textual report, image classification, and heatmap localization). The AI-based CAD system is trained and evaluated using the public benchmark MIMIC-CXR dataset with 14 different classes. The classification performance achieved an overall accuracy of 70 %, precision of 70 %, and F1-score of 0.60 %, while for text report generation, the system obtained an average BERTScore precision of 0.83, RougeL 0.16, and a Meteor score of 0.28. These promising results suggest the potential for further improvement of the CAD system and its applicability to real-world medical tasks. © 2024 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Uncovering the Hidden Insights of the Government AI Readiness Index: Application of Fuzzy LMAW and Schweizer-Sklar Weighted Framework

Decision Making: Applications in Management and Engineering

引用

Decision Making: Applications in Management and engineering 2024年第2期7卷 443-468页

作者： Nasution, Mahyuddin K. M. Elveny, Marischa Pamucar, Dragan Popovic, Milena Gušavac, Bisera Andric Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan20155 Indonesia Data Science & Artificial Intelligence Fasilkom-TI Universitas Sumatera Utara Medan20155 Indonesia University of Belgrade Faculty of Organizational Science Department of Operations Research and Statistics Jove Ilica 154 Belgrade Serbia Department of Mechanics and Mathematics Western Caspian University Baku Azerbaijan School of Engineering and Technology Sunway University Selangor Malaysia

There is considerable promising in artificial intelligence (AI) and algorithms, with governments worldwide increasingly investing in this transformative technology. The potential benefits include improved performance, cost reduction, efficient management, and crime prediction and prevention, among others. The AI era holds the promise of revolutionizing various aspects of society. However, as countries prepare to leverage the power of artificial intelligence, questions arise about the validity of rankings published on the readiness of the governments for the application of AI. In this article, the weighting criteria that are analysed in the Oxford Insights AI Readiness Index are scrutinized, aiming to provide a more accurate assessment. Instead of conventional averaging, arithmetic and geometric non-linear functions are employed to analyse and assess the rank of the countries. Through clustering analysis, countries are categorized into three distinct groups based on observed criteria, offering a nuanced perspective on government AI readiness. This clustering approach not only facilitates a more effective categorization of countries based on their AI preparedness, but also accentuates the variations and similarities within each cluster, which enables deeper insights into regional trends and pinpoint targeted strategies for enhancement within each cluster. © 2024 Regional Association for Security and crisis management. All rights reserved.

关键词： Cost reduction

来源：评论

学校读者我要写书评

暂无评论

Toxicity Unveiled: Understanding Online Conversations

Toxicity Unveiled: Understanding Online Conversations

引用

2024 International Conference on Electrical, Electronics and Computing Technologies, ICEECT 2024

作者： Patil, Ratna Kulkarni, Swapneel Ingole, Prajwal Kumar, Pratiyush Pawar, Sandesh Rawandale, Shiltalkumar Vishwakarma Institute of Information Technology Department of Artificial Intelligence and Data Science Maharashtra Pune India Pimpri Chinchwad College Of Engineering Department of Mechanical Engineering Maharashtra Pune India

ISBN: (纸本)9798350378092

Internet forums enable people to express their opinions and participate in discussions on a range of subjects in the current digital era. But sometimes, this right to free speech can lead to the dissemination of harmful remarks like hate speech, harassment, and other types of damaging material. Ensuring a secure and courteous online space requires identifying and eliminating remarks that are harmful. This research article investigates many approaches to detecting poisonous comments, including classic machine learning techniques like BOW and TF-IDF, and deep learning methods like LSTM. In addition, we explore the performance of stochastic gradient descent (SGD) regressor and decision tree models in categorizing harmful remarks using these variables. Through rigorous research and review, we show that these approaches are effective at recognizing hazardous remarks. Our findings help to build strong models for automated toxic comment detection, promoting healthier online discourse. © 2024 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Numerical Simulation of Deterioration Process in Reinforced Concrete Based on COMSOL Multiphysics

Numerical Simulation of Deterioration Process in Reinforced ...

引用

2023 International Conference on Applied Mechanics and Physics

作者： Li, Gen Wang, Chenggong Jiang, Minghui Li, Lin Wang, Ruiqi College of Artificial Intelligence and Big Data Guangdong Vocational and Technical University of Business and Technology Guangdong China College of Materials Science & Engineering Beijing University of Technology Beijing China

Reinforced concrete is deteriorated by chloride attack and dry-wet cycles to suffer serious durability problems. Reinforced concrete degradation typically occurs in two distinct stages: initially through chloride erosion, followed by the electrochemical corrosion of rebars. In this research, COMSOL Multiphysics was employed to model how various crack widths impact the degradation of reinforced concrete. Findings indicated that the deterioration process of reinforced concrete could be better simulated by COMSOL Multiphysics, and the degradation of reinforced concrete was significantly influenced by crack widths. As crack widths widen, chloride diffusion accelerated, leading to a rise in the corrosion current density of rebars. Notably, a crack width increased from 0.1 mm to 0.4 mm resulted in a 227.53% higher corrosion current density in rebars after 150 days of exposure. This study provides a theoretical basis for predicting reinforced concrete deterioration in the future. © Published under licence by IOP Publishing Ltd.

关键词： Reinforced concrete

来源：评论

学校读者我要写书评

暂无评论

Predicting Agricultural Crop Damage Caused by Unexpected Rainfall Using Deep Learning

Predicting Agricultural Crop Damage Caused by Unexpected Rai...

引用

Intelligent Systems for Cybersecurity (ISCS), International Conference on

作者： Bhushan Fulkar Pawan Patil Gaurav Srivastav Promod Mahale Department of Artificial Intelligence and Data science Faculty of Engineering and Technology Wardha Maharashtra India Artificial Intelligence and Data science Faculty of Engineering and Technology DMIHER(DU) Wardha Maharashtra India Department of Artificial Intelligence and Machine Learning Faculty of Engineering and Technology DMIHER(DU) Wardha Maharashtra India

ISBN: (数字)9798350375237

ISBN: (纸本)9798350375244

Efficient allocation of resources and timely agricultural interventions depend on the precise identification of crop loss at the field parcel level. Using recent data from 2018 to 2023, this study investigates the integration of deep learning techniques with real-time field photography to classify agricultural field parcels into those experiencing crop loss and those not. We build and assess deep learning models specifically for crop loss classification using a dataset from the Finnish Food Authority (FFA) that combines on-the-ground photos taken during field visits with comprehensive field parcel information. In this work, we use convolutional neural networks (CNNs) to examine the visual characteristics that we have extracted from field photos in order to identify the subtleties that may indicate crop health or possible loss. Our goal is to improve the model's generalization capabilities over a variety of crop types and agricultural landscapes by training it on a combination of field parcel data and corresponding photographs.

关键词： Deep learning Training Visualization Uncertainty Rain Crops Real-time systems

来源：评论

学校读者我要写书评

暂无评论

GACL-Net:Hybrid Deep Learning Framework for Accurate Motor Imagery Classification in Stroke Rehabilitation

引用

Computers, Materials & Continua 2025年第4期83卷 517-536页

作者： Chayut Bunterngchit Laith H.Baniata Mohammad H.Baniata Ashraf ALDabbas Mohannad A.Khair Thanaphon Chearanai Sangwoo Kang State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing100190China School of Computing Gachon UniversitySeongnam13120Republic of Korea Computer Science Department Faculty of Information TechnologyThe World Islamic Sciences and Education UniversityAmman11947Jordan Intelligent Systems Department Faculty of Artificial IntelligenceAl-Balqa Applied UniversityAl-Salt19117Jordan IT Infrastructure Department Qatrana Cement CompanyAmman11821Jordan Division of Industrial and Logistics Engineering Technology Faculty of Engineering and TechnologyKing Mongkut’s University of Technology North BangkokRayong CampusRayong21120Thailand

Stroke is a leading cause of death and disability worldwide,significantly impairing motor and cognitive *** rehabilitation is often hindered by the heterogeneity of stroke lesions,variability in recovery patterns,and the complexity of electroencephalography(EEG)signals,which are often contaminated by *** classification of motor imagery(MI)tasks,involving the mental simulation of movements,is crucial for assessing rehabilitation strategies but is challenged by overlapping neural signatures and patient-specific *** address these challenges,this study introduces a graph-attentive convolutional long short-term memory(LSTM)network(GACL-Net),a novel hybrid deep learning model designed to improve MI classification accuracy and ***-Net incorporates multi-scale convolutional blocks for spatial feature extraction,attention fusion layers for adaptive feature prioritization,graph convolutional layers to model inter-channel dependencies,and bidi-rectional LSTM layers with attention to capture temporal *** on an open-source EEG dataset of 50 acute stroke patients performing left and right MI tasks,GACL-Net achieved 99.52%classification accuracy and 97.43%generalization accuracy under leave-one-subject-out cross-validation,outperforming existing state-of-the-art ***,its real-time processing capability,with prediction times of 33–56 ms on a T4 GPU,underscores its clinical potential for real-time neurofeedback and adaptive *** findings highlight the model’s potential for clinical applications in assessing rehabilitation effectiveness and optimizing therapy plans through precise MI classification.

关键词： Motor imagery EEG stroke rehabilitation deep learning brain-computer interface

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：