检索结果-内蒙古大学图书馆

3rd International Conference on Advancement in Electrical and Electronic engineering, ICAEEE 2024

作者： Rakibul Hasan, M.M. Kashem, Mohammod Abul Fatin, Md. Al-Abrar Roni, Md. Mainul Islam Bangladesh University of Professionals Department of Information and Communication Technology Dhaka Bangladesh International University of Business Agriculture and Technology Department of Computer Science and Engineering Dhaka Bangladesh Dhaka University of Engineering and Technology Department of Computer Science and Engineering Gazipur Bangladesh

ISBN: (纸本)9798350388282

The current judicial system process, which is conducted manually in Bangladesh, is characterized by a high degree of uncertainty and risk, as well as a wide range of possibilities for fraudulent documents and the preservation of the ownership details of cases. Therefore, the current system does not appear to be feasible, effective. We have created our proposed blockchain-based judicial management system with the SHA-256 data encryption technique. This system will ensure the safety of the case transactions and will be able to store, authenticate, and maintain entire pertinent information of the case document. The mentioned architecture will be able to revoke and to detect attempts to change the case by using a variety of technologies, including IPFS, Proof of Stack (PoS), and public-key cryptography. These techniques will lead to subsequent more efficient solutions than the existing systems and improve how the general public views Bangladesh's judicial system. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Performance Analysis of Evolutionary Algorithms for Automated Design of Autonomous Vehicles

An Enhanced Performance Analysis of Evolutionary Algorithms ...

引用

2024 International Conference on Optimization Computing and Wireless Communication, ICOCWC 2024

作者： Bhambu, Pawan Ganesh, D. Singh, Vaishali Vivekananda Global University Department of Computer Science and Engineering Jaipur India Department of Computer Science and Information Technology Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India

ISBN: (纸本)9798350383348

This paper presents an extensive performance analysis of evolutionary algorithms (EA) used for automated design of autonomous vehicles (AVs). This research explores the algorithms' abilities to generate AV designs that exhibit safe driving behavior and also meet requirements concerning comfort, efficiency and reliability. The assessment of the EA performance is based on the analysis of two design scenarios-corridor driving and intersection crossing. On each of these scenarios, the performance of two distinct evolutionary algorithms was compared against several baselines, including a hand-crafted controller and several other methods from the literature. The results showed that the EA-generated designs outperform the other methods in terms of safety, efficiency and general performance on both of the test scenarios. Furthermore, the assessment revealed some interesting distinctions between both the tested evolutionary algorithms, which could be useful for practitioners and developers of autonomous vehicles. Overall, the results support the conclusion that evolutionary algorithms can be a reliable and effective tool for automated generation of safe and efficient AV designs © 2024 IEEE.

关键词： automated evolutionary hand-crafted literature performance

来源：评论

学校读者我要写书评

暂无评论

Automated Patient Activity Identification in Cyber-physical Systems Using A Unique Deep Learning Approach and Multi-objective Optimization

引用

International Journal of Sensors, Wireless Communications and Control 2023年第5期13卷 339-352页

作者： Bhagwatrao, Gaikwad Rama Lakshmanan, Ramanathan School of Computer Science and Engineering Vellore Institute of Technology Vellore India

Aims and Background: For video understanding and analysis, human activity recognition (HAR) has emerged as a challenging field to investigate and implement. Patients can be monitored in real-time by a group of healthy individuals, and abnormal behaviors can be used to identify them lat-er. Patients who do not engage in customary physical activities are more likely to suffer from stress, cardiovascular disease, diabetes, and musculoskeletal disorders. Thus, it is critical to collect, evaluate, and analyze data to determine their activities. Objectives and Methodology: Deep learning-based convolutional neural networks (CNNs) can be used to solve the problem of patient activities in the healthcare system by identifying the most efficient healthcare providers. Healthcare relies heavily on the integration of medical devices into cyber-physical systems (CPS). Hospitals are progressively employing these technologies to maintain a high standard of patient care. The CNN-CPS technique can be used by a healthcare organization to exam-ine a patient's medical history, symptoms, and tests to provide personalized care. A network of medical devices must be integrated into healthcare. Hospitals are increasingly using these technologies to ensure that patients get the best possible care at all times. Healthcare automation can dramatically improve quality and consistency by reducing human errors and fatigue. The multiobjective optimization is achieved considering various factors like the time required to find emergency case identifica-tion, new disease prediction, and accuracy of data protection. Results: Consequently, patients are assured of receiving a consistent, attentive service at every visit. Data and orders can be stored and entered more easily via automation, market research suggests. The outcome of this article is obtained based on a comparison of various approaches in health monitoring systems, such as collection of patient data is 82.3%, new disease prediction is 80.14%, e

关键词： convolutional neural networks cyber system DL health Patient physical activity

来源：评论

学校读者我要写书评

暂无评论

DualViT: A Hierarchical Vision Transformer for Broad and Fine Class Embeddings 27th

DualViT: A Hierarchical Vision Transformer for Broad and F...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Chatterjee, Ankita Dutta, Sandip Mukhopadhyay, Jayanta Das, Partha Pratim Department of Computer Science and Engineering Indian Institute of Technology Kharagpur Kharagpur India Department of Computer Science Ashoka University Haryana Sonipat India

ISBN: (纸本)9783031781650

Human brains are natural learning systems which inherently recognise image objects in a hierarchical pattern. Similar association exists among different categories of images which interact while training a deep learning model, leading to misclassification and indistinct features. As semantically related classes form clusters in the embedding space, we can list these classes under a single aggregate class, and make the learning faster by leveraging this knowledge while training a model. In this paper, we introduce a hierarchical architecture that simultaneously learns both broad-class and fine-class embeddings using transformer-based encoders. These encoders are trained alternately, and the hierarchical knowledge is encoded through tensor product between the coarse and fine class representations. Our approach has been able to achieve state-of-the-art performance on benchmark datasets with very less epochs. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Personalized Movie Recommendation Based on User Preferences Using Optimized Sequential Transformer Model

Personalized Movie Recommendation Based on User Preferences ...

引用

2024 International Conference on Artificial Intelligence and Emerging technology, Global AI Summit 2024

作者： Ravikumar, R.N. Jain, Sanjay Sarkar, Manash Amity University Rajasthan Dept. of Computer Science and Engineering Jaipur India Atria Institute of Technology Dept. of Computer Science and Engineering Banglore India

ISBN: (纸本)9798350379716

This study explores the application of a Transformer based model to the 'MovieLens 1M' and 'MovieLens 10M' datasets provided by GroupLens, which includes one million and ten movie ratings. The Transformer model, known for its proficiency in handling sequence-to-sequence tasks, employs multi-head self-attention mechanisms and position-wise feed-forward networks. Our implementation, developed in PyTorch, benefits from its capacity for automatic differentiation and GPU acceleration, which significantly enhances the training efficiency. The model underwent rigorous hyperparameter tuning and optimization to adapt optimally to the characteristics of the dataset. Performance evaluation using the Normalized Discounted Cumulative Gain (NDCG) metric demonstrates that the Transformer model substantially outperforms a conventional popular recommendation system across various top-K rankings. Specifically, for the MovieLens 1M dataset, the Transformer model achieved NDCG scores of 0.0455, 0.0805, 0.0995, and 0.1273 at top 1, 3, 5, and 10, respectively. Comparatively, the popular recommendation system scored 0.0023, 0.0044, 0.0061, and 0.0091 at these same rankings. This trend of superior performance by the Transformer model is also consistent across the MovieLens 10M dataset, further confirming its effectiveness in ranking highly relevant items at the top of the list. Also, to address quality and utility of recommendations, MAP, Precision, Recall, F1 Score, Coverage and Serendipity metrics evaluated. These results underscore the effectiveness of Transformer models in extracting and leveraging complex patterns in sequence data, demonstrating a clear superiority over traditional methods in recommendation systems. This study highlights the potential of deep learning architectures to revolutionize fields reliant on understanding user preferences and sequential data interactions. © 2024 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Designing an AI driven intelligent Tutorial System 5

Designing an AI driven intelligent Tutorial System

引用

5th IEEE International Conference on Recent Trends in computer science and technology, ICRTCST 2024

作者： Alam, Shamsher Kumar, Surjeet Khursheed, Zeeshan Mahato, Hemant Kumar Bashar, Shadan Suman, Anjali R.V.S College of Engineering & Technology Computer Science and Engineering Jamshedpur India Government Engineering College Sheikhpura Computer Science and Engineering Bihar India Jio Platform Limited DGM Mumbai India NSHM Master of Computer Application Durgapur India R.V.S College of Engineering & Technology Master of Computer Application Jamshedpur India R.V.S College of Engineering & Technology Computer Science & Engineering Student Jamshedpur India

ISBN: (纸本)9798350351378

With the fast-evolving field of education, there is an increase in the demand for intelligent tutorial systems that can adapt to the diverse learning needs of individual students. This research paper explores the design and implementation of an AI-driven Intelligent Tutorial System (ITS) aimed at enhancing the personalized learning experience. The system leverages advanced machine learning algorithms to dynamically adjust instructional content, pace, and assessments based on real-time analysis of individual student performance and preferences. The paper delves into the key components of the proposed ITS, including adaptive learning models, natural language processing capabilities for interactive communication, and data-driven decision-making mechanisms. Emphasis is placed on the seamless integration of AI technologies to create an intuitive and responsive educational *** considerations in the development and deployment of the intelligent tutorial system are discussed, addressing issues related to data privacy, algorithmic bias, and the role of human oversight. The paper also highlights the collaborative potential between AI and human educators, emphasizing the system's capacity to support rather than replace teaching professionals. Through a combination of theoretical frameworks and practical examples, the research examines the potential impact of the AI-driven ITS on student engagement, learning outcomes, and the overall educational experience. Case studies and pilot implementations are presented to illustrate the system's efficacy in diverse educational *** research contributes to the ongoing discourse on AI in education by providing insights into the design principles, implementation challenges, and ethical considerations associated with developing an intelligent tutorial system. The findings aim to inform educators, policymakers, and technologists about the potential of AI to revolutionize personalized learning and contribute to the ong

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Dynamic Program Slicing of Agent-oriented Software 2

Dynamic Program Slicing of Agent-oriented Software

引用

2nd International Conference for Innovation in technology, INOCON 2023

作者： Mishra, Alina Kabat, M.R. Mohapatra, D.P. Veer Surendra Sai University of Technology Department of Computer Science and Engineering India National Institute of Technology Department of Computer Science and Engineering India

ISBN: (纸本)9798350320923

Slicing programs is an essential aspect of program development and maintenance. Because numerous statements might be discarded in the procedure of locating a bug, dynamic program slicing approaches are commonly utilized for debugging. Only the statements that have a consequence on the variable are included in a dynamic program slice with regard to that variable. Agent-oriented programming is a novel paradigm which uses agents as their basic entity. Agents are defined as an object which achieves an explicit action in an atmosphere known to it and responds to the variations. In this paper, a different approach for computation of relevant slices in agent-oriented programs is presented. We have taken a single-agent program as our working example. First, we have developed an intermediate representation for the agent-oriented program. Then, we have developed an algorithm based on dependencies among the nodes in the graph to compute slices. © 2023 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Optimizing Lettuce Crop Growth Modeling with XGBoost-SVM and Gaussian Process Regression Fusion 8th

Optimizing Lettuce Crop Growth Modeling with XGBoost-SVM and...

引用

8th International Conference on Inventive Communication and Computational Technologies, ICICCT 2024

作者： Rukumani Khandhan, C. Gothai, E. Kanagaraju, P. Rajkumar, S. Seenivasan, D. Anusurya, R. Department of Computer Science and Engineering Kongu Engineering College Erode Perundurai638060 India Department of Computer Science and Engineering Sri Shanmugha College of Engineering and Technology Salem India Department of Computer Science and Engineering K.S. Rangasamy College of Technology Namakkal Tiruchengode637 215 India Department of Computer Science and Business Systems M. Kumarasamy College of Engineering Karur639113 India Department of Computer Technology-PG Kongu Engineering College Tamil Nadu Perundurai638060 India

ISBN: (纸本)9789819777099

Agriculture plays a pivotal role in ensuring food security and sustainable development. Accurate prediction of crop growth and yield is essential for optimizing agricultural practices and resource allocation. This study presents an integrated approach employing various machine learning techniques to predict crop growth, exemplified by a dataset of 70 plant samples. The dataset includes environmental factors such as temperature, humidity, soil composition, and pH levels, as well as temporal information like growth days. The dataset goes through a thorough preprocessing step that includes resolving missing values, eliminating duplicates, and, encoding categorical variables. To make sure that every variable contributes equally to the models, feature scaling approaches like Z-score standardization and Min–Max scaling are used. The probabilistic outputs of the SVM and XGBoost models are combined in an ensemble technique to improve prediction accuracy. This fusion strategy utilizes the strengths of each model and reduces individual model biases. In addition to classification models, Gaussian Process Regression (GPR) is utilized to provide probabilistic crop growth predictions. GPR offers a continuous output that can be used for yield estimation and uncertainty quantification. Model performance is evaluated using evaluation measures including R-squared (R2), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE). These measures offer information on the precision, accuracy, and capacity of the models to explain crop growth variance. This work suggests using Gaussian Process Regression, a machine learning technique, to improve the outcomes of crop growth monitoring for lettuce in aeroponic vertical farming systems. Compared to previous models, this one generates higher prediction results of 0.99% and has lower error rates of 0.32 (MSE), 0.56 (RMSE), and 0.20 (MAE). It is also very resilient to outliers. © The Author(s), under exclusive license to Springer Nature Singa

关键词： Crop rotation

来源：评论

学校读者我要写书评

暂无评论

Feature Techniques with a Custom Convolutional Model for Breast Tumor Surveillance in Mammograms 3rd

Feature Techniques with a Custom Convolutional Model for Bre...

引用

3rd International Conference on Trends in Electronics and Health Informatics, TEHI 2023

作者： Mahmud, Md. Tanim Islam, Md. Shamiul Yasar, Samin Rahman, Md. Saifur Department of Computer Science and Engineering Bangladesh University of Business and Technology Dhaka1216 Bangladesh

ISBN: (纸本)9789819739363

The most occurring cancer worldwide is breast cancer in which abnormal breast cells grow and form tumors. If left unchecked, it can be more fatal and can spread throughout the body. Globally, 2.3 million cases have been diagnosed and there were 685,000 fatalities in 2020, according to the World Health Organization (WHO). To overcome the fatalities, an early diagnosis is the best approach. Manual diagnosis is not an easy process for this cancer, using mammography images, and always requires an expert person. In this paper, we have used a VGG16-based model to eradicate the feature from the intermediate layers and concatenate the intermediate layers. Then, we used a Convolutional Neural Network (CNN) to train the feature and predict the accuracy and classification. We have evaluated our performance analysis with confusion matrix analysis, ROC curve analysis, and other methods. In our results, we have accomplished an accuracy of 94% among the datasets. Comparing our suggested framework to state-of-the-art (SOTA) technology demonstrates that it increased accuracy, and additional study may enable it to be enhanced to decrease false positives and false negatives in screening mammography findings. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Gender Classification from Fingerprint Using Hybrid CNN-SVM

引用

Journal of Artificial Intelligence and technology 2024年第1期4卷 82-87页

作者： J.Serin Keren T.Vidhya I.S.Mary Ivy Deepa V.Ebenezer A.Jenefa Department of Information Technology Women’s Christian CollegeChennaiIndia Department of Computer Science and Engineering Women’s Christian CollegeChennaiIndia Department of Computer Science and Engineering Karunya Institute of Technology and SciencesCoimbatoreIndia

Gender classification is used in numerous applications such as biometrics,criminology,surveillance,HCI,and business *** biometric factors like gait,face,hand shape,and iris have been used to classify people into genders,the majority of research has focused on facial traits due to their more recognizable *** research employs fingerprints to classify gender,with the intention of being relevant for future *** methods for gender classification utilizing fingerprints have been presented in the literature,including ANN,KNN,Naive Bayes,the Gaussian mixture model,and deep learning-based *** these classifiers have shown good classification accuracy,gender classification remains an unexplored field of study that necessitates the development of new approaches to enhance recognition accuracy,computation,and running *** this paper,a CNN-SVM hybrid framework for gender classification from fingerprints is proposed,where preprocessing,feature extraction,and classification are the three main *** main goal of this study is to use CNN to extract fingerprint *** features are then sent to an SVM classifier to determine *** hybrid model’s performance measures are examined and compared to those of the conventional CNN *** a CNN-SVM hybrid model,the accuracy of gender classification based on fingerprints was 99.25%.

关键词： digital image processing fingerprint gender classification hybrid CNN-SVM hybrid model pattern recognition

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：