检索结果-内蒙古大学图书馆

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Kamma, Vidya Wbaid, Saef Sudhakar, K. Nisha, A. Saravanan, T. Neil Gogte Institute of Technology Department of Computer Science and Engineering Rangareddy Hyderabad India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute of Technology Department of Artificial Intelligence and Data Science Bengaluru India Dhanalakshmi Srinivasan College of Engineering and Technology Department of Computer Science and Engineering Mamallapuram India New Prince Shri Bhavani College of Engineering and Technology Department of Electronics and Communication Engineering Chennai India

ISBN: (纸本)9798331529246

In recent years, toxic comment detection evolved as important in detecting hatred and harmful content present in user-generated content. However, a few challenges are raised in detecting toxic comments like context sensitivity and missing toxic content. To overcome these issues, improved Bi-directional Long Short-Term Memory (Bi-LSTM) is proposed for toxic comment detection. Initially, data is preprocessed with lemmatization and stop words removal methods for converting the texts to its base form and eliminates the common words respectively. Then, the Word to Vector (Word2Vec) technique converts the words into a dense vector representation by capturing semantic relationships and contextual meanings. Finally, improved Bi-LSTM is employed for detecting the toxic comments by capturing both past as well as future context with its bidirectional architecture and focuses on important words within the context dynamically. From the results, proposed Improved Bi-LSTM model attained better outcomes in terms of accuracy (acc) of 94.32%, precision (pr) of 98.07%, and recall of 95.98% compared to existing Convolutional Neural Networks (CNN)-BiLSTMs. © 2025 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Developing a multi-user virtual reality training system for emergency medical technicians: Determinants of acceptance and adoption

引用

Educational technology and Society 2025年第2期28卷 416-433页

作者： Chen, Shih-Yeh Lai, Ying-Hsun Lin, Pei-Hsuan Su, Yu-Sheng Department of Engineering Science National Cheng Kung University Taiwan Department of Computer Science and Information Engineering National Taitung University Taiwan Department of Information Management National Taichung University of Science and Technology Taiwan Department of Computer Science and Information Engineering National Chung Cheng University Taiwan Advanced Institute of Manufacturing with High-tech Innovations National Chung Cheng University Taiwan Department of Computer Science and Engineering National Taiwan Ocean University Taiwan

There is an increasing international focus on multi-user virtual reality (VR) training for all emergency medical technicians within the framework of their respective disaster medical preparedness initiatives. While multiuser VR is often deployed in a variety of digital educational settings, it has not been meaningfully explored in emergency medicine. This study was conducted to fill this research gap by developing a multi-user VR training system for the donning and doffing procedures associated with Level C protective gear. Furthermore, the current investigation also considered the determinants influencing whether emergency medical technicians are willing to adopt and accept multi-user VR training courses via conceptualizing the extended unified theory of acceptance and use of technology. An empirical survey was conducted involving 80 emergency medical technicians in the eastern region of Taiwan to evaluate their experiences with the multi-user VR system. The data were analyzed using Partial Least Squares Structural Equation Modeling, and the results showed that performance expectancy, social impact, facilitating conditions, price value, and habit significantly influenced emergency medical technicians’ readiness to adopt multi-user VR training courses. Moreover, performance expectancy, facilitating conditions, and behavioral intention emerged as pivotal determinants of course adoption. However, effort expectancy and hedonic motivation did not exert a significant influence on adoption behavior. The findings of the study have important theoretical and practical implications. © (2024), (International Forum of Educational technology and Society). All Rights Reserved.

关键词： Behavioral intention Emergency medical preparedness Extended unified theory of acceptance and use of technology (UTAUT 2) Multi-user virtual reality Virtual environment for emergency medical technicians

来源：评论

学校读者我要写书评

暂无评论

Proposing an Advanced Trending-based Grey Wolf Optimizer for Single-objective Optimization Problems 20

Proposing an Advanced Trending-based Grey Wolf Optimizer for...

引用

20th CSI International Symposium on Artificial Intelligence and Signal Processing, AISP 2024

作者： Mokabberi, Amirhossein Golsorkhtabaramiri, Mehdi Varzi, Ramzan Abbasnezhad Mazandaran University of Science and Technology Department of Computer Engineering Babol Iran Islamic Azad University Babol Branch Department of Computer Engineering Babol Iran

ISBN: (纸本)9798350383942

optimization algorithms play a crucial role in solving complex problems in various domains. Single-objective optimization algorithms aim to discover the most optimal solution for a particular objective function, commonly distinguished by a single criterion or goal. Grey Wolf optimizer (GWO) is a swarm-based algorithm that has gained attention due to its simplicity and efficiency in solving optimization problems. In this article, we propose an advanced version of GWO, which is referred to as the Advanced Trending-based Grey Wolf optimizer (ATGWO), specifically tailored for single-objective optimization problems. The motivation behind this modification stems from the need to improve the performance metrics of the original GWO algorithm and avoid local optimum. By altering the algorithm's coefficients, we aim to enhance its convergence rate, exploration, and exploitation abilities. To evaluate the proposed ATGWO algorithm, we conduct simulations using 7 multimodal single-objective benchmark functions. The results suggest that although the ATGWO excels in accuracy, it has more delay in comparison with GWO. This study paves the way for future research about optimization algorithms. © 2024 IEEE.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

EfficientNetB7-Based Deep Learning for Skin Lesion Classification 8

EfficientNetB7-Based Deep Learning for Skin Lesion Classific...

引用

8th IEEE International Conference on Computational System and Information technology for Sustainable Solutions, CSITSS 2024

作者： Ramesh, Shreya Yuktha, B.N. Chaitra, M. Santosh Reddy, P. Anitha, N. Bnm Institute of Technology Affiliated to Vtu Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798331505462

Skin cancer ranks among the most prevalent types of cancer worldwide. For the purpose of giving effective treatment to the patients, it has to be treated in its initial stages. This study introduces Skin Lesion Classification using deep learning techniques with EfficientNetB7. It is trained on the ISIC 2020 Challenge dataset. Data preprocessing included organizing image file paths and labels, followed by data augmentation with Image Data Generator. The EfficientNetB7 model has been pre-trained on ImageNet. It was fine-tuned with additional BatchNormalization, Dense, and Dropout layers. After five epochs of training, the model demonstrated high accuracy in classifying various skin lesions, as evidenced by the validation and test results. Our project's findings emphasize the model's potential as a dependable automated system for detecting skin cancer, assisting dermatologists in early diagnosis and treatment. To enhance our work, we can consider hyperparameter tuning, advanced data augmentation, and enlarging the dataset for enhanced model generalizability. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Capacitor voltage unbalance minimization for three-phase five-level diode-clamped inverter using hexagonal hysteresis space vector modulation

引用

MULTISCALE AND MULTIDISCIPLINARY MODELING EXPERIMENTS AND DESIGN 2024年第2期7卷 661-671页

作者： Ramkumar, R. Singh, Manmohan Ramkumar, R. Usha, S. Thentral, T. M. Thamizh Department of Electrical and Electronics Engineering SRM Institute of Science and Technology Chengalpattu India Department of Computer Engineering and Application GLA University Mathura India Department of Electrical and Electronics Engineering School of Engineering and Technology Dhanalakshmi Srinivasan University Trichy India Department of Renewable Energy University of Maroua National Advanced School of Engineering of Maroua Maroua Cameroon

This article suggests a method for diminishing the voltage unbalance in a three-phase five-level diode-clamped inverter (DCI) through the use of hexagonal hysteresis space vector modulation (HHSVM). Capacitor voltage balancing leads to enhanced system efficiency, reduced stress on components, enhanced performance, abridged electromagnetic interference, and reduced total harmonic distortion. The proposed modulation technique and its implementation are thoroughly examined in this study, along with modeling and experiment data that show how efficient the method is at lowering the capacitor voltage unbalance in the proposed five-level DCI. Capacitor voltage unbalance is reduced with the use of this HHSVM approach to 0.95%, which is a superior reduction compared to traditional PWM methods. The paper also discusses the advantages of the proposed method over other existing methods, making it a promising solution for practical applications in power electronics systems.

关键词： Diode-clamped inverter (DCI) Capacitor voltage balancing Hexagonal hysteresis space vector modulation (HHSVM) Total harmonic distortion

来源：评论

学校读者我要写书评

暂无评论

Performance Improvement of Model View Controller based Applications through Linda's-Key

Performance Improvement of Model View Controller based Appli...

引用

2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication, IConSCEPT 2023

作者： Suhas Reddy, P. Anala, Jayanth Krishnamurthy, Vallidevi Balasubramanian, Surendiran Sujithra Kanmani, R. School of Computer Science and Engineering Vellore Institute of Technology Chennai India School of Computer Science and Engineering Vellore Institute of Technology Vellore India National Institute of Technology Puducherry Department of Computer Science and Engineering India

ISBN: (纸本)9798350312126

The Model-View-Controller (MVC) design pattern is widely used in software engineering for developing user interfaces. While MVC offers many benefits, handling data in a way that is efficient and effective can be a challenge. One approach to optimising the performance of MVC applications is converting lists to dictionaries. This paper discusses the benefits and drawbacks of this approach and presents the findings of recent research on this topic. The main advantage of converting lists to dictionaries is that it can improve the performance of MVC applications by offering faster access times and making code easier to read and maintain. However, there are drawbacks to this approach, such as increased memory usage and slower performance for certain operations. Several studies have been conducted on the performance of MVC applications when using lists versus dictionaries, with varying results. This paper overviews this research and highlights the implications for MVC development. © 2023 IEEE.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

The Analysis of AI Based Algorithms in Personalized and Adaptive E-learning Experiences 2

The Analysis of AI Based Algorithms in Personalized and Adap...

引用

2nd IEEE International Conference on IoT, Communication and Automation technology, ICICAT 2024

作者： Kumar, Ajay Srivastava, Shashank Buddha Institute of Technology Department of Computer Science & Engineering UP Gorakhpur273209 India

ISBN: (纸本)9798350368109

The integration of Artificial Intelligence (AI) into e-learning systems has heralded a new era of personalized and adaptive learning experiences. This comprehensive review delves into the latest advancements and implications of AI in e-learning. By harnessing machine learning algorithms, natural language processing techniques, and predictive analytics, AI-powered e- learning systems provide personalized content delivery, adaptive assessments, and intelligent tutoring capabilities. Additionally, this review examines how AI enhances learner engagement, improves learning outcomes, and tackles the challenges of scalability and accessibility in education. It also addresses ethical considerations, challenges, and future directions for AI-based e-learning, underscoring the transformative potential of AI in shaping the future of education. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Predicting Diseases of Mango Leaves Using ResNet50 and CNN 5

Predicting Diseases of Mango Leaves Using ResNet50 and CNN

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Ramya, Chimakurthi Himasree, Talluri Fathimunnisa Bhavyasri, Kummari Shareefunnisa, Syed Vignan's Foundation for Science Technology and Research Department of Computer Science and Engineering India Vignan's Foundation for Science Technology and Research Department of CSE India

ISBN: (纸本)9798331530013

Mango leaf disease presents a significant challenge to mango trees worldwide, with untreated infections leading to severe leaf damage and potential tree mortality. Early detection is crucial to mitigating the effects of these diseases and preventing their spread. Our dataset includes 4,000 images categorized into eight classifications of mango leaf diseases, with 3,200 images for training and 800 for validation. This study employs a Convolutional Neural Network (CNN) Transfer Learning Model, specifically ResNet50, trained with carefully tuned hyperparameters to achieve an accuracy of 97%. This innovative approach significantly reduces the time and effort required for traditional inspections, offering a precise and automated solution for disease detection. By improving diagnosis and supporting sustainable farming practices, this research contributes to the development of scalable solutions for managing mango crops effectively. © 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

A Double Layer Encryption for Communication using Cryptographic Algorithms 2

A Double Layer Encryption for Communication using Cryptograp...

引用

2nd International Conference on Emerging Trends in Information technology and engineering, ic-ETITE 2024

作者： Ragavan, K. Mohankumar, B. Vivekrabinson, K. Arun, R. Arumuga School of Computer Science and Engineering Vellore Institute of Technology Vellore India Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Tamilnadu Krishnankoil India

ISBN: (纸本)9798350328202

Cryptography is a fundamental field in computer science that focuses on securing communication and protecting sensitive information from unauthorized access. It involves the use of mathematical algorithms and techniques to transform plaintext into ciphertext, rendering it unintelligible to anyone without the proper decryption key. Cryptographic systems play a crucial role in ensuring confidentiality, integrity, and authenticity of data in various domains, including finance, healthcare, e-commerce, and communication networks. In this paper, a double-layer encryption method is proposed that uses the Vigenere and Polybius ciphers to secure communication. The Vigenere cipher is a classical method that uses a keyword to encrypt plaintext, while the Polybius cipher is another classical cipher that uses a grid to map letters to two-digit numbers to encrypt data. By combining these two ciphers, the proposed algorithm aims to enhance the security of the data by introducing a more complex and secure encryption method. The proposed method is implemented using Python programming language with web implementation. The web implementation of the algorithm uses Flask, a Python web framework. This allows users to encrypt and decrypt their data through a user-friendly interface, making it more accessible and practical for real-world use. Based on the obtained results demonstrate that the proposed method provides a higher level of security compared to using each cipher individually, without significantly impacting the encryption and decryption speed. Overall, the proposed double-layer encryption method can be a useful tool for secure communication in various applications. It contributes to the field of cryptography by introducing a novel approach that enhances data security without compromising usability. © 2024 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Neurodegenerative disease detection using Artificial Intelligence

Comparative Analysis of Neurodegenerative disease detection ...

引用

2024 International Conference on Knowledge engineering and Communication Systems, ICKECS 2024

作者： Vidya, J. Yendapalli, Vamsidhar Gitam University Gitam School of Technology Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350359688

Neurodegeneration is one of the features of several debilitating diseases that are rising rapidly. As they are not curable and progressive, early detection may help the patients and the caretakers to maintain a good quality of life. Advancements in computational methods have made it possible to diagnose and classify NDD (neurodegenerative diseases) using the automated procedure, which will be more effective than manual detection. This paper aims to comprehensively describe the neurodegenerative disease classification using ML and DL techniques that may help the community working on early detection of the disease. © 2024 IEEE.

关键词： Contrastive Learning

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：