检索结果-内蒙古大学图书馆

Exploring the Integration of Generative AI in Modern Education Systems: A Comprehensive Analysis

Exploring the Integration of Generative AI in Modern Educati...

2024 International Conference on Artificial Intelligence and Quantum Computation-Based Sensor Applications, ICAIQSA 2024

作者： Dey, Avick Kumar Chauhan, Vineet Kumar Singh, Pradeep Kumar Sarkar, Ananya Dept. of Computer Applications West Bengal Durgapur India Galgotias College of Engg. & Tech Dept. of Information Technology Greater Noida India School of Computer Science and Engineering Galgotias University Greater Noida India DSMS College of Tourism and Management Dept. of Computer Applications West Bengal India

ISBN: (纸本)9798331517953

This paper aims at filling this gap through dissecting the applicability of the Generative AI in the current learning and teaching system. The paper offers an introduction to Generative AI technologies: GPT and DALL-E, and describes the chronological history and current progress of its educational applications. Other objectives include discussing about the uses of Generative AI in adaptive learning environment, smart learning systems, automation of organizational work and in talented minds improvement. Analyzing key successful AI cases, the paper reveals the challenges implementers encountered, and provides debates about the appropriate practices of AI. Research evidence points to the prospect of Generative AI benefiting students and educators in teaching and learning, which indicates the innovative potential of the technology, yet at the same time reveals the potential risks and challenges that need to be addressed concerning the ethical and privacy implications of Generative AI in education. Others may follow general recommendations for policymakers and educators on how to integrate artificial intelligence responsibly, as well as future work for this quickly burgeoning domain. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Designing Blockchain Based Consensus Mechanism for Smart Healthcare IoT

Designing Blockchain Based Consensus Mechanism for Smart Hea...

引用

2023 IEEE International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2023

作者： Kumari, Trishla Kumar, Rakesh Dwivedi, Rajendra Kumar Madan Mohan Malviya University of Technology Dept. of Computer Science and Engineering Gorakhpur India Madan Mohan Malviya University of Technology Dept. of Information Technology and Computer Application Gorakhpur India

ISBN: (纸本)9781665462631

In today's world, healthcare system is improving day by day by using smart IoT based system. Blockchain based system is totally a decentralized system due to which attackers are unable to access the confidential records easily. Blockchain play an important role in controlling and management of sensitive information in healthcare system and insurance sector. Consensus mechanisms used in blockchain technology to validate whichever block is going to be added next in the blockchain network. In this paper we proposed a hybrid based system which solves trust issues arises in the blockchain. Hybrid consensus mechanism provides reputation according to the activities of blocks in a blockchain network. Four layer architecture is designed in Hybrid model. Five algorithms are used to create, validate, fork handling, reward and punishment scheme and Markle tree is constructed respectively. This model is implemented on Ethereum based platform which shows that HCM model is better than a PoXR model as it consume less memory (50 percent) and consume less CPU(below 2 percent). © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Prediction of Cardiac Arrest using Generalized Soft Computing Techniques 18

Prediction of Cardiac Arrest using Generalized Soft Computin...

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Hota, Radhanath Dash, Sachikant Mishra, Sujogya Das, Subhalaxmi Lenka, S. Pradhan, G. Giet University Department of Computer Science Engineering Odisha Gunupur India Gandhi Institute for Education and Technology Department of Computer Science Engineering Odisha Gunupur India Odisha University of Technology and Research Department of Mathematics Bhubaneswar India Odisha University of Technology and Research Dept. of Computer Science and Engineering Bhubaneswar India Utkal University Department of Computer Science and Application Bhubaneswar India

ISBN: (纸本)9789380544519

Cardiac-related diseases always lead to fatal consequences around the globe. This research includes vague data analysis of the data related to cardiac anomalies. This study proposes a method to develop a dimension reduction model using vague data related to cardiac diseases using rough set theory (RST). The overall research is divided into two different sections. The first section of this study proposes analyses of the raw cardiac-related data using RST, and the second section calculates the performance accuracy using Principal Component Analysis (PCA) applied to the universal data set;the performance measures also include a combination of two Universal data sets. The above claims are verified using statistical tests © 2024 Bharati Vidyapeeth, New Delhi.

关键词： PCA Performance and accuracy Rough Set Theory Statistical method Vague data

来源：评论

学校读者我要写书评

暂无评论

BIDS: Blockchain and Intrusion Detection System Coalition for Securing Internet of Medical Things Networks

引用

IEEE Journal of Biomedical and Health Informatics 2023年 PP卷 1-9页

作者： Gupta, Karan Gupta, Koyel Datta Kumar, Devender Srivastava, Gautam Sharma, Deepak Kumar Department of Information Technology Netaji Subhas University of Technology New Delhi India Department of Computer Science and Engineering Maharaja Surajmal Institute of Technology New Delhi India Dept. of Math and Computer Science Brandon University Canada Department of Information Technology Indira Gandhi Delhi Technical University for Women Delhi India

The benefits of the Internet of Medical Things (IoMT) in providing seamless healthcare to the world are at the forefront of technological advancement. However, security concerns of any IoMT systems are high since they threaten to compromise personal information of patients and can even cause health hazards. Researchers are exploring the use of various techniques to ensure a high level of security of IoMT systems. One key concern is that the computing power of any Internet of Things (IoT) device is relatively low, hence mechanisms that require low computational power are appropriate for designing Intrusion Detection Systems (IDS). In this research work, a blockchain IDS coalition is proposed for securing IoMT networks and devices. The blockchain ledger is compact and uses less processing resources. Additionally, the ledger requires less communication overhead. The cryptographic hashes in the suggested architecture ensure complete data secrecy and integrity between parties who are trusted and those who are untrustworthy. Peer-to-peer networks in both central and cluster networks are also included in this work for complete decentralization. The proposed model can counter various attacks, including Denial of Service (DoS), anonymity attacks, impersonation attacks, Man-In-The-Middle (MITM), and Cross-Site Scripting (XSS). The proposed method achieved an F1- score as high as 100% and reported an AUC value of over 99%. IEEE

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Anti-Aliased Convolutional with Data Augmentation for Speech Emotion Recognition

Anti-Aliased Convolutional with Data Augmentation for Speech...

引用

2025 IEEE International Conference on Consumer Electronics, ICCE 2025

作者： Le, Linh-Chi Le, Hoai-Bao Le, Phuong Thi Wang, Jia-Ching Dept. Computer Science and Information Engineering National Central University Taiwan Dept. Computer Science and Information Engineering Fu Jen Catholic University Taiwan

ISBN: (纸本)9798331521165

In this work, we propose a comprehensive framework for speech emotion recognition that combines advanced data augmentation techniques and an innovative deep learning architecture to enhance model performance. Our data augmentation strategies, including noise addition, time stretching, pitch shifting, and time shifting, significantly diversify the training dataset, leading to improved generalization and robustness against real-world variations in speech. We introduce a novel deep learning model architecture based on Anti-Aliased Convolutional (AA-Conv1D) layers, which preserves spatial hierarchies and enhances the model's ability to capture fine-grained emotional nuances in speech signals. Experimental results demonstrate that our model outperforms state-of-the-art methods, achieving a weighted accuracy of 79.38%, which surpasses the performance of existing models, SepTr + LeRaC and EMix-NS. © 2025 IEEE.

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Recognition of American sign language using modified deep residual CNN with modified canny edge segmentation

引用

Multimedia Tools and Applications 2025年 1-28页

作者： Hariharan, U. Devarajan, Devikanniga Kumar, P. Santhosh Rajkumar, K. Meena, M. Akilan, T. Department of Computer Science and Engineering Apex Institute of Technology Chandigarh University Punjab Mohali140413 India Department of Computer Science and Engineering GITAM University Karnataka Bengaluru561203 India Department of Information Technology Faculty of Engineering and technology SRM Institute of Science and Technology Ramapuram Tamil Nadu Chennai600089 India Department of Data Science and Business Systems School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chennai603203 India Department of Computer Science and Engineering Sri Sairam Engineering College Tamil Nadu Tambaram602109 India Research Coordinator Dept. of IQAC Amity University Kolkata West Bengal 700135 India

American Sign Language (ASL) recognition aims to recognize hand gestures, and it is a crucial solution to communicating between the deaf community and hearing people. However, existing sign language recognition algorithms still have some drawbacks, such as difficulty recognizing hand movements and low recognition accuracy for most sign language recognition. A Modified Convolutional Neural Network (MCNN) deep residual 101 classifier-based American Sign Language identification system has been developed to address this problem. There are three main parts presents in the method. The first part is pre-processing the images to remove the noise, enhance the contrast of the picture, adjust the contrast level and smoothen the picture using various filters. The second part is the segmentation, and it’s used to partition the image using a modified canny edge detection method by removing all weak edges present in the image. Finally, classification will be done using the Modified CNN deep residual 101 classifiers. By classifying the image, the American Sign Language is accurately identified. This process is conducted through images. The outcome shows that the suggested approach has a 0.97% accuracy and a 0.05% False Positive Rate. Other CNN architectures such as resNet 50 and resNet 18 reached 0.90% and 0.80% accuracy, respectively, which is lower than our proposed method. In addition, the resNet 101 classifier effectively recognizes the difficult hand gestures through the image data. It obtains high recognition accuracy for 36 signs is 0 to 9 numbers and a to z alphabets from American Sign Language. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Reliability Measures in Neutrosophic Soft Graphs

引用

Neutrosophic Sets and Systems 2022年 49卷 239-252页

作者： Anirudh, A. Kannan, R. Aravind Sriganesh, R. Sundareswaran, R. Kumar, S. Sampath Shanmugapriya, M. Broumi, Said Dept. of Computer Science Sri Sivasubramaniya Nadar College of Engineering India Dept. of Electrical and Electronics Engineering. Sri Sivasubramaniya Nadar College of Engineering India Dept. of Mathematics Sri Sivasubramaniya Nadar College of Engineering India Laboratory of Information Processing Faculty of Science Ben M'Sik University Hassan II B.P 7955 Sidi Othman Casablanca Morocco

This paper introduces the concept of reliable nodes in neutrosophic soft graphs by evaluating path-based parameters. A reliable node is defined as one which is least susceptible to changes that are quantized by the indeterminacy and falsity values in a neutrosophic tuple. A new path measure called farness and three novel reliability measures which make use of the same are presented. Farness is defined in terms of a novel score function. The first, proximity reliability of a node, computes the farness of a node to its neighbours. The second, intermediate reliability of a node, computes the fraction of paths of minimal farness that pass through it. The third, crisis reliability of a node, is a hybrid of the two previously defined. It considers the farness of a node to its neighbours taking into account the farness of the neighbours to other nodes in the graph. © 2022. All Rights Reserved.

关键词： Reliability

来源：评论

学校读者我要写书评

暂无评论

Anti-Aliased Convolutional with Data Augmentation for Speech Emotion Recognition

Anti-Aliased Convolutional with Data Augmentation for Speech...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Linh-Chi Le Hoai-Bao Le Phuong Thi Le Jia-Ching Wang Dept. Computer Science and Information Engineering National Central University Taiwan Dept. Computer Science and Information Engineering Fu Jen Catholic University Taiwan

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

关键词： Deep learning Training Emotion recognition Accuracy Convolution Speech recognition Speech enhancement Data augmentation Data models Robustness

来源：评论

学校读者我要写书评

暂无评论

GridShield: A Robust Fall-Back Control Mechanism for Congestion Management in Distribution Grids

GridShield: A Robust Fall-Back Control Mechanism for Congest...

引用

2022 IEEE PES Innovative Smart Grid Technologies Conference Europe, ISGT-Europe 2022

作者： Tangerding, F. Varenhorst, I.A.M. Hoogsteen, G. Gerards, M.E.T. Hurink, J.L. University of Twente Dept. of Electrical Engineering Mathematics and Computer Science Enschede Netherlands

ISBN: (数字)9781665480321

ISBN: (纸本)9781665480321

The growing number of electric vehicles (EVs) in the low-voltage distribution grid increases the load and thereby the risk of overloading and damaging grid assets. Since energy management systems designed for controlling electric vehicle charging can fail, e.g. due to cyber attacks or failure of communication systems, a robust fall-back control mechanism is required to prevent congestion and overloading problems in the grid. This paper presents three variants of such fall-back control mechanisms and evaluates them using a simulation of a Dutch neighbourhood. Comparison of the three strategies with respect to power limit violations and energy not served to EVs shows that all strategies significantly reduce power limit violations, while the energy not served is less than 21% of the energy served in the base case without control. The AIAD (additive increase, additive decrease) and AIMD (additive increase, multiplicative decrease) strategies achieve similar reductions of total power limit violations, 84.1% and 84.6% respectively, while an optimized PID based controller performs considerably worse with 55.9%. © 2022 IEEE.

关键词： Electric vehicles

来源：评论

学校读者我要写书评

暂无评论

Matched Mode Processing with Phase-Difference Weighting for Underwater Acoustic Source Localization

Matched Mode Processing with Phase-Difference Weighting for ...

引用

2023 MTS/IEEE U.S. Gulf Coast, OCEANS 2023

作者： Ye, Yun Zheng, Yahong Rosa Gerstoft, Peter LaGuardia Community College at City University of New York Dept. of Mathematics Engineering & Computer Science New York City United States Lehigh University Dept. of Electrical and Computer Engineering Bethlehem United States University of California San Diego Dept. of Electrical and Computer Engineering La Jolla United States

ISBN: (纸本)9798218142186

Matched Field Processing (MFP) and its derivative Matched Mode Processing (MMP) estimates similarity between in-situ measurement and the model-based replica to identify source locations from an array of received signals. The similarity is evaluated in an ambiguity function using magnitude and phase of mode coefficients in the received signal. While phase is vulnerable to noises and interference, we find that the phase-difference between signals from adjacent receivers proves to be more robust. We propose to use phase difference as a weighting factor in MMP to select sensors in the space domain and the snapshots in the time domain. The consistency of phase difference in the replica and the measured data is demonstrated with a real experimental data set. Two MMP methods, the singular-value decomposition method and the smallest regularization method, are compared with and without the proposed phase-difference sensor and snapshot selection. The results demonstrate improved sidelobe effect and range detection using the phase-difference selection. © 2023 The Marine Technology Society (MTS).

关键词： Underwater acoustics

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：