检索结果-内蒙古大学图书馆

8th International Conference on Intelligent Technologies, ICIT 2023

作者： Kyaw, Nwe Ni Mitra, Pabitra Sinha, G.R. Department of Computer Science and Engineering Indian Institute of Technology Kharagpur West Bengal721302 India Indian Knowledge System Lab International Institute of Information Technology Bangalore Karnataka Bengaluru560100 India

ISBN: (纸本)9789819738588

The proposed system for recognizing Myanmar sign language between individuals who are deaf. The aim of this study is to develop deep learning models for the purpose of accurately identifying dynamic hand gesture images depicting 14 classes of Myanmar words and numbers. The present system utilizes a new dataset comprising 7834 images for 14 classes obtained through Webcam. The objective of this study is to enhance the robustness of the new model. Next, we proceed to evaluate the proposed model by comparing them to those of existing convolutional neural network models. These models are generally recognized as effective deep-learning approaches for recognition tasks. The proposed model exhibits a performance level of 96% for both validation and testing accuracies. Furthermore, the experimental finding demonstrates that the model, convolutional layers, achieved an accuracy of 100% in recognizing Myanmar Sign Language (MSL). © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Effective Emotion Recognition Method Using Facial and Speech Features 3

An Effective Emotion Recognition Method Using Facial and Spe...

引用

3rd International Conference on Smart Technologies in Computing, Electrical and Electronics, ICSTCEE 2022

作者： Muthumanickam, K. Mahesh, P.C.Senthil Vijayalakshmi, P. Department of Information Technology Tamilnadu Thottiyam India Excel Engineering College Department of Computer Science and Engineering Tamilnadu Komarapalayam India Knowledge Institute of Technology Department of Computer Science and Engineering Tamilnadu Salem India

ISBN: (纸本)9781665456647

In face-To-face conversations, facial expressions help humans communicate nonverbally. Since the early 1990s, academics' focus on automatic facial expression detection, which is essential for human-machine interfaces, has grown. Traditional machine learning techniques can demand a difficult feature extraction procedure and yield subpar results. Using current developments in deep learning, we present efficient deep Convolutional Neural Networks (CNNs) that can automatically and accurately evaluate the semantic information contained in faces and speech without manually defining feature descriptors. Additionally, in order to develop an effective CNNs based emotion recognition system with a high degree of classification capability, we employ various loss functions and training techniques. The experimental results demonstrate that, the proposed method outperforms existing solutions in terms of performance and makes it ideal for real-Time systems. © 2022 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

MKGL: Mastery of a Three-Word Language 38

MKGL: Mastery of a Three-Word Language

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Guo, Lingbing Bo, Zhongpu Chen, Zhuo Zhang, Yichi Chen, Jiaoyan Lan, Yarong Sun, Mengshu Zhang, Zhiqiang Luo, Yangyifei Li, Qian Zhang, Qiang Zhang, Wen Chen, Huajun College of Computer Science and Technology Zhejiang University China ZJU-Ant Group Joint Lab of Knowledge Graph China Ant Group China Department of Computer Science The University of Manchester United Kingdom School of Computer Science and Engineering Beihang University China School of Computer Science Beijing University of Posts and Telecommunications China School of Software Technology Zhejiang University China

Large language models (LLMs) have significantly advanced performance across a spectrum of natural language processing (NLP) tasks. Yet, their application to knowledge graphs (KGs), which describe facts in the form of triplets and allow minimal hallucinations, remains an underexplored frontier. In this paper, we investigate the integration of LLMs with KGs by introducing a specialized KG Language (KGL), where a sentence precisely consists of an entity noun, a relation verb, and ends with another entity noun. Despite KGL's unfamiliar vocabulary to the LLM, we facilitate its learning through a tailored dictionary and illustrative sentences, and enhance context understanding via real-time KG context retrieval and KGL token embedding augmentation. Our results reveal that LLMs can achieve fluency in KGL, drastically reducing errors compared to conventional KG embedding methods on KG completion. Furthermore, our enhanced LLM shows exceptional competence in generating accurate three-word sentences from an initial entity and interpreting new unseen terms out of KGs. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Approaches to Securing Multi-Cloud Architectures: Best Practices and Emerging Solutions 7

Comprehensive Approaches to Securing Multi-Cloud Architectur...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Nair, Raveena R Sreevidya, D. Mohan, Chinnem Rama Banerjee, Joydeep Chouhan, Kuldeep Dharamvir Saveetha School of Law Chennai India and Ai & Ds Hyderabad India Narayana Engineering College Nellore Department of Computer Science and Engineering Andhra Pradesh India Nshm Knowledge Campus Durgapur West Bengal Kolkata India Sharda School of Engineering and Technology Department of Computer Science Applications Uttar Pradesh Greater Noida India The Oxford College of Engineering Department of Mca Bommanahalli Karnataka Bengaluru India

ISBN: (纸本)9798350350067

With an emphasis on multi-cloud networks, this research paper offers a synopsis of cloud computing techniques. It covers the fundamentals of cloud programming, the difficulties that cloud computing faces, and the ways that multi-cloud systems, such as cloud hybridization, federation clouds, cross-clouds, and multi-clouds, might help solve these problems. The opportunity of multi-cloud structures in combination with modern technologies such as Big Data and also Machine Learning (ML) is explored as well in the study, leading to some fascinating breakthroughs. To assist researchers, grasp the difficulties and generate enthusiasm within the community for the upcoming pairing of multi-cloud services with additional cutting-edge technologies, the aim is to present a contemporary perspective on multi-cloud technology and solve outstanding concerns. © 2024 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

2.5D ASF-UNet: Adjacent Slice Spatial Feature Fusion Model for WMH Segmentation from 3D MR Brain Image

2.5D ASF-UNet: Adjacent Slice Spatial Feature Fusion Model f...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Huang, Lan Sun, Yinglu Zhao, Ziqi Guo, Chunjie Wang, Yan College of Computer Science and Technology Jilin University Key Laboratory of Symbol Computation and Knowledge Engineering Ministry of Education Changchun China The First Hospital of Jilin University Department of Radiology Changchun China

ISBN: (纸本)9798350386226

Segmenting brain white matter hyperintensities (WMH) from 3D Magnetic Resonance (MR) images is crucial for the diagnosis, treatment, and prognosis of Multiple Sclerosis (MS). Unlike common 2D images, this task is more challenging and time-consuming. Classical deep learning methods for 3D image segmentation face two main challenges: 1) Pure 3D networks have more parameters and are prone to overfitting. 2) When using 2D networks to segment slices of 3D images, the lack of 3D structural information results in suboptimal segmentation after reconstruction. To address these difficulties, we propose the 2.5D ASF-UNet, which employs the 2.5D workflow and uses adjacent slices as the input for 2D segmentation network ASF-UNet. In ASF-UNet, separate down-sampling paths are used for the adjacent slices, and the Local Spatial Attention Module (LSAM) is designed to more effectively integrate 3D spatial information into the 2D network. Additionally, the Conv-Spectral-Block (CSB) is designed to extract and integrate local and global features. It allows the model to capture global spatial structures while preserving detailed information. Experimental results on MICCAI MSSEG 2016 and Local MS datasets show that 2.5D ASF-UNet achieve better segmentation performance than other deep learning methods. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Ensemble methods-based comparative study of Landsat 8 operational land imager (OLI) and sentinel 2 multi-spectral images (MSI) for smart farming crop classification

引用

Multimedia Tools and Applications 2025年第17期84卷 18025-18068页

作者： Gupta, Priyanka Gupta, Prateek Singh, Suraj Kumar Thakur, Bhavna Kumar, Manoj Suresh Gyan Vihar University Jaipur India School of Computer Science Engineering and Technology Bennett University Greater Noida India Department of Centre for Sustainable Development Suresh Gyan Vihar University Jaipur India School of Agriculture & Allied Science DBS Global University Dehradun India School of Computer Science FEIS University of Wollongong in Dubai Dubai Knowledge Park Dubai United Arab Emirates MEU Research Unit Middle East University Amman Jordan

Agriculture has a significant worldwide impact in terms of generating employment opportunities and stimulating economic growth. In India, agriculture plays a crucial role in development of food sources, boost up individual income of farmer and employment of the whole country. In the agriculture domain, meticulous machine learning-enabled crop classification is essential for production. Nowadays, for meticulous crop classification satellite images are used together with Geographical Information System (GIS) and remote sensing. Proposed ensemble methods are commonly used to estimate and examine the accomplishment of advanced machine learning concepts in the remote sensing community. In this paper, authors describe a framework with the combination of Support vector machine (SVM), Decision tree (DT), K-nearest neighbor (KNN), and Random forest (RF) and proposed ensemble method named as "SVM-DT-KNN-RF" that investigates the potential of crop mapping used to compare different architectures of machine learning as logistic regression (LR), RF, DT, KNN, SVM, bagging as well as boosting. The classifiers are tested on two remotely sensed datasets, one is Landsat 8 OLI (L8) and another is Sentinel 2 MSI (S2). The three primary findings based on our experiments are first, voting model proved to be the most accurate classifier. Second, bagging and boosting offer good accuracy in classification results. Finally, the results with two satellites i.e., S2 as well as L8 are compared. In the S2 dataset, the proposed ensemble method with a combination of two models i.e., SVM-DT, SVM-KNN and SVM-RF gave 89.1%, 89.8% and 89.7% results respectively, and the combination of four models i.e., SVM-DT-KNN-RF (for voting) is the better performer with 91.10% accuracy. In the L8 dataset, the proposed ensemble method which combines all four techniques SVM-DT-KNN-RF gave better results with a score of 90% while the worst performance was achieved by the decision tree with 79.58% accuracy. For KNN, th

关键词： Landsat

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of RPL Protocol Under Decreased and Increased Rank Attacks: A Focus on Smart Home Use-Case

引用

SN computer science 2023年第4期4卷 329页

作者： Bang, Ankur Rao, Udai Pratap Knowledge Associate Centre for Development of Advanced Computing (C-DAC) Maharashtra Mumbai 400049 India Computer Science and Engineering Department National Institute of Technology Bihar Patna 800005 India

The rank value of a node in Routing Protocol for Low Power and Lossy Networks (RPL) plays a significant role in preventing loops and route optimization. Advertising a fake rank value creates a false topology and can degrade network performance to a great extent. This manuscript aims to study the effects of increased and decreased variants of the rank attack on the RPL performance. We consider a smart home network topology to evaluate the RPL performance, and the simulation experiments are performed using the Cooja simulator. Through this study, we portray a rational analysis and discuss how the network performance can be degraded by each variant of the rank attack and the position of the attacker node in the network topology. The simulation results obtained in our work demonstrate how each variant of the rank attack can disrupt the default RPL working. We notice significant effects of both the studied rank attacks on the crucial parameters like packet overhead, average inter-packet time, packet delivery ratio and average power consumption. Researchers working in this field can take advantage of our research findings and extend their study to develop new defence mechanisms against these attacks. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： IoT Performance evaluation Rank attack RPL Smart home

来源：评论

学校读者我要写书评

暂无评论

Augmented Reality based Smart Surgical Glass for Medical Surgery 14

Augmented Reality based Smart Surgical Glass for Medical Sur...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Sudha, S. Ponmurugan, P. Kamatchi Kannan, V. Russia, S. Rohith Bhat, C. Kavin Kumar, K. Velalar College of Engineering and Technology Department of BiomedicalEngineering Tamilnadu Erode India Chennai600078 India Knowledge Institute of Technology Department of Electrical and Electronics Engineering Salem India Velalar College of Engineering and Technology Department of Computer Science and Engineering Erode Thindal India Simats Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Kongu Engineering College Department of Electronics and Communication Engineering Erode Perundurai638060 India

ISBN: (纸本)9798350335095

Surgeons are always looking for technologies to make their working environment better. They frequently take the lead in implementing innovations that help their industry deliver better surgical and patient experiences. The ongoing advancement of the surgical environment in the digital era has resulted in several breakthroughs being observed as possible disruptive technologies in the surgical work place As augmented reality (AR) grows in popularity, availability, and cost, it is critical to evaluate how technology might be leveraged to better utilize medical data in healthcare. Applications in surgical anatomy, surgical processes, and surgical recovery are being researched all the time. The use of computer-generated sensory input to improve performance on a specific task is referred to as "augmented reality". A technique that combines the view of the real world with important information for doctors displayed on semi-transparent glasses attached to an augmented reality headset. For this investigation, sensors are being utilized to monitor patients in a hospital and gather data in real time. The data is then processed by a computer and delivered immediately to the augmented reality glasses used by doctors. The alarm on these spectacles notifies doctors if something is wrong. Taking the patient's current state of health into account, the physician is able to make wise decisions and carry out the necessary procedures. © 2023 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Privacy Analysis of IoT Services in Edge Computing 2

AI-Driven Privacy Analysis of IoT Services in Edge Computing

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Abdulhasan, Maki Mahdi Hussain, Ahmed Ali, Mariam Fadel Al-Dabagh, Mustafa Zuhaer Nayef Rustum Al-Assal, Jawad Radhi Al-Nisour University College Baghdad Iraq Al-Farahidi University Department of Medical Instruments Engineering Techniques Baghdad10011 Iraq Uruk University Department of Radiology Techniques Baghdad Iraq Knowledge University College of Science Department of Computer Science Erbil Iraq Al Kitab University Department of Petroleum Engineering Kirkuk Iraq

ISBN: (纸本)9798331534950

Inevitably, IoT equipment generates more data, but fog computing's concept of transferring all data to the cloud for computation has failed to meet real-time needs. Cutting-edge edge computing delivers all data from the cloud to edge devices, enhancing service quality for IoT applications that need delay. However, Edge devices are more vulnerable to attacks than endpoint technologies due to low processing power and storage. Edge computing IoT services face growing dangers, making security and privacy solutions crucial. This article proposes AI-SPM to optimally solve IoT security and privacy issues in edge computing devices. AI's better learning skills help the proposed system detect harmful intrusions more precisely. The proposed solution was compared to other IoT security and privacy management methods to prove its efficacy. The proposed framework paradigm updates security and gives edge computing devices the most robust defences against IoT service cyberattacks. The AI-SPM achieved 99.54% consumer fulfilment, 99.88% security, 99.98% system reliability, and 5.34% latency compared to other techniques. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Deep Hierarchical Learning for Estimating High Penetration of Renewable Energy Sources in Smart Grid Environments 2

Deep Hierarchical Learning for Estimating High Penetration o...

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Abed Jawad, Mohammed Al-Azzawi, Waleed Ali, Mariam Fadel Hamid, Noor Kaylan Mohammed, Marwan Aziz Al-Nisour University College Baghdad Iraq Al-Farahidi University Department of Medical Instruments Engineering Techniques Baghdad10011 Iraq Uruk University Department of Radiology Techniques Baghdad Iraq Al Kitab University Department of Computer Education Kirkuk Iraq Knowledge University Erbil Iraq College of Science Department of Computer Science Erbil Iraq

ISBN: (纸本)9798331534950

A prototype model for deep hierarchical learning and information for highly penetrating renewable energy resources (HPRES) is presented in this study. Because the stochastic nature of renewable energy increases the potential for hazardous situations, the growing deployment of renewable generators has posed a significant challenge to power system stability. As a result, a learning algorithm is used based on labelled databases and other complex data to learn how to reliably predict HPRES in real time without knowing the incoming renewable power data. The suggested method uses various historical data, such as wind direction, sunshine duration, and power distribution operations data, to produce modest, real-time results on the predictability of the data. MA does a rudimentary spectral analysis before starting to build the training dataset. The strategy's effectiveness is evaluated using a typical 16-machine, 64-bus testing setup. © 2024 IEEE.

关键词： Clean energy

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：