检索结果-内蒙古大学图书馆

4th International Conference on Expert Clouds and Applications, ICOECA 2024

作者： Aryan, Ansh Singh, Dharya Pratap Kumar, Nitish Amity University Dept. of Computer Science and Engineering Uttar Pradesh India

ISBN: (纸本)9798350385793

This research study provides the utilization of an intelligent video surveillance system, a sophisticated technology that integrates video cameras, sensors, and cutting-edge software to monitor and analyze activities within a designated area or locale. By seamlessly combining compute r vision and machine learning techniques, it goes beyond conventional video surveillance installations to provide real-time insights along with automated alerts. Intelligent video surveillance systems harness the power of machine learning and computer vision algorithms to analyze video feeds in real-time, empowering them to detect, track, and comprehend objects, individuals, and occurrences captured within the video frames. Furthermore, these systems can recognize a variety of objects, including cars, people, animals, and particular objects, even in complex and crowded settings. They also offer a variety of analytical tools and insights that are very helpful to organizations and security operations, such as traffic patterns, heatmaps, and other data. This research study provides a thorough explanation of the modern uses of machine learning in the field of surveillance systems. Two crucial issue statements are addressed by it in practice: the identification of human falls and the detection of auto accidents. This study's main goal is to demonstrate an end-to-end system that will act as a beacon for law enforcement and medical personnel, giving them the ability to quickly identify traffic accidents and serious injuries and guarantee that the necessary assistance is provided on time. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Impact of Source Coding on Downstream AI Applications 6

Impact of Source Coding on Downstream AI Applications

引用

6th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2024

作者： Islam, Nazmul Shin, Seokjoo Chosun University Dept. of Computer Engineering Gwangju61452 Korea Republic of

ISBN: (纸本)9798350344349

The use of Artificial Intelligence (AI) in Internet of Things (IoT) ecosystem has been growing exponentially, enabling various computer Vision (CV) applications. These applications must handle large image data demanding reliable communication systems that retain image quality for downstream Deep Learning (DL) tasks. Existing communication systems, such as Orthogonal Frequency Division Multiplexing (OFDM), promise improvements in data rate, spectral efficiency, and mitigation of multipath fading;however, these systems often distort the received images due to complex channel environments and impairments from various physical layer (PHY) blocks. Source Coding is one such PHY block, which aims for compression savings at the expense of image quality. Therefore, in this study, we evaluate the performance of a DL model for downstream image recognition tasks, where images are transmitted over communication systems utilizing various source coding schemes over complex channels. Experimental analysis shows that Variable-Length Coding (VLC) retains superior image quality, which results in over 95% DL model accuracy throughout the experiment. © 2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

A Study on the Global HVDC Trends and the Current Status of HVDC in Korea

引用

Transactions of the Korean Institute of Electrical Engineers 2023年第2期72卷 321-329页

作者： Kim, Kwonchul Kim, Beopsoo Kim, Insu Dept. of Electrical Engineering Inha University Korea Republic of Department of Electrical and Computer Engineering Inha University Korea Republic of

HVDC systems are increasingly playing an important role in energy transmission because they have technical, economic, grid operational advantages over conventional HVAC systems. For example, HVDC is preferable for long-distance bulk transmission and asynchronous interconnection between different frequency systems. Indeed, two HVDC linkages between the Jeju island and mainland (Haenam and Jindo) in South Korea were already constructed in 1998 and 2013, respectively. There are also several HVDC projects currently under construction in South Korea. Thus, the objective of this study is to review the global trends in HVDC energy transmission, including issues in Korean HVDC systems. For this purpose, this study examines the technical and operational advantages and disadvantages in HVDC systems. Then, the global trends, including the current status of HVDC systems in South Korea, are reviewed at the aspects of capacity, converter makers, and circuit breakers. Additionally, this study summarizes the main challenges for the smooth integration of HVDC systems into the conventional AC power systems. For this purpose, this study models a CIGRE HVDC benchmark model, generates a fault, modify the model and analyzes the transient responses of the benchmark model . Copyright © The Korean Institute of Electrical Engineers.

关键词： Electric circuit breakers

来源：评论

学校读者我要写书评

暂无评论

TraceChainBD: Securing Supply Chains from Counterfeiting in Bangladesh with Blockchain and IoT Integration

TraceChainBD: Securing Supply Chains from Counterfeiting in ...

引用

2024 International Conference on Innovations in Science, engineering and Technology, ICISET 2024

作者： Karmoker, Sagar Khan, Md. Adib Lamia, Sanjida Alam Tanjid, Mobinul Ahasan Dihan, Shahriar Sadman Anik, Nur Adnan Chowdhury East West University Dept. of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350355499

The scheme uses blockchain technology in Bangladesh's supply chain to eliminate counterfeit products, improve tax compliance, and build consumer trust. By ensuring product authenticity, it safeguards brand reputations and boosts government revenue. Manufacturers, distributors, and retailers can enter product data which will then generate QR codes. In case of receiving the product or checking its authenticity, they can scan these QR codes via their mobile or a dedicated IOT device and all the information will be stored in Blockchain. Since blockchain data is secure and immutable, it cannot be altered, consumers can easily check product details by scanning QR codes, and if a product is flagged as suspicious, the Mobile Court Management System can trace its origin. This blockchain-based approach ultimately helps prevent counterfeit goods from entering the market and enhances the government's ability to collect taxes. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

A CNN Based Ensemble Deep Learning Approach for Melanoma Detection

A CNN Based Ensemble Deep Learning Approach for Melanoma Det...

引用

2024 IEEE Region 10 Symposium, TENSYMP 2024

作者： Mullick, Mohammad Abu Obaida Khan, Nafi Sadman Fahid, Ahnaf Tahmid Mahmud, Mahin Rahman, Raiyan United International University Dept. of Computer Science & Engineering Dhaka Bangladesh

ISBN: (纸本)9798350364866

Melanoma, the most aggressive form of skin cancer, necessitates early detection for successful treatment. This paper proposes an ensemble Convolutional Neural Networks (CNNs) approach to classify dermoscopic images of Melanoma (MEL) and Melanocytic Nevi (NV), by systematically selecting and comparing various pre-trained models with different optimizers and preprocessors through trial and error, as well as optimizing loss functions. The ensemble method takes predictions from multiple pre-trained models and selects the most reliable outcome using a custom metric. The result presents an optimal CNN ensemble model built of DenseNet121 and VGG16 with cropping and scaling, contrast enhancing, and exposure adjusting as image preprocessors that achieved a notable accuracy of 97.5% on a customized and balanced version of the Kaggle HAM10000 dataset. This approach aims to improve patient outcomes by providing a valuable tool for early melanoma detection. © 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

Classification of non-invasive EEG signals during Motor Imagery tasks using a Large Language Model 23

Classification of non-invasive EEG signals during Motor Imag...

引用

23rd International Conference on Cyberworlds, CW 2024

作者： Lim, Do-Hyeon Cho, Myeong-Ju Kim, Hoon-Hee Pukyong National University Dept. of Computer Engineering Busan Korea Republic of

ISBN: (纸本)9798331527174

EEG data have significant academic and clinical value because of their non-invasive nature which allows for easy extraction. At the same time, they are also prone to distortion from noise, making quality interpretation challenging. Meanwhile, the advancements of Large Language Models (LLMs) have made them applicable to complex tasks. In this study, we propose a fine-tuned LLM classifier that is able to classify motor imagery EEG data. The research compares the performance of fine-tuned LLM with that of Support Vector Machine, Random Forest, and Multi-Layer Perceptron models. The results show that the fine-tuned LLM can achieve comparable performance compared to traditional machine learning methods and demonstrate the possibility that the finetuned LLM could be applied to more diverse tasks based on EEG data. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

The Tree Autoencoder Model, with Application to Hierarchical Data Visualization 38

The Tree Autoencoder Model, with Application to Hierarchical...

引用

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Carreira-Perpiñán, Miguel Á. Gazizov, Kuat Dept. of Computer Science and Engineering University of California Merced United States

We propose a new model for dimensionality reduction, the PCA tree, which works like a regular autoencoder, having explicit projection and reconstruction mappings. The projection is effected by a sparse oblique tree, having hard, hyperplane splits using few features and linear leaves. The reconstruction mapping is a set of local linear mappings. Thus, rather than producing a global map as in t-SNE and other methods, which often leads to distortions, it produces a hierarchical set of local PCAs. The use of a sparse oblique tree and of PCA in its leaves makes the overall model interpretable and very fast to project or reconstruct new points. Joint optimization of all the parameters in the tree is a nonconvex nondifferentiable problem. We propose an algorithm that is guaranteed to decrease the error monotonically and which scales to large datasets without any approximation. In experiments, we show PCA trees are able to identify a wealth of low-dimensional and cluster structure in image and document datasets. © 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

'Liver Disease Risk Prediction Using Regularized Deep Learning: A Novel Approach' 2

'Liver Disease Risk Prediction Using Regularized Deep Learni...

引用

2nd IEEE International Conference on Advancements and Key Challenges in Green Energy and Computing, AKGEC 2024

作者： Rahi, Parvez Kang, Sandeep Singh Singh, Ajay Pal Singh, Inderjeet Chandigarh University Dept. of Computer Science & Engineering Punjab Mohali India

ISBN: (纸本)9798350390179

Liver diseases are common, thereby posing a significant quality-of-life impairment. They have required accurate and prompt assessments to be managed. Typically, conventional methods of evaluation often include subjectivity and laborious amounts of work. It introduces a DNN-based model with L2 regularization to predict risk categorization of liver diseases based on five categories of categorizations: Healthy-Liver, Low-Risk, Moderate-Risk, High-Risk, and Severe-Liver-Disease. The model includes the hidden layers with rectified linear unit (ReLU) activation functions, batch normalization, and dropout for regularizing to achieve robust learning. The DNN was trained in a very comprehensive Kaggle dataset with many physiological and biochemical features and has achieved an impressive 94.07% classification accuracy. Healthcare professionals will be equipped with a significant resource to develop personalized treatment strategies facilitated by this investigation, which highlights the capabilities of deep learning methodologies in the automation of liver disease assessment. Subsequent research will focus on integrating additional data sources to improve the model's scalability and predictive precision, thus promoting the advancement of automated liver disease evaluation in clinical settings. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Korean News Summarization with Contrasts by Augmenting Counterfactual Data

Korean News Summarization with Contrasts by Augmenting Count...

引用

2024 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2024

作者： Lee, Minji Lee, Wonho Lee, Sunmin Kim, Taehoon Park, Cheoneum Hanbat National University Dept. Computer Engineering Daejeon Korea Republic of

ISBN: (纸本)9798331530839

We introduce a method utilizing counterfactual data to increase performance for an abstractive summarization with contrasts. Previous summarization studies concentrate on summary generation given only input text;however, our method incorporates counterfactual data that includes hypothetical scenarios different from the original text. By augmenting the model with these counterfactual examples, it learns to identify key information and its contrasts more effectively, leading to more refined and accurate summaries. Experimental results demonstrate that our proposed method outperforms traditional methods and general LLM prompting methods, showcasing its potential in generating contrastive summaries. © 2024 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Fault Detection of Permanent Magnet Synchronous Motors Employing DQ Current Features and Isolation Forest

Fault Detection of Permanent Magnet Synchronous Motors Emplo...

引用

2024 International Conference on Electrical Machines, ICEM 2024

作者： Koutrakos, Konstantinos Mitronikas, Epameinondas University of Patras Electrical and Computer Engineering Dept. Rion-Patras Greece

ISBN: (纸本)9798350370607

Early and automated fault detection is necessary for proper condition monitoring and operation management of electric motor and drive systems. This paper investigates fault detection of Permanent Magnet Synchronous Motors (PMSM) using Motor Current Signature Analysis (MCSA), d-q Transform and Isolation Forest (iForest). This approach utilizes statistical indicators for feature extraction from dq-transformed current measurements and Isolation Forest, for outlier and fault detection. The proposed methodology is tested in a PMSM test bench under multiple operating conditions. © 2024 IEEE.

关键词： Permanent magnets

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：