检索结果-内蒙古大学图书馆

10th International Conference on Communication and Signal Processing, ICCSP 2024

作者： Annamalai, J. Arjun Sneha, S. Sharon Ashokkumar, C. Srm Institute of Science and Technology School of Computing College of Engineering and Technology Department of Computing Technologies Chennai Kattankulathur603203 India

ISBN: (纸本)9798350353068

Traditional video search engines often rely on tags or manual annotations for content retrieval, limiting the accuracy and efficiency of search results. Moreover, keyword-centric searches may not adeptly capture the nuanced and intricate queries users pose when seeking specific video content. The envisioned video search system integrates machine learning and natural language processing components to enable efficient and effective video retrieval based on user queries. The pipeline includes video processing employing Vision Transformer with GPT-2 (ViT-GPT2) architecture to analyze intricate details within video frames, Speech-to-Text (STT) models for transcribing spoken content, and the combination of transcriptions with video captions to form textual descriptions. These descriptions are then embedded using BERT, a transformer-based model, to grasp contextual relationships. Semantic matching is achieved through deep learning models, and a ranking mechanism based on similarity scores facilitates efficient retrieval. Leveraging datasets such as the MSR-VTT dataset, spanning visual recognition domains, contributes to the evaluation and training of the system's components. The system's efficacy is evaluated using metrics such as precision, recall, F1-score, and ranking metrics, with datasets spanning visual recognition, speech transcription, and semantic similarity domains. The comprehensive evaluation approach ensures the robustness and relevance of the video search system, aligning with user expectations and real-world use cases. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Models in Power Generation for Energy Consumption Prediction 4

Artificial Intelligence Models in Power Generation for Energ...

引用

4th International Conference on Emerging Trends in Networks and Computer Communications, ETNCC 2024

作者： Tan, Lit Yang Chen Kwan, Charis Shwu Ajibade, Samuel-Soma M. Ramly, Athirah Mohd School of Engineering and Technology Sunway University Department of Computing and Information Systems Selangor Malaysia School of Architecture Computing and Engineering University of East London Department of Computing London United Kingdom

ISBN: (纸本)9798350353266

The incorporation of artificial intelligence (AI) into power-related applications signifies a new and unexplored domain in machine learning for predicting power generation. This novel method utilizes prediction models, often used in different fields, to predict energy-related patterns, providing a unique and specialized viewpoint. The synergy of academicians, AI experts, and industry professionals in the energy sector has resulted in the creation of customized AI models to optimize operational efficiency. By customizing various AI models to suit the distinct attributes of energy scenarios and datasets, these models are positioned to transform energy management methods. This study examines the utilization of AI models to enhance energy efficiency in power generation in Malaysia. The project seeks to predict future power consumption in various sectors, analyze growth rates, and identify sectors with investment potential by developing a Linear Regression model. In addition, a thorough power plan is developed using the estimated energy usage. A comparative analysis is performed to determine the most appropriate model for this particular scenario, which will improve decision-making in the energy sector. The results of this study present promising opportunities for further investigation. By broadening the study's focus to encompass a broader array of AI models and their assessment of performance, it is possible to gain useful insights for predicting power generation. Furthermore, the integration of real-time data streams and the inclusion of feedback loops in the AI models could improve their ability to adapt and increase their accuracy as time progresses. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning-Based Cooperative Target Tracking Control of Unmanned Surface Vehicles Under Data Falsification Attacks

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-11页

作者： Liu, Zhao-Qing Ge, Xiaohua Han, Qing-Long Wang, Yu-Long Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing China School of Science Computing and Engineering Technologies Swinburne University of Technology Melbourne VIC Australia School of Mechatronic Engineering and Automation Shanghai University Shanghai China

This paper deals with the problem of cooperative target tracking control for multiple networked unmanned surface vehicles under data falsification attacks. First, a data falsification attack model is constructed to account for unknown falsified control commands. Next, a networked cooperative target tracking model is developed by integrating the concurrent impacts of data falsification attacks and network-induced delays. Then, a reinforcement learning-based compensation mechanism, consisting of an actor neural network and an adaptive critic function, is developed to offset the adverse effects caused by the unknown dynamics and external disturbances. Meanwhile, to cope with data falsification attacks and reduce the neural network approximation errors, a secure control input is subtly developed. Based on the developed compensation mechanism and secure control input, a dynamic control law is constructed to regulate the action of involved unmanned surface vehicles. Furthermore, a resilient cooperative target tracking control scheme is proposed to achieve the expected cooperative target tracking control objectives. At last, two case studies are provided to validate the efficacy of the designed resilient cooperative target tracking control scheme. IEEE

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A MLP-Mixer and mixture of expert model for remaining useful life prediction of lithium-ion batteries

引用

Frontiers of Computer Science 2024年第5期18卷 1-10页

作者： Lingling ZHAO Shitao SONG Pengyan WANG Chunyu WANG Junjie WANG Maozu GUO Faculty of Computing Harbin Institute of TechnologyHarbin 150001China School of Electrical Engineering Liaoning University of TechnologyJinzhou 121004China School of Computer Science Northeast Electric Power UniversityJilin 132000China Department of Medical Informatics School of Biomedical Engineering and InformaticsNanjing Medical UniversityNanjing 211166China School of Electrical and Information Engineering Beijing University of Civil Engineering and ArchitectureBeijing 100044China

Accurately predicting the Remaining Useful Life(RUL)of lithium-ion batteries is crucial for battery management *** learning-based methods have been shown to be effective in predicting RUL by leveraging battery capacity time series ***,the representation learning of features such as long-distance sequence dependencies and mutations in capacity time series still needs to be *** address this challenge,this paper proposes a novel deep learning model,the MLP-Mixer and Mixture of Expert(MMMe)model,for RUL *** MMMe model leverages the Gated Recurrent Unit and Multi-Head Attention mechanism to encode the sequential data of battery capacity to capture the temporal features and a re-zero MLP-Mixer model to capture the high-level ***,we devise an ensemble predictor based on a Mixture-of-Experts(MoE)architecture to generate reliable RUL *** experimental results on public datasets demonstrate that our proposed model significantly outperforms other existing methods,providing more reliable and precise RUL predictions while also accurately tracking the capacity degradation *** code and dataset are available at the website of github.

关键词： lithium-ion battery remaining useful life deep learning MLP-Mixer mixture-of-experts

来源：评论

学校读者我要写书评

暂无评论

Integration of Wireless and Plug-in Charging Systems Using Three Leg Converter Configuration with Wide Output Voltage Range 4

Integration of Wireless and Plug-in Charging Systems Using T...

引用

4th IEEE International Conference on Sustainable Energy and Future Electric Transportation, SEFET 2024

作者： Rai, Ashutosh Tummuru, Narsa Reddy Vakcharla, Venkat Ratnam School of Computing and Electrical Engineering Indian Institute of Technology Mandi India

ISBN: (纸本)9798350383997

With the increasing adoption of EVs it is crucial to have a versatile charging system that can support charging of both the wireless EVs and plug-in two wheelers or three wheelers. To meet such a requirement at residential level a three-leg converter configuration is proposed to accommodate charging for both wireless EVs and plug-in vehicles that require DC charging. Such an integration renders economy in device count and eliminates requirement of dedicated charger assembly for each kind of electric vehicle. Both wireless and plug-in EVs can be charged simultaneously with wide range of output voltages in both channels. The wireless charger assembly is based on full bridge for AC level 1 charging for cars while the plug-in charger is based on half bridge LLC topology to contain 2-wheeler and 3-wheeler DC charging requisites. Variable frequency control (VFC) is implemented to achieve the required voltage gains. Using voltage gain analysis and input impedance characteristics, VFC helps to achieve wide voltage output with ZVS realization. The proposed charger topology is simulated using MATLAB Simulink simulation platform to validate the functionality for desired range of output voltage and soft switching provisions. © 2024 IEEE.

关键词： Wireless charging

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Insights: A Survey on Innovative Approach for Lung Cancer Prediction Utilizing Machine Learning and Deep Learning Methods 3

AI-Driven Insights: A Survey on Innovative Approach for Lung...

引用

3rd International Conference on Automation, computing and Renewable Systems, ICACRS 2024

作者： Bhargav, A. Lakshmi Ashokkumar, C. Department of Computing Technologies School of Computing College of Engineering and Technology SRM Institute of Science & Technology Kattankulathur Chennai603203 India

ISBN: (纸本)9798331532420

The lungs are vital for exchanging oxygen and carbon dioxide, providing oxygen to cells for energy production, and removing waste carbon dioxide from the *** also help filter and protect the body from harmful particles and pathogens in the *** lung function is essential for overall health and *** cancer ranks as the second most common cause of cancer-related fatalities *** emphasizes the challenge of early detection due to the lack of symptoms in the initial *** contributes to a high mortality rate compared to other lung *** identification and precise prediction of lung cancer serves as vital for improving patient outcomes. Machine learning (ML) techniques have shown great promise in revolutionizing lung cancer prediction by leveraging various data sources such as medical images, clinical data, and genomic information. This paper presents a review of lung cancer prediction using ML, DL, and AI *** classification of lung cancer through medical imaging is essential for physicians to determine appropriate treatment options, ultimately aiming to reduce cancer *** goal is to compare the performance and accuracy of convolutional neural networks (CNNs), Random forest algorithm, ensemble extreme boosting (XGBoost) algorithm,Support Vector Machine (SVM), AdaBoost classification model (ADB-C), Long Short-Term Memory Networks (LSTM), incremental multiple resolution residual network (iMRRN) models while also providing explanations for their predictions. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Optimal weight support vector regression ensemble with cluster-based subsampling for electricity price forecasting

引用

Journal of Intelligent and Fuzzy Systems 2024年第1期1卷 1-16页

作者： Li, Yuerong Zhang, Yuhua Che, Jinxing School of Science Nanchang Institute of Technology Jiangxi Nanchang China Key Laboratory of Engineering Mathematics and Advanced Computing Nanchang Institute of Technology Jiangxi Nanchang China

Accurate prediction of short-term electricity price is the key to obtain economic benefit and also an important index of power system planning and management. Support vector regression (SVR) based ensemble works have gained remarkable achievements in terms of high accuracy and steady performance, but they are highly dependent on data representativeness and have a high computational complexity O (k ∗ N 3) of data samples and parameter selection. To further improve the data representativeness and reduce its computational complexity, this paper develops a new approach to forecast electricity price via optimal weighted ensemble. In the model, the cluster-based subsampling algorithm is proposed to categorize the inputs being seasonally decomposed into several groups, and representative data are drawn from each group in a certain proportion to ensure that each subset trained with SVR has the same representativeness and features. Moreover, the optimal weighted combination method is presented to assign weights to the sub-SVRs to obtain the optimal support vector regression ensemble model (OWSSVRE). The experimental results show that the improved support vector regression ensemble model with the same features and representativeness of the subset has better performance in electricity price forecasting. As a result, it is suitable to support decision making in the energy and other sectors. © 2024 - IOS Press. All rights reserved.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Cricket Performance Analysis System Using Machine Learning Techniques 5

Cricket Performance Analysis System Using Machine Learning T...

引用

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

作者： Mishra, Suraj Garg, Animesh Batra, Vansh Saxena, Devansh Om Gouthaman, P. School of Computing College of Engineering and Technology SRM Institute of Science and Technology Department of Networking and Communications 603203 India School of Computing SRM Institute of Science and Technology Faculty of Engineering and Technology Department of Networking and Communications India

ISBN: (纸本)9798331530013

The Cricket Performance Analysis System based on big data tools, like Hadoop and Apache Spark, gives realtime deep insights into performances from players and teams and conditions in matches based on large-scale cricket match data. It scales up speedily and finds patterns using distributed computing capabilities of Spark, which makes it possible to take decisions around performance improvements and strategies. The system applies a set of machine learning techniques including K-means clustering, Logistic Regression, and Random Forest classifiers to be used for the analysis of player performance metrics and match outcomes. Thus, through the conversion of raw data into actionable insights, teams can improve their strategies, make better improvements in performance, and thus gain an upper hand against other competing professional cricket teams. As a result, teams are best positioned to make adjustments in good time and direct finer tactics toward further enhancement of overall performance. © 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

Comprehensive Methods for Secure Medical Image Transfer: Encryption and Standardization Techniques

Comprehensive Methods for Secure Medical Image Transfer: Enc...

引用

2024 International Conference on Science, technology, engineering and Management, ICSTEM 2024

作者： Priyadharshini, K. Nandi, Hitesh Parmar, Harsh Dept. of Computing Technologies School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chennai India

ISBN: (纸本)9798350376913

The primary goal of the process is to securely transfer medical images. This involves utilizing MRI datasets for processing and applying resizing and filtering techniques such as Conv2D and Gaussian blur to standardize the images. Additionally, an attack model is developed to enhance information security, starting with a PGD attack to access model weights and followed by a DAG attack to increase loss functions. Encryption is then performed using a Chaos-based encryption model to create a chaotic map and the Henon map for image conversion. A randomly generated key encryption method is utilized to generate a key for secure transfer. The encrypted image is displayed, and in the receiver section, the process is reversed for decryption by inputting the key generated in the encryption model. Finally, the original medical image is retrieved along with parameters such as MSE, MAE, RMSE, and F2 score to assess the accuracy of the recovered image and ensure its correctness. © 2024 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Detection and Classification of Brain Tumor Using Deep Learning Model 1

引用

4th International Conference on Computer Vision, High-Performance computing, Smart Devices, and Networks, CHSN 2023

作者： Routhu, Manoj Sitaram Govindaraju, Rohith Vigna Saranya, P. Department of Computing Technologies School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chennai603203 India

ISBN: (数字)9789819777945

ISBN: (纸本)9789819777938

Accurate and efficient brain tumor classification is paramount for timely clinical diagnosis and effective treatment planning. In this groundbreaking research, we introduce an innovative Convolutional Neural Network (CNN) architecture intricately integrated with customized preprocessing techniques, resulting in an exceptional classification accuracy of 98.5% on the challenging br35H dataset. By harnessing the power of MRI scans and leveraging diverse datasets, our model expedites brain tumor assessments and sets the stage for advanced classification methodologies. With the global incidence of brain tumors rising, the need for technology-driven diagnosis becomes increasingly evident, and CNNs emerge as pivotal tools in enhancing diagnostic precision. This study not only underscores the profound significance of CNN models but also transcends geographical boundaries, reducing the frequency of misdiagnoses and ultimately empowering global healthcare. This paper comprehensively explores our methodology, delving into the intricate details of data collection processes, model development strategies, and experimental findings. Moreover, it sheds light on the implications of deploying CNN models in medical imaging. By contributing to the ongoing discourse on transformative healthcare technologies, this research aims to propel the adoption of CNN-based approaches, ushering in a new era of precise and efficient brain tumor classification for the benefit of healthcare professionals, patients, and society. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Convolutional neural networks

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：