检索结果-内蒙古大学图书馆

3rd International Conference on Artificial Intelligence, Automation, and High-Performance Computing, AIAHPC 2023

作者： Liang, Fengqi Wang, Licai Yu, Jintao North China Institute of Computing Technology Big Data R&D Center China

ISBN: (数字)9781510666580

ISBN: (纸本)9781510666573

This paper proposes a ship detection method based on contour extraction networks and minimum bounding box generation algorithms. The proposed method utilizes contour extraction networks to extract the contour of the ship target and generate a set of key points. Then, the minimum bounding box generation algorithm is used to transform these key points into the rotational detection box of the target, which can more accurately describe the shape and orientation of ships, thus improving the accuracy and reliability of detection. The experimental results show that the proposed method can effectively detect ships of various orientations and postures, and has better performance than traditional rectangular box detection methods. The paper compares rotated bounding box detection methods based on traditional machine learning and deep learning, and concludes that rotated bounding box detection methods based on deep learning can better solve the problem of ship detection in complex situations, but require a large amount of data for training and may require a higher computational cost. Finally, the paper introduces the Minimum Bounding rectangle Algorithm used in the instance segmentation process. © 2023 SPIE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Control Strategy for Cooperative driving Automation in Traffic Incidents

Control Strategy for Cooperative Driving Automation in Traff...

引用

2023 International Conference on Control, Automation and diagnosis, ICCAd 2023

作者： Kwag, Sujin Kang, Byeongju Jang, Hyeonsoo Park, Junyeop Hwang, Yunhyoung Korea Automotive Technology Institute Department of Big Data and SW Platform R&D Gyeonggi-do Seongnam-si Korea Republic of

ISBN: (纸本)9798350347074

With the advancement on automated vehicle technology, the highly automated driving is expected to work in complicated traffic situations such as urban intersections and traffic incidents. However, the traffic incidents still remain a comprehensively challenging situation especially in the mixed traffic. To resolve this problem, a sophisticated control strategy is required to support the automated driving in these unexpected traffic situations. From this background, this study mainly focuses on developing a generalized control strategy to manage the automated vehicles driving in traffic incident situations. First, the representative scenarios are analyzed, and a generalized control strategy is elaborated based on the framework of cooperative driving automation. The proposed control strategy can be extended to more complicated situations, and it is expected to extend the operational design domain of automated vehicles. © 2023 IEEE.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Advanced Wallis: A domain adaption method based on remote sensing image homogenization technique

Advanced Wallis: A domain adaption method based on remote se...

引用

2023 International Conference on Machine Vision, Image Processing and Imaging technology, MVIPIT 2023

作者： Wang, Hui Zhou, Mengdie Tang, Panpan Zhao, Bo Nanhu Laboratory & Advanced Institute of Big Data Research Center of Big Data Technology Jiaxing Beijing China KQ GEO Technologies Co. Ltd Remote Sensing Platform R&D Center Beijing China

ISBN: (纸本)9798350306545

domain adaption has been a hot topic in artificial intelligence (AI) -driven understanding tasks. Simultaneously, as a critical technology in image preprocessing, the homogenization method plays an irreplaceable role in remote sensing interpretation. This paper proposes a domain adaptation method based on the Wallis homogenization algorithm to improve the reasoning performance of deep models, which is named advanced Wallis. Its core idea is to reduce the variability of intra-class features by reducing the hue difference between the source and target domains. The method was tested on three publicly available datasets and yielded an average improvement of 2.3% in Fl scores. A convenient implementation of the method is provided to make sure it does not consume additional computational resources and storage space. © 2023 IEEE.

关键词： Homogenization method

来源：评论

学校读者我要写书评

暂无评论

Polygenic risk scores adaptation for Height in a Vietnamese population 14

Polygenic risk scores adaptation for Height in a Vietnamese ...

引用

14th International Conference on Knowledge and Systems Engineering, KSE 2022

作者： Tran, Trang T. H Tran, Mai H Nguyen, duong T Pham, Tien M. Vu, Giang M. Vo, Nam S Nguyen, Nam N. Vu, Quang T. Vingroup Big Data Institute R&d Department GeneStory Hanoi Viet Nam Institute of Genome Research Vietnam Academy of Science and Technology R&d Department GeneStory Hanoi Viet Nam

ISBN: (数字)9781665452816

ISBN: (纸本)9781665452809

Genome-wide association studies (GWAS) with millions of genetic markers have proven to be useful for precision medicine applications as means of advanced calculation to provide a Polygenic risk score (PrS). However, the potential for interpretation and application of existing PrS models has limited transferability across ancestry groups due to the historical bias of GWAS toward European ancestry. Here we propose an adapted workflow to fine-tune the baseline PrS model to the dataset of target ancestry. We use the dataset of Vietnamese whole genomes from the 1KVG project and build a PrS model of height prediction for the Vietnamese population. Our best-fit model achieved an increase in r2 of 0.152 (according to 29.8%) compared to the null model, which only consists of the metadata. © 2022 IEEE.

关键词： Knowledge engineering Adaptation models Precision medicine Sociology Genomics Europe Predictive models

来源：评论

学校读者我要写书评

暂无评论

Improving Sign Language recognition for deaf and Hard of Hearing Individuals using the VGG16 Model 3

Improving Sign Language Recognition for Deaf and Hard of Hea...

引用

3rd International Conference on Automation, Computing and renewable Systems, ICACrS 2024

作者： Benjamin, Minu Inba Shanthini Watson Patan, Yaseen Kumar, Ansilin S.M. reddy, Pocharam Nithyanandh Ahamad, Syed Faheez Puneeth, Muvvala Sai Department of Computer Science & Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai India Department of Artificial Intelligence and Data Science Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai India

ISBN: (纸本)9798331532420

Persons who are deaf and who cannot speak face a variety of challenges, which emphasises the need for greater research to offer appropriate assistance. Interaction and communication with others are a big challenge. Since sign language is the major means of communication for these people, there is a significant knowledge gap among hearing individuals when it comes to understand and interpret sign language. As a result, there has been a notable expansion in the field of sign language study to close this gap. This work highlights the importance of sign language detection and offers a thorough analysis of relevant studies carried out in this domain using deep learning technique. It approaches the issue from multiple perspective, including translation, sign language recognition, and access to relevant datasets. Understanding these facets is intended to create a meaningful impact on sign language literature and its practical implementation. VGG16 deep learning model for sign language recognition offers the best solution for solving communication challenges faced by deaf and muted individuals. The results show that the VGG16 based technique achieves accuracy of around 95.8%. The VGG16 model uses a Convolutional Neural Network (CNN) architecture, which applies many layers of convolutional filters to identify patterns and attributes in the input images. recognizing sign language using VGG16. © 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

Image Caption Generation using CNN and Audio Conversion 2

Image Caption Generation using CNN and Audio Conversion

引用

2nd International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2024

作者： Priya, K. Babu, r.Vijay reddy, M.Muralidhar Mohan reddy, T.H. Maanesh, M. Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Artificial Intelligence & Data Science Chennai India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science & Engineering Chennai India Arizona state university Department of Data Science Tempe United States

ISBN: (纸本)9798350368413

This research focuses on developing a system that can generate descriptive captions for images and convert them into audio output. The system employs a Convolutional Neural Network (CNN) to extract visual features from images, which are then fed into a Gated recurrent Unit (GrU) to generate textual descriptions. The generated captions are subsequently converted into audio using text-to-speech techniques. By training the model on a large dataset of image-caption pairs, the system learns to associate visual information with textual descriptions, enabling accurate and coherent caption generation. This research contributes to the advancement of image understanding and generation, with potential applications in various fields such as image search, accessibility, and content creation. © 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 disk Failure Prediction Algorithm Based on Fusion Model 23

A Disk Failure Prediction Algorithm Based on Fusion Model

引用

15th International Conference on Machine Learning and Computing, ICMLC 2023

作者： Zhao, Liqiang Qi, Kaiyuan Su, Zhiyuan Pang, Liye Zhang, Lianfa Wu, dong Cloud Computing R&D Department of Jinan Inspur Data Technology State Key Laboratory of High-end Server & Storage Technology China

ISBN: (纸本)9781450398411

disk failure prediction is of great significance for ensuring the business continuity and data reliability of cloud data centers. Algorithm performance will directly affect operation and maintenance costs and user experience. Nowadays, many disk manufacturers use the threshold of S.M.A.r.T. data to check disk fault detection or make prediction, but the detection accuracy of this method is low. This paper proposes a disk fault prediction method based on deep learning, using deep residual network to extract high-dimensional hidden features;and using deep neural network combined with integrated tree model tool XGBoost to perform Failure prediction. Moreover, we use AutoML strategy based on improved GA to get the best model structure. Experiments based on Backblaze data show that this method has better prediction performance. Compared with pure XGboost methods, it can better reduce the false alarm rate about 50% and improve the accuracy rate, while maintaining a strong generalization ability. © 2023 ACM.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

Intelligent data Center Safety Status Prediction based on Algorithm Ensemble

Intelligent Data Center Safety Status Prediction based on Al...

引用

2023 International Conference on Mobile Internet, Cloud Computing and Information Security, MICCIS 2023

作者： Xu, Wenxin Zhao, Biying Zeng, Yu Wang, Tao China Telecom Research Institute Artificial Intelligence R&D Department Beijing China China Telecom Co. Ltd Big Data and AI Center Beijing China

ISBN: (纸本)9798350300932

With the promotion of energy conservation in data centers, ensuring the indoor safety while reducing energy consumption has become a social concern. Excessive temperature in the data center may cause equipment damage, thus a technical method is needed urgently to ensure the environment temperature stays in a safe state. Based on the requirement for temperature warning, this paper proposed an intelligent data center safety prediction method based on model fusion. The experimental data comes from the intelligent data center project in China Telecom. Most recent works only used a single-model-based method such as SVr, Lr or LGBM to predict temperature. This paper first uses fusion-model-based method, integrating three single regressors (SVr, Lr and LGBM) with the best parameters by soft voting. The performance of fusion model has shown lower rMSE with 0.086, compared with the rMSE of the three single regressors. It finds out that the ensembled model reduces the impact caused by the misjudgment of single weak regressors, which is stable and reliable for intelligent data center safety prediction. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Method of Abnormal detection for Power Grid Control System Metrics Based on AI Platform

A Method of Abnormal Detection for Power Grid Control System...

引用

IEEE Conference on Energy Internet and Energy System Integration (EI2)

作者： Shen Jialing Ji Xuechun Gao Shang Kong Yanru Li Hao Lao Yingying Big Data Technology R&D Department NARI Group Corporation (State Grid Electric Power Research Institute) Nanjing China

ISBN: (数字)9798331523527

ISBN: (纸本)9798331523534

In the intelligent maintenance of power grid control system, a real-time anomaly detection algorithm for metrics based on sliding windows is proposed. Then, short-term prediction and dynamic threshold are distributed constructed based on AI platform. Finally, multi-dimensional correlation analysis are achieved. Based on the metric of a system, a case study was conducted to verify that the method proposed in this paper is significantly superior of timeliness, accuracy and efficient.

关键词： Measurement Accuracy System integration Control systems Power grids real-time systems Maintenance Artificial intelligence System analysis and design Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

rEAL-TIME GLUCOSE MONITOrING SYSTEM ANd dIETArY rECOMMENdATIONS FOr dIABETES MELLITUS USING FOG COMPUTING

引用

Telecommunications and radio Engineering (English translation of Elektrosvyaz and radiotekhnika) 2025年第5期84卷 55-67页

作者： Sathish, N. Elangovan, d. Nagalakshmi, r. Suresh, G. Chitra, devi d. Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Department of Information Technology Saveetha Engineering College Chennai India Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai India Department of Artificial Intelligence and Data Science Kings Engineering College Sriperumbudur India Department of Computer Science And Engineering S.A. Engineering College Chennai India

This systematic review gave special attention to diabetes and the advancements in food and nutrition needed to prevent or manage diabetes in all its forms. There are two main forms of diabetes mellitus: Type 1 (T1d) and Type 2 (T2d). The loss of beta cells brought on by an autoimmune reaction causes the pancreas to be unable to produce enough insulin, which leads to Type 1 diabetes. A deficiency of insulin could arise as the illness worsens. The most frequent cause is a combination of excessive body weight and inadequate exercise. Currently, 90–95% of patients have Type 2 diabetes mellitus (T2dM). Age-specific normal blood sugar ranges exist and knowing them is crucial for determining a target blood sugar level that is both healthy and appropriate. The main takeaway is that diet regimens ought to be tailored to the patient’s requirements and should account for their capacity for change. Carbohydrates are the nutrients that have the biggest impact on the rise in blood glucose. In this paper, we have proposed a novel method for glucose monitoring and diet recommendations for diabetic patients using fog computing. A paradigm known as fog computing makes use of the benefits that come from using both cloud and edge devices to support modern computing systems by offering high-quality services, cutting latency, facilitating mobility, supporting multi-tenancy, and many other features. © 2025 by Begell House, Inc.

关键词： Fog computing

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：