检索结果-内蒙古大学图书馆

IEEE 20th international conference on Automation Science and engineering (CASE)

作者： Mul, Ni Hu, Xiao Jia, Qing-Shan Zhu, Xu He, Xiao Tsinghua Univ Ctr Intelligent & Networked Syst CFINS Dept Automat Beijing 100084 Peoples R China China Informat Technol Designing & Consulting Ins Beijing 100089 Peoples R China

ISBN: (纸本)9798350358513;9798350358520

Cooling control in large-scale data centers (DCs) aims to minimize energy consumption, while maintaining suitable temperatures for IT equipment. In the multi-ACU joint control problem, the high dimensionality of the state and action space, along with time-costly simulation, make traditional control methods inefficient in obtaining the optimal policy. We propose a novel reinforcement learning (RL) framework, which first leverages a surrogate model to train a base RL policy, and then fine-tunes the base policy. Specifically, the use of the surrogate model can exponentially reduce the action space dimension, by treating all ACUs in the room as identical, and interpolating the state space based on physical mechanism. After the base policy for single-ACU control is derived from the surrogate model, we fine-tune it on each individual ACU, using Soft Actor-Critic (SAC) algorithm with balanced replay. The balanced replay technique mitigates the off-policy bootstrapping errors caused by inaccurate value estimation, while enabling efficient Q-value updating. Simulation results demonstrate that our framework significantly improves energy savings and temperature stability for large-scale DC cooling control, while requiring much fewer data samples, compared to existing state-of-the-art methods.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Abnormal Client Detection Federated learning Using Image Vectors 37

Abnormal Client Detection Federated Learning Using Image Vec...

引用

37th international conference on Information Networking (ICOIN)

作者： Park, JinSeon Kim, Ki Tae Park, Seong-Bae Hong, Choong Seon Kyung Hee Univ Dept Comp Sci & Engn Yongin 17104 South Korea

ISBN: (纸本)9781665462686

Federated learning is a distributed machine learning system that can learn AI models in cooperation with each other without directly sharing data stored in multiple locations. Since federated learning requires training the model without direct access to the client data, AI models can be trained while protecting the client's data. In the presence of clients with relatively different data distributions from other clients, this can lead to poor model learning performance in federated learning. In this paper, we propose a method to obtain cosine similarity by computing the vector inner product based on the vector for the client's image data, and to improve the performance of federated learning by eliminating clients with low similarity. Compared to the case of conducting federated learning without detecting abnormal clients, the performance improvement of 6% was confirmed when the proposed method was applied.

关键词： Federated learning Vector Cosine Similarity

来源：评论

学校读者我要写书评

暂无评论

Automated Indigenous Plant Recognition and Medicinal Value Extraction System 7th

Automated Indigenous Plant Recognition and Medicinal Value E...

引用

7th IFIP TC 12 international conference on Computational Intelligence in data Science, ICCIDS 2024

作者： Sendhilkumar, S. Mahalakshmi, G.S. Swaminathan, A. Anirudh, K. Sai Department of IST CEG Anna University Chennai India Department of CSE CEG Anna University Chennai India Department of CSBS Panimalar Engineering College Chennai India

ISBN: (纸本)9783031699818

In an age where environmental awareness and exploration of natural resources are paramount, identifying traditional and indigenous plant species has become crucial across diverse domains. This aim of this work is ultimately develop a mobile application framework that detects and recognizes indigenous medicinal plants of our country, its medicinal value and usage in indigenous food preparation. Moreover the key component essential is the right machine learning model which is scalable, incremental and more accurate. The proposed work is developing a robust and scalable machine learning model for detecting and recognizing indigenous medicinal plants species. Image data set pertaining to whole plant and parts like flower, leaf, fruit, stem, bark, root of unique 2626 Indian plant species were collected and used for training and testing three deep learning CNN models like Resnet50, MobileNetV2 and VGG16 for plant species identification. These three models performed with 85%, 82% and 87% accuracy individually. Finally stochastic weight averaging ensemble of the three independent approaches resulted an overall accuracy of 95%. © IFIP international Federation for Information Processing 2024.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

CONSISTENCY ASSESSMENT OF WAVE DIRECTIONAL SPECTRUM PREDICTIONS FROM machine learning BASED SHIP-AS-A-WAVE-BUOY METHODS 41

CONSISTENCY ASSESSMENT OF WAVE DIRECTIONAL SPECTRUM PREDICTI...

引用

ASME 41st international conference on Ocean, Offshore and Arctic engineering (OMAE)

作者： Scholcz, T. P. Hageman, R. B. Duz, B. Mak, B. Maritime Res Inst Netherlands MARIN POB 28 NL-6700 AA Wageningen Netherlands

ISBN: (纸本)9780791885901

Real-time knowledge of the ocean wave directional spectrum is valuable for maritime safety and navigation. When end-to-end machine learning is used to learn ocean wave directional spectra from ship motions, the spectrum predictions may be inconsistent with measured ship motions from a physical point of view. In order to assess this consistency, a method is proposed that makes use of a numerical seakeeping code to recalculate ship motions from predicted wave spectra. The recalculated ship motions are subsequently compared to the measured ship motions. The method is applied using data from three different vessels, each having a different level of data completeness. For these cases it is concluded that the consistency can be assessed when the sea state is not too extreme. The method may be improved by using higher fidelity seakeeping codes.

关键词： machine learning deep learning ocean wave spectra ship motions wave buoy analogy inverse problem consistency assessment

来源：评论

学校读者我要写书评

暂无评论

Analyzing Federated learning with Enhanced Privacy Preservation 23

Analyzing Federated Learning with Enhanced Privacy Preservat...

引用

23rd IEEE international conference on Mobile data Management (IEEE MDM)

作者： Tseng, Sheng-Po Yeh, Lo-Yao Wu, Lee-Chi Tsai, Pei-Yu Natl Tsing Hua Univ Dept Comp Sci Hsinchu Taiwan Natl Cent Univ Dept Informat Management Taoyuan Taiwan Inst Informat Ind III Blockchain Technol Sect Taipei Taiwan

ISBN: (数字)9781665451765

ISBN: (纸本)9781665451765

For machine learning in online social networks or mobile environments, data privacy-preserving is a very important issue. In the past, artificial intelligence and machine learning algorithms that operating on a stand-alone machine must analyze each data in order to build an accurate model when training a model. However, this method is insufficient in terms of privacy protection, because it must collect data from different sources;on the other hand, if these algorithms analyze only a part of the data, the accuracy of the models constructed by artificial intelligence and machine learning algorithms will be very low. To solve the above problems, this study starts from the privacy protection aspect of industrial data management, combined with the concept of federated learning, and hopes to improve the accuracy of algorithm modules while ensuring data privacy. Therefore, in this paper, we analyze the impact of federated learning under different protocol mechanisms on the accuracy of algorithm modules, and based on this, we can apply this module to integrate blockchain smart contract technology in the future.

关键词： machine learning Federated learning Privacy-preserving

来源：评论

学校读者我要写书评

暂无评论

A machine learning-based Automatic Model to Predicting Performance of Students

A Machine Learning-based Automatic Model to Predicting Perfo...

引用

2022 IEEE international conference on Current Development in engineering and Technology, CCET 2022

作者： Garg, Atul Garg, Nidhi Bansal Ghosh, Pinaki Bansal, Ankit Lilhore, Umesh Kumar Simaiya, Sarita Chitkara University Institute of Engineering and Technology Chitkara University Karnataka India School of Advanced Computing Sage University Bhopal India Chandigarh University Department of Computer Science and Engineering Karnataka Mohali India

ISBN: (纸本)9781665454155

machine learning offers a variety of techniques for use in diverse fields. Massive quantities of student data are produced in educational institutions, and machine-learning techniques are a precious tool for identifying patterns in individuals' behavior. Academicians can learn valuable data concerning the students' expertise and how it relates to their educational assignments by critically examining and evaluating these data. This data serves as the input for cutting-edge techniques and algorithms that can forecast students' academic achievement. This research presents a machine learning-based automatic model for predicting the performance of students. The popular ML methods are Random Forest, K-Neighbors, Extra Trees, Ada-Boost, Decision Tree, Logistic Regression, Gaussian NB, and Bernoulli NB. This research utilizes an online student performance dataset collected from Kaggle. The findings demonstrate that Random forest and decision trees outperform other techniques based on high precision as well as the capacity to interpret the guidelines and structure that were developed for predicting students' educational success. © 2022 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

PRELUDE FLNG FREE WEATHERVANING HEADING PREDICTION AND UNCERTAINTIES, BASED ON machine learning MODEL 41

PRELUDE FLNG FREE WEATHERVANING HEADING PREDICTION AND UNCER...

引用

ASME 41st international conference on Ocean, Offshore and Arctic engineering (OMAE)

作者： Delivre, Quentin Rajaobelina, Jery Kang, Mengchen McConochie, Jason Drobyshevski, Yuriy Technip Energies Paris France Shell Australia Pty Ltd Perth WA Australia

ISBN: (纸本)9780791885857

Prelude Floating Liquefied Natural Gas (FLNG) facility is moored with an internal turret allowing it to free weathervane (FW), i.e. by leaving the unit to rotate according to environmental loads. During the engineering phase, the FLNG FW heading is estimated by the heading analysis (i.e. physics-based approach), and results are then used as input for other studies. Therefore, a good estimation of the various environmental effects (waves, current and wind) and their contributions in terms of loads on the FLNG is critical to ensure a correct prediction of the FW heading. For the predominant contributions (wind and current), the force coefficients have been initially derived from wind tunnel tests during the engineering phase. However, Prelude FLNG being now installed on-site, measurements over recent years have shown slight discrepancies with the numerical predictions by the heading analysis. Preliminary investigations were carried out and were aimed to improve some parameters of the numerical model. Nevertheless, it appeared that even with these improvements, discrepancies between numerical predictions and measurements were not always resolved. These discrepancies may have several origins, such as inadequacy of the numerical model, variability of the metocean data, uncertainties in measurements, etc. In order to overcome the aforementioned uncertainties and unknowns, it has been decided to set-up a machine learning model (i.e. data-based approach). This machine learning model (RBF ANN - Radial Basis Function Artificial Neural Network) was trained with the recorded metocean data (input) and measured FLNG FW heading (output). Considering the amount of the measured data available (two years with a time step of 10 minutes), the necessity to optimize the model's hyperparameters and the computer capability, a stepwise approach has been applied to ensure an accurate model can be built in a reasonable timeframe. Finally, the machine learning model calculation shows a signifi

关键词： prediction uncertainties machine learning optimization

来源：评论

学校读者我要写书评

暂无评论

Object Detection Improvements on Skin Burn Image data via data Augmentation and Semi-supervised learning 14th

Object Detection Improvements on Skin Burn Image Data via Da...

引用

14th international conference on Computer Science and its Applications, CSA 2022 and the 16th KIPS international conference on Ubiquitous Information Technologies and Applications, CUTE 2022

作者： Hong, Dae Hwa Kim, Sin Yeong Park, Min Kyu Oh, Se Jong Doo, Ill Chul Department of German Hankuk University of Foreign Studies Seoul Korea Republic of Department of Statistics Hankuk University of Foreign Studies Yongin Korea Republic of Artificial Intelligence Education Hankuk University of Foreign Studies Yongin Korea Republic of

ISBN: (纸本)9789819912513

Collecting skin burn image data that is treated as medical data is generally restricted to medical practitioners. Labeling them is even more challenging since it requires professionals to review the whole process of detecting burn area and classifying its degree. A typical machine learning model trained with a small dataset gathered by non-professionals does not guarantee sufficient performance since they are mostly left unlabeled. data augmentation on images leads to overcoming the limitations of a small dataset. Semi-supervised learning and knowledge distillation enable the application of unlabeled data. This study examines a combination of various augmentation and machine learning methods to maximize performance on detection and classification. Having an F1 score of 38.0% in the supervised learning model without any treatment, in comparison, the experimental results showed an F1 score of 57.5% in the semi-supervised learning which accumulates distilled unlabeled data and augmented labeled data using rotation, flip, noising, and cutout methods. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Cascade width learning based fatigue detection method

Cascade width learning based fatigue detection method

引用

2024 international conference on Optics, Electronics, and Communication engineering, OECE 2024

作者： Wang, Dong Wu, Pianhui Big Data and Computing Institute Guangdong Baiyun University Guangdong Guangzhou510450 China School of Mechatornic Engineering Guangdong Polytechnic Normal University Guangdong Guangzhou510450 China

ISBN: (纸本)9781510685437

The fatigue detection method based on neural network has been widely applied in the field of land transportation. The accuracy varies by different methods and solutions. Disadvantages of current widely applied methods for fatigue detection have been exposed by rational review, e.g., cost-effective, potable implementation issues. Cascade width learning based detection method with outstanding features is a sound solution to overcome shortcomings of other traditional detection methods. Therefore, it is of great significance and value to research this method and present its academic value and applicable values. This paper introduces a cascade width learning based fatigue detection method. The paper looks forward to development of cascade width learning based fatigue detection method, both academic and applicable values of proposed method have been presented by rational evaluation based on rational discussion on experimental results, the results prove that proposed method has achieved 94.9% accuracy in 52.43ms, which suggests more accuracy and fast speed than other common methods including: combinations of LBP and SVM, ASM and Fuzzy, CNN and PERCLO. © 2024 SPIE.

关键词： Eye Material fatigue machine learning Mouth Head Neural networks Education and training Signal detection Video Visualization

来源：评论

学校读者我要写书评

暂无评论

Application of multi-machine power system supervised machine-learning in error correction of electromechanical sensors

引用

ENERGY REPORTS 2022年 8卷 1381-1391页

作者： Yu, Linlin Su, Li Qin, Fang Wang, Lijuan Dalian Univ Sci & Technol Dalian Peoples R China

The shortage of electric energy in the supply process and supply interruption will not only directly affect the production level of all walks of life, but also affect the normal life order, and cause adverse effects on the development of the whole society. In order to ensure the stable operation of the system under the premise of ensuring safety, the actual control system is often affected by constraints. In this paper, the intelligent control strategy based on supervised machine learning is used to restrict the output of the system. The back stepping method and Lyapunov method are used to design the control, and then the supervised machine learning sensor of multi-machine power system under the constraint condition is optimized and improved. By introducing the k-class function adjusted according to the error, the system gain is automatically corrected. The simulation results show that the designed controllers can ensure that the output of the speed difference of the system is in the constrained range. Through comparison, it is concluded that the constrained fuzzy adaptive controller can further improve the rotation speed of the speed difference, reduce the vibration amplitude of the speed difference, and achieve better results. (C) 2022 The Author(s). Published by Elsevier Ltd.

关键词： Power system Electromechanical sensor Vibration error machine learning Rotation rate correction

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：