检索结果-内蒙古大学图书馆

4th IEEE international conference on Power, Electronics and Computer applications, ICPECA 2024

作者： Chen, Yaqi Luo, Chan He, Zijie Shu, Zhong School of Electronic Information Engineering Jingchu University of Technology Hubei Jingmen China Jingmen Rongmedia Network Technology Co. Ltd Hubei Jingmen China

ISBN: (纸本)9798350359589

this paper utilizes the Stacked Denoising Auto Encoder (SDAE) model to capture the general edge features of images. Additionally, it employs the Convolutional Neural Networks model to extract fine edge features from medical images. By combining preference learning algorithms, the paper implements an image retrieval system and designs a medical image retrieval model termed SDAE+CNN+Preference learning. In the design of the reconstruction residual function in the SDAE model, noise factors are introduced to ensure the accuracy of image feature extraction by accounting for the impact of noise. Adjustments have been made to the structure of the CNN model, specifically in the convolutional layers, pooling layers, and fully connected layers. these adjustments aim to further enhance the accuracy of image feature extraction and ensure the precision of image feature classification. By conducting learning training on key parameters, an optimal preference learning model is obtained. Following the rules for matching the category attributes of input images with those in the medical image database and optimizing the loss function of the preference learning model, the similarity of category attributes for images is ranked. Ultimately, images with higher category attribute similarity are listed as retrieval results. Relevant experiments indicate that the proposed SDAE+CNN image feature extraction module in this paper achieves high accuracy in extracting image features, effectively controlling the influence of image noise;the designed SDAE+CNN+Preference learning medical image retrieval model achieves a retrieval similarity of 96%, a retrieval accuracy of 94%, and a retrieval recall rate of 95%, as per the conducted experiments. © 2024 IEEE.

关键词： Convolutional Neural Networks Image Retrievalt Preference learning Stacked Denoising Auto Encoder

来源：评论

学校读者我要写书评

暂无评论

HLS Based Design and optimization of Merge Sort Algorithm for High Performance Computing 4

HLS Based Design and Optimization of Merge Sort Algorithm fo...

引用

4th international conference for Emerging Technology, INCET 2023

作者： Rani, P. Asha Chinnaiah, M.C. Kumari, Apurva Preethika, G. Reddy, Y. Prem Kumar B V Raju Institute of Technology Department of ECE Narsapur India

ISBN: (纸本)9798350335750

High level synthesis has emerged as a powerful tool for designing hardware algorithms for high performance computing systems. In this paper, we present an HLS based design and optimization of the merge sort algorithm for HPC applications. We use Xilinx's Vivado HLS tool to generate hardware description language code from C based descriptions of the algorithm, and then optimize the code for throughput and latency using HLS directives. Our results demonstrate that the optimized merge sort algorithm provides a significant improvement in performance over traditional software-based implementations. Our work contributes to the growing body of research on using HLS for HPC applications. the proposed HLS based design and optimized merge sort algorithm shows the results like area usage, latency, efficiency, throughput in comparison with unoptimized merge sort. © 2023 IEEE.

关键词： High level synthesis

来源：评论

学校读者我要写书评

暂无评论

Kinect therapeutic Game STEAM-Based learning for Autism Spectrum Disorder (ASD) Students 4

Kinect Therapeutic Game STEAM-Based Learning for Autism Spec...

引用

4th international conference on Emerging Smart Technologies and applications (eSmarTA)

作者： Febry, Dea Muthia Haryani, Fairusy Fitria Rahmawati, Karisma Dewi, Nadia Pramugarini Mutiara Yulandari, Esti Hendix, Andreas Sebelas Maret Univ Phys Educ Surakarta Indonesia Sebelas Maret Univ Bahasa Educ Surakarta Indonesia Sebelas Maret Univ Informat Engn Surakarta Indonesia

ISBN: (纸本)9798350354140;9798350354133

Students with Autism Spectrum Disorder (ASD) experience difficulties in their learning process because they have impairments in cognitive development, adaptive behaviour, focus/attention, and psychomotor problems. Using technology-based learning media can be an effective solution in helping ASD students overcome their learning challenges. this research aims to develop the "Kinect therapeutic Games" learning media by integrating STEAM (Science, Technology, Engineering, Art, and Mathematics). the ADDIE (Analysis, Design, Development, Implementation, Evaluation) approach was the development model used in developing the media. Six ASD students at Special School Mitra Amanda in Surakarta, Indonesia, were the subjects of this research. the result shows that achieving by using the learning media also requires a good balance of psychomotor, attention, and cognitive abilities. For Science, Technology, and Engineering, as many as 4 out of 6 students or more than half of the students in one class, have good results. Only 2 out of 6 students, or 33,33%, have good numeracy skills when using the learning media. Half or 50% of students in a class could achieve aspects of art related to imagination and creativity. It can be concluded that learning media can support STEAM aspects, but not all students can achieve them. Only 2 out of 6 students could accomplish all of the STEAM aspects.

关键词： Kinect therapeutic game autism spectrum disorder STEAM learning media

来源：评论

学校读者我要写书评

暂无评论

Enhancing Machine learning Models through Hyperparameter optimization with Particle Swarm optimization 10

Enhancing Machine Learning Models through Hyperparameter Opt...

引用

10th international conference on Computer, Control, Informatics and its applications, IC3INA 2023

作者： Indrawati, Ariani Wahyuni, Intan N. Research Center for Data and Information Science National Research and Innovation Agency Indonesia Research Center for Computing National Research and Innovation Agency Indonesia

ISBN: (纸本)9798350394870

Hyperparameter tuning plays a crucial role in optimizing the performance of machine learning algorithms. this study explores the effectiveness of Particle Swarm optimization (PSO) in fine-Tuning the hyperparameters of three popular machine learning algorithms, including Random Forest, K-Nearest Neighbors, and Support Vector Machine. the studies use two publicly available datasets: the Heart Failure Clinical Records Dataset and the Iris Dataset. For additional comparative analysis, we also compare with the common optimization technique using Random Search. the result reveals that PSO and Random Search have varying impacts on the performance of different algorithms and datasets. the findings provide valuable insights into the behavior of different optimization techniques and their effect on model performance, paving the way for better and more reliable machine learning models in various domains. through effective hyperparameter optimization, machine learning models can achieve enhanced accuracy. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Research on Magnetic Field optimization of Dual Body Ultra-High Voltage Shunt Reactors Based on Magnetic Shunt Structure 4

Research on Magnetic Field Optimization of Dual Body Ultra-H...

引用

4th IEEE international conference on Power, Electronics and Computer applications, ICPECA 2024

作者： Zhu, Kaizhuang Guo, Jiayi Zhang, Zikang North China Electric Power University Hebei Provincial Key Laboratory of Power Transmission Equipment Security Defense Baoding China

ISBN: (纸本)9798350359589

this paper presents a study on the optimization of the magnetic shunt structure for ultra-high voltage oil-immersed dual-body reactors. Firstly, a three-dimensional finite element simulation model was established for the reactors with rectangular and arc-shaped magnetic shunt configurations, and a magnetic field calculation method was proposed based on this model. Subsequently, the influence of magnetic shunt structure parameters on the maximum magnetic field was investigated. By varying parameters such as magnetic shunt thickness, radius, and side length, the distribution of the primary magnetic flux inside the reactor under different magnetic shunt structures was compared. Based on the research findings, an optimized design scheme for the magnetic shunt was proposed. Comparative analysis with existing magnetic shunt design schemes for reactors demonstrated that the proposed magnetic shunt structure reduced the maximum value of the arc-shaped magnetic shunt by 14.95% and the rectangular magnetic shunt by 16.84%, while maintaining the average value of the primary magnetic flux essentially unchanged. Furthermore, the proposed design achieved a more uniform distribution of the primary magnetic flux inside the reactor. this study provides valuable insights for the optimization of the magnetic shunt structure in ultra-high voltage oil-immersed reactors within the field of electrical engineering. © 2024 IEEE.

关键词： finite element analysis magnetic field magnetic shunt Ultra high voltage shunt reactor

来源：评论

学校读者我要写书评

暂无评论

Greedy Guarantees for Non-submodular Function Maximization Under Independent System Constraint with applications

引用

JOURNAL OF optimization thEORY AND applications 2023年第2期196卷 516-543页

作者： Shi, Majun Yang, Zishen Wang, Wei Xi An Jiao Tong Univ Sch Math & Stat 28 Xianning West Rd Xian 710049 Peoples R China

We study the problems of maximizing a monotone non-submodular function subject to two types of constraints, either an independent system constraint or ap-matroidconstraint. these problems often occur in the context of combinatorial optimization, operations research, economics and especially, machine learning and data science. Using the generalized curvature alpha and the submodularity ratio gamma or the diminishingreturns ratio xi, we analyze the performances of the widely used greedy algorithm, which yields theoretical approximation guarantees of 1/alpha[1-(1-alpha gamma/K)(k)]and xi/p+alpha xi for the two types of constraints, respectively, where k ,K are, respectively, the min-imum and maximum cardinalities of a maximal independent set in the independent system, and p is the minimum number of matroids such that the independent sys-tem can be expressed as the intersection of p matroids. When the constraint is acardinality one, our result maintains the same approximation ratio as that in Bian etal. (Proceedings of the 34th international conference on machine learning, pp 498-507, 2017);however, the proof is much simpler owning to the new definition of the greedy curvature. In the case of a single matroid constraint, our result is competitive compared with the existing ones in Chen et al. (Proceedings of the 35th international conference on machine learning, pp 804-813, 2018) and Gatmiry and Rodriguez (Non-submodular function maximization subject to a matroid constraint, with applications,***:1811.07863v4). In addition, we bound the generalized curvature, thesubmodularity ratio and the diminishing returns ratio for several important real-worldapplications. Computational experiments are also provided supporting our analyses.

关键词： Non-submodular function Independent system p-matroid Greedy algorithm

来源：评论

学校读者我要写书评

暂无评论

Foreign Exchange Market Analysis based on Novel Grey Wolf based Extreme learning Machine Predictor 4

Foreign Exchange Market Analysis based on Novel Grey Wolf ba...

引用

4th international conference on Emerging Systems and Intelligent Computing, ESIC 2024

作者： Dash, Swaty Sahu, Pradip Kumar Mishra, Debahuti Veer Surendra Sai University of Technology Burla Dept. of Information Technology Odisha Sambalpur India University Dept. of Computer Science & Engineering Odisha Bhubaneswar India

ISBN: (纸本)9798350349856

Foreign exchange trading basically bridges a gap between buyer and seller to transact at a set of prices of the currencies to make profit out of it by the traders and investors. In this paper, foreign exchange predictive models are explored based on basic Extreme learning Machine (ELM) along with optimized version of ELM. Initially, this work tried to obtain the best optimized ELM network based upon the four nature-inspired optimization methodologies such as;particle swarm, ant colony, moth flame and grey wolf optimization (GWO). From this phase, it has been observed that the ELM network optimized with GWO outperforms rest of other experimented optimized ELM networks with respect to error graphs and performance metrics. In order to evaluate the performance, the ELM-GWO currency exchange predictor, the recognition performance metrics such as;EVS, MAE, MSE and R2 Score are computed, the error graphs are obtained and the average computational time taken are compared. © 2024 IEEE.

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

Realistic Model Parameter optimization: Shadow Robot Dexterous Hand Use-Case 3rd

Realistic Model Parameter Optimization: Shadow Robot Dextero...

引用

3rd international conference on optimization, learning algorithms and applications (OL2A)

作者： Correia, Tiago Ribeiro, Francisco M. Pinto, Vitor H. Univ Porto Fac Engn SYSTEC DIGI2 ARISE & ECE Dept Rua Dr Roberto Frias P-4200465 Porto Portugal

ISBN: (纸本)9783031530357;9783031530364

the notable expansion of technologies related to automated processes has been observed in recent years, largely driven by the significant advantages they provide across diverse industries. Concurrently, there has been a rise in simulation technologies aimed at replicating these complex systems. Nevertheless, in order to fully leverage the potential of these technologies, it is crucial to ensure the highest possible resemblance of simulations to real-world scenarios. In brief, this work consists of the development of a data acquisition and processing pipeline allowing a posterior search for the optimal physical parameters in MuJoCo simulator to obtain a more accurate simulation of a dexterous robotic hand. In the end, a Random Search optimization algorithm was used to validate this same pipeline.

关键词： optimization realistic simulation model pipeline

来源：评论

学校读者我要写书评

暂无评论

Satellite Imagery and Deep learning Combined for Wheat Yield Forecasting 4th

Satellite Imagery and Deep Learning Combined for Wheat Yield...

引用

4th international conference on Digital Technologies and applications (ICDTA)

作者： Boukhris, Abdelouafi Antari, Jilali Sadiq, Abderrahmane Ibnou Zohr Univ Polydisciplinary Fac Taroudant Lab Comp Syst Engn Math & Applicat ISIMA BP 8106 Agadir Morocco

ISBN: (纸本)9783031686740;9783031686757

In the context of effective resource management and ensuring nutritional stability, precise forecasting of crop yields becomes essential. the development of artificial intelligence methodologies, coupled with satellite imagery, has emerged as a powerful strategy for predicting crop yields in modern times. In this study, deep learning algorithms based on LSTM (Long Short-Term Memory) were developed to efficiently optimize and extract from Sentinel-2 data spatiotemporal information of wheat yield. To estimate accurately wheat yield in Morocco, several machine learning and deep learning techniques such as Random Forest, LSTM, Bi-LSTM (Bidirectional LSTM), stacked LSTM, etc. were used and compared. the optimized Bi-LSTM model accurately estimates wheat yield based on NDVI (normalized difference vegetation index) data and weather data (temperature, precipitation). three datasets gathered from satellite imagery were used which are temperature data, precipitation data and NDVI data combined for training and testing the proposed model. After data processing, different machine learning and deep learning algorithms were compared, and the result showed that Bi-LSTM estimates wheat yield accurately. the proposed and optimized Bi-LSTM model reached a satisfactory accuracy at the sizable regional scale. the obtained result demonstrates that the RMSE (Root Mean Square Error) score was 6.22 and the loss was 6.61 center dot 10(-4) after 20 epochs of training the proposed model, which overcomes most of the existing methods.

关键词： Bi-LSTM KNN (K-Nearest Neighbor) Vegetation Indices Machine learning Deep learning

来源：评论

学校读者我要写书评

暂无评论

4th international conference on Emerging Smart Technologies and applications, eSmarTA 2024

4th International Conference on Emerging Smart Technologies ...

引用

4th international conference on Emerging Smart Technologies and applications, eSmarTA 2024

ISBN: (纸本)9798350354133

the proceedings contain 81 papers. the topics discussed include: imaging modalities in brain cancer detection and diagnosis;exploring metaverse dynamics in supply chain: a bibliometric analysis;towards a lightweight detection system leveraging ranking techniques with wrapper feature selection algorithm for selective forwarding attacks in low power and lossy networks of IoTs;kidney disease classification and diagnosis: a comprehensive review of current AI techniques;sensorless direct torque control in brushless DC motor using sliding mode observer;real-time diabetes detection using machine learning and Apache spark;agile ontology: a dynamic framework for e-business evolution;the role of YOLOv8 in enhancing strategic military equipment detection;and evaluating artificial intelligence bias in answering religious questions.

关键词：

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：