检索结果-内蒙古大学图书馆

2024 Asian Conference on Intelligent Technologies, ACOIT 2024

作者： Evangelin Sonia, S.V. Beulah Christalin Latha, C. Venkatesan, R. Naveen Sundar, G. Shirley, C.P. Harris Stuart, E. Div. of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India Div. of Digital Sciences Karunya Institute of Technology and Sciences Coimbatore India

ISBN: (纸本)9798350374933

Wearable motion capture technology has advanced significantly, enabling detailed and accurate tracking of human movements in three-dimensional space. This paper introduces FocusRec RNN, an innovative Recurrent Neural Network (RNN) architecture designed to enhance the reconstruction and prediction of 3D human poses using wearable IMU sensors. By incorporating a focus mechanism that dynamically prioritizes critical time-steps and body segments, FocusRec RNN improves upon traditional methods in terms of accuracy and robustness. Evaluation on datasets such as Human3.6M and the CMU Motion Capture Database demonstrates that FocusRec RNN achieves lower Mean Absolute Error (MAE) and Root Mean Square Error (RMSE), alongside higher Percentage of Correct Keypoints (PCK) compared to traditional RNNs, LSTM networks, and CNN-based approaches. These improvements highlight FocusRec RNN's potential for applications in sports performance analysis, medical diagnostics, rehabilitation, and interactive entertainment. © 2024 IEEE.

关键词： Motion capture

来源：评论

学校读者我要写书评

暂无评论

Machine-Learning-Assisted Optimization of Type-II Superlattices for Enhanced Vertical Hole Mobility 23

Machine-Learning-Assisted Optimization of Type-II Superlatti...

引用

23rd International Conference on Numerical Simulation of Optoelectronic Devices, NUSOD 2023

作者： Glennon, John Bellotti, Enrico Boston University Div. of Material Science and Engineering BostonMA02215 United States Boston University Div. of Material Science and Engineering Dep. of Electrical and Computer Engineering BostonMA02215 United States

ISBN: (纸本)9798350314298

Gaussian process regression is used to develop a model for predicting the superlattice (SL) structures grown on a 6.3 Å lattice. This model is used to search for optimized hole transport properties. Nonequilibrium Green's functions calculations are used to determine the vertical hole mobility of the structure which is compared with both the calculated and experimental results for an experimental SL grown on a GaSb substrate. Ultimately, a simple analytical model is used to approximate and compare the quantum efficiency of a photodiode containing each structure demonstrating an improvement in device performance using the optimized SL structure. © 2023 IEEE.

关键词： Gallium compounds

来源：评论

学校读者我要写书评

暂无评论

XPM: eXplainable Process Mining 3rd

XPM: eXplainable Process Mining

引用

3rd International Conference on Advances in Information and Communication Technology, ICTA 2024

作者： Kim, Kwanghoon Pio CCSRI Kyonggi University Suwon Korea Republic of Data. Process Engineering Research Lab. Div. of AI Computer Science and Engineering Kyonggi University Gyeonggi Suwon16227 Korea Republic of

ISBN: (纸本)9783031809422

This keynote speech is to all intents and purposes introducing a new process mining approach and its implemented system, which are named as eXplainable process mining (XPM) approach and system, respectively. Through the XPM approach, we can selectively amalgamate a group of process event log traces, and through the XPM system, we can ultimately discover a series of complete and safe process models from a process enactment event log dataset. The XPM approach is theoretically based on the typical process modeling methodology of structured information control nets (abbreviated as SICN) and its algorithmic functionality is substantiated by the explainable ρ-Algorithm that is extended from the original ρ-Algorithm [6]. This keynote speech is also explicating the proven process mining algorithm that is able to discover the underlying SICN-oriented process model from a dataset of process enactment event logs and histories. More specifically, the concrete goal of this keynote speech is about an explainable way of discovering the complete structural formation of SICN-oriented process model. Assume that the structural formation is made up of an arbitrary number of combinational building blocks of the primitive process patterns such as linear (sequential), disjunctive (exclusive-OR), conjunctive (parallel-AND), and repetitive (iterative-LOOP) process patterns. Conclusively, it would be emphasized that the XPM approach and system ought to be very effective and well-fitted for managing life-cycles of very large-scale process models deployed in process-aware enterprises and organizations. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Quantum transport simulation of a mid-wave infrared Ga-based type-II superlattice for curved focal-plane arrays 13

Quantum transport simulation of a mid-wave infrared Ga-based...

引用

Infrared Sensors, Devices, and Applications XIII 2023

作者： Glennon, John Bellotti, Enrico Div. of Material Science and Engineering Boston University BostonMA02215 United States Dept. of Electrical and Computer Engineering Boston University BostonMA02215 United States

ISBN: (纸本)9781510665880

Type-II strained-layer superlattices have theoretically predicted advantages that make them an attractive material system for use in infrared technology. However, the influence of structural disorder has been demonstrated to negatively impact the performance of these materials. A recent development in infrared technology is the use of curved focal-plane arrays which promise improved uniformity of sensitivity and a reduction in the optical complexity of the device. Curving of the wafer introduces mechanical strain into the absorber layer which can also impact the vertical carrier mobility. This work reports on an analysis of the influence of external strain and disorder on the vertical hole mobility in curved focal-plane arrays utilizing a mid-wave InAs/GaSb absorber layers. A series of quantum transport calculations is performed over a range of strain configurations for two different structures: an ideal superlattice and a superlattice with graded interfaces and disorder. Finally, the impact these effects have on the quantum efficiency of a hypothetical curved-FPA is approximated, and a potential avenue for improved device design is suggested. © 2023 SPIE. All rights reserved.

关键词： Quantum efficiency

来源：评论

学校读者我要写书评

暂无评论

FocusRec RNN: Enhancing 3D Human Pose Reconstruction and Prediction with Wearable Motion Capture Technology

FocusRec RNN: Enhancing 3D Human Pose Reconstruction and Pre...

引用

Intelligent Technologies (ACOIT), Asian Conference on

作者： S.V. Evangelin Sonia C Beulah Christalin Latha R. Venkatesan G.Naveen Sundar C.P. Shirley E Harris Stuart Div. of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore Div. of Digital Sciences Karunya Institute of Technology and Sciences Coimbatore

ISBN: (数字)9798350374957

ISBN: (纸本)9798350374964

Wearable motion capture technology has advanced significantly, enabling detailed and accurate tracking of human movements in three-dimensional space. This paper introduces FocusRec RNN, an innovative Recurrent Neural Network (RNN) architecture designed to enhance the reconstruction and prediction of 3D human poses using wearable IMU sensors. By incorporating a focus mechanism that dynamically prioritizes critical time-steps and body segments, FocusRec RNN improves upon traditional methods in terms of accuracy and robustness. Evaluation on datasets such as Human3.6M and the CMU Motion Capture Database demonstrates that FocusRec RNN achieves lower Mean Absolute Error (MAE) and Root Mean Square Error (RMSE), alongside higher Percentage of Correct Keypoints (PCK) compared to traditional RNNs, LSTM networks, and CNNbased approaches. These improvements highlight FocusRec RNN’s potential for applications in sports performance analysis, medical diagnostics, rehabilitation, and interactive entertainment.

关键词： Recurrent neural networks Three-dimensional displays Accuracy Tracking Computational modeling Motion capture Artificial intelligence Wearable sensors Standards Sports

来源：评论

学校读者我要写书评

暂无评论

TripletGAN VeinNet: Palm vein recognition based on generative adversarial network and triplet loss

TripletGAN VeinNet: Palm vein recognition based on generativ...

引用

2021 International Conference on computer engineering and Artificial Intelligence, ICCEAI 2021

作者： Htet, Aung Si Min Lee, Hyo Jong Jeonbuk National University Div. of Computer Science and Engineering Jeonju Korea Republic of Jeonbuk National University Acceptable Div. of Computer Science and Engineering Jeonju Korea Republic of

ISBN: (纸本)9781665439602

In recent years, palm vein recognition has obtained significant attention as its uniqueness, stable features, and high recognition rate. Although state-of-art deep learning methods can outperform several research domains, the lack of sufficiently large data for vein-based biometric recognition can suffer from generalization problems and degrades the model accuracy. Our approach trained Generative Adversarial Nets (GAN) with triplet loss for classification as an additional task. Lately, triplet networks are widely applied as it learns the latent space representation between neighbors and performs significantly higher accuracy even for insufficient data size. Moreover, in practical application, the quality of acquired vein images is low due to external factors and affects the recognition accuracy. To overcome this problem, we propose a CNN-based Encoder-Decoder network for vein segmentation to utilize the accuracy performance. Jerman enhancement filter is applied to enhance the vein ROI images for labeling the ground truth mask images for training the Encoder-Decoder network. © 2021 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Personalized Stress Detection using a Lightweight Machine Learning Framework With Convenient Wrist-Worn Sensors

Personalized Stress Detection using a Lightweight Machine Le...

引用

2024 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2024

作者： Hasan, M. Mithun, S. Mahmud, M. Baral, S. Poudel, K. Middle Tennessee State University Computational And Data Science MurfreesboroTN United States University Of Memphis Dept. Of Computer Science TN United States University Of Memphis Dept. Of Electrical And Computer Engineering TN United States Middle Tennessee State University Dept. Of Computer Science MurfreesboroTN United States Univ. Of Tennessee Health Science Center Div. Of General Internal Medicine MemphisTN United States

ISBN: (纸本)9798350388572

Over 70% Americans experience daily stress, making real-time, accurate stress detection crucial for timely intervention, and promoting physical and mental well-being. In this study, we detect stress using machine learning from publicly available wrist-worn sensor data. We examined both population and indiv.dual levels, focusing on simple, computation friendly statistical features for reduced processing to facilitate adoptions in real-life mHealth applications. Our framework demonstrates that stress detection achieves over 96% accuracy at both the population and indiv.dual levels, with the Extreme Gradient Boosting classifier achieving the highest predictive accuracy. We found significant variability between indiv.duals and achieved an average accuracy of 99.63% with area under the curve (AUC) 99.23%, F1-score 99.00%, precision, and recall 99.22%. This approach offers a promising solution for real-life stress detection due to its high accuracy and simplicity. © 2024 IEEE.

关键词： LightGBM Machine learning Personalization Stress detection Wrist-band sensors

来源：评论

学校读者我要写书评

暂无评论

Fast Dynamic Time Warping for Temperature Compensation in Guided Waves

e-Journal of Nondestructive Testing

引用

e-Journal of Nondestructive Testing 2024年第6期29卷

作者： Kumar, Narendra Gupta, Payal Carlson, Johan E. Department of Computer Science Electrical and Space Engineering Div. of Signals and Systems Luleå University of Technology Luleå Sweden

The paper discusses Structural Health Monitoring (SHM) based on ultrasonic guided waves for damage detection in structures. Guided waves allow inspection over long distances and inaccessible features, but are also sensitive to changes in environmental and operating conditions (EOC). The focus of this paper is on temperature compensation methods for guided waves. The compensation techniques include Baseline Signal Stretch (BSS), Optimal Baseline Selection (OBS), OBS+BSS, and Dynamic Time-Warping (DTW). In particular, a new, fast approximation of DTW is evaluated and compared with conventional but computationally expensive DTW. The FDTW algorithm utilizes a multilevel approach inspired by graph bisection principles to achieve precise warping path determination with linear computational complexity. The study evaluates the compensation performance of FDTW using a single baseline at a single temperature, thus addressing the complexity and inaccessibility issues of obtaining an extensive database of baseline signals in practical applications. The Open Guided Wave (OGW) dataset is employed for a fair comparison with other compensation methods. Results indicate that FDTW performs well, demonstrating comparable warping performance to DTW but with significantly reduced computational complexity. The analysis also includes comparisons with BSS, OBS+BSS, and DTW across a range of temperatures, highlighting the effectiveness of FDTW in mitigating errors introduced by larger temperature variations. © 2024 The Authors.

关键词： Structural health monitoring

来源：评论

学校读者我要写书评

暂无评论

Machine-Learning-Assisted Optimization of Type-II Superlattices for Enhanced Vertical Hole Mobility

Machine-Learning-Assisted Optimization of Type-II Superlatti...

引用

International Conference on Numerical Simulation of Optoelectronic Devices, (NUSOD)

作者： John Glennon Enrico Bellotti Div. of Material Science and Engineering Boston University Boston Massachusetts USA Dep. of Electrical and Computer Engineering Div. of Material Science and Engineering Boston University Boston Massachusetts USA

Gaussian process regression is used to develop a model for predicting the superlattice (SL) structures grown on a 6.3 Å lattice. This model is used to search for optimized hole transport properties. Nonequilibrium Green’s functions calculations are used to determine the vertical hole mobility of the structure which is compared with both the calculated and experimental results for an experimental SL grown on a GaSb substrate. Ultimately, a simple analytical model is used to approximate and compare the quantum efficiency of a photodiode containing each structure demonstrating an improvement in device performance using the optimized SL structure.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Time-Series Process Event Log Preprocessing Approach for Data-Intensive and Predictive Operationalization of Smart Factories 24

A Time-Series Process Event Log Preprocessing Approach for D...

引用

24th International Conference on Advanced Communication Technology, ICACT 2022

作者： Park, Minjae Park, Sohyang Nguyen, Thanh-Hai Pham, DInh-Lam Oh, Dongkeun Kim, Kyoung-Sook Chun, In-Kyoo Kim, Kwanghoon Pio DAELIM UNIVERSITY COLLEGE Div. of Computer Information Gyeonggi Anyang13916 Korea Republic of KYONGGI UNIVERSITY Div. of AI Computer Science Engineering Gyeonggi Suwon16227 Korea Republic of KYONGGI UNIVERSITY Div. of AI Computer Science Engineering Gyeonggi Suwon16227 Korea Republic of Smart Factory Research Institute ICIT Co. Guro Seoul08377 Korea Republic of Smart Factory Research Institute ICIT Co. Guro Seoul08377 Korea Republic of

ISBN: (纸本)9791188428090

This paper proposes a time-series process event log preprocessing approach applied to realize data-intensive and predictive operationalization of IoT-supported smart factories. The advanced conceptual approach of the data-intensive and predictive operationalization processes is newly proposed for effectively and predictively operating very large-scale smart factories that are supported by the Internet of Things platforms with temporal operationalization processes and their time-series event log datasets. The authors' research group is trying to develop a predictive smart factory operationalization system, which is characterized by the advanced conceptual approach, and the starting point of which is at acquiring the time-series process event log datasets with a proper data preprocessing approach. Hence, this paper devises a time-series process event log preprocessing approach with its algorithmic details to arrange the proper datasets to be used for concretizing the data-intensive and predictive operationalization in the very large-scale smart factories. Finally, we develop an XES-formatted event log preprocessing system based upon the devised preprocessing algorithms and apply to a real and nation-wide production smart factory in order to validate the operationality and feasibility of the developed system. © 2022 Global IT Research Institute-GiRI.

关键词： Time series

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：