检索结果-内蒙古大学图书馆

Big Data Analytics and Practices (IBDAP), International Conference on

作者： Sakorn Mekruksavanich Ponnipa Jantawong Anuchit Jitpattanakul Department of Computer Engineering School of Information and Communication Technology University of Phayao Phayao Thailand Department of Mathematics Faculty of Applied Science Intelligent and Nonlinear Dynamic Innovations Research Center King Mongkut's University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9798350391749

ISBN: (纸本)9798350391756

The application of wearable sensors to identify physical activities has drawn significant attention in the healthcare and fitness industries. This study presents a novel ensemble deep learning network to enhance the accuracy of physical movement recognition utilizing data from inertial measurement unit (IMU) sensors. The proposed Ens-CNN-LSTM method merges a convolutional neural network (CNN) with a long short-term memory (LSTM) network. This integration capitalizes on their strengths in analyzing sequential IMU data. The model further incorporates a random forest classifier to finalize predictions. Our proposed model was evaluated using the PAMAP2 benchmark dataset for human activity recognition. This dataset includes data from multiple individuals performing various activities recorded with IMU sensors. We assessed the ensemble model's performance against individual deep learning models through a 5-fold cross-validation method. Results reveal a significant enhancement in overall accuracy, achieving 99.63%, compared to 96.19% for CNN models and 97.35% for LSTM models. The Ens-CNN-LSTM model demonstrated remarkable performance with an accuracy of 99.61%, a recall of 99.63%, and an F1-score of 99.61%. It surpassed the individual models in all metrics. Furthermore, the ensemble model showed increased robustness to variations among individuals and noise in sensor data. The proposed approach improves the accuracy of physical activity recognition and extends its applicability to other domains and activities.

关键词： Deep learning Accuracy Noise Predictive models Robustness Convolutional neural networks Object recognition

来源：评论

学校读者我要写书评

暂无评论

Prescribing Decision Conservativeness in Two-Stage Power Markets: A Distributionally Robust End-to-End Approach

arXiv

引用

arXiv 2024年

作者： Liang, Zhirui Li, Qi Liu, Anqi Dvorkin, Yury Department of Electrical and Computer Engineering Johns Hopkins University BaltimoreMD United States Department of Applied Mathematics and Statistics Johns Hopkins University BaltimoreMD United States Department of Computer Science Johns Hopkins University BaltimoreMD United States Department of Civil and System Engineering Johns Hopkins University BaltimoreMD United States

This paper presents an end-to-end framework for calibrating wind power forecast models to minimize operational costs in two-stage power markets, where the first stage involves a distributionally robust optimal power flow (DR-OPF) model. Unlike traditional methods that adjust forecast parameters and uncertainty quantification (UQ) separately, this framework jointly optimizes both the forecast model parameters and the decision conservativeness, which determines the size of the ambiguity set in the DR-OPF model. The framework aligns UQ with actual uncertainty realizations by directly optimizing downstream operational costs, a process referred to as costoriented calibration. The calibration is achieved using a gradient descent approach. To enable efficient differentiation, the DROPF problem is reformulated into a convex form, and the Envelope Theorem is leveraged to simplify gradient derivation in the two-stage setting. Additionally, the framework supports distributed implementation, enhancing data privacy and reducing computational overhead. By proactively calibrating forecast parameters and prescribing optimal decision conservativeness, the framework significantly enhances cost efficiency and reliability in power system operations. Numerical experiments on an IEEE 5-bus system demonstrate the effectiveness and efficiency of the proposed approach. Copyright © 2024, The Authors. All rights reserved.

关键词： Wind forecasting

来源：评论

学校读者我要写书评

暂无评论

MASTER: Machine Learning-Based Cold Start Latency Prediction Framework in Serverless Edge Computing Environments for Industry 4.0

IEEE Journal of Selected Areas in Sensors

引用

IEEE Journal of Selected Areas in Sensors 2024年 1卷 36-48页

作者： Muhammed Golec Sukhpal Singh Gill Huaming Wu Talat Cemre Can Mustafa Golec Oktay Cetinkaya Felix Cuadrado Ajith Kumar Parlikad Steve Uhlig School of Electronic Engineering and Computer Science Queen Mary University of London London U.K. Abdullah Gul University Kayseri Türkiye Center for Applied Mathematics Tianjin University Tianjin China TFI TAB Food Investments Istanbul Türkiye Faculty of Engineering Computer Engineering Dumlupınar University Kütahya Türkiye Oxford e-Research Centre (OeRC) Department of Engineering Science University of Oxford Oxford U.K. School of Telecommunications Engineering Technical University of Madrid (UPM) Madrid Spain Institute for Manufacturing Department of Engineering University of Cambridge Cambridge U.K.

The integration of serverless edge computing and the Industrial Internet of Things (IIoT) has the potential to optimize industrial production. However, cold start latency is one of the main challenges in this area, resulting in resource waste. To address this issue, we propose a new machine learning-based resource management framework called MASTER which utilizes an extreme gradient boosting (XGBoost) model to predict the cold start latency for Industry 4.0 applications for performance optimization. Furthermore, we created a new cold start dataset using an IIoT scenario (i.e. predictive maintenance) to validate the proposed MASTER framework in serverless edge computing environments. We have evaluated the performance of the MASTER framework using a real-world serverless platform, Google Cloud Platform for single-step prediction (SSP) and multiple-step prediction (MSP) operations and compared it with existing frameworks that used deep deterministic policy gradient (DDPG) and long short-term memory (LSTM) models. The experimental results show that the XGBoost-based resource management framework is the most successful model in predicting cold start with mean absolute percentage error (MAPE) values of 0.23 in SSP and 0.12 in MSP. It has been also identified that the Linear Regression model (utilized in the MASTER framework) has the least computational time (0.03 seconds) as compared to other deep learning and machine learning models considered in this work. Finally, we compare the energy consumption and $\text{CO}_{2}$ emissions of all models to emphasize resource awareness.

关键词： Containers Industrial Internet of Things Edge computing Fourth Industrial Revolution Computational modeling Predictive models Production

来源：评论

学校读者我要写书评

暂无评论

Retrosynthesis Prediction via Search in (Hyper) Graph

arXiv

引用

arXiv 2024年

作者： Lan, Zixun Hong, Binjie Zhu, Jiajun Zeng, Zuo Liu, Zhenfu Yu, Limin Ma, Fei Department of Applied Mathematics Xi’an Jiaotong-Liverpool University China Department of Computer Science The University of Manchester United Kingdom Electrical and Electronic Engineering Xi’an Jiaotong-Liverpool University China Hours Technology Co. Ltd. Suzhou China

Predicting reactants from a specified core product stands as a fundamental challenge within organic synthesis, termed retrosynthesis prediction. Recently, semi-template-based methods and graph-edits-based methods have achieved good performance in terms of both interpretability and accuracy. However, due to their mechanisms these methods cannot predict complex reactions, e.g., reactions with multiple reaction center or attaching the same leaving group to more than one atom. In this study we propose a semi-template-based method, the Retrosynthesis via Search in (Hyper) Graph (RetroSiG) framework to alleviate these limitations. In the proposed method, we turn the reaction center identification and the leaving group completion tasks as tasks of searching in the product molecular graph and leaving group hypergraph respectively. As a semi-template-based method RetroSiG has several advantages. First, RetroSiG is able to handle the complex reactions mentioned above by its novel search mechanism. Second, RetroSiG naturally exploits the hypergraph to model the implicit dependencies between leaving groups. Third, RetroSiG makes full use of the prior, i.e., one-hop constraint. It reduces the search space and enhances overall performance. Comprehensive experiments demonstrated that RetroSiG achieved competitive results. Furthermore, we conducted experiments to show the capability of RetroSiG in predicting complex reactions. Ablation experiments verified the efficacy of specific elements, such as the one-hop constraint and the leaving group hypergraph. Copyright © 2024, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Integrating In-Ear Wearable Sensors with Deep Learning for Head and Facial Movement Analysis

Integrating In-Ear Wearable Sensors with Deep Learning for H...

引用

Big Data Analytics and Practices (IBDAP), International Conference on

ISBN: (数字)9798350391749

ISBN: (纸本)9798350391756

Accurate and inconspicuous identification of eating behavior has substantial implications for wellness surveillance, nutritional tracking, and technological assistance. Conventional approaches for detecting eating habits frequently rely on invasive or unfeasible techniques, which restrict their practicality in real-life situations. This research introduces an innovative eating recognition system that utilizes head and face motions recorded by in-ear wearing sensors and advanced deep learning algorithms. Our approach is a non-invasive and simple-to-use method that utilizes the unique patterns of head and face motions related to eating actions. We use a specially developed in-ear wearable sensor from the EarSet dataset to gather movement information while individuals are eating. The dataset comprises a range of cranial and facial motions recorded from 30 individuals. The unprocessed sensor data is subjected to pre-processing to eliminate interference and extract pertinent characteristics. We use advanced deep learning models, such as CNN, LSTM, BiL-STM, GRU, BiGRU, and our novel hybrid model CNN-LSTM, to acquire knowledge of distinctive patterns and identify eating occurrences. Our eating recognition system has been extensively tested and proven successful. The CNN-LSTM model achieved an accuracy of 95.12% and an F1-score of 95.09% during the 5-fold cross-validation studies. Our technique demonstrates superior efficiency and applicability compared to standard deep learning algorithms, as a comparative study shows. The suggested system can combine in-ear wearable sensors with deep learning to provide inconspicuous and accurate identification of eating activities. This study enhances the development of eating detection technology and introduces new opportunities for individualized wellness tracking and helpful applications. Subsequent research will prioritize the enlargement of the dataset, integration of supplementary modalities, enhancement of deep learning models for

关键词： Deep learning Accuracy Tracking Face recognition Surveillance Sensor phenomena and characterization Sensor systems

来源：评论

学校读者我要写书评

暂无评论

Time-domain Li-ion Battery Modeling under Staircase Charging and Discharging

Time-domain Li-ion Battery Modeling under Staircase Charging...

引用

2021 International Conference on Microelectronics, ICM 2021

作者： Abdelhafiz, Shahenda M. Abdelaty, A.M. Fouda, M.E. Radwan, A.G. Giza Egypt Fayoum University Faculty of Engineering Engineering Mathematics and Physics Dept. Egypt Cairo University Faculty of Engineering Engineering Mathematics and Physics Dept. Egypt University of California-Irvine Electrical Engineering and Computer Science Dept. Irvine United States School of Engineering and Applied Sciences Nile University Giza Egypt

ISBN: (纸本)9781665408394

Parameter identification of Li-ion battery models is important for efficiently charge and discharge the most widely used energy storage devices. In this work, we propose a simplified battery model with a parameter identification method for time-domain charging and discharging. Staircase PotentioElectrochemical Impedance Spectroscopy technique (SPEIS) is chosen to characterize the batteries during charging and discharging cycles at different voltage steps values. Marine Predator Algorithm (MPA) is used to identify the proposed model parameters on two commercial Li-ion coin-shaped batteries. The proposed model shows very good matching with the experiments with absolute current error less than 10 4. Hence, the proposed model can be used for real-time applications to predict the battery's behavior under different operating conditions. © 2021 IEEE.

关键词： Lithium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

Transmon probe for quantum characteristics of magnons in antiferromagnets

引用

Physical Review B 2023年第9期108卷 094430-094430页

作者： Vahid Azimi-Mousolou Anders Bergman Anna Delin Olle Eriksson Manuel Pereiro Danny Thonig Erik Sjöqvist Department of Applied Mathematics and Computer Science Faculty of Mathematics and Statistics University of Isfahan Isfahan 81746-73441 Iran Department of Physics and Astronomy Uppsala University Box 516 SE-751 20 Uppsala Sweden Department of Applied Physics School of Engineering Sciences KTH Royal Institute of Technology AlbaNova University Center SE-10691 Stockholm Sweden Swedish e-Science Research Center (SeRC) KTH Royal Institute of Technology SE-10044 Stockholm Sweden School of Science and Technology Örebro University SE-701 82 Örebro Sweden

The detection of magnons and their quantum properties, especially in antiferromagnetic (AFM) materials, is a substantial step to realize many ambitious advances in the study of nanomagnetism and the development of energy efficient quantum technologies. The recent development of hybrid systems based on superconducting circuits provides the possibility to engineer quantum sensors that exploit different degrees of freedom. Here, we examine the magnon-photon-transmon hybridization based on bipartite AFM materials, which gives rise to an effective coupling between a transmon qubit and magnons in a bipartite AFM. We demonstrate how magnon modes, their chiralities, and quantum properties, such as nonlocality and two-mode magnon entanglement in bipartite AFMs, can be characterized through the Rabi frequency of the superconducting transmon qubit.

关键词： Magnons Quantum correlations in quantum information Quantum entanglement Quantum metrology Photons Superconducting qubits

来源：评论

学校读者我要写书评

暂无评论

New Heuristics for the Operation of an Ambulance Fleet under Uncertainty

arXiv

引用

arXiv 2024年

作者： Guigues, Vincent Kleywegt, Anton J. Nascimento, Victor Hugo School of Applied Mathematics FGV Rio de Janeiro Praia de Botafogo Brazil Georgia Institute of Technology AtlantaGA30332-0205 United States Computer Science and Systems Engineering UFRJ Cidade Universitaria Rio de Janeiro Brazil

The operation of an ambulance fleet involves ambulance selection decisions about which ambulance to dispatch to each emergency, and ambulance reassignment decisions about what each ambulance should do after it has finished the service associated with an emergency. For ambulance selection decisions, we propose four new heuristics: the Best Myopic (BM) heuristic, a NonMyopic (NM) heuristic, and two greedy heuristics (GHP1 and GHP2). Two variants of the greedy heuristics are also considered. We also propose an optimization problem for an extension of the BM heuristic, useful when a call for several patients arrives. For ambulance reassignment decisions, we propose several strategies to choose which emergency in queue to send an ambulance to or which ambulance station to send an ambulance to when it finishes service. These heuristics are also used in a rollout approach: each time a new decision has to be made (when a call arrives or when an ambulance finishes service), a two-stage stochastic program is solved. The proposed heuristics are used to efficiently compute the second stage cost of these problems. We apply the rollout approach with our heuristics to data of the Emergency Medical Service (EMS) of a large city, and show that these methods outperform other heuristics that have been proposed for ambulance dispatch decisions. We also show that better response times can be obtained using the rollout approach instead of using the heuristics without rollout. Moreover, each decision is computed in a few seconds, which allows these methods to be used for the real-time management of a fleet of ambulances. Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Improving Performance and Explainability of Sensor-Based Human Activity Recognition

Improving Performance and Explainability of Sensor-Based Hum...

引用

International ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications engineering (ECTI-NCON)

作者： Sakorn Mekruksavanich Ponnipa Jantawong Anuchit Jitpattanakul Department of Computer Engineering School of Information and Communication Technology University of Phayao Phayao Thailand Department of Mathematics Faculty of Applied Science Intelligent and Nonlinear Dynamic Innovations Research Center King Mongkut’s University of Technology North Bangkok Bangkok Thailand

Significant progress has been made in developing systems that can automatically recognize human activities, largely thanks to deep learning models and sensor data. However, high performance and comprehensibility are often at odds in these systems. The aim of this research is to enhance both the accuracy and understandability of models that use sensors for human activity recognition (HAR). We present a new convolutional neural network design which takes input from accelerometers and gyroscopes across multiple data streams. This allows efficient capture of time and frequency characteristics. Additionally, we put forward an attention module that identifies informative patterns in the sensor signals to shed light on the model’s predictions. Experiments were conducted on a benchmark dataset of common daily movements gathered from ubiquitous sensors. Our model achieves state-of-the-art accuracy exceeding prior deep learning techniques. The attention visuals provide transparency into which sensor segments are most relevant for accurate activity classification. This validates improved model interpretability. Our multi-channel architecture pushes sensor-based HAR forward through heightened predictive performance. We offer original perspectives to create reliable, precise systems for HAR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning of Robotic Manipulation for Whip Targeting

Deep Reinforcement Learning of Robotic Manipulation for Whip...

引用

2025 IEEE International Conference on Simulation, Modeling, and Programming for Autonomous Robots, SIMPAR 2025

作者： Bai, Xiang Wang, Junyi Xiong, Xiaofeng Boukas, Evangelos Technical University of Denmark Applied Mathematics and Computer Science Copenhagen Denmark Technical University of Denmark Automation and Control Group Electrical and Photonics Engineering Copenhagen Denmark University of Southern Denmark Sdu Biorobotics Mærsk Mc-Kinney Moller Institute Odense Denmark

ISBN: (纸本)9798331516857

关键词： Robotic arms

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：