检索结果-内蒙古大学图书馆

Long short-term memory (LSTM) model-based reinforcement learning for nonlinear mass spring damper system control

Procedia computer science 2023年 216卷 213-220页

作者： Santo Wijaya Yaya Heryadi Yulyani Arifin Wayan Suparta Lukas Computer Science Department BINUS Graduate Program – Doctor of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Department of Electrical Engineering Faculty of Industrial Technology Institut Teknologi Nasional Yogyakarta Yogyakarta 55281 Indonesia Cognitive Engineering Research Group (CERG) Universitas Katolik Indonesia Atma Jaya Jakarta 12930 Indonesia

The Neural Networks (NN) model which is incorporated in the control system design has been studied, and the results show better performance than the mathematical model approach. However, some studies consider that only offline NN model learning and does not use the online NN model learning directly on the control system. As a result, the controller's performance decreases due to changes in the system environment from time to time. The Reinforcement Learning (RL) method has been investigated intensively, especially Model-based RL (Mb-RL) to predict system dynamics. It has been investigated and performs well in making the system more robust to environmental changes by enabling online learning. This paper proposes online learning of local dynamics using the Mb-RL method by utilizing Long Short-Term Memory (LSTM) model. We consider Model Predictive Control (MPC) scheme as an agent of the Mb-RL method to control the regulatory trajectory objectives with a random shooting policy to search for the minimum objective function. A nonlinear Mass Spring Damper (NMSD) system with parameter-varying linear inertia is used to demonstrate the effectiveness of the proposed method. The simulation results show that the system can effectively control high-oscillating nonlinear systems with good performance.

关键词： Model-based Reinforcement Learning Random-Shooting Policy LSTM MPC Nonlinear System

来源：评论

学校读者我要写书评

暂无评论

A Preliminary Study on the Collaborative Playing Piano Automatic with Deep Learning

A Preliminary Study on the Collaborative Playing Piano Autom...

引用

IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW)

作者： Varinya Phanichraksaphong Karuna Yampray Department of Electronic Engineering International Graduate Program of Electrical Engineering and Computer Science National Taipei University of Technology Taipei Taiwan College of Creative Design and Entertainment Technology Dhurakij Pundit University Bangkok Thailand

ISBN: (数字)9798350386844

ISBN: (纸本)9798350386851

A great number of deep learning-based models have been recently proposed for automatic piano classification. In this paper, we describe our contribution to the challenge of automatic piano classification when the performer performs at the concert or stage. Among these models in deep learning, we use init-1D-WaveNet and init-2D-MLNet for comparison the accuracy in the piano beginning level of the Christmas song (Jingle bells). Our experimental results show that the assessment using the init-2D-MLNet still achieve high accuracy of 87.5%.

关键词： Deep learning Accuracy Instruments Collaboration Consumer electronics

来源：评论

学校读者我要写书评

暂无评论

Cooperative Observation of Malicious Targets in a 3D Urban Traffic Environment Using UAVs

Cooperative Observation of Malicious Targets in a 3D Urban T...

引用

IEEE Latin American Robotics Symposium, LARS

作者： Matheus S. Araú jo Joã o P. B. Andrade Thayanne F. Da Silva Junior Leonardo F. Da Costa Raimundo J. C. F. Junior Gabriel F. L. Melo Douglas A. Da Silva Gustavo A. L. De Campos Graduate Program in Computer Science State University of Ceara Fortaleza Brazil Graduate Program in Computer Science Federal University of Ceara Fortaleza Brazil

The Cooperative Multi-Robot Observation of Multiple Moving Targets (CMOMMT) considers two types of robots, observers and targets, in a partially observable 2D environment. The observers’ task is to monitor the target robots under a limited radial range of the sensor, minimizing the total time the targets escape observation. The Cooperative Target Observation (CTO), a variant of the CMOMMT problem, considers the environment to be fully observable, where target agents cooperate with observers by reporting their locations. These problems are at the center of many issues that occur in surveillance situations. This work proposes an approach to the extended CTO problem. We call the CTO-URBAN3D problem: a simplified urban traffic scenario in three dimensions for the CTO, considering that suspect transport like cars or buses are targets and Unmanned Aerial Vehicles (UAVs) are observers agents. The approach employs genetic algorithms and recurrent deep neural networks to improve the performance of transport-targets robots and an observer organizational behavior hierarchical consolidated in the CTO literature for UAV-observers robots. The first results were promising, as the average number of transport-targets evasion increased, considering the other approaches to the problem. It raises the need to research new organizations for UAV robots.

关键词：

来源：评论

学校读者我要写书评

暂无评论

OP0379-HPR Tracking Step Counts in Adolescents with Juvenile Idiopathic Arthritis and Familial Mediterranean Fever: A 3-Month m-Health Monitoring Study Using Smartwatches

引用

Annals of the Rheumatic Diseases 2025年 84卷 305-306页

作者： A. Albayrak N. Arman A. Yekdaneh I. Donmez Y. Acikgoz G. Filiz T. Cakar N. Aktay Ayaz Istanbul Kent University Physiotherapy and Rehabilitation Istanbul Türkiye Istanbul University-Cerrahpasa Institute of Graduate Studies Physiotherapy and Rehabilitation Doctorate Program Istanbul Türkiye Istanbul University-Cerrahpasa Faculty of Health Sciences Department of Physiotherapy and Rehabilitation Istanbul Türkiye Fenerbahçe University Vocational School of Health Services Physiotherapy English Program Istanbul Türkiye Istanbul University-Cerrahpasa Institute of Graduate Studies Physiotherapy and Rehabilitation Master of Science Program Istanbul Türkiye EF University Institute of Graduate Studies Computer Engineering Doctorate Program Istanbul Türkiye MEF University Faculty of Engineering Department of Computer Engineering Istanbul Türkiye Istanbul University Istanbul Faculty of Medicine Department of Pediatric Rheumatology Istanbul Türkiye

Background: Physical inactivity is a significant public health issue among both healthy adolescents and those with chronic rheumatic diseases. Despite the benefits of physical activity, most adolescents do not meet recommended activity levels [1, 2]. In this context, wearable activity trackers have emerged as a solution to reduce inactivity. These devices can encourage autonomous motivation by allowing self-monitoring of physical activity behaviors, ultimately increasing physical activity levels [3]. Objectives: The aim of the study was to monitor physical activity in adolescents with Juvenile Idiopathic Arthritis (JIA) and Familial Mediterranean Fever (FMF) over a period of 3 months using a smartwatch, to evaluate step counts and to compare these with their healthy controls. Methods: 47 adolescents aged 12-18, diagnosed with JIA and FMF, and 274 healthy adolescents, were included in the study. Step counts of all adolescents were monitored for 3 months using a wearable activity device and the Pedi@ctivity Mobile Application, which operates on the Android system was developed by our team. The Pedi@ctivity Analysis Mobile Application comprises two modules as User Module and Supervise Module. Pedi@ctivity User Module where the user's health data is obtained through a smartwatch, and Pedi@ctivity Supervisor Module, where the evaluation data of the user is recorded and the smartwatch data can be viewed and managed by the supervisor. The data collected from smartwatch devices is accessed through the Google Fit API, which enables the retrieval of data from wearable technologies or smartphones including historical data. Thus, the data obtained from adolescents' smartwatch usage is transferred to the Pedi@ctivity Mobile Application for further analysis and management. Statistical analyses were performed using Python (version 3.9) with libraries including NumPy, SciPy, and pandas for data manipulation, and statsmodels or scikit-learn for advanced statistical and regression an

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mapping the Landscape of Social Learning: Integrating Key Success Factors, Challenges, and Digital Platforms

Mapping the Landscape of Social Learning: Integrating Key Su...

引用

International Conference on Information Management and Technology (ICIMTech)

作者： Marcel Meyliana Harco Leslie Hendric Spits Warnars Tirta Nugraha Mursitama Computer Science Department BINUS Graduate Program - Doctor of Computer Science Bina Nusantara University Jakarta Indonesia Information Systems Department School of Information Systems Bina Nusantara University Jakarta Indonesia Management Department BINUS Business School Doctor of Research in Management Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350390025

ISBN: (纸本)9798350390032

This research develops a conceptual model to understand the influence of digitalization on social learning, especially in the context of community empowerment. This model maps the relationship between factors that influence success, challenges faced, and variations in the use of digital platforms in social learning. By using a literature study approach, the research results show that effective communication, collaboration and empowerment are the main keys to the success of social learning in society. Key challenges identified include limited access to information, resource constraints, and digital literacy barriers, all of which require specific strategies to overcome. By examining the relationship between success factors, challenges, and use of digital platforms, this research provides new insights that support the development of more effective strategies for using digital technology to support social learning that leads to community empowerment. This research has great potential to increase people's access to learning opportunities and information, allowing them to be more active in the social learning process.

关键词： Information resources Collaboration Information management Digital intelligence Context modeling

来源：评论

学校读者我要写书评

暂无评论

Exploring User Attitudes and Innovative System Design for Remote Lighting Control Systems in Thailand’s Creative Industries

Exploring User Attitudes and Innovative System Design for Re...

引用

IEEE International Conference on Industrial Engineering and Engineering Management

作者： Thammanoon Jeerasottikule Nagul Cooharojananone Kanokwan Atchariyachanvanich Technopreneurship and Innovation Management Program Graduate School Chulalongkorn University Bangkok Thailand Department of Mathematics and Computer Science Faculty of Science Chulalongkorn University Bangkok Thailand School of Information Technology King Mongkut’s Institute of Technology Ladkrabang Bangkok Thailand

ISBN: (数字)9798350386097

ISBN: (纸本)9798350386103

In this paper, the authors investigate the current state of the lighting design and control sector in Thailand’s creative industry. The government aims to promote the creative industry as a key source of income, but there needs more skilled professionals in the industry. The authors have found that successful cases have used the Internet for remote controlling in the creative industry in other countries. Therefore, the paper will explore the potential of using technology to improve professional efficiency and assess the feasibility of implementing remote lighting control systems via the Internet with Thai lighting designers and lighting console operators. Data will be collected through qualitative in-depth interviews and quantitative surveys. The results have shown a promising acceptance rate of wireless devices for lighting control due to their mobility, flexibility, cost-effectiveness, and positive attitudes toward adopting Internet technology. The authors have also proposed a concept design for an internet-based control system tailored to Thai users, focusing on simplicity, ease of connection, and user-friendliness to accommodate those with limited network configuration knowledge. The proposed system aims to reduce professionals, save time, and increase convenience, leveraging Thailand’s extensive wireless internet coverage. These systems could significantly benefit Thailand’s creative industry by addressing the shortage of skilled professionals and improving efficiency.

关键词： Industries Wireless communication Surveys Knowledge engineering Attitude control Lighting Lighting control Internet Interviews System analysis and design

来源：评论

学校读者我要写书评

暂无评论

Analysis of Seismic Hazard Prediction Using Non Parametric Conic Multivariate Adaptive Regression Splines (C-Mars) Methods 1

Analysis of Seismic Hazard Prediction Using Non Parametric C...

引用

1st International Conference on Advanced Information Scientific Development, ICAISD 2020

作者： Priyanto, Dadang Zarlis, Muhammad Mawengkang, Herman Efendi, Syahril Graduate Program of Computer Science Department of Computer Science Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia

The data mining process requires a data set that can be used in determining a number of specific patterns to gain new knowledge. Large data sets (Big data) require special methods to get effective results. Included in this study are using big data related to the earthquake in Lombok. Earthquake research, especially in Lombok, is needed because Lombok is on three active plates in Indonesia, so that the danger of earthquake damage can be minimized. Earthquake data obtained from the Geophysical Station (BMKG) of Mataram has different characteristics and is complex, an appropriate method is needed, namely by detecting a non-parametric method with the Multivariate Adaptive Regression Spline (MARS). The use of the backward stepwise algorithm with the Conical Quadratic programming (CQP) framework of MARS, referred to as CMARS (Conic Multivariate Adaptive Regression Splines), is used for optimizing the results. The conclusions of this study are 1. A mathematical model with a total of 12 basis functions (BF) has contributed to the prediction analysis of the PGA dependent variable. 2. Contributions of the influence of independent variables on the PGA value are the epicenter distance (R e pi) of 100% and the Magnitude (Mw) of 31.08608%, while the temperature of the incident location (SUHU) of 5.48525% and depth (Depth) of 3,52988%. 3. Acquired areas that haveearthquake hazard levels in the order of the most vulnerable are Malaka, Genggelang, Tegal Maja, Senggigi and Mangsit. © 2020 Published under licence by IOP Publishing Ltd.

关键词： Quadratic programming

来源：评论

学校读者我要写书评

暂无评论

FDAM: Filter-Dedicated Approximate Multiplier Design for Real-Time CNN Acceleration

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Nguyen, Kihwan Kim Xuan Truong Jeon, Dongsuk Lee, Hyuk-Jae Korea Republic of program Department of Electrical Engineering Seoul08826 Korea Republic of Inter-University Semiconductor Research Center Seoul National University Graduate School of Convergence Science and Technology Research Institute for Convergence Science Seoul08826 Korea Republic of Department of Electrical and Computer Engineering Seoul08826 Korea Republic of

Video super-resolution (VSR) is widely used in various high-definition applications, such as HDTVs and smartphones, requiring a dedicated upscaling technique for realtime full-HD generation. To reduce on-chip buffers for largesize output feature maps, a streaming VSR accelerator may employ an output stationary dataflow, leading to a large energy consumption caused by frequent filter switching. To mitigate this, we introduce a new filter-dedicated multiplier design for realtime VSR acceleration. We replace costly multipliers with adders, shifters, and multiplexers (MUXes), referred to as unified multiple constant multiplications (UMCM). The conventional UMCM, however, may incur considerable area/power overhead due to the unified topology constraint among different filter sets. To address this problem, we propose a new approximated MCM (AMCM) problem to relax the constraint and an approximate compatible graph synthesis (A-CGS) framework to efficiently solve AMCM by jointly searching for approximated filters and constructing a unified graph. Additionally, we suggest a lightweight finetuning method by freezing approximated filters and only finetuning biases, which can recover the original model’s accuracy within a few epochs. Experimental results with synthetic data demonstrate that AMCM reduces the area by up to 49.8%, 44.8%, and 40.3% when considering constant sets of 2, 4, and 8, respectively. Our designs with SR application achieve up to a 73.3% reduction in energy consumption. Experiments with the Set5 and Set14 datasets show that our model with bias correction achieves similar restoration performance compared to the eightbit models. © 1982-2012 IEEE.

关键词： Acceleration

来源：评论

学校读者我要写书评

暂无评论

Cooperative Observation of Smart Target Agents 9th

Cooperative Observation of Smart Target Agents

引用

9th Brazilian Conference on Intelligent Systems, BRACIS 2020

作者： Araújo, Matheus S. da Silva, Thayanne F. Sampaio, Vinícius A. Melo, Gabriel F. L. Junior, Raimundo J. Ferro da Costa, Leonardo F. Andrade, Joao P. B. de Campos, Gustavo A. L. Graduate Program in Computer Science State University of Ceara Fortaleza Brazil

ISBN: (纸本)9783030613792

The Cooperative Multi-Robot Observation of Multiple Moving Targets (CMOMMT) considers two types of robots, observers and targets, in a partially observable 2D environment, in which the task of the observers is to monitor the target robots under a limited radial range of the sensor, minimizing the total time the targets escape observation. The Cooperative Target Observation (CTO), a variant of the CMOMMT problem, considers the environment to be fully observable, where targets cooperate with observers by reporting their locations. These problems are at the center of many problems that occur in real-world wildlife research, crowd social movement, and surveillance situations. Regarding research related to the field of surveillance, this work proposes an approach to the extended CTO problem, what we call the COSTA problem: Cooperative Observation of Smart Target Agents. The approach employs genetic algorithm and recurrent deep neural networks to improve the performance of target robots and, therefore, to improve the research of new decision-making strategies in the context of observer robots. The first results were auspicious, as the average number of target evasion increased, considering the other recent approaches to the problem. © 2020, Springer Nature Switzerland AG.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Skin cancer diagnosis using NIR spectroscopy data of skin lesions in vivo using machine learning algorithms

arXiv

引用

arXiv 2024年

作者： Loss, Flavio P. da Cunha, Pedro H. Rocha, Matheus B. Zanoni, Madson Poltronieri de Lima, Leandro M. Nascimento, Isadora Tavares Rezende, Isabella Canuto, Tania R.P. de Paula Vieira, Luciana Rossoni, Renan Santos, Maria C.S. Frasson, Patricia Lyra Romão, Wanderson Filgueiras, Paulo R. Krohling, Renato A. Labcin - Nature Inspired Computing Lab Brazil PPGI - Graduate Program in Computer Science Department of Chemistry PPGQ - Graduate Program in Chemistry Department of Specialized Medicine Brazil ES Vitória29075-910 Brazil Secretary of Health of the Espírito Santo State Vitória Brazil ES Vitória29040-780 Brazil

Skin lesions are classified in benign or malignant. Among the malignant, melanoma is a very aggressive cancer and the major cause of deaths. So, early diagnosis of skin cancer is very desired. In the last few years, there is a growing interest in computer aided diagnostic (CAD) using most image and clinical data of the lesion. Although we have seen an increasing progress in CAD of skin lesions, these sources of information present limitations due to their inability to provide information of the molecular structure of the lesion. NIR spectroscopy may provide an alternative source of information to automated CAD of skin lesions. The most commonly used techniques and classification algorithms used in spectroscopy are Principal Component Analysis (PCA), Partial Least Squares - Discriminant Analysis (PLS-DA), and Support Vector Machines (SVM). Nonetheless, there is a growing interest in applying the modern techniques of machine and deep learning (MDL) to spectroscopy. One of the main limitations to apply MDL to spectroscopy is the lack of public datasets. Since there is no public dataset of NIR spectral data to skin lesions, as far as we know, an effort has been made and a new dataset named NIR-SC-UFES, has been collected, annotated and analyzed generating the gold-standard for classification of NIR spectral data to skin cancer. Next, the machine learning algorithms XGBoost, CatBoost, LightGBM, 1D-convolutional neural network (1D-CNN) and standard algorithms as SVM and PLS-DA were investigated to classify cancer and non-cancer skin lesions. Experimental results indicate the best performance obtained by LightGBM with pre-processing using standard normal variate (SNV), feature extraction and data augmentation with Generative Adversarial Networks (GAN) providing values of 0.839 for balanced accuracy, 0.851 for recall, 0.852 for precision, and 0.850 for F-score. The obtained results indicate the first steps in CAD of skin lesions aiming the automated triage of patients with

关键词： Support vector machines

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：