检索结果-内蒙古大学图书馆

Opportunities and Challenges from Using Animal Videos in Reinforcement Learning for Navigation

IFAC-PapersOnLine 2023年第2期56卷 9056-9061页

作者： Vittorio Giammarino James Queeney Lucas C. Carstensen Michael E. Hasselmo Ioannis Ch Paschalidis Division of Systems Engineering Boston University Boston MA 02215 USA Center for Systems Neuroscience Department of Psychological and Brain Sciences and Graduate Program for Neuroscience Boston University Boston MA 02215 USA College of Engineering and Hariri Institute for Computing & Computational Science & Engineering Boston University Boston MA 02215 USA

We investigate the use of animal videos (observations) to improve Reinforcement Learning (RL) efficiency and performance in navigation tasks with sparse rewards. Motivated by theoretical considerations, we make use of weighted policy optimization for off-policy RL and describe the main challenges when learning from animal videos. We propose solutions and test our ideas on a 2D navigation task. We show how the use of animal videos improves performance over RL algorithms that do not leverage such observations.

关键词： Learning for Control Reinforcement Learning Deep Learning RL with demonstrations Imitation Learning Bio-inspired Control

来源：评论

学校读者我要写书评

暂无评论

Smart Waste Segregation for Home Environment 3

Smart Waste Segregation for Home Environment

引用

3rd International Conference on Advanced Research in Computing, ICARC 2023

作者： Rijah, Uthuma Lebbe Muhammed Abeygunawardhana, Pradeep K. W. Sri Lanka Institute of Information Technology Faculty of Graduate Studies and Research Malabe Sri Lanka Sri Lanka Institute of Information Technology Department of Computer Systems Engineering Malabe Sri Lanka

ISBN: (纸本)9798350347371

The segregation of waste and recycling is essential for effective waste management. Due to the busy schedule most of the people do not have a time to separate their waste. However, there is a significant issue with the segregation of the collected garbage. The implementation of an intelligent trash-management architecture is essential for the removal or reduction of waste and the maintenance of a clean, corporate environment. An IoT-stationed smart waste management device is proposed in this study that uses sensor devices to identify rubbish in the dustbins. With the aid of sensors, the waste substances in it will be separated through IoT as soon as it is discovered. Sensors and the IoT module are connected through a microcontroller. To detect the presence of garbage, an ultrasonic sensor is used. All garbage entered will be caught by the web camera and processed by the machine learning module once it has been processed. Using the model, we can identify the many forms of waste, such as paper, plastic, and glass, which account for most of the garbage materials found in a home area. This aids in removing the trash from the trash can in the most efficient and effective manner possible. This research presents an IoT, and Machine Learning based completely intelligent trash segregation and management System that recognizes the dustbins' wastes using sensor systems. This project aims to develop an automated waste segregation system using a CNN algorithm that will capture waste images from a camera with object detection and classify waste materials such as paper, plastic, and glass so that the waste can be recycled appropriately. The proposed architecture with CNN gives an accuracy of 84.67%. This system will help in garbage disposal by categorizing it, contributing to a cleaner environment. © 2023 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Motion Detection Method of Electrostatic MEMS Resonators Operating in Aqueous Media

Motion Detection Method of Electrostatic MEMS Resonators Ope...

引用

International Youth Conference on Radio Electronics, Electrical and Power engineering (REEPE)

作者： Mohamed Hemid Basil Alattar Mehdi Ghommem Alaaeldin Ahmed Eihab Abdel-Rahman Rana Sabouni Mechatronics Graduate Program American University of Sharjah Sharjah UAE Mechanical Engineering Department American University of Sharjah Sharjah UAE Systems Design Engineering University of Waterloo Ontario Canada Chemical Engineering Department American University of Sharjah Sharjah UAE

This paper introduces an experimental method to detect the motion of an electrostatic Micro-Electro-Mechanical systems (MEMS) resonator in aqueous media. The resonator comprises a micro cantilever beam subject to electrostatic actuation through a side electrode. A Finite Element Method (FEM) model of the resonator is developed to determine the in-plane mode shapes and their natural frequencies in order to facilitate the experimental study. The motion of the resonator lead to variations in its capacitance and induce a current. The developed experiments demonstrate that motion-induced current can be measured and analyzed to detect the motion of the resonator's higher-order modes and can be used in chemical sensing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimal Synergic Deep Learning for COVID-19 Classification Using Chest X-Ray Images

引用

Computers, Materials & Continua 2023年第6期75卷 5255-5270页

作者： JoséEscorcia-Gutierrez Margarita Gamarra Roosvel Soto-Diaz Safa Alsafari Ayman Yafoz Romany F.Mansour Departament of Computational Science and Electronic Universidad de la CostaCUCBarranquilla080002Colombia Biomedical Engineering Program Universidad Simón BolívarBarranquilla080002Colombia Department of Computer Science and AI Faculty of Computer Science and EngineeringUniversity of JeddahJeddahSaudi Arabia Department of Information Systems Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddahSaudi Arabia Department of Mathematics Faculty of ScienceNew Valley UniversityEl-Kharga72511Egypt

A chest radiology scan can significantly aid the early diagnosis and management of COVID-19 since the virus attacks the *** X-ray(CXR)gained much interest after the COVID-19 outbreak thanks to its rapid imaging time,widespread availability,low cost,and *** radiological investigations,computer-aided diagnostic tools are implemented to reduce intra-and inter-observer *** lately industrialized Artificial Intelligence(AI)algorithms and radiological techniques to diagnose and classify disease is *** current study develops an automatic identification and classification model for CXR pictures using Gaussian Fil-tering based Optimized Synergic Deep Learning using Remora Optimization Algorithm(GF-OSDL-ROA).This method is inclusive of preprocessing and classification based on *** data is preprocessed using Gaussian filtering(GF)to remove any extraneous noise from the image’s ***,the OSDL model is applied to classify the CXRs under different severity levels based on CXR *** learning rate of OSDL is optimized with the help of ROA for COVID-19 diagnosis showing the novelty of the *** model,applied in this study,was validated using the COVID-19 *** experiments were conducted upon the proposed OSDL model,which achieved a classification accuracy of 99.83%,while the current Convolutional Neural Network achieved less classification accuracy,i.e.,98.14%.

关键词： Artificial intelligence chest X-ray COVID-19 optimized synergic deep learning preprocessing public health

来源：评论

学校读者我要写书评

暂无评论

Exploring a spatiotemporal hetero graph-based long short-term memory model for multi-step-ahead flood forecasting

引用

Journal of Hydrology 2024年 633卷

作者： Luo, Yuxuan Zhou, Yanlai Chen, Hua Xiong, Lihua Guo, Shenglian Chang, Fi-John State Key Laboratory of Water Resources Engineering and Management Wuhan University Wuhan430072 China Department of Bioenvironmental Systems Engineering National Taiwan University Taipei10617 Taiwan

Operational flood prevention platforms and systems rely upon the advance notice provided by flood forecasts to formulate efficient measures for flood mitigation. Capturing complex spatial heterogeneity and correlation of hydro-meteorological variables is fundamentally challenging for artificial neural networks. This challenge becomes even more significant when the complexity involved introduces systematic biases and time-lag phenomena in flood forecasts. For the first time, this study proposed a Spatiotemporal Hetero Graph-based Long Short-term Memory (SHG-LSTM) model for multi-step-ahead flood forecasting. The case study focused on the Jianxi basin in China. 25,341 hydro-meteorological data, with a temporal resolution of three hours, collected during flood events were divided into training and test datasets for model construction purpose. The model was fed with 3-h streamflow and precipitation data from 23 gauge stations, covering a time span of the preceding 21 h, for generating flood forecasts at 1 up to 7 horizons. To make a comparative analysis, both LSTM and the Spatiotemporal Graph Convolutional Network (S-GCN) were constructed. This study conducted multiple rounds of model training with varying initial parameters to assess the accuracy, stability, and reliability of the LSTM, S-GCN, and SHG-LSTM models. The results demonstrated that the SHG-LSTM model outperformed LSTM and S-GCN models, with an average reduction in the volume error (VE) of 6.5% and 11.1%, respectively, a decrease in the Mean Absolute Error (MAE) of 6.7% and 8.1%, respectively, and a reduction in the Root Mean Square Error (RMSE) of 5.0% and 12.9%, respectively. Furthermore, the SHG-LSTM model not only could efficiently overcome the under-prediction bottleneck, but also could largely mitigate the time-lag phenomenon in flood forecasts, even during the testing stages. These findings indicate that the proposed SHG-LSTM model can provide a general framework for modelling the spatial heterogeneit

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

A Conjoint Analysis on the Preference of Pipe Welding Materials and Procedures

A Conjoint Analysis on the Preference of Pipe Welding Materi...

引用

IEEE International Conference on Industrial engineering and engineering management

作者： Erick D. Dela Cruz Yogi Tri Prasetyo Irene Dyah Ayuwati Maela Madel L. Cahigas Reny Nadlifatin School of Industrial Engineering and Engineering Management Mapúa University Manila Philippines School of Graduate Studies Mapúa University Manila Philippines International Bachelor Program in Engineering Yuan Ze University Taoyuan Taiwan Department of Industrial Engineering and Management Yuan Ze University Taoyuan Taiwan University of Surabaya Surabaya Indonesia Department of Information Systems Institut Teknologi Sepuluh Nopember Surabaya Indonesia

ISBN: (数字)9798350386097

ISBN: (纸本)9798350386103

Welding is both as art and science and its common use is the jointing of points. Some of the welding procedures used for jointing metal pipes are Tungsten Inert Gas and Gas Metal Arc welding and in common practice plastic pipes are bonded with the use of butt-fusion welding procedure. Since 1970’s conjoint analysis was used as a way of finding out what the preference of consumers. The objective of this study is to determine the combination welding attributes that were most preferred using a conjoint analysis approach. With conjoint analysis, together with, the orthogonal design the preference for welding materials and procedures were analyzed. It showed that pipe material with 29.24% was the most preferred attribute and Non-destructive test as the least preferred with $\mathbf{2. 6 6 \%}$. The result of this study may be utilized in future related reviews and could be applicable in other related Mechanical systems requiring welding works.

关键词： Surveys Resistance Reviews Welding Tungsten Ventilation Particle measurements Mechanical systems Plastics Testing

来源：评论

学校读者我要写书评

暂无评论

The coherence between resource investment and performance for sustainable development goals in Taiwan cities: A hybrid influence analysis

引用

Sustainable Development 2023年第5期31卷 3734-3760页

作者： Chan, Ya-Ting Wu, Cou-Chen Wu, Kuo-Jui Chiu, Anthony S. F. Tseng, Ming-Lang Graduate Institute of Management National Taiwan University of Science and Technology Taipei City Taiwan Department of Business Administration National Taiwan University of Science and Technology Taipei City Taiwan Department of Management Science and Engineering Management School Hainan University Hainan Haikou China Center for Engineering and Sustainable Development Research De La Salle University Manila Philippines Department of Industrial and Systems Engineering De La Salle University Manila Philippines Institute of Innovation and Circular Economy Asia University Taichung City Taiwan Department of Medical Research China Medical University Hospital China Medical University Taichung City Taiwan UKM-Graduate School of Business Universiti Kebangsaan Malaysia Selangor Bangi Malaysia

This study contributes to visualizing the complicated interrelationships among the sustainable development goals (SDGs) in Taiwanese cities' resource investment and performance under uncertainties. Taiwan faces bottlenecks and uncertainties in pursuing the SDGs due to the complex interrelationships among the SDGs. In particular, the lack of a comprehensive approach causes problems for governments in identifying whether resource investment and performance reach a coherent situation. To address this issue, this study proposes to use secondary data normalization, factor analysis and reliability testing for the validity and reliability of measures, performance-resource analysis and the fuzzy synthetic method to translate qualitative information, as well as the decision-making trial and evaluation laboratory to visualize the relationships. The study (1) establishes validation measures for resource investment and performance;(2) combines qualitative information and secondary data to understand the causal effects of the SDGs;and (3) provides directions for the government to improve the coherence of resource investment and performance. The findings show that SDG 3 has a strong effect on SDGs 11 and 9 and a moderate effect on SDG 8 to achieve the agenda. Guidelines are provided for resource-poor counties/regions that could invest resources to achieve SDG 3. Many cities and counties are underperforming. © 2023 ERP Environment and John Wiley & Sons Ltd.

关键词： coherence decision-making trial and evaluation laboratory fuzzy synthetic method SDG 3 sustainable development goals

来源：评论

学校读者我要写书评

暂无评论

Consistent second-order conic integer programming for learning Bayesian networks

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2023年第1期24卷 15299-15336页

作者： Simge Küçükyavuz Ali Shojaie Hasan Manzour Linchuan Wei Hao-Hsiang Wu Department of Industrial Engineering and Management Sciences Northwestern University Department of Biostatistics University of Washington Department of Industrial and Systems Engineering University of Washington Department of Management Science National Yang Ming Chiao Tung University

Bayesian Networks (BNs) represent conditional probability relations among a set of random variables (nodes) in the form of a directed acyclic graph (DAG), and have found diverse applications in knowledge discovery. We study the problem of learning the sparse DAG structure of a BN from continuous observational data. The central problem can be modeled as a mixed-integer program with an objective function composed of a convex quadratic loss function and a regularization penalty subject to linear constraints. The optimal solution to this mathematical program is known to have desirable statistical properties under certain conditions. However, the state-of-the-art optimization solvers are not able to obtain provably optimal solutions to the existing mathematical formulations for mediumsize problems within reasonable computational times. To address this difficulty, we tackle the problem from both computational and statistical perspectives. On the one hand, we propose a concrete early stopping criterion to terminate the branch-and-bound process in order to obtain a near-optimal solution to the mixed-integer program, and establish the consistency of this approximate solution. On the other hand, we improve the existing formulations by replacing the linear "big-M" constraints that represent the relationship between the continuous and binary indicator variables with second-order conic constraints. Our numerical results demonstrate the effectiveness of the proposed approaches.

关键词： mixed-integer conic programming Bayesian networks directed acyclic graphs early stopping criterion consistency

来源：评论

学校读者我要写书评

暂无评论

Catalytic hydrotreatment of alkaline lignin and its consequent influences on fast pyrolysis

引用

Carbon Resources Conversion 2021年第1期4卷 219-229页

作者： Lijuan Zhang Cheolyong Choi Hiroshi Machida Zhibao Huo Koyo Norinaga Department of Chemical Systems Engineering Graduate School of EngineeringNagoya UniversityAichi 464-8603Japan School of Environmental Science and Engineering Shanghai Jiao Tong University800 Dongchuan RoadShanghai 200240China

The current state of lignin has been characterized by these three:(1)as one of the main components in lignocellulosic biomass with an abundant amount;(2)not be taken seriously but treated as a waste product;(3)underutilized due to a complex and stubborn ***,lignin can be a rich source for hydrocarbons and aromatic compounds when gives appropriate *** this work,we have studied the hydrotreatment of alkaline lignin(AL)under relatively mild conditions and further investigated the characterization of hydrogenated lignin(HL),especially the behavior during fast *** recovery of the HL decreased with increasing reaction temperature from 60 wt.%to 41 wt.%in the range of 150-250℃.The hydrotreated products were analyzed using Elemental Analysis,FTIR(for HL)and GC-MS(for bio-oil).The HL samples were found to have a higher hydrogen/carbon atomic effective ratio(H/C_(eff) ratio)and a higher degree of saturation than *** to the internal structure of the lignin before and after hydrotreatment,the side chain groups were removed from AL during the *** that,from the fast pyrolysis of HL,it was observed that more light hydrocarbons and aromatic compounds were formed than that of ***,fast pyrolysis in the hydrogen atmosphere revealed that more volatile fractions were released compared to the Helium *** total olefins yield was increased for HL compared AL from 1.02 wt.%to 3.1 wt.%at 250℃for 7 *** study of HL is instructive to some extent for the industrial utilization of lignin.

关键词： Alkaline lignin Hydrotreatment Hydrogenated lignin Fast pyrolysis Hydrogen atmosphere

来源：评论

学校读者我要写书评

暂无评论

LEARNING DISCRIMINATIVE FEATURES FROM SPECTROGRAMS USING CENTER LOSS FOR SPEECH EMOTION RECOGNITION

arXiv

引用

arXiv 2025年

作者： Dai, Dongyang Wu, Zhiyong Li, Runnan Wu, Xixin Jia, Jia Meng, Helen Tsinghua-CUHK Joint Research Center for Media Sciences Technologies and Systems Graduate School at Shenzhen Tsinghua University Shenzhen China Department of Computer Science and Technology Tsinghua University Beijing China Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Shatin Hong Kong

Identifying the emotional state from speech is essential for the natural interaction of the machine with the speaker. However, extracting effective features for emotion recognition is difficult, as emotions are ambiguous. We propose a novel approach to learn discriminative features from variable length spectrograms for emotion recognition by cooperating softmax cross-entropy loss and center loss together. The softmax cross-entropy loss enables features from different emotion categories separable, and center loss efficiently pulls the features belonging to the same emotion category to their center. By combining the two losses together, the discriminative power will be highly enhanced, which leads to network learning more effective features for emotion recognition. As demonstrated by the experimental results, after introducing center loss, both the unweighted accuracy and weighted accuracy are improved by over 3% on Mel-spectrogram input, and more than 4% on Short Time Fourier Transform spectrogram input. Copyright © 2025, The Authors. All rights reserved.

关键词： Spectrographs

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：