检索结果-内蒙古大学图书馆

Evaluating single-shot and two-stage vision-based detection of occupancy activity in energy-efficient buildings

Energy and Buildings 2025年 345卷

作者： Shupeng Zhou Wuxia Zhang Paige Wenbin Tien John Calautit School of Engineering University of Edinburgh Scotland UK Department of Architecture and Built Environment University of Nottingham Nottingham UK School of Infrastructure & Built Environment Aston University Birmingham UK College of Built Environment Faculty of Computing Engineering and the Built Environment Birmingham City University Birmingham UK

Building energy consumption is heavily influenced by occupant behavior, yet many heating, ventilation, and air conditioning (HVAC) systems operate on static or pre-defined schedules that may not capture real-time occupancy dynamics. This study presents a novel comparative evaluation of vision-based deep learning methods, specifically YOLO, a single-shot detection model, and Faster R-CNN, a two-stage detection model, for real-time occupancy activity detection in densely populated indoor environments. Unlike previous studies that relied on computationally intensive pose estimation, these models efficiently identify occupancy activities using fewer computational resources, enabling practical real-time applications. A dedicated dataset was developed for training and evaluating these models, ensuring their applicability to dynamic, real-world scenarios. The models were assessed in identifying occupant activities, such as sitting and walking, within a densely occupied lecture hall, capturing different occupancy phases: entering, during class, and leaving. Occupancy data from the models were utilized to estimate internal heat gains and subsequently analyzed for their impacts on heating, cooling, and, notably, dehumidification loads—addressing an aspect frequently overlooked in prior occupancy detection studies. Model performance was assessed against ground truth data and compared with a conventional fixed occupancy schedule. Results show that YOLO v7 outperforms Faster R-CNN, achieving F 1 scores of 0.94 for sitting in high-density conditions and 0.86 for walking in high-density, dynamic scenarios, and closely aligning with ground truth occupancy profiles. In practical building energy simulations, real-time occupancy detection improved accuracy in predicting internal heat gains, prevented unnecessary cooling and over-dehumidification, and enabled better alignment of HVAC system performance with actual occupancy dynamics. This research highlights the potential for energy sa

关键词： Activity detection Built environment Faster R-CNN Occupancy YOLO Energy performance Heating, Ventilation and Air conditioning (HVAC) Deep learning Computer vision Dehumidification

来源：评论

学校读者我要写书评

暂无评论

RISC-NN: Use RISC, NOT CISC as Neural Network Hardware Infrastructure

arXiv

引用

arXiv 2021年

作者： Xiang, Taoran Zhang, Lunkai An, Shuqian Ye, Xiaochun Zhang, Mingzhe Liu, Yanhuan Yan, Mingyu Wang, Da Zhang, Hao Li, Wenming Sun, Ninghui Fan, Dongrui State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing100190 China

Neural Networks (NN) have been proven to be powerful tools to analyze Big Data. However, traditional CPUs cannot achieve the desired performance and/or energy efficiency for NN applications. Therefore, numerous NN accelerators have been used or designed to meet these goals. These accelerators all fall into three categories: GPGPUs, ASIC NN Accelerators and CISC NN Accelerators. GPGPUs achieve general purpose and high computing throughput, but cannot provide desired energy efficiency because their stream architecture cannot achieve efficient data reuse required by NN applications. ASIC NN Accelerators achieve best performance or energy efficiency through advanced data reuse optimization, however, they only support limited NN use cases. CISC NN Accelerators aim to achieve both general purpose and high energy efficiency by decomposing NN applications into multiple relatively simple matrix or vector CISC instructions. Though CISC NN Accelerators can achieve considerable smaller memory footprint than GPGPU thus improve energy efficiency;they still fail to provide same level of data reuse optimization achieved by ASIC NN Accelerators because of the inherited poor pragrammability of their CISC architecture. We argue that, for NN Accelerators, RISC is a better design choice than CISC, as is the case with general purpose processors. We propose RISC-NN, a novel many-core RISC-based NN accelerator that achieves high expressiveness and high parallelism and features strong programmability and low control-hardware costs. We show that, RISC-NN can implement all the necessary instructions of state-of-the-art CISC NN Accelerators;in the meantime, RISC-NN manages to achieve advanced optimization such as multiple-level data reuse and support for Sparse NN applications which previously only existed in ASIC NN Accelerators. Experiment results show that, RISC-NN achieves on average 11.88× performance efficiency compared with state-of-the-art Nvidia TITAN Xp GPGPU for various NN applicati

关键词： Acceleration

来源：评论

学校读者我要写书评

暂无评论

Seismic Hazard Assessment Based on Predominance of Local Earthquake Sources: A Methodological Approach Using Psha Applied to the Main Cities in Peru

SSRN

引用

SSRN 2024年

作者： Aroquipa, Hector Hurtado, Alvaro Heredia, Raul Si-Qi, Li Angel, Christiam Research Group on Numerical and Computational Methods Graphic and Scientific Computing Instituto de Investigación Científica Universidad de Lima Av. Javier Prado Este 4600 Santiago de Surco15023 Peru Civil Engineering Department Universidad Nacional San Antonio Abad del Cusco Cusco Peru Universidad Autónoma del Perú Panamericana Sur Km. 16.3 Villa EL Salvador Lima Peru Heilongjiang University Harbin China School of Architecture Urban Planning and Construction Engineering Politecnico di Milano 13 Milan Italy

Peru is located within the seismically active "Pacific Ring of Fire" and therefore is constantly affected by the dynamic interaction of the Nazca and South American Plates. Due to its location, over the past centuries, devastating earthquakes have hit the country, generating substantial economic and human losses, leading to a constant need to overcome and enhance human safety and building integrity through advanced strategies to mitigate seismic risk. This practice has worldwide been cataloged as "Disaster Risk Reduction Management", which involves a deeper comprehension and representation of the seismic hazard for the assessment of the existing buildings and infrastructure, which often deviates from the practices behind seismic design standards. In this study, a novel approach is proposed to assess seismic hazards at a city-size level. It employs uniform hazard spectra calculated through a comprehensive probabilistic hazard assessment framework. The methodology considered a vast earthquake catalog comprising 22,399 events, 33 earthquake source models derived from previous research, six ground motion prediction models, and five return periods, applied to 25 cities. To address the uncertainties associated with the correctness and accuracy of the results, they were evaluated using a rigorous selection criterion through a logic tree-based weighting system. This accounts for soil classification and fault activity clustered by inter-slab, crustal and intra-slab earthquakes. The findings revealed the specific fault segments influencing the seismic activity for every analyzed city, and also determined if they were in proximity or within the same seismic hazard zone stated within the design standard. This approach can be extended looking forward towards establishing a more reliable seismic hazard comprehension based on local activity, offering valuable insights for the performance-based assessments of existing structures and for the formulation of preparedness policies. © 2

关键词： Seismic design

来源：评论

学校读者我要写书评

暂无评论

Discriminant Model of Driving Distraction During Mobile Phone Conversation Based on Eye Movements 9th

Discriminant Model of Driving Distraction During Mobile Phon...

引用

9th International Conference on Green Intelligent Transportation Systems and Safety, 2018

作者： Xie, Lian Duan, Min Li, Wenyong School Architecture and Transportation Engineering Guilin University of Electronic Technology Guilin541004 China Intelligent Transportation Systems Research Center Wuhan University of Technology Wuhan430063 China School of Mathematics & Computing Science Guilin University of Electronic Technology Guilin541004 China

ISBN: (纸本)9789811506437

In order to investigate the characteristics of drivers’ eye movements during distracted driving caused by mobile phone conversation and establish a driving distraction discriminant model, a driving simulation experiment was conducted. The eye movement index data were collected by eye tracker under different traffic scenes which include normal driving and perform simple or complex conversation secondary task on the urban road and freeway, then the variance analysis was used to analyze the characteristics. Finally, according to the characteristics of drivers’ eye movements, a driving distraction discriminant model based on fisher discriminant analysis was constructed for different road types. The ANOVA results showed that the effectiveness of road type and conversation task on the cumulative proportion of the driver’s focus on the area of interest in the front road is not statistically significant. However, the average duration of the driver’s attention under urban road scene is significantly higher than that of the freeway, and with the increasing of difficulty of driving task, the average duration of attention increased significantly. In addition, the road type and conversation task significantly influenced the change range of pupil area. The accuracy rate of the discriminant model is 75.2% for the driving distraction on urban roads, and 78.3% for the distraction on freeway. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Eye movements

来源：评论

学校读者我要写书评

暂无评论

Seismic Hazard Assessment Based on Predominance of Local Earthquake Sources: A Methodological Approach Using Psha Applied to the Main Cities in Peru

SSRN

引用

SSRN 2024年

作者： Aroquipa, Hector Hurtado, Alvaro Si-Qi, Li Angel, Christiam Heredia, Raul Research Group on Numerical and Computational Methods Graphic and Scientific Computing Instituto de Investigación Científica Universidad de Lima Av. Javier Prado Este 4600 Santiago de Surco15023 Peru Civil Engineering Department Universidad Nacional San Antonio Abad del Cusco Cusco Peru Universidad Autónoma del Perú Panamericana Sur Km. 16.3 Villa EL Salvador Lima Peru Heilongjiang University Harbin China School of Architecture Urban Planning and Construction Engineering Politecnico di Milano Milan13 Italy

关键词： Seismic design

来源：评论

学校读者我要写书评

暂无评论

CSI-Based Human Activity Recognition using Convolutional Neural Networks

CSI-Based Human Activity Recognition using Convolutional Neu...

引用

International eConference on Computer and Knowledge engineering (ICCKE)

作者： Parisa Fard Moshiri Mohammad Nabati Reza Shahbazian Seyed Ali Ghorashi Cognitive Telecommunication Research Group Shahid Beheshti University G. C. Tehran Iran Faculty of Technology and Engineering Standard Research Institute Alborz Iran School of Architecture Computing and Engineering University of East London London UK

ISBN: (纸本)9781665402095

Human activity recognition (HAR) as an emerging technology can have undeniable impacts on several applications such as health monitoring, context-aware systems, transportation, robotics, and smart cities. Among the main research methods in HAR (sensor, image, and WiFi-based), the WiFi-based method has attracted considerable attention due to the ubiquity of WiFi devices. WiFi devices can be utilized to distinguish daily activities such as "walk", "run", and "sleep". These activities affect WiFi signal propagation and can be further used to recognize activities. This paper proposes a Deep Learning method for HAR tasks using channel state information (CSI). A new model is developed in which CSI data are converted to grayscale images. These images are then fed into a 2D-Convolutional Neural Network (CNN) for activity classification. We take advantage of CNN's high accuracy on image classification along with WiFi-based ubiquity. The experimental results demonstrate that our proposed approach achieves acceptable performance in HAR tasks.

关键词： Performance evaluation Smart cities Transportation Activity recognition Robot sensing systems Convolutional neural networks Task analysis

来源：评论

学校读者我要写书评

暂无评论

Experimental Investigation of Curved and Straight Laminated Bamboo-Concrete Beams with New Calibration Method for Interface Slip

Research Square

引用

Research Square 2023年

作者： Deng, Yu Hao, Yuxi Mohamed, Ahmed Wong, Simon H.F. Tang, Yunchao Yuen, Terry Y.P. Sukontasukkul, Piti Shen, Minhe Fernando, Nirodha Saint, Ruth Zhang, Hexin School of Civil Engineering and Architecture Guangxi University of Science and Technology Liuzhou545006 China School of Computing Engineering and the Built Environment Edinburgh Napier University 10 Colinton Road EdinburghEH10 5DT United Kingdom Faculty of Science and Technology Technological Higher Education Institute of Hong Kong 20A Tsing Yi Road Tsing Yi Island New Territories Hong Kong College of Urban Construction Zhongkai University of Agriculture and Engineering Guangzhou510225 China Department of Civil Engineering National Yang Ming Chiao Tung University Hsinchu30010 Taiwan Construction and Building Materials Research Center Department of Civil Engineering King Mongkut's University of Technology North Bangkok Thailand

This study echoes the rising demand for bio-based material in concrete composite structures in the race to accelerate carbon neutrality in construction. Noticing that most previous studies are focused on straight timber or engineered bamboo-to-concrete composite beams, this study focuses on: 1) developing unique and practical curved laminated bamboo-concrete (LBC) composite beams;2) experimentally investigating and comparing the structural performances of the curved and straight LBC composite beams;3) developing a novel and proper in-member interface shear slip calibration method that captures the longitudinal after-slip strain redistribution, validated by stain gauge measurements. This study also highlights the interlayer shear bonding strength of laminated bamboo as the thresholding parameter that determines the composite beams' overall flexural strength, evidenced by detailed failure mode analysis. The proposed interface shear slip calibration method can be extended to the other types of shear connectors such as screws, shear plates, etc. © 2023, CC BY.

关键词： Timber

来源：评论

学校读者我要写书评

暂无评论

A differential public PUF design for lightweight authentication 16

A differential public PUF design for lightweight authenticat...

引用

2021 International Conference on Synthesis, Modeling, Analysis and Simulation Methods and Applications to Circuit Design, SMACD 2021 and 16th Conference on PhD Research in Microelectronics and Electronics, PRIME 2021

作者： Duan, Shengyu Sai, Gaole School of Computer Engineering and Science Shanghai University Shanghai200444 China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology China

ISBN: (纸本)9783800755899

Physical Unclonable Functions (PUFs) have emerged as a promising primitive to provide a hardware keyless security mechanism for integrated circuit applications. Public PUFs (PPUFs) address the crucial PUF vulnerability of requiring databases to store the secrete reference information. This paper investigates one of the PPUF families, differential PPUF (dPPUF), which exploits complexly interacted logic to create time gap between actual execution and simulation, and to prevent simulation attacks. Conventional dPPUFs have high costs. We observe the repressers have large impact on simulation time, but take a great proportion in current dPPUF structure. We thereby present a represser network with specially designed interconnection and shared logic, to maintain a high circuit complexity and to reduce the area cost. We show the proposed dPPUF has similar resilience over simulation attacks as the conventional design. Area cost can be reduced by up to 44%, and thus the proposed design can be used for lightweight authentication. © VDE VERLAG GMBH.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Experimental investigation of mechanically laminated straight or curved-and-tapered bamboo-concrete T-beams

引用

engineering Structures 2023年 283卷

作者： Deng, Yu Hao, Yuxi Mohamed, Ahmed Wong, Simon H.F. Tang, Yunchao Yuen, Terry Y.P. Sukontasukkul, Piti Shen, Minhe Fernando, Nirodha Saint, Ruth Zhang, Hexin School of Civil Engineering and Architecture Guangxi University of Science and Technology Liuzhou545006 China School of Computing Engineering and the Built Environment Edinburgh Napier University 10 Colinton Road Scotland EdinburghEH10 5DT United Kingdom Faculty of Science and Technology Technological Higher Education Institute of Hong Kong 20A Tsing Yi Road Tsing Yi Island New Territories Hong Kong College of Urban Construction Zhongkai University of Agriculture and Engineering Guangzhou510225 China Department of Civil Engineering National Yang Ming Chiao Tung University Hsinchu30010 Taiwan Construction and Building Materials Research Center Department of Civil Engineering King Mongkut's University of Technology North Bangkok Thailand

This study echoes the rising demand for bio-based material in concrete composite structures in the race to accelerate carbon neutrality in construction. Noticing that most previous studies are focused on straight timber or engineered bamboo-to-concrete composite beams, this study developed straight or curved-and-tapered mechanically laminated bamboo-concrete (LBC) T-beams. Six layers of 26 mm thick laminated bamboo panels were glue laminated together to form the bamboo beams. The curved bamboo beams have three different rises of arch: 50 mm, 100 mm and 150 mm. All specimen beams were tested by four-point bending tests to evaluate their structural performances of the curved and straight LBC T-beams. To monitor the flange-to-web interface shear transfer, a novel interface shear slip calibration method that captures the longitudinal after-slip strain redistribution was developed and validated by strain gauge measurements. This study also highlights the interlayer shear bonding strength of laminated bamboo as the thresholding parameter that determines the composite beams' overall flexural strength, evidenced by detailed failure mode analysis. The proposed interface shear slip calibration method can be extended to the other types of shear connectors such as screws, nails, shear plates and notched connections. © 2023 The Author(s)

关键词： Laminated composites

来源：评论

学校读者我要写书评

暂无评论

An Auto-Parallel Method for Deep Learning Models Based on Genetic Algorithm

An Auto-Parallel Method for Deep Learning Models Based on Ge...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Yan Zeng ChengChuang Huang YiJie Ni ChunBao Zhou JiLin Zhang Jue Wang MingYao Zhou MeiTing Xue YunQuan Zhang School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Key Laboratory for Modeling and Simulation of Complex Systems Ministry of Education Hangzhou China Data Security Governance Zhejiang Engineering Research Center Hangzhou China School of ITMO Joint Institute Hangzhou Dianzi University Hangzhou China Institute of Computer Network Information Center of the Chinese Academy of Sciences Beijing China HuaWei State Key Laboratory of Computer Architecture Institute of Computing Technology of the Chinese Academy of Sciences Beijing China

As the size of datasets and neural network models increases, automatic parallelization methods for models have become a research hotspot in recent years. The existing auto-parallel methods based on machine learning or graph algorithms still have issues with search efficiency and applicability. This paper proposes an automatic parallel method based on a dual-population genetic algorithm, TGA, which transforms model partitioning and placement into an integer linear programming problem and constructs a cost model to evaluate the solution. The solution space is built using the neural network’s dataflow graph and device cluster’s topology, and the dual-population genetic algorithm is used to search for the optimal model parallel strategy. Experiments with various models show that the proposed method can improve single-step execution time by up to 42% compared to the Baechi method and up to 37.7% compared to the Hierarchical method.

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：