检索结果-内蒙古大学图书馆

Evaluation of an adjustable support shoulder exoskeleton on static and dynamic Overhead tasks 62

学校读者我要写书评

暂无评论

Evaluation of an adjustable support shoulder exoskeleton on ...

62nd Human Factors and Ergonomics Society Annual Meeting, HFES 2018

作者： Van Engelhoven, Logan Poon, Nathan Kazerooni, Homayoon Ban, Alan Rempel, David Harris-Adamson, Carisa University of California Berkeley Human Engineering and Robotics Lab United States University of California Berkeley San Francisco Ergonomics Graduate Research Training Program United States

ISBN: (纸本)9781510889538

Introduction: Overhead tasks increase the risk of work related musculoskeletal disorders to industrial workers. A shoulder supporting exoskeleton with adjustable and angle dependent torque (referred to as shoulderX in this paper for brevity) was designed and built at the University of California Berkeley Human engineering and robotics Laboratory for workers performing overhead tasks. shoulderX was designed specifically to reduce the exposure to large muscle exertion forces on the shoulder complex from overhead work. Methods: We evaluated shoulderX by measuring the muscle activation of the upper trapezius (UT), anterior deltoid (AD), triceps long head (TR), and infraspinatus (IF) during static and dynamic overhead tasks. Thirteen male subjects with experience in the construction or manufacturing industries were recruited to perform overhead tasks using light (.45 kg) and heavy (2.25 kg) weight tools with four exoskeleton support levels (0, 8.5, 13.0, 20.0 Nm peak torque). Results: During all conditions, the wearer's shoulder flexor muscle activity of UT, AD were reduced with increasing strength of shoulderX by up to 80%. Subjects unanimously preferred the use of shoulderX over the unassisted condition for all task types (static and dynamic overhead tasks) and tool weights (.45 kg and 2.25 kg). Conclusion: shoulderX reduces the wearer's primary muscle activity in overhead static and dynamic work and results in a more desirable and balanced pattern of shoulder complex activation. This investigation indicates that shoulderX reduces the risk of work related shoulder injuries during overhead tasks. © 2018 Human Factors an Ergonomics Society Inc.. All rights reserved.

关键词： Cost reduction

Which ads to show? Advertisement image assessment with auxiliary information via multi-step modality fusion

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Park, Kyung-Wha Lee, JungHoon Kwon, Sunyoung Ha, Jung-Woo Kim, Kyung-Min Zhang, Byoung-Tak Interdisciplinary Program in Neuroscience Seoul National University Statistics and Actuarial Science Soongsil University Clova AI Research NAVER Corp Department of Computer Science and Engineering Seoul National University Surromind Robotics

Assessing aesthetic preference is a fundamental task related to human cognition. It can also contribute to various practical applications such as image creation for online advertisements. Despite crucial influences of image quality, auxiliary information of ad images such as tags and target subjects can also determine image preference. Existing studies mainly focus on images and thus are less useful for advertisement scenarios where rich auxiliary data are available. Here we propose a modality fusion-based neural network that evaluates the aesthetic preference of images with auxiliary information. Our method fully utilizes auxiliary data by introducing multi-step modality fusion using both conditional batch normalization-based low-level and attention-based high-level fusion mechanisms, inspired by the findings from statistical analyses on real advertisement data. Our approach achieved state-of-the-art performance on the AVA dataset, a widely used dataset for aesthetic assessment. Besides, the proposed method is evaluated on large-scale real-world advertisement image data with rich auxiliary attributes, providing promising preference prediction results. Through extensive experiments, we investigate how image and auxiliary information together influence click-through rate. Copyright © 2019, The Authors. All rights reserved.

关键词： Image fusion

Using Bacteria Foraging Optimization in Gesture Reconfiguration from Joint Failure for Semi-Humanoid Robot

学校读者我要写书评

暂无评论

Using Bacteria Foraging Optimization in Gesture Reconfigurat...

International Conference on Control, Automation and Systems ( ICCAS)

作者： Wisanu Jutharee Boonserm Kaewkamnerdpong Jumpol Polvichai Thavida Maneewarn Institute of Field Robotics King Mongkut's University of Technology Thonburi Bangkok Thailand Biological Engineering Program Faculty of Engineering King Mongkut's University of Technology Thonburi Bangkok Thailand Faculty of Engineering King Mongkut's University of Technology Thonburi Bangkok Thailand

Joint failure problem in humanoid robots could often occur in real application. An approach for fault recovery is performing gesture reconfiguration on a redundant manipulator of humanoid robots. In this study, we proposed a gesture reconfiguration method based on bacteria foraging optimization algorithm. After joint failure, we locked the failed joint in place and used the BFOA-based gesture reconfiguration to find a new suitable gesture configuration for the remaining joints. We demonstrated the gesture reconfiguration from joint failure on the Namo robot, which is a semi-humanoid robot for performing emblematic gestures as a receptionist robot. Four emblematic gestures, including the Thai greeting, salute, bye, and side invite gestures, were demonstrated. The experimental results showed that the BFOA-based gesture reconfiguration could generate a suitable gesture configuration for all four gestures; the resulting gestures are close to the original gestures. We investigated further on tuning the number of population size in BFOA. We varied the number of population size as 15, 25, 50, and 100 and found that although the larger population size could result in better gestures than the smaller size, the improvement in gesture similarity were not significant so it may be more efficient to use the smaller size. This could be owing to the performance of bacteria foraging optimization algorithm.

关键词：

Exploring the effect of image enhancement techniques on COVID‐19 detection using chest X‐rays images

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Rahman, Tawsifur Khandakar, Amith Qiblawey, Yazan Tahir, Anas Kiranyaz, Serkan Kashem, Saad Bin Abul Islam, Mohammad Tariqul Maadeed, Somaya Al Zughaier, Susu M. Khan, Muhammad Salman Chowdhury, Muhammad E.H. Department of Biomedical Physics & Technology University of Dhaka Dhaka 1000 Bangladesh Department of Electrical Engineering Qatar University Doha2713 Qatar Faculty of Robotics and Advanced Computing Qatar Armed Forces‐Academic Bridge Program Qatar Foundation Doha24404 Qatar Dept. of Electrical Electronics and Systems Engineering Universiti Kebangsaan Malaysia BangiSelangor43600 Malaysia Department of Computer Science and Engineering Qatar University Doha2713 Qatar Department of Basic Medical Sciences College of Medicine Biomedical and Pharmaceutical Research Unit QU Health Qatar University Doha2713 Qatar University of Engineering and Technology Peshawar Pakistan

The use of computer-aided diagnosis in the reliable and fast detection of corona virus disease (COVID-19) has become a necessity to prevent the spread of the virus during the pandemic to ease the burden on the medical infrastructure. Chest X-ray (CXR) imaging has several advantages over other imaging techniques as it is cheap, easily accessible, fast and portable. CXR images are sometimes of poor quality and so image enhancement techniques can help the machine learning models to extract valuable discriminating features from the image. Numerous works have been reported on COVID-19 detection from smaller set of original X-ray images. However, the effect of image enhancement in COVID-19 detection was not reported in the literature. This paper explores the effect of various popular image enhancement techniques and states the © 2020, CC BY.

关键词： Image enhancement

Parameter Optimization and Learning in a Spiking Neural Network for UAV Obstacle Avoidance targeting Neuromorphic Processors

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Salt, Llewyn Howard, David Indiveri, Giacomo Sandamirskaya, Yulia School of Information Technology and Electrical Engineering University of Queensland QLD Australia Robotics and Autonomous Systems Group in the Cyberphysical System Program CSIRO QLD Australia Institute of Neuroinformatics University of Zurich ETH Zurich Zurich Switzerland

he Lobula Giant Movement Detector (LGMD) is an identified neuron of the locust that detects looming objects and triggers the insect’s escape responses. Understanding the neural principles and network structure that lead to these fast and robust responses can facilitate the design of efficient obstacle avoidance strategies for robotic applications. Here we present a neuromorphic spiking neural network model of the LGMD driven by the output of a neuromorphic Dynamic Vision Sensor (DVS), which incorporates spiking frequency adaptation and synaptic plasticity mechanisms, and which can be mapped onto existing neuromorphic processor chips. However, as the model has a wide range of parameters, and the mixed signal analogue-digital circuits used to implement the model are affected by variability and noise, it is necessary to optimise the parameters to produce robust and reliable responses. Here we propose to use Differential Evolution (DE) and Bayesian Optimisation (BO) techniques to optimise the parameter space and investigate the use of Self-Adaptive Differential Evolution (SADE) to ameliorate the difficulties of finding appropriate input parameters for the DE technique. We quantify the performance of the methods proposed with a comprehensive comparison of different optimisers applied to the model, and demonstrate the validity of the approach proposed using recordings made from a DVS sensor mounted on a UAV. Copyright © 2019, The Authors. All rights reserved.

关键词： Neural networks

Transfer learning with deep Convolutional Neural Network (CNN) for pneumonia detection using chest X-ray

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Rahman, Tawsifur Chowdhury, Muhammad E.H. Khandakar, Amith Islam, Khandaker R. Islam, Khandaker F. Mahbub, Zaid B. Kadir, Muhammad A. Kashem, Saad Department of Biomedical Physics & Technology University of Dhaka Dhaka1000 Bangladesh Department of Electrical Engineering Qatar University Doha2713 Qatar Department of Orthodentics Bangabandhu Sheikh Mujib Medical University Dhaka1000 Bangladesh Department of Mathematics and Physics North South University Dhaka1229 Bangladesh Faculty of Robotics and Advanced Computing Qatar Armed Forces-Academic Bridge Program Qatar Foundation Doha24404 Qatar

Pneumonia is a life threatening disease, which occurs in the lungs caused by either bacterial or viral infection. It can be life endangering if not acted upon in the right time and thus early diagnosis of pneumonia is vital. The aim of this paper is to automatically detect bacterial and viral pneumonia using the digital x-ray images. It provides a detailed report on advances made in making accurate detection of pneumonia and then presents the methodology adopted by the authors. Four different pre-trained deep Convolutional Neural Network (CNN): AlexNet, ResNet18, DenseNet201 and SqueezeNet were used for transfer learning. 5247 chest x-ray images consisting of bacterial, viral and normal chest x-rays were used and through preprocessing techniques, the modified images were trained for the transfer learning based classification task. In this work, the authors have reported three schemes of classifications: normal vs pneumonia, bacterial vs viral pneumonia and normal, bacterial and viral pneumonia. The classification accuracy of normal and pneumonia images, bacterial and viral pneumonia images, and normal, bacterial and viral pneumonia were 98%, 95% and 93.3% respectively. This is the highest accuracy in any scheme than the accuracies reported in the literature. Therefore, the proposed study can be useful in faster diagnosing pneumonia by the radiologist and can help in the fast airports screening of the pneumonia patients. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

Positive pressure testing booths development and deployment in response to the COVID-19 outbreak

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Aroom, Kevin Ge, Jiawei White, Marcee Al-Zogbi, Lidia Trustman, Adrienne Greenbaum, Adena Krieger, Axel Farley, Jason Robert E. Fischell Institute for Biomedical Devices Department of Bioengineering University of Maryland College ParkMD20742 United States Laboratory for Computational Sensing and Robotics Department of Mechanical Engineering Johns Hopkins University BaltimoreMD21218 United States Robert E. Fischell Institute for Biomedical Devices Department of Mechanical Engineering University of Maryland College ParkMD20742 United States Total Health Care Inc. 1501 Division Street BaltimoreMD21217 United States Health Care for the Homeless 421 Fallsway BaltimoreMD21202 United States STI/HIV Program Baltimore City Health Department BaltimoreMD21202 United States The REACH Initiative Johns Hopkins University School of Nursing BaltimoreMD21205 United States

The COVID-19 pandemic left an unprecedented impact on the general public health, resulting in thousands of deaths in the US alone. Nationwide testing plans were initiated to control the spread, with drive-through being the currently dominant testing approach, which, however, exhausts personal protective equipment supplies, and is unfriendly to individuals not owning a vehicle. Walk-up testing booths are a safe alternative, but are too prohibitively priced on the market to allow for nationwide deployment. In this paper, we present an accessible, mobile, affordable, and safe version of a positive-pressure COVID-19 testing booth. The booths are manufactured using primarily off-the-shelf components from US vendors with minimized customization. The booths’ mobility allows them to be easily transported within local communities to test a larger subset of the population with fewer transportation options. Moreover, the final bill of materials does not surpass USD 3,900, which is about half of the market price. The booths are air conditioned and HEPA filtered to offer healthcare providers a safe and comfortable working environment. The prototype passed required pressure and air exchange tests, and was positively reviewed by two healthcare professionals. Currently, five booths are deployed and used at the Johns Hopkins University School of Nursing, Baltimore City Health Department, and two community health centers in Baltimore. Our design facilitates walk-up testing in the US, as it decreases PPE consumption;reduces the risk of infection;and is accessible to lower-income communities and non-drivers. © 2021, CC BY-SA.

关键词： Air conditioning

RRNet: Repetition-reduction network for energy efficient decoder of depth estimation

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Oh, Sangyun Kim, Hye-Jin S. Lee, Jongeun Kim, Junmo School of Electrical and Computer Engineering UNIST Ulsan Korea Republic of Neural Processing Research Center Seoul National University Seoul Korea Republic of Robotics Program School of Electrical Engineering KAIST Daejeon Korea Republic of Artificial Intelligence Laboratory ETRI Daejeon Korea Republic of

We introduce Repetition-Reduction network (RRNet) for resource-constrained depth estimation, offering significantly improved efficiency in terms of computation, memory and energy consumption. The proposed method is based on repetition-reduction (RR) blocks. The RR blocks consist of the set of repeated convolutions and the residual connection layer that take place of the pointwise reduction layer with linear connection to the decoder. The RRNet help reduce memory usage and power consumption in the residual connections to the decoder layers. RRNet consumes approximately 3.84 times less energy and 3.06 times less memory and is approaximately 2.21 times faster, without increasing the demand on hardware resource relative to the baseline network [1], outperforming current state-of-the-art lightweight architectures such as SqueezeNet [2], ShuffleNet [3], MobileNetv2 [4] and PyDNet [5]. Copyright © 2019, The Authors. All rights reserved.

关键词： Energy utilization

On-body non-invasive glucose monitoring sensor based on high figure of merit (FoM) surface plasmonic microwave resonator

学校读者我要写书评

暂无评论

Scientific reports 2023年第1期13卷 17527页

作者： Farzad Soltanian Mehdi Nosrati Saleh Mobayen Chuan-Chun Li Telung Pan Ming-Ta Ke Paweł Skruch Department of Electrical Engineering University of Alberta Edmonton Canada. Department of Electrical Engineering Manhattan College New York USA. Department of Electrical Engineering University of Zanjan Zanjan Iran. mobayens@yuntech.edu.tw. Graduate School of Intelligent Data Science National Yunlin University of Science and Technology Douliou 640301 Yunlin Taiwan. mobayens@yuntech.edu.tw. National Taiwan University Hospital Yunlin Branch Yunlin Taiwan. a***@***. Bachelor Program in Interdisciplinary Studies College of Future National Yunlin University of Science and Technology Yunlin 64002 Taiwan. Graduate School of Intelligent Data Science National Yunlin University of Science and Technology Douliou 640301 Yunlin Taiwan. Department of Automatic Control and Robotics AGH University of Science and Technology 30-059 Kraków Poland.

High-figure of merit (FoM) plasmonic microwave resonator is researched as a non-invasive on-body sensor to monitor the human body's blood glucose variation rate in adults for biomedical applications, e.g., diabetic patients. The resonance frequencies of the proposed sensor are measured to be around [Formula: see text] GHz and [Formula: see text] GHz over the frequency band of DC to 6GHz which are suitable for monitoring interstitial fluid (ISF) changing rate. The [Formula: see text] sensor is experimentally wrapped on the human body arm to monitor the blood glucose changing rate via amplitude and frequency variations of the sensor. Amplitude variation and frequency shift are measured to be around 7 dB and 30 MHz, respectively. The measured results demonstrate the high precision of the proposed approach to depict a valid diagram for glucose changing rate due to good impedance matching of the designed microwave sensor and human body. The sensor is shown to enhance the sensitivity by a factor of 5 compared to the conventional ones.

关键词：