检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Balaskas, Konstantinos Karatzas, Andreas Sad, Christos Siozios, Kostas Anagnostopoulos, Iraklis Zervakis, Georgios Henkel, Jörg The Department of Physics Aristotle University of Thessaloniki Thessaloniki54124 Greece Karlsruhe Institute of Technology Karlsruhe76131 Germany The School of Electrical Computer and Biomedical Engineering Southern Illinois University Carbondale CarbondaleIL62901 United States The Dept. of Computer Engineering & Informatics University of Patras Patras26504 Greece

Deep Neural Networks (DNNs) have shown significant advantages in a wide variety of domains. However, DNNs are becoming computationally intensive and energy hungry at an exponential pace, while at the same time, there is a vast demand for running sophisticated DNN-based services on resource constrained embedded devices. In this paper, we target energy-efficient inference on embedded DNN accelerators. To that end, we propose an automated framework to compress DNNs in a hardware-aware manner by jointly employing pruning and quantization. We explore, for the first time, per-layer fine- and coarse-grained pruning, in the same DNN architecture, in addition to low bit-width mixed-precision quantization for weights and activations. Reinforcement Learning (RL) is used to explore the associated design space and identify the pruning-quantization configuration so that the energy consumption is minimized whilst the prediction accuracy loss is retained at acceptable levels. Using our novel composite RL agent we are able to extract energy-efficient solutions without requiring retraining and/or fine tuning. Our extensive experimental evaluation over widely used DNNs and the CIFAR-10/100 and ImageNet datasets demonstrates that our framework achieves 39% average energy reduction for 1.7% average accuracy loss and outperforms significantly the state-of-the-art approaches. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Boundary-Aware Value Function Generation for Safe Stochastic Motion Planning

arXiv

引用

arXiv 2024年

作者： Xu, Junhong Yin, Kai Gregory, Jason M. Hauser, Kris Liu, Lantao Luddy School of Informatics Computing and Engineering Indiana University-Bloomington United States Expedia Group U.S. Army Research Laboratory United States Department of Computer Science University of Illinois at Urbana-Champaign United States

Navigation safety is critical for many autonomous systems such as self-driving vehicles in an urban environment. It requires an explicit consideration of boundary constraints that describe the borders of any infeasible, non-navigable, or unsafe regions. We propose a principled boundary-aware safe stochastic planning framework with promising results. Our method generates a value function that can strictly distinguish the state values between free (safe) and non-navigable (boundary) spaces in the continuous state, naturally leading to a safe boundary-aware policy. At the core of our solution lies a seamless integration of finite elements and kernel-based functions, where the finite elements allow us to characterize safety-critical states’ borders accurately, and the kernel-based function speeds up computation for the non-safety-critical states. The proposed method was evaluated through extensive simulations and demonstrated safe navigation behaviors in mobile navigation tasks. Additionally, we demonstrate that our approach can maneuver safely and efficiently in cluttered real-world environments using a ground vehicle with strong external disturbances, such as navigating on a slippery floor and against external human intervention. © 2024, CC BY.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

An IoT model for securing examinations from malpractices

引用

Materials Today: Proceedings 2023年 81卷 371-376页

作者： Shameemul Haque Sana Zeba Md. Alimul Haque Kailash Kumar Mudassir Peeran Ali Basha Al-Hafeez College Ara VeerKunwar Singh University Ara India Department of Computer Engineering JamiaMiliaIslamia New Delhi India Department of Computer Science VeerKunwar Singh University Ara India College of Computing and Informatics Saudi Electronic University Riyadh Saudi Arabia Department of Information System University of Bisha Saudi Arabia

The primary objective of university education is to provide students with the required information and skills to enable them to make a successful contribution to the national development effort. In order to evaluate the level of expertise and skill of students, this preparation includes frequent examination and appraisal in the form of tests. Manual exams are carried out by most universities; Post Graduate and Under Graduate in India. Due to multiple uses made of the outcomes of the students, these examinations have high stakes. Consequently, the experiments became subject to different types of malpractice. Test malpractice affects the success of students in exams and leaves the scores/grades earned inaccurate, hence a challenge to examination bodies and the nation's education system (India). These are all disturbing signs that pose a danger to the nation. Examination malpractice has eaten deep into the Indian culture of education. Therefore, the object of this paper is to explore the problem of examination malpractice in India. The paper covered relevant measures, procedure setting/implementation and suggestions for this action. And finally, a model is proposed to stop malpractices in the examination. This IoT based model is used for detecting any metallic object or object in a range more than normal IR proximity sensor range. The block diagram of proposed model and circuit diagram for that model discussed in detail. This proposed model may be used for any investigation in the universities examinations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Causal Structure Learning from Imperfect Longitudinal Data in Healthcare

Causal Structure Learning from Imperfect Longitudinal Data i...

引用

IEEE International Conference on Healthcare informatics (ICHI)

作者： Haoyu Yang Roshan Tourani Jia Li Pedro Caraballo Michael Steinbach Vipin Kumar Gyorgy Simon Dept. of Computer Science and Engineering University of Minnesota Minneapolis USA Institute for Health Informatics University of Minnesota Minneapolis USA Dept. of Internal Medicine Mayo Clinic Rochester USA

Causal Structure Discovery (CSD) is the task of learning the set of underlying causal relationships from observational data. Due to their computational scalability and flexibility, a recently developed class of CSD methods, NOTEARS, based on a formulation allowing for continuous optimization, is gaining popularity. However, this formulation can lead to incorrect edge orientations when little/no likelihood advantage is conferred upon any edge orientation, e.g., a → b → c versus c → b → a. In longitudinal data, like electronic health records (EHRs), temporal relationships are observable among many pairs of variables. Such temporal relationship is imperfect but still suggest an orientation since causal effects cannot travel backwards in time. Following this idea, we propose methods to incorporate precedence constraints into continuous optimization-based CSD methods. Experiments on both a synthetic and two real-world datasets validate the effectiveness of the proposed precedence constraints.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Technical light-field setup for 3D imaging of the human nerve head validated with an eye model

引用

Current Directions in Biomedical engineering 2021年第2期7卷 433-436页

作者： Schramm, Stefan Dietzel, Alexander Blum, Maren-Christina Link, Dietmar Klee, Sascha Institute of Biomedical Engineering and Informatics Faculty of Computer Sciences and Automation Technische Universität Ilmenau Ilmenau Germany Department of General Health Studies Division Biostatistics and Data Science Karl Landsteiner University of Health Sciences Krems an der Donau Austria

With the new technology of 3D light field (LF) imaging, fundus photography can be expanded to provide depth information. This increases the diagnostic possibilities and additionally improves image quality by digitally refocusing. To provide depth information in the human optic nerve head such as in glaucoma diagnostics, a mydriatic fundus camera was upgraded with an LF imager. The aim of the study presented here was the validation of the technical setup and resulting depth estimations with an appropriate eye model. The technical setup consisted of a mydriatic fundus camera (FF450, Carl Zeiss Meditec AG, Jena, Germany) and an LF imager (R12, Raytrix GmbH, Kiel, Germany). The field of view was set to 30°. The eye model (24.65 mm total length) consisted of a two-lens optical system and interchangeable fundus models with papilla excavations from 0.2 to 1 mm in steps of 0.2 mm. They were coated with red acrylic lacquer and vessels were drawn with a thin brush. 15 images were taken for each papilla depth illuminated with green light (wavelength 520 nm ± 20 nm). Papilla depth was measured from the papilla ground to the surrounding flat region. All 15 measurements for each papilla depth were averaged and compared to the printed depth. It was possible to perform 3D fundus imaging in an eye model by means of a novel LF-based optical setup. All LF images could be digitally refocused subsequently. Depth estimation in the eye model was successfully performed over a 30° field of view. The measured virtual depth and the printed model papilla depth is linear correlated. The presented LF setup allowed high-quality 3D one-shot imaging and depth estimation of the optic nerve head in an eye model. © 2021 by Walter de Gruyter Berlin/Boston.

关键词： Optical systems

来源：评论

学校读者我要写书评

暂无评论

The Challenges of Music Deep Learning for Traditional Music 12

The Challenges of Music Deep Learning for Traditional Music

引用

12th International Conference on Modern Circuits and Systems Technologies, MOCAST 2023

作者： Moysis, Lazaros Iliadis, Lazaros Alexios Sotiroudis, Sotirios P. Kokkinidis, Kostas Sarigiannidis, Panagiotis Nikolaidis, Spiridon Volos, Christos Boursianis, Achilles D. Babas, Dimitrios Papadopoulou, Maria S. Goudos, Sotirios K. Aristotle University of Thessaloniki Laboratory of Nonlinear Systems - Circuits & Complexity School of Physics Thessaloniki Greece University of Western Macedonia Department of Mechanical Engineering Kozani Greece Aristotle University of Thessaloniki ELEDIA@AUTH School of Physics Thessaloniki54124 Greece University of Macedonia Department of Applied Informatics Thessaloniki Greece University of Western Macedonia Department of Electrical and Computer Engineering Kozani50131 Greece School of Physics Aristotle University of Thessaloniki Thessaloniki Greece International Hellenic University Department of Information and Electronic Engineering Sindos57400 Greece

ISBN: (纸本)9798350321074

Numerous applications for music listeners, educators, DJs, and musicians have been created over the past decade as the field of Music Deep Learning has expanded. Evidently, the majority of works rely on training their architectures using well-established databases, which consist primarily of Western popular music genres. This creates a deficiency in applications focusing on traditional and regional music, which are vital to preserving culture. As an increasing number of research groups begin to develop works centered on traditional music, several practical challenges for applying deep learning arise. This work discusses these issues and the future of deep learning in the study of traditional music. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Parameter Analysis of Biosignals in Long-Term Control Medical Devices Management

Multi-Parameter Analysis of Biosignals in Long-Term Control ...

引用

Human-computer Interaction, Optimization and Robotic Applications (HORA), International Congress on

作者： Serhii Holdobin Natalia Brynza Olha Tiutiunyk Olena Serhiienko Ihor Sosnov Pavlo Samus Industrial and Biomedical Electronics Department Kharkiv polytechnic institute National Technical University Kharkiv Ukraine Department of Informatics and Computer Technology Simon Kuznets Kharkiv National University of Economics Kharkiv Ukraine Department of Applied Mathematics Kharkiv National University of Radio Electronics Kharkiv Ukraine Department of Informatics and Computer Engineering Simon Kuznets Kharkiv National University of Economics Kharkiv Ukraine Business Trade and Logistics Department Kharkiv Polytechnic Institute National Technical University Kharkiv Ukraine

ISBN: (数字)9798331510886

ISBN: (纸本)9798331510893

The development of data processing technologies, microelectronics and sensor systems allows for high-precision multiparametric analysis of biosignals in real time. The paper considers the problem of automating medical processes to reduce the influence of the human factor and increase the accuracy of diagnostics. An improved method of multiparametric analysis of biosignals is proposed for long-term monitoring of the state of the cardiovascular system using modern sensor devices, data processing algorithms and artificial intelligence technologies. The research is aimed at improving the methods of collecting, transmitting and analyzing biosignals, which contributes to the creation of personalized medical devices and effective prediction of cardiovascular pathologies. The issues of classification of devices and biosignals, as well as their mathematical modeling to increase the accuracy of diagnostics, are considered.

关键词： Cardiovascular system Wireless sensor networks Accuracy Medical devices Heuristic algorithms Robot sensing systems Prediction algorithms Real-time systems Classification algorithms Monitoring

来源：评论

学校读者我要写书评

暂无评论

Stroke Prediction Using Machine Learning

Stroke Prediction Using Machine Learning

引用

International Conference on Advances in Electronics, computers and Communications (ICAECC)

作者： Abinandhini D M Aman Kumar Gudi Vishnu Teja Mandava Sukesh Divya S Naman Chauhan I R Oviya Kalpana Raja Department of Computer Science and Engineering (Artificial Intelligence) Amrita Vishwa Vidyapeetham Chennai India Section for Biomedical Informatics and Data Science School of Medicine Yale University New Haven Connecticut USA

ISBN: (数字)9798350305449

ISBN: (纸本)9798350305456

A stroke is a serious medical emergency that happens when bleeding or blood clots cut off the blood flow to a part of the brain. With a mortality rate of 5.5 million per year, it ranks as the second leading cause of death globally. Over 15 million individuals experience a stroke each year, and one person dies from one every four minutes. According to the World Health Organization, stroke is the main cause of death and disability worldwide (WHO). Identifying the many stroke warning signs helps lessen the severity of the stroke. A stroke can be avoided in up to 80% of instances because it is typically the result of a poor lifestyle. As a result, stroke prediction becomes important and should be employed to stop it from causing long-term harm. The current study uses a variety of machine learning models, including Gaussian Naive Bayes, Logistic Regression, Support Vector Machine (SVM), KNN and Random Forest to predict stroke. The paper presents the comparison among all machine learning algorithms. Analysis of results revealed that KNN had the least accuracy of 76.32% and Random Forest had the highest accuracy of 94.81%.

关键词： Support vector machines Accuracy Organizations Stroke (medical condition) Predictive models Vectors Physiology

来源：评论

学校读者我要写书评

暂无评论

A resource conscious human action recognition framework using 26-layered deep convolutional neural network

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2021年第28-29期80卷 35827-35849页

作者： Khan, Muhammad Attique Zhang, Yu-Dong Khan, Sajid Ali Attique, Muhammad Rehman, Amjad Seo, Sanghyun Department of Computer Science HITEC University Taxila Pakistan Department of Informatics University of Leicester Leicester UK Department of Software Engineering Foundation University Islamabad Islamabad Pakistan Department of Software Sejong University Seoul South Korea Department of Information Sciences Prince Sultan University Riyadh Saudi Arabia School of Computer Art College of Art and Technology Chung-Ang University Anseong Republic of Korea

Vision-based human action recognition (HAR) is a hot topic of research from the decade due to a few popular applications such as visual surveillance and robotics. For correct action recognition, various local and global points are requires known as features. These features modified during the variation in human movement. But due to a bit change in several human actions, the features of these actions are mixed that degrade the recognition performance. In this article, we design a new 26-layered Convolutional Neural Network (CNN) architecture for accurate complex action recognition. The features are extracted from the global average pooling layer and fully connected (FC) layer, and fused by a proposed high entropy-based approach. Further, we propose a feature selection method name Poisson distribution along with Univariate Measures (PDaUM). Few of fused CNN features are irrelevant, and few of them are redundant that makes the incorrect prediction among complex human actions. Therefore, the proposed PDaUM based approach selects only the strongest features that later passed to the Extreme Learning Machine (ELM) and Softmax for final recognition. Four datasets are using for experimental analysis - HMDB51 (51 classes), UCF Sports (10 classes), KTH (6 classes), and Weizmann (10 classes). On these datasets, the ELM classifier gives an improved performance as compared to a Softmax classifier. The achieved accuracy on each dataset is 81.4%, 99.2%, 98.3%, and 98.7%, respectively. Comparison with existing techniques, it is shown that the proposed architecture gives better performance in terms of accuracy and testing time.

关键词： Action recognition CNN architecture Features fusion Features selection ELM

来源：评论

学校读者我要写书评

暂无评论

Memory-Friendly Scalable Super-Resolution via Rewinding Lottery Ticket Hypothesis

Memory-Friendly Scalable Super-Resolution via Rewinding Lott...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Jin Lin Xiaotong Luo Ming Hong Yanyun Qu Yuan Xie Zongze Wu School of Informatics Xiamen University Fujian China School of Computer Science and Technology East China Normal University Shanghai China School of Mechatronics and Control Engineering Shenzhen University Shenzhen China

Scalable deep Super-Resolution (SR) models are increasingly in demand, whose memory can be customized and tuned to the computational recourse of the platform. The existing dynamic scalable SR methods are not memory-friendly enough because multi-scale models have to be saved with a fixed size for each model. Inspired by the success of Lottery Tickets Hypothesis (LTH) on image classification, we explore the existence of unstructured scalable SR deep models, that is, we find gradual shrinkage subnetworks of extreme sparsity named winning tickets. In this paper, we propose a Memory-friendly Scalable SR framework (MSSR). The advantage is that only a single scalable model covers multiple SR models with different sizes, instead of reloading SR models of different sizes. Concretely, MSSR consists of the forward and backward stages, the former for model compression and the latter for model expansion. In the forward stage, we take advantage of LTH with rewinding weights to progressively shrink the SR model and the pruning-out masks that form nested sets. Moreover, stochastic self-distillation (SSD) is conducted to boost the performance of sub-networks. By stochastically selecting multiple depths, the current model inputs the selected features into the corresponding parts in the larger model and improves the performance of the current model based on the feedback results of the larger model. In the backward stage, the smaller SR model could be expanded by recovering and fine-tuning the pruned parameters according to the pruning-out masks obtained in the forward. Extensive experiments show the effectiveness of MMSR. The smallest-scale sub-network could achieve the sparsity of 94% and outperforms the compared lightweight SR methods.

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：