检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Qi, Jun Du, Jun Siniscalchi, Sabato Marco Ma, Xiaoli Lee, Chin-Hui School of Electrical and Computer Engineering Georgia Institute of Technology AtlantaGA30332 United States National Engineering Laboratory for Speech and Language Information Processing University of Science and Technology of China Hefei230027 China Faculty of Architecture and Engineering University of Enna "Kore" Enna94100 Italy Georgia Institute of Technology AtlantaGA30332 United States

In this paper, we exploit the properties of mean absolute error (MAE) as a loss function for the deep neural network (DNN) based vector-to-vector regression. The goal of this work is two-fold: (i) presenting performance bounds of MAE, and (ii) demonstrating new properties of MAE that make it more appropriate than mean squared error (MSE) as a loss function for DNN based vector-to-vector regression. First, we show that a generalized upper-bound for DNN-based vector-to-vector regression can be ensured by leveraging the known Lipschitz continuity property of MAE. Next, we derive a new generalized upper bound in the presence of additive noise. Finally, in contrast to conventional MSE commonly adopted to approximate Gaussian errors for regression, we show that MAE can be interpreted as an error modeled by Laplacian distribution. Speech enhancement experiments are conducted to corroborate our proposed theorems and validate the performance advantages of MAE over MSE for DNN based regression. Copyright © 2020, The Authors. All rights reserved.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Analyzing upper bounds on mean absolute errors for deep neural network based vector-to-vector regression

arXiv

引用

arXiv 2020年

作者： Qi, Jun Du, Jun Marco Siniscalchi, Sabato Ma, Xiaoli Lee, Chin-Hui School of Electrical and Computer Engineering Georgia Institute of Technology AtlantaGA30332 United States National Engineering Laboratory for Speech and Language Information Processing University of Science and Technology of China Hefei230027 China Faculty of Architecture and Engineering University of Enna Kore Enna94100 Italy Georgia Institute of Technology AtlantaGA30332 United States

In this paper, we show that, in vector-to-vector regression utilizing deep neural networks (DNNs), a generalized loss of mean absolute error (MAE) between the predicted and expected feature vectors is upper bounded by the sum of an approximation error, an estimation error, and an optimization error. Leveraging upon error decomposition techniques in statistical learning theory and non-convex optimization theory, we derive upper bounds for each of the three aforementioned errors and impose necessary constraints on DNN models. Moreover, we assess our theoretical results through a set of image denoising and speech enhancement experiments. Our proposed upper bounds of MAE for DNN based vector-to-vector regression are corroborated by the experimental results and the upper bounds are valid with and without the "over-parametrization" technique. Copyright © 2020, The Authors. All rights reserved.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

On buildings that compute. A proposal

arXiv

引用

arXiv 2018年

作者： Adamatzky, Andrew Szacilowski, Konrad Przyczyna, Dawid Konkoli, Zoran Sirakoulis, Georgios C. Werner, Liss C. Unconventional Computing Laboratory UWE Bristol United Kingdom AGH University of Science and Technology Academic Centre for Materials and Nanotechnology Kraków Poland AGH University of Science and Technology Faculty of Physics and Applied Computer Science Kraków Poland Chalmers University of Technology Department of Microtechnology and Nanoscience Göthenburg Sweden Department of Electrical and Computer Engineering Democritus University of Thrace Xanthi Greece Institute of Architecture Technical University of Berlin Germany

We present ideas aimed at bringing revolutionary changes on architectures and buildings of tomorrow by radically advancing the technology for the building material concrete and hence building components. We propose that by using nanotechnology we could embed computation and sensing directly into the material used for construction. Intelligent concrete blocks and panels advanced with stimuli-responsive smart paints are the core of the proposed architecture. In particular, the photo-responsive paint would sense the buildings internal and external environment while the nano-materialconcrete composite material would be capable of sensing the building environment and implement massive-parallel information processing resulting in distributed decision making. A calibration of the proposed materials with in-materio suitable computational methods and corresponding building in-formation modelling, computer-aided design and digital manufacturing tools could be achieved via models and prototypes of information processing at nano-level. The emergent technology sees a building as high-level massiveparallel computer - assembled of computing concrete blocks. Based on the generic principles of neuromorphic computation and reservoir computing we envisage a single building or an urban quarter to turn into a large-scale sensing substrate. It could behave as a universal computer, collecting and processing environmental information in situ enabling appropriate data fusion. The broad range of spatio-temporal effects include infrastructural and human mobility, energy, bio-diversity, digital activity, urban management, art and socializing, robustness with regard to damage and noise or real-time monitoring of environmental changes. The proposed intelligent architectures will increase sustainability and viability in digitised urban environments by decreasing information transfer bandwidth by e.g, utilising 5G networks. The emergence of socio-cultural effect will create a cybernetic relationsh

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Design of a Mobile Data Collection Robot for Learning-based Localization and Autonomous Driving

Design of a Mobile Data Collection Robot for Learning-based ...

引用

Innovations in Intelligent Systems and Applications Conference

作者： Ali Ömer Baykar Jens Lambrecht Ayhan Kural Selçuk Eray Uygur Ahmet Yıldız Department of Mechanical Engineering Istanbul Technical University Istanbul Türkiye Department of Mechanical Engineering Turkish-German University Istanbul Türkiye Chair Industry Grade Networks and Clouds Faculty of Electrical Engineering and Computer Science Berlin Institute of Technology Berlin Germany Turkish-German University Istanbul Türkiye Macromedia University of Applied Sciences Hamburg Germany

This study introduces a mobile robot capable of collecting position and corresponding visual data seamlessly from both indoor and outdoor settings within the same sequence. The mobile robot has been specifically designed to navigate obstacles such as stairs and steps during transitions between indoor and outdoor environments. To accomplish this, the robot incorporates differential driving dynamics and is equipped with essential sensors including two stereo cameras, LIDAR, IMU, and GNSS. The entire system operates on the Robot Operating System (ROS). Consequently, it becomes possible to create a comprehensive dataset that encompasses not only the routes traversed by mobile vehicles but also includes all vehicle and pedestrian roads, as well as indoor spaces, found within a campus environment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Flexible triangular formation keeping of marine robotic vehicles using range measurements 1

引用

IFAC Proceedings Volumes 2014年第3期47卷 5145-5150页

作者： Francisco Rego Jorge M. Soares António Pascoal A. Pedro Aguiar Colin Jones Laboratory of Robotics and Systems in Engineering and Science Instituto Superior Técnico University of Lisbon Lisbon Portugal Department of Electrical and Computer Engineering Faculty of Engineering University of Porto Porto Portugal Institute of Mechanical Engineering School of Engineering École Polytechnique Fédérale de Lausanne Lausanne Switzerland Distributed Intelligent Systems and Algorithms Laboratory School of Architecture Civil and Environmental Engineering École Polytechnique Fédérale de Lausanne Lausanne Switzerland National Institute of Oceanography Dona Paula Goa India

This paper addresses the problem of keeping an autonomous marine vehicle in a moving triangular formation by regulating its position with respect to two leader vehicles. The follower vehicle has no prior knowledge of the path described by the leaders but has access to their heading angle and is able to measure inter-vehicle ranges. It is assumed that the distance between the leaders is constant and known. A control strategy is adopted that generates speed and heading commands so as to drive suitably defined along track and cross track errors to zero. The commands are used as input to local inner loops for yaw and speed control. The paper describes the algorithms derived for range-based control and assesses their performance in simulations using realistic models of the vehicles involved. Tests with three autonomous marine vehicles equipped with acoustic modems and ranging devices allow for the evaluation of the performance of the algorithms in a real-world situation.

关键词： Autonomous Vehicles Marine Systems Control Laws Formation Control Station Keeping Triangular Formations

来源：评论

学校读者我要写书评

暂无评论

Towards an ESL design framework for adaptive and fault-tolerant MPSoCs: MADNESS or not?

Towards an ESL design framework for adaptive and fault-toler...

引用

Embedded Systems for Real-Time Multimedia (ESTIMedia)

作者： Emanuele Cannella Lorenzo Di Gregorio Leandro Fiorin Menno Lindwer Paolo Melonr Olaf Neugebauer Andy Pimentel Leiden Institute of Advanced Computer Science Leiden University The Netherlands Lantiq Deutschland GmbH Neubiberg Germany Faculty of Informatics University of Lugano Switzerland Silicon Hive BV High Tech Campus 83 Eindhoven The Netherlands DIEE - Department of Electrical and Electronic Engineering University of Cagliari Cagliari Italy Informatik Centrum Dortmund Dortmund Germany Computer Systems Architecture Group University of Amsterdam The Netherlands

The MADNESS project aims at the definition of innovative system-level design methodologies for embedded MP-SoCs, extending the classic concept of design space exploration in multi-application domains to cope with high heterogeneity, technology scaling and system reliability. The main goal of the project is to provide a framework able to guide designers and researchers to the optimal composition of embedded MPSoC architectures, according to the requirements and the features of a given target application field. The proposed approach will tackle the new challenges, related to both architecture and design methodologies, arising with the technology scaling, the system reliability and the ever-growing computational needs of modern applications. The methodologies proposed with this project act at different levels of the design flow, enhancing the state-of-the art with novel features in system-level synthesis, architectural evaluation and prototyping. Support for fault resilience and efficient adaptive runtime management is introduced at hardware and middleware level, and considered by the system-level synthesis as one of the optimization factors to be taken into account. This paper presents the first stable results obtained in the MADNESS project, already demonstrating the effectiveness of the proposed methods.

关键词： Hardware Emulation Libraries Program processors Field programmable gate arrays Fault tolerance computer architecture

来源：评论

学校读者我要写书评

暂无评论

Development and study of the impacts of automated walking aids on the elderly

Development and study of the impacts of automated walking ai...

引用

International Conference on electrical engineering/Electronics, computer, Telecommunications and Information Technology, ECTI-CON

作者： Maleeya Tangjitjetsada Tawan Thianthong Chawalit Rakluea Wisit Loedhammacakra Paitoon Rakluea Nipont Tangthong Chatree Mahatthanajatuphat Nonchanutt Chudpooti Department of Electronics and Telecommunication Engineering Faculty of Engineering and Architecture Rajamangala University of Technology Suvarnabhumi Nonthaburi Thailand Siam Airport Ground Services Co. Ltd Bangkok Thailand Department of Electronics and Telecommunication Engineering Faculty of Engineering Rajamangala University of Technology Thanyaburi Pathum Thani Thailand Department of Electrical and Computer Engineering Faculty of Engineering King Mongkut’s University of Technology North Bangkok Bangkok Thailand Department of Industrial Physics and Medical Instrumentation Faculty of Applied Science King Mongkut’s University of Technology North Bangkok Bangkok Thailand

Since Thailand has now completely stepped into an aged society there are more than 20% of the population aged 60 years and over. There was also an increase in those who had problems with their balance. One of the main difficulties for these people is walking on their own. This paper presents an automatic walking aid for people with balance or walking problems. A specially designed automatic walking aid can be adjusted to six levels of height. It has an anti-collision warning system at a distance of up to 40 centimeters and displays GPS coordinates via SMS when falling. The experimental results of the prototype automatic walking aid showed that the walking aid could work as designed and could help people with balance problems walk more comfortably.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Smart Human Posture Monitoring Device Using a Wearable Vest

Design and Implementation of a Smart Human Posture Monitorin...

引用

International Conference on Advances in Biomedical engineering (ICABME)

作者： Roy Abi Zeid Daou Elio Geha Youssef Aoun Ali Hayek Josef Boercsoek Jose Javier Serrano Olmedo Biomedical Engineering department Furn El Chebbak Université La Sagesse Beirut Lebanon Education and Research Center MART Learning Chananir Lebanon Biomedical Technologies Department Faculty of Public Health Lebanese German University Jounieh Lebanon Department Lippstadt 2 Hardware Engineering Marker Allee 76-78 University of Applied Science Hamm-Lippstadt Hamm Department of Computer Architecture and System Programming Faculty of Electrical Engineering /Computer Science University of Kassel Germany Lab of Bioinstrumentation and Nanomedicine Centro de Tecnologia Biomedica Universidad Politecnica de Madrid Spain

Chronic back pain can present a serious health concern, with symptoms that can significantly affect an individual's well-being, mobility, and overall quality of life over an extended period. While chronic back pain may manifest suddenly in some cases, it often develops gradually and persists for weeks, and in untreated cases, it can linger for years. Hence, the utilization of assistive devices such as wearable posture-monitoring vests can offer valuable assistance and guidance to users. This research paper is dedicated to the development of a system for detecting, diagnosing, and correcting poor posture, specifically leaning posture. The vest is designed to provide users with visual, auditory, and tactile cues to help them address this issue, thereby reducing the risk associated with leaning. Additionally, an integrated electrical box has been designed to consolidate all components directly onto the main board in a secure enclosure. This box also displays the daily count of instances where the user has leaned. This system is characterized by its electrical safety, portability, compactness, comfort, and affordability. A comprehensive analysis of the system's performance has been conducted with a meticulous evaluation of accuracy. Each component of the system has undergone successful testing, and the system as a whole is currently in the testing phase. The results of these tests have indicated a lack of faulty errors and have demonstrated outstanding accuracy and detection rates. Over 100 individuals of varying ages, genders, and BMI categories were involved in testing, with each person wearing the device for an average of six hours. The accuracy rate achieved was 98.85%, with an average of 54.35 instances of poor posture detected per participant.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Gain-Analytical Equations Generalized for Fopid Controllers - an Application with Dc-Dc Power Converters

SSRN

引用

SSRN 2024年

作者： Batista, Edson Antonio da Pereira, Luís Felipe S.C. Volpato, Anderson S. de Brito, Moacyr A.G. Godoy, Ruben B. Pinto, João Pereira O. Tolbert, Leon M. Faculty of Engineering Architecture and Urban Planning and Geography Federal University of Mato Grosso do Sul University City Campo Grande 79070-900 Brazil Oak Ridge National Laboratory Oak RidgeTN United States Min H. Kao Department of Electrical Engineering and Computer Science University of Tennessee KnoxvilleTN United States

Algebraic formulations were constructed to determine the gains of a fractional-order PID regulator (FOPID) with a focus on satisfying stipulated gain crossover frequency, phase margin, and robustness to gain variation (iso-damping) specifications, particularly in relation to the fractional degrees inherent to the integral and derivative operations. Moreover, the differential evolution (DE) algorithm offers a viable mechanism for the optimal design of fractional-order values, adhering to constraints and synchronized with the FOPID gain parameter equations. This manuscript elucidates FPGA-in-the-loop simulations of FOPID controllers, which are predicated on DE tuning for both Buck and DC-DC Boost converters. These controllers undergo size optimization via the L 2 norm and are juxtaposed against MATLAB-Simulink simulations to validate the proposed methodology. These FOPID controllers are engineered with specific constraints geared toward modulating the duty cycle of the associated converters. The current study proffers two salient innovations aimed at minimizing electronic device dependency and conserving memory allocation: (a) the sole necessity of a singular sensor for voltage acquisition, and (b) the strategic disaggregation of the FOPID equation, facilitating the application of the L 2 norm-based reduction. The effectiveness of the proposed approach is validated through simulations and experiments. In the context of Buck converters, it demonstrates precision and efficacy in setpoint tracking amid fluctuations in load and input voltage. Simulations integrating parameter variations were also executed, under-scoring the damping rejection in response to load disturbances by the proposed FOPID. Conclusively, a comprehensive test bench was established, reinforcing the experimental validation of the presented methodology for DC-DC converters. For comparison purposes, established controllers, namely conventional PID, Type 3, and PID double derivative anchored on internal m

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Ameliorated Golden Jackal Optimization (Agjo) with Enhanced Movement and Multi-Angle Position Updating Strategy

SSRN

引用

SSRN 2023年

作者： Wahab, Magd Abdel Bai, Jianfu Khatir, Samir Abualigah, Laith Soete Laboratory Department of Electrical Energy Metals Mechanical Constructions and Systems Faculty of Engineering and Architecture Ghent University Belgium Computer Science Department Prince Hussein Bin Abdullah Faculty for Information Technology Al al-Bayt University Mafraq25113 Jordan Department of Electrical and Computer Engineering Lebanese American University Byblos13-5053 Lebanon Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman19328 Jordan MEU Research Unit Middle East University Amman11831 Jordan Applied Science Research Center Applied Science Private University Amman11931 Jordan School of Computer Sciences Universiti Sains Malaysia Pulau Pinang11800 Malaysia School of Engineering and Technology Sunway University Malaysia Petaling Jaya27500 Malaysia College of Engineering Yuan Ze University Taiwan

Golden jackal optimization (GJO), a lately published meta-heuristic optimization algorithm, is inspired by the foraging behavior of pairs of golden jackals and shows an acceptable optimization performance. However, GJO exists a shortage in balancing exploration and exploitation, as it completely focused on exploitation in the later iterations. This study proposes a new variant of GJO, named Ameliorated Golden jackal optimization (AGJO). AGJO uses three strategies to alleviate the imbalance between the exploration and exploitation of GJO: the enhanced movement strategy, the global search strategy, and the multi-angle position update strategy for prey. An environmental disturbance factor is added to the third strategy to strengthen GJO's ability to evade the local optimal solution. The performance of AGJO is tested and compared with GJO and seven well-known meta-heuristic algorithms for 23 classical benchmark functions, CEC 2017 and CEC 2019. These results determined that AGJO performs better over 90% of these functions compared to GJO. AGJO is also highly competitive in terms of optimization capability and convergence speed compared with other algorithms. Finally, AGJO is applied to optimize five engineering design problems with constraints. Results show that AGJO is a more potential algorithm for solving real problems with constraints than GJO and other algorithms. © 2023, The Authors. All rights reserved.

关键词： Optimization

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：