检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Gedon, Daniel Wahlström, Niklas Schön, Thomas B. Ljung, Lennart Dept. of Information Technology Uppsala University Sweden Div. of Automatic Control Linköping University Sweden

Deep state space models (SSMs) are an actively researched model class for temporal models developed in the deep learning community which have a close connection to classic SSMs. The use of deep SSMs as a black-box identification model can describe a wide range of dynamics due to the flexibility of deep neural networks. Additionally, the probabilistic nature of the model class allows the uncertainty of the system to be modelled. In this work a deep SSM class and its parameter learning algorithm are explained in an effort to extend the toolbox of nonlinear identification methods with a deep learning based method. Six recent deep SSMs are evaluated in a first unified implementation on nonlinear system identification benchmarks. Copyright © 2020, The Authors. All rights reserved.

关键词： State space methods

来源：评论

学校读者我要写书评

暂无评论

Role of Body Effect on Threshold Voltage of Strained Si}-Si XGe 1-X} MOSFET 3

Role of Body Effect on Threshold Voltage of Strained Si}-Si ...

引用

3rd International Conference on Devices for Integrated Circuit, DevIC 2019

作者： Mukhopadhyay, Swarnav Deyasi, Arpan Dept. of Electronics and Telecommunication Engineering Jadavpur University Kolkata India Dept. of Electronics and Communication Engineering RCC Institute of Information Technology Kolkata India

ISBN: (纸本)9781538667224

Role of body effect coefficient on threshold voltage of strained Si/SiGe MOSFET is analytically investigated. Effect of dielectric thickness, doping concentration and dielectric material are computed on the threshold condition both in presence and absence of body effect. Simulation findings reveal that introduction of strained material in otherwise ideal structure enhances carrier mobility which, in turn, reduces threshold voltage. Sharp peak is observed when body effect is taken into account for a particular heterostructure composition due to enhancement of tunneling probability which decrease of barrier potential, and thus carrier flow is augmented. A few results for n-channel MOSFET are also represented to further justify the importance of novelty of the paper. Result also suggests that higher doping or thicker dielectric region leads to depletion mode of operation. An optimized design criterion is evaluated for the minimum threshold under inversion condition. © 2019 IEEE.

关键词： Threshold voltage

来源：评论

学校读者我要写书评

暂无评论

Transformerless Single-phase Grid-tied Micro Wind Turbine System Featuring Low Component-count 19

Transformerless Single-phase Grid-tied Micro Wind Turbine Sy...

引用

19th IEEE International Conference on Environment and Electrical engineering and 2019 IEEE Industrial and Commercial Power Systems Europe, EEEIC/I and CPS Europe 2019

作者： Zakzouk, Nahla E. Ahmed, Rana Electrical and Control Dept. College of Engineering and Technology Arab Academy for Science and Technology and Maritime Transport Alexandria Egypt

ISBN: (纸本)9781728106526

In the presented paper, a single-phase micro wind turbine (MWT) grid-tied system is proposed featuring less component-count. The conventional bulky power conversion system, featuring a rectifier, DC/DC converter, single-phase voltage source inverter (VSI) and a step-up transformer, is replaced by only a rectifier and a single-phase current source inverter (CSI) for its voltage boosting capabilities and inherited short-circuit capability. Hence, the entire system size, cost and losses are reduced. Moreover, the VSI DC-link electrolytic capacitor is eliminated improving system reliability and lifetime. However, in the proposed system, the single-stage CSI is solely responsible for tracking the MWT maximum power and injecting it into grid. To achieve the latter, efficient control scheme is proposed along with a simple sinusoidal pulse width modulation technique that results in minimal harmonic in the grid current. Simulation work verified the proposed system effectiveness along with the proposed control scheme and PWM technique, under abrupt changes in the wind speed. © 2019 IEEE.

关键词： Electric power transmission networks

来源：评论

学校读者我要写书评

暂无评论

Two TS-Fuzzy controllers based Direct Torque control of 5-Phase Induction Motor

Two TS-Fuzzy Controllers based Direct Torque Control of 5-Ph...

引用

International Conference on Power Electronic Drives

作者： Malik G. Al-Ghanimi Omar Hanif Mahit V. Jain A. Siva Kumar Ramana Rao M. V R. Kavin Siva Ganesh Malla Jagan Mohana Rao Malla Md. Amzad Hossain Technical institute of Al-Mussaib Al-Furat Al-Awsat Technical University Iraq Dept. of Automatic Control and Systems Engineering The University of Sheffield Sheffield The United Kingdom Sigma Institute of Engineering Vadodara India Department of EEE Panimalar Engineering College Chennai Tamilnadu India University College of Engineering Osmania University Hyderabad India Sri Krishna College of Engineering & Technology Coimbatore India CPGC Pvt. Ltd. Visakhapatnam India Geethanjali College of Engineering and Technology Hyderabad Telangana India Institute of Theoretical Electrical Engineering Ruhr University Bochum (RUB) Germany

The interest on five phase induction motor drives is gradually increasing due to its wide variety of applications including electric vehicles, high compressor systems, ship propulsion etc. The designing of a proper controller to make 5-phase induction motor based electric drive is playing a vital role for many usages among many controllers, a direct torque controller (DTC) is a famous technique to achieve motor torque with fewer ripples. Moreover, Takagi Suguno - Fuzzy (TS-Fuzzy) controllers can provide fast response under rapid changes of inputs. Therefore, TS-Fuzzy based DTC of 5-phase induction motor drive is proposed in this paper. Further, the space vector modulation technique is implemented for obtaining proper pulse sequence for 5-phase inverter to drive the motor. In order to achieve smooth control of both torque and flux, two fuzzy logic controllers are deployed on the DTC of the motor. For better illustration, responses of the proposed TS-Fuzzy based DTC of 5-phase induction motor are compared with 3-phase motor. The proposed method is simulated and presented in this paper to analyze the performance of the proposed method under various conditions.

关键词： Induction motor drives Support vector machines Fuzzy logic Torque Torque control Modulation Switches

来源：评论

学校读者我要写书评

暂无评论

CUTIE: Beyond PetaOp/s/W Ternary DNN inference acceleration with better-than-binary energy efficiency

arXiv

引用

arXiv 2020年

作者： Scherer, Moritz Rutishauser, Georg Cavigelli, Lukas Benini, Luca Dept. of Information Technology and Electrical Engineering ETH Zürich Switzerland Huawei Technologies Zurich Research Center Switzerland Dept. of Electrical Electronic and Information Engineering University of Bologna Italy

We present a 3.1 POp/s/W fully digital hardware accelerator for ternary neural networks. CUTIE, the Completely Unrolled Ternary Inference Engine, focuses on minimizing non-computational energy and switching activity so that dynamic power spent on storing (locally or globally) intermediate results is minimized. This is achieved by 1) a data path architecture completely unrolled in the feature map and filter dimensions to reduce switching activity by favoring silencing over iterative computation and maximizing data re-use, 2) targeting ternary neural networks which, in contrast to binary NNs, allow for sparse weights which reduce switching activity, and 3) introducing an optimized training method for higher sparsity of the filter weights, resulting in a further reduction of the switching activity. Compared with state-of-the-art accelerators, CUTIE achieves greater or equal accuracy while decreasing the overall core inference energy cost by a factor of 4.8×–21×. Copyright © 2020, The Authors. All rights reserved.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

InTrust-IoT: Intelligent Ecosystem based on Power Profiling of Trusted device(s) in IoT for Hardware Trojan Detection 21

InTrust-IoT: Intelligent Ecosystem based on Power Profiling ...

引用

Workshop on Hardware and Architectural Support for Security and Privacy

作者： Hawzhin Mohammed Faiq Khalid Paul Sawyer Gabriella Cataloni Syed Rafay Hasan Information Science and Technology Penn State University United States Inst. of Computer Eng. Technische Universitat Wien Austria School of Engineering Liberty University United States Dept. of Elect. and Comp. Eng. University of Mount Union United States Electrical and Computer Engineering Tennessee Tech University United States

ISBN: (纸本)9781450396141

Modern Resource-Constrained (RC) Internet of Things (IoT) devices are subject to several types of attacks, including hardware-level attacks. Most of the existing state-of-the-art solutions are invasive, require expensive design time interventions, or need dataset generation from non-trusted RC-IoT devices or both. We argue that the health of modern RC-IoT devices requires a final line of defense against possible hardware attacks that go undetected during the IC design and test process. Hence, in this paper, we propose a defense methodology against non-zero-day and zero-day attacks, leveraging machine learning techniques trained on the dataset obtained without design time intervention and using ‘only’ trusted IoT devices. In the process, a complete eco-system is developed where data is generated through a trusted group of devices, and machine learning is done on these trusted datasets. Next, this trusted trained model is deployed in regular IoT systems that contain untrusted devices, where the attack on untrusted devices can be detected in real-time. Our results indicate that for non-zero-day attacks, the proposed technique can concurrently detect DoS and power depletion attacks with an accuracy of about 80%. Similarly, zero-day attack experiments are able to detect the attack without fail as well.

关键词： Decision Tree IoT Power Profiling Hardware Trojan Machine Learning Internet-of-Things Multi-level Perceptron

来源：评论

学校读者我要写书评

暂无评论

Key Generation of Biomedical Implanted Antennas Through Artificial Neural Networks

Key Generation of Biomedical Implanted Antennas Through Arti...

引用

IEEE International Conference on Connected Health: Applications, Systems and engineering Technologies (CHASE)

作者： Lida Kouhalvandi Ladislau Matekovits Ildiko Peter Dogus University Istanbul Turkey Politecnico di Torino Dept. Electronics and TelecommunicationsTurinItaly Faculty of Engineering and Information Technology University of Medicine Pharmacy Science and Technology “George Emil Palade” Târgu-Mureş Romania

ISBN: (纸本)9781665439664

This paper presents an accurate and efficient optimization-based approach for modelling and sizing implanted antennas automatically. The proposed method employs the long short-term memory (LSTM) artificial neural network (ANN) for predicting the design specifications in not only one frequency but also in a large frequency band. The entire process is performed in an automated environment that is the combination of electronic design automation (EDA) tools and the numerical analyzer. Based on this intelligent method, the difficulty of designing electromagnetic (EM)-based antennas is solved to the most degrees and the design parameters can be achieved in the easiest way. To validate the efficiency of the presented ANN, two implanted antennas are designed; they and realized on a grounded biocompatible substrate and covered by bone, muscle, fat, and skin tissues, respectively. These implanted antennas are optimized in terms of input scattering parameter, E-plane and H-plane radiation pattern (RP) specifications and the suitable design parameters are provided automatically. The modelled implanted antennas are appropriate to be used at the industrial, scientific, and medical (ISM) frequency band between 2.4 GHz and 2.5 GHz.

关键词： Performance evaluation Artificial neural networks Muscles Bones Skin Fats Scattering parameters

来源：评论

学校读者我要写书评

暂无评论

Spectroscopic detection of pigments in tissues: correlation with tissue aging and cancer development

Spectroscopic detection of pigments in tissues: correlation ...

引用

2022 International Conference Laser Optics, ICLO 2022

作者： Oliveira, L.M. Goncalves, T.M. Botelho, A.R. Martins, I.S. Silva, H.F. Carneiro, I. Carvalho, S. Henrique, R. Tuchin, V.V. Porto Portugal Center of Innovation in Engineering and Industrial Technology Isep Porto Portugal Department of Electrical and Computer Engineering Porto University-School of Engineering Porto Portugal Department of Pathology and Cancer Biology and Epigenetics Group Portuguese Oncology Institute of Porto Porto Portugal Porto Portugal Viana do Castelo Portugal Dept. of Pathol. and Molecular Immunology Porto University-Institute of Biomedical Sciences Abel Salazar Porto Portugal Science Medical Center Saratov State University Saratov Russia Laboratory of Laser Molecular Imaging and Machine Learning National Research Tomsk State University Tomsk Russia Laboratory of Laser Diagnostics of Technical and Living Systems Institute of Precision Mechanics and Control Frc-Saratov Scientific Centre-of the Russian Academy of Sciences Saratov Russia

ISBN: (纸本)9781665466646

The direct calculation of the absorption coefficient spectra of various tissues from spectral measurements allowed to retrieve the contents of melanin and lipofuscin. In the rabbit brain cortex, 1.8 times higher melanin content is explained by the neuron degeneration process. Similar melanin and lipofuscin contents were found in the rabbit pancreas as a result of the tissue aging process. The conversion of 83 % of the melanin in the human normal kidney into lipofuscin in the cancer kidney indicates that lipofuscin can be considered a kidney cancer marker in humans. © 2022 IEEE.

关键词： Tissue

来源：评论

学校读者我要写书评

暂无评论

Tuina Force Acquisition System of Finger Pressing Therapy 2

Tuina Force Acquisition System of Finger Pressing Therapy

引用

2nd International Conference on Artificial Intelligence and Computer Science, AICS 2020

作者： Zhang, Yu Zhang, Hao Li, Shanhong Meng, Fangfang Ma, Tingting Chu, Zhong Institute of Intelligent Machines Hfips Chinese Academy of Sciences Hefei230031 China University of Science and Technology of China Hefei230026 China Dept. of Electronic Information and Electrical Engineering Hefei University Hefei230601 China

A Tuina force acquisition system of finger pressing therapy is discussed. Based on STC12C5A60S2, a display platform for Tuina force acquisition is designed. The hardware of the system is mainly composed of minimum system module, signal acquisition module, amplification and filtering circuit, sound and light alarm module and display module. The system is initialized at startup and adjusted to data acquisition state. When the doctor starts to massage, the measured data by sensor is transmitted to data acquisition system, then transmitted to host computer after processed by single-chip module. The data is displayed real-Timely and dynamically on host computer and judged whether or not to generate alarm according to the preset threshold. When the sensor prober is placed on his upper arm, and mechanical stimulation is performed using finger-pressing therapy, the system can collect and display finger-pressing massage force accurately in real time. Experiments show that the system can collect massage force quickly and effectively in real time. © Published under licence by IOP Publishing Ltd.

关键词： Data acquisition

来源：评论

学校读者我要写书评

暂无评论

Automatic dairy cow body condition scoring using dept. images and 3D surface fitting

Automatic dairy cow body condition scoring using depth image...

引用

2019 IEEE International Conference on Unmanned Systems and Artificial Intelligence, ICUSAI 2019

作者： Li, Wen-Yong Shen, Yang Wang, Du-Jin Yang, Zhan-Kui Yang, Xin-Ting National Engineering Research Center for Information Technology in Agriculture Dept. Intelligent System Beijing China Tianjin University of Science Technology Dept. Electronic Information and Automation Tianjin China Beijing University of Technology Dept. Computer Science Beijing China

ISBN: (纸本)9781728158594

Automatic and objective body condition scoring of dairy cow has aroused great researches as a method to assist management of nutritional programs in dairy herds. This study presents a 3-dimensional surface fitting approach that provides a structure description of dairy cow's body for BCS estimation. a 3-dimensional algorithm that provides a topographical understanding of the cow's body to estimate BCS. In this study, the hypothesis tested was that the body contour of a fatter dairy cow is plumper than that of a thin dairy cow and, therefore, may better fit a paraboloid surface. dept. image processing and fitting model were investigated and consisted of three stages: (1) object location and separation of individual cow;(2) image surface fitting;and (3) parameters determination in body condition scoring (BCS) model. Compared with the previous studies, the novelty in this paper was completing the full-automation of a BCS system. The proposed model was trained and tested with the BCS value obtained manually. Pearson correlation between the proposed BCS and the manual BCS was 0.84 for the test data set. © 2019 IEEE.

关键词： Computer vision

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：