检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Li, Li El Rami, Jean-Pierre S. Taylor, Adrian Rao, James Hailing Kunz, Thomas Defence Research & Development Canada Ottawa Canada Dept of Electrical and Computer Engineering Queen's University Kingston Canada Dept. of Systems & Computer Engineering Carleton University Ottawa Canada

This work aims to enable autonomous agents for network cyber operations (CyOps) by applying reinforcement and deep reinforcement learning (RL/DRL). The required RL training environment is particularly challenging, as it must balance the need for high fidelity, best achieved through real network emulation, with the need for running large numbers of training episodes, best achieved using simulation. A unified training environment, namely the Cyber Gym for Intelligent Learning (CyGIL), is developed where an emulated CyGIL-E automatically generates a simulated CyGIL-S. From preliminary experimental results, CyGIL-S can train agents in minutes compared with the days required in CyGIL-E. The agents trained in CyGIL-S are transferrable directly to CyGIL-E, showing full decision proficiency in the emulated "real" network. Enabling offline RL, the CyGIL solution presents a promising direction towards simto-real in leveraging RL agents in real-world cyber networks. © 2023, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Speaker's Emotions Recognition Module Based on the GoogleLeNet Neural Network

Speaker's Emotions Recognition Module Based on the GoogleLeN...

引用

2022 International Conference on Smart Information systems and Technologies, SIST 2022

作者： Tereikovskyi, Ihor Tereikovska, Liudmyla Kryvoruchko, Olena Tereikovskyi, Oleh Tyshchenko, Dmytro Franchuk, Tamara National Technical University Of Ukraine Igor Sikorsky Kyiv Polytechnic Institute Dept. Of System Programming And Specialized Computer Systems Kyiv Ukraine Kyiv National University Of Construction And Architecture Dept. Of Information Technology For Design And Applied Mathematics Kyiv Ukraine Kyiv National University Of Trade And Economics Dept. Of Software Engineering And Cyber Security Kyiv Ukraine National Technical University Of Ukraine Igor Sikorsky Kyiv Polytechnic Institute Dept. Of Department Of Computer Engineering Kyiv Ukraine

ISBN: (数字)9781665467902

ISBN: (纸本)9781665467902

The article is devoted to the development of means for recognition of the emotions of the speaker, based on the neural network analysis of fixed fragments of the voice signal. The possibility of improving recognition tools through the use of a convolutional neural network of the GoogLeNet type is shown. The expediency of training the network on the examples of the TESS database is determined. A procedure for representing a voice signal in the form of a square grayscale image has been developed. Based on the use of the specified database, the modification of the GoogLeNet network was carried out. The architecture and software implementation of the recognition module have been developed. With the help of computer experiments, it has been established that after 150 epochs of training on a fairly limited training sample, the modified GoogLeNet makes it possible to achieve an accuracy of recognition of the speaker's emotions of approximately 0.97 on test examples. The obtained accuracy is comparable to the accuracy of the best modern systems of this purpose and confirms the promise of using neural network models like GoogLeNet for emotion recognition based on voice signal analysis. The need for further research aimed at reducing the resource intensity of the neural network model is shown. © 2022 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

A 4-Channel 0.23$mm^{2}$ Voltage-to-Time Converter AFE with $3.7\mu V_{rms}$ Noise and $480nW$ Galvanic Impulse Uplink

A 4-Channel 0.23$mm^{2}$ Voltage-to-Time Converter AFE with ...

引用

Midwest Symposium on Circuits and systems (MWSCAS)

作者： Mehdi Bandali Morgan Riley Benjamin C. Johnson Dept. of Electrical and Computer Engineering Boise State University Boise ID USA Morgan Riley is with Biomedical Engineering Doctoral Program Boise State Universitvy Boise ID USA

ISBN: (数字)9798350387179

ISBN: (纸本)9798350387186

We present a 4-channel 15 kS/s Voltage-to-Time Converter (VTC) analog front-end (AFE) with a $0.49\mu W$ impulse-based galvanic uplink for a peripheral nerve interface. Multiple, low-noise, high-data-rate channels are needed to sense compound action potentials and measure their conduction velocity as they propagate down a peripheral nerve. To achieve high energy efficiency for these constraints, the AFE encodes and transmits data with time-domain charge-balanced impulses through an implantable galvanic link. Each channel consists of an integrator with charge-based sampling and amplification for rapid multiplexing. A shared VTC encodes the amplitude-domain outputs of each integrator into differential time-domain impulses. Since the timing can be synchronized with stimulation, this AFE achieves instant artifact recovery after rail-to-rail stimulation events. We designed this AFE in a 180nm CMOS process, and the simulation results show an SNDR of 60dB and noise of $3.7\mu Vrms$ . Thanks to the new galvanic uplink protocol, this front-end only consumes $11.28\mu W$ including wireless data transmission for four channels.

关键词： Wireless communication Wireless sensor networks Protocols Simulation Noise Data communication Velocity measurement

来源：评论

学校读者我要写书评

暂无评论

Self-Reported Learning Strategies and Preferences in Health Informatics

Self-Reported Learning Strategies and Preferences in Health ...

引用

34th Medical Informatics Europe Conference, MIE 2024

作者： Rohani, Narjes Gallagher, Michael Gal, Kobi Banas, Kasia Manataki, Areti Usher institute University of Edinburgh United Kingdom Moray House School of Education and Sport University of Edinburgh United Kingdom School of Informatics University of Edinburgh United Kingdom Dept. of Software and Information Systems Engineering Ben-Gurion University Israel School of Computer Science University of St Andrews United Kingdom

ISBN: (纸本)9781643685335

Despite the proliferation of educational programmes in Health Informatics (HI) worldwide, there is limited knowledge regarding students' preferences and learning strategies in HI courses. To address this gap, we conducted a study to gather and analyse data from three HI courses. Employing the Motivated Strategies for Learning Questionnaire (MSLQ) and theories of deep and surface learning, we designed a questionnaire to collect data. The analysis of students' responses indicates that machine learning emerges as one of the most interesting topics, while certain topics such as data wrangling of genomics data were more challenging for students. Students expressed a preference for sequential learning. They exhibited multimodal tendencies regarding the type of learning resources, with tendency to prefer learning resources that have more visual contents. In all three courses, learners reported using deep learning strategy rather than surface learning, yet they appear to struggle with employing organisation, elaboration, and peer learning tactics. This study provides valuable insights into HI education, offering recommendations for educators, learners, and researchers to enhance HI education. © 2024 The Authors.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Monitoring and Forecasting Quality Indicators of Predough Production in the Bakery Industry

Monitoring and Forecasting Quality Indicators of Predough Pr...

引用

Advanced Technology (KhPIWeek), IEEE KhPI Week on

作者： Nataliia Lutska Nataliia Zaiets Lidiia Vlasenko Andrii Zhyltsov dept. of Automation and Computer Technologies of Control Systems National University of Food Technologies Kyiv Ukraine dept. of Automation and Robotic Systems National University of Life and Environmental Sciences of Ukraine Kyiv Ukraine dept. of Software Engineering and Cyber Security State University of Trade and Economics Kyiv Ukraine dept. of electromagnetic systems The Institute of Electrodynamics of the National Academy of Sciences of Ukraine Kyiv Ukraine

ISBN: (数字)9798350384499

ISBN: (纸本)9798350384505

The work demonstrates the process of developing a machine learning model for a system for monitoring and controlling the quality of predough at a bakery. This system will provide continuous analysis of the predough parameters, such as temperature, humidity, lifting force and titranic acidity, which will ensure timely detection of deviations in the quality of the predough and avoid production problems. In addition, it will help automate the quality control process and ensure the stability of production processes. Analysis and forecasting of dough parameters will improve the quality of produced bread or other bakery products. Management based also on the predicted values of technological indicators of the predough will allow the enterprise to avoid unnecessary costs of materials and energy and increase economic efficiency. As part of the study, seven machine learning models were created and reviewed, including three linear and four varieties of binary decision trees. An analysis of the best model - a regression decision tree - was carried out, confirming its effectiveness and the validity of the resulting hierarchical structure, in particular, the prediction of important indicators of predough with a high degree of reliability, which indicates its importance in practical applications in production. The created model can be used to monitor and control product quality in real time, allowing operators to quickly identify and correct any deviations in process performance. Also, by analyzing changes in the variables of the predough production process, it is possible to identify precursors of possible production accidents or deviations in product quality, which will allow timely measures to be taken to avoid them.

关键词： Force Process control Production Machine learning Quality control Humidity Predictive models Stability analysis Monitoring Thermal stability

来源：评论

学校读者我要写书评

暂无评论

FPGA-based Low Power Acceleration of HARK Sound Source Localization

FPGA-based Low Power Acceleration of HARK Sound Source Local...

引用

IEEE Cool Chips

作者： Zirui Lin Katsutoshi Itoyama Kazuhiro Nakadai Hideharu Amano Dept. of Systems and Control Engineering School of Engineering Tokyo Institute of Technology Tokyo Japan Honda Research Institute Japan Co. Ltd. Saitama Japan Dept. of Information and Computer Science Keio University Kanagawa Japan

ISBN: (数字)9798350384147

ISBN: (纸本)9798350384154

This paper presents an FPGA-based low-power acceleration of sound source localization in HARK, open-source software for robot audition. Due to the massive matrix operations, sound source localization in HARK takes substantial processing time in edge computing devices. To balance processing time and low power consumption, two functions in sound source localization that include many matrix operations are targeted and migrated on an FPGA SoC board called M-KUBOS. Compared to CPU-based computing on ARM Cortex A53, our implementation achieved a 2.0× speedup and 1.7× lower energy consumption.

关键词： Location awareness program processors Power demand Parallel processing Energy efficiency Matrix decomposition Robots

来源：评论

学校读者我要写书评

暂无评论

Power and Rate Allocation for Energy-Efficient Rate-Splitting Multiple Access via Deep Q-Learning

Power and Rate Allocation for Energy-Efficient Rate-Splittin...

引用

IEEE Globecom Workshops

作者： Maria Diamanti Georgios Kapsalis Eirini Eleni Tsiropoulou Symeon Papavassiliou Institute of Communication and Computer Systems School of Electrical and Computer Engineering National Technical University of Athens Athens Greece Dept. of Electrical and Computer Engineering University of New Mexico Albuquerque NM USA

Rate-Splitting Multiple Access (RSMA) has recently emerged as an effective technique for increasing network capacity by smartly controlling the tradeoff between decoding and treating interference as noise. In this paper, aligned with the need for sustainable wireless networks, we study the energy-efficient power and rate allocation of the common and private messages in the downlink of a network where rate-splitting is adopted. The corresponding energy efficiency maximization problem is transformed into a multi-agent Deep Reinforcement Learning (DRL) problem, based on which each private stream transmitted in the downlink constitutes a different DRL agent. The formulated DRL problem is solved by using Deep Q-Learning (DQL) algorithm and training a single Deep Q-Network (DQN) from the cumulative experiences gained from the DRL agents and their exploration of the environment, i.e., the exploration of different private-message power allocations. Numerical results obtained via modeling and simulation verify the effectiveness of the proposed DQL algorithm, demonstrating that it concludes solutions that outperform existing approaches from the literature in the achieved energy efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Experiment of a Four-Fingered Robotic Hand for T-FLoW 4.0 humanoid robot

Design and Experiment of a Four-Fingered Robotic Hand for T-...

引用

International Electronics Symposium (IES)

作者： Kevin Ilham Apriandy Bima Sena Bayu Dewantara Raden Sanggar Dewanto Dadet Pramadihanto Catoer Ryando Dept. of Informatics and Computer Engineering Robotics and Intelligent Systems Center (RoISC) Politeknik Elektronika Negeri Surabaya (PENS) Dept. of Mechanical and Energy Engineering Robotics and Intelligent Systems Center (RoISC) Politeknik Elektronika Negeri Surabaya (PENS) Dept. of Electrical Engineering Politeknik Elektronika Negeri Surabaya (PENS)

In this research study, we present a novel design of a four-fingered robotic hand for T-FLoW 4.0 humanoid robot along with its experiments to validate its grasping performance. Our proposed robotic hand designed with four fingers and five Degree-of-Freedom (DoF), with a configuration of a thumb, index, middle, and ring fingers to remain within the criteria of an anthropomorphic type robot hand. Our hand is built with a modular design on each finger and its mechanism, allowing for easy assembly and achieving a compact hand result. Main controller Arduino Mega implement the system for grasping movement, and then PCA9685 PWM controller get the hand movement instructions from it and generates the required PWM signal for the servo motors. The process of manufacturing the hand involves 3D printing technology to produce hands with a realistic appearance, and use PLA filament material achieve lightweight, affordable, and easy-to-maintain outcomes. The grasping experimental results show that our proposed robotic hand could perform basic grasping movements on household objects. With the use of Cini’s taxonomy of grasp as the hand functionality standard, we achieved a success rate of 8 out of 14 tests conducted.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dual Inverter Parallel Consequent Pole PM-Assisted Two-Layer Sub-Harmonic Synchronous Machine

Dual Inverter Parallel Consequent Pole PM-Assisted Two-Layer...

引用

IEEE Conference on Electromagnetic Field Computation

作者： S M Sajjad Hossain Rafin Qasim Ali Osama A. Mohammed Dept. of Electrical and Computer Engineering Energy Systems Research Laboratory Florida International University Miami Florida USA Department of Electrical Engineering Sukkur IBA University Sukkur Pakistan

ISBN: (数字)9798350348958

ISBN: (纸本)9798350348965

A parallel consequent pole PM-assisted 2-layer subharmonic machine consisting of dual inverter topology is proposed here, which is designed to enhance torque generation and control compared to its predecessors. The stator of the sub-harmonic synchronous machine has two sets of 3-phase windings, and the dual inverter supplies current to them separately. Similarly, the rotor has two concentric windings, one for field excitation and the other for harmonic excitation. To validate the proposed model, an 8-pole, 48-slot, 2-inverter, 2-layer sub-harmonic machine is designed and simulated through 2-D finite element analysis. The results show a better torque and performance than the subharmonic and wound field synchronous machines.

关键词： Performance evaluation Torque Windings Stator windings Rotors Motors Harmonic analysis

来源：评论

学校读者我要写书评

暂无评论

Integration of a multi-rate electron density profile observer in the plasma control system of TCV 49

Integration of a multi-rate electron density profile observe...

引用

49th EPS Conference on Plasma Physics, EPS 2023

作者： Pastore, F. Felici, F. Sauter, O. Bosman, T.O.S.J. Galperti, C. Vincent, B. Pau, A. Poels, Y. Ravensbergen, T. Vu, N.M.T. Lausanne Switzerland DIFFER - Dutch Institute for Fundamental Energy Research Energy Systems and Control Group Eindhoven Netherlands Eindhoven University of Technology Dept. of Mechanical Engineering Control Systems Technology Group Eindhoven Netherlands Eindhoven University of Technology Dept. of Mathematics and Computer Science Data Mining Group Eindhoven Netherlands ITER Organization Route de Vinon-sur-Verdon St. Paul Lez Durance13067 Cedex France

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：