检索结果-内蒙古大学图书馆

9th International Conference on Control, Decision and Information Technologies, CoDIT 2023

作者： Gómez, Juan Carlos Sad, Gonzalo Daniel Fceia Universidad Nacional de Rosario Cifasis Lab. for Systems Dynamics and Signal Processing Rosario Argentina

ISBN: (纸本)9798350311402

Recursive identification algorithms for the parameter estimation of linear systems from multilevel quantized outputs are introduced in this paper. The proposed algorithms are proved to be optimal in the sense that they minimize the a posteriori parameter estimation error covariance matrix. Numerical simulations are carried out to illustrate their performance for different quantization steps and signal-to-Noise Ratios, as well as their capability to track time varying parameters. © 2023 IEEE.

关键词： Linear systems

来源：评论

学校读者我要写书评

暂无评论

Optimal Parameter Estimation Algorithms from Quantized Outputs

Optimal Parameter Estimation Algorithms from Quantized Outpu...

引用

International Conference on Control, Decision and Information Technologies (CoDIT)

作者： Juan Carlos Gómez Gonzalo Daniel Sad Lab. for Systems Dynamics and Signal Processing FCEIA Universidad Nacional de Rosario and CIFASIS Rosario Argentina

关键词：

来源：评论

学校读者我要写书评

暂无评论

Position Control of Maneuverable Underwater Vehicle Based on Model Identification 5

Position Control of Maneuverable Underwater Vehicle Based on...

引用

5th International Conference on Control systems, Mathematical Modeling, Automation and Energy Efficiency, SUMMA 2023

作者： Alexandrov, Vadim Shatov, Dmitrii Abramenkov, Alexander Abdulov, Alexander V.A. Trapeznikov Institute of Control Sciences of RAS Ya.Z. Tsypkin Lab. of Adaptive and Robust Systems Moscow Russia V.A. Trapeznikov Institute of Control Sciences of RAS Lab. of Automated Queuing Systems and Signal Processing Moscow Russia

ISBN: (纸本)9798350309126

The position control for the experimental maneuverable remotely operated underwater vehicle is considered. The problem is to hold the position or to move a short distance without the attitude changing. So, velocity limitations and attitude control are not considered in the paper. Separate control loops for the body frame axes are designed, while the Eath frame position is transformed into the body frame coordinate system. For each axis, the translational dynamics linearized model is experimentally identified as a second-order transfer function. The PID controllers with setpoint weighting are designed via the pole placement optimization procedure using the identified models. Experimental tests of the obtained controllers showed acceptable performance. © 2023 IEEE.

关键词： Three term control systems

来源：评论

学校读者我要写书评

暂无评论

Development of Multi-Channel DXA Detector for Cone Beam Data Acquisition

Development of Multi-Channel DXA Detector for Cone Beam Data...

引用

IEEE Symposium on Nuclear Science (NSS/MIC)

作者： S. Lee J. Jung Y. Choi J. H. Jung S. Jang Department of Electronic Engineering Intelligent Signal Processing & Systems Lab.(ISPS) Sogang University Seoul Republic of Korea

ISBN: (数字)9798350388152

ISBN: (纸本)9798350388169

Linear-type fan beam detectors have been commonly used in dual-energy X-ray absorptiometry (DXA), which requires long scan time and high radiation exposure when imaging a large area. These problems could be resolved by employing array-type cone beam detectors that could provide a wide field-of-view with a single exposure. The purpose of this study was to develop an array-type multi-channel cone beam DXA detector consisting of SiPM based scintillation detector, analog signal processing circuit and FPGA based TOT. The detector was composed of an 8 × 8 array of 1 × 1 × 2 mm 3 LYSO coupled with an 8 × 8 array of 1 × 1 mm 2 SiPM. Analog signal processing circuit consisted of a resistor-based symmetric charge division readout to reduce the 64 signals of SiPMs to 16 and a diode-based time-over-threshold (ToT) to measure the time and energy information. A 16-ch tapped delay-line TDC was implemented in FPGA to measure the rising edge and the width of the ToT output. To evaluate the energy resolution of the cone beam DXA detector, the energy spectra were acquired using Am-241 and Co-57 point sources. The 64 energy spectra were also acquired using X-ray generator with 83 kVp and 0.2 mA and a Ce filter with K-edge absorption at 40.4 keV. The count variations of the low- and high-energy regions were measured for 5-minutes intervals over 30 minutes to evaluate the uniformity and stability of the detector. The energy resolutions were 25.6% and 18.1% at 60 keV and 122 keV, respectively. Two energy peaks in low- and high-energy regions were clearly discriminated in the 64 energy spectra. Average count variations of the low and high energy regions were 2.4% and 2.3%, respectively. These results indicated that the proposed cone beam DXA detector had sufficient energy resolution, uniformity and stability to discriminate low-energy X-rays and could be useful for cone beam DXA detector. For further study, expansion to 256-ch consisting of 4 modules of 64-ch detector is being studie

关键词： Semiconductor device measurement Particle beams Array signal processing Energy resolution Detectors Time measurement Circuit stability

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning using Musical/Non-Musical Mixtures for Multi-Instrument Recognition 15

Transfer Learning using Musical/Non-Musical Mixtures for Mul...

引用

15th ITG Conference on Speech Communication

作者： Bradl, Hannes Huber, Markus Pernkopf, Franz Joanneum Research Forschungsgesellschaft MbH Austria sonible GmbH Graz Austria Christian Doppler Laboratory for Dependable Intelligent Systems in Harsh Environments Signal Processing and Speech Communication Lab. Graz University of Technology Austria

ISBN: (纸本)9783800761654

Datasets for most music information retrieval (MIR) tasks tend to be relatively small. However, in deep learning, insufficient training data often leads to poor performance. Typically, this problem is approached by transfer learning (TL) and data augmentation. In this work, we compare various of these methods for the task of multi-instrument recognition. A convolutional neural network (CNN) is able to identify eight instrument families and seven specific instruments from polyphonic music recordings. Training is conducted in two phases: After pre-training with a music tagging dataset, the CNN is retrained using multi-track data. Experimenting with different TL methods suggests that training the final fully-connected layers from scratch while fine-tuning the convolutional backbone yields the best performance. Two different mixing strategies – musical and non-musical mixing – are investigated. It turns out that a blend of both mixing strategies works best for multi-instrument recognition. © VDE VERLAG GMBH Berlin Offenbach.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Epilepsy Detection Grand Challenge 48

Epilepsy Detection Grand Challenge

引用

48th IEEE International Conference on Acoustics, Speech and signal processing, ICASSP 2023

作者： Chatzichristos, Christos Bhagubai, Miguel Van Paesschen, Wim De Vos, Maarten Un. Hospital Leuven Lab. for Epilepsy Research KU Leuven & Department of Neurology Belgium Signal Processing and Data Analytics KU Leuven STADIUS Center for Dynamical Systems Department of Electrical Engineering Leuven Belgium KU Leuven Department Development and Regeneration Leuven Belgium

ISBN: (纸本)9781728163277

In this paper, we describe the epilepsy detection grand challenge, in association with ICASSP 2023. The challenge was centered on seizure detection using wearable behind-the-ear EEG. Two separate tasks were set for the participants: 1) obtain the best overall performance in seizure detection;2) systematically engineer the data in a data-centric task to optimize a given AI model for seizure detection. © 2023 IEEE.

关键词： Neurology

来源：评论

学校读者我要写书评

暂无评论

Position Control of Maneuverable Underwater Vehicle Based on Model Identification

Position Control of Maneuverable Underwater Vehicle Based on...

引用

International Conference on Control systems, Mathematical Modelling, Automation and Energy Efficiency (SUMMA)

作者： Vadim Alexandrov Dmitrii Shatov Alexander Abramenkov Alexander Abdulov Ya.Z. Tsypkin Lab. of Adaptive and Robust Systems V.A. Trapeznikov Institute of Control Sciences of RAS Moscow Russia Lab. of Automated Queuing Systems and Signal Processing V.A. Trapeznikov Institute of Control Sciences of RAS Moscow Russia

关键词：

来源：评论

学校读者我要写书评

暂无评论

Epilepsy Detection Grand Challenge

Epilepsy Detection Grand Challenge

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Christos Chatzichristos Miguel Bhagubai Wim Van Paesschen Maarten De Vos Department of Electrical Engineering STADIUS Center for Dynamical Systems Signal Processing and Data Analytics KU Leuven Leuven Belgium KU Leuven & Department of Neurology Lab. for Epilepsy Research Un. Hospital Leuven Belgium Department Development and Regeneration KU Leuven Leuven Belgium

ISBN: (数字)9781728163277

ISBN: (纸本)9781728163284

In this paper, we describe the epilepsy detection grand challenge, in association with ICASSP 2023. The challenge was centered on seizure detection using wearable behind-the-ear EEG. Two separate tasks were set for the participants: 1) obtain the best overall performance in seizure detection; 2) systematically engineer the data in a data-centric task to optimize a given AI model for seizure detection.

关键词： Epilepsy signal processing Brain modeling Electroencephalography Data models Task analysis Speech processing

来源：评论

学校读者我要写书评

暂无评论

Connecting Disconnected Agents in Multiagent systems via Federated Control

Connecting Disconnected Agents in Multiagent Systems via Fed...

引用

European Control Conference (ECC)

作者： Rongrong Qian Zhisheng Duan Yuan Qi Tao Peng Wenbo Wang School of Artificial Intelligence Beijing University of Posts and Telecommunications (BUPT) Beijing China State Key Laboratory for Turbulence and Complex Systems College of Engineering Peking University Beijing China School of Electronic Engineering Beijing University of Posts and Telecommunications (BUPT) Beijing China Wireless Signal Processing and Network Lab (Key Lab. of Universal Wireless Communication Ministry of Education) Beijing University of Posts and Telecommunications (BUPT) Beijing China

ISBN: (数字)9783907144107

ISBN: (纸本)9798331540920

This study develops a control technique, called federated control, to connect disconnected agents in multiagent systems aided by control stations. Specifically, we first use a federated architecture to model multiagent systems with control stations. Based on this architecture, a federated-control procedure is proposed for the task of connecting disconnected agents, together with an initialization procedure. Then, how the federated-control procedure connects disconnected agents by incorporating simple global coordination (i.e., global averaging) is analyzed. We derive the close-form expression of the time sufficient to connect disconnected agents, which possesses interesting properties including early computability and delay independence. The convergence of the formation of multiagent systems and the velocities of all agents can also be proved.

关键词： Robot kinematics Oceans Computer architecture Control systems Space-air-ground integrated networks Path planning Delays

来源：评论

学校读者我要写书评

暂无评论

A review of uncertainty quantification in deep learning: Techniques, applications and challenges

arXiv

引用

arXiv 2020年

作者： Abdar, Moloud Pourpanah, Farhad Hussain, Sadiq Rezazadegan, Dana Liu, Li Ghavamzadeh, Mohammad Fieguth, Paul Cao, Xiaochun Khosravi, Abbas Rajendra Acharya, U. Makarenkov, Vladimir Nahavandi, Saeid Deakin University Australia College of Mathematics and Statistics Guangdong Key Lab. of Intelligent Information Processing Shenzhen University Shenzhen518060 China Dibrugarh University Dibrugarh India Department of Computer Science and Software Engineering Swinburne University of Technology Melbourne Australia Center for Machine Vision and Signal Analysis University of Oulu Oulu Finland Google research United States Department of Systems Design Engineering University of Waterloo Waterloo Canada State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing China Department of Electronics and Computer Engineering Ngee Ann Polytechnic Clementi Singapore Department of Computer Science University of Quebec in Montreal MontrealQC Canada

—Uncertainty quantification (UQ) plays a pivotal role in the reduction of uncertainties during both optimization and decision making, applied to solve a variety of real-world applications in science and engineering. Bayesian approximation and ensemble learning techniques are two of the most widely-used UQ methods in the literature. In this regard, researchers have proposed different UQ methods and examined their performance in a variety of applications such as computer vision (e.g., self-driving cars and object detection), image processing (e.g., image restoration), medical image analysis (e.g., medical image classification and segmentation), natural language processing (e.g., text classification, social media texts and recidivism risk-scoring), bioinformatics, etc. This study reviews recent advances in UQ methods used in deep learning, investigates the application of these methods in reinforcement learning, and highlight the fundamental research challenges and directions associated with the UQ field. Copyright © 2020, The Authors. All rights reserved.

关键词： Image segmentation

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：