检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Guinet, Gauthier Amin, Saurabh Jaillet, Patrick AWS AI Labs United States MIT United States Dept. of Civil and Environmental Engineering Laboratory for Information and Decision Systems United States Dept. of Electrical Engineering and Computer Science & Laboratory for Information and Decision Systems United States

In this paper, we study both multi-armed and contextual bandit problems in censored environments. Our goal is to estimate the performance loss due to censorship in the context of classical algorithms designed for uncensored environments. Our main contributions include the introduction of a broad class of censorship models and their analysis in terms of the effective dimension of the problem – a natural measure of its underlying statistical complexity and main driver of the regret bound. In particular, the effective dimension allows us to maintain the structure of the original problem at first order, while embedding it in a bigger space, and thus naturally leads to results analogous to uncensored settings. Our analysis involves a continuous generalization of the Elliptical Potential Inequality, which we believe is of independent interest. We also discover an interesting property of decision-making under censorship: a transient phase during which initial misspecification of censorship is self-corrected at an extra cost;followed by a stationary phase that reflects the inherent slowdown of learning governed by the effective dimension. Our results are useful for applications of sequential decision-making models where the feedback received depends on strategic uncertainty (e.g., agents’ willingness to follow a recommendation) and/or random uncertainty (e.g., loss or delay in arrival of information). © 2023, CC BY.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Computationally Efficient Predictive Control Based on ANN State-Space Models

Computationally Efficient Predictive Control Based on ANN St...

引用

IEEE Conference on Decision and Control

作者： Jan H. Hoekstra Bence Cseppento Gerben I. Beintema Maarten Schoukens Zsolt Kollár Roland Tóth Dept. of Electrical Engineering at the Eindhoven Control Systems group University of Technology The Netherlands Dept. of Measurement and Information Systems Budapest University of Technology and Economics Hungary Institute for Computer Science and Control Budapest Hungary

Artificial neural networks (ANN) have been shown to be flexible and effective function estimators for the identification of nonlinear state-space models. However, if the resulting models are used directly for nonlinear model predictive control (NMPC), the resulting nonlinear optimization problem is often overly complex due to the size of the network, requires the use of high-order observers to track the states of the ANN model, and the overall control scheme does not exploit the available autograd tools for these models. In this paper, we propose an efficient approach to auto-convert ANN statespace models to linear parameter-varying (LPV) form and solve predictive control problems by successive solutions of linear model predictive problems, corresponding to quadratic programs (QPs). Furthermore, we show how existing deep-learning methods, such as SUBNET that uses a state encoder, enable efficient implementation of MPCs on identified ANN models. Performance of the proposed approach is demonstrated by a simulation study on an unbalanced disc system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intelligent Constellation Generation based on Autoencoder Communication System

Intelligent Constellation Generation based on Autoencoder Co...

引用

computer Vision and Machine Intelligence (CVMI), International Conference on

作者： Kaisei Matsumoto Takao Toma Shiho Oshiro Tomohisa Wada Computer Science and Intelligent Systems Program University of the Ryukyus Okinawa Japan Magna Design Net Inc Okinawa Japan Information Technology Center University of the Ryukyus Okinawa Japan Dept. of Engineering Area of Computer Science and Intelligent Systems University of the Ryukyus Okinawa Japan

This paper discusses intelligent constellation generation based on autoencoder communication system. In previous studies, the amplitude was set to fluctuate between r=0.0 and 1.0. However, when checking the generated constellation, distortion was confirmed instead of the conventional symbol arrangement. Therefore, in this paper, it compares the case where the amplitude is constant, the case where the average amplitude within a Minibatch is 1, and the case where the average amplitude is 1 for Interval time. The communication standard used in this research is IEEE 802.11a, assuming wireless Local Area Network (LAN) specifications. The IEEE 802.11a standard has an Fast Fourier Transform (FFT) length of 64, a subcarrier number of 52, and Quadrature Phase Shift Keying (QPSK) and 16 Quadrature Amplitude Modulation (QAM), modulation methods. A guard interval of 800 ns is added and the symbol length is 4000 ns. First, a simulation was performed under the condition that the amplitude was kept constant. QPSK with 4 symbols, constant amplitude model is rounded more than previous research result. 16QAM with 16 symbols is arranged regularly like lined up on a line. Second, the simulation was performed under the condition that the average amplitude within the minibatch was set to 1. QPSK with 4 symbols, appears to rotate clockwise. 16QAM with 16 symbols has a more uniform symbol placement than previous research result. Third, a simulation was performed under the condition that the average amplitude within Interval time was set to 1. QPSK with 4 symbols, is the closest to square among QPSK output results so far. The direction is slightly tilted, but if it can be rotated a little more, it may be possible to reproduce the same symbol arrangement as before. 16QAM with 16 symbols, the symbol arrangement is biased as a whole. However, it can be seen that are arranged in line on the line, perhaps due to regularity. As future work, in addition to the conditions set this time, it will exa

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of a visualization system for a virtual laboratory for training personnel of industrial enterprises

Development of a visualization system for a virtual laborato...

引用

2021 International Conference on Automatics and Energy, ICAE 2021

作者： Arkhipov, A. Prokudina, N. Patutin, K. Dept. of Computer-Integrated Systems in Engineering Tambov State Technical University Tambov Russia Dept. of Automated Systems of Decision-Making Support Tambov State Technical University Tambov Russia

An urgent task in the training of personnel of industrial enterprises is the development of the required amount of practical skills. In the context of a pandemic, restrictive measures, as well as the high cost and danger of conducting training on real equipment, virtual laboratories are becoming one of the most promising training tools. The virtual laboratory includes a visualization system (many 3D objects, animations and effects), as well as software components, databases, modules for logging and assessing the quality of exercise performance. Within the framework of this work, the task of developing a visualization system for virtual laboratories is considered. A structural diagram of the visualization system is proposed, illustrating all the necessary elements for creating virtual stands, an implementation algorithm is drawn up. The software implementation is described on the example of a laboratory setup for performing the Reynolds experiments. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Personnel training

来源：评论

学校读者我要写书评

暂无评论

DDD: A Perceptually Superior Low-Response-Time DNN-Based Declipper

DDD: A Perceptually Superior Low-Response-Time DNN-Based Dec...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Jayeon Yi Junghyun Koo Kyogu Lee Dept. of Electrical Engineering and Computer Science University of Michigan Dept. of Intelligence and Information Seoul National University Interdisciplinary Program in Artificial Intelligence Seoul National University Artificial Intelligence Institute Seoul National University

Clipping is a common nonlinear distortion that occurs whenever the input or output of an audio system exceeds the supported range. This phenomenon undermines not only the perception of speech quality but also downstream processes utilizing the disrupted signal. Therefore, a real-time-capable, robust, and low-response-time method for speech declipping (SD) is desired. In this work, we introduce DDD (Demucs-Discriminator-Declipper), a real-time-capable speech-declipping deep neural network (DNN) that requires less response time by design. We first observe that a previously untested real-time-capable DNN model, Demucs, exhibits a reasonable declipping performance. Then we utilize adversarial learning objectives to increase the perceptual quality of output speech without additional inference overhead. Subjective evaluations on harshly clipped speech shows that DDD outperforms the baselines by a wide margin in terms of speech quality. We perform detailed waveform and spectral analyses to gain an insight into the output behavior of DDD in comparison to the baselines. Finally, our streaming simulations also show that DDD is capable of sub-decisecond mean response times, outperforming the state-of-the-art DNN approach by a factor of six.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Temperature Alteration Using PID Controller for Energy Harvesting for E-Airplane Application (Case Study Experimental Investigation)

Temperature Alteration Using PID Controller for Energy Harve...

引用

2022 IEEE International Conference on Electrical, computer, and Energy Technologies, ICECET 2022

作者： Grant, Charles El-Shahat, Adel Mirza, Zain Georgia Southern University Dept. of Electrical and Computer Eng StatesboroGA30460 United States Purdue University West Lafayette Energy Program School of Engineering Technology IN47906 United States

ISBN: (数字)9781665470872

ISBN: (纸本)9781665470872

The proportional-integral-derivative (PID) controller is a popular control loop feedback mechanism that allows users to efficiently regulate their system outputs. As demonstrated in this project, one of the main applications of PID control is temperature regulation. This project describes the process of setting up the PID parameters of the controller with a trial-and-error tuning method that aims to implement better control system responses. MATLAB/Simulink is the software environment used to replicate the PID temperature controller, and then a real PID controller is tuned with an Arduino microcontroller. The temperature is regulated by a thermocouple, which employs the Seebeck effect to provide power based on a temperature gradient. Simulated and experimental results are compared to observe how a closed-loop PID system should behave. © 2022 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

Leveraging Artificial Intelligence for Enhanced Data Generation in Addressing Imbalance in Binary Classification System

Leveraging Artificial Intelligence for Enhanced Data Generat...

引用

Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), IEEE Conference on

作者： Srijita Bandopadhyay Srimonti Dutta Imran Haider Bhavaraju Anuraag Jerry Zhu Saad Ahmed Bazaz Dept. of Electronics and Communication Engineering University of Engg. & Management Kolkata India School of Agro and Rural Technology Indian Institute of Technology Guwahati Guwahati India Dept. of Industrial and Systems Engineering Indian Institute of Technology Kharagpur Kharagpur India Dept. of Electronics and Communication Engineering Vellore Institute of Technology Vellore India Faculty of Mathematics University of Waterloo Ontario Canada Dept. of Computer Science National University of Computer & Emerging Sciences Islamabad Pakistan

This paper delves into the challenges of binary classification using imbalanced datasets, particularly when instances of interest are infrequent. It explores a comprehensive approach that integrates Synthetic Minority Over-sampling Technique (SMOTE), Generative Adversarial Networks (GANs), and Variational Autoencoders (VAEs) to enhance classification outcomes. Traditional classification models tend to favor the majority class, while the impact of imbalanced misclassification costs is often overlooked. The integration of SMOTE, GANs, and VAEs in binary classification, or SMOTE-GAN-VAE, addresses these challenges by generating synthetic instances, refining data representations, and capturing latent features. To evaluate the effectiveness of various data generation methods, a credit card fraud dataset is used. The performance metrics considered include F0.5-score, F1-score, and F2-score, which account for both precision and recall. The results indicate that SMOTE-GAN-VAE outperforms individual methods, such as SMOTE, GANs, and VAEs, demonstrating its potential to enhance data representation and classification accuracy, and outperformed the β- VAE filtered approach employed in previous literature.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dental Imaging Using a Higher Signal-to-Noise Ratio Optical Coherence Tomography System

Dental Imaging Using a Higher Signal-to-Noise Ratio Optical ...

引用

Electrical, computer and Energy Technologies (ICECET), International Conference on

作者： Akeem. A. Azeez Biniyam Mezgebo Rodrigo França Sherif S. Sherif Biomedical Engineering Graduate Program University of Manitoba Winnipeg Canada Dept. of Electrical andComputer Engineering University of Manitoba Winnipeg Canada Dept. of Restorative Dentistry University of Manitoba Winnipeg Canada Dept. of Electrical and Computer Engineering University of Manitoba Winnipeg Canada

This paper presents an optical coherence tomography (OCT) system in conjunction with a novel image reconstruction technique employed for in vitro imaging of human teeth. The primary goal is to enhance the signal-to-noise ratio (SNR) in the obtained images. The study entails a comparative analysis between the conventional Fast Fourier Transform (FFT) OCT image reconstruction method and a newly introduced scaled nonuniform discrete Fourier transform (NDFT) approach. The findings reveal that the NDFT method consistently delivers superior results in terms of peak signal-to-noise ratio (PSNR) and overall image quality, even when dealing with redundant and nonuniform frequency domain samples. In light of these results, this paper concludes that integrating NDFT into OCT procedures has the potential to significantly enhance the quality of image reconstructions, thereby fostering its broader application in the field of dental imaging.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Meaning of the Clusters on Dimensionality Reduction by Word Clustering 12

Meaning of the Clusters on Dimensionality Reduction by Word ...

引用

12th International Congress on Advanced Applied Informatics, IIAI-AAI 2022

作者： Deguchi, Toshinori Seo, Sinsuke Ishii, Naohiro Dept. of Electrical and Computer Engineering Gifu College Gifu Japan Interdisciplinary Technology Development Gifu College Gifu Japan Information Systems Architecture Advanced Institute of Industrial Technology Tokyo Japan

ISBN: (数字)9781665497558

ISBN: (纸本)9781665497558

In text mining, Latent Semantic Analysis (LSA) is the popular method to reduce the dimension of document vectors. Since LSA produces a set of topics by statistical information, the meaning of each topic is not *** proposed a method to reduce the dimension by clustering the words in the documents. This method produces a set of clusters of words instead of topics. Using Word2vec to vectorize the words, the mean vector of the cluster is calculated, which shows the meaning of the *** this paper, we show the dimensionality reduction and the meaning of the generated clusters by word cloud, on document classification problem with a subset of BBC Dataset. © 2022 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Neuromorphic Camera Assisted High-Flow Imaging Cytometry for Particle Classification

Neuromorphic Camera Assisted High-Flow Imaging Cytometry for...

引用

Conference on Lasers and Electro-Optics Europe (CLEO EUROPE)

作者： Ioannis Tsilikas Stavros Deligiannidis Aris Tsirigotis Georgios N. Tsigaridas Adonis Bogris Charis Mesaritakis Dept. Physics National Technical University of Athens Zografou Athens Greece Dept. Information and Communication Systems Engineering University of the Aegean Karlovasi Samos Greece Dept. Informatics and Computer Engineering University of West Attica Egaleo Greece

ISBN: (纸本)9798350345995

In this work we combine a high flow cytometry experimental setup and a 10Kframe/sec capable neuromorphic event-based camera, followed by lightweight machine learning schemes, thus allowing the simultaneous imaging and real-time classification of test particles, moving at a speed of 0.8m/sec with an accuracy of 97.6%. The key advantage of the utilized microscopy system, is the use of an event-based camera, generating spiking events, triggered by pixel's contrast changes. This bio-inspired operation, contrary to conventional CMOS cameras [1], alleviates bandwidth constraints and can significantly boost frame-rate capabilities, thus capturing high speed events. Following this paradigm, medical imaging modalities, where the detection and analysis of fast-moving particles is a necessity, such as high-flow cytometry, can greatly proliferate from the proposed approach.

关键词： Biomedical imaging Cameras CMOS cameras Cytometry Machine learning Real time imaging

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：