检索结果-内蒙古大学图书馆

On Model and Data Scaling for Skeleton-based Self-Supervised Gait Recognition

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Cosma, Adrian Cǎtrunǎ, Andy Rǎdoi, Emilian University Politehnica of Bucharest Faculty of Automatic Control and Computer Science Romania

Gait recognition from video streams is a challenging problem in computer vision biometrics due to the subtle differences between gaits and numerous confounding factors. Recent advancements in self-supervised pretraining have led to the development of robust gait recognition models that are invariant to walking covariates. While neural scaling laws have transformed model development in other domains by linking performance to data, model size, and compute, their applicability to gait remains unexplored. In this work, we conduct the first empirical study scaling on skeleton-based self-supervised gait recognition to quantify the effect of data quantity, model size and compute on downstream gait recognition performance. We pretrain multiple variants of GaitPT — a transformer-based architecture — on a dataset of 2.7 million walking sequences collected in the wild. We evaluate zero-shot performance across four benchmark datasets to derive scaling laws for data, model size, and compute. Our findings demonstrate predictable power-law improvements in performance with increased scale and confirm that data and compute scaling significantly influence downstream accuracy. We further isolate architectural contributions by comparing GaitPT with GaitFormer under controlled compute budgets. These results provide practical insights into resource allocation and performance estimation for real-world gait recognition systems. © 2025, CC BY-NC-ND.

关键词： Budget control

Noise Reduction in Industry Based on Virtual Instrumentation

学校读者我要写书评

暂无评论

computers, Materials & Continua 2021年第10期69卷 1073-1096页

作者： Radek Martinek Rene Jaros Jan Baros Lukas Danys Aleksandra Kawala-Sterniuk Jan Nedoma Zdenek Machacek Jiri Koziorek Faculty of Electrical Engineering and Computer Science Department of Cybernetics and Biomedical EngineeringVSB–Technical University of Ostrava70800Ostrava-PorubaCzechia Faculty of Electrical Engineering Automatic Control and InformaticsOpole University of TechnologyOpolePoland Faculty of Electrical Engineering and Computer Science Department of TelecommunicationsVSB–Technical University of Ostrava70800Ostrava-PorubaCzechia

This paper discusses the reduction of background noise in an industrial environment to extend *** the Industry 4.0 era,the mass development of voice control(speech recognition)in various industrial applications is possible,especially as related to augmented reality(such as hands-free control via voice commands).As Industry 4.0 relies heavily on radiofrequency technologies,some brief insight into this problem is provided,including the Internet of things(IoT)and 5G *** study was carried out in cooperation with the industrial partner Brose CZ spol.s.r.o.,where sound recordings were made to produce a *** experimental environment comprised three workplaces with background noise above 100 dB,consisting of a laser/magnetic welder and a press.A virtual device was developed from a given dataset in order to test selected commands from a commercial speech recognizer from *** tested a hybrid algorithm for noise reduction and its impact on voice command recognition *** virtual devices,the study was carried out on large speakers with 20 participants(10 men and 10 women).The experiments included a large number of repetitions(100 times for each command under different noise conditions).Statistical results confirmed the efficiency of the tested *** welding environment efficiency was 27%before applied filtering,76%using the least mean square(LMS)algorithm,and 79%using LMS+independent component analysis(ICA).Magnetic welding environment efficiency was 24%before applied filtering,70%with LMS,and 75%with LMS+*** workplace environment efficiency showed no success before applied filtering,was 52%with LMS,and was 54%with LMS+ICA.

关键词： 5G hybrid algorithms signal processing speech recognition

Improvement of Random Undersampling to Avoid Excessive Removal of Points from a Given Area of the Majority Class 21st

学校读者我要写书评

暂无评论

Improvement of Random Undersampling to Avoid Excessive Remov...

21st International Conference on Computational science, ICCS 2021

作者： Bach, Malgorzata Werner, Aleksandra Department of Applied Informatics Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland

ISBN: (纸本)9783030779665

In this paper we focus on class imbalance issue which often leads to sub-optimal performance of classifiers. Despite many attempts to solve this problem, there is still a need to look for better ones, which can overcome the limitations of known methods. For this reason we developed a new algorithm that in contrast to traditional random undersampling removes maximum k nearest neighbors of the samples which belong to the majority class. In such a way, there has been achieved not only the effect of reduction in size of the majority set but also the excessive removal of too many points from the given area has been successfully prevented. The conducted experiments are provided for eighteen imbalanced datasets, and confirm the usefulness of the proposed method to improve the results of the classification task, as compared to other undersampling methods. Non-parametric statistical tests show that these differences are usually statistically significant. © 2021, Springer Nature Switzerland AG.

关键词： Classification (of information)

Spectra based on Bohl exponents and Bohl dichotomy for nonautonomous difference equations

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Czornik, Adam Kitzing, Konrad Siegmund, Stefan Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland Institute of Analysis Faculty of Mathematics TU Dresden Germany

For nonautonomous linear difference equations with bounded coefficients on N which have a bounded inverse, we introduce two different notions of spectra and discuss their relation to the well-known exponential dichotomy spectrum. The first new spectral notion is called Bohl spectrum and is based on an extended notion of the concept of Bohl exponents. The second new spectral notion is called Bohl dichotomy spectrum and is based on a relaxed version of exponential dichotomy called Bohl dichotomy. We prove spectral theorems and show that the Bohl dichotomy spectrum is the closure of the Bohl spectrum and also a subset of the exponential dichotomy spectrum. We discuss the spectra of upper triangular systems and how they relate to the spectra of their diagonal entries. An example illustrates the subtle differences between the different notions of *** Codes 39A30 Copyright © 2023, The Authors. All rights reserved.

关键词： Difference equations

The new notion of Bohl dichotomy for nonautonomous difference equations and its relation to exponential dichotomy

学校读者我要写书评

暂无评论

arXiv 2023年

In [7] the concept of Bohl dichotomy is introduced which is a notion of hyperbolicity for linear nonautonomous difference equations that is weaker than the classical concept of exponential dichotomy. In the class of systems with bounded invertible coefficient matrices which have bounded inverses, we study the relation between the set BD of systems with Bohl dichotomy and the set ED of systems with exponential dichotomy. It can be easily seen from the definition of Bohl dichotomy that ED ⊆ BD. Using a counterexample we show that the closure of ED is not contained in BD. The main result of this paper is the characterization int BD = ED. The proof uses upper triangular normal forms of systems which are dynamically equivalent and utilizes a diagonal argument to choose subsequences of perturbations each of which is constructed with the Millionshikov Rotation Method. An Appendix describes the Millionshikov Rotation Method in the context of nonautonomous difference equations as a universal *** Codes 37B55, 34D09 Copyright © 2023, The Authors. All rights reserved.

关键词： Difference equations

Using the LQI2R control Method on the Adaptive Cruise control System for a Platoon of Vehicles 7

学校读者我要写书评

暂无评论

Using the LQI2R Control Method on the Adaptive Cruise Contro...

7th International Scientific Conference on Applying New Technology in Green Buildings, ATiGB 2022

作者： Luu, Duc Lich Pham, Huu Truyen Pham, Quoc Thai Lupu, Ciprian Van Nguyen, Thien Vinh University of Technology Education Nghe An Vinh City Viet Nam Fac. of Transp. Mechanical Engineering the University of Danang-University of Science and Technology Danang Viet Nam Faculty of Automatic Control and Computers University Politehnica of Bucharest Bucharest Romania Academy of Science and Technology Hanoi Viet Nam

ISBN: (数字)9781665472852

ISBN: (纸本)9781665472852

Autonomous vehicles refer to vehicles whose operations and actuations are directed towards fully controlled. However, we need a long transition period where drivers of vehicles with different levels of partial automation will be responsible for the driving function. The Adaptive Cruise control (ACC) is one of the key subsystems of Advanced Driver Assistance Systems that have attracted considerable research and development efforts due to their multifaceted advantages such as increasing the urban arterial capacity, improve traffic safety with shorter inter-vehicle spacing between vehicles [1], [2]. This study proposes a Linear Quadratic Integral Regulator with double integrator (LQI2R) for ACC technology in a platoon by using radars. An important criterion in ACC controller design is string stability which is analyzed by using a frequency-domain approach and Nyquist diagram within considering the different values of the constant headway time. The main purpose of platoon control is to keep the desired inter-vehicle distance while guaranteeing string stability requirements. The numerical simulations are carried out to validate the effectiveness of our results. © 2022 IEEE.

关键词： Adaptive cruise control

Ranking of attributes-comparative study based on data from stylometric domain 26

学校读者我要写书评

暂无评论

Ranking of attributes-comparative study based on data from s...

26th International Conference on Knowledge-Based and Intelligent Information and Engineering Systems, KES 2022

作者： Zielosko, Beata Stanczyk, Urszula Zabinski, Krzysztof Institute of Computer Science University of Silesia in Katowice B edzinska 39 Sosnowiec41-200 Poland Department of Graphics Computer Vision and Digital Systems Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Akademicka 2A Gliwice44-100 Poland

The area of feature selection methods constantly expands along with the development of artificial intelligence domain, and has great impact on almost every field, whenever data is processed and explored. The paper presents research where a ranking method was proposed, inspired by an approach which comes from an algorithm for induction of decision rules. The ranking procedure was based on calculation of standard deviation for attributes, taking into account assigned class labels. This method was compared with another ranking mechanism, a modified version of popular Relief algorithm, with incorporating characteristics of variables by supervised discretisation. Comparison of obtained results included the aspect of knowledge representation as well as the perspective of the accuracy for constructed rule-based classifiers. The experiments were performed on datasets from stylometry domain, where authorship attribution was considered as a classification task, and stylometric descriptors as characteristic features defining writing styles of authors. © 2022 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the 26th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES 2022)

关键词： Knowledge representation

Setting up a Distributed control System Laboratory 11

学校读者我要写书评

暂无评论

Setting up a Distributed Control System Laboratory

11th International Conference and Exposition on Electrical And Power Engineering, EPE 2020

作者： Postovei, Danut Adrian Bulac, Constantin Tristiu, Ion Camachi, Balduino University Politehnica of Bucharest Faculty of Power Engineering Bucharest Romania University Politehnica of Bucharest Faculty of Automatic Control and Computer Science Bucharest Romania

ISBN: (纸本)9781728181264

This paper presents a practical laboratory for student education purpose in Distributed control Systems, with focus on applications for high voltage transmission substations. The monitoring, control and protection part is realized with a software platform and IED devices manufactured by AREVA TD France, while the primary equipment, like circuit breakers and disconnectors are simulated with latched relays. The system architecture and communication network are reproducing a real one usually used in transmission substations. The implementation of this laboratory, both through specific laboratory works and experiments, makes the theoretical part to be supported by a practical experience, resulting in future graduates with added value in the electric power industry. © 2020 IEEE.

关键词： Laboratories

GETAE: Graph Information Enhanced Deep Neural Network Ensemble ArchitecturE for Fake News Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Truica, Ciprian-Octavian Apostol, Elena-Simona Marogel, Marius Paschke, Adrian Computer Science and Engineering Department Faculty of Automatic Control and Computers National University of Science and Technology Politehnica Bucharest Splaiul Independentei 313 Bucharest060042 Romania Academy of Romanian Scientists Ilfov 3 Bucharest050044 Romania Department of Mathematics and Computer Science Freie Universität Berlin Arnimallee 14 Berlin14195 Germany Fraunhofer Institute for Open Communication Systems Kaiserin-Augusta-Allee 31 Berlin10589 Germany

In today’s digital age, fake news has become a major problem that has serious consequences, ranging from social unrest to political upheaval. To address this issue, new methods for detecting and mitigating fake news are required. In this work, we propose to incorporate contextual and network-aware features into the detection process. This involves analyzing not only the content of a news article but also the context in which it was shared and the network of users who shared it, i.e., the information diffusion. Thus, we propose GETAE, Graph Information Enhanced Deep Neural Network Ensemble ArchitecturE for Fake News Detection, a novel ensemble architecture that uses textual content together with the social interactions to improve fake news detection. GETAE contains two Branches: the Text Branch and the Propagation Branch. The Text Branch uses Word and Transformer Embeddings and a Deep Neural Network based on feed-forward and bidirectional Recurrent Neural Networks ([Bi]RNN) for learning novel contextual features and creating a novel Text Content Embedding. The Propagation Branch considers the information propagation within the graph network and proposes a Deep Learning architecture that employs Node Embeddings to create novel Propagation Embedding. GETAE Ensemble combines the two novel embeddings, i.e., Text Content Embedding and Propagation Embedding, to create a novel Propagation-Enhanced Content Embedding which is afterward used for classification. The experimental results obtained on two real-world publicly available datasets, i.e., Twitter15 and Twitter16, prove that using this approach improves fake news detection and outperforms state-of-the-art models. © 2024, CC BY-NC-ND.

关键词： Graph embeddings