检索结果-内蒙古大学图书馆

TechRxiv 2022年

作者： Hamza, Anis Amazigh Dayoub, Iyad Alouani, Ihsen Amrouche, Abderrahmane Laboratory of Speech Communication and Signal Processing Faculty of Electronics and Computer Science University of Science and Technology Houari Boumediene UPHF Bab Ezzouar Algiers16111 Algeria Polytechnic University Hauts-de-France CNRS Univ. Lille ISEN Centrale Lille UMR8520- IEMN Institut D’Electronique de Microlectronique Et de Nanotechnologie - DOAE Dpartement Opto-Acousto-Electronique Valenciennes59313 France INSA Hauts-de-France Valenciennes59313 France

Cell-edge users of the future cellular internet of things (IoT) with massive IoT sensors can suffer from extremely severe channel conditions, especially under very high-speed scenarios. In this paper, we present a performance improvement method for cell-edge users of multi-carrier modulation (MCM)-based non-orthogonal multiple access (NOMA) downlink systems. To this end, we consider the implementation of cooperative user relaying NOMA (CUR-NOMA) and derive its lower bound E2E-BER under doubly selective channels. In addition, the imperfect successive interference cancellation (SIC) process is analyzed, wherein two interference cancellation schemes are combined to remove the NOMA induced inter-user interference (IUI) and the doubly selective channel induced inter-carrier interference (ICI). © 2022, CC BY.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Clustering via Information-Theoretic Markov Chain Aggregation

arXiv

引用

arXiv 2021年

作者： Steger, Sophie Geiger, Bernhard C. Śmieja, Marek Signal Processing and Speech Communication Laboratory Graz University of Technology Inffeldgasse 16c Graz8010 Austria Know-Center GmbH Inffeldgasse 13 Graz8010 Austria Faculty of Mathematics and Computer Science Jagiellonian University Lojasiewicza 6 Krakow Poland

We connect the problem of semi-supervised clustering to constrained Markov aggregation, i.e., the task of partitioning the state space of a Markov chain. We achieve this connection by considering every data point in the dataset as an element of the Markov chain's state space, by defining the transition probabilities between states via similarities between corresponding data points, and by incorporating semi-supervision information as hard constraints in a Hartigan-style algorithm. The introduced Constrained Markov Clustering (CoMaC) is an extension of a recent information-theoretic framework for (unsupervised) Markov aggregation to the semi-supervised case. Instantiating CoMaC for certain parameter settings further generalizes two previous information-theoretic objectives for unsupervised clustering. Our results indicate that CoMaC is competitive with the state-of-the-art. Furthermore, our approach is less sensitive to hyperparameter settings than the unsupervised counterpart, which is especially attractive in the semi-supervised setting characterized by little labeled data. Copyright © 2021, The Authors. All rights reserved.

关键词： Information theory

来源：评论

学校读者我要写书评

暂无评论

Improving Acoustic Echo Cancellation in Hands-free communication Systems

Improving Acoustic Echo Cancellation in Hands-free Communica...

引用

International Conference on Image and signal processing and their Applications (ISPA)

作者： Mahfoud Hamidia Abderrahmane Amrouche USTHB Faculty of Electronics and Computer Science Speech Communication and Signal Processing Laboratory Algiers Algeria

ISBN: (纸本)9781728131573

Acoustic echo cancellation (AEC) is the technique used to improve the speech quality in communication systems. This technique removes the undesirable acoustic echo generated by the acoustic coupling between the loudspeaker and the microphone of the terminal devices. In addition, AEC is generally based on adaptive filtering. This paper presents a new structure of AEC system to improve the performance of the conventional AEC. Simulation results using normalized least mean square (NLMS) algorithm demonstrate that better performance can be achieved by the proposed structure compared to the conventional structure of AEC. Therefore, three criteria measures are used to evaluate the proposed structure of AEC: misalignment, mean square error (MSE) and echo return loss enhancement (ERLE).

关键词： Acoustic echo cancellation Adaptive filtering NLMS Misalignement MSE ERLE acoustic echo cancellation adaptive filters Mean square error communication SYSTEMS Avian enteric calicivirus ATOMIC ENERGY COMMISSION proposed structure nonlinear material Echo cancellers acoustic coupling Terminal equipment

来源：评论

学校读者我要写书评

暂无评论

Resource-Efficient Neural Networks for Embedded Systems

arXiv

引用

arXiv 2020年

作者： Roth, Wolfgang Schindler, Günther Klein, Bernhard Peharz, Robert Tschiatschek, Sebastian Fröning, Holger Pernkopf, Franz Ghahramani, Zoubin Graz University of Technology Laboratory of Signal Processing and Speech Communication Austria Institute of Computer Engineering Heidelberg University Germany Institute of Theoretical Computer Science Graz University of Technology Austria Faculty of Computer Science University of Vienna Austria University of Cambridge Cambridge United Kingdom

While machine learning is traditionally a resource intensive task, embedded systems, autonomous navigation, and the vision of the Internet of Things fuel the interest in resourceefficient approaches. These approaches aim for a carefully chosen trade-off between performance and resource consumption in terms of computation and energy. The development of such approaches is among the major challenges in current machine learning research and key to ensure a smooth transition of machine learning technology from a scientific environment with virtually unlimited computing resources into everyday's applications. In this article, we provide an overview of the current state of the art of machine learning techniques facilitating these real-world requirements. In particular, we focus on resource-efficient inference based on deep neural networks (DNNs), the predominant machine learning models of the past decade. We give a comprehensive overview of the vast literature that can be mainly split into three non-mutually exclusive categories: (i) quantized neural networks, (ii) network pruning, and (iii) structural efficiency. These techniques can be applied during training or as post-processing, and they are widely used to reduce the computational demands in terms of memory footprint, inference speed, and energy efficiency. We also briefly discuss different concepts of embedded hardware for DNNs and their compatibility with machine learning techniques as well as potential for energy and latency reduction. We substantiate our discussion with experiments on well-known benchmark data sets using compression techniques (quantization, pruning) for a set of resource-constrained embedded systems, such as CPUs, GPUs and FPGAs. The obtained results highlight the difficulty of finding good trade-offs between resource efficiency and prediction quality. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Reliable Method to Estimate the Bispectral Index Value Using a Single Frontal EEG Channel for Intra and Inter Subject Variability

A Reliable Method to Estimate the Bispectral Index Value Usi...

引用

IEEE International Workshop on Medical Measurement and Applications (MEMEA)

作者： Mohammad Shahbakhti Matin Beiramvand Roza Krycinska Erfan Nasiri Wei Chen Jordi Solé-Casals Michal Wierzchon Anna Broniec-Wójcik Piotr Augustyniak Vaidotas Marozas Biomedical Engineering Institute Kaunas University of Technology Kaunas Lithuania Faculty of Information Technology and Communication Tampere University Tempere Finland Doctoral School in Medical and Health Sciences Jagiellonian University Medical College Krakow Poland Department of Interdisciplinary Intensive Care Jagiellonian University Collegium Medicum Krakow Poland Faculty of Statistics Mathematics and Computer Allameh Tabataba’i University Tehran Iran Center for Intelligent Medical Electronics School of Information Science and Technology Fudan University Shanghai China Data and Signal Processing Research Group University of Vic-Central University of Catalonia Vic Spain Institute of Psychology Jagiellonian University Krakow Poland Department of Biocybernetics and Biomedical Engineering AGH University of Science and Technology Krakow Poland

Objective: Monitoring the depth of anesthesia (DoA) plays an important role for administering the drug injection during a surgery, i.e., preventing undesired awareness and inordinate anesthetic depth. Although the bispectral index (BIS) monitor is the golden standard system for the DoA monitoring, it is still not affordable for the developing countries. Alternatively, a low-cost electroencephalogram (EEG) headband can be used. The objective of this paper is to present a new algorithm for estimating the BIS values using a single frontal EEG channel. Method: In the first step, the EEG signal is filtered for the elimination of artifacts and is split into its sub-bands. In the second step, several linear and nonlinear features are extracted from each sub-band and fed to a random forest regression model in order to estimate the BIS. The performance of the proposed algorithm is assessed using EEG data recorded from twenty-four subjects during the general anesthesia and is validated in terms of correlation coefficient (CC) and absolute error (AE) between the reference and estimated BIS values. Results: The proposed algorithm achieved the mean CC of 0.83 and AE of 6.5 for intra subject variability and mean CC of 0.87 and AE of 5.5 for inter subject variability. Significance: Given the similar results for both intra and inter subject variability, the proposed algorithm has the potential to be used in the real-world scenario.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Importance of Gender Specification for Detection of Driver Fatigue using a Single EEG Channel

The Importance of Gender Specification for Detection of Driv...

引用

Biomedical Engineering International Conference (BMEiCON)

作者： Mohammad Shahbakhti Matin Beiramvand Erfan Nasiri Wei Chen Jordi Solé-Casals Michal Wierzchon Anna Broniec-Wójcik Piotr Augustyniak Vaidotas Marozas Biomedical Engineering Institute Kaunas University of Technology Kaunas Lithuania Faculty of Information Technology and Communication Tampere University Tempere Finland Faculty of Statistics Mathematics and Computer Allameh Tabataba’i University Tehran Iran Center for Intelligent Medical Electronics School of Information Science and Technology the Human Phenome Institute Fudan University Shanghai China Data and Signal Processing Research Group University of Vic-Central University of Catalonia Vic Spain Institute of Psychology Jagiellonian University Krakow Poland Department of Biocybernetics and Biomedical Engineering AGH University of Science and Technology Krakow Poland

ISBN: (纸本)9781665489041

Although detection of the driver fatigue using a single electroencephalography (EEG) channel has been addressed in literature, the gender differentiation for applicability of the model has not been investigated heretofore. Motivated accordingly, we address the detection of driver fatigue based the gender-segregated datasets, where each of them contains 8 subjects. After splitting the EEG signal into its sub-bands (delta, theta, alpha, beta, and gamma) using discrete wavelet transform, the log energy entropy of each band is computed to form the feature vector. Afterwards, the feature vector is randomly split into 50% for training and 50% for the unseen testing, and fed to a support vector machine model. When comparing the classification results of fatigue driving detection between the gender segregated and non-gender segregated datasets, the former achieved the accuracy 78% and 77% for male and female subjects, respectively, than the latter (71%). The obtained results show the importance of gender-specification for the driver fatigue detection.

关键词： Training Support vector machines Computational modeling Transforms Fatigue Brain modeling Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Emerging Technologies for 6G Non-Terrestrial-Networks: From Academia to Industrial Applications

arXiv

引用

arXiv 2024年

作者： Nguyen, Cong T. Saputra, Yuris Mulya Van Huynh, Nguyen Nguyen, Tan N. Hoang, Dinh Thai Nguyen, Diep N. Pham, Van-Quan Voznak, Miroslav Chatzinotas, Symeon Tran, Dinh-Hieu Institute of Fundamental and Applied Sciences Duy Tan University Ho Chi Minh City70000 Viet Nam Faculty of Information Technology Duy Tan University Da Nang50000 Viet Nam Internet Engineering Technology Department of Electrical Engineering and Informatics Vocational College Universitas Gadjah Mada Yogyakarta55281 Indonesia Department of Electrical Engineering and Electronics University of Liverpool LiverpoolL69 3GJ United Kingdom Communication and Signal Processing Research Group Faculty of Electrical and Electronics Engineering Ton Duc Thang University Ho Chi Minh City Viet Nam School of Electrical and Data Engineering University of Technology Sydney SydneyNSW2007 Australia Nokia Bell Labs Murray Hill NJ07974 United States Department of Telecommunications Faculty of Electrical Engineering and Computer Science VSB-Technical University of Ostrava Ostrava708 00 Czech Republic University of Luxembourg Esch-sur-Alzette4365 Luxembourg Nokia France

Terrestrial networks form the fundamental infrastructure of modern communication systems, serving more than 4 billion users globally. However, terrestrial networks are facing a wide range of challenges, from coverage and reliability to interference and congestion. As the demands of the 6G era are expected to be much higher, it is crucial to address these challenges to ensure a robust and efficient communication infrastructure for the future. To address these problems, Non-terrestrial Network (NTN) has emerged to be a promising solution. NTNs are communication networks that leverage airborne (e.g., unmanned aerial vehicles) and spaceborne vehicles (e.g., satellites) to facilitate ultra-reliable communications and connectivity with high data rates and low latency over expansive regions. This article aims to provide a comprehensive survey on the utilization of network slicing, Artificial Intelligence/Machine Learning (AI/ML), and Open Radio Access Network (ORAN) to address diverse challenges of NTNs from the perspectives of both academia and industry. Particularly, we first provide an in-depth tutorial on NTN and the key enabling technologies including network slicing, AI/ML, and ORAN. Then, we provide a comprehensive survey on how network slicing and AI/ML have been leveraged to overcome the challenges that NTNs are facing. Moreover, we present how ORAN can be utilized for NTNs. Finally, we highlight important challenges, open issues, and future research directions of NTN in the 6G era. © 2024, CC BY.

关键词： Radio access networks

来源：评论

学校读者我要写书评

暂无评论

Dynamics of the competition between two languages

引用

SeMA Journal 2020年第4期77卷 351-373页

作者： Tchendjeu, A. E. Tchahou Bowong, S. Tchitnga, R. Fotsin, H.B. Department of Computer Engineering National Higher Polytechnic Institute University of Bamenda PO Box 39 Bambili Cameroon Laboratory of Condensed Matters Electronics and Signal Processing (LAMACETS) Department of Physics Faculty of Science University of Dschang PO Box 63 Dschang Cameroon Research Group on Experimental and Applied Physics for Sustainable Development (EAPhySuD) Department of Physics Faculty of Science University of Dschang PO Box 63 Dschang Cameroon Laboratory of Applied Mathematics Department of Mathematics and Computer Science Faculty of Science University of Douala PO Box 24157 Douala Cameroon UMI 209 IRD/UPMC UMMISCO Bondy France LIRIMA Project Team GRIMCAPE Yaounde Cameroon The African Center of Excellence in Information and Communication Technologies (CETIC) University of Yaounde 1 Yaounde Cameroon Institute of Surface Chemistry and Catalysis University of Ulm Albert-Einstein-Allee 47 Ulm 89081 Germany

This paper reports a new kind of mathematical model for language competition dynamics using compartmental epidemiological modeling approach. The model describes the competition between two languages, say the predominant one called language 1, and the less spoken language 2, both in the same community. We distinguish three groups of population building the concerned community: one majority speaking language 1, one minority speaking language 2 and a last minority speaking neither language 1 nor language 2. The study of the proposed model includes an analysis of the evolution of the number of speakers over time. This model predicts that language 2 can inevitably disappear if the threshold parameter R is less than one. We show that our model is well-posed mathematically and linguistically. We also show that the model has basically two linguistic equilibrium points. A monolingual equilibrium point that corresponds to the case where only one language is spoken: some individuals speak only the language 1 and some others do speak neither language 1, nor language 2. A bilingual equilibrium point which corresponds to the case where all the languages are spoken: some individuals speak both languages 1 and 2, some others speak only language 1, while a third group does speak only language 2, and the last group speaks none of the two languages. In this bilingual equilibrium point, both languages coexist. Depending on the threshold parameter, we demonstrate the stability of these equilibria. The model presents on one hand, a direct bifurcation phenomenon, in which we have a stable equilibrium point without bilingual speakers when the associated basic reproduction number is less than one. On the other hand, it presents a stable bilingual equilibrium point when the number of associated basic reproductions is greater than one. The analysis of the overall sensitivity of the model is performed and the impact of the system parameters on the basic reproduction number was performed using

关键词： Bilingualism Compartmental modeling Dynamical system Language competition Stability

来源：评论

学校读者我要写书评

暂无评论

Emotion recognition in Arabic speech

Emotion recognition in Arabic speech

引用

International Conference on Advanced Electrical Engineering (ICAEE)

作者： Imene Hadjadji Leila Falek Lyes Demri Hocine Teffahi Laboratory of spoken communication and signal processing. Electronics and Computer Faculty USTHB Algiers Algeria

ISBN: (数字)9781728122205

ISBN: (纸本)9781728122212

The general objective of this paper is to build a system in order to automatically recognize emotion in speech. The linguistic material used is a corpus of Arabic expressive sentences phonetically balanced. The dependence of the system on speaker is an encountered problem in this field; in this work we will study the influence of this phenomenon on our result. The targeted emotions are joy, sadness, anger and neutral. After an analytical study of a large number of speech acoustic parameters, we chose the cepstral parameters, their first and second derivatives, the Shimmer, the Jitter and the duration of the sentence. A classifier based on a multilayer perceptron neural network to recognize emotion on the basis of the chosen feature vector that has been developed. The recognition rate could reach more than 98% in the case of an intra-speaker classification and 54.75% in inter-speaker classification. We can see the system's dependence on speaker clearly.

关键词： Emotion recognition speech recognition Mel frequency cepstral coefficient Databases Jitter Neural networks Neurons

来源：评论

学校读者我要写书评

暂无评论

Chaotic dynamics, topological analysis and flat analog electronic control by physiological signals of a neurally-inspired system

引用

Chinese Journal of Physics 2025年 96卷 20-52页

作者： Tabekoueng Njitacke, Zeric Ngamsa Tegnitsap, Joakim Vianney Zhao, Manyu Barà, Chiara Fozin, Théophile Fonzin Awrejcewicz, Jan Yoshimura, Natsue Valdes-Sosa, Pedro A. Letellier, Christophe Minati, Ludovico School of Life Science and Technology University of Electronic Science and Technology of China Chengdu 611731 China Department of Electrical and Electronic Engineering College of Technology (COT) University of Buea P.O. Box 63 Buea Cameroon Fotso-Victor University Institute of Technology University of Dschang P.O. Box 134 Dschang Cameroon Research Unit of Condensed Matter Electronics and Signal Processing Department of Physics University of Dschang Cameroon Department of Engineering University of Palermo Palermo 90128 Italy Department of Electrical and Electronic Engineering Faculty of Engineering and Technology (FET) University of Buea P.O. Box 63 Buea Cameroon Department of Automation Biomechanics and Mechatronics Łódź University of Technology Stefanowskiego Str. 1/15 Lodz 90-924 Poland School of Computing Institute of Science Tokyo (formerly Tokyo Institute of Technology) Yokohama Japan ATR Brain Information Communication Research Laboratory Group Kyoto Japan Department of Neuroinformatics Cuban Neuroscience Center Havana 11600 Cuba CORIA Rouen Normandie University Saint-Etienne du Rouvray 76800 France Center for Mind/Brain Sciences (CIMeC) University of Trento Trento 38123 Italy

A novel abstract bicompartmental neural model based on a cubic nonlinearity, consisting of introducing a Josephson junction as a coupling element, is presented. Through numerical simulations and experimental measurements involving an analog electronic circuit, it is found that the system can generate a double-scroll chaotic attractor endowed with a remarkably complex topology. This is accompanied by diversification of the spectral signature across its four variables and multistability. An analysis of the global observability and controllability is conducted, leading to the synthesis of a flat controller that can steer the dynamics towards those of structurally different entities, as exemplified by a modified Lorenz system. The first analog realization of flat control is then introduced. The possibility of low-latency and high-accuracy manipulation of the dynamics is demonstrated by considering the challenging case of tracking extraneous external signals, namely, physiological recordings indexing autonomic and central nervous system activity. Besides showing the flexibility and adaptability of the approach, the controller enables the concomitant generation of multiple additional signals with spectrogram features compared to the individual inputs, offering a promising substrate for future applications in physical time series data augmentation. © 2025 The Physical Society of the Republic of China (Taiwan)

关键词： Chaotic circuits Flat control Josephson junction Multistability Neural models Physiological recordings Topological analysis

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：