检索结果-内蒙古大学图书馆

An automated speech analysis system for the detection of cognitive decline in elderly

International Journal of Speech technology 2023年第2期26卷 337-353页

作者： Loizou, Christos P. Pantzaris, Marios Faculty of Engineering & Technology Department of Electrical Engineering and Computer Engineering and Informatics Cyprus University of Technology 30 Arch. Kyprianos Str. Office 420 Limassol3036 Cyprus Cyprus Institute of Neurology and Genetics P. O. Box 23462 Nicosia1683 Cyprus

The goal of this study is to develop and test an automated integrated speech analysis system for detecting mild cognitive impairment (MCI) and dementia in spontaneous free speech. During the years 2010–2016, speech recordings (N = 2800) were obtained from 200 Greek Cypriots over the age of 65. These were divided into three groups (G1, G2, and G3) based on the results of their Mini-mental state examination (MMSE): G1:95 normal (NOR) individuals with an MMSE greater than 26;G2:65 MCI subjects with 20 ≤ MMSE ≤ 26;G3:40 dementia subjects with 0 ≤ MMSE © 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Capacity Bounds for Identification With Effective Secrecy

Capacity Bounds for Identification With Effective Secrecy

引用

2023 IEEE International Symposium on Information Theory, ISIT 2023

作者： Rosenberger, Johannes Ibrahim, Abdalla Bash, Boulat A. Deppe, Christian Ferrara, Roberto Pereg, Uzi Technical University of Munich Tum School of Computation Information and Technology Germany University of Arizona Electrical and Computer Engineering Department United States Technion - Israel Institute of Technology Faculty of Electrical and Computer Engineering Helen Diller Quantum Center Israel

ISBN: (纸本)9781665475549

An upper bound to the identification capacity of discrete memoryless wiretap channels is derived under the requirement of semantic effective secrecy, combining semantic secrecy and stealth constraints. A previously established lower bound is improved by applying it to a prefix channel, formed by concatenating an auxiliary channel and the actual channel. The bounds are tight if the legitimate channel is more capable than the eavesdropper's channel. An illustrative example is provided for a wiretap channel that is composed of a point-to-point channel, and a parallel, reversely degraded wiretap channel. A comparison with results for message transmission and for identification with only secrecy constraint is provided. © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Least-Distortion Maximum Gain Beamformer for Time-Domain Region-of-Interest Beamforming

IEEE Transactions on Audio, Speech and Language Processing

引用

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 2286-2301页

作者： Ariel Frank Israel Cohen Andrew and Erna Viterbi Faculty of Electrical and Computer Engineering Technion – Israel Institute of Technology Haifa Israel

Region-of-interest (ROI) beamformers are very useful in cases where precise information about the source position is unavailable, such as situations involving estimation errors or source movement. This paper presents an approach to ROI beamforming using convolutive filters in the time domain. The proposed beamformer can focus on a specific spatial region of interest while suppressing interference and noise from other directions. We formulate the signal model, considering a desired source signal propagating from a particular ROI and an array of sensors capturing a convolved version of the signal in some noise field. Appropriate performance measures are introduced to derive and analyze ROI-centric beamformers. The ROI beamformer is designed to maximize the gain in signal-to-noise ratio under a constraint on the signal distortion in the spatial region of interest. Additional parameters are introduced to balance the beamformer’s gain, distortion, and robustness. Simulations demonstrate the effectiveness of the proposed method in ROI beamforming and interference suppression.

关键词： Array signal processing Sensors Time-domain analysis Acoustic distortion Noise Time-frequency analysis Computational modeling Acoustics Accuracy Covariance matrices

来源：评论

学校读者我要写书评

暂无评论

Depth and Pitch Control of Autonomous Underwater Glider Using Model Predictive Control with ARX Model

Depth and Pitch Control of Autonomous Underwater Glider Usin...

引用

2023 International Conference on electrical engineering and Informatics, ICEEI 2023

作者： Jeremy, Jason Hidayat, Egi Muhammad Idris Siregar, Simon Trilaksono, Bambang Riyanto Habibullah, Natsir School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia Telkom University Faculty of Applied Science Department Computer Engineering Bandung Indonesia

ISBN: (纸本)9798350381290

Autonomous Underwater Gliders (AUGs) are extensively developed vehicles capable of prolonged exploration and observation in complex marine environments. Control of the AUG is challenging due to its slow response system and its constraints. In this research, a linear model representation of AutoRegressive eXogenous input (ARX) will be constructed using input and output data from the AUG system, built Model Predictive Control (MPC), analyzed the performance, comparing with traditional Proportional-Integral-Derivative (PID). The objective is to enhance setpoint tracking accuracy and minimize energy to extend exploration time while faced with constraints. Simulation results reveal MPC exhibits potential setpoint tracking, low overshoot as low as 0.6% up to 0.3m/s maximum depth rate, has relatively low input changes indicating good efficiency compared to PID. MPC approach effectively addresses slow response systems, managing momentum, and handling actuator constraints commonly encountered in AUG. © 2023 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

A Front-End Adaptation Network for Improving Speech Recognition Performance in Packet Loss and Noisy Environments

IEEE Transactions on Audio, Speech and Language Processing

引用

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 2175-2188页

作者： Yehoshua Dissen Shiry Yonash Israel Cohen Joseph Keshet Andrew and Erna Viterbi Faculty of Electrical and Computer Engineering Technion–Israel Institute of Technology Haifa Israel

Robust automatic speech recognition (ASR) in packet loss and noisy environments remains a significant challenge. Large pretrained transformer models have made notable strides in improving ASR performance across diverse domains. However, considerable room remains for improvement, even in moderate packet loss and noise conditions. Enhancing these models is particularly difficult because retraining is computationally prohibitive, and fine-tuning introduces the risk of domain shift, which can degrade performance in other languages or environments. We introduce a novel method that leverages a front-end adaptation network to improve word error rate (WER) performance in scenarios with packet loss and noise. Our approach addresses the constraints of working with large pretrained ASR models while avoiding retraining or fine-tuning. We connect an adaptation network to a frozen ASR model, where the network is trained to modify corrupted input spectra using both the loss function of the ASR model and an enhancement loss. This strategy allows the system to adapt to packet loss and noise without compromising the performance of the original ASR model or generalization across domains. The method focuses on improving WER rather than signal quality or intelligibility, targeting it for ASR applications. We conduct a comprehensive set of experiments on various types of noise. Our results demonstrate that the adaptation network significantly reduces WER in all conditions while preserving the foundational performance of the pretrained ASR model.

关键词： Adaptation models Packet loss Noise Speech enhancement Computational modeling Data models Training Noise measurement Robustness Transformers

来源：评论

学校读者我要写书评

暂无评论

Exploring Charge Trapping Dynamics in Si:HfO-FeFETs by Temperature-Dependent electrical Characterization 8

Exploring Charge Trapping Dynamics in Si:HfO-FeFETs by Tempe...

引用

8th IEEE Electron Devices technology and Manufacturing Conference, EDTM 2024

作者： Dahan, Mor Mordechai Ber, Emanuel Levit, Or Mulaosmanovic, Halid Dunkel, Stefan Muller, Johannes Beyer, Sven Yalon, Eilam Viterbi Faculty of Electrical and Computer Engineering Technion-Israel Institute of Technology Israel GlobalFoundries Fab1 Llc & Co. Kg Dresden01109 Germany

ISBN: (纸本)9798350371529

Ferroelectric HfO2 technology shows promise for non-volatile memory and neuromorphic devices. However, charge trapping limits their performance. This work presents temperature-dependent electrical characterization that reveals distinct memory window behaviors, transitioning from ferroelectric to trapping. Our measurements span six orders of magnitude in time, and ambient temperatures of 80-300 K. Analysis of threshold voltage, memory window, and de-trapping dynamics extracts a trap energy level of 0.2 eV, providing crucial insights for advancing FE HfO2-based FeFETs technology. © 2024 IEEE.

关键词： Hafnium oxides

来源：评论

学校读者我要写书评

暂无评论

Explainability-based Trust Algorithm for electricity price forecasting models

引用

Energy and AI 2023年第4期14卷 141-158页

作者： Leena Heistrene Ram Machlev Michael Perl Juri Belikov Dmitry Baimel Kfir Levy Shie Mannor Yoash Levron Electrical Engineering Department School of TechnologyPandit Deendayal Energy UniversityGandhinagarGujarat382007India The Andrew and Erna Viterbi Faculty of Electrical&Computer Engineering Technion-Israel Institute of TechnologyHaifa3200003Israel Department of Software Science Tallinn University of TechnologyAkadeemia tee 15ATallinn12618Estonia Electrical&Electronics Engineering Department Sami Shamoon College of EngineeringBeer-Sheva84100Israel

Advanced machine learning(ML)algorithms have outperformed traditional approaches in various forecasting applications,especially electricity price forecasting(EPF).However,the prediction accuracy of ML reduces substantially if the input data is not similar to the ones seen by the model during *** is often observed in EPF problems when market dynamics change owing to a rise in fuel prices,an increase in renewable penetration,a change in operational policies,*** the dip in model accuracy for unseen data is a cause for concern,what is more,challenging is not knowing when the ML model would respond in such a *** uncertainty makes the power market participants,like bidding agents and retailers,vulnerable to substantial financial loss caused by the prediction errors of EPF ***,it becomes essential to identify whether or not the model prediction at a given instance is *** this light,this paper proposes a trust algorithm for EPF users based on explainable artificial intelligence *** suggested algorithm generates trust scores that reflect the model’s prediction quality for each new *** scores are formulated in two stages:in the first stage,the coarse version of the score is formed using correlations of local and global explanations,and in the second stage,the score is fine-tuned further by the Shapley additive explanations values of different *** score-based explanations are more straightforward than feature-based visual explanations for EPF users like asset managers and traders.A dataset from Italy’s and ERCOT’s electricity market validates the efficacy of the proposed *** show that the algorithm has more than 85%accuracy in identifying good predictions when the data distribution is similar to the training *** the case of distribution shift,the algorithm shows the same accuracy level in identifying bad predictions.

关键词： Electricity price forecasting EPF Explainable AI model XAI SHAP Explainability

来源：评论

学校读者我要写书评

暂无评论

Thermalization and Entanglement of Quantum Light in a Nonlinear Multimode System

Thermalization and Entanglement of Quantum Light in a Nonlin...

引用

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Birk, Michael Lyubarov, Mark Ruimy, Ron Even-Tzur, Matan Wu, Fan O. Cohen, Oren Segev, Mordechai Kaminer, Ido Sidorenko, Pavel Solid State Institute Faculty of Physics Technion - Israel Institute of Technology Israel Solid State Institute Faculty of Electrical & Computer Engineering Techmon - Israel Institute of Technology Israel School of Applied and Engineering Physics Cornell University IthacaNY United States

We study how thermodynamic behavior in classical nonlinear optical multimode systems presents itself in quantum many-body settings, and find multimode entanglement arising in the formalization process. © Optica P... 详细信息

ISBN: (纸本)9781957171258

关键词： Quantum entanglement

来源：评论

学校读者我要写书评

暂无评论

Indirect Minimization of Common-Mode Voltage with Finite Control-Set Model Predictive Control in a Five-Level Inverter

Indirect Minimization of Common-Mode Voltage with Finite Con...

引用

2024 IEEE Energy Conversion Congress and Exposition, ECCE 2024

作者： Prajapati, Dharmikkumar Dekka, Apparao Ronanki, Deepak Rodriguez, Jose Lakehead University Department of Electrical and Computer Engineering Thunder Bay Canada Indian Institute of Technology Madras Department of Engineering Design Chennai India Universidad San Sebastian Santiago Faculty of Engineering Santiago Chile

ISBN: (纸本)9798350376067

The cost function with weighting factor has been adopted in the conventional finite control-set model predictive control (FCS-MPC) methods to directly minimize the common-mode voltage (CMV) of multilevel inverters (MLIs), which further affects the MLI's output current and voltage quality. These methods also need higher execution time to implement in real-time controllers. In this paper, a new FCS-MPC philosophy is presented to minimize the CMV indirectly, thereby eliminating the need of weighting factors and their impact on voltage and current harmonic distortions. Also, the proposed FCS-MPC is designed to achieve the control objectives of each phase by using an independent cost function, resulting in shorter execution time. The proposed method applied to a five-level MLI (5L-MLI), and the corresponding discrete-time models are developed by using Heun's integration method. The efficacy of the proposed FCS-MPC method is demonstrated through a scale-down laboratory prototype. Furthermore, the experimental comparison studies with the conventional Heun's integration method-based FCS-MPC methods with and without CMV minimization are presented. © 2024 IEEE.

关键词： Harmonic distortion

来源：评论

学校读者我要写书评

暂无评论

Classification of Electroencephalogram Signals Using LSTM and SVM Based on Fast Walsh-Hadamard Transform

引用

computers, Materials & Continua 2023年第6期75卷 5271-5286页

作者： Saeed Mohsen Sherif S.M.Ghoneim Mohammed S.Alzaidi Abdullah Alzahrani Ashraf Mohamed Ali Hassan Electronics and Communications Engineering Department Al-Madinah Higher Institute for Engineering and TechnologyGiza12947Egypt Department of Artificial Intelligence Engineering Faculty of Computer Science and EngineeringKing Salman International University(KSIU)South Sinai46511Egypt Department of Electrical Engineering College of EngineeringTaif UniversityTaif21944Saudi Arabia Department of Electronics and Communications Engineering October High Institute for Engineering and Technology6th of October CityGiza12596Egypt

Classification of electroencephalogram(EEG)signals for humans can be achieved via artificial intelligence(AI)***,the EEG signals associated with seizure epilepsy can be detected to distinguish between epileptic and non-epileptic *** this perspective,an automated AI technique with a digital processing method can be used to improve these *** paper proposes two classifiers:long short-term memory(LSTM)and support vector machine(SVM)for the classification of seizure and non-seizure EEG *** classifiers are applied to a public dataset,namely the University of Bonn,which consists of 2 classes–seizure and *** addition,a fast Walsh-Hadamard Transform(FWHT)technique is implemented to analyze the EEG signals within the recurrence space of the ***,Hadamard coefficients of the EEG signals are obtained via the ***,the FWHT is contributed to generate an efficient derivation of seizure EEG recordings from non-seizure EEG ***,a k-fold cross-validation technique is applied to validate the performance of the proposed *** LSTM classifier provides the best performance,with a testing accuracy of 99.00%.The training and testing loss rates for the LSTM are 0.0029 and 0.0602,respectively,while the weighted average precision,recall,and F1-score for the LSTM are 99.00%.The results of the SVM classifier in terms of accuracy,sensitivity,and specificity reached 91%,93.52%,and 91.3%,*** computational time consumed for the training of the LSTM and SVM is 2000 and 2500 s,*** results show that the LSTM classifier provides better performance than SVM in the classification of EEG ***,the proposed classifiers provide high classification accuracy compared to previously published classifiers.

关键词： Electroencephalogram LSTM SVM fast Walsh-Hadamard transform seizure accuracy sensitivity specificity

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：