检索结果-内蒙古大学图书馆

data-driven environmental compensation for speech recognition: A unified approach

SPEECH COMMUNICATION 1998年第4期24卷 267-285页

作者： Moreno, PJ Raj, B Stern, RM Carnegie Mellon Univ Dept Elect & Comp Engn Pittsburgh PA 15213 USA Carnegie Mellon Univ Sch Comp Sci Pittsburgh PA 15213 USA

Environmental robustness for automatic speech recognition systems based on parameter modification can be accomplished in two complementary ways. One approach is to modify the incoming features of environmentally-degraded speech to more closely resemble the features of the (normally undegraded) speech used to train the classifier. The other approach is to modifying the internal statistical representations of speech features used by the classifier to more closely resemble the features representing degraded speech in a particular target environment. This paper attempts to unify these two approaches to robust speech recognition by presenting several techniques that share the same basic assumptions and internal structure while differing in whether they modify the features of incoming speech or whether they modify the statistics of the classifier itself. We present the multivaRiate gAussian-based cepsTral normaliZation (RATZ) family of algorithms which modify incoming cepstral features, along with the STAR (STAtistical Reestimation) family of algorithms, which modify the internal statistics of the classifier. Both types of algorithms are data driven, in that they make use of a certain amount of adaptation data for learning compensation parameters. The algorithms were evaluated using the SPHINX-II speech recognition system on subsets of the Wall Street Journal database. While all algorithms demonstrated improved recognition accuracy compared to previous algorithms, the STAR family of algorithms tended to provide lower error rates than the RATZ family of algorithms as the SNR was decreased. (C) 1998 Elsevier Science B.V. All rights reserved.

关键词： Robust speech communication Environmental compensation data-driven algorithms

来源：评论

学校读者我要写书评

暂无评论

A Practical data-driven Battery State-of-Health Estimation for Electric Vehicles

引用

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2023年第2期70卷 1973-1982页

作者： Rahimian, Saeed Khaleghi Tang, Yifan E Powertrain SERES EV Santa Clara CA 95054 USA

In this article, to estimate the battery state of health (SOH) under realistic electric vehicle (EV) conditions, a robust and efficient data-driven algorithm is developed and validated through comprehensive battery life testing. More than 50 state-of-the-art EV battery cells have been tested under a variety of cycling conditions with different charging protocols, dynamic driving cycles, voltage ranges, pulse rates, and temperatures. Some of the cells have also been tested under a combination of cycling and storage conditions, constant current and multistep charging, and a periodic temperature variation that mimics real life conditions. Only partial data (voltage, current, and temperature) within a narrow state-of-charge range under a dynamic driving condition are required to extract the health indicators. A neural network is trained to find the mapping between the health features and the battery SOH. The life test data are divided into three groups. The first dataset ( approximate 55% of data) is used for training and initial validation and testing, whereas the second and third datasets ( approximate 45% of data) are entirely used for the final validation and testing to minimize the network overfitting. The results show that the SOH estimation root-mean-squared error for all datasets is less than 0.9%, signifying the fidelity and reliability of the proposed method.

关键词： Batteries Estimation State of charge Heuristic algorithms Feature extraction Training Protocols Battery management system (BMS) battery state of health (SOH) data-driven algorithms Li-ion batteries neural networks (NNs)

来源：评论

学校读者我要写书评

暂无评论

Flow Reconstruction Around a Surface-Mounted Prism from Sparse Velocity and/or Scalar Measurements Using a Combination of POD and a data-driven Estimator

引用

FLOW TURBULENCE AND COMBUSTION 2023年第4期110卷 1059-1090页

作者： Lu, Shengqi Papadakis, George Imperial Coll London Dept Aeronaut Exhibit Rd London SW7 2AZ England

A data-driven algorithm is proposed for flow reconstruction from sparse velocity and/or scalar measurements. The algorithm is applied to the flow around a two-dimensional, wall-mounted, square prism. To reduce the problem dimensionality, snapshots of flow and scalar fields are processed to derive POD modes and their time coefficients. Then a system identification algorithm is employed to build a reduced order, linear, dynamical system for the flow and scalar dynamics. Optimal estimation theory is subsequently applied to derive a Kalman estimator to predict the time coefficients of the POD modes from sparse measurements. Analysis of the flow and scalar spectra demonstrate that the flow field leaves its footprint on the scalar, thus extracting velocity from scalar concentration measurements is meaningful. The results show that remarkably good reconstruction of the flow statistics (Reynolds stresses) and instantaneous flow patterns can be obtained using a very small number of sensors (even a single scalar sensor yields very satisfactory results for the case considered). The Kalman estimator derived at one condition is able to reconstruct with acceptable accuracy the flow fields at two nearby off-design conditions. Further work is needed to assess the performance of the algorithm in more complex, three-dimensional, flows.

关键词： Flow reconstruction data-driven algorithms POD Flow around a prism

来源：评论

学校读者我要写书评

暂无评论

Anomaly detection in multivariate time series of drilling data

GEOENERGY SCIENCE AND ENGINEERING

引用

GEOENERGY SCIENCE AND ENGINEERING 2024年 237卷

作者： Altindal, Mehmet Cagri Nivlet, Philippe Tabib, Mandar Rasheed, Adil Kristiansen, Tron Golder Khosravanian, Rasool Norwegian Univ Sci & Technol Dept Engn Cybernet Trondheim Norway Sintef Ind Dept Appl Geosci Trondheim Norway Sintef Digital Dept Math & Cybernet Trondheim Norway Aker BP Stavanger Norway Equinor ASA Stavanger Norway Halliburton Tananger Norway

Different clusters of abnormal activities often arise within same temporal domain of drilling operations. This contrasts with employing simplified scenarios, such as anomaly detection models for specific issues like stuck pipe or loss circulation. The dynamic nature of drilling environments demands a holistic framework that can adapt to evolving conditions and detect anomalies beyond predefined categories. There exists a need to evaluate the performance of various data -driven models and achieve a broader applicability of anomaly detection instead of focusing on a single abnormal activity type. This study presents a generalized framework designed to detect anomalous events in drilling operations. Three different unsupervised learning algorithms, principal component analysis (PCA), isolation forest (IF) and lstm-autoencoder (LSTM-AE), are used to determine abnormal patterns and irregularities in the drilling data. PCA is chosen for its interpretability and efficiency in handling high -dimensional data by reducing the dimensionality. IF is selected for its effectiveness in isolating anomalies, making it robust for scenarios where anomalies exhibit distinct patterns. LSTM-AE is employed due to its capability to capture temporal dependencies and nonlinear patterns in time series data. A multivariate time series of drilling data from an offshore well is collected to use in this work. The dataset comprises approximately six months of drilling operations, including drilling and non -drilling periods. The input variables are chosen from the common controllable parameters continuously monitored by the drilling crew. The pre-processed drilling data with input features is organized into groups based on each drilling section. These unlabeled data is split into train, validation and test sets. Cross -validation (CV) is applied into train and validation sets to prevent overfitting and tune the hyperparameters. The test data is used to evaluate the generalizability and robustness

关键词： Drilling Multivariate time series data analysis Anomaly detection data-driven algorithms Machine learning

来源：评论

学校读者我要写书评

暂无评论

TS-RTPM-Net: data-driven Tensor Sketching for Efficient CP Decomposition

引用

IEEE TRANSACTIONS ON BIG data 2024年第1期10卷 1-11页

作者： Cao, Xingyu Zhang, Xiangtao Zhu, Ce Liu, Jiani Liu, Yipeng Univ Elect Sci & Technol China UESTC Sch Informat & Commun Engn Chengdu 611731 Peoples R China

Tensor decomposition is widely used in feature extraction, data analysis, and other fields. As a means of tensor decomposition, the robust tensor power method based on tensor sketch (TS-RTPM) can quickly mine the potential features of tensor, but in some cases, its approximation performance is limited. In this paper, we propose a data-driven framework called TS-RTPM-Net, which improves the estimation accuracy of TS-RTPM by jointly training the TS value matrices with the RTPM initial matrices. It also uses two greedy initialization algorithms to optimize the TS location matrices. In addition, TS-RTPM-Net accelerates TS-RTPM by using fast power iteration modules. Comparative experiments on real-world datasets verify that TS-RTPM-Net outperforms TS-RTPM in terms of estimation accuracy, running speed, and memory consumption.

关键词： Accelerated tensor decomposition data-driven algorithms dimensionality reduction greedy algorithms low-rank tensor approximation

来源：评论

学校读者我要写书评

暂无评论

Optimal perfect corrective maintenance policy for a system with multiple components using data-driven decision-making methods

引用

QUALITY AND RELIABILITY ENGINEERING INTERNATIONAL 2024年第1期40卷 472-498页

作者： Misaii, Hasan Fouladirad, Mitra Haghighi, Firoozeh Univ Tehran Coll Sci Sch Math Stat & Comp Sci Tehran Iran Univ Technol Troyes LISTEN Troyes France Aix Marseille Univ CNRS Cent Marseille Marseille France

This paper considers a multicomponent series system to be inspected periodically. It is assumed that the exact cause of system failure might be unknown, and we only know that it belongs to a subset of all components, called masked set. In this case, it is said that the exact cause of failure is masked. A perfect corrective maintenance policy is applied to repair the system, such that a failed component is replaced by a new one at the first inspection time after failure. The distance between each two inspections is considered a decision parameter that should be optimized. Three levels of information availability are considered, including full, partial, and noninformation availability, in which the maintenance policy should be optimized. The former is considered a benchmark, and the statistical and machine learning data-driven algorithms are used to estimate the cost for the other two information levels. Eventually, using Monte Carlo simulation studies, the proposed method application is analyzed.

关键词： data-driven algorithms masked data perfect corrective repair statistical decision-making methods

来源：评论

学校读者我要写书评

暂无评论

data-driven detection and identification of IoT-enabled load-altering attacks in power grids

引用

IET SMART GRID 2022年第3期5卷 203-218页

作者： Lakshminarayana, Subhash Sthapit, Saurav Jahangir, Hamidreza Maple, Carsten Poor, H. Vincent Univ Warwick Sch Engn Coventry W Midlands England Univ Warwick Warwick Mfg Grp Coventry W Midlands England Princeton Univ Dept Elect & Comp Engn Princeton NJ USA

Advances in edge computing are powering the development and deployment of Internet of Things (IoT) systems to provide advanced services and resource efficiency. However, large-scale IoT-based load-altering attacks (LAAs) can seriously impact power grid operations, such as destabilising the grid's control loops. Timely detection and identification of any compromised nodes are essential to minimise the adverse effects of these attacks on power grid operations. In this work, two data-driven algorithms are proposed to detect and identify compromised nodes and the attack parameters of the LAAs. The first method, based on the Sparse Identification of Nonlinear Dynamics approach, adopts a sparse regression framework to identify attack parameters that best describe the observed dynamics. The second method, based on physics-informed neural networks, employs neural networks to infer the attack parameters from the measurements. Both algorithms are presented utilising edge computing for deployment over decentralised architectures. Extensive simulations are performed on IEEE 6-, 14-, and 39-bus systems to verify the effectiveness of the proposed methods. Numerical results confirm that the proposed algorithms outperform existing approaches, such as those based on unscented Kalman filter, support vector machines, and neural networks (NN), and effectively detect and identify locations of attack in a timely manner.

关键词： nonlinear filters power grid operations Sparse Identification power engineering computing computer network security physics-informed neural networks advanced services compromised nodes neural nets power grids Kalman filters data-driven algorithms Internet of Things Nonlinear Dynamics approach utilising edge computing IoT-enabled load-altering attacks edge computing Things systems sparse regression framework regression analysis large-scale IoT-based load-altering attacks support vector machines LAAs attack parameters

来源：评论

学校读者我要写书评

暂无评论

Termination detection in data-driven parallel computations/applications

引用

JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING 2003年第3期63卷 312-326页

作者： Khokhar, AA Hambrusch, SE Kocalar, E Univ Illinois Dept Elect & Comp Sci Chicago IL 60607 USA Purdue Univ Dept Comp Sci W Lafayette IN 47907 USA WebTV Networks Mountain View CA 94043 USA

High-performance computing applications with data-driven communication and computation characteristics require synchronization routines in the form of eureka, barrier, or termination synchronization. In this paper, we consider termination synchronization for two different execution models, the AP and the APS model. In the AP model, processors are either active or passive and a passive processor can be made active by another active processor. In the APS model, processors can also be in a server state. A passive processor entering the server state does not become active again. In addition, a server processor cannot change the status of other processors. We describe and analyze solutions for both models and present experimental work highlighting the differences between the models. We show that in almost all situations the use of an AP algorithm to detect termination in an APS environment will result in loss of performance. Our experimental work on the Cray T3E provides insight into where and why this performance loss occurs. (C) 2003 Elsevier Science (USA). All rights reserved.

关键词： data-driven algorithms termination detection tree and ring networks synchronization

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study on data-driven Prognostic Approaches Using Fleet Knowledge

A Comparative Study on Data-Driven Prognostic Approaches Usi...

引用

IEEE International Instrumentation and Measurement Technology Conference (I2MTC)

作者： Cristaldi, Loredana Leone, Giacomo Ottoboni, Roberto Subbiah, Subanatarajan Turrin, Simone Politecn Milan Dept Elect Engn Milan Italy ABB AG Corp Res Ctr Germany Ind Software & Applicat Ladenburg Germany

ISBN: (纸本)9781467392204

Recently, Prognostics and Heath Management techniques have been deeply investigated with the aim to reduce life-cycle cost of products and systems. The increasing availability of condition monitoring data in substantial quantities for multitudes of homogeneous products and the need for generic algorithms that are applicable to complex systems motivates the development of new data-driven prognostic approaches. In this paper, two data-driven algorithms, one based on a statistical approach and another based on Neural Network, are discussed and tested for an application case. The analysis of the results has shown that both the considered approaches are characterized by reliable prediction performances on Remaining Useful Life calculation, thus resulting as potential tools for the application of a Condition-Based Maintenance strategy.

关键词： prognostics and health management data-driven algorithms fleet management condition-based maintenance

来源：评论

学校读者我要写书评

暂无评论

Advanced Analytics for Train Delay Prediction Systems by Including Exogenous Weather data 3

Advanced Analytics for Train Delay Prediction Systems by Inc...

引用

3rd IEEE/ACM International Conference on data Science and Advanced Analytics (DSAA)

作者： Oneto, Luca Fumeo, Emanuele Clerico, Giorgio Canepa, Renzo Papa, Federico Dambra, Carlo Mazzino, Nadia Anguita, Davide Univ Genoa DIBRIS Via Opera Pia 13 I-16145 Genoa Italy Rete Ferroviaria Italiana SpA Via Don Vincenzo Minetti 6-5 I-16126 Genoa Italy Ansaldo STS SpA Via Paolo Mantovani 3-5 I-16151 Genoa Italy

ISBN: (纸本)9781509052066

State-of-the-art train delay prediction systems neither exploit historical data about train movements, nor exogenous data about phenomena that can affect railway operations. They rely, instead, on static rules built by experts of the railway infrastructure based on classical univariate statistics. The purpose of this paper is to build a data-driven train delay prediction system that exploits the most recent analytics tools. The train delay prediction problem has been mapped into a multivariate regression problem and the performance of kernel methods, ensemble methods and feed-forward neural networks have been compared. Firstly, it is shown that it is possible to build a reliable and robust data-driven model based only on the historical data about the train movements. Additionally, the model can be further improved by including data coming from exogenous sources, in particular the weather information provided by national weather services. Results on real world data coming from the Italian railway network show that the proposal of this paper is able to remarkably improve the current state-of-the-art train delay prediction systems. Moreover, the performed simulations show that the inclusion of weather data into the model has a significant positive impact on its performance.

关键词： data-driven algorithms Delay Prediction Exogenous Weather data Intelligent Transportation Systems Railway

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：