检索结果-内蒙古大学图书馆

2010 20th International Conference on Pattern Recognition, ICPR 2010

作者： Chen, Si-Bao Wang, Hai-Xian Luo, Bin Key Lab. of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei Anhui 230039 China Key Lab. of Child Development and Learning Science Research Center for Learning Science Southeast University Nanjing Jiangsu 210096 China

ISBN: (纸本)9780769541099

Although many methods of refining initialization have appeared, the sensitivity of K-Means to initial centers is still an obstacle in applications. In this paper, we investigate a new class of clustering algorithm, K-Alpha Means (KAM), which is insensitive to the initial centers. With K-Harmonic Means as a special case, KAM dynamically weights data points during iteratively updating centers, which deemphasizes data points that are close to centers while emphasizes data points that are not close to any centers. Through replacing minimum operator in K-Means by alpha-mean operator, KAM significantly improves the clustering performances. © 2010 IEEE.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

A Neuro-Symbolic Approach for Marine Vessels Power Prediction Under Distribution Shifts

A Neuro-Symbolic Approach for Marine Vessels Power Predictio...

引用

2023 IEEE Jordan International Joint Conference on Electrical Engineering and Information Technology, JEEIT 2023

作者： Hammoudeh, Ahmad Ghannam, Ibrahim Mubarak, Hamza Jean, Emmanuael Vandenbulcke, Virginie Dupont, Stephane MAiA Lab ISlA Lab Umons Trail Belgium RWTH Aachen University Electrical Engineering Germany Griffith University Engineering and Built Environment Australia Machine Learning & Signal Processing Multitel Trail Belgium Umons Isia Lab Belgium Umons Maia Lab Belgium

ISBN: (纸本)9798350324051

This paper proposes a neuro-symbolic approach to predict the power of marine cargo vessels. The neuro-symbolic approach combines two parts. The first is a neural networks part, and the second is a symbolic part that relies on physics-based formulae. The Shifts-power dataset was used for evaluation. The experimental results showed that a combination of a physics-based module (symbolic part) with a neural networks model (namely ensemble Monte Carlo dropout) superseded the state-of-the-art results by 2.3% in terms of uncertainty estimation measured using R-AUC, and by 3.4% in terms of power prediction for out-of-distribution (OOD) examples measured using RMSE. It also superseded the symbolic approach by 6.3% in terms of uncertainty and 17.7% in terms of OOD power prediction. © 2023 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

On the Robustness of Out-of-Distribution Detection Methods for Camera-based Systems 58

On the Robustness of Out-of-Distribution Detection Methods f...

引用

58th Asilomar Conference on signals, Systems and Computers, ACSSC 2024

作者： Huber, Christian Lehner, Bernhard Hofmann, Claus Moser, Bernhard Feger, Reinhard Silicon Austria Labs GmbH Jku Lit Sal eSPML Lab Austria Johannes Kepler University Linz Jku Lit Sal eSPML Lab Austria Institute for Machine Learning Austria Institute of Signal Processing China Institute for Communications Engineering and RF-Systems China

ISBN: (纸本)9798350354058

Out-of-distribution (OOD) detection refers to recognizing instances that lie outside the scope of what a machine learning model has been exposed to during training. In safetycritical domains like autonomous driving, OOD detection is paramount for enhancing the reliability and safety of machine learning systems. To investigate the robustness of OOD de-tection methods, we conduct experiments tailored to camera-based systems, focusing on realistic challenges these systems may encounter. Our experimental setup includes benchmarking various types of corruption, such as image sensor degradation, lens contamination and motion blur. The findings suggest intrinsic weaknesses across all tested state-of-the-art OOD detection methods. Unexpectedly, even single-pixel alterations corresponding to image sensor degradation over time can result in notable changes in performance. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Revealing Emotional Clusters in Speaker Embeddings: A Contrastive learning Strategy for Speech Emotion Recognition

Revealing Emotional Clusters in Speaker Embeddings: A Contra...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Ismail Rasim Ulgen Zongyang Du Carlos Busso Berrak Sisman Speech & Machine Learning (SML) Lab The University of Texas at Dallas USA Multimodal Signal Processing (MSP) Lab The University of Texas at Dallas USA

Speaker embeddings carry valuable emotion-related information, which makes them a promising resource for enhancing speech emotion recognition (SER), especially with limited lab.led data. Traditionally, it has been assumed that emotion information is indirectly embedded within speaker embeddings, leading to their under-utilization. Our study reveals a direct and useful link between emotion and state-of-the-art speaker embeddings in the form of intra-speaker clusters. By conducting a thorough clustering analysis, we demonstrate that emotion information can be readily extracted from speaker embeddings. In order to leverage this information, we introduce a novel contrastive pretraining approach applied to emotion-unlab.led data for speech emotion recognition. The proposed approach involves the sampling of positive and the negative examples based on the intra-speaker clusters of speaker embeddings. The proposed strategy, which leverages extensive emotion-unlab.led data, leads to a significant improvement in SER performance, whether employed as a standalone pretraining task or integrated into a multi-task pretraining setting.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Independent vector analysis for SSVEP signal enhancement

Independent vector analysis for SSVEP signal enhancement

引用

Annual Conference on Information Sciences and Systems (CISS)

作者： Darren K. Emge François-Benoît Vialatte Gérard Dreyfus Tülay Adalı Department of CSEE University of Maryland Baltimore County MD ESPCI ParisTech. SIGnal processing and MAchine learning (SIGMA) lab France

Steady state visual evoked potentials (SSVEP) have been identified as a highly viable solution for brain computer interface (BCI) systems. The SSVEP is observed in the scalp-based recordings of electroencephalogram (EEG) signals, and is one component buried amongst the normal brain signals and complex noise. By taking advantage of sample diversity, higher order statistics and statistical dependencies associated with the analysis of multiple datasets, independent vector analysis (IVA) can be used to enhance the detection of the SSVEP signal content. In this paper, we present a novel method for detecting SSVEP signals by treating each EEG signal as a stand alone data set. IVA is used to exploit the correlation across the estimated sources, as well as statistical diversity within datasets to enhance SSVEP detection, offering a significant improvement over averaging based methods for the detection of the SSVEP signal.

关键词： Harmonic analysis Electroencephalography Visualization Mutual information Brain-computer interfaces Higher order statistics Correlation

来源：评论

学校读者我要写书评

暂无评论

SENSITIVITY ANALYSIS OF GAUSSIAN PROCESSES FOR OCEANIC CHLOROPHYLL PREDICTION

SENSITIVITY ANALYSIS OF GAUSSIAN PROCESSES FOR OCEANIC CHLOR...

引用

IEEE International Geoscience and Remote Sensing Symposium

作者： Katalin Blix Gustau Camps-Valls Robert Jenssen Machine Learning @ UiT Lab University of Tromso (UiT) - The Arctic University of Norway Image and Signal Processing Group - Universitat de Valencia

ISBN: (纸本)9781479979301

Gaussian Process Regression (GPR) for machine learning has lately been successfully introduced for chlorophyll content mapping from remotely sensed data. The method provides a fast, stable and accurate prediction of biophysical parameters. However, since GPR is a non-linear kernel regression method, the relevance of the features are not accessible. In this paper, we introduce a probabilistic approach for feature sensitivity analysis (SA) of the GPR in order to reveal the relative importance of the features (bands) being used in the regression process. We evaluated the SA on GPR ocean chlorophyll content prediction. The method revealed the importance of the spectral bands, thus allowing the discrimination between Case-1 water and Case-2 water conditions.

关键词： Kernel methods Gaussian Process Regression (GPR) Sensitivity Analysis (SA) Oceanic Chlorophyll Prediction Gaussian processes ground penetrating radar Sensitivity analysis kernel method Chlorophyll spectral bands chlorophyll content Regression (Psychology)

来源：评论

学校读者我要写书评

暂无评论

One network to solve all ROIs: Deep learning CT for any ROI using differentiated backprojection

arXiv

引用

arXiv 2018年

作者： Han, Yoseob Ye, Jong Chul BISPL - Bio Imaging Signal Processing and Learning lab. Dept. of Bio and Brain Engineering KAIST Daejeon Korea Republic of

Purpose: Computed tomography for the reconstruction of region of interest (ROI) has advantages in reducing the X-ray dose and the use of a small detector. However, standard analytic reconstruction methods such as filtered back projection (FBP) suffer from severe cupping artifacts, and existing model-based iterative reconstruction methods require extensive computations. Recently, we proposed a deep neural network to learn the cupping artifacts, but the network was not generalized well for different ROIs due to the singularities in the corrupted images. Therefore, there is an increasing demand for a neural network that works well for any ROI sizes. Method: Two types of neural networks are designed. The first type learns ROI size-specific cupping artifacts from FBP images, whereas the second type network is for the inversion of the truncated Hilbert transform from the truncated differentiated backprojection (DBP) data. Their generalizabilities for different ROI sizes, pixel sizes, detector pitch and starting angles for short-scan are then investigated. Results: Experimental results show that the new type of neural networks significantly outperform existing iterative methods for all ROI sizes despite significantly lower runtime complexity. In addition, performance improvement is consistent across different acquisition scenarios. Conclusions: Since the proposed method consistently surpasses existing methods, it can be used as a general CT reconstruction engine for many practical applications without compromising possible detector truncation. Copyright © 2018, 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

PPLSA: Parallel probabilistic latent semantic analysis based on MapReduce

PPLSA: Parallel probabilistic latent semantic analysis based...

引用

7th IFIP International Conference on Intelligent Information processing, IIP 2012

作者： Li, Ning Zhuang, Fuzhen He, Qing Shi, Zhongzhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China Graduate University Chinese Academy of Sciences Beijing China Key Lab. of Machine Learning and Computational Intelligence College of Mathematics and Computer Science Hebei University Baoding China

ISBN: (纸本)9783642328909

PLSA(Probabilistic Latent Semantic Analysis) is a popular topic modeling technique for exploring document collections. Due to the increasing prevalence of large datasets, there is a need to improve the scalab.lity of computation in PLSA. In this paper, we propose a parallel PLSA algorithm called PPLSA to accommodate large corpus collections in the MapReduce framework. Our solution efficiently distributes computation and is relatively simple to implement. © 2012 IFIP International Federation for Information processing.

关键词： MapReduce

来源：评论

学校读者我要写书评

暂无评论

A multi-sensor helmet to capture rare singing, an intangible cultural heritage study 10

A multi-sensor helmet to capture rare singing, an intangible...

引用

10th International Seminar on Speech Production, ISSP 2014

作者： Al Kork, S.K. Jaumard-Hakoun, A. Adda-Decker, M. Amelot, A. Buchman, L. Chawah, P. Dreyfus, G. Fux, T. Pillot-Loiseau, C. Roussel, P. Stone, M. Xu, K. Denby, B. Université Pierre Marie Curie Paris France Signal Processing and Machine Learning Lab ESPCI Paris-Tech Paris France Phonetics and Phonology Laboratory LPP-CNRS UMR7018 University Paris3 Sorbonne Nouvelle France Vocal Tract Visualization Lab University of Maryland Dental School Baltimore United States

A portable helmet based system has been developed to capture motor behavior during singing and other oral-motor functions in a non-lab.ratory experimental environment. The system, based on vocal tract sensing methods developed for speech production and recognition, consists of a lightweight "hyper-helmet" containing an ultrasonic (US) transducer to capture tongue movement, a video camera for the lips, and a microphone, coupled with a further sensor suite including an electroglottograph (EGG), nose-mounted accelerometer, and respiration sensor. The system has been tested on two rare, endangered singing musical styles, Corsican "Cantu in Paghjella", and Byzantine hymns from Mount Athos, Greece. The versatility of the approach is furthermore demonstrated by capturing a contemporary singing style known as "Human Beat Box." © 2014 10th International Seminar on Speech Production, ISSP 2014. All rights reserved.

关键词： Ultrasonics

来源：评论

学校读者我要写书评

暂无评论

Toward big data in QSAR/QSPR

Toward big data in QSAR/QSPR

引用

IEEE Workshop on machine learning for signal processing

作者： A. Duprat J.L. Ploix F. Dioury G. Dreyfus ESPCI ParisTech SIGnal processing and MAchine learning (SIGMA) lab Paris France Cnam Equipe Chimie Moléculaire Laboratoire CMGPCM Paris France

We investigate a prospective path to processing “big data” in the field of computer-aided drug design, motivated by the expected increase of the size of availab.e databases. We argue that graph machines, which exempt the designer of a predictive model from handcrafting, selecting and computing ad hoc molecular descriptors, may open a way toward efficient model design procedures. We recall the principle of graph machines, which perform predictions directly from the molecular structure described as a graph, without resorting to descriptors. We discuss scalab.lity issues in the present implementation of graph machines, and we describe an application to the prediction of an important thermodynamic property of contrast agents for MRI imaging.

关键词： Training Databases Drugs Computational modeling Magnetic resonance imaging Neural networks Standards

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：