2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)最新文献_第5页

A Copula-Driven Unsupervised Learning Framework for Anomaly Detection with Multivariate Heterogeneous Data 多元异构数据异常检测的copula驱动无监督学习框架

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596359

Swaroop Damodaran, Ram Padmanabhan, R. Maahin, Sanjeev Gurugopinath

{"title":"A Copula-Driven Unsupervised Learning Framework for Anomaly Detection with Multivariate Heterogeneous Data","authors":"Swaroop Damodaran, Ram Padmanabhan, R. Maahin, Sanjeev Gurugopinath","doi":"10.1109/mlsp52302.2021.9596359","DOIUrl":"https://doi.org/10.1109/mlsp52302.2021.9596359","url":null,"abstract":"We consider the problem of anomaly detection with heterogeneous and correlated multivariate data, with no assumption on the knowledge of statistical correlation. First, we use a copula-based approach to measure the statistical correlation among the modalities. Next, we employ an unsupervised learning (UL) framework for anomaly detection, using data points sampled from the copula-based joint distribution. In particular, we consider Gaussian, R-Vine, D-Vine and C-Vine copula techniques, with isolation forest, one-class SVM, local outlier factor, elliptic envelope and autoencoder UL algorithms, for our extensive study. Through Monte Carlo simulations and an experimental study on the IEEE signal processing cup – 2020 dataset, we show that the proposed framework significantly outperforms the direct training method, in terms of detection accuracy. Furthermore, we show that the C-Vine-based autoencoder technique yields the best performance in comparison with other techniques, in terms of area under the receiver operating characteristics curve, and accuracy of detecting anomalies.","PeriodicalId":156116,"journal":{"name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127389559","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Lightweight Forest Fire Detection Based on Deep Learning 基于深度学习的轻量级森林火灾探测

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596409

Rui Fan, Mingtao Pei

引用次数: 9

Message Passing-Based Inference in the Gamma Mixture Model Gamma混合模型中基于消息传递的推理

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596329

Albert Podusenko, B. V. Erp, Dmitry V. Bagaev, Ismail Senöz, B. Vries

引用次数: 6

A Neural Beamforming Network for B-Format 3D Speech Enhancement and Recognition 用于b格式三维语音增强和识别的神经波束形成网络

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596418

Xinlei Ren, Lianwu Chen, Xiguang Zheng, Chenglin Xu, Xu Zhang, Chen Zhang, Liang Guo, Bin Yu

引用次数: 17

Convolutional Dense Neural Network Based Spirometry Variable FVC Prediction Using Sustained Phonations 基于卷积密集神经网络的呼吸量测量变量FVC持续发声预测

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596159

Shivani Yadav, D. Gope, U. Krishnaswamy, P. Ghosh

{"title":"Convolutional Dense Neural Network Based Spirometry Variable FVC Prediction Using Sustained Phonations","authors":"Shivani Yadav, D. Gope, U. Krishnaswamy, P. Ghosh","doi":"10.1109/mlsp52302.2021.9596159","DOIUrl":"https://doi.org/10.1109/mlsp52302.2021.9596159","url":null,"abstract":"Spirometry is a lung function test used to diagnose and monitor lung diseases like asthma, pneumonia, chronic obstructive pulmonary disease, etc. Spirometry measures forced vital capacity (FVC), forced expiratory volume in 1 sec (FEV1), and their ratio to determine lung health. Spirometry is very time-consuming, strenuous, and requires proper training. Alternate methods based on voice for diagnosis and monitoring of lung health are promising because they are faster, easy to do, and require minimal training. Non-speech sounds, namely, cough and wheeze, have been used to predict spirometry variables, but the role of speech sounds that occur in natural speaking for a similar task has not been explored. In this work, the spirometry variable, FVC has been predicted from sustained phonations of vowel sounds using a convolutional dense neural network (CDNN). Mel-spectrogram has been used as a feature. An experiment conducted using 160 subjects indicates, /i/ is the best sound and /u:/ is worst for the prediction task with an average Mean Absolute Error of 0.67l(±. 07l) and 0.70l(± 0.13l) among all sustained phonations of vowels sounds considered in this work.","PeriodicalId":156116,"journal":{"name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","volume":"284 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132278241","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fast Subspace Clustering Algorithm with Efficient Similarity-Constrained Sampling for Hyperspectral Images 高光谱图像快速子空间聚类算法与高效相似约束采样

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596507

Jhon Lopez, Carlos Hinojosa, H. Arguello

引用次数: 0

Dynamic Graph Convolutional Network: A Topology Optimization Perspective 动态图卷积网络:拓扑优化视角

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596206

Bowen Deng, Aimin Jiang

{"title":"Dynamic Graph Convolutional Network: A Topology Optimization Perspective","authors":"Bowen Deng, Aimin Jiang","doi":"10.1109/mlsp52302.2021.9596206","DOIUrl":"https://doi.org/10.1109/mlsp52302.2021.9596206","url":null,"abstract":"Recently, graph convolutional networks(GCNs) have drawn increasing attention in many domains, e.g., social networks, recommendation systems. It's known that, in the task of graph node classification, inter-class edges connecting nodes from different categories often degrade the GCN model performance. On the other hand, a stronger intra-class connection in terms of the edge number and edge weights is always beneficial to node classification. Most existing GCN models assume that the topology and edge weights of the underlying graph are both fixed. However, real-world networks are often noisy and incomplete. To take into account such uncertainty in graph topology, we propose in this paper a dynamic graph convolution network (DyGCN), where edge weights are treated as learnable parameters. A novel adaptive edge dropping (AdaDrop) strategy is developed for DyGCN, such that even graph topology can be optimized. DyGCN is also a flexible architecture that can be readily combined with other deep GCN models to cope with the oversmoothness encountered when the network goes very deep. Experimental results demonstrate that the proposed DyGCN and its deep variants can achieve competitive classification accuracy in many datasets.","PeriodicalId":156116,"journal":{"name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125786317","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Understanding Linear Style Transfer Auto-Encoders 理解线性风格传输自动编码器

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596412

Ian Pradhan, Siwei Lyu

引用次数: 1

Model Selection of Kernel Ridge Regression for Extrapolation 外推核岭回归的模型选择

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596089

A. Tanaka, Masanari Nakamura, H. Imai

引用次数: 0

Tracking of Quantized Signals Based on Online Kernel Regression 基于在线核回归的量化信号跟踪

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596115

Emilio Ruiz Moreno, B. Beferull-Lozano

{"title":"Tracking of Quantized Signals Based on Online Kernel Regression","authors":"Emilio Ruiz Moreno, B. Beferull-Lozano","doi":"10.1109/mlsp52302.2021.9596115","DOIUrl":"https://doi.org/10.1109/mlsp52302.2021.9596115","url":null,"abstract":"Kernel-based approaches have achieved noticeable success as non-parametric regression methods under the framework of stochastic optimization. However, most of the kernel-based methods in the literature are not suitable to track sequentially streamed quantized data samples from dynamic environments. This shortcoming occurs mainly for two reasons: first, their poor versatility in tracking variables that may change unpredictably over time, primarily because of their lack of flexibility when choosing a functional cost that best suits the associated regression problem; second, their indifference to the smoothness of the underlying physical signal generating those samples. This work introduces a novel algorithm constituted by an online regression problem that accounts for these two drawbacks and a stochastic proximal method that exploits its structure. In addition, we provide tracking guarantees by analyzing the dynamic regret of our algorithm. Finally, we present some experimental results that support our theoretical analysis and show that our algorithm has a favorable performance compared to the state-of-the-art.","PeriodicalId":156116,"journal":{"name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129889758","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3