2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)最新文献_第7页

Anonymizing Motion Sensor Data Through Time-Frequency Domain 基于时频域的运动传感器数据匿名化

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596442

Pierre Rougé, A. Moukadem, A. Dieterlen, A. Boutet, Carole Frindel

{"title":"Anonymizing Motion Sensor Data Through Time-Frequency Domain","authors":"Pierre Rougé, A. Moukadem, A. Dieterlen, A. Boutet, Carole Frindel","doi":"10.1109/mlsp52302.2021.9596442","DOIUrl":"https://doi.org/10.1109/mlsp52302.2021.9596442","url":null,"abstract":"The recent development of Internet of Things (IoT) has democratized activity monitoring. Even if the data collected can be useful for healthcare, sharing this sensitive information exposes users to privacy threats and re-identification. This paper presents two approaches to anonymize the motion sensor data. The first is an extension of an earlier work based on filtering in the time-frequency plane and convolutional neural network; and the second is based on handcrafted features extracted from the zeros distribution of the time-frequency representation. The two approaches are evaluated on a public dataset to assess the accuracy of activity recognition and user re-identification. With the first approach we obtained an accuracy rate in activity recognition of 73% while limiting the identity recognition to an accuracy rate of 30% which corresponds to an activity identity ratio of 2.4. With the second approach we succeeded in improving the activity and identity ratio to 2.67 by attaining an accuracy rate in activity recognition of 80% while maintaining the re-identification rate at 30%.","PeriodicalId":156116,"journal":{"name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","volume":"3 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":"123058614","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: 2

Block-Wise Intra-Prediction of Imaging Data Based on Overfitted Neural Networks with On-Line Learning 基于在线学习的过拟合神经网络成像数据分块内预测

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596526

Victor Sanchez, Miguel Hernández-Cabronero, J. Serra-Sagristà

{"title":"Block-Wise Intra-Prediction of Imaging Data Based on Overfitted Neural Networks with On-Line Learning","authors":"Victor Sanchez, Miguel Hernández-Cabronero, J. Serra-Sagristà","doi":"10.1109/mlsp52302.2021.9596526","DOIUrl":"https://doi.org/10.1109/mlsp52302.2021.9596526","url":null,"abstract":"Block-wise intra-prediction is a key technique used by modern video codecs to reduce the amount of data to be compressed. Recently, machine learning (ML) has successfully improved block-wise intra-prediction by employing neural networks. Notwithstanding, the performance of such ML-based methods depends on the amount, quality, and relevance of the training data. Furthermore, they require signalling the learned parameters into the bitstream to be able to reconstruct the original data after decompression, thus increasing bitrates. This work proposes a novel block-wise intra-prediction strategy based on fully connected neural networks (FC-NNs) that avoids the two aforementioned shortcomings within the context of lossless compression. To do so, shallow FC-NNs are used, whose parameters are refined in an on-line manner using only the data being predicted. This allows to accurately fit the FC-NNs to the data of interest and replicate the optimization process, avoiding signaling the learned parameters. Experimental results indicate that the proposed ML-based intra-prediction strategy can outperform the intra-prediction used by modern video codecs with prediction accuracy gains of up to 7.01 dB PSNR.","PeriodicalId":156116,"journal":{"name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","volume":"222 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":"116492051","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

Opinion Recommendation Using Coverage for Adaptive Prediction 使用覆盖率进行自适应预测的意见推荐

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596474

Emmanouil Gionanidis, Constantine Kotropoulos, Myrsini Ntemi

引用次数: 0

Beyond the Bias Variance Trade-Off: A Mutual Information Trade-Off in Deep Learning 超越偏差方差权衡:深度学习中的互信息权衡

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596544

Xinjie Lan, Bin Zhu, C. Boncelet, K. Barner

引用次数: 0

A Hybrid Model Integrating LSTM and Garch for Bitcoin Price Prediction 基于LSTM和Garch的比特币价格预测混合模型

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596429

Zidi Gao, Yi He, E. Kuruoğlu

{"title":"A Hybrid Model Integrating LSTM and Garch for Bitcoin Price Prediction","authors":"Zidi Gao, Yi He, E. Kuruoğlu","doi":"10.1109/mlsp52302.2021.9596429","DOIUrl":"https://doi.org/10.1109/mlsp52302.2021.9596429","url":null,"abstract":"Due to the nonlinearity and highly volatile dynamics of the price data of cryptocurrency, classic parametric models show limited success in tracking and prediction. With the rise of deep learning recently, various researches on forecasting the price of cryptocurrency using deep neural network have reported encouraging results in the cases of low volatility. In this study, we propose a hybrid approach which combines the advantages of non-stationary parametric models such as Generalized Autoregressive Conditional Heteroskedasticity (GARCH) with the nonlinear modelling potential of Long-Short Term Memory (LSTM) neural networks. The results show that our hybrid model has a similar predictive performance in terms of MSE, MAE and RMSE but higher metric scores in precision, accuracy and F1 score under optimal hyperparameters. This study reveals that the combination of parametric models like GARCH with deep neural network may come up with better results in cryptocurrency price forecasting especially in the case of highly volatile data or when short data sequences are available. Moreover, the proposed framework can be used also in other applications where high volatility and scarcity of data are the main characteristics.","PeriodicalId":156116,"journal":{"name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","volume":"31 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":"115238005","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

Content-Based Recommendation Using Machine Learning 使用机器学习的基于内容的推荐

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596525

Yifan Tai, Zhenyu Sun, Zixuan Yao

引用次数: 7

A Deep Q-Network Based Approach for Online Bayesian Change Point Detection 基于深度q网络的在线贝叶斯变化点检测方法

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596490

Xiaochuan Ma, L. Lai, Shuguang Cui

引用次数: 4

Ambiguity-Free and Efficient Sparse Phase Retrieval from Affine Measurements Under Outlier Corruption 离群点损坏下仿射测量的无歧义高效稀疏相位恢复

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596316

Ming-Hsun Yang, Yao-Win Peter Hong, Jwo-Yuh Wu

{"title":"Ambiguity-Free and Efficient Sparse Phase Retrieval from Affine Measurements Under Outlier Corruption","authors":"Ming-Hsun Yang, Yao-Win Peter Hong, Jwo-Yuh Wu","doi":"10.1109/mlsp52302.2021.9596316","DOIUrl":"https://doi.org/10.1109/mlsp52302.2021.9596316","url":null,"abstract":"Conventional sparse phase retrieval schemes can recover sparse signals from the magnitude of linear measurements but only up to a global phase ambiguity. This work proposes a novel approach to achieve ambiguity-free signal reconstruction using the magnitude of affine measurements, where an additional bias term is used as reference for phase recovery. The proposed scheme consists of two stages, i.e., a support identification stage followed by a signal recovery stage in which the nonzero signal entries are resolved. In the noise-free case, perfect support identification is guaranteed using a simple counting rule subject to a mild condition on the signal sparsity, and the exact recovery of the nonzero signal entries can be obtained in closed-form. The proposed scheme is then extended to the sparse noise (or outliers) scenario. Perfect support identification is still ensured in this case under mild conditions on the support size of the sparse outliers. With perfect support estimation, exact signal recovery from noisy measurements can be achieved using a simple majority rule. Computer simulations using both synthetic and real-world data sets are provided to demonstrate the effectiveness of the proposed scheme.","PeriodicalId":156116,"journal":{"name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","volume":"51 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":"116911225","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

Uncertain Bayesian Networks: Learning from Incomplete Data 不确定贝叶斯网络:从不完整数据中学习

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/MLSP52302.2021.9596205

Conrad D. Hougen, L. Kaplan, F. Cerutti, A. Hero

引用次数: 1

An Improved Diracnet Convolutional Neural Network for Haze Visibility Detection 一种改进的直接卷积神经网络用于霾能见度检测

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596249

Mu Xiyu, Xu Qi, Zhang Qiang, Ren Junch, Wang Hongbin, Zhou Linyi

引用次数: 2