Electronic medical records (EMRs) support the development of machine learning algorithms for predicting disease incidence, patient response to treatment, and other healthcare events. But so far most algorithms have be...
详细信息
Electronic medical records (EMRs) support the development of machine learning algorithms for predicting disease incidence, patient response to treatment, and other healthcare events. But so far most algorithms have been centralized, taking little account of the decentralized, non-identically independently distributed (non-IID), and privacy-sensitive characteristics of EMRs that can complicate data collection, sharing and learning. To address this challenge, we introduced a community-based federated machine learning (CBFL) algorithm and evaluated it on non-IID ICU EMRs. Our algorithm clustered the distributed data into clinically meaningful communities that captured similar diagnoses and geographical locations, and learnt one model for each community. Throughout the learning process, the data was kept local at hospitals, while locally-computed results were aggregated on a server. Evaluation results show that CBFL outperformed the baseline federated machine learning (FL) algorithm in terms of Area Under the Receiver Operating Characteristic Curve (ROC AUC), Area Under the Precision-Recall Curve (PR AUC), and communication cost between hospitals and the server. Furthermore, communities' performance difference could be explained by how dissimilar one community was to others.
Facing the very high-resolution( VHR) image classification problem,a feature extraction and fusion framework is presented for VHR panchromatic and multispectral image classification based on deep learning techniques. ...
详细信息
Facing the very high-resolution( VHR) image classification problem,a feature extraction and fusion framework is presented for VHR panchromatic and multispectral image classification based on deep learning techniques. The proposed approach combines spectral and spatial information based on the fusion of features extracted from panchromatic( PAN) and multispectral( MS) images using sparse autoencoder and its deep version. There are three steps in the proposed method,the first one is to extract spatial information of PAN image,and the second one is to describe spectral information of MS image. Finally,in the third step,the features obtained from PAN and MS images are concatenated directly as a simple fusion feature. The classification is performed using the support vector machine( SVM) and the experiments carried out on two datasets with very high spatial resolution. MS and PAN images from WorldView-2 satellite indicate that the classifier provides an efficient solution and demonstrate that the fusion of the features extracted by deep learning techniques from PAN and MS images performs better than that when these techniques are used separately. In addition,this framework shows that deep learning models can extract and fuse spatial and spectral information greatly,and have huge potential to achieve higher accuracy for classification of multispectral and panchromatic images.
Each Brazilian Deputy receives a quota of money quota to cover the politician activity expenses, besides their salary. The amount of money reserved for that quota can sum up to almost 1 billion of Brazilian currency (...
详细信息
ISBN:
(纸本)9781538614174
Each Brazilian Deputy receives a quota of money quota to cover the politician activity expenses, besides their salary. The amount of money reserved for that quota can sum up to almost 1 billion of Brazilian currency (approximately 300 million US Dollars) in a 4 year legislature. Civic society is using that data to perform independent auditing to verify expenses that are against the rules. This article presents the application of deep autoencoders to identify anomalies in that data. The anomalies found indicate new suspicious expenses and several data quality problems in the data opened to the society.
In this study, we tried to find a solution for inpainting problem using deep convolutional autoencoders. A new training approach has been proposed as an alternative to the Generative Adversarial Networks. The neural n...
详细信息
ISBN:
(纸本)9781509064946
In this study, we tried to find a solution for inpainting problem using deep convolutional autoencoders. A new training approach has been proposed as an alternative to the Generative Adversarial Networks. The neural network that designed for inpainting takes an image, which the certain part of its center is extracted, as an input then it attempts to fill the blank region. During the training phase, a distinct deep convolutional neural network is used and it is called Advisor Network. We show that the features extracted from intermediate layers of the Advisor Network, which is trained on a different dataset for classification, improves the performance of the autoencoder.
The field of similarity based image retrieval has experienced a game changer lately. Hand crafted image features have been vastly outperformed by machine learning based approaches. Deep learning methods are very good ...
详细信息
ISBN:
(纸本)9781450353335
The field of similarity based image retrieval has experienced a game changer lately. Hand crafted image features have been vastly outperformed by machine learning based approaches. Deep learning methods are very good at finding optimal features for a domain, given enough data is available to learn from. However, hand crafted features are still means to an end in domains, where the data either is not freely available, i.e. because it violates privacy, where there are commercial concerns, or where it cannot be transmitted, i.e. due to bandwidth limitations. Moreover, we have to rely on hand crafted methods whenever neural networks cannot be trained effectively, e.g. if there is not enough training data. In this paper, we investigate a particular approach to combine hand crafted features and deep learning to (i) achieve early fusion of off the shelf hand-crafted global image features and (ii) reduce the overall number of dimensions to combine both worlds. This method allows for fast image retrieval in domains, where training data is sparse.
This paper presents several geometrically motivated techniques for the visualization of high-dimensional biological data sets. The Grassmann manifold provides a robust framework for measuring data similarity in a subs...
详细信息
This paper presents several geometrically motivated techniques for the visualization of high-dimensional biological data sets. The Grassmann manifold provides a robust framework for measuring data similarity in a subspace context. Sparse radial basis function classification as a visualization technique leverages recent advances in radial basis function learning via convex optimization. In the spirit of deep belief networks, supervised centroid-encoding is proposed as a way to exploit class label information. These methods are compared to linear and nonlinear principal component analysis (autoencoders) in the context of data visualization;these approaches may perform poorly for visualization when the variance of the data is spread across more than three dimensions. In contrast, the proposed methods are shown to capture significant data structure in two or three dimensions, even when the information in the data lives in higher dimensional subspaces. To illustrate these ideas, the visualization techniques are applied to gene expression data sets that capture the host immune system's response to infection by the Ebola virus in non-human primate and collaborative cross mouse. (C) 2017 Published by Elsevier Inc.
In this paper, we propose a new supervised monaural source separation based on autoencoders. We employ the autoencoder for the dictionary training such that the nonlinear network can encode the target source with high...
详细信息
ISBN:
(纸本)9781509041176
In this paper, we propose a new supervised monaural source separation based on autoencoders. We employ the autoencoder for the dictionary training such that the nonlinear network can encode the target source with high expressiveness. The dictionary is trained by each target source without the mixture signal, which makes the system independent from the context where the dictionaries will be used. In separation process, the decoder portions of the trained autoencoders are used as dictionaries to find the activations in a iterative manner such that a summation of the decoder outputs approximates the original mixture. The results of the instruments source separation experiments revealed that the separation performance of the proposed method was superior to that of the NMF.
We propose a deep-learning-based channel estimation technique for wireless energy transfer. Specifically, we develop a channel learning scheme using the deep autoencoder, which learns the channel state information (CS...
详细信息
We propose a deep-learning-based channel estimation technique for wireless energy transfer. Specifically, we develop a channel learning scheme using the deep autoencoder, which learns the channel state information (CSI) at the energy transmitter based on the harvested energy feedback from the energy receiver, in the sense of minimizing the mean square error (mse) of the channel estimation. Numerical results demonstrate that the proposed scheme learns the CSI very well and significantly outperforms the conventional scheme in terms of the channel estimation mse as well as the harvested energy.
A phoneme classification model has been developed for Bengali continuous speech in this experiment. The analysis was conducted using a deep neural network based classification model. In the first phase, phoneme classi...
详细信息
A phoneme classification model has been developed for Bengali continuous speech in this experiment. The analysis was conducted using a deep neural network based classification model. In the first phase, phoneme classification task has been performed using the deep-structured classification model along with two baseline models. The deep-structured model provided better overall classification accuracy than the baseline systems which were designed using hidden Markov model and multilayer Perceptron respectively. The confusion matrix of all the Bengali phonemes generated by the classification model is observed, and the phonemes are divided into nine groups. These nine groups provided better overall classification accuracy of 98.7%. In the next phase of this study, the place and manner of articulation based phonological features are detected and classified. The phonemes are regrouped into 15 groups using the manner of articulation based knowledge, and the deep-structured model is retrained. The system provided 98.9% of overall classification accuracy this time. This is almost equal to the overall classification accuracy which was observed for nine phoneme groups. But as the nine phoneme groups are redivided into 15 groups, the phoneme confusion in a single group became less which leads to a better phoneme classification model.
暂无评论