Depression is one of the most common mental health problems, which can lead to significant mental disorders and suicidal behavior. To diagnose depression levels, patients with depressive disorders are required to comp...
详细信息
ISBN:
(纸本)9781665438759
Depression is one of the most common mental health problems, which can lead to significant mental disorders and suicidal behavior. To diagnose depression levels, patients with depressive disorders are required to complete self-assessment questionnaires. However, many depressed patients are misdiagnosed in clinical practice due to patients' missing data. In this paper, we introduce, APD, a novel data-driven approach based on autoencoder to predict the missing responses accurately. Inspired by existing autoencoder-based recommender systems, our autoencoder is based on collaborative filtering, which estimates unobserved data by cooperation with other patients' responses. Experimental results show that the proposed autoencoder-based prediction system outperforms the averaging and the linear models. We demonstrate that this model can be used to predict patients' depression status with a low error of 2.85%.
Temporal Convolutional autoencoders are used as feature extractors to project time series onto a latent space where similarity detection can be easily performed. This model can generate accurate descriptors of the tem...
详细信息
ISBN:
(纸本)9781665403696
Temporal Convolutional autoencoders are used as feature extractors to project time series onto a latent space where similarity detection can be easily performed. This model can generate accurate descriptors of the temporal profile of the input time-series. We apply this algorithm to PolSAR S1 uncoherent SAR time series where the model learns highly discriminative data representations. This reduction method is compared to others such as PCA or Temporal Averaging and is shown to outperform them when leveraging the learnt representation using K-Means clustering.
Fault detection is one of the most challenging tasks in industrial applications, which aims at identifying the faulty condition deviating from the normal condition of the machine. In this work, a fault detection metho...
详细信息
ISBN:
(纸本)9781665433860
Fault detection is one of the most challenging tasks in industrial applications, which aims at identifying the faulty condition deviating from the normal condition of the machine. In this work, a fault detection method is proposed based on autoencoders and online sequential extreme learning machines (OS-ELM). The autoencoder is employed for high-level feature extraction from the monitoring signal and the OS-ELM is developed based on features extracted from signals of normal condition. The fault detection is performed based on i) the updating of OS-ELM using the newly collected data;U) the quantification of the model modification. The data collected under the faulty condition is expected to significantly modify the OS-ELM model. The proposed fault detection method is validated considering a benchmark bearing case study.
Hyperspectral unmixing is an important tool to learn the material constitution and distribution of a scene. Model-based unmixing methods depend on well-designed iterative optimization algorithms, which is usually time...
详细信息
ISBN:
(纸本)9781728176055
Hyperspectral unmixing is an important tool to learn the material constitution and distribution of a scene. Model-based unmixing methods depend on well-designed iterative optimization algorithms, which is usually time consuming. Learning-based methods perform unmixing in a data-driven manner but heavily rely on the quality and quantity of the training samples due to the lack of physical interpretability. In this paper, we combine the advantages of both model-based and learning-based methods and propose a nonnegative matrix factorization (NMF) inspired sparse autoencoder (NMF-SAE) for hyperspectral unmixing. NMF-SAE consists of an encoder and a decoder, both of which are constructed by unrolling the iterative optimization rules of L-1 sparsity-constrained NMF for the linear spectral mixture model. All parameters in our method are obtained by end-to-end training in a data-driven manner. Our network is not only physically interpretable and flexible but also has higher learning capacity with fewer parameters. Experimental results on both synthetic and real-world data demonstrate that our method is capable of producing desirable unmixing results when compared against several alternative approaches.
Automated visual defect detection on textile products under unconstrained setting is a much sought-after, and at the same time a challenging problem. In general, textile products are structurally complex and highly va...
详细信息
ISBN:
(纸本)9783030879860;9783030879853
Automated visual defect detection on textile products under unconstrained setting is a much sought-after, and at the same time a challenging problem. In general, textile products are structurally complex and highly varied in design, which makes the development of a generalized approach using conventional image processing methods impossible. Deep supervised machine learning models have been very successful on similar problems but cannot be applied in this use-case due to lack of annotated data. This paper demonstrates a novel automated approach which still leverages on the ability of deep learning models to capture complex features on the textured and colored fabric, but in an unsupervised manner. Specifically, deep autoencoders are applied to capture the complex features, which are further processed by image processing techniques like thresholding and blob detection, subsequently leading to detection of defects in the images.
System logs produced by modern computer systems are valuable resources for detecting anomalies, debugging performance issues, and recovering application failures. With the increasing scale and complexity of the log da...
详细信息
ISBN:
(数字)9783030821531
ISBN:
(纸本)9783030821531;9783030821524
System logs produced by modern computer systems are valuable resources for detecting anomalies, debugging performance issues, and recovering application failures. With the increasing scale and complexity of the log data, manual log inspection is infeasible and man-power expensive. In this paper, we proposed LogAttn, an autoencoder model that combines an encoder-decoder structure with an attention mechanism for unsupervised log anomaly detection. The unstructured normal log data is proceeded by a log parser that uses a semantic analyse and clustering algorithm to parse log data into a sequence of event count vectors and semantic vectors. The encoder combines deep neural networks with an attention mechanism that learns the weights of different features to form a latent feature representation, which is further used by a decoder to reconstruct the log event sequence. If the reconstruction error is above a predefined threshold, it detects an anomaly in the log sequence and reports the result to the administrator. We conduct extensive experiments based on three real-world log datasets, which show that LogAttn achieves the best comprehensive performance compared to the state-of-the-art methods.
Financial markets are noisy learning environments. We propose an approach that regularizes the Temporal Convolutional Network using a supervised autoencoder, which we term the Supervised Temporal autoencoder (STAE). W...
详细信息
ISBN:
(纸本)9781665424639
Financial markets are noisy learning environments. We propose an approach that regularizes the Temporal Convolutional Network using a supervised autoencoder, which we term the Supervised Temporal autoencoder (STAE). We show that the addition of the auxiliary reconstruction task is beneficial to the primary supervised learning task in the context of stock return time-series forecasting. We also show that STAE is able to learn features directly from transformed price series, alleviating the need for handcrafted features. The autoencoder also improves interpretability as users can observe output of the decoder and inspect features retained by the network.
Network-wide traffic prediction is more effective for implementing traffic management control than traffic prediction for a single road. In order to improve the efficiency of network traffic forecasting, this research...
详细信息
ISBN:
(纸本)9781728189956
Network-wide traffic prediction is more effective for implementing traffic management control than traffic prediction for a single road. In order to improve the efficiency of network traffic forecasting, this research proposes a hybrid machine learning-based model, the autoencoder-VAR (AE-VAR), which takes traffic time series from all locations of interest as input and performs predictions for network-wide locations simultaneously. Firstly, the autoencoder is used to extract the essential features of the original data, retain the spatial-temporal dynamic effects between traffic flows and exclude random noises as much as possible. Then, the extracted feature time series are modeled and predicted with a VAR model at a lower dimension. Finally, the predicted features are projected back to the original data space. This methodology can take into account interactive dynamics of traffic flows between adjacent roads within the entire network with a less complicated model structure than many existing models. The empirical study on an urban road network using ground truth data indicates that the proposed AE-VAR model can effectively improve the accuracy of traffic predictions at network level. The proposed model structure is an efficient approach for network-scale traffic prediction.
This work proposes a new ultra low-power fault detection system, suitable for extreme edge or in-sensor computing. The system is composed of a hybrid HW/SW architecture: a hardware auto-encoder (AE) is always on at th...
详细信息
ISBN:
(纸本)9781728182810
This work proposes a new ultra low-power fault detection system, suitable for extreme edge or in-sensor computing. The system is composed of a hybrid HW/SW architecture: a hardware auto-encoder (AE) is always on at the edge for anomaly detection (AD), and of a software convolutional neural network (CNN) is activated only if the anomaly is detected for its classification. To achieve low area and energy requirements, the AE exploits an original partially binarization scheme, while the CNN shares the feature extraction module with the AE. The implementation of the AE on a Xilinx Artix-7 FPGA demonstrates that it is capable to manage in real-time sensors with a maximum Output Data Rate (ODR) of 365 kHz with a power dissipation of 122 mW. Best synthesis results with TSMC CMOS 65 nm standard cells show a power consumption of 138 mu W/MHz and an area occupation of 0.49 mm(2) when real-time operations are set, enabling the possibility to integrate the complete HW accelerator in the auxiliary circuitry that typically equips inertial MEMS and on the same die. Comparisons with the current literature show that the proposed system obtains state-of-the-art performances in terms of accuracy and compactness.
This work addresses the problem of hyperspectral data compression and compares the reconstruction accuracy for different compression rates. Through data compression, the enormous amount of data created by hyperspectra...
详细信息
ISBN:
(数字)9781510645691
ISBN:
(纸本)9781510645691;9781510645684
This work addresses the problem of hyperspectral data compression and compares the reconstruction accuracy for different compression rates. Through data compression, the enormous amount of data created by hyperspectral sensors can be transmitted effectively. Remote sensing-related applications such as disaster management, land cover classification, and object recognition are improved with real-time information. We propose a 1D-Convolutional autoencoder structure for lossy hyperspectral data compression and the necessary adjustments for realizing compression rates of C-R = 4,C-R = 8,C-R = 16, and C-R = 32. Unlike many other contributions, we not only evaluate the reconstruction accuracy based on standard metrics like Signal to Noise Ratio and Spectral Angle Mapper but also on a target application, namely land cover classification. The reconstruction accuracy of the 1D-Convolutional autoencoder is compared to machine learning-based lossy compression methods, namely Deep autoencoder, Nonlinear Principal Component Analysis, and the Principal Component Analysis. The compression performances are compared using two data sets with different amounts of spectral signatures. The 1D-Convolutional autoencoder performance surpasses the benchmark methods for all compression rates using the standard metrics. In addition, the 1D-Convolutional autoencoder achieves the highest classification results for the land cover classification for all compression rates and is able to compress hyperspectral data efficiently. Furthermore, the robustness and generalization capability of the 1D-Convolutional autoencoder is demonstrated by using unknown data for the evaluation.
暂无评论