High frequency oscillations(HFOs) have been acknowledged as a putative biomarker of epileptic seizure onset zones(SOZs). Accurate detection of HFOs is significant for the preoperative localization of epileptic SOZs. I...
详细信息
High frequency oscillations(HFOs) have been acknowledged as a putative biomarker of epileptic seizure onset zones(SOZs). Accurate detection of HFOs is significant for the preoperative localization of epileptic SOZs. In this paper, a new method is proposed to automatically detect ripples(Rs) and fast ripples(FRs) from intracranial electroencephalography(iEEG)in epilepsy. A moving-window technique is utilized to segment the filtered signals which are obtained by filtering the raw iEEG signals using two Chebyshev band-pass filters. Two stacked sparse autoencoder(SSAE) models are proposed to automatically detect Rs and FRs, respectively. By optimizing the parameters of the two SSAE models, our method yields higher sensitivity(88.9±2.4% for Rs and 83.2±2.5% for FRs) and higher specificity(92.3±2.8% for Rs and 86.1±2.8% for FRs) than other three methods do.
Deep learning techniques have been gaining prominence in the research world in the past years;however, the deep learning algorithms have high computational cost, making them hard to be used to several commercial appli...
详细信息
Deep learning techniques have been gaining prominence in the research world in the past years;however, the deep learning algorithms have high computational cost, making them hard to be used to several commercial applications. On the other hand, new alternatives have been studied and some methodologies focusing on accelerating complex algorithms including those based on reconfigurable hardware has been showing significant results. Therefore, the objective of this paper is to propose a neural network hardware implementation to be used in deep learning applications. The implementation was developed on a field-programmable gate array (FPGA) and supports deep neural network (DNN) trained with the stacked sparse autoencoder (SSAE) technique. In order to allow DNNs with several inputs and layers on the FPGA, the systolic array technique was used in the entire architecture. Details regarding the designed implementation were evidenced, as well as the hardware area occupation and the processing time for two different implementations. The results showed that both implementations achieved high throughput enabling deep learning techniques to be applied for problems with large data amounts.
Most leaf chlorophyll predictions based on digital image analyzes are modeled by manual extraction features and traditional machine learning methods. In this study, a series of image preprocessing operations, such as ...
详细信息
Most leaf chlorophyll predictions based on digital image analyzes are modeled by manual extraction features and traditional machine learning methods. In this study, a series of image preprocessing operations, such as image threshold segmentation, noise processing, and background separation, were performed based on digital image processing technology to remove the background and noise interference. The intrinsic features of the leaf RGB image were automatically learned through a stacked sparse autoencoder (SSAE) network to obtain concise data features. Finally, a prediction model between the RGB image features of a leaf and its SPAD value (arbitrary units) was established to predict the chlorophyll content in the plant leaf. The results show that the accuracy and automation of the detection of chlorophyll content of the deep neural network in this study are higher than those of traditional machine learning methods.
Magnetic resonance imaging (MRI) is employed in medical treatment broadly, due to the quick development of computer technology. It is beneficial to classify the pathological brain images into healthy or other differen...
详细信息
Magnetic resonance imaging (MRI) is employed in medical treatment broadly, due to the quick development of computer technology. It is beneficial to classify the pathological brain images into healthy or other different categories automatically and accurately. This work aims to generate a pathological brain detecting system to classify the pathological brain images into five different categories of healthy;cerebrovascular disease;neoplastic disease;degenerative disease;and inflammatory disease. Our proposed method can be composed of the following several steps: First, we used data augmentation technology to deal with unbalanced distribution of the dataset. Then, we used deep stacked sparse autoencoder with minibatch scaled conjugate gradient to train the network, and the softmax layer is used as the classifier. As a result, the accuracy of our deep stacked sparse autoencoder over the test set is 98.6%. The prediction time of each image in test stage is only 0.070s. Our experiment will be a powerful proof of the effectiveness of our proposed method that based on deep stacked sparse autoencoder.
Recently, many deep learning methods are applied with the spatial information to learn features for polarimetric synthetic aperture radar (PolSAR) image classification. However, without considering the multi-scale inf...
详细信息
Recently, many deep learning methods are applied with the spatial information to learn features for polarimetric synthetic aperture radar (PolSAR) image classification. However, without considering the multi-scale information, the classification performance of these methods are limited. Hence, this paper proposes a multi-scale feature extraction method based on stacked sparse autoencoder (SSAE), named the multi-scale SSAE (MS-SSAE), to improve the classification performance. This method extracts the deep multi-scale features by a two-stage framework. In the first stage, the SSAE uses training data at different scales to extract the multi-scale features. Then, a 1-D average pooling strategy is proposed to reduce the feature dimensionality at the second stage. Therefore, the MS-SSAE can capture discriminative multi-scale features. The experimental results certify that the MS-SSAE can not only improve the classification accuracy, but also remain the details in the image. (C) 2019 Elsevier B.V. All rights reserved.
Combustion instability is a well-known problem in the combustion processes and closely linked to lower combustion efficiency and higher pollutant emissions. Therefore, it is important to monitor combustion stability f...
详细信息
Combustion instability is a well-known problem in the combustion processes and closely linked to lower combustion efficiency and higher pollutant emissions. Therefore, it is important to monitor combustion stability for optimizing efficiency and maintaining furnace safety. However, it is difficult to establish a robust monitoring model with high precision through traditional data-driven methods, where prior knowledge of labeled data is required. This study proposes a novel approach for combustion stability monitoring through stacked sparse autoencoder based deep neural network. The proposed stacked sparse autoencoder is firstly utilized to extract flame representative features from the unlabeled images, and an improved loss function is used to enhance the training efficiency. The extracted features are then used to identify the classification label and stability index through clustering and statistical analysis. Classification and regression models incorporating the stacked sparse autoencoder are established for the qualitative and quantitative characterization of combustion stability. Experiments were carried out on a gas combustor to establish and evaluate the proposed models. It has been found that the classification model provides an F-1-score of 0.99, whilst the R-squared of 0.98 is achieved through the regression model. Results obtained from the experiments demonstrated that the stacked sparse autoencoder model is capable of extracting flame representative features automatically without having manual interference. The results also show that the proposed model provides a higher prediction accuracy in comparison to the traditional data-driven methods and also demonstrates as a promising tool for monitoring the combustion stability accurately.
Lip feature extraction from human mouth image plays an essential role in visual speech recognition applications. This paper presents a lip feature extraction algorithm based on Local Binary Patterns (LBP) and stacked ...
详细信息
ISBN:
(纸本)9783030020538;9783030020521
Lip feature extraction from human mouth image plays an essential role in visual speech recognition applications. This paper presents a lip feature extraction algorithm based on Local Binary Patterns (LBP) and stacked sparse autoencoders (SSAE). First, LBP texture features are extracted from lip images. Then SSAE uses greedy unsupervised learning to extract high-level features. At last, we improve the performance of overall system by fine-tuning and input the extracted features into the Softmax classifier. Compared with traditional methods, the model proposed in this paper has higher classification accuracy and more applicability.
Marine aquaculture plays an important role in marine economic, which distributes widely around the coast. Using satellite remote sensing monitoring, it can achieve large scale dynamic monitoring. As a classic model of...
详细信息
ISBN:
(数字)9783030228088
ISBN:
(纸本)9783030228088;9783030228071
Marine aquaculture plays an important role in marine economic, which distributes widely around the coast. Using satellite remote sensing monitoring, it can achieve large scale dynamic monitoring. As a classic model of deep learning, stacked sparse autoencoder (SSAE) has the advantages of simple model and self-learning of features. Nonlocal spatial information is utilized to assist SSAE construct NSSAE to improve the precision in this paper. Experimental results demonstrate the superiority of nonlocal SSAE methods on marine target recognition.
An accurate vertebrae segmentation in the spine is an essential pre-requisite in many applications of image-based spine assessment, surgical planning, clinical diagnostic treatment, and biomechanical modeling. In this...
详细信息
ISBN:
(数字)9781510630765
ISBN:
(纸本)9781510630765
An accurate vertebrae segmentation in the spine is an essential pre-requisite in many applications of image-based spine assessment, surgical planning, clinical diagnostic treatment, and biomechanical modeling. In this paper, we present the stacked sparse autoencoder (SSAE) model for the segmentation of vertebrae from CT images. After the preprocessing step, we extracted overlapped patches from the vertebrae CT images as the inputs of our proposed model. The SSAE model was trained in an unsupervised way to learn high-level features from the input pixels of the unlabeled images patch. To improve the discriminability of the learned features, we further refined the feature representation in a supervised fashion and fine-tuned the whole model by using the feedforward neural network parameters for classifying the overlapped patches. We then validated our model on a publicly available MICCAI CSI2014 dataset and found that our model outperforms the other state-of-the-art methods.
Nowadays, the prediction of industry components’ remaining useful life(RUL) has already become a hot topic. In this paper, a RUL prediction method based on stacked sparse autoencoder(SAE) and echo state network(...
详细信息
Nowadays, the prediction of industry components’ remaining useful life(RUL) has already become a hot topic. In this paper, a RUL prediction method based on stacked sparse autoencoder(SAE) and echo state network(ESN) is ***(AE) is an unsupervised learning method that can be used for feature extraction to obtain a health index(HI). To enhance the performance of the HI, a sparse constraint is added and a stacked structure is used to increase depth. The RUL of the industry components is then predicted using a method that maps directly to the RUL value based on the health factor curve. With the capability of encapsulating dynamic time behavior and saving historical information of input data, ESN is selected as the prediction network. The proposed method is verified using the C-MPASS dataset. The experimental results show that the method has better performance than the stacked AE based method.
暂无评论