1
|
Dogan H, Dogan RO, Ay I, Sezen SF. DL-EDOF: Novel Multi-Focus Image Data Set and Deep Learning-Based Approach for More Accurate and Specimen-Free Extended Depth of Focus. J Imaging Inform Med 2024:10.1007/s10278-024-01076-z. [PMID: 38528289 DOI: 10.1007/s10278-024-01076-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/04/2023] [Revised: 11/09/2023] [Accepted: 11/13/2023] [Indexed: 03/27/2024]
Abstract
Depth of focus (DOF) is defined as the axial range in which the specimen stage moves without losing focus while the imaging apparatus remains stable. It may not be possible to capture an image that includes the entire specimen in focus due to the narrow DOF in microscopic systems. Extended depth of focus (EDOF) is used to overcome this limitation in microscopic systems. Although the researchers have developed so many EDOF microscope approaches, this research field still has some crucial shortcomings such as high computational costs, complexity and execution time, requiring additional equipment, low precise characterization of curves, and edges in images, varying performance depending on the specimen and microscope, using only gray levels of input images to acquire the pixel's focus values. In order to minimize these shortcomings and comprehensively analyze the performance of EDOF approaches, a novel multi-focus image data set is generated, and a deep learning-based EDOF microscope approach is proposed in this study. When compared with the state-of-art EDOF approaches, our study provides various crucial contributions such as the first EDOF approach based on unsupervised deep learning, providing more accurate and specimen-free EDOF, generating a novel multi-focus image data, not requiring any pre- or post-processing technique and acquiring the pixel's focus degrees using deep features. In order to evaluate the effectiveness of the suggested approach, 20 different EDOF approaches are applied to a multi-focus image data set containing 9 image collections (4 synthetic and 5 microscope image collections) in total. Performance analysis metrics with and without requiring a reference image are preferred to identify which EDOF microscope approach can extract more essential details from the multi-focus images for the synthetic and microscope image collections, which are Root Mean Square Error (RMSE), Peak Signal Noise Ratio (PSNR), Universal Quality Index (UQI), Correlation Coefficient (CC), Perception-based Image Quality Evaluator (PIQE), Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE), Extension of Universal Quality Index for N Images (UQIN), and Naturalness Image Quality Evaluator (NIQE). Objective and subjective analysis of this study demonstrates that unsupervised deep learning model is more efficient to transmit crucial details from multi-focus images. Moreover, the suggested EDOF microscope approach with highest PSNR, UQI, CC, UQIN and lowest RMSE, PIQE, BRISQUE, NIQE produces higher performance than the state-of-art approaches.
Collapse
Affiliation(s)
- Hulya Dogan
- Department of Software Engineering, Faculty of Engineering, Karadeniz Technical University, Trabzon, 61080, Türkiye.
- Drug and Pharmaceutical Technology Application & Research Center, Karadeniz Technical University, Trabzon, 61080, Türkiye.
| | - Ramazan Ozgur Dogan
- Department of Software Engineering, Faculty of Engineering and Natural Sciences, Gumushane University, Gumushane, 29100, Türkiye
| | - Ilyas Ay
- Drug and Pharmaceutical Technology Application & Research Center, Karadeniz Technical University, Trabzon, 61080, Türkiye
| | - Sena F Sezen
- Drug and Pharmaceutical Technology Application & Research Center, Karadeniz Technical University, Trabzon, 61080, Türkiye
- Department of Pharmacology, Faculty of Pharmacy, Karadeniz Technical University, Trabzon, 61080, Türkiye
| |
Collapse
|
2
|
Ding Y, Jia M, Zhao X, Yan X, Lee CG. Joint optimization of degradation assessment and remaining useful life prediction for bearings with temporal convolutional auto-encoder. ISA Trans 2024; 146:451-462. [PMID: 38320915 DOI: 10.1016/j.isatra.2023.12.031] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/08/2023] [Revised: 11/30/2023] [Accepted: 12/22/2023] [Indexed: 02/08/2024]
Abstract
Remaining useful life (RUL) prediction and degradation assessment are pivotal components of prognostic and health management (PHM) and represent vital tasks in the implementation of predictive maintenance for bearings. In recent years, data-driven PHM techniques for bearings have made substantial progress through the integration of deep learning methods. However, modeling the temporal dependencies inherent in raw vibration signals for both degradation assessment and RUL prediction remains a significant challenge. Hence, we propose a joint optimization architecture that uses a temporal convolutional auto-encoder (TCAE) for the degradation assessment and RUL prediction of bearings. Specifically, the architecture includes a sequence-to-sequence model to extract degradation-sensitive features from the raw signal and utilizes temporal distribution characterization (TDC) and a nonlinear regressor to determine the degradation stages and predict RUL, respectively. Our framework integrates the tasks of degradation assessment and RUL prediction in a unified, end-to-end manner, using raw signals as input, resulting in high RUL prediction accuracy (RMSE = 0.0832) on publicly available and self-built datasets. Our approach outperforms state-of-the-art methods, indicating its potential to significantly advance the field of PHM for bearings.
Collapse
Affiliation(s)
- Yifei Ding
- School of Mechanical Engineering, Southeast University, Nanjing 211189, PR China; Centre for Maintenance Optimization and Reliability Engineering, University of Toronto, Toronto M5S 3G8, Canada
| | - Minping Jia
- School of Mechanical Engineering, Southeast University, Nanjing 211189, PR China.
| | - Xiaoli Zhao
- School of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing 210014, PR China
| | - Xiaoan Yan
- School of Mechatronics Engineering, Nanjing Forestry University, Nanjing 210037, PR China
| | - Chi-Guhn Lee
- Centre for Maintenance Optimization and Reliability Engineering, University of Toronto, Toronto M5S 3G8, Canada
| |
Collapse
|
3
|
Naqvi SSA, Li Y, Uzair M. DDoS attack detection in smart grid network using reconstructive machine learning models. PeerJ Comput Sci 2024; 10:e1784. [PMID: 38259891 PMCID: PMC10803083 DOI: 10.7717/peerj-cs.1784] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/22/2023] [Accepted: 12/07/2023] [Indexed: 01/24/2024]
Abstract
Network attacks pose a significant challenge for smart grid networks, mainly due to the existence of several multi-directional communication devices coupling consumers to the grid. One of the network attacks that can affect the smart grid is the distributed denial of service (DDoS), where numerous compromised communication devices/nodes of the grid flood the smart grid network with false data and requests, leading to disruptions in smart meters, data servers, and the state estimator, ultimately effecting the services for end-users. Machine learning-based strategies show distinctive benefits in resolving the challenge of securing the network from DDoS attacks. Regardless, a notable hindrance in deploying machine learning-based techniques is the requirement of model retraining whenever new attack classes arise. Practically, disrupting the normal operations of smart grid is really discouraged. To handle this challenge effectively and detect DDoS attacks without major disruptions, we propose the deployment of reconstructive deep learning techniques. A primary benefit of our proposed technique is the minimum disruption during the introduction of a new attack class, even after complete deployment. We trained several deep and shallow reconstructive models to get representations for each attack type separately, and we performed attack detection by class-specific reconstruction error-based classification. Our technique experienced rigid evaluation via multiple experiments using two well-acknowledged standard databases exclusively for DDoS attacks, including their subsets. Later, we performed a comparative estimation of our outcomes against six methods prevalent within the same domain. Our outcomes reveal that our technique attained higher accuracy, and notably eliminates the requirement of a complete model retraining in the event of the introduction of new attack classes. This method will not only boost the security of smart grid networks but also ensure the stability and reliability of normal operations, protecting the critical infrastructure from ever-evolving network attacks. As smart grid is advancing rapidly, our approach proposes a robust and adaptive way to overcome the continuous challenges posed by network attacks.
Collapse
Affiliation(s)
- Sardar Shan Ali Naqvi
- School of Control and Computer Engineering, North China Electric Power University, Beijing, China
| | - Yuancheng Li
- School of Control and Computer Engineering, North China Electric Power University, Beijing, China
| | - Muhammad Uzair
- Department of Computer Engineering, COMSATS Institute Of Information Technology, Wah cantt, Pakistan
| |
Collapse
|
4
|
Yeganeh A, Johannssen A, Chukhrova N, Erfanian M, Azarpazhooh MR, Morovatdar N. A monitoring framework for health care processes using Generalized Additive Models and Auto-Encoders. Artif Intell Med 2023; 146:102689. [PMID: 38042610 DOI: 10.1016/j.artmed.2023.102689] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/12/2023] [Revised: 10/11/2023] [Accepted: 10/13/2023] [Indexed: 12/04/2023]
Abstract
In recent years, there has been a considerable focus on developing effective methods for monitoring health care processes. Utilizing Statistical Process Monitoring (SPM) approaches, particularly risk-adjusted control charts, has emerged as a highly promising approach for achieving robust frameworks for this aim. Considering risk-adjusted control charts, longitudinal health care process data is typically monitored by establishing a regression relationship between various risk factors (explanatory variables) and patient outcomes (response variables). While the majority of prior research has primarily employed logistic models in risk-adjusted control charts, there are more intricate health care processes that necessitate the incorporation of both parametric and nonparametric risk factors. In such scenarios, the Generalized Additive Model (GAM) proves to be a suitable choice, albeit it often introduces higher computational complexity and associated challenges. Surprisingly, there are limited instances where researchers have proposed advancements in this direction. The primary objective of this paper is to introduce an SPM framework for monitoring health care processes using a GAM over time, coupled with a novel risk-adjusted control chart driven by machine learning techniques. This control chart is implemented on a data set encompassing two stroke types: ischemic and hemorrhagic. The key focus of this study is to monitor the stability of the relationship between stroke types and predefined explanatory variables over time within this data set. Extensive simulation results, based on real data from patients with acute stroke, demonstrate the remarkable flexibility of the proposed method in terms of its detection capabilities compared to conventional approaches.
Collapse
Affiliation(s)
- Ali Yeganeh
- University of Hamburg, 20146 Hamburg, Germany.
| | | | | | - Mahdiyeh Erfanian
- Department of Statistics, Ferdowsi University of Mashhad, Mashhad, Iran.
| | - Mahmoud Reza Azarpazhooh
- Department of Neurology, Ghaem Hospital, Mashhad University of Medical Sciences (MUMS), Mashhad, Iran; Department of Clinical Neurological Sciences, Schulich School of Medicine and Dentistry, Western University, London, Ontario, Canada.
| | - Negar Morovatdar
- Clinical Research Development Unit, Imam Reza Hospital, Faculty of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran.
| |
Collapse
|
5
|
Chen B, Xu S, Xu H, Bian X, Guo N, Xu X, Hua X. Structure-aware deep clustering network based on contrastive learning. Neural Netw 2023; 167:118-128. [PMID: 37657251 DOI: 10.1016/j.neunet.2023.08.020] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/12/2023] [Revised: 07/05/2023] [Accepted: 08/12/2023] [Indexed: 09/03/2023]
Abstract
Recently, deep clustering has been extensively employed for various data mining tasks, and it can be divided into auto-encoder (AE)-based and graph neural networks (GNN)-based methods. However, existing AE-based methods fall short in effectively extracting structural information, while GNN suffer from smoothing and heterophily. Although methods that combine AE and GNN achieve impressive performance, there remains an inadequate balance between preserving the raw structure and exploring the underlying structure. Accordingly, we propose a novel network named Structure-Aware Deep Clustering network (SADC). Firstly, we compute the cumulative influence of non-adjacent nodes at multiple depths and, thus, enhance the adjacency matrix. Secondly, an enhanced graph auto-encoder is designed. Thirdly, the latent space of AE is endowed with the ability to perceive the raw structure during the learning process. Besides, we design self-supervised mechanisms to achieve co-optimization of node representation learning and topology learning. A new loss function is designed to preserve the inherent structure while also allowing for exploration of latent data structure. Extensive experiments on six benchmark datasets validate that our method outperforms state-of-the-art methods.
Collapse
Affiliation(s)
- Bowei Chen
- School of Information Engineering, Yancheng Institute of Technology, Yancheng, 224051, China.
| | - Sen Xu
- School of Information Engineering, Yancheng Institute of Technology, Yancheng, 224051, China.
| | - Heyang Xu
- School of Information Engineering, Yancheng Institute of Technology, Yancheng, 224051, China
| | - Xuesheng Bian
- School of Information Engineering, Yancheng Institute of Technology, Yancheng, 224051, China
| | - Naixuan Guo
- School of Information Engineering, Yancheng Institute of Technology, Yancheng, 224051, China
| | - Xiufang Xu
- School of Information Engineering, Yancheng Institute of Technology, Yancheng, 224051, China
| | - Xiaopeng Hua
- School of Information Engineering, Yancheng Institute of Technology, Yancheng, 224051, China
| |
Collapse
|
6
|
Chen D, Zhang H, Lin L, Zhang Z, Zeng J, Chen L, Chen X. Auto-encoder design based on the 1D-VD-CNN model for the detection of honeysuckle from unknown origin. J Pharm Biomed Anal 2023; 234:115572. [PMID: 37478551 DOI: 10.1016/j.jpba.2023.115572] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/10/2023] [Revised: 06/23/2023] [Accepted: 07/10/2023] [Indexed: 07/23/2023]
Abstract
The disadvantages of the traditional one-dimensional convolution neural network (1D-CNN) model based on honeysuckle near-infrared spectral data (NIRS) include high parameter quantity, low efficiency, and inability to identify unknown categories effectively. In this paper, we propose a one-dimensional very deep convolution neural network (1D-VD-CNN) and design an auto-encoder mechanism for detecting honeysuckle from unexplored habitats. First, the 1D-VD-CNN model uses the efficient very deep (VD) structure to replace the hidden layer structure in the traditional 1D-CNN model. The model can be directly applied to analyze one-dimensional near-infrared spectral data (NIRS). Second, combining the reconstruction error of the auto-encoder, a honeysuckle identification method considering an unknown origin is designed, which can solve the problem of high confidence in convolution neural networks by using an auto-encoder and reconstruction errors of the samples to be tested. Whether the sample is an unknown variety can be determined by comparing the corrected confidence level with the preset threshold value. The results show that the accuracy of the 1D-VD-CNN training set and test set is 100%, and the loss value converges to 0.001. Compared with the traditional 1D-CNN model, the parameters and FLOPs are reduced by nearly 71% and 8%, respectively. At the same time, compared with the NIRS analysis and the PLS-DA method, the 1D-VD-CNN model has higher efficiency and better recognition performance for honeysuckle near-infrared spectral classification. Meanwhile, the accuracy rate of the auto-encoder for the category detection mechanism of honeysuckle from an unknown origin is 98%. The model can quickly and efficiently classify honeysuckle from different habitats and detect honeysuckle from unexplored habitats.
Collapse
Affiliation(s)
- Dongying Chen
- College of Electronic Information Science, Fujian Jiangxia University, Fuzhou, Fujian 350108, China; Smart Home Information Collection and Processing on Internet of Things Laboratory of Digital Fujian, Fuzhou, Fujian 350108, China
| | - Hao Zhang
- College of Electronic Information Science, Fujian Jiangxia University, Fuzhou, Fujian 350108, China; Smart Home Information Collection and Processing on Internet of Things Laboratory of Digital Fujian, Fuzhou, Fujian 350108, China.
| | - Lingyan Lin
- College of Electronic Information Science, Fujian Jiangxia University, Fuzhou, Fujian 350108, China
| | - Zilong Zhang
- College of Electronic Information Science, Fujian Jiangxia University, Fuzhou, Fujian 350108, China
| | - Jian Zeng
- College of Electrical Engineering and Automation, Fuzhou University, Fuzhou, Fujian 350108, China
| | - Lu Chen
- Institute of Agricultural Quality Standards and Testing Technology, Shandong Academy of Agricultural Sciences, Jinan 250100, China
| | - Xiaogang Chen
- College of Electronic Information Science, Fujian Jiangxia University, Fuzhou, Fujian 350108, China; Smart Home Information Collection and Processing on Internet of Things Laboratory of Digital Fujian, Fuzhou, Fujian 350108, China
| |
Collapse
|
7
|
Li H, Gao Q, Zhang Z, Zhang Y, Ren G. Spatial and temporal prediction of secondary crashes combining stacked sparse auto-encoder and long short-term memory. Accid Anal Prev 2023; 191:107205. [PMID: 37413700 DOI: 10.1016/j.aap.2023.107205] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/11/2023] [Revised: 06/26/2023] [Accepted: 07/02/2023] [Indexed: 07/08/2023]
Abstract
Secondary crashes occur within the spatial and temporal impact area of primary crashes, resulting in traffic delays and safety problems. While most existing studies focus on the likelihood of secondary crashes, predicting the spatio-temporal location of secondary crashes could offer valuable insights for implementing prevention strategies. This includes guiding the deployment of emergency response measures and determining appropriate speed limits. The main objective of this study is to develop a prediction method for the spatial and temporal locations of secondary crashes. A hybrid deep learning model SSAE-LSTM is proposed by combining stacked sparse auto-encoder (SSAE) and long short-term memory network (LSTM). Traffic and crash data on the California I-880 highway covering the period of 2017-2021 are collected. The identification of secondary crashes is performed by the speed contour map method. The time and distance gaps between primary and secondary crashes are modeled using multiple 5-minute interval traffic variables as inputs. Multiple models are developed for benchmarking purposes, including PCA-LSTM, which incorporates principal component analysis (PCA) and LSTM, SSAE-SVM, which incorporates SSAE and support vector machine (SVM), and back propagation neural network (BPNN). The performance comparison indicates that the hybrid SSAE-LSTM model outperforms the other models in terms of both spatial and temporal prediction. In particular, SSAE4-LSTM1 (with 4 SSAE layers and 1 LSTM layer) demonstrates superior spatial prediction performance, while SSAE4-LSTM2 (with 4 SSAE layers and 2 LSTM layers) excels in temporal prediction. A joint spatio-temporal evaluation is also conducted to measure the overall accuracy of the optimal models over different permitted spatio-temporal ranges. Finally, practical suggestions are provided for secondary crash prevention.
Collapse
Affiliation(s)
- Haojie Li
- School of Transportation, Southeast University, China; Jiangsu Key Laboratory of Urban ITS, China; Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies, China.
| | - Qi Gao
- School of Transportation, Southeast University, China; Jiangsu Key Laboratory of Urban ITS, China; Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies, China
| | - Ziqian Zhang
- School of Transportation, Southeast University, China; Jiangsu Key Laboratory of Urban ITS, China; Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies, China
| | - Yingheng Zhang
- School of Transportation, Southeast University, China; Jiangsu Key Laboratory of Urban ITS, China; Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies, China
| | - Gang Ren
- School of Transportation, Southeast University, China; Jiangsu Key Laboratory of Urban ITS, China; Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies, China
| |
Collapse
|
8
|
Ojha MK, Wadhwani S, Wadhwani AK, Shukla A. Automatic detection of arrhythmias from an ECG signal using an auto-encoder and SVM classifier. Phys Eng Sci Med 2022; 45:665-674. [PMID: 35304901 DOI: 10.1007/s13246-022-01119-1] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/17/2021] [Accepted: 03/09/2022] [Indexed: 12/29/2022]
Abstract
Millions of people around the world are affected by arrhythmias, which are abnormal activities of the functioning of the heart. Most arrhythmias are harmful to the heart and can suddenly become life-threatening. The electrocardiogram (ECG) is an important non-invasive tool in cardiology for the diagnosis of arrhythmias. This work proposes a computer-aided diagnosis (CAD) system to automatically classify different types of arrhythmias from ECG signals. First, the auto-encoder convolutional network (ACN) model is used, which is based on a one-dimensional convolutional neural network (1D-CNN) that automatically learns the best features from the raw ECG signals. After that, the support vector machine (SVM) classifier is applied to the features learned by the ACN model to improve the detection of arrhythmic beats. This classifier detects four different types of arrhythmias, namely the left bundle branch block (LBBB), right bundle branch block (RBBB), paced beat (PB), and premature ventricular contractions (PVC), along with the normal sinus rhythms (NSR). Among these arrhythmias, PVC is particularly a dangerous type of heartbeat in ECG signals. The performance of the model is measured in terms of accuracy, sensitivity, and precision using a tenfold cross-validation strategy on the MIT-BIH arrhythmia database. The obtained overall accuracy of the SVM classifier was 98.84%. The result of this model is portrayed as a better performance than in other literary works. Thus, this approach may also help in further clinical studies of cardiac cases.
Collapse
Affiliation(s)
- Manoj Kumar Ojha
- Madhav Institute of Technology and Science, Gwalior, Madhya Pradesh, India.
| | - Sulochna Wadhwani
- Madhav Institute of Technology and Science, Gwalior, Madhya Pradesh, India
| | | | - Anupam Shukla
- Indian Institute of Information Technology, Pune, Maharashtra, India
| |
Collapse
|
9
|
Jiang Z, Wang D, Chen Y. Automatic classification of nerve discharge rhythms based on sparse auto-encoder and time series feature. BMC Bioinformatics 2022; 22:619. [PMID: 35168551 PMCID: PMC8848584 DOI: 10.1186/s12859-022-04592-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/09/2022] [Accepted: 01/11/2022] [Indexed: 12/01/2022] Open
Abstract
Background Nerve discharge is the carrier of information transmission, which can reveal the basic rules of various nerve activities. Recognition of the nerve discharge rhythm is the key to correctly understand the dynamic behavior of the nervous system. The previous methods for the nerve discharge recognition almost depended on the traditional statistical features, and the nonlinear dynamical features of the discharge activity. The artificial extraction and the empirical judgment of the features were required for the recognition. Thus, these methods suffered from subjective factors and were not conducive to the identification of a large number of discharge rhythms. Results The ability of automatic feature extraction along with the development of the neural network has been greatly improved. In this paper, an effective discharge rhythm classification model based on sparse auto-encoder was proposed. The sparse auto-encoder was used to construct the feature learning network. The simulated discharge data from the Chay model and its variants were taken as the input of the network, and the fused features, including the network learning features, covariance and approximate entropy of nerve discharge, were classified by Softmax. The results showed that the accuracy of the classification on the testing data was 87.5%, which could provide more accurate classification results. Compared with other methods for the identification of nerve discharge types, this method could extract the characteristics of nerve discharge rhythm automatically without artificial design, and show a higher accuracy. Conclusions The sparse auto-encoder, even neural network has not been used to classify the basic nerve discharge from neither biological experiment data nor model simulation data. The automatic classification method of nerve discharge rhythm based on the sparse auto-encoder in this paper reduced the subjectivity and misjudgment of the artificial feature extraction, saved the time for the comparison with the traditional method, and improved the intelligence of the classification of discharge types. It could further help us to recognize and identify the nerve discharge activities in a new way. Supplementary Information The online version contains supplementary material available at 10.1186/s12859-022-04592-3.
Collapse
Affiliation(s)
- Zhongting Jiang
- School of Information Science and Engineering, University of Jinan, Jinan, 250022, China
| | - Dong Wang
- School of Information Science and Engineering, University of Jinan, Jinan, 250022, China. .,Shandong Provincial Key Laboratory of Network Based Intelligent Computing, Jinan, 250022, China.
| | - Yuehui Chen
- School of Information Science and Engineering, University of Jinan, Jinan, 250022, China.,Shandong Provincial Key Laboratory of Network Based Intelligent Computing, Jinan, 250022, China
| |
Collapse
|
10
|
Skarga-Bandurova I, Biloborodova T, Skarha-Bandurov I, Boltov Y, Derkach M. A Multilayer LSTM Auto-Encoder for Fetal ECG Anomaly Detection. Stud Health Technol Inform 2021; 285:147-52. [PMID: 34734866 DOI: 10.3233/SHTI210588] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register]
Abstract
The paper introduces a multilayer long short-term memory (LSTM) based auto-encoder network to spot abnormalities in fetal ECG. The LSTM network was used to detect patterns in the time series, reconstruct errors and classify a given segment as an anomaly or not. The proposed anomaly detection method provides a filtering procedure able to reproduce ECG variability based on the semi-supervised paradigm. Experiments show that the proposed method can learn better features than the traditional approach without any prior knowledge and subject to proper signal identification can facilitate the analysis of fetal ECG signals in daily life.
Collapse
|
11
|
Sakaguchi K, Kaida H, Yoshida S, Ishii K. Attenuation correction using deep learning for brain perfusion SPECT images. Ann Nucl Med 2021; 35:589-99. [PMID: 33751364 DOI: 10.1007/s12149-021-01600-z] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/17/2020] [Accepted: 02/15/2021] [Indexed: 12/24/2022]
Abstract
OBJECTIVE Non-uniform attenuation correction using computed tomography (CT) improves the image quality and quantification of single-photon emission computed tomography (SPECT). However, it is not widely used because it requires a SPECT/CT scanner. This study constructs a convolutional neural network (CNN) to generate attenuation-corrected SPECT images directly from non-attenuation-corrected SPECT images. METHODS We constructed an auto-encoder (AE) using a CNN to correct the attenuation in brain perfusion SPECT images. SPECT image datasets of 270 (44,528 slices including augmentation), 60 (5002 slices), and 30 (2558 slices) cases were used for training, validation, and testing, respectively. The acquired projection data were reconstructed in three patterns: uniform attenuation correction using Chang's method (Chang-AC), non-uniform attenuation correction using CT (CT-AC), and no attenuation correction (No-AC). The AE learned an end-to-end mapping between the No-AC and CT-AC images. The No-AC images in the test dataset were loaded into the trained AE, which generated images simulating the CT-AC images as output. The generated SPECT images were employed as attenuation-corrected images using the AE (AE-AC). The accuracy of the AE-AC images was evaluated in terms of the peak signal-to-noise ratio (PSNR) and the structural similarity metric (SSIM). The intensities of the AE-AC and CT-AC images were compared by voxel-by-voxel and region-by-region analysis. RESULTS The PSNRs of the AE-AC and Chang-AC images, compared using CT-AC images, were 62.2, and 57.9, and their SSIM values were 0.9995 and 0.9985, respectively. The AE-AC and CT-AC images were visually and statistically in good agreement. CONCLUSIONS The proposed AE-AC method yields highly accurate attenuation-corrected brain perfusion SPECT images.
Collapse
|
12
|
Lu H, Liu S, Wei H, Chen C, Geng X. Deep multi-kernel auto-encoder network for clustering brain functional connectivity data. Neural Netw 2021; 135:148-157. [PMID: 33388506 DOI: 10.1016/j.neunet.2020.12.005] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/18/2020] [Revised: 11/28/2020] [Accepted: 12/06/2020] [Indexed: 11/17/2022]
Abstract
In this study, we propose a deep-learning network model called the deep multi-kernel auto-encoder clustering network (DMACN) for clustering functional connectivity data for brain diseases. This model is an end-to-end clustering algorithm that can learn potentially advanced features and cluster disease categories. Unlike other auto-encoders, DMACN has an added self-expression layer and standard back-propagation is used to learn the features that are beneficial for clustering brain functional connectivity data. In the self-expression layer, the kernel matrix is constructed to extract effective features and a new loss function is proposed to constrain the clustering portion, which enables the training of a deep neural learning network that tends to cluster. To test the performance of the proposed algorithm, we applied the end-to-end deep unsupervised clustering algorithm to brain connectivity data. We then conducted experiments based on four public brain functional connectivity data sets and our own functional connectivity data set. The DMACN algorithm yielded good results in various evaluations compared with the existing clustering algorithm for brain functional connectivity data, the deep auto-encoder clustering algorithm, and several other relevant clustering algorithms. The deep-learning-based clustering algorithm has great potential for use in the unsupervised recognition of brain diseases.
Collapse
Affiliation(s)
- Hu Lu
- School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang 212013, China.
| | - Saixiong Liu
- School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang 212013, China
| | - Hui Wei
- School of Computer Science, Laboratory of Cognitive and Model Algorithm, Fudan University, Shanghai 200433, China
| | - Chao Chen
- School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang 212013, China
| | - Xia Geng
- School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang 212013, China
| |
Collapse
|
13
|
Zhu H, Fang Q, Huang Y, Xu K. Semi-supervised method for image texture classification of pituitary tumors via CycleGAN and optimized feature extraction. BMC Med Inform Decis Mak 2020; 20:215. [PMID: 32907561 PMCID: PMC7488038 DOI: 10.1186/s12911-020-01230-x] [Citation(s) in RCA: 12] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/13/2019] [Accepted: 08/24/2020] [Indexed: 11/17/2022] Open
Abstract
Background Accurately determining the softness level of pituitary tumors preoperatively by using their image textures can provide a basis for surgical options and prognosis. Existing methods for this problem require manual intervention, which could hinder the efficiency and accuracy considerably. Methods We present an automatic method for diagnosing the texture of pituitary tumors using unbalanced sequence image data. Firstly, for the small sample problem in our pituitary tumor MRI image dataset where T1 and T2 sequence data are unbalanced (due to data missing) and under-sampled, our method uses a CycleGAN (Cycle-Consistent Adversarial Networks) model for domain conversion to obtain fully sampled MRI spatial sequence. Then, it uses a DenseNet (Densely Connected Convolutional Networks)-ResNet(Deep Residual Networks) based Autoencoder framework to optimize the feature extraction process for pituitary tumor image data. Finally, to take advantage of sequence data, it uses a CRNN (Convolutional Recurrent Neural Network) model to classify pituitary tumors based on their predicted softness levels. Results Experiments show that our method is the best in terms of efficiency and accuracy (91.78%) compared to other methods. Conclusions We propose a semi-supervised method for grading pituitary tumor texture. This method can accurately determine the softness level of pituitary tumors, which provides convenience for surgical selection and prognosis, and improves the diagnostic efficiency of pituitary tumors.
Collapse
Affiliation(s)
- Hong Zhu
- School of Medical Information, Xuzhou Medical University, Xuzhou, China. .,Department of Computer Science and Engineering, State University of New York at Buffalo, Buffalo, USA.
| | - Qianhao Fang
- School of Medical Information, Xuzhou Medical University, Xuzhou, China
| | - Yihe Huang
- School of Medical Information, Xuzhou Medical University, Xuzhou, China
| | - Kai Xu
- Affiliated Hospital of Xuzhou Medical University, Xuzhou, China.
| |
Collapse
|
14
|
Abstract
Background RNA sequencing technique (RNA-seq) enables scientists to develop novel data-driven methods for discovering more unidentified lincRNAs. Meantime, knowledge-based technologies are experiencing a potential revolution ignited by the new deep learning methods. By scanning the newly found data set from RNA-seq, scientists have found that: (1) the expression of lincRNAs appears to be regulated, that is, the relevance exists along the DNA sequences; (2) lincRNAs contain some conversed patterns/motifs tethered together by non-conserved regions. The two evidences give the reasoning for adopting knowledge-based deep learning methods in lincRNA detection. Similar to coding region transcription, non-coding regions are split at transcriptional sites. However, regulatory RNAs rather than message RNAs are generated. That is, the transcribed RNAs participate the biological process as regulatory units instead of generating proteins. Identifying these transcriptional regions from non-coding regions is the first step towards lincRNA recognition. Results The auto-encoder method achieves 100% and 92.4% prediction accuracy on transcription sites over the putative data sets. The experimental results also show the excellent performance of predictive deep neural network on the lincRNA data sets compared with support vector machine and traditional neural network. In addition, it is validated through the newly discovered lincRNA data set and one unreported transcription site is found by feeding the whole annotated sequences through the deep learning machine, which indicates that deep learning method has the extensive ability for lincRNA prediction. Conclusions The transcriptional sequences of lincRNAs are collected from the annotated human DNA genome data. Subsequently, a two-layer deep neural network is developed for the lincRNA detection, which adopts the auto-encoder algorithm and utilizes different encoding schemes to obtain the best performance over intergenic DNA sequence data. Driven by those newly annotated lincRNA data, deep learning methods based on auto-encoder algorithm can exert their capability in knowledge learning in order to capture the useful features and the information correlation along DNA genome sequences for lincRNA detection. As our knowledge, this is the first application to adopt the deep learning techniques for identifying lincRNA transcription sequences.
Collapse
Affiliation(s)
- Ning Yu
- Department of Computing Sciences, The College at Brockport, State University of New York, 350 New Campus Drive, Brockport, 14420, NY, USA.
| | - Zeng Yu
- School of Information Science and Technology, Southwest Jiaotong University, Chengdu, 610031, Sihuan, China
| | - Yi Pan
- Department of Computer Science, Georgia State University, 25 Park Place, Atlanta, 30303, GA, USA
| |
Collapse
|
15
|
Taghanaki SA, Kawahara J, Miles B, Hamarneh G. Pareto-optimal multi-objective dimensionality reduction deep auto-encoder for mammography classification. Comput Methods Programs Biomed 2017; 145:85-93. [PMID: 28552129 DOI: 10.1016/j.cmpb.2017.04.012] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/02/2016] [Revised: 03/21/2017] [Accepted: 04/12/2017] [Indexed: 06/07/2023]
Abstract
BACKGROUND AND OBJECTIVE Feature reduction is an essential stage in computer aided breast cancer diagnosis systems. Multilayer neural networks can be trained to extract relevant features by encoding high-dimensional data into low-dimensional codes. Optimizing traditional auto-encoders works well only if the initial weights are close to a proper solution. They are also trained to only reduce the mean squared reconstruction error (MRE) between the encoder inputs and the decoder outputs, but do not address the classification error. The goal of the current work is to test the hypothesis that extending traditional auto-encoders (which only minimize reconstruction error) to multi-objective optimization for finding Pareto-optimal solutions provides more discriminative features that will improve classification performance when compared to single-objective and other multi-objective approaches (i.e. scalarized and sequential). METHODS In this paper, we introduce a novel multi-objective optimization of deep auto-encoder networks, in which the auto-encoder optimizes two objectives: MRE and mean classification error (MCE) for Pareto-optimal solutions, rather than just MRE. These two objectives are optimized simultaneously by a non-dominated sorting genetic algorithm. RESULTS We tested our method on 949 X-ray mammograms categorized into 12 classes. The results show that the features identified by the proposed algorithm allow a classification accuracy of up to 98.45%, demonstrating favourable accuracy over the results of state-of-the-art methods reported in the literature. CONCLUSIONS We conclude that adding the classification objective to the traditional auto-encoder objective and optimizing for finding Pareto-optimal solutions, using evolutionary multi-objective optimization, results in producing more discriminative features.
Collapse
Affiliation(s)
| | - Jeremy Kawahara
- Medical Image Analysis Lab, Simon Fraser University, Canada.
| | - Brandon Miles
- Medical Image Analysis Lab, Simon Fraser University, Canada.
| | | |
Collapse
|
16
|
Vakanski A, Ferguson JM, Lee S. Mathematical Modeling and Evaluation of Human Motions in Physical Therapy Using Mixture Density Neural Networks. J Physiother Phys Rehabil 2016; 1:118. [PMID: 28111643 PMCID: PMC5242735] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Subscribe] [Scholar Register] [Indexed: 06/06/2023]
Abstract
OBJECTIVE The objective of the proposed research is to develop a methodology for modeling and evaluation of human motions, which will potentially benefit patients undertaking a physical rehabilitation therapy (e.g., following a stroke or due to other medical conditions). The ultimate aim is to allow patients to perform home-based rehabilitation exercises using a sensory system for capturing the motions, where an algorithm will retrieve the trajectories of a patient's exercises, will perform data analysis by comparing the performed motions to a reference model of prescribed motions, and will send the analysis results to the patient's physician with recommendations for improvement. METHODS The modeling approach employs an artificial neural network, consisting of layers of recurrent neuron units and layers of neuron units for estimating a mixture density function over the spatio-temporal dependencies within the human motion sequences. Input data are sequences of motions related to a prescribed exercise by a physiotherapist to a patient, and recorded with a motion capture system. An autoencoder subnet is employed for reducing the dimensionality of captured sequences of human motions, complemented with a mixture density subnet for probabilistic modeling of the motion data using a mixture of Gaussian distributions. RESULTS The proposed neural network architecture produced a model for sets of human motions represented with a mixture of Gaussian density functions. The mean log-likelihood of observed sequences was employed as a performance metric in evaluating the consistency of a subject's performance relative to the reference dataset of motions. A publically available dataset of human motions captured with Microsoft Kinect was used for validation of the proposed method. CONCLUSION The article presents a novel approach for modeling and evaluation of human motions with a potential application in home-based physical therapy and rehabilitation. The described approach employs the recent progress in the field of machine learning and neural networks in developing a parametric model of human motions, by exploiting the representational power of these algorithms to encode nonlinear input-output dependencies over long temporal horizons.
Collapse
Affiliation(s)
- A Vakanski
- Industrial Technology, University of Idaho, Idaho Falls, United States
| | - JM Ferguson
- Center for Modeling Complex Interactions, University of Idaho, Moscow, United States
| | - S Lee
- Department of Statistical Science, University of Idaho, Moscow, United States
| |
Collapse
|
17
|
Chai X, Wang Q, Zhao Y, Liu X, Bai O, Li Y. Unsupervised domain adaptation techniques based on auto-encoder for non-stationary EEG-based emotion recognition. Comput Biol Med 2016; 79:205-214. [PMID: 27810626 DOI: 10.1016/j.compbiomed.2016.10.019] [Citation(s) in RCA: 89] [Impact Index Per Article: 11.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/17/2016] [Revised: 10/17/2016] [Accepted: 10/19/2016] [Indexed: 11/30/2022]
Abstract
In electroencephalography (EEG)-based emotion recognition systems, the distribution between the training samples and the testing samples may be mismatched if they are sampled from different experimental sessions or subjects because of user fatigue, different electrode placements, varying impedances, etc. Therefore, it is difficult to directly classify the EEG patterns with a conventional classifier. The domain adaptation method, which is aimed at obtaining a common representation across training and test domains, is an effective method for reducing the distribution discrepancy. However, the existing domain adaptation strategies either employ a linear transformation or learn the nonlinearity mapping without a consistency constraint; they are not sufficiently powerful to obtain a similar distribution from highly non-stationary EEG signals. To address this problem, in this paper, a novel component, called the subspace alignment auto-encoder (SAAE), is proposed. Taking advantage of both nonlinear transformation and a consistency constraint, we combine an auto-encoder network and a subspace alignment solution in a unified framework. As a result, the source domain can be aligned with the target domain together with its class label, and any supervised method can be applied to the new source domain to train a classifier for classification in the target domain, as the aligned source domain follows a distribution similar to that of the target domain. We compared our SAAE method with six typical approaches using a public EEG dataset containing three affective states: positive, neutral, and negative. Subject-to-subject and session-to-session evaluations were performed. The subject-to-subject experimental results demonstrate that our component achieves a mean accuracy of 77.88% in comparison with a state-of-the-art method, TCA, which achieves 73.82% on average. In addition, the average classification accuracy of SAAE in the session-to-session evaluation for all the 15 subjects in a dataset is 81.81%, an improvement of up to 1.62% on average as compared to the best baseline TCA. The experimental results show the effectiveness of the proposed method relative to state-of-the-art methods. It can be concluded that SAAE is a useful and effective tool for decreasing domain discrepancy and reducing performance degradation across subjects and sessions in the EEG-based emotion recognition field.
Collapse
Affiliation(s)
- Xin Chai
- School of Electrical Engineering and Automation, Harbin Institute of Technology, Harbin, China
| | - Qisong Wang
- School of Electrical Engineering and Automation, Harbin Institute of Technology, Harbin, China.
| | - Yongping Zhao
- School of Electrical Engineering and Automation, Harbin Institute of Technology, Harbin, China
| | - Xin Liu
- Department of Traffic Information and Control Engineering, School of Transportation Science and Engineering, Harbin Institute of Technology, Harbin, China
| | - Ou Bai
- Department of Electrical and Computer Engineering, Florida International University, USA
| | - Yongqiang Li
- School of Electrical Engineering and Automation, Harbin Institute of Technology, Harbin, China
| |
Collapse
|