Maize seed variety identification is the key to improving the quality and yield of maize. The study aimed to investigate a stacked sparse autoencoder combined with a cuckoo search (CS) optimized support vector machine...
详细信息
Maize seed variety identification is the key to improving the quality and yield of maize. The study aimed to investigate a stacked sparse autoencoder combined with a cuckoo search (CS) optimized support vector machine (SSAE-CS-SVM) to meet the identification requirements of accurate detection. First, the near-infrared (NIR) (871.61-1766.32 nm) hyperspectral data of maize seeds were processed using Savitzky-Golay (SG) combined with standard normal variables (SNV). Subsequently, SSAE, SAE, principal component analysis (PCA), and competitive adaptive reweighted sampling were employed for feature extraction. Finally, the recognition model was constructed using the SoftMax regression model, SVM, and CS optimized SVM (CS-SVM). The results indicated that the SSAE-CS-SVM model achieved satisfactory performance (the training set and testing set accuracies were 99.45% and 95.81%, respectively). This study confirmed the great potential of combining NIR hyperspectral imaging technology with deep learning algorithms for maize seed variety identification. Practical applications The identification of maize seed varieties is extremely important for ensuring seed purity and improving maize quality and yield. A method based on SSAE and NIR hyperspectral imaging technology was studied to identify maize seed varieties. The method proposed in this paper could identify maize seed varieties non-destructively and accurately, which provided a new way for the online detection of seed varieties.
Network traffic analytics has become a crucial task in order to better understand and manage network resources, especially in the network softwarization era where the implementation of this concept can be done easily ...
详细信息
Network traffic analytics has become a crucial task in order to better understand and manage network resources, especially in the network softwarization era where the implementation of this concept can be done easily with network function virtualization. Currently, many approaches have been proposed to improve the performance of traffic classification. However, as new types of traffic emerge every day (and they are generally not labeled), this opens a new challenge to be handled. Moreover, the question of how to accurately classify the traffic using a limited amount of labeled data or partially labeled data is also another important concern. In fact, labeling data is often difficult and time-consuming. In order to solve the previously described issues, we reformulate traffic classification into a semi-supervised learning where both supervised learning (using labeled data) and unsupervised learning (no label data) are combined. To do so, this paper presents a stacked sparse autoencoder (SSAE) based semi-supervised deep-learning model for traffic classification. The main motivations of this approach are: (i) unlabeled data is often abundant and easily available;(ii) classification performance of the whole model can be greatly improved when a large amount of unlabeled traffic is included in the training process;(iii) there is a limit to how much human effort can be thrown at the labeling problem. To investigate the performance of our approach, an empirical study has been conducted on a real dataset and results indicate that using a large amount of unlabeled data in the SSAE pre-trained phase can improve significantly the classification performance of the whole model. Furthermore, the proposed approach is compared against other representative machine-learning and deep-learning models, which are Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Multi-Layer Perceptron (MLP), eXtreme Gradient Boosting (XGBoost), and autoencoder.
Cavitation is a phenomenon that occurs during the continuous operation of a hydro turbine that directly affects the efficiency and working capacity of the unit. This paper proposes an innovative classification paradig...
详细信息
Cavitation is a phenomenon that occurs during the continuous operation of a hydro turbine that directly affects the efficiency and working capacity of the unit. This paper proposes an innovative classification paradigm that uses deep learning-based methodologies in order to identify both cavitation noise signal and non-cavitation noise signal that will help prevent the damage or breakage in the earliest possible time to avoid more irreversible and irreparable damage to the hydro turbine. The stacked sparse autoencoder (SSA) nuclear framework is utilized to learn more abstract and invariant high-level features from the multiple feature sets. Then, the method on minimum redundancy maximum relevance (mRMR) selection is used to evaluate and sort out all the characteristics found by the stacked sparse autoencoder. Finally, the random forest (RF) classifier algorithm is employed to perform supervised fine-tuning and classification. The traditional supervised learning models such as support vector machine, logistic regression, and sparse representation classification are chosen to be used as contrast algorithms. SSA-mRMR-RF generally produces a better performance than the support vector machine, logistic regression and sparse representation classification when used in the same set of features. The SSA-mRMR-RF produced the highest overall average accuracy since it reached 93.18%. The SSA-mRMR-RF offers a 3.85% higher overall accuracy than the support vector machine. It also offers a 2.44% higher overall accuracy than logistic regression. In addition, it also offers a 20.30% higher overall accuracy than the sparse representation classification on the average. When the signals are divided into three categories, the highest overall accuracy decreased to 71.88%, and the classification accuracy of incipient noise signals is very low. Therefore, this paper proposes the models of power spectral-SSA-mRMR-RF and fast Fourier transform-SSA-mRMR-RF to be used, and these discoveries ar
Security is a crucial factor for information systems and other vital infrastructures. Ensuring robust security measures is imperative due to the substantial volume of network traffic. On the other hand, many network c...
详细信息
Security is a crucial factor for information systems and other vital infrastructures. Ensuring robust security measures is imperative due to the substantial volume of network traffic. On the other hand, many network components are susceptible to cyber threats and attacks due to their inherent properties. The increasing use of networks paves the way for widespread security vulnerabilities. In this context, the implementation of intrusion detection systems (IDS) plays a key role in safeguarding information systems and their network architectures. This research introduces an optimized deep learning model aimed at improving network security by accurately detecting intrusions. The proposed IDS, also termed as the POA-SSAE IDS model (pelican optimization model-stacked sparse autoencoder), integrates a POA for optimal feature selection and an SSAE for feature classification. The effectiveness of this IDS was tested using benchmark datasets, namely CICIDS2018 and KDDCUP'99. The results exhibited the proposed model's superior performance, achieving an accuracy of 97.45% on the CICIDS2018 dataset and 98.7% accuracy on the KDDCUP'99 dataset.
The power battery constitutes the fundamental component of new energy vehicles. Rapid and accurate fault diagnosis of power batteries can effectively improve the safety and power performance of the vehicle. In respons...
详细信息
The power battery constitutes the fundamental component of new energy vehicles. Rapid and accurate fault diagnosis of power batteries can effectively improve the safety and power performance of the vehicle. In response to the issues of limited generalization ability and suboptimal diagnostic accuracy observed in traditional power battery fault diagnosis models, this study proposes a fault diagnosis method utilizing a Convolutional Block Attention Capsule Network (CBAM-CapsNet) based on a stacked sparse autoencoder (SSAE). The reconstructed dataset is initially input into the SSAE model. Layer-by-layer greedy learning using unsupervised learning is employed, combining unsupervised learning methods with parameter updating and local fine-tuning to enhance visualization capabilities. The CBAM is then integrated into the CapsNet, which not only mitigates the effect of noise on the SSAE but also improves the model's ability to characterize power cell features, completing the fault diagnosis process. The experimental comparison results show that the proposed method can diagnose power battery failure modes with an accuracy of 96.86%, and various evaluation indexes are superior to CNN, CapsNet, CBAM-CapsNet, and other neural networks at accurately identifying fault types with higher diagnostic accuracy and robustness.
(Aim)COVID-19 is an ongoing infectious *** has caused more than 107.45 m confirmed cases and 2.35 m deaths till 11/Feb/*** computer vision methods have achieved promising results on the automatic smart diagnosis.(Meth...
详细信息
(Aim)COVID-19 is an ongoing infectious *** has caused more than 107.45 m confirmed cases and 2.35 m deaths till 11/Feb/*** computer vision methods have achieved promising results on the automatic smart diagnosis.(Method)This study aims to propose a novel deep learning method that can obtain better *** use the pseudo-Zernike moment(PZM),derived from Zernike moment,as the extracted *** settings are introducing:(i)image plane over unit circle;and(ii)image plane inside the unit ***,we use a deep-stacked sparse autoencoder(DSSAE)as the ***,multiple-way data augmentation is chosen to overcome *** multiple-way data augmentation is based on Gaussian noise,salt-and-pepper noise,speckle noise,horizontal and vertical shear,rotation,Gamma correction,random translation and scaling.(Results)10 runs of 10-fold cross validation shows that our PZM-DSSAE method achieves a sensitivity of 92.06%±1.54%,a specificity of 92.56%±1.06%,a precision of 92.53%±1.03%,and an accuracy of 92.31%±1.08%.Its F1 score,MCC,and FMI arrive at 92.29%±1.10%,84.64%±2.15%,and 92.29%±1.10%,*** AUC of our model is 0.9576.(Conclusion)We demonstrate“image plane over unit circle”can get better results than“image plane inside a unit circle.”Besides,this proposed PZM-DSSAE model is better than eight state-of-the-art approaches.
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....
详细信息
ISBN:
(纸本)9789881563903
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 ERs) than other three methods do.
Accurate nucleus detection is of great importance in pathological image analyses and diagnoses, which is a critical prerequisite for tasks such as automated grading hepatocellular carcinoma (HCC) nuclei. This paper pr...
详细信息
Accurate nucleus detection is of great importance in pathological image analyses and diagnoses, which is a critical prerequisite for tasks such as automated grading hepatocellular carcinoma (HCC) nuclei. This paper proposes an automated nucleus detection framework based on a stacked sparse autoencoder (SSAE) and a case-based postprocessing method (CPM) in a coarse-to-fine manner. SSAE, an unsupervised learning model, is first trained using image patches of breast cancer. Then, the transfer learning and sliding window techniques are applied to other cancers' pathological images (HCC and colon cancer) to extract the high-level features of image patches via the trained SSAE. Subsequently, these high-level features are fed to a logistic regression classifier (LRC) to classify whether each image patch contains a complete nucleus in a coarse detection process. Finally, CPM is developed for refining the coarse detection results which removes false positive nuclei and locates adhesive or overlapped nuclei effectively. SSAE-CPM achieves an average nucleus detection accuracy of 0.8748 on HCC pathological images, which can accurately locate almost all nuclei on the pathological images with serious differentiation. In addition, our proposed detection framework is also evaluated on a public dataset of colon cancer, with a mean F-1 score of 0.8355. Experimental results demonstrate the performance advantages of our proposed SSAE-CPM detection framework as compared with related work. While our detection framework is trained on the pathological images of breast cancer, it can be easily and effectively applied to nucleus detection tasks on other cancers without re-training. (C) 2019 Elsevier B.V. All rights reserved.
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
ISBN:
(纸本)9789881563903
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 proposed. autoencoder (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.
Diabetes mellitus and lung cancer are two of the most common fatal diseases in the world, causing considerable deaths every year. However, it is not easy to detect diabetes mellitus and lung cancer efficiently-needing...
详细信息
ISBN:
(数字)9781509066315
ISBN:
(纸本)9781509066315
Diabetes mellitus and lung cancer are two of the most common fatal diseases in the world, causing considerable deaths every year. However, it is not easy to detect diabetes mellitus and lung cancer efficiently-needing professional medical instruments such as a CT and a qualified individual to perform the Fasting Plasma Glucose test. Considering the risks and various inconveniences with conventional diagnosis methods, noninvasive approaches based on computerized analysis are desired. The aim of this paper is to distinguish patients with diabetes mellitus, lung cancer from healthy people simultaneously by analyzing facial images through the stacked sparse autoencoder. Experimental results on a dataset containing 450 healthy samples, 284 diabetes and 175 lung cancer patients produced the F1-score of 93.57%, 97.54%, 81.56% for detecting healthy, diabetes and lung cancer, respectively, validating the effectiveness of our proposed method.
暂无评论