Stacked Autoencoder Neural Network Research Articles

Detection of Citrus Huanglongbing Based on Multi-Input Neural Network Model of UAV Hyperspectral Remote Sensing

Citrus is an important cash crop in the world, and huanglongbing (HLB) is a destructive disease in the citrus industry. To efficiently detect the degree of HLB stress on large-scale orchard citrus trees, an UAV (Uncrewed Aerial Vehicle) hyperspectral remote sensing tool is used for HLB rapid detection. A Cubert S185 (Airborne Hyperspectral camera) was mounted on the UAV of DJI Matrice 600 Pro to capture the hyperspectral remote sensing images; and a ASD Handheld2 (spectrometer) was used to verify the effectiveness of the remote sensing data. Correlation-proven UAV hyperspectral remote sensing data were used, and canopy spectral samples based on single pixels were extracted for processing and analysis. The feature bands extracted by the genetic algorithm (GA) of the improved selection operator were 468 nm, 504 nm, 512 nm, 516 nm, 528 nm, 536 nm, 632 nm, 680 nm, 688 nm, and 852 nm for the HLB detection. The proposed HLB detection methods (based on the multi-feature fusion of vegetation index) and canopy spectral feature parameters constructed (based on the feature band in stacked autoencoder (SAE) neural network) have a classification accuracy of 99.33% and a loss of 0.0783 for the training set, and a classification accuracy of 99.72% and a loss of 0.0585 for the validation set. This performance is higher than that based on the full-band AutoEncoder neural network. The field-testing results show that the model could effectively detect the HLB plants and output the distribution of the disease in the canopy, thus judging the plant disease level in a large area efficiently.

Hyperspectral image classification using multi-task feature leverage with multi-variant deep learning

Deep learning framework aids the researchers in learning different application areas to a greater extent. Deep learning framework is preferred over machine learning since it helps to learn the input from end to end, whereas latter one require the inputs to be cut into pieces according to the need. This paper proposes a Multi-Variant Deep Learning framework for learning and classifying the hyperspectral images. Multi-task Feature Leverage is incorporated by doing two-ordered feature extraction. The first order feature extraction was done by using Two Dimensional Empirical Wavelet Transforms (2D-EWT) and the second-order feature extraction was done by using Stacked Autoencoder (SAE) and Convolutional Neural Network (CNN) for the approximation image of 2D-EWT. Because of the possibility of working on prominent feature, the proposed work uses approximation image than the raw image. The classification was carried out by using Random Forest (RF), Multi- Support Vector Machine (MSVM) and Extreme learning machine (ELM).

A hyperspectral anomaly detection framework based on segmentation and convolutional neural network algorithms

ABSTRACT Hyperspectral imagery (HSI) creates a lot of applications in target or anomaly detection due to their rich spectral content. Generally, one scene of an HSI contains more than one class. Therefore, the Gaussian distribution assumption of the background fails. Furthermore, the high dimensionality of data makes background modelling more difficult by increasing redundancy and disturbances. In this paper, a segmented-distance based anomaly detection method is proposed for HSI. The proposed method is based on segmentation and takes advantage of the statistical properties of the segmented areas to suppress the false-alarms. In addition to that, nonlinear feature extraction based on convolutional stacked auto-encoder (SAE) neural networks are implemented to extract deep and nonlinear relations from the input data. Both 1-D and 2-D convolutional layers are investigated. The proposed method is tested on the three different datasets. The experimental results show that the integration of segmentation and deep feature extraction generally performs better than other state-of-the-art methods.

오토인코더를 이용한 지하전력구 이상감지 시스템

With the advent of the era of the 4th industrial revolution, AI technique has been applied in various fields. KEPCO developed an anomaly detection system using AI technology to detect abnormal situation in the underground cable tunnel. This anomaly-detection system consists of a robot-based data acquisition, communication and analysis module which works with stacked autoencoder neural network model. This system utilizes the data from audio sensors and determines the condition of equipment in the underground cable tunnel which is normal or abnormal. Moreover, by adding the attention-module in autoencoder neural network model we increased the recognition accuracy by 4%. The performance of this system is over 90%. Also, we investigated the performance of adversarial autoencoder (AAE) and attention based AAE model, which showed worse failure detection rate than attention added autoencoder model.

Detection of glucose concentration in a turbid medium using a stacked auto-encoder deep neural network

In order to detect the components of a turbid medium, this paper proposes a glucose concentration reconstruction method based on a stacked auto-encoder (SAE) deep neural network. Analysis of different optical properties is performed using multiple diffused reflection spectroscopy and multiple source-detector separation (SDS). In this experiment, a 20% intralipid solution was used to prepare 4%, 5% and 10% intralipid solutions as the research object. At a certain glucose concentration, thirty source-detector separations of diffused reflection spectral signals within the 0.47–4.095 mm range (0.125 mm interval) from the incident position were detected, and a SAE deep neural network was used for modeling and predicting glucose concentration under multiple spectra. The root mean square error of prediction (RMSEP) of the SAE deep neural network using the 4% and 5% intralipid solutions decreased by approximately 26.42% compared with the results using only the 4% intralipid solutions by partial least squares regression (PLSR) method. Moreover, the RMSEP of the SAE deep neural network using the 4% and 5% intralipid solutions decreased by approximately 34.25% compared with the PLSR method using the 5% intralipid solution sample. These results show that the reconstruction accuracy of the SAE deep neural network is higher than the traditional PLSR method, which proves that the SAE neural network is highly suitable for prediction of turbid medium concentration.

High-Voltage Circuit Breaker Fault Diagnosis Using a Hybrid Feature Transformation Approach Based on Random Forest and Stacked Autoencoder

In recent years, machine learning techniques have been applied to test the fault type in high-voltage circuit breakers (HVCBs). Most related research involves in improving the classification method for higher precision. Nevertheless, as an important part of the diagnosis, the feature information description of the vibration signal of an HVCB has been neglected; in particular, its diversity and significance are rarely considered in many real-world fault-diagnosis applications. Therefore, in this paper, a hybrid feature transformation is proposed to optimize the diagnosis performance for HVCB faults. First, we introduce a nonlinear feature mapping in the wavelet package time–frequency energy rate feature space based on random forest binary coding to extend the feature width. Then, a stacked autoencoder neural network is used for compressing the feature depth. Finally, five typical classifiers are applied in the hybrid feature space based on the experimental dataset. The superiority of the proposed feature optimal approach is verified by comparing the results in the three abovementioned feature spaces.

Visual Loop Closure Detection Based on Stacked Convolutional and Autoencoder Neural Networks

Simultaneous localization and mapping is the basis for solving the problem of robotic autonomous movement. Loop closure detection is vital for visual simultaneous localization and mapping. Correct detection of closed loops can effectively reduce the accumulation error of the robot poses, which plays an important role in building a globally consistent environment map. Traditional loop closure detection adopts the method of extracting handcrafted image features, which are sensitive to dynamic environments and are poor in robustness. In this paper, a method called stacked convolutional and autoencoder neural networks is proposed to automatically extract image features and perform dimensionality reduction processing. These features have multiple invariances in image transformation. Therefore, this method is robust to environmental changes. Experiments on public datasets show that the proposed method is superior to traditional methods in terms of accuracy, recall, and average accuracy, thereby validating the effectiveness of the proposed method.

Construction and Reduction Methods of Web Spam Identification Index System

Background: With the rapid development of the Internet, the number of web spam has increased dramatically in recent years, which has wasted search engine storage and computing power on a massive scale. To identify the web spam effectively, the content features, link features, hidden features and quality features of web page are integrated to establish the corresponding web spam identification index system. However, the index system is highly correlation dimension. Methods: An improved method of autoencoder named stacked autoencoder neural network (SAE) is used to realize the reduction of the web spam identification index system. Results: The experiment results show that our method could reduce effectively the index of web spam and significantly improves the recognition rate in the following work. Conclusion: An autoencoder based web spam indexes reduction method is proposed in this paper. The experimental results show that it greatly reduces the temporal and spatial complexity of the future web spam detection model.

Optimization of Reconstruction Accuracy of Anomaly Position Based on Stacked Auto-Encoder Neural Networks

The diffuse optical tomography (DOT) technique which uses the traditional linear iterative algorithm has the problems of slow calculation speed and low reconstruction imaging accuracy in the inverse problem reconstruction, which limits its clinical application and development. This paper proposes an inverse-problem solving technology based on a stacked auto-encoder (SAE) network to improve the reconstruction accuracy of anomaly position, size and absorption coefficient in tissues. The reconstruction accuracy of anomaly position, size and absorption coefficient obtained by the traditional algebraic reconstruction technique (ART) method and the SAE based method are experimentally compared. The experimental results show that the SAE based method achieves the prediction accuracy of anomaly position of 96.25%, thus improving the accuracy and shortening the reconstruction time compared with the traditional ART method. Accordingly, the proposed method provides a better solution to the problem of the inaccurate reconstruction of the position and size of the rapid DOT based positioning of anomalies.

Dynamic fine-tuning stacked auto-encoder neural network for weather forecast

With the advent of the big data era, dynamic and real-time data have increased in both volume and variety. It is difficult to make accurate predictions regarding data as they undergo rapid and dynamic changes. Autonomous cloud computing aims to reduce the time required for traditional machine learning. The stacked auto-encoder is a neural network approach in machine learning for feature extraction. It attempts to model high-level abstractions and to reduce data dimensions by using multiple processing layers. However, some common issues may occur during the implementation of deep learning or neural network models, such as over-complicated dimensions of the input data and difficulty in processing dynamic data. Therefore, combining the concept of dynamic data-driven system with a stacked auto-encoder neural network will help obtain the dynamic data correlation or relationship between the prediction results and actual data in a dynamic environment. This study applies the concept of a dynamic data-driven system to obtain the correlations between the prediction goals and number of different combination results. Association analysis, sequence analysis, and stacked auto-encoder neural network are employed to design a dynamic data-driven system based on deep learning.

Human fatigue expression recognition through image-based dynamic multi-information and bimodal deep learning

Human fatigue is an important cause of traffic accidents. To improve the safety of transportation, we propose, in this paper, a framework for fatigue expression recognition using image-based facial dynamic multi-information and a bimodal deep neural network. First, the landmark of face region and the texture of eye region, which complement each other in fatigue expression recognition, are extracted from facial image sequences captured by a single camera. Then, two stacked autoencoder neural networks are trained for landmark and texture, respectively. Finally, the two trained neural networks are combined by learning a joint layer on top of them to construct a bimodal deep neural network. The model can be used to extract a unified representation that fuses landmark and texture modalities together and classify fatigue expressions accurately. The proposed system is tested on a human fatigue dataset obtained from an actual driving environment. The experimental results demonstrate that the proposed method performs stably and robustly, and that the average accuracy achieves 96.2%.

An Imbalanced Data Classification Algorithm of De-noising Auto-Encoder Neural Network Based on SMOTE

Imbalanced data classification problem has always been one of the hot issues in the field of machine learning. Synthetic minority over-sampling technique (SMOTE) is a classical approach to balance datasets, but it may give rise to such problem as noise. Stacked De-noising Auto-Encoder neural network (SDAE), can effectively reduce data redundancy and noise through unsupervised layer-wise greedy learning. Aiming at the shortcomings of SMOTE algorithm when synthesizing new minority class samples, the paper proposed a Stacked De-noising Auto-Encoder neural network algorithm based on SMOTE, SMOTE-SDAE, which is aimed to deal with imbalanced data classification. The proposed algorithm is not only able to synthesize new minority class samples, but it also can de-noise and classify the sampled data. Experimental results show that compared with traditional algorithms, SMOTE-SDAE significantly improves the minority class classification accuracy of the imbalanced datasets.