Stacked Autoencoder Algorithm Research Articles

Granular risk assessment of earthquake induced landslide via latent representations of stacked autoencoder

Earthquake-induced landslides are ubiquitous on slopes in terrestrial environments, which can pose a serious threat to local communities and infrastructures. Data-driven landslide assessments play a crucial role in preventing future landslide occurrences and recurrences. We present a novel granular computing approach that assesses landslide risk by combining fuzzy information granulation and a stacked autoencoder algorithm. The stacked autoencoder is trained using an end-to-end learning strategy to obtain a central latent vector with reduced dimensionality. The multivariate landslide dataset was used as both the input and output to train the stacked autoencoder algorithm. Subsequently, in the central latent vector of the stacked autoencoder, the Fuzzy C-means clustering algorithm was applied to cluster the landslides into various groups with different risk levels, and the intervals for each group were computed using the granular computing approach. An empirical case study in Wenchuan County, Sichuan, China, was conducted. A comparative analysis with other state-of-the-art approaches including Density-based spatial clustering of applications with noise (DBSCAN), K-means clustering, and Principal Component Analysis (PCA), is provided and discussed. The experimental results demonstrate that the proposed approach using a stacked autoencoder integrated with fuzzy information granulation provides superior performance compared to those by other state-of-the-art approaches, and is capable of studying deep patterns in earthquake-induced landslide datasets and provides sufficient interpretation for field engineers.

AI Driven False Data Injection Attack Recognition Approach for Cyber-Physical Systems in Smart Cities

Abstract Cyber-physical systems (CPS) combine the typical power grid with recent communication and control technologies, generating new features for attacks. False data injection attacks (FDIA) contain maliciously injecting fabricated data as to the system measurements, capable of due to improper decisions and disruptions in power distribution. Identifying these attacks is vital for preserving the reliability and integrity of the power grid. Researchers in this domain utilize modern approaches namely machine learning (ML) and deep learning (DL) for detecting anomalous forms in the data that signify the existence of such attacks. By emerging accurate and effective detection approaches, this research purposes to improve the resilience of CPS and make sure of a secure and continuous power supply to consumers. This article presents an Improved Equilibrium Optimizer with Deep Learning Enabled False Data Injection Attack Recognition (IEODL-FDIAR) technique in a CPS platform. The main purpose of the IEODL-FDIAR technique is to enable FDIA attack detection and accomplishes security in the CPSS environment. In the presented IEODL-FDIAR technique, the IEO algorithm is used for the feature subset selection process. Moreover, the IEODL-FDIAR technique applies a stacked autoencoder (SAE) model for FDIA attack detection. Furthermore, the pelican optimization algorithm (POA) can be utilized for the optimum hyperparameter chosen for the SAE algorithm which in turn boosts the detection outcomes of the SAE model. To portray the better outcome of the IEODL-FDIAR system, a wide range of simulation analyses are executed. A wide comparison analysis described the improved results of the IEODL-FDIAR technique with existing DL models.

Exploiting Stacked Autoencoders for Improved Sentiment Analysis

Sentiment analysis is an ongoing research field within the discipline of data mining. The majority of academics employ deep learning models for sentiment analysis due to their ability to self-learn and process vast amounts of data. However, the performance of deep learning models depends on the values of the hyperparameters. Determining suitable values for hyperparameters is a cumbersome task. The goal of this study is to increase the accuracy of stacked autoencoders for sentiment analysis using a heuristic optimization approach. In this study, we propose a hybrid model GA(SAE)-SVM using a genetic algorithm (GA), stacked autoencoder (SAE), and support vector machine (SVM) for fine-grained sentiment analysis. Features are extracted using continuous bag-of-words (CBOW), and then input into the SAE. In the proposed GA(SAE)-SVM, the hyperparameters of the SAE algorithm are optimized using GA. The features extracted by SAE are input into the SVM for final classification. A comparison is performed with a random search and grid search for parameter optimization. GA optimization is faster than grid search, and selects more optimal values than random search, resulting in improved accuracy. We evaluate the performance of the proposed model on eight benchmark datasets. The proposed model outperformed when compared to the baseline and state-of-the-art techniques.

Detection of sea‐surface target of coastal defense radar based on Stacked Autoencoder (SAE) algorithm

In recent years, machine learning theory has set off a wave of research in the field of radar signal processing. In this study, a novel algorithm for sea-surface target detection based on a stacked autoencoder (SAE) is proposed, which has already been applied in the authors’ coastal defense radar system. In the proposed algorithm, the sea surface echo data are cut into a large number of two-dimensional (2-D) images through a sliding window, mapping the cell under test (CUT) and the 2-D images one by one and performing classification or detection from the perspective of 2-D signal processing. Experimental results of simulated data and real radar data show that the proposed algorithm based on the SAE has better target detection performance compared with the traditional cell averaging constant false alarm rate (CA-CFAR) algorithm. Besides, the proposed algorithm shows certain interference suppression ability in real data processing. As far as it is known, there is no public report on the detection of 2-D sea surface targets based on the SAE algorithm in coastal defense radar.

Smartphone Motion Sensor-Based Complex Human Activity Identification Using Deep Stacked Autoencoder Algorithm for Enhanced Smart Healthcare System.

Human motion analysis using a smartphone-embedded accelerometer sensor provided important context for the identification of static, dynamic, and complex sequence of activities. Research in smartphone-based motion analysis are implemented for tasks, such as health status monitoring, fall detection and prevention, energy expenditure estimation, and emotion detection. However, current methods, in this regard, assume that the device is tightly attached to a pre-determined position and orientation, which might cause performance degradation in accelerometer data due to changing orientation. Therefore, it is challenging to accurately and automatically identify activity details as a result of the complexity and orientation inconsistencies of the smartphone. Furthermore, the current activity identification methods utilize conventional machine learning algorithms that are application dependent. Moreover, it is difficult to model the hierarchical and temporal dynamic nature of the current, complex, activity identification process. This paper aims to propose a deep stacked autoencoder algorithm, and orientation invariant features, for complex human activity identification. The proposed approach is made up of various stages. First, we computed the magnitude norm vector and rotation feature (pitch and roll angles) to augment the three-axis dimensions (3-D) of the accelerometer sensor. Second, we propose a deep stacked autoencoder based deep learning algorithm to automatically extract compact feature representation from the motion sensor data. The results show that the proposed integration of the deep learning algorithm, and orientation invariant features, can accurately recognize complex activity details using only smartphone accelerometer data. The proposed deep stacked autoencoder method achieved 97.13% identification accuracy compared to the conventional machine learning methods and the deep belief network algorithm. The results suggest the impact of the proposed method to improve a smartphone-based complex human activity identification framework.

A Stacked Autoencoder Neural Network Algorithm for Breast Cancer Diagnosis With Magnetic Detection Electrical Impedance Tomography

Magnetic detection electrical impedance tomography (MDEIT) is a novel imaging technique that aims to reconstruct the conductivity distribution with electrical current injection and the external magnetic flux density measurement by magnetic sensors. Aiming at improving the resolution and accuracy of MDEIT and providing an efficient imaging method for breast cancer diagnosis, a new algorithm based on stacked auto-encoder (SAE) neural network is proposed. Both numerical simulation and phantom experiments are done to verify its feasibility. In the numerical simulation, an amount of sample data with different conductivity distribution are calculated. Then a neural network model is established and trained by training these samples. Finally, the conductivity distribution of an imaging target with the anomaly location can be reconstructed by the network model. The reconstruction result of the SAE algorithm is compared with the reconstruction results of the traditional sensitivity matrix (SM) algorithm and the back propagation (BP) neural network algorithm. Under the noise of 30dB, the relative errors of BP algorithm, SM algorithm and SAE algorithm are 137.19%, 24.90% and 15.28% respectively. Result shows by the SAE algorithm, the location of anomalies is reconstructed more accurately, the conductivity value is more closely to the real one and the anti-noise performance is more robust. At last, a breast phantom experiment by self-made platforms is completed to verify the application feasibility of the new algorithm. The relative reconstruction error of conductivity by proposed SAE algorithm can be reduced to 14.56%. The results show that by SAE algorithm, MDEIT can be a promising approach in clinical diagnosis of breast cancer, and it also provide more potential application prospect for the extensive application of MDEIT.

An Effective Cell Pathology Image Detection Method Based on Deep Stacked Auto-Encoder Combined with Random Forest

Cytopathology mainly studies the causes and pathogenesis of disease occurrence, as well as the changes in the physiological functions of cells during the process of disease occurrence, providing a basis for the prevention and diagnosis of diseases. Using computational simulation technology to accurately detect cell pathology images can effectively avoid the influence of subjective factors in diagnostic operation by pathologist, and provide reliable technical means for case diagnosis. In this study, we design an effective model to detect cell pathology images based on deep stacked auto-encoder algorithm. Firstly, the cell pathology images are preprocessed by standardization. Secondly, the processed images are sent to the stacked auto-encoder algorithm to extract theirs hidden feature information. Finally, the random forest algorithm is used to quickly and accurately detect theirs category. We introduce cross-validation in our experiments to test the robustness and stability of the results. In addition, we also compared the model based on a k-nearest neighbor classifier and achieved good results. These excellent experiment results indicated that the proposed method can accurately detect cell pathology images and can be used as a reliable tool for pathologists to diagnose rapidly.

A Label Noise Robust Stacked Auto-Encoder Algorithm for Inaccurate Supervised Classification Problems

In real applications, label noise and feature noise are two main noise sources. Similar to feature noise, label noise imposes great detriment on training classification models. Motivated by successful application of deep learning method in normal classification problems, this paper proposes a new framework called LNC-SDAE to handle those datasets corrupted with label noise, or so-called inaccurate supervision problems. The LNC-SDAE framework contains a preliminary label noise cleansing part and a stacked denoising auto-encoder. In preliminary label noise cleansing part, the K-fold cross-validation thought is applied for detecting and relabeling those mislabeled samples. After being preprocessed by label noise cleansing part, the cleansed training dataset is then input into the stacked denoising auto-encoder to learn robust representation for classification. A corrupted UCI standard dataset and a corrupted real industrial dataset are used for test, both of which contain a certain proportion of label noise (the ratio changes from 0% to 30%). The experiment results prove the effectiveness of LNC-SDAE, the representation learnt by which is shown robust.

Stacked Autoencoder for classification of glioma grade III and grade IV

Abstract Invention of the microarray technology has rendered it possible to inspect the whole genome at once in cancer classification. However, in order to curtail the computational complexity and augment the accuracy of cancer classification, it is essential to sift the vast microarray data for the informative genes. In this paper, Thresholding and Ratio methods are presented, individually as well as conjointly (hybrid method) to choose optimal gene subset from the microarray data. Moreover, Discrete Wavelet Transform (DWT) is deployed to pare the size of microarray data still further. The classification is accomplished by using various neural network algorithms and Stacked Autoencoder algorithm. The results of classification are compared for number of thresholds, ratios, wavelets and classification algorithms. It is observed that the Stacked Autoencoder network trained by Back Propagation algorithm delivers the best results in terms of classification accuracy and number of genes.