Restricted Boltzmann Machine Research Articles

Automated detection of offshore wave power using machine learning techniques

BackgroundVarious statistical methods are used for estimating sea state and wave characteristics using digital wave models. Several machine learning techniques help to develop the computational difficulties of these methods. Materials and methodsThis study aims to estimate the wave power with Extreme Learning Machine (ELM), Regression, Restricted Boltzmann Machine (RBM), and RBM-ELM methods using nonlinear wave input parameters at different depths. Furthermore, the performance criteria are improved by applying the Relief feature selection algorithm to these methods. The input bias and input weights for the ELM have been determined using the RBM. ResultsIn the RBM-based presented method, the highest estimation values were obtained using Relief feature selection and without Relief as 96.96% and 94.02%, respectively. The highest accuracy rate based on ELM is 76.86% in the estimation of wave power without Relief. In the same way, the accuracy rate with Relief was calculated as 92.16%. These values were increased to 90.10% (without Relief) and 95.73% (with Relief) using the RBM-ELM method. ConclusionsThis study demonstrates that the performance of the presented methods with Relief feature selection was improved.

On the neural network flow of spin configurations

We study the so-called neural network flow of spin configurations in the 2-d Ising ferromagnet. This flow is generated by successive reconstructions of spin configurations, obtained by an artificial neural network like a restricted Boltzmann machine or an autoencoder. It was reported recently that this flow may have a fixed point at the critical temperature of the system, and even allow the computation of critical exponents. Here we focus on the flow produced by a fully-connected autoencoder, and we refute the claim that this flow converges to the critical point of the system by directly measuring physical observables, and showing that the flow strongly depends on the network hyperparameters. We explore the network metric, the reconstruction error, and we relate it to the so called intrinsic dimension of data, to shed light on the origin and properties of the flow.

Outdoor Clothing Design for Traffic Safety Based on Big Data and Artificial Intelligence

With the development of technologies in various fields, more and more technologies have been applied to safety clothing, which has led to the rapid development of safety clothing. The improvement of living standards is accompanied by the change of consumption concepts. Consumers’ requirements for clothing products have become more artistic, healthier, and more ecological, and they look forward to more and better safety clothing to meet their health needs. In this context, this article studies traffic safety outdoor clothing design based on big data (BD) and AI. This article introduces the design method of outdoor safety clothing for traffic based on BD and machine learning in artificial intelligence (AI) and did two experiments. To this end, this paper adopts a Deep Belief Network (DBN), which is trained layer by layer through Restricted Boltzmann Machine (RBM), and successfully solves the problems of lack of a large number of labeled samples and easy to fall into local optimum. The first experiment is to test the accuracy of various machine learning algorithms for clothing size measurement. The results obtained are as follows: the predicted value of the DBN neural network is the closest to the actual value, the average prediction accuracy of DBN for the cuff size is 90%, and the average prediction accuracy for the neck circumference is 91.5%. The second experiment is to investigate the functional needs and performance concerns of children and outdoor workers. The results of the experiment are as follows: for children, 79.9% of people want clothing to have a positioning function, which accounts for the highest proportion. For outdoor workers, the most important clothing function they need is eye-catching style, and 90.1% of those choose this option. In terms of clothing performance concerns, most people choose to care very much, and the second most people choose to care about comfort.

Classification of steel based on laser-induced breakdown spectroscopy combined with restricted Boltzmann machine and support vector machine

In recent years, a laser-induced breakdown spectrometer (LIBS) combined with machine learning has been widely developed for steel classification. However, the much redundant information of LIBS spectra increases the computation complexity for classification. In this work, restricted Boltzmann machines (RBM) and principal component analysis (PCA) were used for dimension reduction of datasets, respectively. Then, a support vector machine (SVM) was adopted to process feature information. Two models (RBM-SVM and PCA-SVM) are compared in terms of performance. After optimization, the accuracy of the RBM-SVM model can achieve 100%, and the maximum dimension reduction time is 33.18 s, which is nearly half of that of the PCA model (53.19 s). These results preliminarily indicate that LIBS combined with RBM-SVM has great potential in the real-time classification of steel.

Research Based on the Application and Exploration of Artificial Intelligence in the Field of Traditional Music

Traditional Chinese music has undergone trials and tribulations. To date, traditional music has been gradually improved, preserved, and passed down, both in terms of theoretical works and traditional music varieties. However, the current state of traditional music is still a cause for concern. Whether it is scholars engaged in the study of traditional music, universities, or local government agencies, there are still areas that need to be improved individually. The need to cultivate a future audience for traditional music and to make full use of new media such as the Internet is a priority at this stage. The emergence of any new technology is bound to have some impact on the existing social system, and the emergence of artificial intelligence is no exception. Due to the limitation of technology, only a small number of basic applications have been developed, and it is the future mission of research workers whether they can develop more advanced products for music lovers to experience on the basis of ensuring the basic maturity of these applications. In this paper, we introduce the convolutional deep belief network model based on the restricted Boltzmann machine and apply the convolutional deep belief network algorithm to the music melody recognition. Firstly, it was pretrained by an unsupervised greedy layer-by-layer algorithm. Then, the network parameters were fine-tuned by a supervised network training method, and the recognition ability of the model was improved by adjusting the network parameters. The experimental results show that the recognition effect of the system is more obvious under the condition that the length of music samples is 3 s, and the recognition effect is better when the number of model layers is 2 than that when the number of layers is 1.

Artificial neural networks: Prediction for restricted Boltzmann machines

Artificial Neural Network (ANN) is the branch of Artificial Intelligence (AI) that is inspired by the architecture of the human brain. A type of recurrent ANN known as Restricted Boltzmann Machines (RBMs) are probabilistic graphical models that can be interpreted two-layered network of stochastic units with undirected connections between pairs of units in the two layers. RBMs are used specifically as a generative model. The result obtained from Neural Network Model shows 0.000373 errors with 88 steps. Prediction using neural network shows 0.9928202080, 0.3335543925 and 0.9775153014 while Converting probabilities into binary classes setting threshold level 0.5 result shows that the predicted results are 1, 0, and 1.

APPLICATION OF DEEP BOLTZMANN MACHINE IN DIAGNOSIS PROCESSES OF HEPATITIS TYPES B & C

Correct diagnosis of diseases is the main problem in medicine. Artificial intelligence and learning methods have been developed to solve problems in many fields, such as biology and medical sciences. Correct diagnosis before treatment is the most challenging and the first step in achieving proper cures. The primary objective of this paper is to introduce an intelligent system that develops beyond the deep neural network. It can diagnose and distinguish between Hepatitis types B and C by using a set of general tests for liver health. The deep network used in this research is the Deep Boltzmann Machine (DBM). Learning components within Restricted Boltzmann Machine (RBM) lead to intended results. The RBMs extract features to be used in an efficient classification process. An RBM is robust computing and well-suited to extract high-level features and diagnose hepatitis B and C. The method was tested on general items in laboratory tests that check the liver’s health. The DBM could predict hepatitis type B and C with an accuracy between 90.1% and 92.04%. Predictive accuracy was obtained with10-fold cross-validation. Compared with other methods, simulation results on DBM architecture reveal the proposed method’s efficiency in diagnosing Hepatitis B and C. What made this approach successful was a deep learning network in addition to discovering communication and extracting knowledge from the data.

A random energy approach to deep learning

We study a generic ensemble of deep belief networks (DBN) which is parametrized by the distribution of energy levels of the hidden states of each layer. We show that, within a random energy approach, statistical dependence can propagate from the visible to deep layers only if each layer is tuned close to the critical point during learning. As a consequence, efficiently trained learning machines are characterised by a broad distribution of energy levels. The analysis of DBNs and restricted Boltzmann machines on different datasets confirms these conclusions.

A feature learning method for rotating machinery fault diagnosis via mixed pooling deep belief network and wavelet transform

Deep learning has extensive application in fault diagnosis regarding the health monitoring of machinery core components. Although deep networks have better nonlinear representation ability, they inevitably introduce a large number of parameters, resulting in slow model training, as well as poor generalization. Additionally, the compound fault tends to be neglected in conventional fault diagnosis. For this purpose, a bearing fault diagnosis method based on mixed pooling deep belief network (MP-DBN) is suggested. Firstly, the Morlet wavelet is adopted for obtaining the corresponding time–frequency representation to enhance analysis efficiency. Then, a new MP-DBN model with a mixed pooling layer and restricted Boltzmann machines (RBM) is constructed to reduce the effects of overfitting and the parameters scale. Finally, the MP-DBN-based method is employed for the bearings in the laboratory and actual working circumstances to verify its performance. The results show that MP-DBN is a powerful compound fault diagnosis technique for rolling bearings with superior feature extraction ability and diagnosis efficiency.

Accident Detection in Autonomous Vehicles Using Modified Restricted Boltzmann Machine

Accident detection in autonomous vehicles could save lives by reducing the time it takes for information to reach emergency responder. One of the most common reason for the death of humans is accident. Indeed, it was determined throughout the survey that road accidents are indeed the second greatest cause of death in the United States for people aged 30 to 44 years, representing for 1/3 among all deaths. The transportation industry is increasingly relying on mathematical methods and new data assets to detect injuries. Many machine learning and deep learning models have already been proposed for accident detection but still there is much space for further improvement to be done to save human lives in case of accident detection, if accidents are not identified well. In our present study, we proposed modified restricted Boltzmann machine for accident detection. Our proposed methodology consists of the following steps. In the first step, we took different accidental and nonaccidental images as an input. In the second step, we applied our proposed deep learning technique modified restricted Boltzmann machine. In the third step, when weight acceleration and coefficient adjustments are run as a generalization mechanism, then we check our model performance after applying through multiple procedures. As a result, multiple images are classified as accidental and nonaccidental images of vehicles. Proposed methodology has been applied for data set, and data have been divided into different training and testing ratios. The proposed MRBM model has an accuracy of 98% in classification of both accidental and nonaccidental images of vehicles. The proposed model outperforms the competition significantly than other in which they are compared like artificial neural network, support vector machine, and restricted Boltzmann machine techniques.

Interactive 3D reconstruction method of fuzzy static images in social media

Abstract Because the traditional social media fuzzy static image interactive three-dimensional (3D) reconstruction method has the problem of poor reconstruction completeness and long reconstruction time, the social media fuzzy static image interactive 3D reconstruction method is proposed. For preprocessing the fuzzy static image of social media, the Harris corner detection method is used to extract the feature points of the preprocessed fuzzy static image of social media. According to the extraction results, the parameter estimation algorithm of contrast divergence is used to learn the restricted Boltzmann machine (RBM) network model, and the RBM network model is divided into input, output, and hidden layers. By combining the RBM-based joint dictionary learning method and a sparse representation model, an interactive 3D reconstruction of fuzzy static images in social media is achieved. Experimental results based on the CAD software show that the proposed method has a reconstruction completeness of above 95% and the reconstruction time is less than 15 s, improving the completeness and efficiency of the reconstruction, effectively reconstructing the fuzzy static images in social media, and increasing the sense of reality of social media images.

Deep scalable and distributed restricted boltzmann machine for recommendations

Deep scalable and distributed restricted boltzmann machine for recommendations

Research on Virtual Interactive Animation Design System Based on Deep Learning.

With the rapid development of computer network technology, the advantages of virtual reality technology in the field of instant messaging are becoming more and more significant. Virtual reality technology plays an important role in communication networks, including enhanced resource utilization, device redundancy, immersion, interactivity, conceptualization, and holography. In this paper, we use the basic theory of Restricted Boltzmann Machine to establish a semisupervised spatio-temporal feature model through the animation capture data style recognition problem. The bottom layer can be pretrained with a large amount of unlabeled data to enhance the model's feature perception capability of animation data, and then train the high-level supervised model with the labeled data to finally obtain the model parameters that can be used for the recognition task. The layer-by-layer training method makes the model have good parallelism, that is, when the layer-by-layer training method makes the model well parallelized, that is, when the bottom features cannot effectively represent the animation features, such as overfitting or underfitting, only the bottom model needs to be retrained, while the top model parameters can be kept unchanged. Simulation experiments show that the design assistance time of this paper's scheme for animation is reduced by 10 minutes compared to baseline.

Shallow and deep learning of an artificial neural network model describing a hot flow stress Evolution: A comparative study

In recent years, the utilization of artificial neural networks (ANNs) as regression models to solve the issue of hot flow stress forecasting has become a standard approach. In a connection with this kind of regression issue, employed ANNs are usually learned via a shallow learning technique while only limited attention has been paid to a deep learning method. In the frame of the submitted research, the shallow learning approach is thoroughly compared to the deep learning techniques which are based on the use of a Restricted Boltzmann Machine (RBM) and an Auto-Encoder (AE). To do so, these learning techniques are applied on a feed-forward multi-layer ANN describing the experimental hot flow curve dataset of micro-alloyed medium carbon steel. In comparison with the shallow learning method, both deep learning approaches provided higher accuracy in the network response – especially in the case of a higher number of hidden layers. The results have also shown that neither the RBM-based deep learning method nor the AE-based method had a significant effect on the duration of the necessary calculations. However, it turned out that the RBM-based method can, under certain conditions, lead to a more reliable network performance.

The Use of Deep Learning-Based Intelligent Music Signal Identification and Generation Technology in National Music Teaching.

The research expects to explore the application of intelligent music recognition technology in music teaching. Based on the Long Short-Term Memory network knowledge, an algorithm model which can distinguish various music signals and generate various genres of music is designed and implemented. First, by analyzing the application of machine learning and deep learning in the field of music, the algorithm model is designed to realize the function of intelligent music generation, which provides a theoretical basis for relevant research. Then, by selecting massive music data, the music style discrimination and generation model is tested. The experimental results show that when the number of hidden layers of the designed model is 4 and the number of neurons in each layer is 1,024, 512, 256, and 128, the training result difference of the model is the smallest. The classification accuracy of jazz, classical, rock, country, and disco music types can be more than 60% using the designed algorithm model. Among them, the classification effect of jazz schools is the best, which is 77.5%. Moreover, compared with the traditional algorithm, the frequency distribution of the music score generated by the designed algorithm is almost consistent with the spectrum of the original music. Therefore, the methods and models proposed can distinguish music signals and generate different music, and the discrimination accuracy of different music signals is higher, which is superior to the traditional restricted Boltzmann machine method.

A semi-supervised classification RBM with an improved fMRI representation algorithm

Background and objectiveTraining an effective and robust supervised learning classifier is not easy due to the limitations of acquiring and labeling considerable human functional magnetic resonance imaging (fMRI) data. Semi-supervised learning uses unlabeled data for feature learning and combines them into labeled data to build better classification models. MethodsSince no premises or assumptions are required, a restricted Boltzmann machine (RBM) is suitable for learning data representation of neuroimages. In our study, an improved fMRI representation algorithm with a hybrid L1/L2 regularization method (HRBM) was proposed to optimize the original model for sparsity. Different from common semi-supervised classification models that treat feature learning and classification as two separate training steps, we then constructed a new semi-supervised classification RBM based on a joint training algorithm with HRBM, named Semi-HRBM. This joint training algorithm jointly trains the objective function of feature learning and classification process, so that the learned features can effectively represent the original fMRI data and adapt to the classification tasks. ResultsThis study uses fMRI data to identify categories of visual stimuli. In the fMRI data classification task under four visual stimuli (house, face, car, and cat), our HRBM has satisfactory feature representation capabilities and better performance for multiple classification tasks. Taking the supervised RBM (sup-RBM) as an example, our Semi-HRBM classification model improves the average accuracy of the four-classification task by 7.68%, and improves the average F1 score of each visual stimulus task by 8.90%. In addition, the generalization ability of the model was also improved. ConclusionThis research might contribute to enrich solutions for insufficiently labeled neuroimaging samples, which could help to identify complex brain states under different stimuli or tasks.

Classifying pedestrian trajectories by Machine learning using laser sensor data

Abstract. In the field of facility planning, the analysis of pedestrian trajectories using laser sensor-based behavior monitoring technologies is a proven way to improve our understanding of the behavioral features of foot-travelers. While these technologies can gather large volumes of trajectory data, the analysis of such data is a chaotic and complicated task and creates a large workload if it must be interpreted visually by human analysts. Hence, a method is needed for automatically extracting the features and their separate components from pedestrian trajectories and patterns. This study proposes just such a method based on a Restricted Boltzmann machine, a machine learning tool, to automatically extract and classify the latent features of pedestrian trajectories. Our method was applied to data taken in the outpatient waiting area of a hospital and the machine learning generated results were compared to those of visual classifications by human analysts. It was shown to be functional for classifying trajectories by orientation, stopping location and walking speed, and was considered effective for furnishing rough classifications resembling the intuition-based classifications of a human analyst.

Deep Learning Algorithm-Based Magnetic Resonance Imaging Feature-Guided Serum Bile Acid Profile and Perinatal Outcomes in Intrahepatic Cholestasis of Pregnancy.

This study was aimed to explore magnetic resonance imaging (MRI) based on deep learning belief network model in evaluating serum bile acid profile and adverse perinatal outcomes of intrahepatic cholestasis of pregnancy (ICP) patients. Fifty ICP pregnant women diagnosed in hospital were selected as the experimental group, 50 healthy pregnant women as the blank group, and 50 patients with cholelithiasis as the gallstone group. Deep learning belief network (DLBN) was built by stacking multiple restricted Boltzmann machines, which was compared with the recognition rate of convolutional neural network (CNN) and support vector machine (SVM), to determine the error rate of different recognition methods on the test set. It was found that the error rate of deep learning belief network (7.68%) was substantially lower than that of CNN (21.34%) and SVM (22.41%) (P < 0.05). The levels of glycoursodeoxycholic acid (GUDCA), glycochenodeoxycholic acid (GCDCA), and glycocholic acid (GCA) in the experimental group were dramatically superior to those in the blank group (P < 0.05). Both the experimental group and the blank group had notable clustering of serum bile acid profile, and the experimental group and the gallstone group could be better distinguished. In addition, the incidence of amniotic fluid contamination, asphyxia, and premature perinatal infants in the experimental group was dramatically superior to that in the blank group (P < 0.05). The deep learning confidence model had a low error rate, which can effectively extract the features of liver MRI images. In summary, the serum characteristic bile acid profiles of ICP were glycoursodeoxycholic acid, glycochenodeoxycholic acid, and glycocholic acid, which had a positive effect on clinical diagnosis. The toxic effects of high concentrations of serum bile acids were the main cause of adverse perinatal outcomes and sudden death.

The Application of the Gestalt Theory in Music Psychotherapy for Piano.

This paper presents an in-depth study and analysis of the application of the Gestalt theory to music psychotherapy for piano. The paper focuses on how to apply the “whole and part” and “epiphany” perspectives of the Gestalt learning theory to singing and music appreciation lessons. In addition, the Gestalt school's ideas of developing creative thinking, creating problematic situations, and transferring learning were demonstrated through the implementation of teaching cases. There are differences in the effects of different music on the distribution of body surface temperature; there are differences in the effects of yang music on the Directing Vessel compared to the effects of yin music on the Directing Vessel, and the effects are following the hierarchical model of thinking; there are individual differences in the magnitude of the effects of the same music on the body surface temperature of different people, and the identification of music needs to be combined with the three factors. The wavelet energy entropy (WEE) characteristics of EEG signals were extracted as the input of the designed and optimized deep belief network model, and the average emotional classification accuracy of EEG signals in the left and right brain regions could be obtained as 84.20% and 83.07%, respectively, under the condition of distinguishing brain regions and different music environments. Compared with the classification accuracies of DBN, restricted Boltzmann machine (RBM), and K nearest neighbor (kNN) algorithms in mixed music environments, the classification effects were improved by about 3.49%, 12.89%, and 7.24%. Relying on the ability-poor theory and Weiner attribution theory, different types of secondary school students, their psychological characteristics, and their causes were pointed out. Combined with the psychological characteristics, the case study illustrates the positive effect of music therapy on psychological support.

Approximation properties of Gaussian-binary restricted Boltzmann machines and Gaussian-binary deep belief networks

Despite the successful use of Gaussian-binary restricted Boltzmann machines (GB-RBMs) and Gaussian-binary deep belief networks (GB-DBNs), little is known about their theoretical approximation capabilities to represent distributions of continuous random variables. In this paper, we address the expressive properties of GB-RBMs and GB-DBNs, contributing theoretical insights to the optimal number of hidden variables. We first treat the GB-RBM’s unnormalized log-likelihood as a sum of a special two-layer feedforward neural network and a negative quadratic term. Then, a series of simulation results are established, which can be used to relate GB-RBMs to general two-layer feedforward neural networks whose expressive properties are much better understood. On this basis, we show that a two-layer ReLU network with all weights in the second layer being 1, along with a negative quadratic term, can approximate all continuous functions. In addition, we provide qualified lower bounds for the number of hidden variables of GB-RBMs required to approximate distributions whose log-likelihood are given by some classes of smooth functions. Moreover, we further study the universal approximation of GB-DBNs with two hidden layers by providing a sufficient number of hidden variables O(ɛ−2) that are guaranteed to approximate any given strictly positive continuous distribution within a given error ɛ. Finally, numerical experiments are carried out to verify some of the proposed theoretical results.