Propagation Neural Network Research Articles

Weight Loss Prediction Model for Pig Carcass Based on a Genetic Algorithm Back- Propagation Neural Network

HighlightsWe propose five spraying parameters according to the characteristics of pig carcasses in the spray-chilling process.A prediction model for pig carcass weight loss, based on a genetic algorithm back-propagation neural network, is proposed to reveal the relationship between weight loss and spraying parameters.To study the effects of various spraying parameters on weight loss, an automatic spray-chilling device was designed, which can modify up to five spraying parameters.Abstract. Because the weight loss of a pig carcass in the spray-chilling process is easily affected by the spraying frequency and duration, a prediction model for weight loss based on a genetic algorithm (GA) back-propagation (BP) neural network is proposed in this article. With three-way crossbred pig carcasses selected as the test materials, the duration and time interval of high-frequency spraying, the duration and time interval of low-frequency spraying, and the duration of a single spray were selected as inputs to the network model. The weight and threshold of the network were then optimized by the GA. The prediction model for pig carcass weight loss established by the GA BP neural network yielded a correlation coefficient of R = 0.99747 between the network output value of the test samples and the target value. Weight loss prediction by the model is feasible and allows better expression of the nonlinear relationship between weight loss and the main controlling factors. The results can be a reference for chilled meat production. Keywords: BP neural network, Genetic algorithm, Pig carcass, Predictive model, Weight loss

Genetic Algorithm – Back Propagation (GA-BP) Neural Network for Chlorophyll-a Concentration Inversion Using Landsat 8 OLI Data

Chlorophyll-a (Chl-a) accurate inversion in inland water is important for water environmental protection. In this study, we tested the Genetic Algorithm optimized Back Propagation (GA-BP) neural network model to precisely simulated the Chl-a in an inland lake using Landsat 8 OLI images. The result show that the R2 of GA-BP neural network model has increased 28.17% compared to traditional BP neural network model. Then this GA-BP model was applied to another two scenes of Landsat 8 OLI image with the R2 of 0.961, 0.954 respectively for March 26 2018, October 26 2018. And the spatial distribution have shown a reasonable result of Chl-a variation in Lake Donghu. This study can provide a new method for Chla concentration inversion in urban lakes and support water environment protection on a large scale.

Prediction of three-dimensional coordinate measurement of space points based on BP neural network

In order to improve the measurement accuracy of three-dimensional coordinate measurement system based on dual-PSD, this paper proposes a three-dimensional coordinate measurement method based on back propagation (BP) neural network considering the high ability of the neural network to deal with the complex nonlinear mapping problem. This method can describe the mapping relationship between three-dimensional coordinates of space points in the world coordinate system and coordinates of light spots on dual-PSD well. Levenberg-Marquardt learning algorithm is used to train the network, and then trained BP neural network model is used to predict three-dimensional coordinates of space points. Experimental results show that the average measurement error of space points obtained by the method is low. It proves that the built BP neural network model can be used to predict three-dimensional coordinates of space points. [Submitted 9 July 2018; Accepted 30 October 2018]

Path Trajectory Prediction of Rapidly Rotated Ping Pong Ball after Hitting

The path trajectory prediction of rapidly rotated ping pong ball after hitting plays a great role in the training of athletes and even in the competition. It can improve the level and efficiency of training. Therefore it is necessary to optimize the parameters of ping pong ball such as position, angle and speed after hitting to complete data collection. This study established a prediction model of the path trajectory of rapidly rotated ping pong ball after hitting and predicted the path trajectory using extreme learning machine (ELM) algorithm and back propagation (BP) neural network. The results were compared to find out the better algorithm. Moreover the two algorithms were improved. The result demonstrated that the improved EML algorithm could realize minimum error.

Study on the intelligent system of sports culture centers by combining machine learning with big data

With the vigorous development of sports, people’s awareness of engaging in sports has gradually increased, and the requirements for a sports culture center have been higher. However, the service system of traditional sports cultures center is single, which cannot meet people’s growing experience needs. Therefore, it is urgent for the service system of sports culture centers to move towards intellectualization. Firstly, this paper discusses the service system of traditional sports culture centers and finds that there are some problems, such as slow transmission of information, poor sharing of resources, and weak flexibility of response, which seriously affect the consumer experience of users and restrict the development of sports culture centers. Then, with the help of computer network technology, the design of intelligent system architecture of sports culture centers is completed, which makes many intelligent subsystems interconnected and interoperable, integrates information, realizes the integration of data application network, and achieves the goal of resource sharing and function upgrading. Then, based on the intelligent system, the big data platform is built with the help of big data technology, and the support vector machine-back propagation (SVM-BP) neural network composite model is used to realize the prediction of the passenger flow in the cultural center, which provides guidance for adjusting the service plan in advance, effectively coping with the peak passenger flow and improving the user experience. Finally, through empirical analysis, we know that the design of an intelligent system greatly improves the service quality of cultural centers. The research results not only achieve a significant increase in passenger flow but also provide an effective way for the service of sports culture centers to move towards intellectualization.

Analysis of pressure distribution during movement for the top part of female socks

Female sports socks were studied to achieve the correlation between the ankle surface curvature and pressure distribution of the top part of socks. The transverse tension performance of the socks’ top part was obtained using an Instron universal strength tester, and the leg size was measured with a [TC]2 contactless 3D body scanner. The pressure was monitored by a Pliance-X-32 pressure test system. Gray correlation, variance, and regression analysis were applied to study the correlation between movement velocity, fabric performance, leg circumference, and ankle pressure distribution. The dynamic pressure prediction models of multiple regression and back propagation (BP) neural network on the top part of socks were also established. The results show that the transverse tension performance and sock density have a significant effect on the ankle static pressure. Movement velocity, sock density, and leg circumference are positively correlated with dynamic pressure, while the elastic recovery rate of the fabric is negatively correlated with the pressure. Both of the multiple regression and BP neural network models can predict the dynamic pressure, and the BP neural network model is better than multiple regression at prediction error, which was kept to less than 0.5%. Therefore, the BP neural network model can be effectively used in female ribbed sock top design.

A Knowledge Base System for Operation Optimization: Design and Implementation Practice for the Polyethylene Process

Abstract Setting up a knowledge base is a helpful way to optimize the operation of the polyethylene process by improving the performance and the efficiency of reuse of information and knowledge—two critical elements in polyethylene smart manufacturing. In this paper, we propose an overall structure for a knowledge base based on practical customer demand and the mechanism of the polyethylene process. First, an ontology of the polyethylene process constructed using the seven-step method is introduced as a carrier for knowledge representation and sharing. Next, a prediction method is presented for the molecular weight distribution (MWD) based on a back propagation (BP) neural network model, by analyzing the relationships between the operating conditions and the parameters of the MWD. Based on this network, a differential evolution algorithm is introduced to optimize the operating conditions by tuning the MWD. Finally, utilizing a MySQL database and the Java programming language, a knowledge base system for the operation optimization of the polyethylene process based on a browser/server framework is realized.

Edge micro-creation of Ti(C, N) cermet inserts by micro-abrasive blasting process and its tool performance

In this study, the cutting edge passivation by a micro-abrasive blasting method for cermet inserts and its machining performance were investigated. The micro-abrasive blasting parameters for cermet inserts were optimized and the micro-creation of cutting edge was determined with detail. A Back Propagation (BP) neural network prediction model was further established based on our micro-abrasive blasting experiment datum, which can directly evaluate the micro-abrasive blasting ability to generate the specific edge radius. The improvement of cutting performance of micro-abrasive blasted cermet inserts benefits from the strengthening of cutting edge that caused by the obvious elimination of a large number of micro-defects rooted around the edge, and the formation of circular cutting edge is the result of brittle removal and plastic removal. The micro-creation of inserts can acquire a circular cutting edge, and the optimal edge radius is 15 μm under the selected cutting conditions when the tool life was chosen as an optimization target and the surface roughness was simultaneously taken into account. It is found that the blasted cermet inserts can prolong the tool life by at least 86% and the machined-surface quality can be improved by up to 1.65 μm, compared to inserts without micro-abrasive blasting.

Optical Lensless-Camera Communications Aided by Neural Network

Currently, the optical components of a camera embedded in the device constrain its overall thickness. Moreover, if the camera is strongly shaken, the lens and sensor may be misaligned, resulting in a defocusing effect. In this paper, we propose a novel lensless-camera communication model, which removes the lens of camera, therefore decreasing the overall thickness of the device without affecting communications. To decode the images captured by the lensless camera, a decoding algorithm aided by back propagation (BP) neural network was designed, which recognizes the blurred image patterns efficiently. To adapt to time-varying environments, an adaptive training sequence adjustment mechanism was designed. Simulation results show that the proposed image decoding algorithm presents a good bit-error-rate (BER) performance. The proposed system has robust movements and provides resilience to interference, benefiting from the neural network and the designed algorithm.

Identification-based aeroengine nonlinear modeling: a comparative study

Aeroengine modeling plays an important role in the development of advanced controls and other intelligent functions such as engine health management etc. This is particularly true for those on-board applications, where identification-based modeling approaches are often utilized. While linear modeling methodologies have been extensively introduced in the literature, identification-based nonlinear modeling should be investigated, due to the inherent nonlinear nature of an aeroengine’s dynamical properties. Three approaches, i.e., back propagation (BP) neural networks (BPNN), improved BP neural networks (IBPNN), and a piecewise nonlinear autoregression with extra inputs (PNARX) model, are presented. A comparative study is given for systematic development and illustration of nonlinear modeling techniques. Some practical considerations are also given for guidance of implementing the identification-based nonlinear modeling methodologies.

Generation and Analysis of Gridded Visibility Data in the Arctic

With the accelerated warming of the arctic and the gradual opening of the Arctic passages, more and more attention has been paid to assessing the risk of the navigation environment in the Arctic. Due to the scarcity of visibility data in the Arctic, this study proposes a model for referring visibility based on a back propagation (BP) neural network. The reliability of the model is validated and the gridded atmospheric visibility data in the Arctic from 2009 to 2018 was obtained. At the same time, this study analyzed the spatial and temporal features of visibility in the Arctic. The results show that the mean relative error is less than 20% under the different sample forms and it is more accurate to infer the visibility in a specific month using the multiple-year data of that month as training samples. Furthermore, the amount of sample data has a positive effect on the accuracy of inferred visibility, but the effect decreases with data quantity increasing. Visibility changes quickly in the south of 80° N in August, but slowly in the north in that time. At the same time, visibility in July and August is lower than that in other months but higher in March and May.

Extraction of built-up areas from Landsat-8 OLI data based on spectral-textural information and feature selection using support vector machine method

Information of built-up area is essential for various applications, such as sustainable development or urban planning. Built-up area extraction using optical data is challenging due to spectral confusion between built-up and other classes (bare land or river sand, etc.). Here an automated approach has been proposed to generate built-up maps using spectral-textural features and feature selection techniques. Eight Grey-Level Co-Occurrence Matrix based texture features are extracted using Landsat-8 Operational Land Imager bands and combined with multispectral data. The most informative features are selected from combined spectral-textural dataset using feature selection techniques. Further, Support Vector Machine (SVM) classifiers are trained on labelled samples using optimal features and results are compared with Back Propagation-Neural Network (BP-NN) and k-Nearest Neighbour (k-NN). The results show that inclusion of textural features and applying feature selection methods increases the highest overall accuracy of Linear-SVM, RBF-SVM, BP-NN, and k-NN by 9.20%, 9.09%, 8.42%, and 7.39%, respectively.

PREDICTION OF TRAFFIC ACCIDENT SEVERITY USING DATA MINING TECHNIQUES IN IBB PROVINCE, YEMEN

Traffic accidents are the leading causes beyond death; it is the concern of most countries that strive for finding radical solutions to this problem. There are several methods used in the process of forecasting traffic accidents such as classification, assembly, association, etc. This paper surveyed the latest studies in the field of traffic accident prediction; the most important tools and algorithms were used in the prediction process such as Back- propagation Neural Networks and the decision tree. In addition, this paper proposed a model for predicting traffic accidents based on dataset obtained from the Directorate General of Traffic Statistics, Ibb, Yemen.

No-reference quality assessment for contrast-distorted images based on multifaceted statistical representation of structure

In many real-world applications, images are prone to be degraded by contrast distortions during image acquisition. Quality assessment for contrast-distorted images is vital for benchmarking and optimizing the contrast-enhancement algorithms. To this end, this paper proposes a no-reference quality metric for contrast-distorted images based on Multifaceted Statistical representation of Structure (MSS). The “Multifaceted” has two meanings, namely (1) not only the luminance information, but also the chromatic information is used for structure representation. This is inspired by the fact that the chromatic information on the one hand affects the perception of image quality as well, and on the other hand it changes along with the contrast distortions. Therefore, the chromatic information should be integrated with the luminance information for quality assessment of contrast-distorted images, a fact most existing quality metrics overlook; (2) regarding structure representation, three aspects, i.e. spatial intensity, spatial distribution, and orientation of structures are calculated, which is enlightened by the fact that the human visual system (HVS) is sensitive to the three aspects of structures. Specifically, the image is first transformed from RGB to the S-CIELAB color space to obtain a representation that is more consistent with the characteristics of the HVS, as well as to separate the chromatic information from the luminance. Then the statistical structural features are extracted from both luminance and chromatic channels. Finally, the back propagation (BP) neural network is adopted to train a quality prediction model. Experimental results conducted on four public contrast-distorted image databases demonstrate the superiority of the proposed method to the relevant state-of-the-arts.

PNitro-Tyr-PseAAC: Predict Nitrotyrosine Sites in Proteins by Incorporating Five Features into Chou's General PseAAC.

Closely related to causes of various diseases such as rheumatoid arthritis, septic shock, and coeliac disease; tyrosine nitration is considered as one of the most important post-translational modification in proteins. Inside a cell, protein modifications occur accurately by the action of sophisticated cellular machinery. Specific enzymes present in endoplasmic reticulum accomplish this task. The identification of potential tyrosine residues in a protein primary sequence, which can be nitrated, is a challenging task. To counter the prevailing, laborious and time-consuming experimental approaches, a novel computational model is introduced in the present study. Based on data collected from experimentally verified tyrosine nitration sites feature vectors are formed. Later, an adaptive training algorithm is used to train a back propagation neural network for prediction purposes. To objectively measure the accuracy of the proposed model, rigorous verification and validation tests are carried out. Through verification and validation, a promising accuracy of 88%, a sensitivity of 85%, a specificity of 89.18% and Mathew's Correlation Coefficient of 0.627 is achieved. It is concluded that the proposed computational model provides the foundation for further investigation and be used for the identification of nitrotyrosine sites in proteins.

Toxic gas dispersion prediction for point source emission using deep learning method

Accurate and rapid toxic gas concentration prediction model plays an important role in emergency aid of sudden gas leak. However, it is difficult for existing dispersion model to achieve accuracy and efficiency requirements at the same time. Although some researchers have considered developing new forecasting models with traditional machine learning, such as back propagation (BP) neural network, support vector machine (SVM), the prediction results obtained from such models need to be improved still in terms of accuracy. Then new prediction models based on deep learning are proposed in this paper. Deep learning has obvious advantages over traditional machine learning in prediction and classification. Deep belief networks (DBNs) as well as convolution neural networks (CNNs) are used to build new dispersion models here. Both models are compared with Gaussian plume model, computation fluid dynamics (CFD) model and models based on traditional machine learning in terms of accuracy, prediction time, and computation time. The experimental results turn out that CNNs model performs better considering all evaluation indexes.

An adaptive power distribution control strategy for an electric vehicle with dual-motor coupling in consideration of road gradient

An optimal power distribution control strategy is proposed in consideration of road gradient. Two original contributions are made to distinguish our work from current research. First, a sub-optimal State of Charge (SOC) predictive model is proposed based on Back Propagation (BP) neural network. The sampling set of the BP is obtained from the optimal results from Dynamic Programming (DP), based on a series of driving cycles in real-world and the corresponding road gradient. Second, an adaptive control method based on PID is proposed with the designed sub-optimal SOC predictive model. Specifically, the optimal shift schedule of the coupler is designed offline based on DP and is implemented into the controller in a prior fashion, to decouple the relationship between the coupler and the motors. Simulation results demonstrate that the proposed adaptive control strategy can realise optimally real-time power distribution control and is better than rule-based power distribution strategy.

Intelligent evaluation and computation of food packaging culture in Shanghai

Presently, the priority of the design in Shanghai is to quantitatively evaluate food packaging culture connotation with intelligence. This paper introduces analytic hierarchy process (AHP) to establish Shanghai food packaging culture evaluation system and determine its index factors with ample computation. By selecting 50 sets of sample data, using artificial intelligence (AI) and back propagation (BP) neural network, the paper builds up Shanghai food packaging intelligent evaluation system, and provides a theoretical basis for the scientific computation on Shanghai food packaging culture connotation.

Visual prediction of gas diffusion concentration based on regression analysis and BP neural network

In order to realise the prediction of the diffusion trend of chemical gases under toxic, flammable, and explosive conditions, this article used a multiple regression model and a back propagation (BP) neural network model, established two kinds of leakage gas diffusion models based on Fluent simulation data. First, the multivariate function relation between multiple influencing factors and diffusion concentration is established by using linear fitting method, i.e. multivariate regression model. Second, according to the large number and non-linearity of Fluent simulation data of leakage gas, a three-layer BP neural network prediction model for leakage gas, wind speed, X-axis diffusion distance, and Y-axis diffusion distance was established by using BP neural network algorithm. Under the same data conditions, the prediction error of BP neural network prediction model is smaller than that of multivariate reversion model, and the fitting degree is high, but the stability of multiple linear regression is better.

Electronic Systems Diagnosis Fault in Gasoline Engines Based on Multi-Information Fusion.

The rapid development of electronic techniques in automobile has led to an increase of potential safety hazards, thus, a strong on-board diagnostic (OBD) system is desperately needed. To solve the problem of OBD insensitivity to manufacture errors or aging faults, the paper proposes a novel multi information fusion method. The diagnostic model is composed of a data fusion layer, feature fusion layer, and decision fusion layer. They are based on the back propagation (BP) neural network, support vector machine (SVM), and evidence theory, respectively. Algorithms are mainly focused on the reliability allocation of diagnostic results, which come from the data fusion layer and feature fusion layer. A fault simulator system was developed to simulate bias and drift faults of the intake pressure sensor. The real vehicle experiment was carried out to acquire data that are used to verify the availability of the method. Diagnostic results show that the multi-information fusion method improves diagnostic accuracy and reliability effectively. The study will be a promising approach for the diagnosis bias and drift fault of sensors in electronic control systems.