Multiple Artificial Neural Network Research Articles

다중회귀분석 및 인공신경망을 이용한 과부하 굴삭기 소음의 음질 인덱스

다중회귀분석 및 인공신경망을 이용한 과부하 굴삭기 소음의 음질 인덱스

Wearable Continuous Body Temperature Measurement Using Multiple Artificial Neural Networks

Continuous body temperature measurement (CBTM) is of great significance for human health state monitoring. To avoid interfering with users' daily activities, CBTM is usually achieved using wearable noninvasive thermometers. Current wearable noninvasive thermometers employ steady-state models used in nonwearable thermometers; as a result, the reaction time is long and the measurement can be disturbed by users' activities. However, there is no work to solve these issues. In this paper, first, differences between wearable and nonwearable temperature measurement are analyzed. Second, the relationship among the human body temperature, the skin temperature, and the device temperature is modeled based on artificial neural networks (ANNs). Third, this paper proposes a novel multiple ANNs-based wearable CBTM method. Experiments show that the reaction time of the proposed method is about one-tenth of that of other popular wearable noninvasive CBTM methods, while the accuracy and the robustness are improved.

Model of Multiple Artificial Neural Networks Oriented on Sales Prediction and Product Shelf Design

Model of Multiple Artificial Neural Networks Oriented on Sales Prediction and Product Shelf Design

Modeling and simulation of river discharge using artificial neural networks

The study developed multiple artificial neural network models with the aim of establishing the most suitable non-linear discharge perdition model of Ibu River. A 12-year daily discharge of River Ibu gauged near Sagamu was obtained from the Ogun-Oshun River Basin Development Authority (OORBDA), Abeokuta Nigeria to model and simulate daily discharge. The back-propagation method was used in developing the artificial neural network model. The study revealed that only three artificial neural network (ANN) models out of fifteen developed, have overall results that are satisfactory for prediction, out of these, the model with the least error was used for validation. The results obtained with ANNs based on two hidden layers for 1-day ahead are better than those obtained by models with single layers. It was concluded that the general performance of ANN models depends solely on the data used. While it was recommended that additional basin characteristics such as slope, geology, morphology and surface roughness features should be included to obtain more robust river discharge models. Keywords: Artificial Neural Network, Hydrologic record, Prediction

Modelling asphalt pavement analyzer rut depth using different statistical techniques

Different computer-operated temperature-controlled equipments are used to predict asphalt mixture performance in laboratory at approximately similar conditions to actual in-service pavements. Asphalt pavement analyzer (APA) is one such multi-functional sophisticated equipment. Wearing course layers are primarily attributable to be deteriorated by rutting distress in flexible asphalt pavements. Therefore, 30 representative wearing course mixtures commonly used in road pavements were tested for rutting distress using APA. Mixtures were evaluated based on their rutting performance and found that consistent ranking has been observed at temperature conditions of 40°C and 50°C. It was observed that APA rut depth could be effectively modelled using statistical techniques of multiple non-linear regression and artificial neural network. Novel aggregate material indices designated as ‘aggregate source index’ and ‘aggregate gradation index’ were developed in this study. Based on past literature; temperature, aggregate source index (ASI), aggregate gradation index, bitumen penetration values, and number of APA loading cycles/strokes were included as independent variables in the model developed for selected asphalt mixtures. It has been concluded from the values of non-linear regression parameters that temperature has the highest significance for rut depth prediction, followed by the bitumen penetration value, ASI, aggregate gradation index and number of loading cycles. Statistical parameters i.e. coefficient of determination, root mean squared error, values account for, and mean absolute percentage error showed that the artificial neural network technique better predicts the APA rut depth as compared to multiple non-linear regression techniques.

Cost Estimation Model for I-Girder Bridge Superstructure Using Multiple Linear Regression and Artificial Neural Network

One of the owner’s common problem before executing construction projects is the complexity in estimating the project cost in an early stage. Inaccurate cost estimation will force the owner to make further arrangement to the project budget. This study aims to develop an initial cost estimation model for superstructures of Precast I-girder Bridge. Cost estimation model was developed based on thirteen data of detail engineering design of I-girder bridge in Daerah Istimewa Yogyakarta (DIY). Factors influencing the cost of the superstructures of the I-girder bridge were identified. Bridge span and width, the size of the sidewalk, and railing’s type are considered as variables affecting the cost of superstructures. These variables are then arranged into two different analysis Multiple Linear Regression (MLR) analysis and Artificial Neural Network (ANN), in order to obtain the best estimation model. The results of the analysis showed that bridge span and width were the significant factors influencing cost. The correlation value of bridge span is 89.0%, bridge width is 74.2%, the size of the sidewalk is 66.1%, and railing’s type is 46.1% as identified factors that affect the cost of the superstructure. A comparative model of two approaches shows that the ANN has better accuracy than that of MLR, although the difference was not significant.

Impact of metal ionic characteristics on adsorption potential of Ficus carica leaves using QSPR modeling

ABSTRACTThe present study describes Quantitative Structure Property Relationship (QSPR) modeling to relate metal ions characteristics with adsorption potential of Ficus carica leaves for 13 selected metal ions (Ca+2, Cr+3, Co+2, Cu+2, Cd+2, K+1, Mg+2, Mn+2, Na+1, Ni+2, Pb+2, Zn+2, and Fe+2) to generate QSPR model. A set of 21 characteristic descriptors were selected and relationship of these metal characteristics with adsorptive behavior of metal ions was investigated. Stepwise Multiple Linear Regression (SMLR) analysis and Artificial Neural Network (ANN) were applied for descriptors selection and model generation. Langmuir and Freundlich isotherms were also applied on adsorption data to generate proper correlation for experimental findings. Model generated indicated covalent index as the most significant descriptor, which is responsible for more than 90% predictive adsorption (α = 0.05). Internal validation of model was performed by measuring (0.98). The results indicate that present model is a useful tool for prediction of adsorptive behavior of different metal ions based on their ionic characteristics.

Simple estimation of available water capacity in soils of semiarid and subhumid environments

ABSTRACTSoil available water capacity (AWC) is an important factor affecting soil productivity in semiarid and subhumid environments and is mainly determined by the soil textural composition. As the soils of these environments usually present fairly uniform textures across depth, we hypothesized that it would be possible to accurately estimate the whole-profile AWC using surface information. Our objective was to test this hypothesis in the Argentine Semiarid Pampas. Information was collected from 152 sites where AWC was measured in 20 cm layers up to a depth of 140 cm or up to the upper limit of the petrocalcic horizon, when present. In each case, whole profile AWC was estimated using a one-step and a two-step approach, comparing multiple regression and artificial neural networks as modeling techniques. Both modeling methods were effective (R2 > 0.76, P < 0.05), however the former was chosen as no special software is required to run it, thus favoring simplicity. Models showed a strong interaction between surface AWC and soil depth and a simple nomogram was developed to estimate whole-profile AWC. Sampling and laboratory efforts should be significantly reduced using the model proposed in this paper.

Using Multiple Linear Regression and Artificial Neural Network to Predict Surface Roughness in Turning Operations

Using Multiple Linear Regression and Artificial Neural Network to Predict Surface Roughness in Turning Operations

Studies on solvent extraction of La(III) using [A336][NO3–] and modeling by statistical analysis and neural network

ABSTRACTSolvent extraction of La(III) from acidic nitrate medium has been studied with [A336][NO3–] in kerosene. The factors affecting the extraction of La(III) like equilibration time, nitrate ion, extractant and La(III) concentrations, aqueous acidity, O/A ratio variation, nature of diluent, and temperature have been investigated. McCabe-Thiele diagram has been plotted to find out the actual number of theoretical stages needed for complete extraction of lanthanum. The solvent has been successfully regenerated for further use after stripping of the metal. IR studies of [A336][NO3–] and La(III) loaded [A336][NO3–] have been carried out. Modeling of extraction data has been done using Multiple linear regression analysis and Artificial Neural Network, and the performances have been compared. Error in each case was evaluated in terms of R2 and Root mean squared error (RMSE). Maximum extraction of La(III) was 82% when 0.6 M [A336][NO3–] was used for extraction. About 98% of the metal has been recovered using 0.2 M HNO3 as stripping agent. Extractive separation of La(III) and Sm(III) was maximum (β = 65.2) using 0.1 M [A336][NO3–]. IR studies revealed formation of lanthanum complex in the extraction process. Artificial Neural Network proved to be better over Multiple linear regression in data prediction.

A CADe system for nodule detection in thoracic CT images based on artificial neural network

Lung cancer has been the leading cause of cancer-related deaths in 2015 in United States. Early detection of lung nodules will undoubtedly increase the five-year survival rate for lung cancer according to prior studies. In this paper, we propose a novel rating method based on geometrical and statistical features to extract initial nodule candidates and an artificial neural network approach to the detection of lung nodules. The novel method is solely based on 3D distribution of neighboring voxels instead of user-specified features. During initial candidates detection, we combine organized region properties calculated from connected component analysis with corresponding voxel value distributions from statistical analysis to reduce false positives while retaining true nodules. Then we devise multiple artificial neural networks (ANNs) trained from massive voxel neighbor sampling of different types of nodules and organize the outputs using a 3D scoring method to identify final nodules. The experiments on 107 CT cases with 252 nodules in LIDC-IDRI data sets have shown that our new method achieves sensitivity of 89.4% while reducing the false positives to 2.0 per case. Our comprehensive experiments have demonstrated our system would be of great assistance for diagnosis of lung nodules in clinical treatments.

Comparison Between Multiple Linear Regression (MLR) Model and Artificial Neural Network(ANN) Model for the Lean Practices of Manufacturing Industries (SMEs) of Gujarat

Lean Manufacturing practices are basically waste reduction perspective, in which value adding activities are focused over non value adding activities, however there are other advantages like process improvement, muda elimination, muri elimination but its main principal is work improvement through process flow and pull kanban.which finally results in increased productivity and key performance factor improvement like quality, cost, financial impact. Performance measures can only be controlled, if the critical factors are identified and explored among various process parameters. The objective of the paper is to compare the ANN base SPSS model with conceptual model and its linear regression model for lean manufacturing for SMEs. The comparison will gives the closeness of the data obtained for Model development and theory development .The residual indices were measured and equated to predict the performance measures. The operational level factors were explored for different performance measures of lean practices and their synaptic weightage for ANN was determined by activating hidden layer method in SPSS 20.

Prediction of Ultimate Bearing Capacity of Soft Soils Reinforced by Gravel Compaction Pile Using Multiple Regression Analysis and Artificial Neural Network

Prediction of Ultimate Bearing Capacity of Soft Soils Reinforced by Gravel Compaction Pile Using Multiple Regression Analysis and Artificial Neural Network

PREDICTING THE PROPERTIES OF CORRUGATED BASE PAPERS USING MULTIPLE LINEAR REGRESSION AND ARTIFICIAL NEURAL NETWORKS

The difficulty in predicting the properties and behaviour of paper products produced using heterogeneous raw materials with high percentages of recovered fibres poses restrictions on their efficien ...

Kinetic Data Analysis by MLR and ANN Models for Phenol Attenuation in Peat Soil

AbstractThe efficacy of phenol transport from the aqueous phase to peat soil for assessment of the attenuation capacity for migratory phenol in subsurface water pollution was investigated by the application of multiple linear regression (MLR) and artificial neural network (ANN) models. The batch kinetics study was performed, which revealed that the Freundlich isotherm model fits reasonably well with experimental results. A maximum value of 43% phenol removal efficiency was achieved in 200 g/L of soil, an initial concentration of phenol of 10 mg/L, and an equilibration time of 6 h. A sum total of 270 laboratory batch adsorption tests were conducted, and the results were applied in MLR and ANN models. Some of the influencing factors, such as pH, initial concentration, mass of soil, contact time, and so forth, on removal of sorbate by peat were also investigated in the present research. The experimental results exhibit a reasonable goodness of fit [higher coefficient of determination, R2, and lower root-mean...

Multiple Artificial Neural Networks with Interaction Noise for Estimation of Spatial Categorical Variables

This paper presents a multiple artificial neural networks (MANN) method with interaction noise for estimating the occurrence probabilities of different classes at any site in space. The MANN consists of several independent artificial neural networks, the number of which is determined by the neighbors around the target location. In the proposed algorithm, the conditional or pre-posterior (multi-point) probabilities are viewed as output nodes, which can be estimated by weighted combinations of input nodes: two-point transition probabilities. The occurrence probability of a certain class at a certain location can be easily computed by the product of output probabilities using Bayes’ theorem. Spatial interaction or redundancy information can be measured in the form of interaction noises. Prediction results show that the method of MANN with interaction noise has a higher classification accuracy than the traditional Markov chain random fields (MCRF) model and can successfully preserve small-scale features.

Predict Time Series with Multiple Artificial Neural Networks

Predict Time Series with Multiple Artificial Neural Networks

Combining DFT and QSAR computation to predict the interaction of flavonoids with the GABA (A) receptor using electronic and topological descriptors

To establish a quantitative structure-activity relationship model of the binding affinity constants (−log Ki) of 41 flavonoid derivatives towards the GABA (A) receptor, the DFT-B3LYP method with basis set 6-31G (d) was performed to gain insights into the chemical structure and property information for the studied compounds. The best topological and electronic descriptors were selected. This work was conducted with principal component analysis (PCA), multiple linear regression (MLR), multiple non-linear regression (MNLR) and artificial neural network (ANN). According to these analyses, we propose quantitative models and interpret the activity of the compounds based on multivariate statistical analysis. The statistical results of the MLR, MNLR and ANN indicate that the determination coefficients R2 were 0.896, 0.925 and 0.916, respectively. The results show that the three modelling methods can predict the studied activity well and may be useful for predicting the biological activity of new compounds. The statistical results indicate that the models are statistically significant and stable with data variation in the external validation.

Quantitative Structure-Property Relationship Study to Predict the Retention Times of Some Volatile Compounds in Rosé Wines

In this work, quantitative structure-property relationship (QSPR) models for prediction of retention time (RT) of 47 volatile compounds in rosé wines on the basis of their molecular structures were developed by applying multiple linear regression (MLR) and artificial neural network (ANN). A Levenberg- Marquardt algorithm trained feed-forward back-propagation artificial neural network (ANN) was employed. The data were randomly divided into 29 training and 9 validation sets. For comparison purpose, multiple linear regression (MLR) model of the same data was developed. Cross-validation was used to validate the QSPR models. Also, the application of the models for prediction of external set’s retention times of compounds without any contribution to model development steps was another validation process. The MLR model yielded marginally acceptable statistics with test correlation R2 = 0.993 and mean squared error (MSE) = 0.0075. Not surprisingly, the ANN model was significantly more accurate with test correlation R2 = 0.995 and mean squared error (MSE) = 0.00013.

Cost estimation using ANFIS

ABSTRACTCost function estimation is vital for decision-making in project management. In this article, a novel cost estimator is investigated based on an adaptive neuro-fuzzy inference system (ANFIS). In the numerical studies, ANFIS is tested to modeling pressure vessel cost as a case study. According to the comparative results, ANFIS shows better accuracy than multiple linear regression (MLR), Taylor Kriging (TK), and artificial neural networks (ANNs). Hence, ANFIS can be applicable to various cost function estimation problems.