Docking study and QSAR analysis based on the artificial neural network and multiple linear regression of novel harmine derivatives

Type 2 diabetes mellitus (T2DM) is a metabolic disease with complex causes, manifestations, complications and management. Understanding the wide range of risk factors for T2DM can facilitate diagnosis, proper classification and cost-effective management of the disease. To compare the power of an artificial neural network (ANN) and logistic regression in identifying T2DM risk factors. This descriptive and analytical study was conducted in 2013. The study samples were all residents aged 15-64 years of rural and urban areas in East Azerbaijan, Islamic Republic of Iran, who consented to participate (n = 990). The latest data available were collected from the Noncommunicable Disease Surveillance System of East Azerbaijan Province (2007). Data were analysed using SPSS version 19. Based on multiple logistic regression, age, family history of T2DM and residence were the most important risk factors for T2DM. Based on ANN, age, body mass index and current smoking were most important. To test for generalization, ANN and logistic regression were evaluated using the area under the receiver operating characteristic curve (AUC). The AUC was 0.726 (SE = 0.025) and 0.717 (SE = 0.026) for logistic regression and ANN, respectively (P < 0.001). The logistic regression model is better than ANN and it is clinically more comprehensible.

It is key index of cotton yarn quality such as cotton yarn strength and so on. It can well control cotton yarn quality by predicting yarn strength and so on. Generally, it is normal used to predict yarn strength such as Multiple Linear Regression (MLR), Support Vector Regression (SVR) and shallow Artificial Neural Network (ANN). Because the processing of cotton yarn production has time sequence, the paper proposes a new deep neural network, it is artificial Recurrent Neural Network (RNN). It used 1800 sets of data to train RNN, SVR and ANN. It tested RNN, MLR, SVR and ANN with 200 sets of data. Experimental results show that the Recurrent Neural Network (RNN) is the best accuracy among these four algorithms.

Docking study and QSAR analysis based on the artificial neural network and multiple linear regression of novel harmine derivatives

This paper compares the capabilities of the artificial neural network (ANN) and multiple linear regression (MLR) for recognizing and discriminating partial discharge (PD) defects. Statistical fingerprints obtained from a several PD measurement were applied for training and testing both the ANN and MLR. The result indicates that for both the ANN and MLR trained and tested with the same insulation defect, the ANN has better recognition capability. But, when both ANN and MLR were trained and tested with different PD defects, the MLR is generally more sensitive in discriminating them. In this paper, the results were evaluated for practical PD recognition and it shows that both of them can be used simultaneously for both online and offline PD detection.

Groundwater always has been one of the important and reliable resource to supply drinking and agriculture water. Hence accurate estimation of groundwater recharge over a catchment is essential for boosting of economy of the country. The study involved use tools of Artificial Neural Network (ANN) and Multiple Linear Regression (MLR) for estimation of groundwater recharge in single catchment Shivade, located in upper Krishna river basin in the district of Kolhapur and Sangli of Maharashtra State, India. Monthly monsoon data from January 2002 to Dec 2010 was used for the analysis. All the models were trained and tested for the recharge at Shivade catchment area located in upper Krishna river basin. The models were tested using four statistical performance criteria namely mean absolute error (MAE), root mean squared error (RMSE), correlation coefficient (R) and mean squared error (MSE). The groundwater recharge has been estimated and compared using Artificial Neural Network (ANN) and Multiple Linear Regression (MLR). The analysis showed that performance of Artificial Neural Network (ANN) was excellent in the catchment area shows higher values of correlation coefficient and lower values of the error measures as compared to Multiple Linear Regression (MLR).

Artificial neural network and multiple regression analysis models to predict essential oil content of ajowan (Carum copticum L.)

Application of artificial neural network and multiple linear regression in modeling nutrient recovery in vermicompost under different conditions

The purpose of this study was to develop artificial neural network (ANN) and multiple linear regression (MLR) models that are capable of predicting the bonding strength of wood based on moisture content, open assembly time and closed assembly time of the joints prior to pressing process. For this purpose, the experimental studies were conducted and the models based on the experimental results were set up. As a result of the experiments conducted, it was observed that bonding strength first increased and then decreased with increasing the wood moisture content and adhesive open assembly time. In addition, the increased closed assembly time caused a decrease in bonding strength of wood. The ANN results were compared with the results obtained from the MLR model to evaluate the models’ predictive performance. It was found that the ANN model with the R 2 value of 97.7% and the mean absolute percentage error of 3.587% in test phase exhibits higher prediction accuracy than the MLR model. The comparison results confirm the feasibility of ANN model in terms of predictive performance. Consequently, it can be said that ANN is an effective tool in predicting wood bonding strength, and quite useful instead of costly and time-consuming experimental investigations.

Metabolic syndrome (MetS) is an important side effect of second-generation antipsychotics (SGAs). However, many SGA-treated patients with MetS remain undetected. In this study, we trained and validated artificial neural network (ANN) and multiple logistic regression models without biochemical parameters to rapidly identify MetS in patients with SGA treatment. A total of 383 patients with a diagnosis of schizophrenia or schizoaffective disorder (DSM-IV criteria) with SGA treatment for more than 6 months were investigated to determine whether they met the MetS criteria according to the International Diabetes Federation. The data for these patients were collected between March 2005 and September 2005. The input variables of ANN and logistic regression were limited to demographic and anthropometric data only. All models were trained by randomly selecting two-thirds of the patient data and were internally validated with the remaining one-third of the data. The models were then externally validated with data from 69 patients from another hospital, collected between March 2008 and June 2008. The area under the receiver operating characteristic curve (AUC) was used to measure the performance of all models. Both the final ANN and logistic regression models had high accuracy (88.3% vs 83.6%), sensitivity (93.1% vs 86.2%), and specificity (86.9% vs 83.8%) to identify MetS in the internal validation set. The mean +/- SD AUC was high for both the ANN and logistic regression models (0.934 +/- 0.033 vs 0.922 +/- 0.035, P = .63). During external validation, high AUC was still obtained for both models. Waist circumference and diastolic blood pressure were the common variables that were left in the final ANN and logistic regression models. Our study developed accurate ANN and logistic regression models to detect MetS in patients with SGA treatment. The models are likely to provide a noninvasive tool for large-scale screening of MetS in this group of patients.

Objective To explore the role of artificial neural network and logistic regression model in predicting the effect of extracorporeal shock wave for upper urinary tract calculi. Methods From January, 2010 to January, 2015, d 340 patients with renal calculus were treated by ESWL at our hospital. The predictive parameters were sex, symptoms induced by urethral irritation, blood urine, renal colic, stone position, stone of one side, age, BMI, disease course, and stone size. Artificial neural network and logistic regression model were built basing on these parameters to predict the clinical effect of ESWL for calculus of upper urinary tract. Results The most important five parameters in artificial neural network were stone size, disease course, blood urine, stone position, and BMI, with statistical differences (P<0.05). The most important parameters in logistic regression model were disease course, blood urine, and stone position, with statistical differences (P<0.05). Conclusions Artificial neural network and logistic regression model in predicting the effect of extracorporeal shock wave for upper urinary tract calculi are both highly accurate, so both are worth being clinically generalized. Key words: Artificial neural network; Logistic regression model; Upper urinary tract calculi; Extracorporeal shock wave

Recently, core-spun yarns showed many improved characteristics. The tensile properties of such yarns are accepted as one of the most important parameters for assessment of yarn quality. The tensile properties decide the performance of post-spinning operations; warping, weaving, and knitting, and the properties of the final textile product; hence, its accurate prediction carries much importance in industrial applications. In this study, artificial neural network (ANN) and multiple regression methods for modeling the tensile properties of cotton/spandex core-spun yarns are investigated. Yarn breaking strength, breaking elongation, and work of rupture of the core-spun yarns are studied. The two models were assessed by verifying root mean square error, mean bias error, and coefficient of determination (R2-value). The results of this study revealed that ANN has better performance in predicting comparing with multiple linear regression.

In this paper, the accurate electricity consumption forecasting has become important decisions in the energy planning of the developing countries. Last decade has several new techniques are used for electricity consumption forecasting to accurately predict the future demand. The considerable amount of electricity consumption modeling was efforts. This research approach to develop electricity models, statistical approach is a good to engineering approaches when observed and measured data is available. The statistical models, linear regression analysis has shown promising results because of the reasonable accuracy and relatively simple implementation which compared to other methods. In this study, artificial neural network and multiple linear regression analysis were performed data from Electricity Generating Authority of Thailand. In the models, gross electricity generation, installed capacity, gross domestic products (GDP) and population are used as independent variables using historical data from 1993 to 2015. Forecasting results are compared using MAPE and RMSE for the test period data. The results indicate electricity consumption model are accurate and minimum cost for electricity generation in Thailand.

Prediction of wind drift and evaporation losses from sprinkler irrigation using neural network and multiple regression techniques

The present study focuses on the application of artificial neural network (ANN) and Multiple linear Regression (MLR) analysis for developing a model to predict the unconfined compressive strength (UCS) and split tensile strength (STS) of the fiber reinforced clay stabilized with grass ash, fly ash and lime. Unconfined compressive strength and Split tensile strength are the nonlinear functions and becomes difficult for developing a predicting model. Artificial neural networks are the efficient tools for predicting models possessing non linearity and are used in the present study along with regression analysis for predicting both UCS and STS. The data required for the model was obtained by systematic experiments performed on only Kaolin clay, clay mixed with varying percentages of fly ash, grass ash, polypropylene fibers and lime as between 10-20%, 1-4%, 0-1.5% and 0-8% respectively. Further, the optimum values of the various stabilizing materials were determined from the experiments. The effect of stabilization is observed by performing compaction tests, split tensile tests and unconfined compression tests. ANN models are trained using the inputs and targets obtained from the experiments. Performance of ANN and Regression analysis is checked with statistical error of correlation coefficient (R) and both the methods predict the UCS and STS values quite well; but it is observed that ANN can predict both the values of UCS as well as STS simultaneously whereas MLR predicts the values separately. It is also observed that only STS values can be predicted efficiently by MLR.

Estimation of sediment load can provide basic information on a range of problems related to the design and operation of river system and for water resources engineering as well as environmental problems. High sediment load is an integral component of the Brahmaputra River system, and its role, despite being critical in the overall systemic behaviour of the river, is little understood. Due to its sheer quantity and complex behavior during transport, sediment control has remained a challenge. Sediment flux depends on sediment properties, characteristics of the sediment load, and properties of the fluid flow. Artificial Neural Network (ANN) and Multiple Linear Regression (MLR) models were utilized to predict both sediment and particulate heavy metal concentration. Samples from river suspended and bank materials were analyzed with the help of X-Ray Diffraction, Scanning Electron Microscope, Laser Particle Size analyzer and Atomic Absorption Spectrometer. EDX spectra were generated for individual grains to understand compositional characters of the samples. Results of all these investigations were combined to develop a comprehensive understanding of the sediment load of the Brahmaputra River. The performances of the desired models confirmed that the model derived using ANNs gave a better prediction than the model derived using MLR.