Artificial Intelligence Prediction Research Articles

Comparison of physical models and artificial intelligence for prediction of flood levels

La hidrologia ha utilizado metodos tradicionales para pronosticar niveles de inundacion. Sin embargo, estos pueden generar problemas de precision, causados por el comportamiento no lineal de las inundaciones y las limitaciones al no incluir todas las variables, como flujo, y nivel de agua y precipitacion. En consecuencia, algunos cientificos comenzaron a utilizar metodos no convencionales basados en modelos de inteligencia artificial, pronosticando las inundaciones de manera mas precisa y rigurosa. Este articulo presenta una comparacion de un modelo de transito de flujo unidimensional desarrollado en HEC-RAS y un modelo de inteligencia artificial, basado en redes neuronales artificiales, desarrollado en MatLab, para predecir inundaciones. El analisis de los resultados se llevo a cabo utilizando seis indicadores estadisticos: error absoluto medio (MAE, por su nombre en ingles); error cuadratico medio (MSE); error medio porcentual absoluto (MAPE, por su nombre en ingles); raiz cuadrada de la MSE; coeficiente de correlacion de Pearson (CC, por su nombre en ingles), y coeficiente de correlacion de concordancia (ρc, por su nombre en ingles). Ademas, el coeficiente de eficiencia se calculo empleando una herramienta virtual llamada Hydrotest. A partir del analisis se observo en los modelos de pronostico que el uso de redes neuronales tiene resultados precisos, dada su cercania con los datos reales: MAPE, entre 11.95 y 12.51; CC, entre 0.90 y 0.92; ρc, entre 0.84 y 0.87, y finalmente un CE mas grande que 0.8. El estudio se realizo en una seccion de las partes altas del rio Bogota, en Colombia, entre las estaciones hidrologicas de puente Florencia y Tocancipa. Los datos de flujo fueron tomados por la Corporacion Autonoma Regional de Cundinamarca (CAR) de septiembre de 2009 a octubre de 2013.

Applying Adaptive Neural Fuzzy Inference System to Improve Concrete Strength Estimation in Ultrasonic Pulse Velocity Tests

When inspecting the property of material, nondestructive testing methods are more preferable than destructive testing since they do not damage the test sample. Nondestructive testing methods, however, might not yield the same accurate results in examining the property of material when compared with destructive testing. To improve the result of nondestructive testing methods, this research applies artificial neural networks and adaptive neural fuzzy inference system in predicting the concrete strength estimation using nondestructive testing method, the ultrasonic pulse velocity test. In this research, data from a total of 312 cylinder concrete samples were collected. Ultrasonic pulse velocity test was applied to those 312 samples in the lab, following the ASTM procedure. Then, the testing results of 312 samples were used to develop and validate two artificial intelligence prediction models. The research results show that artificial intelligence prediction models are more accurate than statistical regression models in terms of the mean absolute percentage error.

Artificial Intelligence Predicts Progress of Diabetic Kidney Disease-Novel Prediction Model Construction with Big Data Machine Learning

Background: Diabetic kidney diseases (DKD) including diabetic nephropathy is the most frequent cause of hemodialysis (HD), and more precise prediction model could be useful to early intervention of DKD. Methods: We constructed new prediction model for DKD by using artificial intelligence (AI) based on electronic medical records (EMRs). From EMRs of 64,059 diabetes patients who visited our hospital, we extracted a variety of features. This model uses the stage of nephropathy as labels, and predicts whether the stage 1 patients will move up their stage after 180 days. Results: AI constructed new prediction model by big data machine learning. First, AI extracted raw features in past 6 months at reference period, and selected 22 factors. Then, time series data analysis using convolutional autoencoder was conducted to find time series patterns relating to 6-month DKD aggravation. AI then constructed the prediction model with 17raw features as well as time series and text as secondary features using logistic regression. Finally, AI predicted DKD aggravation with 0.74 AUC score at maximum. Furthermore, DKD aggravation group had significantly higher incidence of HD than non-aggravation group in 10 years. Conclusion: The new prediction model by AI could detect progress of DKD, which could contribute to more effective and accurate intervention to reduce HD. Disclosure M. Makino: Research Support; Spouse/Partner; THE DAI-ICHI LIFE INSURANCE COMPANY, LIMITED. Self. M. Ono: None. T. Itoko: Employee; Self; IBM. T. Katsuki: Employee; Self; IBM. A. Koseki: Employee; Self; IBM. M. Kudo: Employee; Self; IBM. K. Haida: Employee; Self; Daiichilife Insurance Company. J. Kuroda: Employee; Self; The Dai-ichi Life Insurance Company, Limited. R. Yanagiya: None. A. Suzuki: Research Support; Self; THE DAI-ICHI LIFE INSURANCE COMPANY, LIMITED.. Speaker's Bureau; Self; Astellas Pharma Inc., Mitsubishi Tanabe Pharma Corporation. Research Support; Self; EA Pharma Co Ltd, Daiichi Sankyo Company, Limited, Chugai Pharmaceutical Co., Ltd., Kyowa Hakko Kirin Co., Ltd., MSD K.K., Novo Nordisk Inc., Ono Pharmaceutical Co., Ltd., Pfizer Inc., Taisho Pharmaceutical Co., Ltd., Takeda Pharmaceutical Company Limited.

215 Artificial Intelligence Predicts Sepsis After Burn Injury

215 Artificial Intelligence Predicts Sepsis After Burn Injury

Prediction of pork loin quality using online computer vision system and artificial intelligence model

The objective of this project was to develop a computer vision system (CVS) for objective measurement of pork loin under industry speed requirement. Color images of pork loin samples were acquired using a CVS. Subjective color and marbling scores were determined according to the National Pork Board standards by a trained evaluator. Instrument color measurement and crude fat percentage were used as control measurements. Image features (18 color features; 1 marbling feature; 88 texture features) were extracted from whole pork loin color images. Artificial intelligence prediction model (support vector machine) was established for pork color and marbling quality grades. The results showed that CVS with support vector machine modeling reached the highest prediction accuracy of 92.5% for measured pork color score and 75.0% for measured pork marbling score. This research shows that the proposed artificial intelligence prediction model with CVS can provide an effective tool for predicting color and marbling in the pork industry at online speeds.

Physicochemical properties of alkanolamine-choline chloride deep eutectic solvents: Measurements, group contribution and artificial intelligence prediction techniques

Further development in the utilization of deep eutectic solvents (DESs) for new processes requires an insightful understanding of their fundamental properties. Hence, in this study, we report experimental measurements of the density, viscosity, conductivity, pH, surface tension and thermal stability of three different amine based deep eutectic solvents (DESs), (Choline chloride+monoethanolamine, ChCl-MEA), (Choline chloride+diethanolamine, ChCl-DEA) and (Choline chloride+methyldiethanolamine, ChCl-MDEA), representing the primary, secondary and tertiary amines, respectively. The experimental data was obtained at temperature from 293.15–353.15K and for three different choline chloride to amine molar ratios of 1:6, 1:8 and 1:10. Moreover, the densities of the amine based DESs were predicted with the empirical group contribution method, conventional artificial neural network (ANN) and bagging artificial neural network (ANN). Due to the special nature of bonds that exists between the alkanol-amines and the choline chloride salt, the deviations for the traditional group contribution and ANN methods are quite high when compared to the experimental values. Hence, a technique based on bagging ANN, which combines the results of several ANNs in order to reduce the deviations and errors, was established. The experimental results revealed that amine-based DESs are more thermally stable as compared to stand-alone amine solvents. The density, viscosity, stability and conductivity increased with decreasing choline chloride to amine molar ratio in the DESs. However, there was no clear trend in the pH with molar ratio. The bagging ANN provided the best prediction for both the density and conductivity of the amine based DESs with a normalized mean square error (NMSE) of 2.799×10−7 and 5.820×10−4, respectively.

THE USE OF ARTIFICIAL INTELLIGENCE FOR ESTIMATING SOIL RESISTANCE TO PENETRATION

ABSTRACT The aim of this study was to present and to evaluate methodologies for the estimation of soil resistance to penetration (RP) using artificial intelligence prediction techniques. In order to do so, a data base with values of physical-water characteristics of the soils available in the literature was used, and the performances of Artificial Neural Networks (ANN) and Support Vector Machines (SVM) were evaluated. The models generated from the ANNs were implemented through the multilayer perceptron with backpropagation algorithm of Matlab software, varying the number of neurons in the input and intermediate layers. For the procedure from SVM, the RapidMiner software was used, varying input variables, the kernel function and the coefficients of these functions. The efficiency of the techniques was analyzed by the ratio 1:1, and later, compared to the Busscher non-linear model (Busscher, 1990). The results showed that the artificial intelligence models (ANN and SVM) are efficient and have predictive capacity superior to the Busscher model, under data conditions of soils with textural classes and different, and similar managements, although with higher performance index values for conditions of soils of the same textural class exposed to the same management.

Application of Artificial Intelligence in Prediction of Road Freight Transportation

Road freight transport often requires the prediction of volume. Such knowledge is necessary to capture trends in the industry and support decision making by large and small trucking companies. The aim of the presented work is to demonstrate that application of some artificial intelligence methods can improve the accuracy of the forecasts. The first method employed was double exponential smoothing. The modification of this method has been proposed. Not only the parameters but also the initial values were set in order to minimize the mean absolute percentage error (MAPE) using the artificial immune system. This change resulted in a marked improvement in the effects of minimization, and suggests that the variability of the initial value of S2 has an impact on this result. Then, the forecasting Bayesian networks method was applied. The Bayesian network approach is able to take into account not only the historical data concerning the volume of freight, but also the data related to the overall state of the national economy. This significantly improves the quality of forecasting. The application of this approach can also help in predicting the trend changes caused by overall state of economy, which is rather impossible when analysing only the historical data.

Artificial Intelligence for Prediction of Standard Lactation Milk yield in Deoni Cattle

A study was carried out on 1764 test day records of Deoni cattle breed located in cattle breeding farm, College of Veterinary and Animal Sciences, Udgir Dist- Latur Maharashtra, the western state of India. A multilayer feed forward neural network with back propagation of error learning mechanism was developed using artificial neural network. The network was trained and simulated using Bayesian regularization (BR) algorithms. The performance efficiency of the network model was evaluated using the value of coefficient of determination (R2-value) and root mean square error. It was observed that, the mean value of test days varies from 1.13 to 1.83 with standard deviation ranged from 0.50 to 1.01. Test day nine contributes highest (87.57%) to the total variability. The highest coefficient of determination i.e. 89.55 % was explained in fourth set with 2 layers and 10 neurons. It was inferred that, standard lactation milk yield of Deoni cows could be predicted on the basis of monthly test day milk records as early as 155th days of lactation with 89.55 % of coefficient of determination and 0.138 of root mean squares error.

Prediction of carbon dioxide solubility in aqueous mixture of methyldiethanolamine and N-methylpyrrolidone using intelligent models

Clear knowledge about the solubility of acid gases such as CO2 in different solvents at different states is very important, especially for carbon capture from flue gases. This study highlights the application of artificial intelligence in prediction of carbon dioxide solubility in a mix solvent of methyldiethanolamine and N-methylpyrrolidone at wide range of temperature and pressure.The input data of the models were temperature, pressure, and saturation pressure and the output parameter was the solubility of CO2. Different intelligent approaches such as MLP-ANN, GA-RBF, CSA-LSSVM, Hybrid-ANFIS, PSO-ANFIS, and CMIS were developed and the reliability of models was investigated through different graphical and statistical methods. Result showed that the developed models are accurate and predictive for estimation of experimental solubility data. However, the CMIS approach exhibited better results compared to other intelligent approaches. Results of this study showed that intelligent based algorithms are powerful alternatives for time-consuming and difficult experimental processes of solubility measurement.

Artificial Intelligent Models for Improved Prediction of Residential Space Heating

AbstractUsing artificial intelligence (AI) models, cost effective electricity meter, and easily accessible weather data, this paper discusses a methodology for improved prediction of hourly residential space heating electricity use. Four AI models [back propagation neural network (BPNN), radial basis function neural network (RBFNN), general regression neural network (GRNN), and support vector regression (SVR)] were used for predicting hourly residential heating electricity use. For this study, a typical single-family house was used to obtain the data used for AI prediction models. Results showed SVR’s ability to predict hourly residential heating electricity use was better when compared with other AI models. Furthermore, through comparison of prediction performance in different time periods, additional investigation was conducted to evaluate the effect of dynamic human behaviors on the prediction accuracy of the AI models. Results revealed that dynamic human behaviors have a negative effect on the predict...

The errors, insights and lessons of famous AI predictions – and what they mean for the future

Predicting the development of artificial intelligence (AI) is a difficult project – but a vital one, according to some analysts. AI predictions are already abound: but are they reliable? This paper starts by proposing a decomposition schema for classifying them. Then it constructs a variety of theoretical tools for analysing, judging and improving them. These tools are demonstrated by careful analysis of five famous AI predictions: the initial Dartmouth conference, Dreyfus's criticism of AI, Searle's Chinese room paper, Kurzweil's predictions in the Age of Spiritual Machines, and Omohundro's ‘AI drives’ paper. These case studies illustrate several important principles, such as the general overconfidence of experts, the superiority of models over expert judgement and the need for greater uncertainty in all types of predictions. The general reliability of expert judgement in AI timeline predictions is shown to be poor, a result that fits in with previous studies of expert competence.

Applying Support Vector Machines in Rebound Hammer Test

There are several nondestructive testing techniques available to test the compressive strength of the concrete and the Rebound Hammer Test is among one of the fast and economical methods. Nevertheless, it is found that the prediction results from Rebound Hammer Test are not satisfying (over 20% mean absolute percentage error). In view of this, this research intends to develop a concrete compressive strength prediction model for the SilverSchmidt test hammer, using data collected from 838 lab tests. The Q-values yield from the concrete test hammer SilverSchmidt is set as the input variable and the concrete compressive strength is set as the output variable for the prediction model. For the non-linear relationships, artificial intelligence technique, Support Vector Machines (SVMs), are adopted to develop the prediction models. The results show that the mean absolute percentage errors for SVMs prediction model, 6.76%, improves a lot when comparing to SilverSchmidt predictions. It is recommended that the artificial intelligence prediction models can be applied in the SilverSchmidt tests to improve the prediction accuracy.

On the suitability of resampling techniques for the class imbalance problem in credit scoring

In real-life credit scoring applications, the case in which the class of defaulters is under-represented in comparison with the class of non-defaulters is a very common situation, but it has still received little attention. The present paper investigates the suitability and performance of several resampling techniques when applied in conjunction with statistical and artificial intelligence prediction models over five real-world credit data sets, which have artificially been modified to derive different imbalance ratios (proportion of defaulters and non-defaulters examples). Experimental results demonstrate that the use of resampling methods consistently improves the performance given by the original imbalanced data. Besides, it is also important to note that in general, over-sampling techniques perform better than any under-sampling approach.