Yacoub M. Najjar

Computational neural networks for predictive microbiology II. Application to microbial growth

The growth of a specific microorganism on a certain food is influenced by a number of environmental factors such as temperature, pH, and salt concentration. Methods that delineate the history of the growth of microorganisms are always subject to a considerable debate and scrutiny in the field of predictive microbiology. Regardless of its types, a growth model (e.g., modified Gompertz model) contains several parameters that vary depending on the microorganisms/food combination and the associated prevailing environmental conditions. The growth model parameters for a set of operating conditions are commonly determined from expressions developed via multiple linear regressions. In the present study, a substitute for the nonlinear regression-based equations is developed using computational neural networks. Computational neural networks are applied herein on experimental data pertaining to the anaerobic growth of Shigella flexneri. Results have indicated that predictions by neural networks offer better agreement with experimental data as compared to predictions obtained via corresponding regression equations.

Rainfall-runoff model usingan artificial neural network approach

The use of artificial neural networks (ANNs) is becoming increasingly common in the analysis of hydrology and water resources problems. In this research, an ANN was developed and used to model the rainfall-runoff relationship, in a catchment located in a semiarid climate in Morocco. The multilayer perceptron (MLP) neural network was chosen for use in the current study. The results and comparative study indicate that the artificial neural network method is more suitable to predict river runoff than classical regression model.

On the identification of compaction characteristics by neuronets

Abstract Compaction of soils is aimed at modifying their engineering properties to fulfil the needs of earthwork projects. The two characteristic compaction parameters, namely the optimum moisture content and the maximum dry density, can only be determined experimentally. In this paper, neuronets have been developed and used to determine these two parameters from variables pertinent to geotechnical engineering soil properties and indices. The predictions of the various developed neuronets are compared with corresponding actual values and values obtained via statistical correlation models. Moreover, the advantages of neuronets as prediction techniques over the conventional regression methods are addressed.

Use of artificial neural network simulation metamodelling to assess groundwater contamination in a road project

The estimation of the extent of a polluted zone after an accidental spill occurred in road transport is essential to assess the risk of water resources contamination and to design remediation plans. This paper presents a metamodel based on artificial neural networks (ANN) for estimating the depth of the contaminated zone and the volume of pollutant infiltration in the soil in a two-layer soil (a silty cover layer protecting a chalky aquifer) after a pollutant discharge at the soil surface. The ANN database is generated using USEPA NAPL-Simulator. For each case the extent of contamination is computed as a function of cover layer permeability and thickness, water table depth and soil surface-pollutant contact time. Different feedforward artificial neural networks with error backpropagation (BPNN) are trained and tested using subsets of the database, and validated on yet another subset. Their performance is compared with a metamodelling method using multilinear regression approximation. The proposed ANN metamodel is used to assess the risk for a DNAPL pollution to reach the groundwater resource underneath the road axis of a highway project in the north of France.

Computational neural networks for predictive microbiology: I. methodology

Artificial neural networks are mathematical tools inspired by what is known about the physical structure and mechanism of the biological cognition and learning. Neural networks have attracted considerable attention due to their efficacy to model wide spectrum of challenging problems. In this paper, we present one of the most popular networks, the backpropagation, and discuss its learning algorithm and analyze several issues necessary for designating optimal networks that can generalize after being trained on examples. As an application in the area of predictive microbiology, modeling of microorganism growth by neural networks will be presented in a second paper of this series.

Neural Modeling of Kansas Soil Swelling

Damage due to soil swelling is very noticeable in a wide spectrum of structures such as roads, buildings, canal linings, and landfill liners. To control or overcome any damage, swelling soils are commonly chemically stabilized (e.g., by lime treatment). To evaluate the severity of swelling and design for the best and most economical stabilization strategy, an accurate assessment of the swell potential is acquired. In this study, a huge data base representing 413 soils retrieved from 45 different projects covering 28 counties in Kansas was used to develop prediction models. Neural network-based models and a statistical model were developed. It is shown that neural models provide significant improvements in prediction accuracy over statistical models.

Setting Speed Limits on Kansas Two-Lane Highways: Neuronet Approach

Recent federal legislation allowing states to set their own speed limits on highways, as well as increases in the number of requests from citizens and neighborhood groups to implement actions to reduce “excessive” speeding on their streets and highways, has created considerable debate about and scrutiny of the appropriate speed limits that should be posted on state highways. Various speed studies have indicated that sensible and cautious drivers will most likely drive at the speed dictated by roadway and traffic conditions rather than relying on a posted speed limit. To incorporate roadway characteristics and traffic volumes into the selection of the most appropriate (i.e., comfortable, safe, and efficient) speed limit, actual engineering field speed studies are carried out. Generally, the 85th percentile speed at which the drivers surveyed are driving is selected as a primary factor in determining the posted speed limit. Carrying out such field studies for all highway sections is a costly and time-consuming process. Therefore, characterizing the relationship between the 85th percentile speed and the roadway characteristics will assist in selecting the most appropriate posted speed limit on highway sections where field surveying is difficult due to resource limitations. A back-propagation neural network is used to extract the relationship between roadway characteristics and 85th percentile speed. The developed neural-network-based speed model was found to perform satisfactorily for characterization of speed on Kansas two-lane, uninterrupted-flow rural highways and for quantifying the influence of prevailing roadway characteristics on the anticipated 85th percentile speed.

Neuronet-based approach for assessing liquefaction potential of soils

A backpropagation artificial neural network (ANN) algorithm with one hidden layer was used as a new numerical approach to characterize the soil liquefaction potential. For this purpose, 61 field data sets representing various earthquake sites from around the world were used. To develop the most accurate prediction model for liquefaction potential, alternating combinations of input parameters were used during the training and testing phases of the developed network. The accuracy of the designed network was validated against an additional 44 records not used previously in either the network training or testing stages. The prediction accuracy of the neural network approach–based model is compared with predictions obtained by using fuzzy logic and statistically based approaches. Overall, the ANN model outperformed all other investigated approaches.

Swelling Potential of Kansas Soils: Modeling and Validation Using Artificial Neural Network Reliability Approach

Determination of the swell potential of a troublesome soil can only be made possible through the use of systematic methods for identifying, testing, and evaluating that potential. For proper evaluation of the severity of swelling for such soils, an accurate soil swell potential assessment method is warranted. To address this key issue, a two-phase research study was performed to develop combined artificial neural network and reliability-based soil swell prediction models. In Phase 1, a reasonable-sized database representing 514 swell soil tests retrieved from over 51 different projects in Kansas was used to develop both neural network–based (NNB) and statistical-based (SB) swell potential prediction models. Direct comparison of results obtained showed that NNB models provide significant improvements in prediction accuracy over their SB counterparts. In the second phase, predictions obtained using the developed NNB models along with the available experimental database were used to produce reliability (probability) factor matrices, which are used to assign a specific confidence level to predictions obtained via NNB models in order to classify the soil under consideration as a swelling or nonswelling type.

THREE-DIMENSIONAL MODELING OF SPATIAL SOIL PROPERTIES VIA ARTIFICIAL NEURAL NETWORKS

Geotechnical engineers recognize the variability of the geological materials they work with, including uncertainties associated with subsurface characterization tasks. These uncertainties include data scattering, such as real spatial variation in soil properties, or random testing errors. Systematic errors, as can occur in bias measurement procedures, are also common. In almost all construction projects, penetration tests play a major role in subsoil characterization. Interpretation of test results is mostly empirical, and it is therefore prudent to find a suitable computational method to minimize the error in predicting values at points away from actual test locations. In this research, the capabilities of artificial neural networks (ANNs) are assessed as a computational method for predicting standard penetration test (SPT) results at any point (x, y, z) in a field where a set of SPTs is performed. SPT and moisture content data for five bore holes are used to train and test the developed three-dimensional network models. To graphically visualize the underlying soil strata, select contour maps of blows and moisture content values at various locations are presented. The results obtained indicate the viability and flexibility of ANN methodology as an efficient tool for site characterization tasks.