Direct Prediction Method Research Articles

Multi-Views Fusion CNN for Left Ventricular Volumes Estimation on Cardiac MR Images.

Left ventricular (LV) volume estimation is a critical procedure for cardiac disease diagnosis. The objective of this paper is to address a direct LV volume prediction task. In this paper, we propose a direct volume prediction method based on the end-to-end deep convolutional neural networks. We study the end-to-end LV volume prediction method in items of the data preprocessing, network structure, and multiview fusion strategy. The main contributions of this paper are the following aspects. First, we propose a new data preprocessing method on cardiac magnetic resonance (CMR). Second, we propose a new network structure for end-to-end LV volume estimation. Third, we explore the representational capacity of different slices and propose a fusion strategy to improve the prediction accuracy. The evaluation results show that the proposed method outperforms other state-of-the-art LV volume estimation methods on the open accessible benchmark datasets. The clinical indexes derived from the predicted volumes agree well with the ground truth ( ${\rm{EDV:R}}^{{\rm 2}}={\text{0.974}}$, ${\rm{RMSE\,}}= {\text{9.6}}{\rm{\,ml}}$; ${\rm{ESV:R}}^{{\rm 2}}={\text{0.976}}$, ${\rm{RMSE}}= {\text{7.1}}\,{\text{ml}}$; ${\rm{EF:R}}^{{\rm 2}} ={\text{0.828}}$, ${\rm{RMSE}}= {\text{4.71}}\% $). Experimental results prove that the proposed method may be useful for the LV volume prediction task. The proposed method not only has application potential for cardiac diseases screening for large-scale CMR data, but also can be extended to other medical image research fields.

Abstract TMEM-035: GLYCOMARKERS FOR PREDICTING PLATINUM–DRUG RESPONSE IN OVARIAN CANCER

Abstract Platinum-based drugs (pt-drugs) continue to be the mainstay of first-line therapy for a wide range of cancers including ovarian carcinoma. Despite common applications, resistance to pt-drugs is an ongoing dilemma in cancer treatments, because tumor cells have different molecular characteristics that affect their responses to drugs. A molecular test that can accurately identify pt-drug resistance would provide invaluable guidance for chemotherapy strategy and reduce the random use of ineffective drugs. This would be a significant advancement in treatment management. Our studies address this unmet need in cancer care by introducing an innovative method to predict pt-drug resistance, before administrating the drug. Our method is based on a new concept linking glycan cell surface expression with drug reactivity. We have identified a glycan structure, namely Glycomarker 1, whose expression level on the cancer cell surface is associated with a response to first-line chemotherapy. A patent for this discovery has been issued by the US patent office in 2009(1). Flow cytometry with a series of fluorescent lectins was initially used to profile the cell surface glycans on three isogenic pairs of ovarian carcinoma cell lines, each pair consisting of parental chemosensitive cell lines, 2008, A2780, IGROV-1, and their corresponding resistant cell lines 2008/C13*5.25, A2780/CP and IGROV-1/CP, respectively. The cell surface glycan comparison revealed that the expression levels of Glycomarker 1 on resistant phenotypes were at least ten times lower than that of sensitive parental cells, on all three pairs of cell lines. Further experiments by various methods of fluorescent confocal microscopy (with fluorescently labeled cisplatin), colony forming assay, glycan modifications, and mass spectrometry confirmed the association of Glycomarker 1 with drug uptake by ovarian carcinoma cell lines(1). Lectin histochemistry (LHC) was adopted as a clinical method to test the Glycomarker 1 on human ovarian tissue samples. The LHC was optimized and validated for reproducibility, specificity, and sensitivity by colorimetric and fluorescent staining systems. The feasibility of LHC as a clinical test was evaluated on a training panel of 64 ovarian tissue sections. In retrospective studies, LHC correctly predicted drug-response in 22 out of 27 (81.4%) cancer specimens from patients with a known history of response to first-line chemotherapy. In the course of testing the clinical samples for Glycomarker 1, we identified another glycan structure, namely Glycomarker 2, whose expression pattern was strongly similar to that of the Glycomarker 1, suggesting the association of two glycan motifs with drug response. A patent for this discovery is pending in the US, Canada and European patent office(2). The ultimate objective of this work is to translate the assays to clinical tests used to predict platinum response in ovarian cancer. This is a novel direct predictive method, truly different from existing procedures, which will provide molecular information for treatment strategy. Thus far, our experiments have focused on ovarian cancer. However, evidence indicates that this method may also apply to other cancers that are treated with pt-drugs. 1) US patent #7585503 2) PCT patent # 20150024409, 01/22/2015 pending in the US, Canada & Europe. Citation Format: Nahid Razi, Afshin Bahador, Nathalie Scholler and Nissi Varki. GLYCOMARKERS FOR PREDICTING PLATINUM–DRUG RESPONSE IN OVARIAN CANCER [abstract]. In: Proceedings of the 11th Biennial Ovarian Cancer Research Symposium; Sep 12-13, 2016; Seattle, WA. Philadelphia (PA): AACR; Clin Cancer Res 2017;23(11 Suppl):Abstract nr TMEM-035.

Assessment of CPTU and static load test methods for predicting ultimate bearing capacity of pile

ABSTRACTFor the static pressure pile, the most important is to determine the standard value of ultimate bearing capacity of single pile. At present, the bearing capacity of pile foundation is usually determined by the cone penetration test (CPT) test. The empirical formula was used in practice, but the effect of excess pore water pressure generated in the penetration on the measured cone-tip resistance and side friction is neglected. In this study, based on the field test results at Fengyu playground at Yancheng Institute of Technology by CPT and CPTU methods, the bearing capacity of pile was predicted by the standardized methods, the LCPC (France method) and CPTU direct prediction methods. The prediction was also compared with the results by the static load test method. The prediction accuracy of the CPTU method was then discussed as well. The results reveal that the accuracy of the CPTU method was the highest, which was consistent with the results obtained by the static load test method. It is the best method and worthy of being applied for predicting bearing capacity of piles in engineering applications.

A study of hybrid prediction method for ship parametric rolling

The parametric rolling (PR) in the head or following waves has been considered as one of the main stability failure modes in the development of the 2nd generation Intact Stability criterion by the International Maritime Organization (IMO). According to previous studies, the estimation methods of the roll damping affect the prediction of the PR significantly, and most of them are based on experiment data or Ikeda's empirical formula. The accuracy of the estimation method for the roll damping could be a key aspect for the validity of its prediction for the full scale ship. In this research, a hybrid prediction method is developed for the numerical prediction of the parametric rolling when experiment data are not available for the roll damping. Comparison study is also carried out between the hybrid method and a nonlinear dynamics method, where the roll damping is estimated by the simplified Ikeda's method and the direct CFD prediction method in a direct non-linear simulation based on the 3-D CFD approach in the model scale. It is shown that the results of the hybrid method are in satisfactory agreements with the model experiment results, and the method can be used for analysis especially at the early design stage where experiment data are often not available.

Predictions of biochar yield and elemental composition during torrefaction of forest residues

In this work, a direct prediction method coupled with a consecutive reaction model is developed to estimate the biochar yield and elemental composition in a biomass torrefaction process. Norway forest residues were chosen as feedstock and torrefied at different temperatures under nitrogen atmosphere in a thermogravimetric analyzer. Obtained data were modeled to predict the mass loss during torrefaction. Distributions of initial, intermediate and final solid products as well as torrefaction kinetic parameters are reported. Thereafter, a direct method to predict the elemental composition of biochar is introduced. The results show that the decomposition of initial biomass to form an intermediate solid has higher conversion rate than the degradation of the intermediate. Moreover, the predictions reproduce well the experimental thermogravimetric curves and show composition trends similar to the literature data. This method is useful for the design and optimization of industrial torrefaction processes with predictable biochar yield and elemental composition.

Using data-driven approach for wind power prediction: A comparative study

Although wind energy is intermittent and stochastic in nature, it is increasingly important in the power generation due to its sustainability and pollution-free. Increased utilization of wind energy sources calls for more robust and efficient prediction models to mitigate uncertainties associated with wind power. This research compares two different approaches in wind power forecasting which are indirect and direct prediction methods. In indirect method, several times series are applied to forecast the wind speed, whereas the logistic function with five parameters is then used to forecast the wind power. In this study, backtracking search algorithm with novel crossover and mutation operators is employed to find the best parameters of five-parameter logistic function. A new feature selection technique, combining the mutual information and neural network is proposed in this paper to extract the most informative features with a maximum relevancy and minimum redundancy. From the comparative study, the results demonstrate that, in the direct prediction approach where the historical weather data are used to predict the wind power generation directly, adaptive neuro fuzzy inference system outperforms five data mining algorithms namely, random forest, M5Rules, k-nearest neighbor, support vector machine and multilayer perceptron. Moreover, it is also found that the mean absolute percentage error of the direct prediction method using adaptive neuro fuzzy inference system is 1.47% which is approximately less than half of the error obtained with the indirect prediction methods.

Genomic prediction for tick resistance in Braford and Hereford cattle.

One of the main animal health problems in tropical and subtropical cattle production is the bovine tick, which causes decreased performance, hide devaluation, increased production costs with acaricide treatments, and transmission of infectious diseases. This study investigated the utility of genomic prediction as a tool to select Braford (BO) and Hereford (HH) cattle resistant to ticks. The accuracy and bias of different methods for direct and blended genomic prediction was assessed using 10,673 tick counts obtained from 3,435 BO and 928 HH cattle belonging to the Delta G Connection breeding program. A subset of 2,803 BO and 652 HH samples were genotyped and 41,045 markers remained after quality control. Log transformed records were adjusted by a pedigree repeatability model to estimate variance components, genetic parameters, and breeding values (EBV) and subsequently used to obtain deregressed EBV. Estimated heritability and repeatability for tick counts were 0.19 ± 0.03 and 0.29 ± 0.01, respectively. Data were split into 5 subsets using k-means and random clustering for cross-validation of genomic predictions. Depending on the method, direct genomic value (DGV) prediction accuracies ranged from 0.35 with Bayes least absolute shrinkage and selection operator (LASSO) to 0.39 with BayesB for k-means clustering and between 0.42 with BayesLASSO and 0.45 with BayesC for random clustering. All genomic methods were superior to pedigree BLUP (PBLUP) accuracies of 0.26 for k-means and 0.29 for random groups, with highest accuracy gains obtained with BayesB (39%) for k-means and BayesC (55%) for random groups. Blending of historical phenotypic and pedigree information by different methods further increased DGV accuracies by values between 0.03 and 0.05 for direct prediction methods. However, highest accuracy was observed with single-step genomic BLUP with values of 0.48 for -means and 0.56, which represent, respectively, 84 and 93% improvement over PBLUP. Observed random clustering cross-validation breed-specific accuracies ranged between 0.29 and 0.36 for HH and between 0.55 and 0.61 for BO, depending on the blending method. These moderately high values for BO demonstrate that genomic predictions could be used as a practical tool to improve genetic resistance to ticks and in the development of resistant lines of this breed. For HH, accuracies are still in the low to moderate side and this breed training population needs to be increased before genomic selection could be reliably applied to improve tick resistance.

Nonlinear generalized predictive control based on online least squares support vector machines

For a class of nonlinear discrete systems with unknown parameters, an adaptive direct generalized predictive control method based on online least squares support vector machines (OLS–SVM) is proposed. In the method, the OLS–SVM is used to design the controller directly, and an improved projection algorithm based on the tracking error is introduced to adjust the weights of the OLS–SVM adaptively, so the inverse matrix is avoided in the process of online real-time control. It is proved that the proposed method can make the tracking error converge to a small neighborhood of the origin. Simulation results have shown the correctness and effectiveness of the proposed method.

Emergent protein folding modeled with evolved neural cellular automata using the 3D HP model.

We used cellular automata (CA) for the modeling of the temporal folding of proteins. Unlike the focus of the vast research already done on the direct prediction of the final folded conformations, we will model the temporal and dynamic folding process. To reduce the complexity of the interactions and the nature of the amino acid elements, lattice models like HP were used, a model that categorizes the amino acids regarding their hydrophobicity. Taking into account the restrictions of the lattice model, the CA model defines how the amino acids interact through time to obtain a folded conformation. We extended the classical CA models using artificial neural networks for their implementation (neural CA), and we used evolutionary computing to automatically obtain the models by means of Differential Evolution. As the iterative folding also provides the final folded conformation, we can compare the results with those from direct prediction methods of the final protein conformation. Finally, as the neural CA that provides the iterative folding process can be evolved using several protein sequences and used as operators in the folding of another protein with different length, this represents an advantage over the NP-hard complexity of the original problem of the direct prediction.

Direct method for life prediction of fibre reinforced polymer composites based on kinematic of damage potential

In this paper, a direct computational method of life prediction for fibre-reinforced polymers (FRP) is developed. This approach is based on a simplified direct method (SDM) which allows to predict the life from the stabilized damage state. The SDM is extended to the case of anisotropic continuous damage mechanics of FRP. It is shown that damage processes in composite material subjected to fatigue load can reach stabilized damage state. Damage state and thermodynamic forces associated with damage mechanisms at the stabilized state are related to life. Experimental validation was done on the standard glass-fibre/epoxy angle-ply and cross-ply laminate plates subjected to fatigue loading with different load ratios (R=0.1,0.5).

Geometrical prediction of maximum power point for photovoltaics

It is important to drive solar photovoltaic (PV) system to its utmost capacity using maximum power point (MPP) tracking algorithms. This paper presents a direct MPP prediction method for a PV system considering the geometry of the I–V characteristic of a solar cell and a module. In the first step, known as parallelogram exploration (PGE), the MPP is determined from a parallelogram constructed using the open circuit (OC) and the short circuit (SC) points of the I–V characteristic and Lagrangian interpolation. In the second step, accurate values of voltage and power at the MPP, defined as Vmp and Pmp respectively, are decided by the Lagrangian interpolation formula, known as the Lagrangian interpolation exploration (LIE). Specifically, this method works with a few (V, I) data points instead most of the MPP algorithms work with (P, V) data points. The performance of the method is examined by several PV technologies including silicon, copper indium gallium selenide (CIGS), copper zinc tin sulphide selenide (CZTSSe), organic, dye sensitized solar cell (DSSC) and organic tandem cells’ data previously reported in literatures. The effectiveness of the method is tested experimentally for a few silicon cells’ I–V characteristics considering variation in the light intensity and the temperature. At last, the method is also employed for a 10W silicon module tested in the field. To testify the preciseness of the method, an absolute value of the derivative of power (P) with respect to voltage (V) defined as (dP/dV) is evaluated and plotted against V. The method estimates the MPP parameters with high accuracy for any kind of PV technologies with different environmental conditions. In future, this method proposes a guide line to construct control scheme for real-time MPPT tracking in the PV system.

Base a EMD-Grey Model for Textile Export Time Series Prediction

The grey forecasting model has been used widely. This paper proposes a hybrid method that combines the GM (1,1) grey forecasting model and the EMD method to forecast textile export time series with seasonality characteristics. Empirical mode decomposition is good at dealing with nonlinear, non-stationary signal and GM (1,1) model can be used to prediction time series. Through the empirical mode decomposition, the textile export series is decomposed into several intrinsic mode function component and a trend component, then using GM (1,1) model to predict these components, and reconstruct the final prediction results. The time series data of the total number of textile export (2003 to 2011) are used as test data sets. Results show that the method has better prediction effect compared with the direct prediction method.

A sampling framework for incorporating quantitative mass spectrometry data in protein interaction analysis

BackgroundComprehensive protein-protein interaction (PPI) maps are a powerful resource for uncovering the molecular basis of genetic interactions and providing mechanistic insights. Over the past decade, high-throughput experimental techniques have been developed to generate PPI maps at proteome scale, first using yeast two-hybrid approaches and more recently via affinity purification combined with mass spectrometry (AP-MS). Unfortunately, data from both protocols are prone to both high false positive and false negative rates. To address these issues, many methods have been developed to post-process raw PPI data. However, with few exceptions, these methods only analyze binary experimental data (in which each potential interaction tested is deemed either observed or unobserved), neglecting quantitative information available from AP-MS such as spectral counts.ResultsWe propose a novel method for incorporating quantitative information from AP-MS data into existing PPI inference methods that analyze binary interaction data. Our approach introduces a probabilistic framework that models the statistical noise inherent in observations of co-purifications. Using a sampling-based approach, we model the uncertainty of interactions with low spectral counts by generating an ensemble of possible alternative experimental outcomes. We then apply the existing method of choice to each alternative outcome and aggregate results over the ensemble. We validate our approach on three recent AP-MS data sets and demonstrate performance comparable to or better than state-of-the-art methods. Additionally, we provide an in-depth discussion comparing the theoretical bases of existing approaches and identify common aspects that may be key to their performance.ConclusionsOur sampling framework extends the existing body of work on PPI analysis using binary interaction data to apply to the richer quantitative data now commonly available through AP-MS assays. This framework is quite general, and many enhancements are likely possible. Fruitful future directions may include investigating more sophisticated schemes for converting spectral counts to probabilities and applying the framework to direct protein complex prediction methods.

Genetic components of milk Fourier-transform infrared spectra used to predict breeding values for milk composition and quality traits in dairy goats

The usual practice today is that milk component phenotypes are predicted using Fourier-transform infrared (FTIR) spectra and they are then, together with pedigree information, used in BLUP for calculation of individual estimated breeding values. Here, this is referred to as the indirect prediction (IP) approach. An alternative approach—a direct prediction (DP) method—is proposed, where genetic analyses are directly conducted on the milk FTIR spectral variables. Breeding values of all derived milk traits (protein, fat, fatty acid composition, and coagulation properties, among others) can then be predicted as traits correlated only to the genetic information of the spectra. For the DP, no need exists to predict the phenotypes before calculating breeding values for each of the traits—the genetic analysis is done once for the spectra, and is applicable to all traits derived from the spectra. The aim of the study was to compare the effects of DP and IP of milk composition and quality traits on prediction error variance (PEV) and genetic gain. A data set containing 27,927 milk FTIR spectral observations and milk composition phenotypes (fat, lactose, and protein) belonging to 14,869 goats of 271 herds was used for training and evaluating models. Partial least squares regression was used for calibrating prediction models for fat, protein, and lactose percentages. Restricted maximum likelihood was used to estimate variance components of the spectral variables after principal components analysis was applied to reduce the spectral dimension. Estimated breeding values were predicted for fat, lactose, and protein percentages using DP and IP methods. The DP approach reduced the mean PEV by 3.73, 4.07, and 7.04% for fat, lactose, and protein percentages, respectively, compared with the IP method. Given the reduction in PEV, relative genetic gains were 2.99, 2.78, and 4.85% for fat, lactose, and protein percentages, respectively. We concluded that more accurate estimated breeding values could be found using genetic components of milk FTIR spectra compared with single-trait animal model analyses on phenotypes predicted from the spectra separately. The potential and application is not only limited to milk FTIR spectra, but could also be extended to any spectroscopy techniques implemented in other species and for other traits.

An Improved Direct Current Prediction Method for Intra Coding

Direct current mode is one of the primary prediction modes for intra coding. In the coding standard, it has not concerned the spatial correlations between neighboring pixels, which limits its coding performance. To address this problem, an improved prediction method is proposed in this paper. In the prediction scheme, prediction pixel uses its available neighbor samples and its value is set to be the mean of the references. The reference samples are not only from other encoder blocks but also pixels predicted in current block. Experimental results demonstrate that the proposed method advances in both coding performance and coding efficiency, compared with the existing method.

A Modified Model of Direct Estimation Method for Fine Fuel Moisture Content Prediction by Considering Crown Density

Moisture content of forest fine fuel is one of the most important factors for forest fire risk assessment and fire spread prediction. The weather parameters above the fuel surface used in Catchpole's existing Direct Estimation Model are not suitable for forecast. The crown density of the forest area in the model, which may has great influence to the fine fuel moisture content in the forest, is not considered. A series of outdoor experiments were carried out in order to study the effect of the crown density, including 3 simulated crown densities and 2 real tests. In the experiments, the collected Pinus Sylvestris needles in the Da Hinggan Mountains of China are used. The dynamic variations of the weights of the needles are captured in 0.5h or 1h interval, and the dry weights of them are measured after 24h kiln dry. During the experiments, the local meteorological data including the temperature, the humidity and the winds velocity, are recorded from the homepage of Weather China at the same time. Based on the experiments, a modified model for fine fuel moisture content prediction is achieved, in which the crown density is used to adjust the temperature and the humidity near the fuel surface. The comparison results show that under different conditions of crown densities, the Mean Absolute Error (MAE) and the Root Mean Square Error (RMSE) of the modified model are decreased significantly, and the Mean Absolute Percentage Errors (MAPE) for different crown densities are all less than 6%. The contrast validation between forest field observation and the prediction values of the modified method indicates that the absolute errors are less than 10%. This modified method can effectively reduce the prediction errors due to different crown densities; meanwhile, the calculation is using meteorological forecast data directly, so it has better applicability.

Diagnosis of lubricating oil by evaluating cyanide and carbon molecular emission lines in laser induced breakdown spectra

To prevent engine failure it is essential to change lubricating oil regularly before it loses its protective properties. It is also necessary to monitor the physical and chemical conditions of the oil to reliably determine the optimum oil-change intervals. The present work focuses on studying evolution of the cyanide (CN) and carbon (C 2) molecular spectral emission lines in the laser induced breakdown spectra of lubricating oil as a function of its consumption. The intensities of these molecular bands have been taken as indicator of engine oil degradation at certain mileage. Furthermore, the percentage of decay of CN and C 2 integral intensity values at the corresponding mileage was calculated in order to relate it to the degree of consumption of the motor oil. Such percentage decay of the CN and C 2 integral intensities have been found to increase gradually with increasing mileage which is accompanied with increasing depletion of engine oil. The results of using LIBS technique in the present measurements proved that it is possible to have a direct, straightforward and easy method for prediction of lubricating oil degree of consumption. This may facilitate scheduling the proper time and/or mileage intervals for changing the oil to avoid any possibility of engine failure.

Modeling of cytochrome P450 (Cyt P450, CYP) channels

The precise location of a substrate in cytochrome P450 (CYP) governs the orientation of the oxidation position. Such information is generally obtained from biochemical data, but modeling approaches have also been used to explain these locations. We used X-ray data and modeling techniques to distinguish between the series of putative linear or curved channels which lead the substrate from the outer side of the protein to the inner, and then into the heme pocket; these techniques were also used to identify the largest such channels. Two new methods for precisely determining the 3-D structure of proteins using X-ray crystallography were proposed in order to identify these channels: first, the use of both straight and curved channels, and second, the sphere method. These data are compared with Poulos channels, and with Caver (or Mol on line) modeling methodologies. Our methods were developed from studies of the interaction between cytochrome P450CAM(CYP101) fromPseudomonas putida(as expressed inEscherichia coli) and the indolic base β-carboline. Apart from the identification of potential access channels leading to the heme-containing active site, a new explanation was advanced for the substrate's hydroxylation position. The sphere method seems to have potential to become a general and direct method for prediction of substrate access channels from reduced- or low-resolution crystallographic data.

Modeling of cytochrome P450 (Cyt P450, CYP) channels

The precise location of a substrate in cytochrome P450 (CYP) governs the orientation of the oxidation position. Such information is generally obtained from biochemical data, but modeling approaches have also been used to explain these locations. We used X-ray data and modeling techniques to distinguish between the series of putative linear or curved channels which lead the substrate from the outer side of the protein to the inner, and then into the heme pocket; these techniques were also used to identify the largest such channels. Two new methods for precisely determining the 3-D structure of proteins using X-ray crystallography were proposed in order to identify these channels: first, the use of both straight and curved channels, and second, the sphere method. These data are compared with Poulos channels, and with Caver (or Mol on line) modeling methodologies. Our methods were developed from studies of the interaction between cytochrome P450CAM (CYP101) from Pseudomonas putida (as expressed in Escherichia coli) and the indolic base β-carboline. Apart from the identification of potential access channels leading to the heme-containing active site, a new explanation was advanced for the substrate's hydroxylation position. The sphere method seems to have potential to become a general and direct method for prediction of substrate access channels from reduced- or low-resolution crystallographic data.

Hybrid method for driver accommodation using optimization-based digital human models

Many applications exist where humans are required to perform a task in a seated position, such as operating a vehicle. Seated posture inside a vehicle influences driver performance and control of the vehicle. For people of extreme stature, tall or short, and for people of extreme width, obese or pregnant populations, it can be difficult to safely operate a vehicle if there is not enough room in the cab or if some controls cannot be reached. This study proposes a hybrid method for predicting the optimum driver seat adjustment range to accommodate diverse drivers in any vehicle based on a direct optimization-based posture prediction method. The proposed hybrid method combines three approaches: a boundary manikin approach, a population sampling approach, and a special population approach. The boundary manikin approach places two boundary manikins (5% female and 95% male) inside a virtual vehicle cab to perform tests. The population sampling approach spans a multitude of test subjects ranging in stature from 158 to 185 cm, determining the range from a plot of predicted hip point distances from the point of contact of the right heel and the floor. The special population approach studies the effect that size and shape changes, such as pregnancy, have on seated posture inside a vehicle. Also given is an indication of discomfort through the output values of the multi-objective function in the optimization formulation. A combination of the three approaches is used to determine an optimal adjustment range for the driver seat, thus allowing most people to safely operate the vehicle. Results of the simulations are validated using experimental determinations of the driver seat adjustment range from the literature. The main benefit of using this method is that the human aspect of design can be included early in the design process, thereby reducing or eliminating prototypes. Another benefit of the simulation is that it can be adapted to other seating tasks such as: occupant seat check inside a vehicle; workstation design; and issues related to other special populations such as obese individuals, dwarfs, and children.