Artificial neural network model for predicting protein subcellular location.

The function of a protein is closely correlated to its subcellular location. Is it possible to utilize a bioinformatics method to predict the protein subcellular location? To explore this problem, proteins are classified into 12 groups (Protein Eng. 12 (1999) 107-118) according to their subcellular location: (1) chloroplast, (2) cytoplasm, (3) cytoskeleton, (4) endoplasmic reticulum, (5) extracellular, (6) Golgi apparatus, (7) lysosome, (8) mitochondria, (9) nucleus, (10) peroxisome, (11) plasma membrane and (12) vacuole. In this paper, the neural network method was proposed to predict the subcellular location of a protein according to its amino acid composition. Results obtained through self-consistency, cross-validation and independent dataset tests are quite high. Accordingly, the present method can serve as a complement tool for the existing prediction methods in this area.     

Support vector regression and multilayer feed forward neural networks for non-exercise prediction of VO2max

The purpose of this study is to develop non-exercise (N-Ex) VO₂max prediction models by using support vector regression (SVR) and multilayer feed forward neural networks (MFFNN). VO₂max values of 100 subjects (50 males and 50 females) are measured using a maximal graded exercise test. The variables; gender, age, body mass index (BMI), perceived functional ability (PFA) to walk, jog or run given distances and current physical activity rating (PA-R) are used to build two N-Ex prediction models. Using 10-fold cross validation on the dataset, standard error of estimates (SEE) and multiple correlation coefficients (R) of both models are calculated. The MFFNN-based model yields lower SEE (3.23 ml kg^?1 min^?1) whereas the SVR-based model yields higher R (0.93). Compared with the results of the other N-Ex prediction models in literature that are developed using multiple linear regression analysis, the reported values of SEE and R in this study are considerably more accurate. Therefore, the results suggest that SVR-based and MFFNN-based N-Ex prediction models can be valid predictors of VO₂max for heterogeneous samples.     

An Elman neural network-based model for predicting anti-germ performances and ingredient levels with limited experimental data

Anti-germ performance test is critical in the production of detergents. However, actual biochemical tests are often costly and time-consuming. In this paper, we present an Elman neural network-based model to predict detergents’ anti-germ performance and ingredient levels, respectively. The model made it much faster and cost effective than doing actual biochemical tests. We also present preprocessing methods that can reduce data conflicts while keeping the monotonicity on limited experimental data. The model can find out the relationship between ingredient levels and the corresponding anti-germ performance, which is not widely used in solving biochemical problems. The results of experiments are generated on the base of two detergent products for two types of bacteria, and appear reasonable according to natural rules. The prediction results show a high accuracy and fitting with the monotonicity rule mostly.     

Artificial neural network for predicting creep of concrete

The concrete is today the building material by excellence. Drying accompanies the hardening of concrete and leads to significant dimensional changes that appear as cracks. These cracks influence the durability of the concrete works. Deforming a concrete element subjected to long-term loading is the sum of said instantaneous and delayed deformation due to creep deformation. Concrete creep is the continuous process of deformation of an element, which exerts a constant or variable load. It depends in particular on the characteristics of concrete, age during loading, the thickness of the element of the environmental humidity, and time. Creep is a complex phenomenon, recognized but poorly understood. It is related to the effects of migration of water into the pores and capillaries of the matrix and to a process of reorganization of the structure of hydrated binder crystals. Applying a nonparametric approach called artificial neural network (ANN) to effectively predict the dimensional changes due to creep drying is the subject of this research. Using this approach allows to develop models for predicting creep. These models use a multilayer backpropagation. They depend on a very large database of experimental results issued from the literature (RILEM Data Bank) and on appropriate choice of architectures and learning processes. These models take into account the different parameters of concrete preservation and making, which affect drying creep of concrete as relative humidity, cure period, water-to-cement ratio (W/C), volume-to-surface area ratio (V/S), and fine aggregate-to-total aggregate ratio, or fine aggregate-to-total aggregate ratio. To validate these models, they are compared with parametric models as B3, ACI 209, CEB, and GL2000. In these comparisons, it appears that ANN approach describes correctly the evolution with time of drying creep. A parametric study is also conducted to quantify the degree of influence of some of the different parameters used in the developed neural network model.     

A neural network-based model for paper currency recognition andverification

This paper describes the neural-based recognition and verification techniques used in a banknote machine, recently implemented for accepting paper currency of different countries. The perception mechanism is based on low-cost optoelectronic devices which produce a signal associated with the light refracted by the banknotes. The classification and verification steps are carried out by a society of multilayer perceptrons whose operation is properly scheduled by an external controlling algorithm, which guarantees real-time implementation on a standard microcontroller-based platform. The verification relies mainly on the property of autoassociators to generate closed separation surfaces in the pattern space. The experimental results are very interesting, particularly when considering that the recognition and verification steps are based on low-cost sensors.     

Artificial neural network-based kinematics Jacobian solution for serial manipulator passing through singular configurations

Singularities and uncertainties in arm configurations are the main problems in kinematics robot control resulting from applying robot model, a solution based on using Artificial Neural Network (ANN) is proposed here. The main idea of this approach is the use of an ANN to learn the robot system characteristics rather than having to specify an explicit robot system model.Despite the fact that this is very difficult in practice, training data were recorded experimentally from sensors fixed on each joint for a six Degrees of Freedom (DOF) industrial robot. The network was designed to have one hidden layer, where the input were the Cartesian positions along the X, Y and Z coordinates, the orientation according to the RPY representation and the linear velocity of the end-effector while the output were the angular position and velocities for each joint, In a free-of-obstacles workspace, off-line smooth geometric paths in the joint space of the manipulator are obtained.The resulting network was tested for a new set of data that has never been introduced to the network before these data were recorded in the singular configurations, in order to show the generality and efficiency of the proposed approach, and then testing results were verified experimentally.     

Artificial neural network-based techniques for the retrieval of SWE and snow depth from SSM/I data

The retrieval of snow water equivalent (SWE) and snow depth is performed by inverting Special Sensor Microwave Imager (SSM/I) brightness temperatures at 19 and 37 GHz using artificial neural network ANN-based techniques. The SSM/I used data, which consist of Pathfinder Daily EASE-Grid brightness temperatures, were supplied by the National Snow and Ice Data Centre (NSIDC). They were gathered during the period of time included between the beginning of 1996 and the end of 1999 all over Finland. A ground snow data set based on observations of the Finnish Environment Institute (SYKE) and the Finnish Meteorological Institute (FMI) was used to estimate the performances of the technique. The ANN results were confronted with those obtained using the spectral polarization difference (SPD) algorithm, the HUT model-based iterative inversion and the Chang algorithm, by comparing the RMSE, the R², and the regression coefficients. In general, it was observed that the results obtained through ANN-based technique are better than, or comparable to, those obtained through other approaches, when trained with simulated data. Performances were very good when the ANN were trained with experimental data.     

Artificial neural network method for predicting protein secondary structure content

In this paper, the neural network method was applied to predict the content of protein secondary structure elements that was based on 'pair-coupled amino acid composition', in which the sequence coupling effects are explicitly included through a series of conditional probability elements. The prediction was examined by a self-consistency test and an independent-dataset. Both indicated good results obtained when using the neural network method to predict the contents of alpha-helix, beta-sheet, parallel beta-sheet strand, antiparallel beta-sheet strand, beta-bridge, 3(10)-helix, pi-helix, H-bonded turn, bend, and random coil.     

Time-delayed dynamic neural network-based model for hysteresis behavior of shape-memory alloys

Shape-memory alloys (SMAs) have received considerable amount of attentions for their engineering applications in recent years. The hysteresis in SMAs is sensitive to the state-varying tendency and frequency. Utilizing past information to estimate the hysteretic behavior gets increasing attention. In this paper, a time-delayed dynamic neural network (TDDNN) is proposed for modeling hysteresis of SMAs in online applications. By introducing a time delay between the input and output response, the TDDNN considers the time delay’s effect on the hysteresis. This proposed network was applied to a SMA wire actuator. Experimental results demonstrate the effectiveness of TDDNN. The identified results obtained by TDDNN are better than those obtained by dynamic neural network without considering the delay information. It demonstrates the importance of introducing the time delay. The different values of time delay item can also affect TDDNN’s identified results.     

Deep neural network-based fusion model for emotion recognition using visual data

The Journal of Supercomputing - In this study, we present a fusion model for emotion recognition based on visual data. The proposed model uses video information as its input and generates emotion...     

A neural network-based method for tracking features from satellitesensor images

A new approach for feature tracking on sequential satellite sensor images using neural networks has been developed. The method defines the correspondence problem between features as the minimization of a cost function using a Hopfield neural network. It has been tested on Meteosat radiometer images by tracking a cloud with rotational movement and compared to the maximum cross-correlation method. The Hopfield net was found to be more accurate and faster.     

Artificial neural networks for predicting maximum wave runup on rubble mound structures

Accurate prediction of maximum wave runup on breakwaters is a vital issue for determining crest level of coastal structures. In practice, traditional regression-based empirical model, recommended by the “Coastal Engineering Manual”, as well as the “Manual on the use of rock in hydraulic engineering”, is widely used. However, use of these approaches brings additional restrictive assumptions such as linearity, normality (Gaussian distributed variables), variance constancy (homoscedasticity) etc. This paper focuses on the prediction of maximum wave runup elevation through artificial neural networks (ANNs), which has no restrictive assumptions. Out of 261 irregular wave runup data of Van der Meer and Stam, 100 randomly chosen data points are used for training the model. The remaining data are exploited for testing purposes. This study has two objectives: (1) to develop ANN models and search their applicability to estimate maximum wave runup elevation on breakwaters; (2) to compare widely used empirical model with these models. For these purposes, different ANN models are constructed and trained with their own topology. The performance of the ANN models is tested against the same testing data, none of which is employed in the training. It is found that ANN technique gives more accurate results and the extent of accuracy can be affected by the structure of ANNs.     

Impedance model force control using a neural network-based effective stiffness estimator for a desktop NC machine tool

In manufacturing industries of metallic molds, various NC machine tools are used. A desktop NC machine tool with compliance control capability has been already proposed to automatically cope with the finishing process of an LED lens mold. The NC machine tool can control the polishing force acting between an abrasive tool and a workpiece, where the force control method developed is an impedance model force control. The most important gain, which gives a large influence to the stability, is the desired damping of the impedance model. Ideally, the desired damping is calculated from the critical damping condition of the force control system in consideration of the effective stiffness. The effective stiffness means the total stiffness including the characteristics composed of the NC machine tool itself, force sensor, tool attachment, abrasive tool, workpiece, zig and floor. One of the serious problems is that the effective stiffness of the NC machine tool has undesirable nonlinearity, so that it may destroy the stability of the force control system. In this paper, a systematic tuning method of the desired damping in the control system is considered by using neural networks, where the neural networks acquire the nonlinearity of effective stiffness. It is confirmed that the impedance model force controller with the neural network-based (NN-based) stiffness estimator allows the NC machine tool to achieve a high quality finished surface of an LED lens mold with a diameter of 3.6 mm.     

Artificial neural networks for predicting dorsal pressures on the foot surface while walking

In this work, artificial neural networks (ANNs) are proposed to predict the dorsal pressure over the foot surface exerted by the shoe upper while walking. A model that is based on the multilayer perceptron (MLP) is used since it can provide a single equation to model the exerted pressure for all the materials used as shoe uppers. Five different models are produced, one model for each one of the four subjects under study and an overall model for the four subjects. The inputs to the neural model include the characteristics of the material and the positions during a whole step of 14 pressure sensors placed on the foot surface. The goal is to find models with good generalization capabilities, (i.e., models that work appropriately not only for the cases used to train the model but also for new cases) in order to have a useful predictor in routine practice. New cases may involve either new materials for the same subject or even new subjects and new materials. To accomplish this goal, two thirds of the patterns are trained to obtain the model (training data set) and the remaining third is kept for validation purposes. The achieved accuracy was very satisfactory since correlation coefficients between the predicted output and the actual pressure in the validation data were higher than 0.95 for those models developed for individual subjects. For the much more challenging problem of an overall prediction for all the subjects, the correlation coefficient was close to 0.9 in the validation data set (i.e., with data not previously seen by the model).     

Artificial neural network visual model for image quality enhancement

An artificial neural network visual model is developed, which extracts multi-scale edge features from the decompressed image and uses these visual features as input to estimate and compensate for the coding distortions. This provides a generic postprocessing technique that can be applied to all the main coding methods. Experimental results involving postprocessing of the JPEG and quadtree coding systems show that the proposed artificial neural network visual model significantly enhances the quality of reconstructed images, both in terms of the objective peak signal-to-noise ratio and subjective visual assessment.     

A fuzzy neural network model for predicting clothing thermal comfort

This paper presents a Fuzzy Neural Network (FNN) based local to overall thermal sensation model for prediction of clothing thermal function in functional textile design system. Unlike previous experimental and regression analysis approaches, this model depends on direct factors of human thermal response — body core and skin temperatures. First the local sensation is predicted by a FNN network using local body part skin temperatures, their change rates, and core temperature as inputs; then the overall sensation is predicted. This is also performed by a FNN network. The FNN networks are developed on the basis of the Feed-Forward Back-Propagation (FFBP) network; the advantage of using fuzzy logic here is to reduce the requirement of training data. The simulation result shows a good correlation between predicted and the traditional experimental data.     

A GMDH neural network-based approach to passive robust fault detection using a constraint satisfaction backward test

This paper proposes a new passive robust fault detection scheme using non-linear models that include parameter uncertainty. The non-linear model considered here is described by a group method of data handling (GMDH) neural network. The problem of passive robust fault detection using models including parameter uncertainty has been mainly addressed by checking if the measured behaviour is inside the region of possible behaviours based on the so-called forward test since it bounds the direct image of an interval function. The main contribution of this paper is to propose a new backward test, based on the inverse image of an interval function, that allows checking if there exists a parameter in the uncertain parameter set that is consistent with the measured system behaviour. This test is implemented using interval constraint satisfaction algorithms which can perform efficiently in deciding if the measured system state is consistent with the GMDH model and its associated uncertainty. Finally, this approach is tested on the servoactuator being a FDI benchmark in the European Project DAMADICS.     

A neural network-based prediction model for fine pitch stencil-printing quality in surface mount assembly

The soldering problems in surface mount assembly can represent considerable production cost increases and yield loss. About 60% of the soldering defect problems can be attributed to the solder paste stencil printing process. This paper proposes to solve a solder-paste stencil-printing quality problem by a neural network approach. Employment of a neuro-computing approach allows multiple inputs to the generation of multiple outputs. In this study, the inputs are composed of eight important factors in modeling the nonlinear behavior of the stencil-printing process for predicting deposited paste volumes. A 3^8-3 fractional factorial experimental design is conducted to efficiently collect structured data used for neural network training and testing. The results show that the proposed neural-network model is effective in solving a practical application.     

Artificial neural network model for voltage security based contingency ranking

The continual increase in demand for electrical energy and the tendency towards maximizing economic benefits in power transmission system has made real-time voltage security analysis an important issue in the operation of power system. The most important task in real time security analysis is the problem of identifying the critical contingencies from a large list of credible contingencies and rank them according to their severity. This paper presents an artificial neural network (ANN)–based approach for contingency ranking. A set of feed forward neural networks are developed to estimate the voltage stability level at different load conditions for the selected contingencies. Maximum L-index of the load buses in the system is taken as the indicator of voltage instability. A mutual information-based method is proposed to select the input features of the neural network. The effectiveness of the proposed method has been demonstrated through contingency ranking in IEEE 30-bus system. The performance of the developed model is compared with the unified neural network trained with the full feature set. Simulation results show that the proposed method takes less time for training and has good generalization abilities.     

A neural network-based preset generation tool for a steel tandem cold mill

This paper traces the development of a software tool, based on a combination of artificial neural networks (ANN) and a few process equations, aiming to serve as a backup operation instrument in the reference generation for real-time controllers of a steel tandem cold mill. By emulating the mathematical model responsible for generating presets under normal operational conditions, the system works as an option to maintain plant operation in the event of a failure in the processing unit that executes the mathematical model. The system, built from the production data collected over six years of plant operation, steered to the replacement of the former backup operation mode (based on a lookup table), which degraded both product quality and plant productivity. The study showed that ANN are appropriated tools for the intended purpose and that by this instrument it is possible to achieve nearly the totality of the presets needed by this kind of process. The text characterizes the problem, relates the investigated options to solve it, justifies the choice of the ANN approach, describes the methodology and system implementation and, finally, shows and discusses the attained results.