Abhijit S. Pandya

On-line learning control of autonomous underwater vehicles using feedforward neural networks

A neural-network-based learning control scheme for the motion control of autonomous underwater vehicles (AUV) is described. The scheme has a number of advantages over the classical control schemes and conventional adaptive control techniques. The dynamics of the controlled vehicle need not be fully known. The controller with the aid of a gain layer learns the dynamics and adapts fast to give the correct control action. The dynamic response and tracking performance could be accurately controlled by adjusting the network learning rate. A modified direct control scheme using multilayered neural network architecture is used in the studies with backpropagation as the learning algorithm. Results of simulation studies using nonlinear AUV dynamics are described in detail. The robustness of the control system to sudden and slow varying disturbances in the dynamics is studied and the results are presented. >

A comparative study of pattern recognition techniques for quality evaluation of telecommunications software

The extreme risks of software faults in the telecommunications environment justify the costs of data collection and modeling of software quality. Software quality models based on data drawn from past projects can identify key risk or problem areas in current similar development efforts. Once these problem areas are identified, the project management team can take actions to reduce the risks. Studies of several telecommunications systems have found that only 4-6% of the system modules were complex /spl lsqb/LeGall et al. 1990/spl rsqb/. Since complex modules are likely to contain a large proportion of a systems faults, the approach of focusing resources on high-risk modules seems especially relevant to telecommunications software development efforts. A number of researchers have recognized this, and have applied modeling techniques to isolate fault-prone or high-risk program modules. A classification model based upon discriminant analytic techniques has shown promise in performing this task. The authors introduce a neural network classification model for identifying high-risk program modules, and compare the quality of this model with that of a discriminant classification model fitted with the same data. They find that the neural network techniques provide a better management tool in software engineering environments. These techniques are simpler, produce more accurate models, and are easier to use. >

A neural network approach for predicting software development faults

Accurately predicting the number of faults in program modules is a major problem in the quality control of a large scale software system. In this paper, the use of the neural networks as a tool for predicting the number of faults in programs is explored. Software complexity metrics have been shown to be closely related to the distribution of faults in program modules. The objective in the construction of models of software quality is to use measures that may be obtained relatively early in the software development life cycle to provide reasonable initial estimates of quality of an evolving software system. Measures of software quality and software complexity to be used in this modeling process exhibit systematic departures of normality assumptions of regression modeling. This paper introduces a new approach for static reliability modeling and compares its performance in the modeling of software reliability from software complexity in terms of the predictive quality and the quality of fit with more traditional regression modeling techniques. The neural networks did produce models with better quality of fit and predictive quality when applied to one data set obtained from a large commercial system.<<ETX>>

Application of neural networks for predicting program faults

Accurately predicting the number of faults in program modules is a major problem in the quality control of large software development efforts. Some software complexity metrics are closely related to the distribution of faults across program modules. Using these relationships, software engineers develop models that provide early estimates of quality metrics that do not become available until late in the development cycle. By considering these early estimates, software engineers can take actions to avoid or prepare for emerging quality problems. Most often, the predictive models are based upon multiple regression analysis. However, measures of software quality and complexity exhibit systematic departures from the assumptions of these analyses. With extreme violations of these assumptions, multiple regression models become unstable and lose most of their predictive quality. Since neural network models carry no data assumptions, these models could be more appropriate than regression models for modeling software faults. In this paper, we explore a neural network methodology for developing models that predict the number of faults in program modules. We apply this methodology to develop neural network models based upon data collected during the development of two commercial software systems. After developing neural network models, we apply multiple linear regression methods to develop regression models on the same data. For the data sets considered, the neural network methodology produced better predictive models in terms of both quality of fit and predictive quality.

A recurrent neural network controller and learning algorithm for the on-line learning control of autonomous underwater vehicles

A new on-line direct control scheme for the Autonomous Underwater Vehicles (AUV), using recurrent neural networks, is investigated. In the proposed scheme, the controller consists of a three-layer network architecture having feedforward input and output layers, and a totally recurrent hidden layer. All the interconnection strengths are synchronously updated using a computationally inexpensive learning algorithm called Alopex. The updating is based on the output error of the system directly, rather than using a transformed version of the error employed in the other neural network based direct control schemes. In the present implementation, the network starts from random initial conditions without needing any prior training, and learns the dynamics of the AUV to provide the correct control signal. Based on the simulation experiments using the nonlinear dynamics of an AUV, we demonstrate that the proposed learning algorithm and the network architecture provide stable and accurate tracking performance. We have also addressed the issue of robustness of the controller to system parameter variations as well as to measurement disturbances.

Dynamic pattern recognition of coordinated biological motion

So far in this book we have been concerned with static patterns. As humans, we may also recognize patterns of movement such as walking and trotting of horses. This leads us to ask whether movement patterns can also be recognized by the synergetic computer.

The Impact of Gene Selection on Imbalanced Microarray Expression Data

Microarray experiments usually output small volumes but high dimensional data. Selecting a number of genes relevant to the tasks at hand is usually one of the most important steps for the expression data analysis. While numerous researches have demonstrated the effectiveness of gene selection from different perspectives, existing endeavors, unfortunately, ignore the data imbalance reality, where one type of samples (e.g., cancer tissues) may be significantly fewer than the other (e.g., normal tissues). In this paper, we carry out a systematic study to investigate the impact of gene selection on imbalanced microarray data. Our objective is to understand that if gene selection is applied to imbalanced expression data, what kind of consequences it may bring to the final results? For this purpose, we apply five gene selection measures to eleven microarray datasets, and employ four learning methods to build classification models from the data containing selected genes only. Our study will bring important findings and draw numerous conclusions on (1) the impact of gene selection on imbalanced data, and (2) behaviors of different learning methods on the selected data.

An improved scheme for direct adaptive control of dynamical systems using backpropagation neural networks

This paper presents an improved direct control architecture for the on-line learning control of dynamical systems using backpropagation neural networks. The proposed architecture is compared with the other direct control schemes. In this scheme the neural network interconnection strengths are updated based on the output error of the dynamical system directly, rather than using a transformed version of the error employed in other schemes. The ill effects of the controlled dynamics on the on-line updating of the network weights are moderated by including a compensating gain layer. An error feedback is introduced to improve the dynamic response of the control system. Simulation studies are performed using the nonlinear dynamics of an underwater vehicle and the promising results support the effectiveness of the proposed scheme.

Logistic GMDH-type neural networks and their application to the identification of the X-ray film characteristic curve

Logistic group method of data handing (GMDH)-type neural networks identifying a complex nonlinear system are proposed. Logistic GMDH-type neural networks are automatically organized by using the heuristic self-organization method which is used in the GMDH method. In the logistic GMDH-type neural networks, the structural parameters such as the number of layers, the number of neurons in each layer, useful input variables and optimum neuron architectures are automatically determined by using the error criterion derived from the AIC (Akaikes Information Criterion). This way, optimum neural network architectures which fit the complexity of the nonlinear system are produced. The logistic GMDH-type neural networks have been applied to the identification problem of the X-ray film characteristic curve. It has been found that the modeling with the logistic GMDH-type neural networks is more accurate than when multiple regression analysis, the conventional neural networks and the GMDH method are used.

A neural network modeling methodology for the detection of high-risk programs

The profitability of a software development effort is highly dependent on both timely market entry and the reliability of the released product. To get a highly reliable product to the market on schedule, software engineers must allocate resources appropriately across the development effort. Software quality models based upon data drawn from past projects can identify key risk or problem areas in current similar development efforts. Knowing the high-risk modules in a software design is a key to good design and staffing decisions. A number of researchers have recognized this, and have applied modeling technqiues to isolate fault-prone or high-risk program modules early in the development cycle. Discriminant analytic classification models have shown promise in performing this task. We introduce a neural network classification model for identifying high-risk program modules, and we compare the quality of this model with that of a discriminant classification model fitted with the same data. We find that the neural network techniques provide a better management tool in software engineering environments.