Durgesh Pant

Automatic apple grading model development based on back propagation neural network and machine vision, and its performance evaluation

This paper describes a new apple classification system based on machine vision and artificial neural network (ANN), which classifies apple in real time on the basis of physical parameters of apple such as size, color and external defects. A specific hardware subsystem has been developed and described for every stage of input and output. The hardware subsystem is interfaced with the software to make the whole system automatic. The purpose of this paper is to automate apple classification. Presently, ANN is used in a wide range of classification applications. We have trained a back-propagation neural network to classify apple. Two sets of variables are used for the training purpose. First set is the independent variable, which is the surface level apple quality parameter. Second set is the dependent variable, which is the quality of the apple. The results of ANN model are discussed; however, the modeling results showed that there is an excellent agreement between the experimental data and predicted values, with a high determination coefficient, very good performance, fewer parameters, shorter calculation time and lower prediction error. The classification accuracy achieved is high, showing that a neural network is capable of making such classification. A low level of errors in classification confirmed that the neural network models are an effective instrument for apple classification. This model might be an alternative method for assessing the quality of apple and provide consumers with a safer food supply.

An analysis of the performance of Artificial Neural Network technique for apple classification

The purpose of this paper is to develop Artificial Neural Network (ANN)-based apple classifier. Testing effort is calculated using ANN method. The complete system is divided into two modules. In the first module, input (surface level apple quality parameter) from the different sources is collected by the software developed in Visual Basic through different input device like web camera, weight machine, etc. In the second module, the input data are used by ANN simulator to classify the apple according to their quality. The final result of an ANN model for apple classification is discussed; however, the modeling results showed that there is excellent agreement between the experimental data and predicted values. A low level of error prediction confirmed the fact that the Neural Network model is an effective instrument of the apple quality estimation. There is not any misclassification during testing. The paper presents alternative method for quality assessment of apple and provides consumers with a safer food supply.

Optimal component selection for component based software development using pliability metric

Component Based Software Development (CBSD) has gained widespread acceptance as it often results in higher quality software with a significant reduction in development time and costs. A key idea behind CBSD is the extensive reuse and composition of preexisting modules into new software. In this paper we introduce the pliability metric, which is well suited to a component-based orientation and extends previous metrics. Pliability is a flexible measure that assesses software quality across different quality attributes in terms of the quality of its components. In addition, we have developed an optimal component selection model based on integer programming, for maximizing pliability. Through computational experimentation we demonstrate that this model is capable of finding optimal solutions to problems with a very large number of components and requirements in a short time.

Proposed E-Health Service Model by using Smart Phone Apps for Uttarakhand

For E-HEALTH initiatives in Uttarakhand the proposed E-HEALTH service model may allow better sharing of health information among multiple government departments, locally as well as at a distant location. But without coordination of different departments in Uttarakhand we cannot setup good e-health solutions. Priorities of Uttarakhand government for providing E-HEALTH facilities to rural areas are yet to be fulfilled. At present stage less budget from state government for health, and lack of coordination have triggered down trend in health services in rural and hilly areas of Uttarakhand This paper reviews use of ICT applications at different locations in our country and also try to provide a model for Uttarakhand province. Some suggested services using ICT and smart phone apps in healthcare are explained in this paper also. Use of smart phone apps to communicate health associated alerts using SMS services and collect information from rural areas suggested here in this paper.

Role of Cloud enabled data center for transforming E-Health services in Uttarakhand

Using various technologies in health services of Uttarakhand may allow the sharing of patient information among multiple sites. By using the concept of Cloud computing in healthcare services of Uttarakhand we could setup an effective model for delivering of health services. Role of data centre is very important while transforming health services in rural and remote Uttarakhand. Establishment of data centre through cloud may help in overcoming the challenges of geographical constraints like availability of phone network, road connectivity, power backup etc. We could propose the use of smart phone apps in using of this cloud enabled data centre.

IT-initiatives for empowering difficult geographies: A review

While studying the effectiveness of IT-initiatives in Uttarakhand state, a hill state in the central Himalayan region in India, it was realized that unless technology reaches and benefits the last man, it is way beyond its intended role. The present paper puts forward the concept of Inclusive-IT which can counter the asymmetries cropping up because of the rising differentiation between informatics haves and have-nots. The present work takes into account the conceptual issues related to the information technology initiatives in the state of Uttarakhand.

A Gaps Approach to Access the Efficiency and Effectiveness of IT-Initiatives In Rural Areas: case study of Samalta, a village in the central Himalayan Region of India

This paper focuses on the effectiveness and efficiency of IT initiatives in rural areas where topology creates isolation to developmental activities. A village is selected for the study and information is gathered through interviews of village dwellers. These collected responses are then analyzed and a gaps model is proposed.

On Some Quality Issues of Component Selection in CBSD

Component based development offers many potential benefits, viz. software reuse, reduced time-to-market, inter- operability, ease of quality certification etc. However, it is not always that benefits derived from addition of components from a component repository are more than the costs involved in developing the module from scratch. This work evaluates various software quality models and suggests recommendations for enhancing software quality in COTS (component off-the-shelf) based software products by designing software quality metrics that would help in managing and enhancing quality in component-based software development.