No abstract

No abstract

A drawback of the error-back propagation algorithm for a multilayer feed forward neural network is over learning or over fitting. We have discussed this problem, and obtained necessary and sufficient Experiment and conditions for over-learning problem to arise. Using those conditions and the concept of a reproducing, this paper proposes methods for choosing training set which is used to prevent over-learning. For a classifier, besides classification capability, its size is another fundamental aspect. In pursuit of high performance, many classifiers do not take into consideration their sizes and contain numerous both essential and insignificant rules. This, however, may bring adverse situation to classifier, for its efficiency will been put down greatly by redundant rules. Hence, it is necessary to eliminate those unwanted rules. We have discussed various experiments with and without over learning or over fitting problem.

Cervical intraepithelial neoplasia (CIN) and cervical cancer are major health problems faced by women worldwide. The conventional Papanicolaou (Pap) smear analysis is an effective method to diagnose cervical pre-malignant and malignant conditions by analyzing swab images. Various computer vision techniques can be explored to identify potential precancerous and cancerous lesions by analyzing the Pap smear image. The majority of existing work cover binary classification approaches using various classifiers and Convolution Neural Networks. However, they suffer from inherent challenges for minute feature extraction and precise classification. We propose a novel methodology to carry out the multiclass classification of cervical cells from Whole Slide Images (WSI) with optimum feature extraction. The actualization of Conv Net with Transfer Learning technique substantiates meaningful Metamorphic Diagnosis of neoplastic and pre-neoplastic lesions. As the Progressive Resizing technique (an advanced method for training ConvNet) incorporates prior knowledge of the feature hierarchy and can reuse old computations while learning new ones, the model can carry forward the extracted morphological cell features to subsequent Neural Network layers iteratively for elusive learning. The Progressive Resizing technique superimposition in consultation with the Transfer Learning technique while training the Conv Net models has shown a substantial performance increase. The proposed binary and multiclass classification methodology succored in achieving benchmark scores on the Herlev Dataset. We achieved singular multiclass classification scores for WSI images of the SIPaKMed dataset, that is, accuracy (99.70%), precision (99.70%), recall (99.72%), F-Beta (99.63%), and Kappa scores (99.31%), which supersede the scores obtained through principal methodologies. GradCam based feature interpretation extends enhanced assimilation of the generated results, highlighting the pre-malignant and malignant lesions by visual localization in the images.

No abstract

Data mining tools aims to find useful patterns from large amount of data. These patterns represent information and are conveyed in decision trees, clusters or association rules. The knowledge discovered by various data mining techniques may contain private information about people or business. Preservation of privacy is a significant aspect of data mining and thus study of achieving some data mining goals without losing the privacy of the individuals' .The analysis of privacy preserving data mining (PPDM) algorithms should consider the effects of these algorithms in mining the results as well as in preserving privacy. Within the constraints of privacy, several methods have been proposed but still this branch of research is in its formative years .The success of privacy preserving data mining algorithms is measured in terms of its performance, data utility, level of uncertainty or resistance to data mining algorithms etc. However no privacy preserving algorithm exists that outperforms all others on all possible criteria. Rather, an algorithm may perform better than another on one specific criterion. So, the aim of this paper is to present current scenario of privacy preserving data mining framework and techniques.

The problem of model selection is considerably important for acquiring higher levels of generalization capability in supervised learning. Neural networks are commonly used networks in many engineering applications due to its better generalization property. An ensemble neural network algorithm is proposed based on the Akaike information criterion (AIC). Ecologists have long relied on hypothesis testing to include or exclude variables in models, although the conclusions often depend on the approach used. The advent of methods based on information theory, also known as information-theoretic approaches, has changed the way we look at model selection The Akaike information criterion (AIC) has been successfully used in model selection. It is not easy to decide the optimal size of the neural network because of its strong nonlinearity. We discuss problems with well used information and propose a model selection method.

Abstract-an Artificial Neural Network classifier is a nonparametric classifier. It does not need