In this paper, we formulated around a certifiable issue identified with sewer-pipeline gas detection using the approaches which classified the problem into two categories,also known as classificationbased approach. The primary objective of this project is to recognize the dangerous gases present inside sewer-pipeline to offer protected access to sewer-pipeline with the goal that the human fatalities, which happen due to presence of toxic gases can be avoided. The dataset is created through mixing all the different gases present in sewer pipelines under different situation to make sure all the cases are taken into consideration, these datasets were sorted out to plan a predictive model that could distinguish/characterize hazardous and non-hazardous circumstance of sewer-pipeline. To design such prediction model, classification algorithms were utilized and their performance were assessed and thought about, both exactly and factually, over the collected dataset. In addition, the project also will predict the composition of gases present in the sewer pipeline and display the values for the better understanding of the condition present in sewer pipeline. The final observation of this study demonstrated that the performed of instance basedlearning algorithm were superior to numerous different algorithms, for example, multi-layer perceptron, support vector machine, and so on. Also, it was observed that multi-scheme ensemble approach improved the execution of base indicators.

This paper deals with the implementation of Neural Network based face recognition system. As we know that face recognition system is one of the biometric information processing which has speed up in the last few decades. The developed algorithm for the face recognition system originates an image based approach, which uses the Two-Dimensional Discrete Cosine Transform (2D-DCT) to compress image, and then Self Organizing Map (SOM) Neural Network to recognize the face and its simulated in MATLAB. With the help of 2D-DCT the image vectors are extracted and these vectors sends to the neural network classifier which is developed using self organizing map, algorithm to recognize trained faces, faces with variations in expressions, changes of illumination, upto certain degrees. The alternate way of the same face recognition system is developed with the help of principle component analysis (PCA) instead of Two Dimensional Cosine Transform and Self-Organizing Map Neural Network to recognize the faces. In this proposed algorithm we use unsupervised single neural network as a classifier for both Two Dimensional Discrete Cosine Transform (2D-DCT) and Principal Component Analysis (PCA).