In recent days, skin cancer is seen as one of the most Hazardous form of the Cancers found in Humans. Skin cancer is found in various types such as Melanoma, Basal and Squamous cell Carcinoma among which Melanoma is the most unpredictable. The detection of Melanoma cancer in early stage can be helpful to cure it. Computer vision can play important role in Medical Image Diagnosis and it has been proved by many existing systems. In this paper, we present a computer aided method for the detection of Melanoma Skin Cancer using Image Processing tools. The input to the system is the skin lesion image and then by applying novel image processing techniques, it analyses it to conclude about the presence of skin cancer. The Lesion Image analysis tools checks for the various Melanoma parameters Like Asymmetry, Border, Colour, Diameter,(ABCD) etc. by texture, size and shape analysis for image segmentation and feature stages. The extracted feature parameters are used to classify the image as Normal skin and Melanoma cancer lesion

In traditional machine learning approaches to classification, one uses only a labelled set to train the classifier. Labelled instances however are often difficult, expensive, or time consuming to obtain, as they require the efforts of experienced human annotators. Meanwhile unlabeled data may be relatively easy to collect, but there has been few ways to use them. Semi-supervised learning addresses this problem by using large amount of unlabeled data, together with the labelled data, to build better classifiers. Because semi-supervised learning requires less human effort and gives higher accuracy, it is of great interest both in theory and in practice. The paper discusses various important approaches to semi-supervised learning such as self-training, co-training(CO), expectation maximization (EM), CO-EM, Then how graph-based methods are useful is explained. All semi-supervised learning methods are classified into generative and discriminative methods. But experimental results show that the hybrid algorithm gives better classification accuracy.

A number of algorithms are available in the areas of data mining, machine learning and pattern recognition for solving the same kind of problem. But there is a little guidance for suggesting algorithm to use which gives best results for the problem at hand. This paper shows an approach for solving this problem using meta-learning. The paper uses three types of data characteristics. Simple, information theoretic, and statistical data characteristics are used. Results are generated using nine different algorithms on thirty eight benchmark datasets from UCI repository. The proposed approach uses K-nearest neighbor algorithm for suggesting the suitable algorithm. Classifier accuracy is taken as a basis for recommending the algorithm. By using meta-learning, accurate method can be recommended as per the given data, and cognitive overload for applying each method, comparing with other methods and then selecting the suitable method for use can be reduced. Thus it helps in adaptive learning methods. The experimentation shows that predicted accuracies are matching with the actual accuracies for more than 90 % of the benchmark datasets used. Thus it is concluded that the number of attributes, the number of instances, the number of classes, maximum probability of class and class entropy are playing a major role in classifier accuracy and algorithm selection for thirty eight datasets used for experimentation.

Classification of imbalance data is the major challenge to the community these days. Machine learning algorithms can evolve a one-sided classifier when data is imbalance. The vital challenge in imbalance dataset problem is that sometimes the minority (tiny) classes are more useful, but standard classifiers tend to be biased toward the majority (huge) classes and ignore the tiny ones. In this paper we compared the existing methods to handle imbalance dataset and provide a new hybrid approach which will improve the accuracy of classifier on imbalanced data.

The advent of social media and the rapid development of mobile communication technologies have dramatically changed the way to express the feeling, attitude, mood, passion etc. People often express their reactions, fancies, preferences etc. through social media in the form of short texts instead of long texts. In micro blogging services like twitter, people can share and discuss their views without any constraints. Thus, these are the sentiments of people which can characterize their behavior. Nowadays, politicians also refer facebook, twitter and blogs to collect reviews amongst the people about them. A model is developed which captures the comments of people and forwards it to the preprocessing module. It contains URL removal, stopword removal, tokenization, abbreviation expansion and stemming processes. Further the result obtained is passed on to neural network. Here, Recurrent Neural Network (RNN) model is used to predict the sentiments, whether audience have positive or negative responses. RNN uses its Long Short Term Memory (LSTM) module for processing of the data. The final result obtained is binary classification and representation of opinions.