Analyzing and processing a big data is a challenging task because of its various characteristics and presence of data in large amount. Due to the enormous data in today’s world, it is not only a challenge to store and manage the data, but to also analyze and retrieve the best result out of it. In this paper, a study is made on the different types available for big data analytics and assesses the advantages and drawbacks of each of these types based on various metrics such as scalability, availability, efficiency, fault tolerance, real-time processing, data size supported and iterative task support. The existing system approaches for range-partition queries are insufficient to quickly provide accurate results in big data. In this paper, various partitioning techniques on structured data are done. The challenge in existing system is, due to the proper partitioning technique, and so the system has to scan the overall data in order to provide the result for a query. Partitioning is performed; because it provides availability, maintenance and improvised query performance to the database users. A holistic study has been done on balanced range partition for the structured data on the hadoop ecosystem i.e. the HIVE and the impact on fast response which would eventually be taken as specification for testing its efficiency. So, in this paper a thorough survey on various topics for processing and analysis of vast structured datasets, and we have inferred that balanced partitioning through HIVE hadoop ecosystem would produce fast and an adequate result compared to the traditional databases. Keywords –

The Breast cancer is one of the leading cancers for women in world countries including India. It is the second most common causes of cancer death in women. The high incidence of breast cancer in women has increased significantly in the last few years. Detecting cancer in the later stages, leads to very complicated surgeries and the chances of death is very high nowadays. Early detection of Breast Cancer helps in less complicated procedures and early recovery. Many tests have been found so as to detect cancer. Some of those tests are mammography, ultrasound etc. Mammography is a method that helps in early detection of Breast Cancer. But finding the mass and its spread from mammographic images is very difficult. Expert radiologists were needed for accurate reading of a mammogram image, and analyses have been for kMeans algorithm which helps for easy detection and extraction tumor area. The mammography image helps to provide some criteria in order to help the physicians to decide whether a certain disease is abnormal or normal. This research work is to identify the breast cancer tumor area and find its affected region by splitting the images into five clusters. The tumor area has been identified in the last cluster and classified with the help of decision tree algorithms J48 and CART.

Automated text categorisation has been considered as a vital method to manage and process vast amount of documents in digital form that are widespread and continuously increasing.Traditional classification problems are usually associated with a single label.Text Categorization uses Multi-label Learning which is a form of supervised learning where the classification algorithm is required to learn from a set of instances, each instance can belong to multiple classes and then be able to predict a set of class labels for a new instance. Multi-label classification methods have been increasingly used in modern applications such as music categorization, functional genomics (gene protein interactions) and semantic annotation of images besides document filtering, email classification and Web search. Multi-label classification methods can be broadly classified asProblem transformation and Algorithm adaptation. This paper presents anoverview of single-label text classificationand an analysis ofsome multilabel classification methods.

Depressive disorder is an illness that involves the body, mood and thoughts. It interferes with daily life, normal functioning and causes pain for both the person with the disorder and those who care about him/her. Severe depression may lead to serious illness or suicide. The most affected sector is the Adolescent Community. The biggest problem in diagnosing and treating depressive disorders is recognizing that someone is suffering from it. As various factors are involved, it is very difficult for the Psychologists to diagnose depressive disorders correctly at an early stage itself. Nowadays, computers are used in assisting Physicians to diagnose diseases and identify correct treatments according to the patient details. In the same way, computers can also be used in assisting psychologists to diagnose mental disorders and identify correct treatments according to the patient details. Various techniques are available to store the expert knowledge and computerize the diagnosis process. Bayesian Network is such a technique that combines statistics and expert knowledge to diagnose diseases effectively. This paper proposes a Framework for diagnosing depression level in adolescents using Bayesian Networks. Initially, Ontology should be constructed to provide a basis for Bayesian Networks. The ontology acts as the topology and shows the relationships between adolescent depression concepts. By applying probabilities to the relationships between concepts from the statistics, and by using Bayes Theorem, depression level of a patient can be diagnosed effectively. This framework may help novice psychologists to understand the domain concepts and also to diagnose the depression level and suggest correct treatments.

Let us not make the cure of the disease more unbearable than the disease itself this quote is the most durable and inspirational line of medicine field. Data mining is said to be an umbrella term which refers to the progression of finding out the patterns in data. This can be even succeeded typically with an assistance of authoritative algorithm to automate search (as a part). This paper reveals out, how the C2P (Cervical Cancer Prediction) model is approached by a data mining algorithm for prediction. The prediction of C2 (Cervical Cancer) has been a challenging problem in research field. In the Data mining applications, we are utilizing RFT (Random Forest Tree) algorithm to do the prediction. To the best of our knowledge, we use popular clustering K-means technique to achieve more accuracy.

The main objective of education institutions is to provide quality education to its students. One way to achieve highest level of quality in higher education system is by discovering knowledge of students in a particular course. The knowledge is hidden among the educational data set and it is extractable through data mining techniques. In this paper, the K-Median method in clustering technique is used to evaluate students performance. By this task the extracted knowledge that describes students performance in end semester examination. It helps earlier in identifying the students who need special attention and allow the teacher to provide appropriate advising and coaching.

The large amount of data stored in unstructured texts cannot simply be used for further processing by computers, which typically handle text as simple sequences of character strings. Therefore, specific (pre-) processing methods and algorithms are required in order to retrieve useful information via text. Text mining refers generally to the process of retrieving information and knowledge from formless text. This research work analyses about the use of classification algorithms and their uses to predict the applications of text mining. The purpose of this work is to present an analysis of recent publications concerning with text mining using classification algorithm in particular. This survey finds out some of the best suitable algorithms for text mining analyses suggested by the various researchers in their research work.

The large amount of data stored in unstructured texts cannot simply be used for further processing by computers, which typically handle text as simple sequences of character strings. Therefore, specific (pre-) processing methods and algorithms are required in order to retrieve useful information via text. Text mining refers generally to the process of retrieving information and knowledge from formless text. This research work analyses about the use of classification algorithms and their uses to predict the applications of text mining. The purpose of this work is to present an analysis of recent publications concerning with text mining using classification algorithm in particular. This survey finds out some of the best suitable algorithms for text mining analyses suggested by the various researchers in their research work.

Text mining is vast area as compared to information retrieval. Typical text mining tasks include document classification, document clustering, building ontology, sentiment analysis, document summarization, Information extraction etc. Text mining, also referred to as text data mining, roughly equivalent to text analytics, refers to the process of deriving high-quality information from text. Information Extraction is a vital area in Text Mining Techniques, which is an automatic/semi automatic extraction of structured information from unstructured documents. In most of the cases this activity concerns processing human language texts by means of natural language processing (NLP). In this paper, we present themultimedia document processing and automatic annotation out of images/video as information extraction.

Mining distributed databases is emerging as a fundamental computational problem. A common approach for mining distributed databases is to move all of the data from each database to a central site and a single model is built. Privacy concerns in many application domains prevents sharing of data, which limits data mining technology to identify patterns and trends from large amount of data. Traditional data mining algorithms have been developed within a centralized model. However, distributed knowledge discovery has been proposed by many researchers as a solution to privacy preserving data mining techniques. By vertically partitioned data, each site contains some attributes of the entities in the environment.In this paper, we present a method for Agglomerative clustering algorithm in situations where different sites contain different attributes for a common set of entities for verticallypartitioned data. Using association rules data are partitioned into vertically.

Digital Retinal Funds image is analyzed for the classification and stages of Diabetic Retinopathy (DR).This imparts importance, since many of heart, lung, and kidney related problems could be predicted well in advance, by analyzing the fundus image itself which is an cost effective technique. Also, Later stages of DR causes abnormal changes in human retina and vision loss is occurred in most of the patients. The aim is to extract the abnormal features like Microaneurysms, exudates, and blood vessels, to classify DR at its proliferative stage itself. At the same time, the healthy or normal features like optic disk, blood vessel map is to be removed by suitable enhancement technique (Morphological technique) .The abnormal features and its normal ground features are trained for classification. The classification is done using ANFIS architecture. The detection and classification method , surely provide an additional and promising data and information to ophthalmologists and to the analyst for further treatment. The proposed method will give a promising accuracy when compared with the methods available in the literature.

The organizations have always sought ways and methodologies to boost the quality level of their product. Obviously, economic aspect ought to be taken into account, eschewing irrational costs in the system. Data mining can be applied as one of the best technics at hand in case of analysis and prediction of performance and quality. In this work, we have used a new methodology based on data mining to predict and improve the quality level of the electronic parts. The results suggest better accuracy compared to the previous studies.

In this paper we propose a new method for improving the clustering accuracy of text data. Our method encodes the string values of a dataset using Arithmetic encoding algorithm, and declares these attributes as integer in the clustering phase. In the experimental part, we calculate the efficiency of proposed method, and we obtained a better clustering accuracy than the one found with traditional methods. This method is useful when the dataset to be clustered has only string attributes, because in this case, a traditional clustering method does not recognize, or recognize with a low accuracy, the category of instances.