Abstract-Optimizing K-means is still an active area of research for purpose of clustering. Recent developments in Cloud Co mputing have resulted in emergence of Big Data Analytics. There is a fresh need of simp le, fast yet accurate algorithm for clustering huge amount of data. This paper proposes optimization of K-means through reduction of the points which are considered for reclustering in each iteration. The work is generalizat ion of earlier work by Poteras et al who proposed this idea. The suggested scheme has an improved average runtime. The cost per iteration reduces as number of iterations grow which makes the proposal very scalable.
Abstract-TextClassificat ion is done mainly through classifiers proposed over the years, Naï ve Bayes and Maximu m Entropy being the most popular of all. However, the individual classifiers show limited applicability according to their respective domains and scopes. Recent research works evaluated that the combination of classifiers when used for classification showed better performance than the individual ones. This work introduces a modified Maximu m Entropy-based classifier. Maximu m Entropy classifiers provide a great deal of flexibility for parameter defin itions and follow assumptions closer to real world scenario. This classifier is then combined with a Naï ve Bayes classifier. Naï ve Bayes Classification is a very simp le and fast technique. The assumption model is opposite to that of Maximu m Entropy. The combination of classifiers is done through operators that linearly co mbine the results of two classifiers to predict class of documents in query. Proper validation of the 7 proposed modifications (4 mod ifications of Maximu m Entropy, 3 combined classifiers) are demonstrated through imp lementation and experimenting on real life datasets.
Blood cell malignantly growth has been accounted for to be one of the most transcendent types of disease maladies. ALL (Acute Lymphoblastic Leukaemias) is the malignant types of blood cancer and their detection and classification in earlier stage is biggest issue. Automatic detection and classification of ALL from microscopic images is a challenging and intellectual assignment in medical science. Existing techniques for ALL detection and classification are an understandable alternative for real-time dermoscopic data analysis. Existing microscopic image processing approaches are unable to analyze the ALL data with non-stationary nature. In this perspective, the focus of this research is to design hybrid Convolutional Neural Network (CNN) architecture by utilizing Firefly Optimization Algorithm (FOA/FFA) to detect the ALL from microscopic images of human blood cell into malignant or normal blood cell. Methods: For training and testing of proposed ALL Detection and Classification (ALL-DC) Model, Standard ALL-IDB (Acute-Lymphoblastic-Leukaemias Image Database for Image Processing) is used with hybrid CNN architecture based on the FOA. Here, Histogram of Oriented Gradients (HOG) descriptor with FOA is used as feature extraction and selection mechanism from the Region of Blood Cell (ROBC).Feature extraction approach plays an important responsibility to classify lots of blood diseases. On the way to achieve this goal, we proposed ALL-DC model that combines recent developments in deep learning with fuzzy based CNN structure and for ROBC segmentation, hybridization of K-means segmentation algorithm with FOA that are capable to segment the accurate blood cell region from microscopic images. Using k-means segmentation technique, the foreground and background component is separated into two regions and after that to improve the segmentation results; FOA is used with the novel concept of image enhancement approach. Results: The proposed ALL-DC system is evaluated using the largest publicly accessible standard ALL-IDB dataset, containing 600 training and 400 testing microscopic images. When the evaluation parameters of proposed work is compared with a number of other state-of-art schemes, the proposed scheme achieves the most excellent performance of 98.5% in terms of accuracy which also known as area under the curve (AUC) in differentiating ALL from benign cell using only the extracted and optimized HOG feature. Conclusion: When the proposed model is tested on different microscopic images, evaluation parameters is calculated and compared with a few other state-of-art methods and we obtained the proposed method achieves the best performance in terms of classification accuracy. ALL-DC model is implemented and constructed using the concept of Image
Cloud computing is the most popular term among enterprises and news. The concepts come true because of fast internet bandwidth and advanced cooperation technology. Resources on the cloud can be accessed through internet without self built infrastructure. Cloud computing is effectively manage the security in the cloud applications. Data classification is a machine learning technique used to predict the class of the unclassified data. Data mining uses different tools to know the unknown, valid patterns and relationships in the dataset. These tools are mathematical algorithms, statistical models and Machine Learning (ML) algorithms. In this paper author uses improved Bayesian technique to classify the data and encrypt the sensitive data using hybrid stagnography. The encrypted and non encrypted sensitive data is sent to cloud environment and evaluate the parameters with different encryption algorithms.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.