Search

In this paper, we use structural deformations to classify dementia patients. Firstly, surface meshes are recovered from MRI segmented hippocampal, and node-to-node interactions between all the surface meshes are constructed using a spectral matching approach. Then, to learn the low-dimensional feature representation, an enhanced version of the variational auto-encoder (VAE) is given to the vertex coordinates of the surface meshes. We describe a new strategy for increasing variational autoencoder performance (VAE). We designed a generative adversarial training (GAN) technique to train the VAE to generate realistic medical images and apply the deep feature consistency principle, ensuring that the VAE output and its related input images have identical features. A discriminator with a SoftMax layer is concurrently trained to distinguish people with Alzheimer's from healthy people. Studies on the ADNI dataset show that the proposed method can distinguish normal people from early AD/NC and AD/EMCI classes with low computational time and higher accuracy that outperforms the support vector machine (SVM) baseline approach. All the simulation results are carried out with the Anaconda tool.

Diabetes is a terrible health situation characterized by high-rise blood glucose levels. If it is not predicted at an early stage, then it generates the problems in the human body like kidney failure or premature death, and stroke. Controlling blood glucose levels provides patients with helpful dietary recommendations, which are critical components of diabetes management. In the past decades, diverse conventional approaches have been executed to predict the beginning stages of diabetes mellitus depending on physical and substance tests. Still, developing a new framework that can effectively diagnose diabetes mellitus-affected patients is required. To this end, the major target of this task is to predict diabetes mellitus with an advanced accuracy rate with the help of the Heuristic-based Ensemble Model Selection Strategy (H-EMSS). In the data collection phase, the Pima Indian Diabetes dataset (PID) is taken from the storage area of UCI. The data cleaning is performed in the pre-processing stage, which is the technique of removing or fixing, corrupted, incorrect, duplicate, incomplete data, or incorrectly formatted, inside a dataset. Then, the diabetes prediction is accomplished by the H-EMSS. Here, 10 base learners like Naive Bayes (NB), Convolutional Neural Network (CNN), Linear Regression (LR), Deep Neural Network (DNN), Support Vector Machine (SVM), Artificial Neural Network (ANN), Decision Tree (DT), Random Forest (RF), Auto Encoder (AE) and Recurrent Neural Network (RNN) are considered. From these, three classifiers are optimally selected by the Modified Scalar Factor-based Elephant Herding Optimization (MSF-EHO), so that the prediction rate will be high. The suggested methodology’s efficacy is also compared and analyzed, with the findings demonstrating the recommended model’s superiority. The overall evaluation is that the Root Mean Square Error (RMSE) of the designed Modified Scalar Factor-based Elephant Herding Optimization-Heuristic-based Ensemble Model Selection Strategy (MSF-EHO-H-EMSS) attains 4.601% and also the Mean Absolute Error (MAE) on the designed method achieves 0.99%. Thus, the given outcomes of the designed method revealed that it achieves elevated performance than the other existing techniques regarding diverse error metrics.

Big data is a term used to refer to the datasets that are too large (Ex. GBs, TBs, PBs, ZBs, etc.) or complex for traditional data processing application software. Distributed and parallel processing becomes increasingly important for big data. There are two most popular parallel and distributed processing frameworks available, namely Hadoop and Spark. Hadoop and Spark are open-source software frameworks for reliable, scalable, and distributed computing. Hadoop is created by Apache Software Foundation. This framework allows the processing of extremely large datasets on clusters of computers using a simple programming model called MapReduce. It works on a distributed file system called HDFS (Hadoop Distributed File System) to run on commodity hardware. It is designed to scale up horizontally from a single machine to thousands of machines, each offering local computation and storage. Performance of Hadoop cluster depends on the application and several parameters. In this paper we aim to study the performance of Hadoop homogeneous cluster by tuning a few parameters like cluster size, dataset size, and HDFS block size, etc.

High utility patterns mining from transaction databases is an important research area in the field of data mining. Due to the unavailability of downward closure property among the utilities of the itemsets it becomes great challenge to the researchers. Even though, efficient pruning strategy called, transaction weighted utility downward closure property used to reduce the number of candidate itemsets, total time to generate and test candidate itemsets is more. In view of this, in this paper we have proposed a time-efficient tree-based algorithm (TTBM) for mining high utility patterns from transaction databases. We construct conditional pattern bases to generate high transaction weighted utility patterns in the second pass of our algorithm. We used an efficient tree structure called, HP-Tree and tracing method to keep high transaction weighted utility patterns and for discovering high utility patterns respectively. We have compared the performance against Two-Phase and HUI-Miner algorithms. The experimental results show that the execution time of our approach is better.

High utility pattern mining is one of the emerging researches in data mining. Mining these patterns from the evolving data streams is a big challenge, due the characteristics of data streams like high arrival rate, unbounded and gigantic in size, etc. Commonly there are three window models (landmark window, sliding window, time fading window) used in data streams. However, in most applications, users are interested in recent happenings. Hence, sliding window model has attracted high interest among three. Many approaches have been proposed based on the sliding window model. However, most of the approaches are based on level-wise candidate generation and text approach. In view of this, we propose an efficient one pass, tree based approach for mining high utility patterns over data streams. Experimental results show that the performance of our approach is better than the level-wise approach.

The efficiency of covariance descriptors (CovDs) has been explored in several image/video categorization tasks. CovDs lie on Riemannian manifolds known as tensor manifolds. Therefore, the non-Euclidean geometry should be taken into account in devising inference methods that exploit them. In this chapter, we extend the conventional bag-of-words model from Euclidean space to non-Euclidean Riemannian manifolds. To this end, we elaborate on an intrinsic bag-of-Riemannian-words (BoRW) model, which takes into account the true geometry of tensors in obtaining its codebook and histogram. Experiments on challenging a virus texture data set show that the proposed BoRW on CovDs obtains notable improvements in discrimination accuracy, in comparison to popular bag-of-words models.

Support for dynamic attributes is increasingly important for facilitating high-quality web service discovery for service-oriented architectures. we proposed the static discovery dynamic selection (SDDS) architecture to overcome limitations of existing web service discovery methods. Our service discovery algorithms consider dynamic attributes to reduce the number of viable and acceptable services and thereby improve the consumer experience. In this paper, we propose a semantic model based on finite state automata to validate interactions among the SDDS components that deal with dynamic attributes. Our analysis using the automata model revealed a flaw in the SDDS communication synchronization. This flaw was corrected by introducing a webbased synchronization component to enforce valid communication patterns.

High utility pattern mining is an emerging research topic in the data mining field. Unlike frequent pattern mining, high utility pattern mining deals with non-binary databases, in which the information about purchased quantities of items is maintained. Due to the non-existence of anti-monotone property among the utilities of itemsets, utility mining becomes a big challenge. Moreover, discovering useful patterns from the huge number of potential patterns is a mining bottleneck. However, the compact (Closed and Maximal) high utility pattern mining moderately lessens the number of patterns, but it does not solve it. Recently, an efficient framework called GUIDE, was proposed in the literature to address this issue. Though, GUIDE effectively reduced the number of high utility patterns, yet the quality of few mined patterns and their utilities are not exact. In view of this, we propose a modified MGUIDELM algorithm to improve the quality and determine exact utilities of maximal patterns.