Machine Learning

We investigate the possibility to apply a known machine learning algorithm of Q-learning in the domain of a Virtual Learning Environment (VLE). It is important in this problem domain to have algorithms that learn their optimal values in a rather short time expressed in terms of the iteration number. The problem domain is a VLE in which an agent plays

Diseases related to Heart i.e. Cardiovascular Dis-eases (CVDs) are the main reason for the number of deaths in the course of the most recent couple of decades and has developed as the most perilous ailment, in India and in the entire world. In this way, there is a need for accurate, feasible and reliable system to analyze such maladies in time for legitimate treatment.  Machine Learning algorithms and procedures have been im-plemented to various medical datasets to various medical datasets to investigate of extensive and complex information. Numerous analysts, as of late, have been using several methods to enable the health care industry and the professionals in the diagnosis of heart related diseases. This paper demonstrates a survey of various models based on such algorithms and techniques and analyze their perfor-mance. Models depend on supervised learning algorithms such as Support Vector Machines (SVM), K-Nearest Neighbour (KNN), Naive Bayes, Decision Trees (DT), Random Forest ...

In order for information retrieval to be used in software engineering, text must be available. The most obvious sources for this text are the code, comments, and external documentation. The challenge then becomes determining the appropriate information retrieval tools and techniques to apply. The choice most often depends on the task under consideration. One task might be to facilitate the identification of code that needs modification in a maintenance task. Such a system would require a search engine that could make use of relevance models, for example. However, other tasks may benefit from the work in machine translation or summarization. Many of the projects that have incorporated information retrieval in software engineering tasks have made use of LSI, Latent Semantic Indexing. This is a technique used in the vector space model approach to information retrieval, which collapses the dimensionality of the vector based on topics. LSI was developed in 1990. In 1999 pLSI was introduc...

Studies on drug design datasets are continuing to grow. These datasets are usually known as hard modeled, having a large number of features and a small number of samples. The most common problems in the drug design area are of regression type. Committee machines (ensembles) have become popular in machine learning because of their high performance. In this study, dynamics of ensembles on regression related drug design problems are investigated on a big dataset collection. The study tries to determine the most successful ensemble algorithm, the base algorithm-ensemble pair having the best / worst results, the best successful single algorithm, and the similarities of algorithms according to their performances. We also discuss whether ensembles always generate better results than single algorithms.

Classification of nonlinearly separable data by nonlinear support vector machines is often a difficult task especially due to the necessity of a choosing a convenient kernel type. In this study, we propose a new classification method called support vector selection and adaptation (SVSA) that is applicable to both linearly and nonlinearly separable data in terms of some reference vectors generated by processing of support vectors obtained from the linear SVM. The method consists of two steps called selection and adaptation. In these two steps, once the support vectors are obtained by a linear SVM, some of them are rejected and others are selected and adapted to become the reference vectors. Classification is next carried out by using the K Nearest Neighbor Method (KNN) with the reference vectors. In the first step, all support vectors are classified by KNN with respect to the training data excluding the support vectors. The misclassified support vectors are rejected, and the remainin...

Sketch as an image search query is an ideal alternative to text in capturing the fine-grained visual details. Prior successes on fine-grained sketch-based image retrieval (FG-SBIR) have demonstrated the importance of tackling the unique traits of sketches as opposed to photos, e.g., temporal vs. static, strokes vs. pixels, and abstract vs. pixel-perfect. In this paper, we study a further trait of sketches that has been overlooked to date, that is, they are hierarchical in terms of the levels of detail -- a person typically sketches up to various extents of detail to depict an object. This hierarchical structure is often visually distinct. In this paper, we design a novel network that is capable of cultivating sketch-specific hierarchies and exploiting them to match sketch with photo at corresponding hierarchical levels. In particular, features from a sketch and a photo are enriched using cross-modal co-attention, coupled with hierarchical node fusion at every level to form a better ...

Sketch-based image retrieval (SBIR) is a cross-modal matching problem which is typically solved by learning a joint embedding space where the semantic content shared between photo and sketch modalities are preserved. However, a fundamental challenge in SBIR has been largely ignored so far, that is, sketches are drawn by humans and considerable style variations exist amongst different users. An effective SBIR model needs to explicitly account for this style diversity, crucially, to generalise to unseen user styles. To this end, a novel style-agnostic SBIR model is proposed. Different from existing models, a cross-modal variational autoencoder (VAE) is employed to explicitly disentangle each sketch into a semantic content part shared with the corresponding photo, and a style part unique to the sketcher. Importantly, to make our model dynamically adaptable to any unseen user styles, we propose to metatrain our cross-modal VAE by adding two style-adaptive components: a set of feature tr...

In the ‘Museo Archeologico Nazionale della Magna Grecia' in Reggio Calabria (south Italy) are located two full-size bronzes cast around the 5th century BC: The Riace Bronzes; thanks to their outstanding manufacture, they truly represent significant sculptural masterpieces of Greek art in the world. This paper describes the methodology used by the Geomatics Laboratory of the DICEAM of the Mediterranean University of Reggio Calabria to achieve a 3D model of the two sculptures. The 3D modelling is based on the use of imaging techniques, such as digital photogrammetry and computer vision. The achieved results demonstrate the effectiveness of the technique used in the cultural heritage field for the creation of a digital production and replication through 3d printing. Moreover considering that in the renewed interest in the context of international museological studies, Augmented Reality innovation represents a new method for amplifying visitor numbers into museums despite concerns o...

Este trabalho tem como objetivo avaliar o uso de tecnicas de aprendizado de maquina em um banco de dados de acidentes maritimos. Os algoritimos Naive Bayes, Bayes Net e Simple Logistic apresentaram os melhores resultados no desempenho. Os resultados evidenciam que os dados podem ser modelados por diferentes tipos de algoritmos de um modo muito satisfatorio.

Heart is the most important part in all living organisms. Cardiovascular diseases or heart related diseases are at its peak in today’s world. Cardiovascular diseases prediction in a living being is a critical challenge analysis in the medical field. Machine learning algorithms are used in effective decision making, perfection and correctness because of little fatigue problem. In this work a survey has been done among various machine learning algorithms such as SVM, Decision Tree, K-Nearest Neighbor (KNN), Artificial Neural Networks (ANN) and Random Forest with linear model to predict out of this heart disease. In performance level 92% is achieved through Support Vector Machine prediction model for heart diseases. Support Vector Machine method aims at finding large amount of feature by applying machine learning algorithm to improve the accuracy in the prediction of cardiovascular diseases.

With the increasing number of cameras available in the cities, video traffic analysis can provide useful insights for the transportation segment. One of such analysis is the Automatic License Plate Recognition (ALPR). Previous approaches divided this task into several cascaded subtasks, i.e., vehicle location, license plate detection, character segmentation and optical character recognition. However, since each task has its own accuracy, the error propagation between each subtask is detrimental to the final accuracy. Therefore, focusing on the reduction of error propagation, we propose a technique that is able to perform ALPR using only two deep networks, the first performs license plate detection (LPD) and the second performs license plate recognition (LPR). The latter does not execute explicit character segmentation, which reduces significantly the error propagation. As these deep networks need a large number of samples to converge, we develop new data augmentation techniques that...

The diagnosis of mental disorders is in most cases very difficult because of the high heterogeneity and overlap between associated cognitive impairments. Furthermore, early and individualized diagnosis is crucial. In this paper, we propose a methodology to support the individualized characterization and diagnosis of cognitive impairments. The methodology can also be used as a test platform for existing theories on the causes of the impairments. We use computational cognitive modeling to gather information on the cognitive mechanisms underlying normal and impaired behavior. We then use this information to feed machine-learning algorithms to individually characterize the impairment and to differentiate between normal and impaired behavior. We apply the methodology to the particular case of specific language impairment (SLI) in Spanish-speaking children. The proposed methodology begins by defining a task in which normal and individuals with impairment present behavioral differences. Ne...