Search results for "machine learning."

2021

Strength training exercises are essential for rehabilitation, improving our health as well as in sports. For optimal and safe training, educators and trainers in the industry should comprehend exercise form or technique. Currently, there is a lack of tools measuring in-depth skills of strength training experts. In this study, we investigate how data mining methods can be used to identify novel and useful skill patterns from a binary multiple choice questionnaire test designed to measure the knowledge level of strength training experts. A skill test assessing exercise technique expertise and comprehension was answered by 507 fitness professionals with varying backgrounds. A triangulated appr…

Metrics in method engineering

1995

So many software development methods have been introduced in the last decade, that one can talk about a “methodology jungle”. To aid the method developers and evaluators in fighting their way through this jungle we propose a systematic approach for measuring properties of methods. We describe two sets of metrics, which measure the complexity of diagrammatic specification techniques on the one hand, and of complete systems development methods on the other hand. Proposed metrics provide a relatively fast and simple way to analyse the technique (or method) properties, and when accompanied with other selection criteria, can be used for estimating the cost of learning the technique and the relat…

A Windowing strategy for Distributed Data Mining optimized through GPUs

2017

Abstract This paper introduces an optimized Windowing based strategy for inducing decision trees in Distributed Data Mining scenarios. Windowing consists in selecting a sample of the available training examples (the window) to induce a decision tree with an usual algorithm, e.g., J48; finding instances not covered by this tree (counter examples) in the remaining training examples, adding them to the window to induce a new tree; and repeating until a termination criterion is met. In this way, the number of training examples required to induce the tree is reduced considerably, while maintaining the expected accuracy levels; which is paid in terms of time performance. Our proposed enhancements…

Using interactive evolutionary algorithms to help fit cochlear implants

2010

A Novel Angle Estimation for mmWave FMCW Radars Using Machine Learning

2021

In this article, we present a novel machine learning based angle estimation and field of view (FoV) enhancement techniques for mmWave FMCW radars operating in the frequency range of 77 - 81 GHz. Field of view is enhanced in both azimuth and elevation. The Elevation FoV enhancement is achieved by keeping the orientation of antenna elements in elevation. In this orientation, radar focuses the beam in vertical direction there by enhancing the elevation FoV. An Azimuth FoV enhancement is achieved by mechanically rotating the radar horizontally, which has antenna elements in the elevation. With the proposed angle estimation technique for such rotating radars, root mean square error (RMSE) of 2.5…

Intelligent system for material quality control using impact-echo testing

2008

This paper introduces an intelligent system to discern the quality of materials inspected by the impact-echo technique. The system includes a hardware setup to inspect parallelepiped-shape materials and a procedure to classify the material depending on its quality condition. Four levels of classification with different grades of knowledge about the material defects are approached: material condition, kind of defect, defect orientation, and defect dimension. The number of classes (material qualities) in the lowest classification level is 12. The procedure is applied on signals coming from 3D finite element simulations and lab experiments with aluminium specimens. The classification procedure…

Image Recognition through Incremental Discriminative Common Vectors

2010

An incremental approach to the discriminative common vector (DCV) method for image recognition is presented. Two different but equivalent ways of computing both common vectors and corresponding subspace projections have been considered in the particular context in which new training data becomes available and learned subspaces may need continuous updating. The two algorithms are based on either scatter matrix eigendecomposition or difference subspace orthonormalization as with the original DCV method. The proposed incremental methods keep the same good properties than the original one but with a dramatic decrease in computational burden when used in this kind of dynamic scenario. Extensive …

Context-Awareness in Ensemble Recommender System Framework

2021

Recommender systems that provide recommendations based uniquely on information over users and items may not be very accurate in some situations. Therefore, adding contextual information to recommendations may be a good choice resulting in a system with increased precision. In an early work, we proposed an Ensemble Variational Autoencoders (EnsVAE) framework for recommendation. EnsVAE is adjusted to output interest probabilities by learning the distribution of each item's ratings and attempts to provide diverse novel items that are pertinent to users. In this paper, we propose and investigate a context awareness framework based on the Ensemblist Variational Autoencoders model with integratin…

Mining Interpretable Rules for Sentiment and Semantic Relation Analysis Using Tsetlin Machines

2020

Tsetlin Machines (TMs) are an interpretable pattern recognition approach that captures patterns with high discriminative power from data. Patterns are represented as conjunctive clauses in propositional logic, produced using bandit-learning in the form of Tsetlin Automata. In this work, we propose a TM-based approach to two common Natural Language Processing (NLP) tasks, viz. Sentiment Analysis and Semantic Relation Categorization. By performing frequent itemset mining on the patterns produced, we show that they follow existing expert-verified rule-sets or lexicons. Further, our comparison with other widely used machine learning techniques indicates that the TM approach helps maintain inter…

Clustering categorical data: A stability analysis framework

2011

Clustering to identify inherent structure is an important first step in data exploration. The k-means algorithm is a popular choice, but K-means is not generally appropriate for categorical data. A specific extension of k-means for categorical data is the k-modes algorithm. Both of these partition clustering methods are sensitive to the initialization of prototypes, which creates the difficulty of selecting the best solution for a given problem. In addition, selecting the number of clusters can be an issue. Further, the k-modes method is especially prone to instability when presented with ‘noisy’ data, since the calculation of the mode lacks the smoothing effect inherent in the calculation …