A Web-Based Micro-service Architecture for Comparing Parallel Implementations of Dissimilarity Measures Daniel-Stiven Valencia-Hern´ andez , Ana-Lorena Uribe-Hurtado (B ) , and Mauricio Orozco-Alzate Facultad de Administraci´on, Departamento de Inform´atica y Computaci´on, Grupo de Ambientes Inteligentes Adaptativos - GAIA, Universidad Nacional de Colombia - Sede Manizales, km 7 v´ ıa al Magdalena, Manizales 170003, Colombia {dsvalenciah,alhurtadou,morozcoa}@unal.edu.co Abstract. The performance of an application can be significantly improved by using parallelization, as well as by defining micro-services which allow the distribution of the work into several independent tasks. In this paper, we show how a micro-service architecture can be used for developing an efficient and flexible application for the nearest neighbor classification problem. Several dissimilarity measures are compared, in terms of both accuracy and computational time, for sequential as well parallel executions. In addition, a web-based interface was developed in order to facilitate the interaction with the user and easily monitoring the progress of the experiments. Keywords: Micro-services · Dissimilarity measures Multi-core implementation 1 Introduction Classifying objects in a fast, efficient and automatic way is a very important issue in applications such as industry and medicine [7]. Examples in those areas include, in the industrial case, discarding or accepting manufactured objects in a production chain or identifying diseases in the case of health care. The auto- matic classification is typically performed by using an algorithm —the so-called classifier— which is designed according to the information from a collection of samples equipped with class labels. Once deployed, the classifier assigns labels to new incoming and unlabeled samples which are typically represented as images or other digital signals derived from them, e.g. histograms or spectra. Among all the available classification algorithms, the k nearest neighbor rule (kNN) is a A.-L. Uribe-Hurtado—Estudiante del Doctorado en Ingenier´ ıa, Industria y Organi- zaciones - Universidad Nacional de Colombia - Sede Manizales. c  Springer International Publishing AG, part of Springer Nature 2019 F. De La Prieta et al. (Eds.): DCAI 2018, AISC 800, pp. 164–171, 2019. https://doi.org/10.1007/978-3-319-94649-8_20