A Systematic Literature Review on Distributed Machine Learning in Edge Computing.

Distributed edge intelligence is a disruptive research area that enables the execution of machine learning and deep learning (ML/DL) algorithms close to where data are generated. Since edge devices are more limited and heterogeneous than typical cloud devices, many hindrances have to be overcome to fully extract the potential benefits of such an approach (such as data-in-motion analytics). In this paper, we investigate the challenges of running ML/DL on edge devices in a distributed way, paying special attention to how techniques are adapted or designed to execute on these restricted devices. The techniques under discussion pervade the processes of caching, training, inference, and offloading on edge devices. We also explore the benefits and drawbacks of these strategies.

Factor and Rasch analysis of the Fonseca anamnestic index for the diagnosis of myogenous temporomandibular disorder.

BACKGROUND: Rasch analysis has been used in recent studies to test the psychometric properties of a questionnaire. The conditions for use of the Rasch model are one-dimensionality (assessed via prior factor analysis) and local independence (the probability of getting a particular item right or wrong should not be conditioned upon success or failure in another). OBJECTIVE: To evaluate the dimensionality and the psychometric properties of the Fonseca anamnestic index (FAI), such as the fit of the data to the model, the degree of difficulty of the items, and the ability to respond in patients with myogenous temporomandibular disorder (TMD). METHODS: The sample consisted of 94 women with myogenous TMD, diagnosed by the Research Diagnostic Criteria for Temporomandibular Disorders (RDC/TMD), who answered the FAI. For the factor analysis, we applied the Kaiser-Meyer-Olkin test, Bartlett's sphericity, Spearman's correlation, and the determinant of the correlation matrix. For extraction of the factors/dimensions, an eigenvalue >1.0 was used, followed by oblique oblimin rotation. The Rasch analysis was conducted on the dimension that showed the highest proportion of variance explained. RESULTS: Adequate sample "n" and FAI multidimensionality were observed. Dimension 1 (primary) consisted of items 1, 2, 3, 6, and 7. All items of dimension 1 showed adequate fit to the model, being observed according to the degree of difficulty (from most difficult to easiest), respectively, items 2, 1, 3, 6, and 7. CONCLUSION: The FAI presented multidimensionality with its main dimension consisting of five reliable items with adequate fit to the composition of its structure.

Exploring the genome of Trypanosoma vivax through GSS and in silico comparative analysis.

A survey of the Trypanosoma vivax genome was carried out by the genome sequence survey (GSS) approach resulting in 1,086 genomic sequences. A total of 455 high-quality GSS sequences were generated, consisting of 331 non-redundant sequences distributed in 264 singlets and 67 clusters in a total of 135.5 Kb of the T. vivax genome. The estimation of the overall G+C content, and the prediction of the presence of ORFs and putative genes were carried out using the Glimmer and Jemboss packages. Analysis of the obtained sequences was carried out by BLAST programs against 12 different databases and also using the Conserved Domain Database, InterProScan, and tRNAscan-SE. Along with the existing 23 T. vivax entries in the GenBank, the 32 putative genes predicted and the 331 non-redundant GSS sequences reported herein represent new potential markers for the development of PCRbased assays for specific diagnosis and typing of Trypanosoma vivax.

GARSA: genomic analysis resources for sequence annotation.

SUMMARY: Growth of genome data and analysis possibilities have brought new levels of difficulty for scientists to understand, integrate and deal with all this ever-increasing information. In this scenario, GARSA has been conceived aiming to facilitate the tasks of integrating, analyzing and presenting genomic information from several bioinformatics tools and genomic databases, in a flexible way. GARSA is a user-friendly web-based system designed to analyze genomic data in the context of a pipeline. EST and GGS data can be analyzed using the system since it accepts (1) chromatograms, (2) download of sequences from GenBank, (3) Fasta files stored locally or (4) a combination of all three. Quality evaluation of chromatograms, vector removing and clusterization are easily performed as part of the pipeline. A number of local and customizable Blast and CDD analyses can be performed as well as Interpro, complemented with phylogeny analyses. GARSA is being used for the analyses of Trypanosoma vivax (GSS and EST), Trypanosoma rangeli (GSS, EST and ORESTES), Bothrops jararaca (EST), Piaractus mesopotamicus (EST) and Lutzomyia longipalpis (EST). AVAILABILITY: The GARSA system is freely available under GPL license (http://www.biowebdb.org/garsa/). For download requests visit http://www.biowebdb.org/garsa/ or contact Dr Alberto Dávila.