Mapping and navigation for mobile robots, human-robot interaction, cognitive systems, and systems integration .

IEEE transactions on systems, man and cybernetics

Bioinformatics research is regarded as an area which encompasses voluminous, expanding and complex datasets. Nowadays, with the use of high-throughput next-generation sequencing technologies, there is significant expansion of biological big data, which presents storage and processing challenges. Performing data analytics to harvest the wealth of data from biological and biomedical data, such as genetic mapping on the DNA sequence, will only help to advance our understanding of the human condition, health and disease; which will consequently allow curing diseases and improving human health and lives by supporting the development of precision methods for healthcare. In this chapter, big data analytics with regards to the Hadoop big data framework for storing and processing big data is described in the context of bioinformatics. Moreover, machine learning is an important approach for performing predictive and prescriptive analytics. Thus, machine learning and deep learning approaches currently being used in the context of big data analytics in the Hadoop framework are also presented, as well as the current uses of such techniques and tools in bioinformatics.

Big Data Analytics and Deep Learning in Bioinformatics With Hadoop

Being able to check whether an IC is functional or not after the manufacturing process is very difficult. Particularly for analog and Radio Frequency (RF) circuits, test equipment and procedures required have a major impact on the circuits cost. An interesting approach to reduce the impact of the test cost is to measure parameters requiring low cost test resources and correlate these measurements, called indirect measurements, with the targeted specifications. This is known as indirect test technique because there is no direct measurement for these specifications, which requires so expensive test equipment and an important testing time, but these specifications are estimated w.r.t "low-cost measurements". While this approach seems attractive, it is only viable if we are able to establish a sufficient accuracy for the performance estimation and if this estimation remains stable and independent from the circuits sets under test.The main goal of this thesis is to implement a robust and effective indirect test strategy for a given application and to improve test decisions based on data analysis.To be able to build this strategy, we have brought various contributions. Initially, we have defined new metric developed in this thesis to assess the reliability of the estimated performances. Secondly, we have analyzed and defined a strategy for the construction of an optimal model. This latter includes a data preprocessing followed by a comparative analysis of different methods of indirect measurement selection. Then, we have proposed a strategy for a confidant exploration of the indirect measurement space in order to build several best models that can be used later to solve trust and optimization issues. Comparative studies were performed on 2 experimental data sets by using both of the conventional and the developed metrics to evaluate the robustness of each solution in an objective way.Finally, we have developed a comprehensive strategy based on an efficient implementation of the redundancy techniques w.r.t to the build models. This strategy has greatly improved the robustness and the effectiveness of the decision plan based on the obtained measurements. This strategy is adaptable to any context in terms of compromise between the test cost, the confidence level and the expected precision.

Confident alternate test implementation

With development of recent open source software in HPC, such as Hadoop project, bioinformatics applications with large scale biological data can be solved more efficiently. The emerging machine learning algorithms are widely adapted for analysis, recognition and prediction. This paper will survey recent literatures about open source software of machine learning and HPC for bioinformatics applications. The commonly used machine learning algorithms for bioinformatics applications will be summarized here, and the situations of HPC adaption are also provided. Finally, the issues of future usages of machine learning for bioinformatics applications will be included.

An Overview of Machine Learning and HPC in Open Sources for Bioinformatics

Routine inspections are conducted at various food establishments that yield large data sets, which capture attributes useful for data mining algorithms to predict critical violations. Critical violations related to food establishments cause serious public health problems, which may happen as result of unhygienic environment, leading to food contamination. This study presents predictive models to detect critical violations in food establishments by employing Logistic Regression (LR), Support Vector Machine (SVM) and K-Nearest Neighbour (KNN). A database from the City of Chicago data portal that contained food inspections from 2011 to 2014 was used. In the preliminary analysis, Principal Component Analysis was utilised and ten (10) relatively relevant variables, that are independent of each other, were selected from twenty-eight (28) to be used as inputs in the models. In the family of the SVM, several kernels were used and the optimal model selected was based on the performance measures Receiver Operating Characteristic (ROC), sensitivity and specificity. The optimal model of the KNN was also selected based on the same performance measures. The out of sample classification accuracies for the LR, SVM and KNN classifiers were 92.7872%, 92.7873% and 92.6650% respectively. The performances of the models showed no large marginal differences in classification accuracies; however, the SVM model appears to provide a better discrimination ability as compared to the LR and KNN. iv University of Ghana http://ugspace.ug.edu.gh

Predictive Models for Identifying Critical Units for Inspection in a Regulatory Body

Machine learning is the adaptive process that makes computers improve from experience, by example, and by analogy. So It is a discipline of methodologies that provides, in one form or another, intelligent information processing capabilities for handling real life. Bioinformatics is one of the application of Machine Learning. Bioinformatics is the interdisciplinary science of interpreting biological data using information technology and computer science. Machine learning (ML) focuses on automatic learning from data set. Machine learning includes the learning speed, the guarantee of convergence, and how the data can be learned incrementally. We usually refer to methods like Artificial Neural Networks (ANNs), Genetic algorithms (GAs), and Fuzzy systems along with hybrid methods including a combination of some of these methods. One of the major problems is to classify the normal genes and the invalid genes which are infected by some kind of diseases. In genomic research, classifying DNA sequences into existing categories is used to learn the functions of a new protein. So, it is important to identify those genes and classify them. In order to identify the infected genes and the normal genes with the use of classification methods here we use the machine learning techniques. This paper gives a review on the mechanisms of gene sequence classification using Machine Learning techniques, which includes a brief detail on bioinformatics, literature survey and key issues in DNA Sequencing using Machine Learning.

Pooja Dixit

Papers

Machine Learning in Bioinformatics: A Novel Approach for DNA Sequencing