Machine Learning Based Metagenomic Prediction of Inflammatory Bowel Disease

In this study, we investigate faecal microbiota composition, in an attempt to evaluate performance of classification algorithms in identifying Inflammatory Bowel Disease (IBD) and its two types: Crohn’s disease (CD) and ulcerative colitis (UC). From many investigated algorithms, a random forest (RF) classifier was selected for detailed evaluation in three-class (CD versus UC versus nonIBD) classification task and two binary (nonIBD versus IBD and CD versus UC) classification tasks. We dealt with class imbalance, performed extensive parameter search, dimensionality reduction and two-level classification. In three-class classification, our best model reaches F1 score of 91% in average, which confirms the strong connection of IBD and gastrointestinal microbiome. Among most important features in three-class classification are species Staphylococcus hominis, Porphyromonas endodontalis, Slackia piriformis and genus Bacteroidetes.

Efficient spreading strategy for global solution search using a trust-region optimization method: an application to CRS stacking problem

Some processes in seismic imaging can be formulated as a coherence-based problem, such as common reflection surface (CRS) stacking.The approach consists of obtaining the CRS attributes that provide the best fitting CRS surface in the multi-coverage data. The problem can be described as an optimization problem and solved by an optimization algorithm. Generally, quick convergent optimization algorithms are local solvers. To obtain the global solution, an efficient strategy is proposed to be used combined with a trust-region local optimization method. This strategy can be divided into two features: sequential parameters search and spreading solution.The idea is to first find solutions on a coarse output grid by sequential parameter search. This feature is based on constructing splines to estimate the maxima of the objective function in one dimension. These estimated maxima are the initial approximations to the local solver.The optimization algorithm obtains the parameters by sequentially solving one, two, and three-dimensional problems. Once the solutions are found on the coarse grid, useful information is propagated in the neighborhood to obtain the solutions on all output grid. Although the idea of spreading solution seems easy, its implementation is complex. It is essential to consider the properties of the problem as well as the properties of the optimization algorithm. Through some numerical experiments, the results using this strategy are shown. The use of sequential parameter search and spreading solution provides an improvement not only in the parameters but also in computational time.

Consensus in networks of uncertain robot manipulators without using neighbors’ velocity information

In this paper, new distributed adaptive methods are proposed for solving both leaderless and leader–follower consensus problems in networks of uncertain robot manipulators, by estimating only the gravitational torque forces. Comparing with the existing adaptive methods, which require the estimation of the whole dynamics, presented methods reduce the excitation levels required for efficient parameter search, the convergence time, and the complexity of the regressor. Additionally, proposed schemes eliminate the need for velocity information exchange between the agents. Global asymptotic synchronization is shown by introducing new Lyapunov functions. Simulation results are provided for a network of 10 4-DOF robot manipulators.

A Module-Linking Graph Assisted Hybrid Optimization Framework for Custom Analog and Mixed-Signal Circuit Parameter Synthesis

Analog and mixed-signal (AMS) computer-aided design tools are of increasing interest owing to demand for the wide range of AMS circuit specifications in the modern system on a chip and faster time to market requirement. Traditionally, to accelerate the design process, the AMS system is decomposed into smaller components (called modules ) such that the complexity and evaluation of each module are more manageable. However, this decomposition poses an interface problem, where the module’s input-output states deviate from when combined to construct the AMS system, and thus degrades the system expected performance. In this article, we develop a tool module-linking-graph assisted hybrid parameter search engine with neural networks (MOHSENN) to overcome these obstacles. We propose a module-linking-graph that enforces equality of the modules’ interfaces during the parameter search process and apply surrogate modeling of the AMS circuit via neural networks. Further, we propose a hybrid search consisting of a global optimization with fast neural network models and a local optimization with accurate SPICE models to expedite the parameter search process while maintaining the accuracy. To validate the effectiveness of the proposed approach, we apply MOHSENN to design a successive approximation register analog-to-digital converter in 65-nm CMOS technology. This demonstrated that the search time improves by a factor of 5 and 700 compared to conventional hierarchical and flat design approaches, respectively, with improved performance.