Identification of Biomarkers for Arsenicosis Employing Multiple Kernel Learning Embedded Multiobjective Swarm Intelligence.

Arsenic is a carcinogen, and long-term exposure to it may result in the development of multi-organ disease. Understanding the underlying intricate molecular network of toxicity and carcinogenicity is crucial for identifying a small set of differentially expressed biomarker genes to predict the risk of the exposed population. In this paper, a multiple kernel learning (MKL) embedded multi-objective swarm intelligence technique has been proposed to identify the candidate biomarker genes from the transcriptomic profile of arsenicosis samples.

On-Device Reliability Assessment and Prediction of Missing Photoplethysmographic Data Using Deep Neural Networks.

Photoplethysmographic (PPG) measurements from ambulatory subjects may suffer from unreliability due to body movements and missing data segments due to loosening of sensor. This paper describes an on-device reliability assessment from PPG measurements using a stack denoising autoencoder (SDAE) and multilayer perceptron neural network (MLPNN). The missing segments were predicted by a personalized convolutional neural network (CNN) and long-short term memory (LSTM) model using a short history of the same channel data.

On-chip estimation of hematocrit level for diagnosing anemic conditions by Impedimetric techniques.

An on-chip device has been fabricated on Si platform for precise estimation of the hematocrit (Hct) level of human blood with rapid turn out. Impedance/capacitance spectroscopy and current-voltage (I-V) measurements have been employed to observe the variation of electrical parameters of erythrocyte suspensions with varying Hct level. Experimentally obtained values of capacitance, impedance and conductance with Hct level suggests a linear variation.

lBest-HS algorithm based concurrent L adaptive control for non-Linear systems.

This paper proposes a new approach for designing stable hybrid L adaptive controller employing lbest topological model of harmony search (HS) algorithm. The proposed design approach guarantees desired stability and simultaneously provides satisfactory tracking performance for a class of non-linear systems. The design methodology for the controller utilizes the meta-heuristic global search feature of HS algorithm and the local search phenomenon of L adaptive control strategy in tandem.