Heritage Institute of Technology

About: Heritage Institute of Technology is a based out in . It is known for research contribution in the topics: Support vector machine & Transconductance. The organization has 581 authors who have published 1045 publications receiving 8345 citations.

A Novel Equilibrium Optimization Technique for Band Selection of Hyperspectral Images

Abstract: Band selection of hyperspectral images is a rising research area. Because of the shortage of the labeled information set of hyperspectral imagery, it is additionally challenging task. Band selection problem can be seen as a two-way problem i.e. optimization of the number of chosen bands as well as optimization of the chosen bands itself. In this article, a novel strategy primarily based on Equilibrium Optimization (EO) is proposed. The Equilibrium Law of any object acts as the motivation in favour of this method. This technique suggests a persuasive result in assessment with other popular methods like MI (Mutual Information), WaLuDi (Wards linkage strategy using divergence), TMI (Trivariate MI), ACO (Ant Colony Optimization), and DE (Differential Evolution) for different datasets like Botswana, KSC, etc.

Identifying the degree of genetic interactions using Restricted Boltzmann Machine-A study on colorectal cancer.

Abstract: The phenomenon of two or more genes affecting the expression of each other in various ways in the development of a single character of an organism is known as gene interaction. Gene interaction not only applies to normal human traits but to the diseased samples as well. Thus, an analysis of gene interaction could help us to differentiate between the normal and the diseased samples or between the two/more phases any diseased samples. At the first stage of this work we have used restricted Boltzmann machine model to find such significant interactions present in normal and/or cancer samples of every gene pairs of 20 genes of colorectal cancer data set (GDS4382) along with the weight/degree of those interactions. Later on, we are looking for those interactions present in adenoma and/or carcinoma samples of the same 20 genes of colorectal cancer data set (GDS1777). The weight/degree of those interactions represents how strong/weak an interaction is. At the end we will create a gene regulatory network with the help of those interactions, where the regulatory genes are identified by using Naive Bayes Classifier. Experimental results are validated biologically by comparing the interactions with NCBI databases.

Monitoring of the lung fluid movement and estimation of lung area using Electrical Impedance Tomography: A Simulation Study

Abstract: Patients suffering from the acute respiratory distress syndrome (ARDS) requires thoracic electrical impedance tomography (EIT) for the monitoring their conditions ranging from dynamic shifting of body fluids to lung aeration right at the bedside. More objectively, EIT-derived numeric parameters would help the physician to evaluate the state of the lung. Thus, here we have performed a Finite Element Method based simulation study for monitoring the condition of lungs and heart of ARDS patients. Therefore, a finite element method (FEM)- model of a human thorax in 3 dimensional platform of FEM Multiphysics software is created and is tested with new ventilation indices regarding their ability to quantitatively describe structural changes in the lung due to the gravitationally dependent lung collapse. Additionally, analysis is made to find the electrode pairs capable of separating the lung and heart activity when a particular amount of constant current is injected through them are also carried out. Finally, a real time of the EIT system using 16 Ag-AgCl electrodes were developed for real time imaging of the human thorax. The data were collected using the adjacent current injection technique and are plotted using FEM Multiphysics software. The reconstructed FEM images using the forward solver of EIT shows the approximate area of the thorax (lungs, heart etc.) under observation.

Effect of Packing Density on Crosstalk in On-chip Optical Interconnects

Abstract: Optical interconnects hold the promise of revolutionizing computing speed having higher bandwidth and lower power consumption. For high packing density of optical interconnects, crosstalk is calculated considering the coupling of fields of two parallel identical neighboring waveguides. The study shows that there exists minimum pitch for a particular length and width of the interconnects to avoid significant amount of crosstalk. Again, an optimum ratio of width-to-pitch exists for which crosstalk is minimum.

Computer-Aided Drug Design Against Dopamine D2 Receptor for Antischizophrenia Drug Development

Abstract: Schizophrenia is a long term psychosis caused by dysregulation of dopamine D2R. Existing antipsychotic drugs that alleviate positive symptoms of schizophrenia exhibit varied side effects for which designing antipsychotic drugs with reduced side effects remains an important therapeutic goal. This research project has been designed to develop potential amino acid and small molecule-based lead compounds for the reduction of schizophrenic symptoms using in silico drug design tools and methods. Use of LIGDREAM resulted in generation of 100 analogues of Eticlopride. Those with better ADMET properties were subjected to molecular docking against D2R receptor using AutoDock Vina and iGEM dock which yielded two analogues that had more substantial binding affinities for D2R than Eticlopride. NCS-1 is a signalling protein that desensitizes Dopamine D2R. Hence, a protein-based therapeutic compound for schizophrenia was being developed by conserved mutations of two amino acid residues on NCS1 (Phe55 and Leu189) by more hydrophilic and hydrophobic substituent, respectively. Protein-protein docking using the CLUSPRO docking portal and subsequent energy analysis have shown that increased hydrophilicity one had enhanced stabilization. Results obtained from both the modified Eticlopride leads and NCS1 mutations indicate that they can be collectively taken further downstream in anti-schizophrenia drug development.