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.

Multi-class support vector machine for quality estimation of black tea using electronic nose

Abstract: Electronic nose (e-nose) is a machine olfaction system that has shown significant possibilities as an improved alternative of human taster as olfactory perceptions vary from person to person. In contrast, electronic noses also detect smells with their sensors, but in addition describe those using electronic signals. An efficient e-nose system should analyze and recognize these electronic signals accurately. For this it requires a robust pattern classifier that can perform well on unseen data. This research work shows the efficient prediction of black tea quality using machine learning algorithm with e-nose. This paper investigates the potential of three different types of multi-class support vector machine (SVM) to build taster-specific computational models. Experimental results show that all the three models offer more than 97% accuracies to predict the considerable variation in tea quality.

A Novel Approach for Determination of Optimal Number of Cluster

Abstract: Image clustering and categorization is a means for high-level description of image content. In the field of content-based image retrieval (CBIR), the analysis of gray scale images has got very much importance because of its immense application starting from satellite images to medical images. But the analysis of an image with such number of gray shades becomes very complex, so, for simplicity we cluster the image into a lesser number of gray levels. Using K-Means clustering algorithm we can cluster an image to obtain segments. The main disadvantage of the k-means algorithm is that the number of clusters, K, must be supplied as a parameter. Again, this method does not specify the optimal cluster number. In this paper, we have provided a mathematical approach to determine the optimal cluster number of a clustered grayscale images. A simple index, based on the intra-cluster and inter-cluster distance measures has been proposed in this paper, which allows the number of clusters to be determined automatically.

Study and Classification of Cell Bio-Impedance Signature for Identification of Malignancy Using Artificial Neural Network

Abstract: This article presents development of a microcapacitive sensor-based bio-impedance classification system for identification of malignant cells in a known volume (400 $\mu \text{L}$ ) of biological tissue sample Malignancy induces various physical changes in an affected cell, among which increased intracellular water and sodium ion content are a couple of prominent ones In this work, the change in electrical properties of a cell [here white blood cell (WBC)] that is membrane and cytoplasm permittivity due to afore-mentioned reasons is used for distinguishing malignant from normal cells based on their deviation in bio-impedance signature This change in bio-impedance signature of the WBC is measured by exciting the mentioned microcapacitive sensor by a 2 V p-p signal The developed system consists of an on-board impedance analyzer to carry out bio-impedance spectroscopy over a frequency range of 1–100 kHz The bio-impedance data are then obtained from the sensor for different concentrations of cultured human malignant and normal white blood cells The difference in impedance values between concentrations is then used as a discerning factor for identification the degree of malignancy, for which an artificial neural network (ANN) is employed A detailed study considering detection efficiency for this ANN revealed classification accuracy up to 950%, upon which this ANN model is transferred to a portable single board computer (SBC) along with other associated circuitry that could carry out the same classification at a nominal power consumption of 51645 mW