Swaminathan Ramakrishnan

Bio: Swaminathan Ramakrishnan is an academic researcher from Madras Institute of Technology. The author has contributed to research in topics: Spirometer & Ultimate tensile strength. The author has an hindex of 8, co-authored 15 publications receiving 158 citations. Previous affiliations of Swaminathan Ramakrishnan include Anna University.

Comparison of Two ANN Methods for Classification of Spirometer Data

Abstract: In this work, classification of spirometric pulmonary function test data performed using two artificial neural network methods is compared and reported. The pulmonary function data (N=150) were obtained from volunteers, using commercially available Spirometer, and recorded by standard data acquisition protocol. The data were then used to train (N=100) as well as to test (N=50) the neural networks. The classification was carried out using back propagation and radial basis function neural networks. The results confirm that the artificial neural network methods are useful for the classification of spirometric pulmonary function data. Further, it appears that the Radial basis function neural network is more sensitive when compared to back propagation neural networks. In this paper, the methodology, data collection procedure and neural network based analysis are described in details.

Detection of Obstructive Respiratory Abnormality Using Flow---Volume Spirometry and Radial Basis Function Neural Networks

Abstract: In this work detection of pulmonary abnormalities carried out using flow-volume spirometer and Radial Basis Function Neural Network (RBFNN) is presented. The spirometric data were obtained from adult volunteers (N?=?100) with standard recording protocol. The pressure and resistance parameters were derived using the theoretical approximation of the activation function representing pressure---volume relationship of the lung. The pressure---time and resistance---expiration volume curves were obtained during maximum expiration. The derived values together with spirometric data were used for classification of normal and obstructive abnormality using RBFNN. The results revealed that the proposed method is useful for detecting the pulmonary functions into normal and obstructive conditions. RBFNN was found to be effective in differentiating the pulmonary data and it was confirmed by measuring accuracy, sensitivity, specificity and adjusted accuracy. As spirometry still remains central in the observations of pulmonary function abnormalities these studies seems to be clinically relevant.

An Approach to Identify Optic Disc in Human Retinal Images Using Ant Colony Optimization Method

Abstract: In this work, an attempt has been made to identify optic disc in retinal images using digital image processing and optimization based edge detection algorithm. The edge detection was carried out using Ant Colony Optimization (ACO) technique with and without pre-processing and was correlated with morphological operations based method. The performance of the pre-processed ACO algorithm was analysed based on visual quality, computation time and its ability to preserve useful edges. The results demonstrate that the ACO method with pre-processing provides high visual quality output with better optic disc identification. Computation time taken for the process was also found to be less. This method preserves nearly 50% more edge pixel distribution when compared to morphological operations based method. In addition to improve optic disc identification, the proposed algorithm also distinctly differentiates between blood vessels and macula in the image. These studies appear to be clinically relevant because automated analyses of retinal images are important for ophthalmological interventions.

Assessment and classification of mechanical strength components of human femur trabecular bone using digital image processing and neural networks

Abstract: In this work, the assessment of the mechanical strength of human femur trabecular bone and its classification into normal or abnormal are carried out using digital image processing and neural networks. The mechanical strength components of femur trabeculae, such as primary compressive (PC), primary tensile (PT), secondary tensile (ST), and Ward's triangle (WT), are delineated by the semiautomatic image processing procedure from the planar radiographic images (N = 90) of subjects that are acquired under controlled clinical settings. Parameters such as apparent mineralization and total area of the individual mechanical strength components are calculated for normal and abnormal samples. The data are trained with neural networks and validated. The classifications are carried out using feed-forward neural networks trained with the standard backpropagation algorithm. The abnormal and normal outputs are validated by sensitivity and specificity measurements. The observation shows that the investigation of bone mechanical strength at the various strength components is useful in classifying normal and abnormal human femur trabeculae from conventional radiographs. Furthermore, the results confirm the effectiveness of the neural network–based classification of femur trabeculae into normal and abnormal conditions. The sensitivity and specificity are found to be 100% and 80%, respectively. In this paper, the methodology, data collection procedures, and neural network–based analysis and results are discussed in detail.

Prediction of Spirometric Forced Expiratory Volume (FEV1) Data Using Support Vector Regression

Abstract: In this work, prediction of forced expiratory volume in 1 second (FEV1) in pulmonary function test is carried out using the spirometer and support vector regression analysis. Pulmonary function data are measured with flow volume spirometer from volunteers (N=175) using a standard data acquisition protocol. The acquired data are then used to predict FEV1. Support vector machines with polynomial kernel function with four different orders were employed to predict the values of FEV1. The performance is evaluated by computing the average prediction accuracy for normal and abnormal cases. Results show that support vector machines are capable of predicting FEV1 in both normal and abnormal cases and the average prediction accuracy for normal subjects was higher than that of abnormal subjects. Accuracy in prediction was found to be high for a regularization constant of C=10. Since FEV1 is the most significant parameter in the analysis of spirometric data, it appears that this method of assessment is useful in diagnosing the pulmonary abnormalities with incomplete data and data with poor recording.

Classifying Affective States Using Thermal Infrared Imaging of the Human Face

Abstract: In this paper, time, frequency, and time-frequency features derived from thermal infrared data are used to discriminate between self-reported affective states of an individual in response to visual stimuli drawn from the International Affective Pictures System. A total of six binary classification tasks were examined to distinguish baseline and affect states. Affect states were determined from subject-reported levels of arousal and valence. Mean adjusted accuracies of 70% to 80% were achieved for the baseline classifications tasks. Classification accuracies between high and low ratings of arousal and valence were between 50% and 60%, respectively. Our analysis showed that facial thermal infrared imaging data of baseline and other affective states may be separable. The results of this study suggest that classification of facial thermal infrared imaging data coupled with affect models can be used to provide information about an individual's affective state for potential use as a passive communication pathway.

Changes in erythrocyte aggregation and deformability in diabetes mellitus: a brief review.

Abstract: Diabetes mellitus (DM) is a metabolic disorder characterized by varying or persistent hyperglycemia either due to insufficient production of insulin by pancreas or improper utilization of the glucose. Erythrocytes remain in hyperglycemic environment throughout their life span and thus are subjected to series of compositional changes, which in turn affect their flow properties through alteration of deformation at individual level and aggregation at collective level. This brief review summarizes the changes in biochemical parameters primarily contributing to the erythrocyte deformability and aggregation as measured by various techniques, of blood samples obtained from diabetic subjects. The significant changes in erythrocyte aggregation and deformability, in comparison with that of control subjects show the relevance of these measurements. These changes are further supported by in vivo observations of blood flow through microvessels. Finally the relevance of these in combination with other clinical parameters is suggested.

Erythrocyte deformability and its variation in diabetes mellitus.

Abstract: Erythrocyte deformability improves blood flow in the microvessels and in large arteries at high shear rate. The major determinants of RBC deformability include cell geometry, cell shape and internal viscosity (i.e., mean cell hemoglobin concentration and components of the erythrocyte membrane). The deformability is measured by several techniques but filtration of erythrocytes through micro-pore membranes and ektacytometry are two sensitive techniques to detect changes in erythrocytes under varied experimental and diseased conditions. Diabetes mellitus (DM) is a metabolic disorder, characterized by varying or persistent hyperglycemia, which induces several changes in the erythrocyte membrane and its cytoplasm, leading to alteration in the deformability. A decreasing trend of deformability in these patients is observed. The shape descriptor form factor, as determined by processing of erythrocyte images, increases with the increase of blood glucose levels and shows a pattern similar to filtration time of erythrocyte suspensions through cellulose membranes. Fluidity of the membrane as measured in erythrocytes of these patients is decreased. With prolonged diabetic conditions the deformability of erythrocytes is further decreased, which may complicate the flow of these cells in microvessels.

Automatic detection of a prefrontal cortical response to emotionally rated music using multi-channel near-infrared spectroscopy.

Abstract: Emotional responses can be induced by external sensory stimuli. For severely disabled nonverbal individuals who have no means of communication, the decoding of emotion may offer insight into an individual's state of mind and his/her response to events taking place in the surrounding environment. Near-infrared spectroscopy (NIRS) provides an opportunity for bed-side monitoring of emotions via measurement of hemodynamic activity in the prefrontal cortex, a brain region known to be involved in emotion processing. In this paper, prefrontal cortex activity of ten able-bodied participants was monitored using NIRS as they listened to 78 music excerpts with different emotional content and a control acoustic stimuli consisting of the Brown noise. The participants rated their emotional state after listening to each excerpt along the dimensions of valence (positive versus negative) and arousal (intense versus neutral). These ratings were used to label the NIRS trial data. Using a linear discriminant analysis-based classifier and a two-dimensional time-domain feature set, trials with positive and negative emotions were discriminated with an average accuracy of 71.94% ± 8.19%. Trials with audible Brown noise representing a neutral response were differentiated from high arousal trials with an average accuracy of 71.93% ± 9.09% using a two-dimensional feature set. In nine out of the ten participants, response to the neutral Brown noise was differentiated from high arousal trials with accuracies exceeding chance level, and positive versus negative emotional differentiation accuracies exceeded the chance level in seven out of the ten participants. These results illustrate that NIRS recordings of the prefrontal cortex during presentation of music with emotional content can be automatically decoded in terms of both valence and arousal encouraging future investigation of NIRS-based emotion detection in individuals with severe disabilities.