S. Kalaivani

Bio: S. Kalaivani is an academic researcher from VIT University. The author has contributed to research in topics: Fault (power engineering) & Polygon. The author has an hindex of 3, co-authored 10 publications receiving 24 citations. Previous affiliations of S. Kalaivani include Indian Institutes of Technology & Thiagarajar College of Engineering.

Respiratory Sound Analysis for Detection of Pulmonary Diseases

Abstract: Large number of people die every year of Pulmonary chronic lung diseases irrespective of their age. Lung sound analysis has been a key diagnostic aid to accurately detect Pulmonary Diseases. Earlier, manual detection was used which was not a dependable method to detect lung diseases due to various reasons like low audibility and difference in perceptions of different physicians for different sounds. Modern computerized analysis yield results with much higher accuracy and thus a better treatment can be given to patients suffering from various kinds of lung diseases. These disorders include Asthma, Bronchitis, Emphysema, Tuberculosis and Pneumonia. Some of the symptoms are wheezing, shortness of breath, rhonchi and chronic cough. In general, the analysis is carried out in two stages- Separation of Heart Sound (HS) from the Lung Sound (LS) and the characterization of waveform of the filtered LS. In this paper, we propose a very simple yet effective method for the second stage analysis- characterization of waveform of the filtered LS for some of the male and female age groups. We have taken the filtered Lung sounds from different online repositories and performed Welch method. This method helps to obtain power spectrum plot of a particular LS. Different diseases have peaks in different frequency ranges of the power spectrum plot. This helps in identification of a particular disease.

A heuristic method for initial dominant point detection for polygonal approximations

Abstract: This paper presents a novel initial dominant point detection technique for polygonal approximation in digital planar curves. This technique concentrates on the local and global deviation of the curve and detects the dominant point of the polygon. An iterative split and merge strategy is used effectively to insert and/or delete vertex during the approximation of the polygon. Since the internal steps are automated, a symmetric and better approximation is achieved. The technique is robust to rotation and noise of the shape and produces better results compared to the results obtained by recent work. The performance of the proposed system is evaluated using the benchmark data set and the same is compared in terms of the quantitative and qualitative measures. The experimental results show that proposed technique has outperformed an existing similar method with respect to visual perception and numeric metrics.

Laplacian pyramid-based change detection in multitemporal SAR images

Abstract: The Synthetic Aperture Radar (SAR) has many attractive and desired features to cope with uncertain weather conditions and also provides superlative resolution in images In this paper, a un

Spray coated aluminum oxide thin film for P-type crystalline silicon surface passivation

Abstract: Aluminum oxide (Al2O3) thin films deposited by spray coating process is evaluated for surface passivation of silicon. The fixed oxide charge (Qf) and interface state density (Dit) are found to be −4.2 × 1012 cm−2 and 3.5 × 1011 eV−1cm−2, which demonstrates its potential for silicon surface passivation. High breakdown electric field up to 10.2 MV/cm was obtained for 13nm Al2O3 film which indicates the high quality of the Al2O3 film. Effective lifetime (τeff) of 502 µs and corresponding SRV of 28 cm/s was obtained on float-zone wafers passivated by these films. The film also shows excellent thermal stability. XPS analysis reveals that the film is stoichiometric.

Analysis of spectrum handoff schemes for cognitive radio networks considering secondary user mobility

Abstract: Cognitive radio has been proposed as an intelligent wireless communication system towards the usage of dynamic spectrum access in next generation networks, where the primary users (PU) and secondary users (SU) can share the spectrum, while causing minimum interference to each other. Spectrum mobility is the main element for the effective execution of cognitive radio networks. Spectrum mobility can be achieved by means of spectrum handoff (SHO). Initially, SUs continuously sense the channels to identify an idle channel. Error in sensing channel is possible. A detection theory is put forth to analyse the spectrum-sensing errors with the receiver operating characteristic (ROC) considering false alarm probability, missed detection and detection probability. Also, we meticulously investigate and analyse the probability of spectrum handoff (PSHO) with lognormal-3 and Hyper-Erlang distribution models considering SU call duration and residual time of spectrum holes availability designed for tele-traffic analysis.

An Automated System for Classification of Chronic Obstructive Pulmonary Disease and Pneumonia Patients Using Lung Sound Analysis.

Abstract: Chronic obstructive pulmonary disease (COPD) and pneumonia are two of the few fatal lung diseases which share common adventitious lung sounds. Diagnosing the disease from lung sound analysis to design a noninvasive technique for telemedicine is a challenging task. A novel framework is presented to perform a diagnosis of COPD and Pneumonia via application of the signal processing and machine learning approach. This model will help the pulmonologist to accurately detect disease A and B. COPD, normal and pneumonia lung sound (LS) data from the ICBHI respiratory database is used in this research. The performance analysis is evidence of the improved performance of the quadratic discriminate classifier with an accuracy of 99.70% on selected fused features after experimentation. The fusion of time domain, cepstral, and spectral features are employed. Feature selection for fusion is performed through the back-elimination method whereas empirical mode decomposition (EMD) and discrete wavelet transform (DWT)-based techniques are used to denoise and segment the pulmonic signal. Class imbalance is catered with the implementation of the adaptive synthetic (ADASYN) sampling technique.

Pothole Classification Model Using Edge Detection in Road Image

Abstract: Since the image related to road damage includes objects such as potholes, cracks, shadows, and lanes, there is a problem that it is difficult to detect a specific object. In this paper, we propose a pothole classification model using edge detection in road image. The proposed method converts RGB (red green and blue) image data, including potholes and other objects, to gray-scale to reduce the amount of computation. It detects all objects except potholes using an object detection algorithm. The detected object is removed, and a pixel value of 255 is assigned to process it as a background. In addition, to extract the characteristics of a pothole, the contour of the pothole is extracted through edge detection. Finally, potholes are detected and classified based by the (you only look once) YOLO algorithm. The performance evaluation evaluates the distortion rate and restoration rate of the image, and the validity of the model and accuracy of the classification. The result of the evaluation shows that the mean square error (MSE) of the distortion rate and restoration rate of the proposed method has errors of 0.2–0.44. The peak signal to noise ratio (PSNR) is evaluated as 50 db or higher. The structural similarity index map (SSIM) is evaluated as 0.71–0.82. In addition, the result of the pothole classification shows that the area under curve (AUC) is evaluated as 0.9.