MKSSS's Cummins College of Engineering for Women

About: MKSSS's Cummins College of Engineering for Women is a based out in . It is known for research contribution in the topics: Support vector machine & Discrete wavelet transform. The organization has 432 authors who have published 424 publications receiving 1919 citations.

A DTMOS-based power efficient recycling folded cascode operational transconductance amplifier

Abstract: The focus of the present study is on a recycling folded cascode (RFC) operational transconductance amplifier (OTA) in which the transconductance, as well as the slew rate of OTA, are enhanced. RFC OTA, proposed in this study, is employed using a Dynamic Threshold Voltage MOSFET (DTMOS) based differential pair with class AB operation. To achieve class AB operation, an adaptive biasing technique comprising a flip voltage follower is used which boosts the dynamic current and gain-bandwidth product of OTA. Conventional current mirrors are replaced with source degenerated non-linear current mirrors to achieve a better slew rate. The conventional and proposed RFC structures are designed and simulated in a standard 180 nm CMOS process at 1 V supply voltage. The proposed RFC OTA demonstrates a significant enhancement in the performance parameter as 11 dB improvement in the gain as well as 290% more GBW and achieves a slew rate that is nine times better compared to the conventional RFC.

Multimodal medical image fusion under nonsubsampled contourlet transform domain

Abstract: The Paper presents the multi modal medical image fusion technique based on discrete non subsamples contour let transform and pixel level fusion rule The fusion criteria is to minimize different errors between the fused image and the input images With respect to the medical diagnosis, the edges and outlines of the interested objects is more important than other information Therefore how to preserve the edge like features is worthy of investing for medical image fusion As we know the image with higher contrast contains more edge like features In term of this view, the project proposed a new medical fusion scheme based on discrete contour lettransformation, which is useful to provide more details about edges at curves This transformation will decompose the image into finer and coarser details and finest details will be decomposed into different resolution in different orientation The pixel and decision level fusion rule will be applied selected for low frequency and high frequency and in these rule we are following Image Averaging, Gabor filter bank and Gradient based fusion algorithm The fused contour let coefficients are reconstructed by inverse NS contour lettransformation The visual experiments and quantitative assessments demonstrate the effectiveness of this method compared to present image fusion schemes, especially for medical diagnosis The goal of image fusion is to obtain useful complementary information from CT/MRI multimodality images Image quality metrics can be found out by satisfactory entropy,better correlation coefficient, PSNR (Peak Signal to Noise Ratio) and less MSE (Mean Square Error)

Evaluation of wavelet based ECG steganography system by using Percentage Residual Difference (PRD) measurements

Abstract: Remote healthcare monitoring and Point of Care (PoC) based systems are widely used for managing diagnostic information of patients. These systems introduce many threats such as privacy, security data integrity, reliability, accuracy, etc. issues. In this paper, a new technique is introduced for solving the problem of privacy and security issues. In proposed method, ECG steganography technique using Discrete Wavelet Transforms (DWT) is implemented. This method is based on encryption and decryption techniques. Encryption method is used to hide the patient information inside the ECG signal by using scrambling matrix and shared key and produces the watermarked ECG signal. Decryption method is used to extract the patient secret information from the ECG signal by using same shared key and scrambling matrix. For evaluating the diagnosability, Percentage Residual Difference (PRD) and extracted PRD measurements are analyzed. From the results, table are calculated that there is no difference between PRD of original ECG and extracted ECG so watermarked ECG is also used for diagnosis purpose. In this paper, Signal to Noise Ratio (SNR) of normal PRD and extracted PRD are calculated using different wavelets and we have concluded that sym20 wavelet gives better response from the results than any other wavelet.

Analysis of Emotional State of a Person and Its Effect on Speech Features Using PRAAT Software

Abstract: Emotion Recognition and classification is emerging as an inevitable sub-system in human-machine interaction. In this paper, various features like pitch, formant frequencies, intensity, standard deviation, energy and duration have been extracted for emotion recognition and classification. Praat, which is open source scientific software for speech analysis, has been used to extract the features. Epoch count is also used, which is calculated using Zero Frequency Filtering method in MATLAB R2013a. Here, four different emotions namely Neutral, Angry, Happy and Sad are used for analysis. Effect of the above mentioned features on these four emotions have been analyzed and compared. Finally, significance of every feature for different emotions has been studied and analyzed.

Gray level co-occurrence matrix feature based object tracking in thermal infrared imagery

Abstract: Object tracking plays a vital role in many computer vision systems applications, such as video surveillance, robotics, 3-D image reconstruction, medical imaging, human computer interface, etc. In many proposed approaches, feature-based object tracking is widely used due to its accuracy. Feature extraction and feature correspondence are two main components of feature-based object tracking. In our proposed method, we have used gray level co-occurrence matrix (GLCM) features for object tracking in thermal imagery. As spatial resolution of the thermal sensor is fairly coarse, it also implies that temperature scales are close but may not exactly be the same, which indicates the presence of mutually related pixels or group of pixels. The GLCM texture analysis is based on assumption that the texture information of an image is an average spatial relationship between the gray tones in the image. Thus, this similarity in spatial resolution properties makes GLCM features suitable for object tracking in thermal infrared imagery. Initially, the target blobs to be tracked are provided by object detection stage. Then, for a given target blob in a frame, we first calculate GLCM feature points and then find corresponding features in the next successive frame. The sum of squared differences between two feature point sets is calculated to find feature correspondence between two frames for object tracking. Simultaneously, the codebook of the center of the blobs for prediction of the target candidate region in the next frame is maintained in order to have robust object tracking under occlusions. GLCM-based object tracking in thermal imagery outperforms the color or LBP-based mean-shift approach. This algorithm is also able to track objects in split and merge condition. The accuracy of this algorithm also depends on the object detection stage, such as Kalman tracking.