http://nopr.niscpr.res.in/handle/123456789/58077 2026-10-10T02:14:19Z http://nopr.niscpr.res.in/handle/123456789/58085 Title: Renyi entropy based Bi-histogram equalization for contrast enhancement of MRI brain images Authors: D, Vijayalakshmi; Elangovan, Poonguzhali; Nath, Malaya Kumar Abstract: The quality of the MRI brain images is dependent on the sensor. It is essential to have a pre-processing technique to meet the finest quality at the sensor’s cost. A pre-processing algorithm has been proposed in this paper to enhance the low contrast MRI brain images. The input image’s histogram has been divided into two sub histograms using its median value to uphold the input image’s mean brightness. After calculating the Renyi entropy from the sub histogram, histogram clipping has been done to regulate the enhancement rate. The clipping limit has been selected automatically from the minimum value of the mean, median of the distribution function, and itself. Additionally, the proposed algorithm has incorporated the Discrete Cosine Transform (DCT) to improve the enhancement. Experimental results have shown that the proposed algorithm enhances the input image and maintains the mean brightness. Page(s): 5-11 2021-03-01T00:00:00Z http://nopr.niscpr.res.in/handle/123456789/58084 Title: Segmentation of satellite images using machine learning algorithms for cloud classification Authors: Sebastian, Sruthy; Kumar, Lakshmi Sutha; Annadurai, Pugazhenthi Abstract: Clouds play a significant role in determining the state of a changing weather. Clouds offer useful information for forecasting precipitation and provide measurement for showcasing solar irradiance variability. The influence of specific types of clouds on rainfall prediction and solar radiance has been discussed in this paper. Various segmentation algorithms, clustering algorithms and supervised machine learning algorithms such as K Nearest Neighbors and Random forest have been used to segment/classify the clouds using the dataset obtained from INSAT-3DR satellite. Clouds have been classified into high level clouds (Cirrus clouds), medium level clouds (Alto clouds) and low level clouds (Stratus clouds) in accordance with the altitude and cloud densities. The performance metrics has been found for the segmented images. Parameters that provide optimum results for supervised machine learning algorithms have been explored. On the images, different machine learning algorithms have been compared. Page(s): 12-18 2021-03-01T00:00:00Z http://nopr.niscpr.res.in/handle/123456789/58083 Title: Accurate prognosis of Covid-19 using CT scan images with deep learning model and machine learning classifiers Authors: Gupta, Siddharth; Aggarwal, Palak; Chaubey, Nisha; Panwar, Avnish Abstract: The Covid-19 disease is caused by coronavirus or SARS-CoV-2 has wrecked havoc globally. This epidemic severely impacted the economy of most of the countries across the world and has taken away many lives. To control the pandemic situation many researchers, organizations, and institutes have come up with the pathogenesis and developing vaccines to decimate this disease. Out of the several techniques, one of the techniques use image patterns on Computed Tomography (CT) to detect whether a patient is Covid-19 positive or not. In this work, the SARS-COV-2 dataset has been used for the detection of Covid-19 images and normal images. These dataset images have been fed to various deep learning models for extracting the features and finally passed to various ML classifiers which classify the images as Covid-19 or normal images. The results have established that the VGG19 model along with Logistic Regression (LR) classifier gives the maximum AUC and accuracy of 98.5% and 94.6%. Page(s): 19-24 2021-03-01T00:00:00Z http://nopr.niscpr.res.in/handle/123456789/58082 Title: Design of 3.1GHz/4.1GHz/5.1GHz/9.8GHz tetra band microstrip antenna for wireless applications Authors: Byanigoudra, Shiddanagouda; Kumar, N Dinesh; R M, Vani; Hunagund, P V Abstract: In this paper, a novel engineered tetra band microstrip antenna is designed for wireless applications. The proposed antenna is printed on flame-retardant fiberglass epoxy (FR-4) substrate with the dimensions of 40mmx40mmx1.6mm and ground plane etched with rectangular split ring defected ground structure (RSRDGS). The RSRDGS unit cell is used to miniaturize the designed antenna as well as for multiband resonance. The proposed antenna resonates at tetra band frequency points i.e., 3.1GHz, 4.1GHz, 5.1GHz, and 9.8GHz with satisfactory bandwidth of 209MHz, 313MHz, 168MHz, and 195MHz respectively. The total peak gain at tetra band frequency points are 8.54dB, 7.65dB, 1.79dB, and 4.65dB as well as 48% of virtual size miniaturization is achieved. The proposed antenna results make it suitable to use for S-band to X-band wireless applications. Page(s): 25-28 2021-03-01T00:00:00Z