JSS Research Foundation

Mysore, India

JSS Research Foundation

Mysore, India
Time filter
Source Type

Nagabhushan T.N.,JSS Research Foundation | Manoli N.,JSS Medical College and Hospital | Basavaraj V.,JSS Medical College and Hospital
Proceedings - 2016 2nd International Conference on Cognitive Computing and Information Processing, CCIP 2016 | Year: 2016

We propose a simple approach to identify concave points in Histopathological Images. Identification of all valid concave points play an important role in separating irregular shaped cells forming clumps in the Histopathological images. There exists several studies for accurate identification of concave points. Our experimental analysis reveal that existing methods fail to identify both deep, and shallow concave points. In this paper we propose an integrated curvature and convex hull based concave points detection in Histopathological images. The proposed method performed well when compared to the existing methods. © 2016 IEEE.

Shiva Prakash S.P.,SJCE | Nagabhushan T.N.,JSS Research Foundation | Krinkin K.,Saint Petersburg Electrotechnical University Leti
Proceedings - 2016 2nd International Conference on Cognitive Computing and Information Processing, CCIP 2016 | Year: 2016

Owing to the self organizing, self configuring and self healing capabilities, Wireless Mesh Networks (WMN) have emerged as most powerful architectures in recent times. WMN operate with limited battery resources. To save energy, ieee 802.11s has introduced a mechanism called power save mode(PSM) which switches STA mode from active to light sleep or deep sleep mode when STA is not involved in transmission. Several models have been proposed by researchers to improve the energy saving mechanisms in 802.11s. Most of the researchers have considered node position as static while proposing their model. In WMN nodes are subjected to change their position over a period of time depending on the mobility mode and pattern. Under mobility conditions there could be higher energy consumption at STA compared to static cases. Hence in this work, we propose an energy saving model that involves STA mobility and trigger power save modes based on the remaining energy at each STA. The experiments have been conducted using RandomWayPoint mobility model in Network Simulator3. The behaviour of the model is observed by keeping STA position dynamic. The results show that energy consumption rate of STA is high under mobility conditions compared to static. By Implementing PSM under mobility situations, we are able save substantial energy thus increasing the life of the batteries associated with each STA in a WMN. © 2016 IEEE.

Divakara S.S.,JSS Research Foundation
International Journal of Wavelets, Multiresolution and Information Processing | Year: 2017

In this paper, systolic array-based novel architecture for dual-tree complex wavelet transform (DTCWT) computation is designed and implemented on FPGA. The wavelet filter coefficients of DTCWT are quantized and rounded to nearest integer and the loss in rounding and quantization is limited to 0.5(Formula presented.)dB as compared with software implementation. The parallel architecture designed computes row elements simultaneously and pipelined architecture is designed to compute column elements. The proposed architecture is modeled using Verilog and implemented on Xilinx Virtex II FPGA. For 2D implementation, the design operates at a maximum frequency of 156(Formula presented.)MHz and consumes power less than 3(Formula presented.)W. This is the first design with systolic array architecture on FPGA for DTCWT computation operating at frequencies greater than 100(Formula presented.)MHz. © 2017 World Scientific Publishing Company

Asha V.,JSS Research Foundation | Nagabhushan P.,University of Mysore | Bhajantri N.U.,Government Engineering College
Pattern Recognition Letters | Year: 2012

In this paper, we propose a method of automatic detection of texture-periodicity using superposition of distance matching functions (DMFs) followed by computation of their forward differences. The method has been specifically devised for automatically identifying row and column periodicities and thereby the size of periodic units from textile fabrics belonging to any of the 17 wallpaper groups and is a part of automatic fabric defect detection scheme being developed by us that needs periodicities along row and column directions. Overall row-DMF (or overall column-DMF) is obtained based on superposition of DMF of all rows (or columns) from the input image and its second forward difference is computed to get the overall maximum which is a direct measure of periodicity along row (or column) direction. Results from experiments on various near-regular textures demonstrate the capability of the proposed method for automatic periodicity extraction without the need of human intervention. © 2011 Elsevier B.V. All rights reserved.

Chandra A.P.J.,JSS Research Foundation
2011 2nd International Conference on Computer and Communication Technology, ICCCT-2011 | Year: 2011

Electronic laboratory experiments mainly describe the design and implementation of various circuits which assists theoretical study. Web based environment for these experiments helps the learners with any time accessibility of the remote hardware resources through online environment. The graphical programming language LabVIEW and data acquisition facilities provide an attractive solution through the availability of rich functions to acquire and analyze the signals. The custom interface circuits are designed to configure the circuit remotely based on the design requirement. The remote switching of different components to the circuit experimentation is achieved through the transistor switching circuitry. The switching circuitry is operated by the Boolean control actuations on graphical user interface, which can be remotely operated through a common web browser. A case study is presented with the circuit experimentation on the generation of frequency modulation signal. © 2011 IEEE.

Chethana M.,JSS Research Foundation | Prashantha K.,British Petroleum
Journal of Applied Polymer Science | Year: 2015

Ecological concern on accumulation of neutraceutical industrial waste material and the demands for newer composite materials have promoted extensive research on utilizing industrial wastes materials. Therefore, in the present study finely powdered ginger spent (GS), filled polyurethane (PU) green composites with varying amount viz., 0, 2.5, 5, 7.5, and 10 wt % of GS have been fabricated. The prepared PU/GS green composites have been characterized for their mechanical properties, density and void content. Interaction between filler and matrix has been confirmed from Fourier transform infrared spectroscopy studies. Moisture absorption and desorption studies have been performed at different relative humidity (RH). The moisture absorption and desorption studies, shows that as the hydrophilic GS content increases in the matrix the RH also increases. Water uptake behavior of PU/GS were measured in different chemical environments such as 5% sodium chloride solution, cold water at different temperature and in hydrochloric acid solution. The water uptake values increases as increase in GS concentration. Equilibrium water content, diffusivity and equilibrium time taken for all PU/GS composites have been investigated. Biodegradation studies reveals that as the GS content increases the weight loss also increases. Thermal properties have been performed using differential scanning calorimetry (DSC) and dynamic mechanical analysis (DMA). From DSC and DMA thermograms it is revealed that increase in Tg with increase in GS content. RH and contact angle measurement have been performed to understand the hydrophilic nature of the prepared composite. The morphological behavior of composites has been studied using scanning electron microscopy. © 2014 Wiley Periodicals, Inc.

Patil C.M.,JSS Research Foundation
Communications in Computer and Information Science | Year: 2010

A wide variety of biometrics based tools are under development to meet the challenges in security in the existing complex scenario. Among these, iris pattern based identification is the most promising for its stability, reliability, uniqueness, noninvasiveness and immunity from duplication. Hence the iris identification technique has become hot research point in the past several years. This paper compares recognition rates, speed and other efficiency parameters resulting from three iris feature extraction algorithms that use statistical measures, lifting wavelet transform (LWT), and Gray-Level Co-occurrence Matrix (GLCM) respectively. Experimental results show that while LWT provides higher recognition rate, GLCM approach offers reduction in computation time with a small compromise in recognition rate. It also demonstrates that statistical measures is the most economical when recognition requirement is crucial. © 2010 Springer-Verlag Berlin Heidelberg.

Ulle A.R.,JSS Research Foundation | Nagabushan T.N.,JSS Research Foundation | Basavaraj V.,JSS Medical College and Hospital
Proceedings - 2015 International Conference on Cognitive Computing and Information Processing, CCIP 2015 | Year: 2015

This paper proposes a simple approach to split the clumps found in Histopathological Images. Watershed algorithm is generally used to segment and separate the clumps. Several studies have revealed that watershed algorithm suffer drawbacks leading to lesser accuracy in clump splitting. From the literature it is evident that most of the existing methods on clump splitting have been applied on binary image without considering the color information. In this paper we propose a novel clump splitting method by considering color features. The proposed method shows better accuracy when clumps are irregular in shape and have multiple splits. © 2015 IEEE.

Shreekanth T.,JSS Research Foundation | Udayashankara V.,SJCE
Proceedings of 2014 International Conference on Contemporary Computing and Informatics, IC3I 2014 | Year: 2015

The Optical Braille Character Recognition (OBR) system is in significant need in order to preserve the Braille documents to make them available in future for the large section of visually impaired people and also to make the bi-directional communication between the sighted people and the visually impaired people feasible. The recognition and transcribing the double sided Braille document into its corresponding natural text is a challenging task. This difficulty is due to the overlapping of the front side dots (Recto) with that of the back side dots (Verso) in the Inter-point Braille document. In such cases, the usual method of template matching to distinguish recto and verso dots is not efficient. In this paper a new system for double sided Braille dot recognition is proposed, which employs a two-stage highly efficient and an adaptive technique to differentiate the recto and verso dots from an inter-point Braille using the projection profile method. In this paper we present (i) a horizontal projection profile for Braille line segmentation, (ii) vertical projection profile for Braille word segmentation and (iii) Integration of horizontal and vertical projection profiles along with distance thresholding for Braille character segmentation. We demonstrate the effectiveness of this segmentation technique on a large dataset consisting of 754 words from Hindi Devanagari Braille documents with varying image resolution and with different word patterns. A recognition rate of 96.9% has been achieved. © 2014 IEEE.

Kiranmayi G.R.,JSS Research Foundation | Udayashankara V.,JSS Research Foundation
2013 International Conference on Circuits, Controls and Communications, CCUBE 2013 | Year: 2013

Epilepsy is a neurological disorder which affects the nervous system. Epileptic seizures are due to hyperactivity in certain parts of the brain. Automatic seizure detection helps in diagnosis and monitoring of epilepsy especially during long term recordings of EEG. This paper presents the bispectrum analysis of electroencephalogram (EEG) for the detection of epilepsy. Bispectrum is a higher order spectrum. It characterizes the nonlinearities in the signal. Features extracted from the bispectrum of EEG are applied to the neural network classifier to detect normal and epileptic EEGs. The classification accuracy of 81.67% is obtained. The results demonstrate that the proposed features are more effective in differentiating epileptic EEG as compared to features from the conventional power spectrum. © 2013 IEEE.

Loading JSS Research Foundation collaborators
Loading JSS Research Foundation collaborators