Conference Papers
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506
Browse
18 results
Search Results
Item Automatic Optic Disc segmentation using maximum intensity variation(2013) Kumar, V.; Sinha, N.Optic disc (OD) segmentation is an important step in automating eye screening for pathological conditions. In this paper, we propose an intensity-based approach to detect the OD boundary, given OD center. OD center is utilized to crop the sub-image that encloses the OD, within which candidate contour points are obtained. Points of maximum intensity variation, both horizontally and vertically, are chosen as candidate contour points. Iterative curve fitting is carried out, incorporating smoothness constraints. The area within the contour is checked for values of mean intensity, variance and compactness. The algorithm is applied on 152 images taken from two public datasets, DIARETDB1 and MESSIDOR. The validation criteria used are common area overlapping between automated segmentation and true OD region (score), sensitivity and Mean Distance to Closest Point (MDCP). The algorithm renders, on an average, a score value of 90%, sensitivity of 93% and MDCP of 8.3 pixels. © 2013 IEEE.Item Multi-label annotation of music(Institute of Electrical and Electronics Engineers Inc., 2015) Ahsan, H.; Kumar, V.; Jawahar, C.V.Automatic annotation of an audio or a music piece with multiple labels helps in understanding the composition of a music. Such meta-level information can be very useful in applications such as music transcription, retrieval, organization and personalization. In this work, we formulate the problem of annotation as multi-label classification which is considerably different from that of a popular single (binary or multi-class) label classification. We employ both the nearest neighbour and max-margin (SVM) formulations for the automatic annotation. We consider K-NN and SVM that are adapted for multi-label classification using one-vs-rest strategy and a direct multi-label classification formulation using ML-KNN and M3L. In the case of music, often the signatures of the labels (e.g. instruments and vocal signatures) are fused in the features. We therefore propose a simple feature augmentation technique based on non-negative matrix factorization (NMF) with an intuition to decompose a music piece into its constituent components. We conducted our experiments on two data sets - Indian classical instruments dataset and Emotions dataset [1], and validate the methods. © 2015 IEEE.Item Handheld electrochemical workstation for serum albumin measurement(Institute of Electrical and Electronics Engineers Inc., 2016) Hebbar, S.; Kumar, V.; Bhat, M.S.; Bhat, N.This paper presents a novel handheld electrochemical workstation for serum albumin measurement. The system consists of a multi-path potentiostat module which performs electrochemical measurements on disposable test strip. The strip provides a port for applying blood sample. The test strip consists of 3 electrochemical cells for redundancy and parallel testing. The 3 sets of 3 electrodes (Working, Reference and Counter electrodes) are screen printed on a Polyethylene Terephthalate (PET) substrate. The system provides the unique capability of performing Cyclic Voltammetry and Chrono Amperometry measurements in three parallel paths. The system is very generic and flexible, with user defined inputs for voltage, sweep rate and time through 5 inch capacitive touch screen. The experimental results can be stored on micro SD card and the data is accessible with USB or Bluetooth interface. This paper reports an extensive characterization of system through several tests conducted on standard redox solution. The system is then validated for human serum albumin measurement, using clinical samples. This is the first ever point of care handheld diagnostic device in the world for human serum albumin measurement. © 2016 IEEE.Item TCP Kay: An end-to-end improvement to TCP performance in lossy wireless networks using ACK-DIV technique and FEC(Institute of Electrical and Electronics Engineers Inc., 2016) Krishnaprasad, K.; Tahiliani, M.P.; Kumar, V.Wireless networks have evolved considerably in the last decade and the world has seen an exponential increase in the number of mobile device users. The performance of the wireless networks has become a critical factor and researchers nowadays are trying to bring out even the slightest increase in network performance wherever possible. TCP, which is the most dominant transport protocol of the Internet, fails to perform well in lossy wireless networks because it cannot differentiate congestion losses from non-congestion losses. This paper aims to improve the performance of TCP in lossy wireless networks and the resulting protocol is termed as TCP Kay. The major contributions of TCP Kay are: (1) it uses a modified ACK-DIV (Acknowledgment Division) technique for combating the loss of acknowledgement packets (ACKs) on the reverse path and (2) it combines the modified ACK-DIV technique with FEC to further enhance the robustness of data transmission in lossy wireless networks. The performance of TCP Kay has been studied using ns-2 and the same has been compared with TCP Reno with SACK (TCP SACK) and TCP Westwood+ (TCPW+). Results show that TCP Kay outperforms other TCPs in terms of goodput, received/sent ratio and packet drop rate in various wireless scenarios with up to 5% packet error rate. © 2015 IEEE.Item Soil classification using airborne hyperspectral data employing various approaches(Asian Association on Remote Sensing Sh1939murai@nifty.com, 2017) George, J.K.; Kumar, V.; Tarun, B.; Kumar, S.; Senthil Kumar, A.S.Hyperspectral remote sensing technology is one of the advance technology for detailed land cover feature extraction. Hyperspectral datasets contain large number of contiguous spectral bands with a narrow spectral bandwidth which enables identification of peculiar absorption features for distinguishing different type of soils. The potential of Airborne Visible Infrared Imaging Spectrometer-Next Generation (AVIRIS-NG) data was tested for distinguishing black and red soils in the ICRISAT area near Hyderabad, Telangana. The AVIRIS-NG data captured in 432 narrow contiguous bands (346–2505 nm) with spectral sampling of 5 nm bandwidth and a 4m ground pixel size was used in this study. The dataset was first spectrally subsetted by identification and removal of bad bands and was atmospherically corrected by converting it to surface reflectance using FLAASH. The data was finally georeferenced using the Internal Geometry Module (IGM) parameters. Optimal spectral bands from the reflectance data were selected on the basis of different characteristics of various soils. Data dimensionality reduction technique Minimum Noise Fraction (MNF) was also performed to extract noise free components. Total five classes including red and black soils were considered for land cover classification. Pixel based classification techniques such as Spectral Angle Mapper(SAM) and Support Vector Machine (SVM) were performed on the reflectance as well as MNF transformed data. SVM was also performed on data containing noise free MNF components and the selected optimal spectral bands. In the resultant classified output of reflectance data, SVM classifier provided higher accuracy and was able to classify black and red soil in a better way than SAM technique. The results also suggested that use of MNF components and specific spectral bands altogether improvised the classification of black and red soil. © 2017 ACRS. All rights reserved.Item Smart handheld platform for electrochemical bio sensors(Institute of Electrical and Electronics Engineers Inc., 2017) Hebbar, S.; Kumar, V.; Bhat, M.S.; Bhat, N.In this paper we present a smart handheld system for point of care biosensors. The system consists of a novel multi-path potentiostat module which performs electrochemical measurements on disposable test strip. The strip provides a port for applying bio-sample such as blood or urine. The analyte port on the disposable strip is designed with 3 sets of 3 electrodes (Working, Reference and Counter electrodes) screen printed on a Polyethylene Terephthlate (PET) substrate. The system provides the unique capability of performing Cyclic Voltametry and Chrono Amperometry measurements in three parallel paths, facilitating simultaneous measurement of three bio-analytes. The system is very generic and flexible, with user defined inputs for voltage, sweep rate and time through 5 inch capacitive touch screen. The experimental results can be stored on micro SD card and the data is accessible with USB or Bluetooth interface. © 2016 IEEE.Item Risk aware portfolio construction using deep deterministic policy gradients(Institute of Electrical and Electronics Engineers Inc., 2018) Hegde, S.; Kumar, V.; Singh, A.Allocation of liquid capital to the financial instruments in a portfolio is typically done using a two-step process. In the first step, predictive techniques are used to determine the future risk and rewards for the instrument. In the subsequent step, a quadratic optimization problem is solved to obtain the allocation that maximizes a relevant measure of the portfolio performance computed using a combination of the risks and the rewards. Deep Reinforcement Learning (DRL) eliminates the need for a two step process to find the allocation across the instruments that will optimize a measure of portfolio performance obtained from the market. DRL based portfolio construction autonomously adjusts to a change in the environment unlike traditional machine learning algorithms used in prediction. The existing DRL methods suffer from the challenges of stability, and do not lend themselves well to the portfolio construction problem that has a continuous action space. Proposed in 2015, Deep Deterministic Policy Gradients (DDPG) is a type of actorcritic DRL algorithm that provides support for continuous action space which is encountered in portfolio construction. This paper evaluates the use of DDPG to solve the problem of risk aware portfolio construction. Simulations are done on a portfolio of twenty stocks and the use of both Rate of Return and Sortino ratio as a measure of portfolio performance are evaluated. Results are presented that demonstrate the effectiveness of DDPG for risk aware portfolio construction. The simulation results presented in this paper show that having a risk-aware measure of portfolio performance such as Sortino ratio give a portfolio with superior return and lower variance. © 2018 IEEE.Item Effect of Mechanical properties on Multi Axially Forged LM4 Aluminium Alloy(Elsevier Ltd, 2020) Sajjan, S.S.; Kulkarni, M.V.; Ramesh, S.; Sharath, P.C.; Kumar, V.; Rajole, S.Commercially available LM4 Aluminum alloy was subjected through Severe Plastic Deformation (SPD) method by Multi-Axial Forging Process (MAF) in ambient temperature. In this process, the material was processed successfully up to 5 Passes and mechanical properties such as tensile strength, compression strength and hardness of the as received and processed samples at ambient temperature were evaluated. The MAF processed sample result showed that the ultimate strength, percentage elongation and compression strength improved by 55 MPa, 3.75% and 162 MPa respectively as compared with the unprocessed sample. Hardness also increased with the increase in the number of passes. In the case of microstructure, grain size reduced from 110 μm to 8 μm after subjecting the sample to MAF. Fractography explains the nature of the fracture from received to processed samples by decreasing the size of the dimple and the type of fracture observed was ductile in nature. Improvement in strength and hardness of processed samples was observed due to the grain refinement and high amount of density dislocation in the material during MAF. © 2018 Elsevier Ltd.Item 2019-nCoV disease control and rehabilitation: Insights from twitter analytics(Institute of Electrical and Electronics Engineers Inc., 2020) Chetty, N.; Alathur, S.; Kumar, V.Coronaviruses are the large family of viruses and life threatening with the capabilities to cause respiratory related diseases. The current outbreak of 2019-nCoV (novel Coronavirus) is challenging governance authorities and health care systems around the globe. The epidemic of 2019-nCoV is affecting people globally. The purpose of this paper is to examine the current status of disease control and rehabilitation in relation to outbreak of 2019-nCoV. In this regard, the Twitter social media contents are collected, analyzed and interpreted. Using a set of appropriate keywords, 110000 tweets are extracted from Twitter social media. The collected tweets are first pre-processed and then analyzed with a software developed in R language. The discussions on social media in relation to the outbreak of 2019-nCoV involves disease control, rehabilitation and anti-rehabilitation. Expressions involving specific locations revealed that the discussions are more oriented towards antirehabilitation than rehabilitation and disease control. The content analysis also revealed that the outbreak epidemic victimizes those who possess weaker immune system. © 2020 IEEE.Item Child online safety in indian context(Institute of Electrical and Electronics Engineers Inc., 2020) Andrews, D.; Alathur, S.; Chetty, N.; Kumar, V.Children initiates the usage of Internet during young age and spend more time online. Apart from the benefits like improved education, entertainment, news and gaming, Internet poses severe threats to the children online. Ensuring online safety is a global challenge. The purpose of this paper is to examine online social media responses and awareness posts on children online safety. In this relation, Twitter social media responses after freeing the accusers of children sexual harassment and Facebook pages of some prominent personalities in India for online safety are analyzed. The results reveal that though the people are angry and fearful, they believe judiciary and police system and expecting safety from the same. The analysis of Facebook posts depicts that the concerned authorities are active towards child online safety and providing awareness through their representatives. People demand legal actions against the perpetrators of the crime to punish them. The necessary actions should be taken for cyber-crime awareness information to reach all social media users. © 2020 IEEE.