Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
41 results
Search Results
Item Automatic identification of diabetic maculopathy stages using fundus images(2009) Nayak, J.; Subbanna Bhat, P.S.; Acharya, R.Diabetes mellitus is a major cause of visual impairment and blindness. Twenty years after the onset of diabetes, almost all patients with type 1 diabetes and over 60% of patients with type 2 diabetes will have some degree of retinopathy. Prolonged diabetes retinopathy leads to maculopathy, which impairs the normal vision depending on the severity of damage of the macula. This paper presents a computer-based intelligent system for the identification of clinically significant maculopathy, non-clinically significant maculopathy and normal fundus eye images. Features are extracted from these raw fundus images which are then fed to the classifier. Our protocol uses feed-forward architecture in an artificial neural network classifier for classification of different stages. Three different kinds of eye disease conditions were tested in 350 subjects. We demonstrated a sensitivity of more than 95% for these classifiers with a specificity of 100%, and results are very promising. Our systems are ready to run clinically on large amounts of datasets. © 2009 Informa Healthcare USA, Inc.Item An intelligent system for squeeze casting process—soft computing based approach(Springer London, 2016) Gowdru Chandrashekarappa, G.C.; Krishna, P.; Parappagoudar, M.B.The present work deals with the forward and reverse modelling of squeeze casting process by utilizing the neural network-based approaches. The important quality characteristics in squeeze casting, namely surface roughness and tensile strength, are significantly influenced by its process variables like pressure duration, squeeze pressure, and pouring and die temperatures. The process variables are considered as input and output to neural network in forward and reverse mapping, respectively. Forward and reverse mappings are carried out utilizing back propagation neural network and genetic algorithm neural network. For both supervised learning networks, batch training is employed using huge training data (input-output data). The input-output data required for training is generated artificially at random by varying process variables between their respective levels. Further, the developed model prediction performances are compared for 15 random test cases. Results have shown that both models are capable to make better predictions, and the models can be used by any novice user without knowing much about the mechanics of materials and the process. However, the genetic algorithm tuned neural network (GA-NN) model prediction performance is found marginally better in forward mapping, whereas BPNN produced better results in reverse mapping. © 2016, Springer-Verlag London.Item Cumulant-based correlated probabilistic load flow considering photovoltaic generation and electric vehicle charging demand(Higher Education Press Limited Company, 2017) Bhat, N.G.; Prusty, B.R.; Jena, D.This paper applies a cumulant-based analytical method for probabilistic load flow (PLF) assessment in transmission and distribution systems. The uncertainties pertaining to photovoltaic generations and aggregate bus load powers are probabilistically modeled in the case of transmission systems. In the case of distribution systems, the uncertainties pertaining to plug-in hybrid electric vehicle and battery electric vehicle charging demands in residential community as well as charging stations are probabilistically modeled. The probability distributions of the result variables (bus voltages and branch power flows) pertaining to these inputs are accurately established. The multiple input correlation cases are incorporated. Simultaneously, the performance of the proposed method is demonstrated on a modified Ward-Hale 6-bus system and an IEEE 14-bus transmission system as well as on a modified IEEE 69-bus radial and an IEEE 33-bus mesh distribution system. The results of the proposed method are compared with that of Monte-Carlo simulation. © 2017, Higher Education Press and Springer-Verlag Berlin Heidelberg.Item Location prediction algorithm for a nonlinear vehicular movement in VANET using extended Kalman filter(Springer New York LLC barbara.b.bertram@gsk.com, 2017) Jaiswal, R.K.; Jaidhar, C.D.Vehicular ad-hoc network (VANET) is an essential component of the intelligent transportation system, that facilitates the road transportation by giving a prior alert on traffic condition, collision detection warning, automatic parking and cruise control using vehicle to vehicle (V2V) and vehicle to roadside unit (V2R) communication. The accuracy of location prediction of the vehicle is a prime concern in VANET which enhances the application performance such as automatic parking, cooperative driving, routing etc. to give some examples. Generally, in a developed country, vehicle speed varies between 0 and 60 km/h in a city due to traffic rules, driving skills and traffic density. Likewise, the movement of the vehicle with steady speed is highly impractical. Subsequently, the relationship between time and speed to reach the destination is nonlinear. With reference to the previous work on location prediction in VANET, nonlinear movement of the vehicle was not considered. Thus, a location prediction algorithm should be designed by considering nonlinear movement. This paper proposes a location prediction algorithm for a nonlinear vehicular movement using extended Kalman filter (EKF). EKF is more appropriate contrasted with the Kalman filter (KF), as it is designed to work with the nonlinear system. The proposed prediction algorithm performance is measured with the real and model based mobility traces for the city and highway scenarios. Also, EKF based prediction performance is compared with KF based prediction on average Euclidean distance error (AEDE), distance error (DE), root mean square error (RMSE) and velocity error (VE). © 2016, Springer Science+Business Media New York.Item Redesigned Spatial Modulation for Spatially Correlated Fading Channels(Springer New York LLC barbara.b.bertram@gsk.com, 2017) G.D., G.S.; Koila, K.; Neha, N.; Raghavendra, R.; Sripati, U.In this paper, a new variant of Spatial Modulation (SM) Multiple-Input Multiple-Output (MIMO) transmission technique, designated as Redesigned Spatial Modulation (ReSM) has been proposed. In ReSM scheme, a dynamic mapping for antenna selection is adopted. This scheme employs both single antenna as well as double antenna combinations depending upon channel conditions to combat the effect of spatial correlation. When evaluated over spatially correlated channel conditions, for a fixed spectral efficiency and number of transmit antennas, ReSM exhibits performance improvement of at least 3 dB over all the conventional SM schemes including Trellis Coded Spatial Modulation (TCSM) scheme. Furthermore, a closed form expression for the upper bound on Pairwise Error Probability (PEP) for ReSM has been derived. This has been used to calculate the upper bound for the Average Bit Error Probability (ABEP) for spatially correlated channels. The results of Monte Carlo simulations are in good agreement with the predictions made by analytical results. The relative gains of all the comparison plots in the paper are specified at an ABER of 10?4. © 2017, Springer Science+Business Media, LLC.Item A comprehensive framework for Double Spatial Modulation under imperfect channel state information(Elsevier B.V., 2017) G.D., G.S.; Koila, K.; Raghavendra, R.; Shripathi Acharya, U.The essential requirement for a 5G wireless communication system is the realization of energy efficient as well as spectrally efficient modulation schemes. Double Spatial Modulation (DSM) is a recently proposed high rate Index Modulation (IM) scheme, designed for use in Multiple Input Multiple Output (MIMO) wireless systems. The aim of this scheme is to increase the spectral efficiency of conventional Spatial Modulation (SM) systems while keeping the energy efficiency intact. In this paper, the impact of imperfect channel knowledge on the performance of DSM system under Rayleigh, Rician and Nakagami-m fading channels has been quantified. Later, a modified low complexity decoder for the DSM scheme has been designed using ordered block minimum mean square error (OB-MMSE) criterion. Its performance under varied fading environments have been quantified via Monte Carlo simulations. Finally, a closed form expression for the pairwise error probability (PEP) for a DSM scheme under conditions of perfect and imperfect channel state information has been derived. This is employed to calculate the upper bound on the average bit error probability (ABEP) over aforementioned fading channels. It is observed that, under perfect and imperfect channel conditions DSM outperforms all the other variants of SM by at least 2dB at an average bit error ratio (ABER) of 10?5. Tightness of the derived upper bound is illustrated by Monte Carlo simulation results. © 2017 Elsevier B.V.Item Signal constellations employing multiplicative groups of Gaussian and Eisenstein integers for Enhanced Spatial Modulation(Elsevier B.V., 2017) G.D., G.S.; Raghavendra, R.; Koila, K.; Shripathi Acharya, U.In this paper, we propose two new signal constellation designs employing Gaussian and Eisenstein Integers for Enhanced Spatial Modulation (ESM). ESM is a novel technique which was propounded by Cheng et al. The advantage of ESM over other Spatial Modulation (SM) schemes lies in its ability to enhance spectral efficiency while keeping the energy efficiency intact. This is done by activating either one or two antennas judiciously depending upon the required trade-off. In ESM, information radiated from the antennas depends upon index of the active transmit antenna combination(s) and also on the set of constellation points chosen, which may include points from multiple constellations. In this paper, we propose signal constellations based on multiplicative groups of Gaussian and Eisenstein integers. The set comprising of Gaussian and Eisenstein integers serves as primary and secondary constellation points for Gaussian Enhanced Spatial Modulation (GESM) scheme. The secondary constellation points are deduced from a single geometric interpolation from the primary constellation points. The Monte Carlo simulation results indicate that the proposed nonuniform constellations achieve impressive SNR gains compared to conventional constellation points used in the design of ESM. This new design has been described for MIMO employing 4 × 4 and 8 × 8 antenna configurations with only two active antennas. Furthermore, a closed form expression for the pairwise error probability (PEP) for the GESM scheme has been deduced. The PEP is utilized to determine the upper bound on the average bit error probability (ABEP). Our simulations indicate that the proposed GESM from Gaussian and Eisenstein integers scheme outperforms all the other variants of SM including conventional ESM by at least 2.5 dB at an average bit error ratio (ABER) of 10?5. Close correspondence between the theoretical analysis and the Monte Carlo simulation results are observed. © 2017 Elsevier B.V.Item Spatially Modulated Non Orthogonal Space Time Block Code: Construction and design from cyclic codes over Galois Field(Elsevier B.V., 2019) Godkhindi Shrutkirthi, G.S.; G.D., G.S.; Shripathi Acharya, U.S.A new class of non-binary Spatially Modulated Non-orthogonal Space Time Block Code designs (SM-NSTBC) has been proposed. These designs employ full rank, length n,(n|qm?1,m?n) cyclic codes defined over GF(qm). The underlying cyclic code constructions have the property that the codewords when viewed as m×n matrices over GF(q) have rank equal to m (Full rank). These codes are punctured to yield m×m full rank matrices over GF(q). Rank preserving transformations are used to map the codewords of full rank codes over a finite field to full rank Space Time Block Codes. The proposed scheme can be generalized to handle any number of transmit antenna greater than two. Due to the characteristics of Full rank cyclic codes employed, a coding gain of approximately 1.5 dB to 5 dB is obtained over conventional STBC-SM and SM-OSTBC schemes. This is demonstrated for spectral efficiencies of 4, 5, 7 and 8 bpcu. Analytical as well as Monte-Carlo simulations show that proposed SM-NSTBC outperforms STBC-SM and its variants. The upper bound on average bit error rate has been derived and the computation complexity for ML detection has been estimated. © 2019Item Inductor-less PVT robust gain switching balun LNA for multistandard applications(Taylor and Francis Ltd. michael.wagreich@univie.ac.at, 2019) Vasudeva Reddy, K.; Prashantha Kumar, H.An inductor-less single to differential low-noise amplifier (LNA) is proposed for multistandard applications in the frequency band of 0.2–2 GHz. The proposed LNA incorporates noise cancellation and voltage shunt feedback configuration to achieve minimum noise characteristics and low power consumption. In addition to noise cancellation, trans-conductance of common-source stage is scaled to improve the noise performance. In this way, noise figure (NF) of LNA below 3 dB is achieved. An additional capacitor C c is used to correct the gain and phase imbalance at the output. The gain switching has been enabled with a step size of 4 dB for high linearity and power efficiency. The bias point of all transistors is chosen such that the variation in g m is not more than 10%. The proposed LNA is implemented in UMC 0.18-?m RF CMOS technology. The core area is 182 ?m × 181 ?m. Moreover, the LNA has better ratio of relevant performance to area. The proposed balun LNA is validated by rigorous Monte Carlo simulation. The 3? deviation of gain and NF is less than 5%. Finally, the proposed LNA is robust to unavoidable PVT variations. © 2019, © 2019 Informa UK Limited, trading as Taylor & Francis Group.Item Correlation analysis and statistical characterization of heterogeneous sensor data in environmental sensor networks(Elsevier B.V., 2019) Rajesh, G.; Chaturvedi, A.In wireless sensor networks, missing data is an inevitable phenomenon due to the inherent limitations of the sensor nodes, such as battery power constraints of nodes, missing communication links, bandwidth limitation, etc. Missing data adversely affects the quality of data received by the sink node. Since the data acquired by the sensor nodes in a multimodal environmental sensor network are spatially and temporally correlated, these correlations play a pivotal role in missing data recovery and data prediction. This paper proposes an analytical framework to characterize the correlation between two different pairs of modalities in an environmental sensor network using a set of classical and robust measures of correlation coefficient estimates. Monte Carlo simulation is performed to approximately model sensed environmental data characteristics. Three classical estimates (Pearson's correlation coefficient, Spearman's rank correlation coefficient, and Kendall's-tau rank correlation coefficient), and four robust estimates of correlation coefficients are used to establish the correlation between different pairs of sensed modalities in the data characteristics. The efficacy of these estimates is obtained using the two performance metrics, mean-squared error (MSE) and relative estimation efficiency (RE). Stationarity analysis among the acquired environmental variables shed light upon the best estimates of the correlation coefficient, which could be used for prediction of temperature modality in a known region of slope/stationarity in the data characteristics. The robustness of the correlation coefficient estimates in the presence of outliers present in the data due to noise, errors, low residual battery power of sensor nodes, etc. is also investigated. © 2019 Elsevier B.V.