Faculty Publications

Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736

Publications by NITK Faculty

Browse

Author: search.filters.author.Ranjan, R.

Search Results

Now showing 1 - 7 of 7
  • No Thumbnail Available
    Item
    A novel approach for classification of normal/abnormal phonocardiogram recordings using temporal signal analysis and machine learning
    (IEEE Computer Society help@computer.org, 2016) Vernekar, S.; Nair, S.; Vijayasenan, D.; Ranjan, R.
    This paper discusses a novel approach used for classification of phonocardiogram (PCG) excerpts into normal and abnormal classes as a part of Physionet 2016 challenge [10]. The dataset used for the competition comprises of cardiac abnormalities such as mitral valve prolapse (MVP), benign murmurs, aortic diseases, coronary artery disease, miscellaneous pathological conditions etc. [3], We present the approach used for classification from a general machine learning application standpoint, giving details on feature extraction, type of classifiers used comparing their performances individually and in combination. We propose a technique which leverages previous research on feature extraction with a novel approach to modeling temporal dynamics of the signal using Markov chain analysis [7,9]. These newly introduced Markov features along with other statistical and frequency domain features, trained over an ensemble of artificial neural networks and gradient boosting trees, with bagging, gave us an accuracy of 82% on the validation dataset provided in the competition and was consistent with the test data with the best result of 78%. © 2016 CCAL.
  • No Thumbnail Available
    Item
    A novel approach for Robust Detection of Heart Beats in Multimodal Data using neural networks and boosted trees
    (IEEE Computer Society help@computer.org, 2016) Vernekar, S.; Vijayasenan, D.; Ranjan, R.
    This work describes a novel approach designed for Physionet 2014 Challenge, Robust Detection of Heart Beats in Multimodal Data [5]. The objective here is to detect the location of R peaks from QRS complex of an electrocardiogram (ECG) excerpt. Robust detection of heart beats in a noisy ECG signal is an extremely difficult task. To overcome the challenge in such situations, besides ECG, blood pressure (BP) signal is also recorded at the same time; hence the idea here is that, if a segment of one of the signals is noisy, the peaks in that segment can be better estimated by peaks found in the corresponding segment of other signal, if good. The approach uses Machine Learning (ML) methods to identify locations of R-peaks in a given segment of ECG or BP signal. Peaks from both ECG and BP signal are found separately using a novel feature representation and subsequent ML approaches that renders R peaks in the signal, easier to be detected, by a simple windowing technique. Individually detected peaks, from both ECG and BP are further analyzed in chunks of equal short time periods, and the best result of the two is chosen in final peak prediction based on variance comparison techniques. The performance of system on the training dataset [11] provided in the competition is 99.95%. The performance on test datasets which are hidden for phase I, phase II and phase III of the competition respectively are 93.27%, 90.28% and 89.74%. The submission resulted in 1st place in all three phases of the competition. © 2016 CCAL.
  • No Thumbnail Available
    Item
    Deep Learning Based Smart Garbage Monitoring System
    (Institute of Electrical and Electronics Engineers Inc., 2020) Rao, P.P.; Rao, S.P.; Ranjan, R.
    India has witnessed an unprecedented increase in garbage levels in the past 20 years. Massive quantities of waste, particularly solid waste, are generated daily and seldom picked up. Consequently, garbage is being dumped in landfills and water bodies, hence not managed effectively. This mismanagement has detrimental consequences on our environment. Thus, there is a need to develop an efficient system to manage waste. In this paper, an IoT-based, automated smart bin monitoring system is proposed. Moreover, a deep learning model was used to forecast future garbage levels from the data collected. The proposed neural network model was able to predict garbage levels with an accuracy of 80.33%. Results verify the accurate prognosis of garbage levels. Additionally, data were analysed using bar charts. The amalgamation of IoT and Deep learning can bring a revolutionary change in technology and be applied to waste management. Consequently, prediction and examination of garbage levels may help municipal authorities incorporate an efficient garbage management system and reduce the overflow of garbagebins. © 2020 IEEE.
  • No Thumbnail Available
    Item
    The microstructure of a solidifying lead free Sn-3.5Ag solder alloy is found to be highly sensitive to the surface condition of the copper substrate. A transition from lamellar to fine fibrous eutectic structure is observed as the surface condition of the substrate is altered by increasing the surface roughness and application of flux. This is attributed to lowering of interfacial tension and improved wetting of the solidifying solder on the substrate material leading to a better contact at the metal/substrate interface. The results also indicated the importance of surface texture of the substrate and the application of the flux to the quality of the solder/substrate joint. © 2003 Elsevier Ltd. All rights reserved.
    (Elsevier Ltd, Effect of substrate surface texture and flux coating on the evolution of microstructure during solidification of lead free Sn-3.5Ag solder alloy) Prabhu, K.; Bali, R.; Ranjan, R.
    2004
  • No Thumbnail Available
    Item
    One-Dimensional Multichannel g-C3N4.7Nanostructure Realizing an Efficient Photocatalytic Hydrogen Evolution Reaction and Its Theoretical Investigations
    (American Chemical Society, 2021) Antil, B.; Kumar, L.; Ranjan, R.; Shenoy, S.; Tarafder, K.; Gopinath, C.S.; Deka, S.
    The emerging metal-free carbon nitride (C3N4) offers prominent possibilities for realizing the highly effective hydrogen evolution reaction (HER). However, its poor surface conductivity and insufficient catalytic sites hinder the HER performance. Herein, a one-dimensional vermicular rope-like graphitic carbon nitride nanostructure is demonstrated that consists of multichannel tubular pores and high nitrogen content, which is fabricated through a cost-effective approach having the final stoichiometry g-C3N4.7 for HER application. The present g-C3N4.7 is unique owing to the presence of abundant channels for the diffusion process, modulated surface chemistry with rich-electroactive sites from N-electron lone pairs, greatly reduced recombination rate of photoexcited exciton pairs, and a high donor concentration (4.26 × 1017 cm3). The catalyst offers a visible-light-driven photocatalytic H2 evolution rate as high as 4910 ? mol h-1 g-1 with an apparent quantum yield of 14.07% at band gap absorption (2.59 eV, 479 nm) under 7.68 mW cm-2 illumination. The number of hydrogen gas molecules produced is 1.307 × 1015 s-1 cm-2, which remained constant for a minimum of 18 h of repeated cycling in the HER without any degradation of the catalyst. In density functional theory calculations, a significant change in the band offset is observed due to N doping into the system in favor of electron catalysis. The theoretical band gap of a monolayer of g-C3N4.7 was enormously reduced because of the presence of additional densities of states from the doped N atom inside the band gap. These impurity or donor bands are formed inside the band gap region, which ultimately enhance the hydrogen ion reduction reaction enormously. © 2021 American Chemical Society.
  • No Thumbnail Available
    Item
    Profile generation from web sources: an information extraction system
    (Springer, 2022) Ranjan, R.; Vathsala, H.; Koolagudi, S.G.
    The Internet space has a vast collection of information which is not always structured. These sources of information such as social media, news articles, blogs, speeches and videos often contain information that could be utilized to generate decision making tools such as reports about events and individuals. Using this information is a long and tedious process if done manually. Over the years, a lot of research has been done in data mining and natural language processing techniques to facilitate the consumption of this vast amount of data. The current work describes ProfileGen, an information extraction system that uses a variety of these data sources to form a profile of a given person. There are two parts to this application: The first part uses information publicly available on social media sites, news articles on news websites and blogs and compiles this information to form a corpus about the given person, and in the second part, the information is ranked using machine learning techniques, so as to provide information in the order of importance. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Austria, part of Springer Nature.
  • No Thumbnail Available
    Item
    Physical unclonable functions and QKD-based authentication scheme for IoT devices using blockchain
    (Elsevier B.V., 2024) Cunha, T.B.D.; Manjappa, M.; Ranjan, R.; Vasilakos, A.V.
    As the number of Internet of Things (IoT) devices is increasing exponentially, strong security measures are needed to guard against different types of cyberattacks. This research offers a novel IoT device authentication technique to mitigate these challenges by integrating three cutting-edge technologies namely blockchain technology, Quantum Key Distribution (QKD), and Physically Unclonable Functions (PUFs). By utilizing the distinctive qualities of PUFs for device identification and the unrivaled security of QKD for key exchange, the proposed approach seeks to address the significant security issues present in IoT environments. Adopting blockchain technology ensures transparency and verifiability of the authentication process across distributed IoT networks by adding an unchangeable, decentralized layer of trust. An examination of the computing and communication costs reveals that the proposed protocol is effective, necessitating low computational resources that are critical for IoT devices with limited resources. The protocol's resistance against a variety of attacks is demonstrated by formal proofs based on the Real-Or-Random (ROR) model and security evaluations using the Scyther tool, ensuring the integrity and secrecy of communications. Various threats are analyzed, and the protocol is proven to be secure and efficient from all forms of attacks. © 2024 Elsevier B.V.