Faculty Publications

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

Publications by NITK Faculty

Browse

Author: search.filters.author.Kumar, K.Has files: No

Search Results

Now showing 1 - 10 of 22
  • No Thumbnail Available
    Item
    A semantic search engine for answering domain specific user queries
    (2013) Kamath S․, S.S.; Piraviperumal, D.; Meena, G.; Karkidholi, S.; Kumar, K.
    With the exponential growth in web content and due to its sheer volume, the answers provided by traditional search engines by query specific keywords to content has resulted in markedly high recall and low precision. In order to alleviate this problem, the notion of incorporating semantics in content and in Search Engines, i.e., a Semantic Search Engine is increasingly crucial. Several Semantic Search Engines (SSEs) have been proposed and deployed till date and each is inherently different from the other. As such, the objective of this paper is to present a discussion on semantically enhanced search engines for intelligent web content discovery. We also present the architecture of a new SSE based on a bottom up approach that focuses on building a semantic base for Web content first and then carry out the process of querying it for attaining high precision and lower recall. © 2013 IEEE.
  • No Thumbnail Available
    Item
    Advertisement detection in commercial radio channels
    (Institute of Electrical and Electronics Engineers Inc., 2016) Koolagudi, S.G.; Sridhar, S.; Elango, N.; Kumar, K.; Afroz, F.
    In this paper, real time identification of advertisement segments in a radio broadcast is performed. There are certain distinctive characteristics of advertisements that distinguish from the rest of the broadcasting information, Speech technology related to recognition of specific patterns in speech signal can characterize this distinction. Machine learning tools such as Hidden Markov Models, Artificial Neural Networks and Ensemble Method are used to classify advertisement and non-advertisement patterns. An ensemble classification technique gave a better classification performance. The system was created using blind audio segmentation for optimization of real time analysis. This work is done mainly using audio characteristics and can be extended to visual data. © 2015 IEEE.
  • No Thumbnail Available
    Item
    Fault Diagnosis of Face Milling Tool using Decision Tree and Sound Signal
    (Elsevier Ltd, 2018) Madhusudana, C.K.; Kumar, K.; Narendranath, S.
    The monitoring of machining process can improve the quality of product and economy of production. The monitoring system helps to recognize and monitor the surface roughness, dimensional tolerance and tool condition. In this way, the condition monitoring system provides precise dimensional products, high productivity and enhanced machine tool life. This paper presents the classification of healthy and faulty conditions of the face milling tool using Decision tree (J48 algorithm) technique through machine learning approach. The sound signals of the face milling tool under healthy and faulty conditions are acquired. A set of discrete wavelet features are extracted from the sound signals using discrete wavelet transform (DWT) method. Decision tree technique is used to select prominent features out of all extracted features. The selected features are fed to the same algorithm for classification. Output of the algorithm is used to study and categorize the tool conditions. The decision tree model has provided a good classification accuracy of about 81% for the given sound signals and can be considered for fault diagnosis/condition monitoring. From the experimental results, it is suggested that the proposed method which comprises of decision tree and DWT techniques with sound signals can be recommended for the applications of fault diagnosis of the face milling tool. © 2017 Elsevier Ltd. All rights reserved.
  • No Thumbnail Available
    Item
    A study of influence of material properties on magnetic flux density induced in magneto rheological damper through finite element analysis
    (EDP Sciences edps@edpsciences.com, 2018) Gurubasavaraju, T.M.; Kumar, K.; Arun, M.
    Magnetorheological fluids are smart materials, which are responsive to the external stimulus and changes their rheological properties. The damper performance (damping force) is dependent on the magnetic flux density induced at the annular gap. Magnetic flux density developed at fluid flow gap of MR damper due to external applied current is also dependent on materials properties of components of MR damper (such as piston head, outer cylinder and piston rod). The present paper discus about the influence of different materials selected for components of the MR damper on magnetic effect using magnetostatic analysis. Different materials such as magnetic and low carbon steels are considered for piston head of the MR damper and magnetic flux density induced at fluid flow gap (filled with MR fluid) is computed for different DC current applied to the electromagnetic coil. Developed magnetic flux is used for calculating the damper force using analytical method for each case. The low carbon steel has higher magnetic permeability hence maximum magnetic flux could pass through the piston head, which leads to higher value of magnetic effect induction at the annular gap. From the analysis results it is observed that the magnetic steel and low carbon steel piston head provided maximum magnetic flux density. Eventually the higher damping force can be observed for same case. © The Authors, published by EDP Sciences, 2018.
  • No Thumbnail Available
    Item
    Compositionally modulated multilayer Cu-Zn alloy coatings fabricated using eco-friendly non-cyanide pulse electrochemical deposition
    (Elsevier Ltd, 2023) Bharadishettar, N.; Kumar, K.; Udaya Bhat, K.
    Pulse electrodeposition of Cu-Zn compositional modulated multilayer alloy (CMA) coatings was carried out onto AISI 304 stainless steel substrate using an environmentally friendly alkaline non-cyanide electrolytic bath. Cu-Zn alloy multilayer coating was co-electrodeposited using a trapezoidal pulse current. Multilayer coatings can have two different metals in layers or two-phase mixtures. Different sets of multilayers of 10, 20, 50, and 100 were done using a trapezoidal pulse current. In the trapezoidal pulse current module, during the higher current stage (0.1 A) Zn was deposited as compared to the lower current module (0.02 A) where Cu was deposited. Microstructural and structural analysis of the coatings confirmed nanocrystalline morphology with peaks corresponding to crystallographic planes of (002), (111), (020), and (022). Deposited coatings are hydrophilic in nature. The microhardness of the coatings is decreased with an increase in the number of layers deposited. © © 2023 Elsevier Ltd. All rights reserved.
  • No Thumbnail Available
    Item
    High Gain Ultra-Low NF Wideband CMOS Low Noise Amplifier Design Using 2-Stage Series-Parallel LC Matching Network
    (Institute of Electrical and Electronics Engineers Inc., 2023) Sudhanva, P.V.C.S.; Yugandhar, B.; Kumar, S.; Kumar, K.; Bhat, K.G.
    The focus of this work is the development of a sub-6 GHz (2-6 GHz) low noise amplifier (LNA) for 5G applications, using a 65 nm CMOS process. A novel two stage common source (CS) cascode source degeneration LNA topology by incorporating a contemporary series parallel LC network and two stage LC network for input and output matching respectively is proposed. The circuit implementation, simulations and evaluation of the LNA's performance are done utilizing the RF Spectre Cadence Virtuoso. According to the evaluation results, the LNA dissipates a total power of 19.6 mW at the supply voltage of 0.7 V. It offers an operational wide bandwidth (BW) of 3.2 GHz which ranges from 2.8 GHz to 6 GHz. The LNA has a peak gain of 36 dB and minimum noise figure (NF) of 1.1 dB across the sub-6 GHz spectrum. The proposed LNA also performs well in terms of stability and linearity measures. The layout of the proposed LNA occupies an area of 0.182mm2 © 2023 IEEE.
  • No Thumbnail Available
    Item
    Face Detection and Recognition Using OpenCV and Vision Transformer
    (Institute of Electrical and Electronics Engineers Inc., 2023) Kumar, K.; Pingale, N.; Rudra, B.
    Face recognition technology is vital in the real world with diverse applications. It is primarily used for security, law enforcement, personalization, healthcare, and education. Face recognition systems use biometric features like facial landmarks, texture, and shape to identify and verify individuals. The suggested approach employs a transformer-based architecture that solely relies on self-attention and does not utilize Convolutional Layers. This design choice enables the model to be trained efficiently with minimal computational power and fewer parameters than a CNN. The application of Vision Transformer (ViT) in various computer vision tasks has been highly successful, making it a state-of-the-art approach. Given its superior performance, we are interested in exploring whether ViT can enhance the accuracy of sheep face recognition.In this paper, we show that ViT can be a useful technique for facial recognition. Since there was no predefined dataset for face recognition, a PCI dataset was built for this investigation. Along with the PCI dataset, two more well-known datasets, AT&T and 5-Celebrity, we used to examine performance. In our model was seen that ViT could identify human faces on the PCI dataset with a 99% accuracy rate and perform much better than other face recognition algorithms like Eigenface, FisherFace, and LBPH. © 2023 IEEE.
  • No Thumbnail Available
    Item
    A L/S/C/X/Ku-Band Three-Stack, Two stages Fully Integrated CMOS Power Amplifier with 20.9 % PAE Using T-Network
    (Institute of Electrical and Electronics Engineers Inc., 2023) Kumar, K.; Kumar, S.; Gupta, M.P.
    This work proposes an L/S/C/X/Ku-Band three-stack two stages fully integrated CMOS power amplifier (PA) that realized in 65nm and achieves high efficiency, high output power over wide impedance bandwidth from 2-20 GHz. The proposed PA circuit comprises of T-network broadband input power match design, interstage tuning network and output power stage. The interstage tuning network is employed to achieve an excellent gain (|S21|) flatness of 16.3 ± 0.9 dB. The proposed PA design is employed 3-stack of transistor under supply of 3V at stage-1 followed LC and stage-2 to achieve high output power. The load pull analysis is performed to optimize the T- type output matching network for achieving PAE of 20.9 % and output power of 15.97 dBm at 7 GHz with 50 Ω load impedance. Besides, this PA provides 1 dB output compression point of 11.2 ± 0.8 dBm over full frequency band and also achieves the output third order intercept point of 23.2 dBm at 7 GHz using two tone signal. © 2023 IEEE.
  • No Thumbnail Available
    Item
    Run-up, run-down and reflection characteristics of semicircular breakwater for varying seaside perforations
    (2012) Hegde, A.V.; Rao, S.; Kumar, K.
    Breakwaters are mainly used for the purpose of withstanding and dissipating the dynamic energy of ocean waves and thereby provide tranquillity conditions on the lee side. Semicircular breakwaters are being used increasingly around the globe because of their great advantages. The paper explains physical studies conducted on seaside-perforated semicircular breakwater models to evaluate the wave run-up, wave run-down, and reflection coefficient for various wave heights (H), wave periods (T), water depths (d), incident wave steepness (H i/gT 2), depth parameter (d/gT 2), and relative spacing S/D (S = c/c spacing of perforations, D = diameter of perforations) on the seaside. It is observed that as the incident wave steepness increases, there is a decrease in the reflection coefficient (K r), and relative run-down (R d/H i) but increase in relative run-up (R u/H i). As the S/D ratio decreased (percentage of perforations increased), there was drop in the reflection coefficient, relative run-up, and relative run-down. As the depth parameter increased, there was a decrease in the relative run-up and reflection coefficient, but increase in relative run-down. © 2012 Taylor & Francis Group, LLC.
  • No Thumbnail Available
    Item
    New extracellular thermostable oxalate oxidase produced from endophytic Ochrobactrum intermedium CL6: Purification and biochemical characterization
    (Taylor and Francis Inc. 325 Chestnut St, Suite 800 Philadelphia PA 19106, 2016) Kumar, K.; Belur, P.D.
    Oxalate oxidase (EC 1.2.3.4) catalyzes the oxidative cleavage of oxalate to carbon dioxide with the reduction of molecular oxygen to hydrogen peroxide. Oxalate oxidase found its application in clinical assay for oxalate in blood and urine. This study describes the purification and biochemical characterization of an oxalate oxidase produced from an endophytic bacterium, Ochrobactrum intermedium CL6. The cell-free fermentation broth was subjected to two-step enzyme purification, which resulted in a 58.74-fold purification with 83% recovery. Specific activity of the final purified enzyme was 26.78 U mg?1 protein. The enzyme displayed an optimum pH and temperature of 3.8 and 80°C, respectively, and high stability at 4–80°C for 6 h. The enzymatic activity was not influenced by metal ions and chemical agents (K+, Na+, Zn2+, Fe3+, Mn2+, Mg2+, glucose, urea, lactate) commonly found in serum and urine, with Cu2+ being the exception. The enzyme appears to be a metalloprotein stimulated by Ca2+ and Fe2+. Its Km and Kcat for oxalate were found to be 0.45 mM and 85 s?1, respectively. This enzyme is the only known oxalate oxidase which did not show substrate inhibition up to a substrate concentration of 50 mM. Thermostability, kinetic properties, and the absence of substrate inhibition make this enzyme an ideal candidate for clinical applications. © 2016, Copyright © Taylor & Francis Group, LLC.