Journal Articles
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/19884
Browse
12 results
Search Results
Item Machine learning techniques for periodontitis and dental caries detection: A narrative review(Elsevier Ireland Ltd, 2023) Radha, R.C.; Raghavendra, B.S.; Subhash, B.V.; Rajan, J.; Narasimhadhan, A.V.Objectives: In recent years, periodontitis, and dental caries have become common in humans and need to be diagnosed in the early stage to prevent severe complications and tooth loss. These dental issues are diagnosed by visual inspection, measuring pocket probing depth, and radiographs findings from experienced dentists. Though a glut of machine learning (ML) algorithms has been proposed for the automated detection of periodontitis, and dental caries, determining which ML techniques are suitable for clinical practice remains under debate. This review aims to identify the research challenges by analyzing the limitations of current methods and how to address these to obtain robust systems suitable for clinical use or point-of-care testing. Methods: An extensive search of the literature published from 2015 to 2022 written in English, related to the subject of study was sought by searching the electronic databases: PubMed, Institute of Electrical and Electronics Engineers (IEEE) Xplore, and ScienceDirect. Results: The initial electronic search yielded 1743 titles, and 55 studies were eventually included based on the selection criteria adopted in this review. Studies selected were on ML applications for the automatic detection of periodontitis and dental caries and related dental issues: Apical lessons, Periodontal bone loss, and Vertical root fracture. Conclusion: While most of the ML-based studies use radiograph images for the detection of periodontitis and dental caries, few pieces of the literature revealed that good diagnostic accuracy could be achieved by training the ML model even with mobile photos representing the images of dental issues. Nowadays smartphones are used in every sector for different applications. Training the ML model with as many images of dental issues captured by the smartphone can achieve good accuracy, reduce the cost of clinical diagnosis, and provide user interaction. © 2023 Elsevier B.V.Item In this paper, block based texture segmentation is proposed based on contourlets and the hidden Markov model (HMM). Hidden Markov model is combined with hidden Markov tree (HMT) to form HMM-HMT model that models global dependency between the blocks in addition to the local statistics within a block. The HMM-HMT model is modified to use the contourlet transform, a new extension to the wavelet transform that forms a true basis for image representations. The maximum likelihood multiresolution segmentation algorithm is used to handle several block sizes at once. Since the algorithm works on the contourlet transformed image data, it can directly segment images without the need for transforming into the space domain. The experimental results demonstrate the competitive performance of the algorithm on contourlets with that of the other methods and excellent visual performance at small block sizes. The performance is comparable with that of wavelets and is superior at small block sizes. © Springer-Verlag 2004.(Springer Verlag, Contourlet based multiresolution texture segmentation using contextual hidden markov models) Raghavendra, B.S.; Subbanna Bhat, P.2004Item Subtractive clustering and phase correlation similarity measure for endmember extraction(Elsevier B.V., 2020) Palla, P.Y.; Shetty, A.; Raghavendra, B.S.; Narasimhadhan, A.V.Target identification using Remote Sensing techniques saves time, cost and reduces difficulties in field investigation. The endmember is a reference spectral response of a pure pixel in the hyperspectral image and is used for object identification/classification from hyperspectral data. Quality of endmembers selected influences classification accuracy. Though there have been several algorithms proposed for endmember extraction, choosing a benchmark algorithm requires further investigation. To the best of our knowledge, similarity measures have not been explored much in the extraction of spectrally distinct signatures called endmembers. In this paper, we propose a similarity measures based subtractive clustering algorithm (SM-SCA) for endmember extraction. The objective of this paper is to explore the applicability of a SM-SCA and effectiveness of different similarity measures in endmember extraction and to compare it's performance with classical endmember extraction algorithms. Implementation on airborne hyperspectral (Samson data and AVIRIS data over Cuprite region) and synthetic data proves that SM-SCA is capable of extracting endmembers of all the materials identified in the data, with appropriate similarity measure. Experimental results show that (i) the similarity measures are potential not only to discriminate but also in extraction of different endmember signatures and (ii) the proposed SM-SCA with phase correlation similarity measure perform comparable to the classical endmember extraction algorithms in identifying endmembers. © 2020 Elsevier B.V.Item CloudX-net: A robust encoder-decoder architecture for cloud detection from satellite remote sensing images(Elsevier B.V., 2020) Kanu, S.; Khoja, R.; Lal, S.; Raghavendra, B.S.; Cs, A.Cloud Detection is an important pre-processing step for any application involving remote sensing data. This paper presents a deep learning based CloudX-Net architecture, that can detect cloud cover with improved accuracy in comparison to the benchmark from satellite remote sensing images. The proposed CloudX-Net model reduces the number of parameters needed for accurate predictions and thus make deep learning based cloud detection method very efficient. Atrous Spatial Pyramid Pooling (ASPP) and Separable convolution are used to optimize the network. For experimentation, we have used Landsat 8 images and 38-Cloud dataset and trained the architectures using Soft Jaccard loss function. Comparing several quantifying metrics result from various recent deep learning architectures proves the efficiency and effectiveness of the proposed CloudX-Net model for cloud detection from satellite images. The source code and data are available at https://github.com/shyamfec/CloudXNet. © 2020 Elsevier B.V.Item Efficient deep learning architecture with dimension-wise pyramid pooling for nuclei segmentation of histopathology images(Elsevier Ltd, 2021) Aatresh, A.A.; Yatgiri, R.P.; Chanchal, A.K.; Kumar, A.; Ravi, A.; Das, D.; Raghavendra, B.S.; Lal, S.; Kini, J.Image segmentation remains to be one of the most vital tasks in the area of computer vision and more so in the case of medical image processing. Image segmentation quality is the main metric that is often considered with memory and computation efficiency overlooked, limiting the use of power hungry models for practical use. In this paper, we propose a novel framework (Kidney-SegNet) that combines the effectiveness of an attention based encoder-decoder architecture with atrous spatial pyramid pooling with highly efficient dimension-wise convolutions. The segmentation results of the proposed Kidney-SegNet architecture have been shown to outperform existing state-of-the-art deep learning methods by evaluating them on two publicly available kidney and TNBC breast H&E stained histopathology image datasets. Further, our simulation experiments also reveal that the computational complexity and memory requirement of our proposed architecture is very efficient compared to existing deep learning state-of-the-art methods for the task of nuclei segmentation of H&E stained histopathology images. The source code of our implementation will be available at https://github.com/Aaatresh/Kidney-SegNet. © 2021 Elsevier LtdItem Multitarget Detection and Tracking by Mitigating Spot Jammer Attack in 77-GHz mm-Wave Radars: An Experimental Evaluation(Institute of Electrical and Electronics Engineers Inc., 2023) Kumuda, D.K.; Vandana, G.S.; Pardhasaradhi, B.; Raghavendra, B.S.; Srihari, P.; Cenkarmaddi, L.R.Small form factor radar sensors at millimeter wavelengths find numerous applications in the industrial and automotive sectors. These radar sensors provide improved range resolution, good angular resolution, and enhanced Doppler resolution for short range and ultrashort ranges. However, it is challenging to detect and track the targets accurately when a radar is interfered by another radar. This article proposes an experimental evaluation of a 77-GHz IWR1642 radar sensor in the presence of a second 77-GHz AWR1642 radar sensor acting as a spot jammer. A real-time experiment is carried out by considering five different targets of various cross sections, such as a car, a larger size motorcycle, a smaller size motorcycle, a cyclist, and a pedestrian. The collected real-time data are processed by four different constant false alarm rate detectors, cell averaging (CA)-CFAR, ordered statistics (OS)-CFAR, greatest of CA (GOCA)-CFAR, and smallest of CA (SOCA)-CFAR. Following that, data from these detectors are fed into two different clustering algorithms (density-based spatial clustering of applications with noise (DBSCAN) and K-means), followed by the extended Kalman filter (EKF)-based tracker with global nearest neighbor (GNN) data association, which provide tracks of various targets with and without the presence of a jammer. Furthermore, four different metrics [tracks reported (TR), track segments (TSs), false tracks (FTs), and track loss (TL)] are used to evaluate the performance of various tracks generated for two clustering algorithms with four detection schemes. The experimental results show that the DBSCAN clustering algorithm outperforms the K-means clustering algorithm for many cases. © 2001-2012 IEEE.Item Universal Discrete Finite Rate of Innovation Scheme for Sparse Signal Reconstruction(Birkhauser, 2023) Sudhakar Reddy, P.; Raghavendra, B.S.; Narasimhadhan, A.V.Finite rate of innovation (FRI) schemes have been proposed to reconstruct a class of discrete-time signals having small number of nonzero coefficients (sparse signals) from a limited number of observations. However, these reconstruction schemes achieve optimal performance up to a certain signal-to-noise ratio (SNR) and breakdown for smaller SNR values. Moreover, these are not universal as they are aware of the number of nonzero coefficients (a.k.a. L0 norm) for reconstruction of the signal. In this paper, we propose a novel FRI reconstruction scheme based on error decrease detector criterion to extend the current scheme to a universal one which enables reconstructing signals with an unknown number of nonzero coefficients. With noiseless conditions, we show that the proposed FRI scheme achieves perfect reconstruction of the original signal. And also, computer simulations for the noisy case are presented where the proposed scheme shows improvements over the traditional FRI scheme in the breakdown SNR. Further, an application of the proposed universal FRI scheme on reconstruction of magnetic resonance images and QRS complexes is demonstrated. © 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.Item Sparse-Prony FRI signal reconstruction(Springer Science and Business Media Deutschland GmbH, 2023) Sudhakar Reddy, P.S.; Raghavendra, B.S.; Narasimhadhan, A.V.Finite rate of innovation (FRI) approach is used for sampling and reconstruction of a class of non-bandlimited continuous signals having a finite number of free parameters. Traditionally, Prony and matrix-pencil methods are proposed to reconstruct FRI signals from the discrete samples. However, these methods tend to break down at a certain signal-to-noise ratio (SNR). In this paper, we propose sparsity-based annihilating filter, refer it as sparse-Prony, which avoids polynomial root-finding. In the noiseless scenario, the proposed method is able to recover perfectly the original signal. Simulation results for the noisy scenario demonstrate significant improvement in the performance in terms of MSE over the traditional FRI methods, especially in the breakdown SNR. © 2023, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.Item RMDNet-Deep Learning Paradigms for Effective Malware Detection and Classification(Institute of Electrical and Electronics Engineers Inc., 2024) S, S.; Lal, S.; Pratap Singh, M.; Raghavendra, B.S.Malware analysis and detection are still essential for maintaining the security of networks and computer systems, even as the threat landscape shifts. Traditional approaches are insufficient to keep pace with the rapidly evolving nature of malware. Artificial Intelligence (AI) assumes a significant role in propelling its design to unprecedented levels. Various Machine Learning (ML) based malware detection systems have been developed to combat the ever-changing characteristics of malware. Consequently, there is a growing interest in exploring advanced techniques that leverage the power of Deep Learning (DL) to effectively analyze and detect malicious software. DL models demonstrate enhanced capabilities for analyzing extensive sequences of system calls. This paper proposes a Robust Malware Detection Network (RMDNet) for effective malware detection and classification. The proposed RMDNet model branches the input and performs depth-wise convolution and concatenation operations. The experimental results of the proposed RMDNet and existing DL models are evaluated on 48240 malware and binary visualization image dataset with RGB format. Also on the multi-class malimg and dumpware-10 datasets with grayscale format. The experimental results on each of these datasets demonstrate that the proposed RMDNet model can effectively and accurately categorize malware, outperforming the most recent benchmark DL algorithms. © 2013 IEEE.Item Approximate Finite Rate of Innovation Based Seismic Reflectivity Estimation(Birkhauser, 2024) Sudhakar Reddy, P.S.; Raghavendra, B.S.; Narasimhadhan, A.V.Reflectivity inversion is an important deconvolution problem in reflection seismology that helps to describe the subsurface structure. Generally, deconvolution techniques iteratively work on the seismic data for estimating reflectivity. Therefore, these techniques are computationally expensive and may be slow to converge. In this paper, a novel method for estimating reflectivity signals in seismic data using an approximate finite rate of innovation (FRI) framework, is proposed. The seismic data is modeled as a convolution between the Ricker wavelet and the FRI signal, a Dirac impulse train. Relaxing the accurate exponential reproduction limitation given by generalised Strang-Fix (GSF) conditions, we develop a suitable sampling kernel utilizing Ricker wavelet which allows us to estimate the reflectivity signal. The experimental results demonstrate that the proposed approximate FRI framework provides a better reflectivity estimation than the deconvolution technique for medium-to-high signal-to-noise ratio (SNR) regimes with nearly 18% of seismic data. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.