Journal Article
Permanent URI for this collectionhttps://ir.daiict.ac.in/handle/123456789/37
Browse
25 results
Search Results
Publication Metadata only Hybrid and parallel GAN architecture with non-IID noise input(Springer, 10-06-2025) Gohel, Prashant; Joshi, Manjunath V; DA-IICT, GandhinagarPublication Metadata only Data-Driven Soft Sensor for Optical Intensity Estimation in High-Power Plasma Source(IEEE, 15-07-2025) Tyagi, Himanshu; Joshi, Manjunath V; Bandyopadhyay, Mainak; Singh, M J; DA-IICT, GandhinagarInductively coupled plasma (ICP) sources are used in multiple industrial and research applications varying from material reactors, semiconductor fabrication, and nuclear fusion-based reactors. Experiments using ICP source are prone to noise due to the presence of high-power radio frequency (RF) radiation as well as the high voltage (HV). In order to operate such plasma sources, we need rich set of diagnostics that supports the control system as well as the operators in order to derive the important plasma parameters. Some of these sensors are prone to degradation and need constant maintenance and testing that creates challenges during operations. In order to monitor the performance and also mitigate the risks associated with the sensor failure, soft sensors can offer an alternative low-cost approach in estimating the physical parameters. Although soft sensors have found applications in industrial environments, limited implementation has been seen in experimental systems. Hence, in this article, we propose a soft sensor model for an optical (light) sensor which is one of the critical sensors used in ICP and other plasma sources. The proposed model is developed using data-driven machine-learning (ML) and deep-learning (DL) algorithms for a plasma-based system operating under noisy environments. After a thorough exploration, a comparatively better performance was observed using the artificial neural network (ANN)-based models. The ANN model was trained with various hyper parameters in order to obtain a test R2 score of 0.91 that was able to model the transient behavior of the sensor. After the model development, it was used for performing fault identification in the signal by comparing the predicted signal with actual signal. The article presents the steps followed in developing the data-driven models for the plasma light sensor and its application for sensor fault identification along with associated challenges.Publication Metadata only Robust Adversarial Defense: An Analysis on Use of Auto-Inpainting(Springer, 01-01-2025) Sharma, Shivam; Joshi, Rohan; Bhilare, Shruti; Joshi, Manjunath V; DA-IICT, GandhinagarPublication Metadata only Matching parameter estimation for high power Inductively coupled plasma sources using Machine learning techniques(Elsevier) Tyagi, Himanshu; Joshi, Manjunath V; Bandyopadhyay, Mainak; Singh, MJ; Pandya, Kaushal; Chakraborty, Arun; Joshi, Manjunath V; Joshi, Manjunath V; Joshi, Manjunath V; Joshi, Manjunath V; Joshi, Manjunath V; DA-IICT, GandhinagarInductively coupled plasma�or ICP sources form a basis for multiple applications ranging from�semiconductor fabrication�to reliable heating systems for�tokamak�machines. To meet the functional requirements, ICP sources need efficient plasma formation utilizing the various input parameters. Operation of ICP sources is a complex and challenging task since it involves scanning a wide multi-dimensional parameter space involving filament bias, radio frequency (RF) power, gas pressure, matching parameters, and other system configurations. The foremost challenge is to maximize the coupling of RF power in the ion source for efficient plasma formation. Standard ICP sources use a matching network that consists of variable capacitors to compensate for plasma inductance to enable maximum power coupling. Identification of an accurate set of matching parameters for high power sources is a complex task and is generally driven by operator experience which is established after years of operations. Due to these challenges, recent developments in the area of machine learning can be utilized for identifying the underlying model function to make accurate predictions and explore an alternative approach to the existing Physics-electrical models developed for the estimation of matching parameters for�plasma sources. The present work attempts to perform a data-driven model discovery for the identification of appropriate matching parameters utilizing�machine learning algorithms. In this work, ROBIN, a high-power ICP source that operates with a 1MHz, 100 kW RF generator is considered which has been operational since 2011 and has generated a considerable database. This database can be utilized for training/developing data-driven models for the estimation of matching parameters for ensuring better power coupling. The paper describes the development of two data-driven regression models for predicting the coupling efficiency in terms of power factor (denoted by Cos) and the capacitor values based on input parameters utilizing well known algorithms such as�support vector machine, random forest and�neural networks. Emphasis has been laid on developing the models using parameters that are tuneable externally. Also, the effect of system configurations on parameter prediction is investigated. The developed machine learning-based models have achieved test accuracy scores of 0.93 and 0.91 for predicting Cos�and capacitor values respectively. The paper presents the training and optimization process for various machine and�deep learning algorithms�in detail.Publication Metadata only Identifying the Source of Water on Plant Using the Leaf Wetness Sensor and via Deep Learning-Based Ensemble Method(IEEE, 01-01-2024) Saini, Riya; Garg, Pooja; Kumar, Naveen Chaudhary; Joshi, Manjunath V; Palaparthy, Vinay; Kumar, Ahlad; DA-IICT, Gandhinagar; Garg, Pooja (202021011)Plant disease detection and management is one of the pivotal areas in the agriculture sector, which needs attention to abate crop loss. The recent trends in machine learning and deep learning have played a significant role in reducing crop loss with the help of early plant disease detection. For plant disease detection prior information on soil moisture, ambient temperature, relative humidity, leaf wetness sensor (LWS), rainfall are crucial parameters. In this work, the objective is to identify the source of leaf wetness on the leaf canopy, which can arise due to irrigation, rainfall, or dew. To identify the source of wetness on the leaf canopy, either rainfall or humidity/mist sensors are used, which substantially increases the cost of the system. For this purpose, we have used the LWS, which is deployed in the field and various patterns for the irrigation, rainfall, or dew has been analyzed by using the in-house developed the Internet of Things (IoT)-enabled sensor system. The data collected from the field is used as a learning dataset for the proposed ensemble neural network (NN) developed to identify the source of leaf wetness. Short-time Fourier transform (STFT) has been employed to enhance data representation by transforming numerical data from the LWS into informative images. The provided ensemble model incorporates convolutional NN (CNN) and multilayer perceptron (MLP), which process image and numerical data (ambient temperature, relative humidity, leaf wetness duration, and maximum magnitude of frequency of images) as input. Their outputs combined in an artificial neural network (ANN) sub-model for precise leaf wetness event detection (dew, rainfall, or irrigation). The proposed model achieved an accuracy of 96.13% with average precision, recall, and F1 score for the leaf wetness events is about 84%, 85%, and 83%, respectively.Publication Metadata only Design of Complex Adaptive Multiresolution Directional Filter Bank and Application to Pansharpening(Springer, 01-02-2017) Gajbhar, Shrishail S; Joshi, Manjunath V; Joshi, Manjunath V; Joshi, Manjunath V; Joshi, Manjunath V; Joshi, Manjunath V; Joshi, Manjunath V; DA-IICT, Gandhinagar; Gajbhar, Shrishail S (201121016)This paper proposes a new 2-D transform design, namely�complex adaptive multiresolution directional filter bank, to represent the spatial orientation features of an input image�adaptively. The proposed design is completely�shift invariant�and represents the input image by one low-pass and multiscale�N�directional band-pass subbands. Here,�N�represents estimated number of dominant directions present in the input image. Our design consists of two main filter bank stages. A fix partitioned complex-valued directional filter bank (CDFB) is at the core of the design followed by a novel partition filter bank stage. Fine partitioning of the CDFB subbands is used to get the adaptive nature of the proposed transform. The partitioning decision is made based on the directional significance of range of CDFB subband angle selectivity in the input image. Partition filter bank stage which�nonuniformly�partitions the CDFB subbands provides total�N�dominant direction selective subbands. Local orientation map of the input image is used to determine the dominant directions and hence�N. For better sparsity properties, we design the multiresolution stage with filters having high�vanishing moments�and better frequency selectivity. Applicability of the proposed adaptive design is shown for pansharpening of multispectral images. Our proposed pansharpening approach is evaluated on images captured using QuickBird and IKONOS-2 satellites. Results obtained using the proposed approach on these datasets show considerable improvements in qualitative as well as quantitative evaluations when compared to state-of-the-art pansharpening approaches including transform-based methods.Publication Metadata only Abundance estimation using discontinuity preserving and sparsity-induced priors(IEEE, 30-05-2019) Patel, Jignesh R; Joshi, Manjunath V; Bhatt, Jignesh S; Joshi, Manjunath V; Joshi, Manjunath V; Joshi, Manjunath V; Joshi, Manjunath V; Joshi, Manjunath V; DA-IICT, Gandhinagar; Patel, Jignesh R (201521011)Abundance estimation is used to infer the proportions of endmembers with the given endmember signatures and reflectance value at each location. In this paper, we propose a two-phase iterative approach to estimate the abundances (fractions) of materials (endmembers) from the pixels of hyperspectral images (HSIs) by using the energy minimization framework. A linear mixture model is used to define the data term. We observe that abundance maps have homogeneous regions with limited discontinuity, and they exhibit spatial redundancy. Hence, we use inhomogeneous Gaussian Markov random field (IGMRF) and sparsity-induced priors as the regularization terms. While the IGMRF prior captures the smoothness and preserves discontinuities among abundance values, the sparsity-induced prior accounts for redundancy. We calculate the IGMRF parameters at every pixel location and learn a dictionary and the sparse representation for abundances using the initial estimate in phase 1, while the final abundance maps are estimated in phase 2. In order to learn the sparsity, we use the approach based on K-singular value decomposition. Both the IGMRF and sparseness parameters are initialized using an initial estimate of abundances and refined using the two-phase iterative approach. The experiments are conducted on synthetic hyperspectral HSIs with different noise levels, as well as on two real HSIs. The results are qualitatively and quantitatively compared with state-of-the-art approaches. Experimental results demonstrate the effectiveness of the proposed approach.Publication Metadata only SNR wall for generalized energy detector in the presence of noise uncertainty and fading(Elsevier, 01-02-2019) Captain, Kamal; Joshi, Manjunath V; Joshi, Manjunath V; Joshi, Manjunath V; Joshi, Manjunath V; Joshi, Manjunath V; Joshi, Manjunath V; DA-IICT, Gandhinagar; Captain, Kamal (201321003)The performance of energy detection (ED) degrades under low�SNR, noise uncertainty (NU) and fading. The generalized energy detector (GED) is obtained by changing the squaring operation in ED by an arbitrary positive number�. In this paper, we investigate the signal to noise ratio (SNR) wall for GED under diversity considering NU as well as fading by considering�-Law combining (pLC) and�law selection (pLS) diversity. First, the�SNR�walls considering�AWGN�channel are derived. It is shown that for pLC diversity, increasing��results in lower�SNR�wall. It is also shown that under no diversity and pLS diversity, the�SNR�wall is independent of�. The analysis is then extended to the channel with Nakagami fading where it is shown that the SNR wall increases significantly. As a byproduct of this work, we also study the effect of NU and fading on the detection performance and show that above certain value, the effect of NU is more severe when compared to the fading. The effect of��on the performance is analyzed and it is shown that the performance is the best for values of��close to 2. The performance of pLC and pLS is also compared.Publication Metadata only A regularized pan-sharpening approach based on self-similarity and Gabor prior(Taylor & Francis, 01-01-2017) Upla, Kishor P; Joshi, Manjunath V; Khatri, Nilay; Joshi, Manjunath V; Joshi, Manjunath V; Joshi, Manjunath V; Joshi, Manjunath V; Joshi, Manjunath V; DA-IICT, Gandhinagar; Khatri, NilayIn this article, we propose a new regularization-based approach for pan-sharpening based on the concepts of self-similarity and Gabor prior. The given low spatial resolution (LR) and high spectral resolution multi-spectral (MS) image is modelled as degraded and noisy version of the unknown high spatial resolution (HR) version. Since this problem is ill-posed, we use regularization to obtain the final solution. In the proposed method, we first obtain an initial HR approximation of the unknown pan-sharpened image using self-similarity and sparse representation (SR) theory. Using self-similarity, we obtain the HR patches from the given LR observation by searching for matching patches in its coarser resolution, thereby obtaining LR�HR pairs. An SR framework is used to obtain the patch pairs for which no matches are available for the patches in LR observation. The entire set of matched HR patches constitutes initial HR approximation (initial estimate) to the final pan-sharpened image which is used to estimate the degradation matrix as used in our model. A regularization framework is then used to obtain the final solution in which we propose to use a new prior which we refer as Gabor prior that extracts the bandpass details from the registered panchromatic (Pan) image. In addition, we also include Markov random field (MRF) smoothness prior that preserves the smoothness in the final pan-sharpened image. MRF parameter is derived using the initial estimate image. The final cost function consists of data fitting term and two prior terms corresponding to Gabor and MRF. Since the derived cost function is convex, simple gradient-based method is used to obtain the final solution. The efficacy of the proposed method is evaluated by conducting the experiments on degraded as well as on un-degraded datasets of three different satellites, i.e., Ikonos-2, Quickbird, and Worldview-2. The results are compared on the basis of traditional measures as well as recently proposed quality with no reference (QNR) measure, which does not require the reference image.Publication Metadata only Auto-inpainting Heritage Scenes: a Complete Framework for Detecting and Infilling Cracks in Images and Videos with Quantitative Assessment(Springer, 01-04-2015) Padalkar, Milind G; Joshi, Manjunath V; Joshi, Manjunath V; Joshi, Manjunath V; Joshi, Manjunath V; Joshi, Manjunath V; Joshi, Manjunath V; DA-IICT, Gandhinagar; Padalkar, Milind G (201121015)The need for preservation of cultural heritage has necessitated the research on digitally repairing the photographs of damaged monuments. In this paper, we first propose a technique for automatically detecting the cracked regions in photographs of monuments. Unlike the usual practice of manually selecting the mask for inpainting, the detected regions are supplied to an inpainting algorithm. Thus, the process of digitally repairing the cracked regions that physical objects have, using inpainting, is completely automated. The detection of cracked regions is based on comparison of patches, for which we use a measure derived from the edit distance, which is a popular string metric used in the area of text mining. Further, we extend this method to perform inpainting of video frames by making use of the scale-invariant feature transform and homography. We consider the camera to move while capturing video of the heritage site, as such videos are typically captured by novices, hobbyists and tourists. Finally, we also propose a video quality measure to quantify the temporal consistency of the inpainted video. Experiments have been carried out on videos captured from the heritage site at Hampi, India.
- «
- 1 (current)
- 2
- 3
- »