Browsing by Author "Gupta, Karunesh Kumar"

Now showing 1 - 20 of 80

Active Power Filter Control Algorithm using Wavelets
(IEEE, 2006) Kumar, Rajneesh; Gupta, Karunesh Kumar
This paper presents a wavelet transform (WT) based technique to extract fundamental frequency component from a nonsinusoidal and unbalanced load current in a three phase system. The fundamental frequency component is extracted using multiresolution analysis (MRA). The remaining harmonics can be used by the active filter for compensation. Simulation result obtained for a rectifier load current shows the usefulness of the proposed method.
Adaptive fault identification of bearing using empirical mode decomposition–principal component analysis-based average kurtosis technique
(IET, 2017-01) Gupta, Karunesh Kumar
The kinematics of the bearing is erratic and random in nature and requires timely attention to avoid any catastrophic failure. In this study, the authors have proposed and analysed the amplitude and frequency modulated signals emanating from the bearing using four steps, i.e. standardisation, empirical mode decomposition, principal component analysis (PCA), envelope and cepstral envelope techniques. First, the standardised frequency modulated signals are decomposed into stationary non-linear modes called intrinsic mode functions (IMFs). In this approach, PCA is applied on the decomposed IMFs to produce uncorrelated signals. The uncorrelated signals whose value is above the average kurtosis are recombined to form a modified signal. The modified signal incurred from the approach is followed by spectrum, envelope, cepstrum, and cepstral envelope techniques to identify the features. It is observed this proposed combined approach effectively and adaptively identifies the inner/ball faults, shaft rotating frequency and corresponding harmonics in ease with least utilisation of IMFs.
Adaptive Shrinkage Function Optimization by Differential Evolution
(IEEE, 2008) Gupta, Karunesh Kumar; Gupta, Rajiv
In this paper, a new wavelet shrinkage denoising algorithm is presented. The algorithm uses wavelet transform (WT) to extract information about sharp variation in multiresolution images and applies shrinkage function adapting the image features. The features are detected by energy of neighboring pixels, whereas in standard wavelet methods, the empirical wavelet coefficients shrink pixel by pixel, on the basis of their individual magnitude. The shrinkage function is optimized by differential Evolution (DE)
Air Quality Monitoring and Analysis Network
(IEEE, 2020) Gupta, Karunesh Kumar
With the advent of technology, more and more aspects of our lives are being digitized. Hence, eventually, there will be a need for sensor-based networks for creating sustainable living conditions. This paper aims to describe the implementation and application of an Air Quality monitoring and analysis network(AQMAN) capable of monitoring different air quality parameters which could then be used to predict the sustainability of a locality at the expense of precision. The network employs various Machine Learning algorithms for forecasting the parameters on multiple time granularity. A method for constructing a Geo-spatial graph of the parameter's concentration has also been discussed in the later sections. The paper takes a more pragmatic approach of making the system cheaper, reliable, scalable and accessible.
An algorithm for road enhancement in SAR images using wavelet transform
(Springer, 2007-12) Gupta, Karunesh Kumar; Gupta, Rajiv
Image denoising and enhancement plays an important role in the field of Synthetic Aperture Radar (SAR) imagery. The geographical features detection applications such as road detection are very demanding. The objective of image enhancement is to improve the visibility of lowcontrast features while suppressing the speckle. It improves the visible quality of the image. Image has locally varying statistics, has different edges and smoothness in it. Speckle reduction can be done on an image by wavelet analysis. Wavelet gives a superior performance in speckle reduction due to properties such as sparsity and multi resolution.
Assessment of Water Quality Parameters in Real-Time Environment
(Springer, 2020-10) Gupta, Raj Kumar; Gupta, Karunesh Kumar
Assessment of drinking water quality has been an important issue nowadays as the water available is severely polluted and can be the cause of diseases like cholera, diarrhea, dysentery, etc. The traditional methods for water quality monitoring require a high-labor-cost and tine consumption as these methods include a sample collection followed by lab-based chemical testing. In addition, the chemicals used in the testing are toxic and of high-cost. So, there is a need for real-time monitoring and chemical-free testing of water quality parameters. This paper presents a real-time water quality monitoring system based on the Raspberry Pi 3 development board and a Python framework. The water quality parameters utilized for water quality monitoring are temperature, pH, oxidation reduction potential, electrical conductivity, and dissolved oxygen and E. coli. The water quality sensors were interfaced with the designed embedded platform. Finally, the acquired parameters were compared with the benchmark equipment for validation.
Assessment of Water Quality Parameters in Real-Time Environment
(Springer, 2020-10) Gupta, Raj Kumar; Gupta, Karunesh Kumar
Assessment of drinking water quality has been an important issue nowadays as the water available is severely polluted and can be the cause of diseases like cholera, diarrhea, dysentery, etc. The traditional methods for water quality monitoring require a high-labor-cost and tine consumption as these methods include a sample collection followed by lab-based chemical testing. In addition, the chemicals used in the testing are toxic and of high-cost. So, there is a need for real-time monitoring and chemical-free testing of water quality parameters. This paper presents a real-time water quality monitoring system based on the Raspberry Pi 3 development board and a Python framework. The water quality parameters utilized for water quality monitoring are temperature, pH, oxidation reduction potential, electrical conductivity, and dissolved oxygen and E. coli. The water quality sensors were interfaced with the designed embedded platform. Finally, the acquired parameters were compared with the benchmark equipment for validation.
Background Modeling for HEVC Compressed Videos using Radial Basis Network
(IEEE, 2019) Gupta, Karunesh Kumar
High Efficiency Video Coding (HEVC) or H.265 is a successor of H.264/AVC, which is designed to gain performance, ease parallel processing and achieve better compression ratio over the latter. We present a compressed domain background modelling technique utilizing residual information from inter predicted motion compensated coding blocks at HEVC encoder. We employ machine learning techniques to model the dynamic background using training sequence and test it on target video sequences with highly dynamic background content. Rather than operating on a pixel level granularity, the proposed method operates on 8×8 data blocks from residual frames. The method classifies each 8×8 block of the input frame as foreground or background. After block level segmentation, conventional background subtraction methods can be used on the foreground blocks for pixel level segmentation, resulting in reduced computation time and effective utilization of resources.
Bearing Fault analysis using Kurtosis and Wavelet Multi-scale PCA
(2019-02) Gupta, Karunesh Kumar
The vibration signal monitoring that is being generated by a rotor supported by a rolling element bearing is becoming important to define reliability of rotary machine. It is most prudent and useful method for bearing fault detection. Recently, there has been a lot of research on rolling element bearings fault. The kurtosis is most vital parameter to find inner race fault and outer race fault. It is enhanced by a proper selection of variable frame sizes and decompositions levels using wavelet based multi-scale principal component analysis (WMSPCA). It is observed that the kurtosis changes significantly as compared to the actual kurtosis of the un-decomposed faulty signals by proper selection of frame size and decompositions level.
Bearing fault analysis using variational mode decomposition
(IEEE, 2014) Gupta, Karunesh Kumar
Bearing health analysis plays a significant role in industry to improve reliability and performance of critical processes by alarming the faults at early stages. Conventional techniques do no guarantee to detect the faults at early stages because the low energy bearing frequencies get suppressed by stern noise and higher vibrations. The Fast Fourier Transform fails to analyse the transient and non-stationary signals directly. This paper performs the signal analysis on vibration data of ball bearing using Variational mode decomposition (VMD). Firstly, the intrinsic mode functions are extracted using VMD followed by Fast Fourier Transform, and finally the status of bearing is analyzed to be faulty or impeccable. This paper, stress on VMD rather than on EMD, due to its qualities in the detection of close tone vibration signatures and takes less computation time.
Characterization of wireless accelerometer sensor and its industrial applications
(IEEE, 2014) Gupta, Karunesh Kumar
The basic idea of this paper is to characterize wireless MEMS capacitive accelerometer sensor based on their field of applications. The selection of accelerometers are difficult for certain applications, that demands the sensor to be mount on rotating platform, higher value of g, sensitivity, and wide bandwidth of operation. Whenever higher sensitivity is chosen, the short fall is in the range of g and the bandwidth of operation. This is a serious issue with the sensor as far as industrial applications i.e., ball mill and sag mills are concerned. There is a misconception of using higher value of g (approximately around 500 g) with lower sensitivity in ball mill that is justified in this paper. Generally, the internal frequency of vibration of the ball mill is unknown, and the vibration due to impact during grinding is also random due to non uniformity in the grinding action inside the mill. For such an application, random selection of sensors can mislead the data acquisition and interpretation process. The perplexity of the application demands the characterization of accelerometer, when they are mounted on rotating platform. In this paper the sensor is characterized in mechanical testing lab using lathe machine and later on the same sensor is subjected to measure vibration of the industrial ball mill. Further, the data is transmitted using Zigbee (IEEE 802.15.4), and the RF signal losses during rotation and transmission are also taken care to avoid the high frequency losses due to multiple reflections. Finally, the vibration signatures obtained during experimental phases are analyzed using Fast Fourier Transform (FFT) to characterize the sensor at different operating speeds of the lathe machine.
Comparative study between VMD and EMD in bearing fault diagnosis
(IEEE, 2014) Gupta, Karunesh Kumar
This paper proposes a novel Variational mode decomposition (VMD) algorithm for bearing fault diagnosis. The Fast Fourier Transform fails to analyse the transient and non-stationary signals. Discrete Fourier transform and Empirical mode decomposition do not have the ability to attain the accurate Intrinsic mode functions under dynamic system fault conditions because the characteristic of exponentially decaying dc offset is not consistent. EMD is a fully data-driven, not model-based, adaptive filtering procedure for extracting signal components. The EMD technique has high computational complexity and requires a large data series. The proposed technique has high accuracy and convergent speed, and is greatly appropriate for bearing fault diagnosis. This paper illustrates that VMD removes the exponentially decaying dc offset and evaluates its performance compared to EMD.
Comparative Study of Cepstral Editing and Unitary Sample Shifted Probability Distribution Function method for Bearing Fault Diagnosis
(Springer, 2020-05) Gupta, Karunesh Kumar
This paper presents a comparative study of cepstral editing and unitary sample shifted probability distribution function method used for bearing fault diagnosis. Traditionally, different signal processing techniques are employed for this application. This study compares recent methods including cepstral editing and unitary sample shifted Laplacian window method. The superiority of these methods under different conditions and fault types is discussed based on the squared envelope spectrum (SES) feature and kurtosis. It is concluded from this study that use of cepstral pre-whitening (CPW) before the unitary sample shifted Laplacian window method significantly improves the performance for the diagnosis of ball faults.
A Comparative Study of SIFT and SURF Algorithms under Different Object and Background Conditions
(IEEE, 2017) Gupta, Karunesh Kumar
Feature detection and feature matching have been essential parts of Computer Vision algorithms. Feature detection algorithms like Scale Invariant Feature Transform (SIFT) form the basis of every feature extraction algorithm proposed till date. Since SIFT was proposed, researchers are continuously exploring the possibilities with it. It is one of the most prominently used algorithm or feature matching because of its invariance to scale. One of the other widely used algorithm in Computer Vision is Speeded up Robust features (SURF). In this paper, SIFT and SURF algorithms are compared and analysed under different object and background conditions. The SIFT algorithm performs better than SURF under blur and illumination changes. It also holds true for two different images where one image is being subjected to such property changes. The SURF will always perform faster than SIFT.
A contrast enhancement technique for low light images
(AIP, 2016-03) Gupta, Karunesh Kumar
Digital Imagery systems are traditionally bad in low light conditions. In this paper, a new algorithm for contrast improvement is proposed. The algorithm consists of two stages. The first stage is decomposing the input image into four subbands by applying two-dimensional discrete wavelet transform and estimates the singular value matrix of sub band image. The second stage is that it reconstructs the enhanced image by applying the inverse DWT. The technique is compared with conventional image equalization technique such as standard General Histogram Equalization (GHE) and other state-of-the-art techniques such as Quadrant Dynamic Histogram Equalization (QDHE), Singular-Value-Wavelet based image Equalization (SVWE) and Singular Value Equalization (SVE) on the basis of their Peak Signal to Noise Ratio (PSNR) and Root Mean Square Error (RMSE) values. The simulation results indicated that the image contrast enhanced by the purposed method was higher than that of the images enhanced by the other conventional state-of-the-art techniques. REFERENCES
Cumulative Distribution Sharpness Profiling Based Bearing Fault Diagnosis Framework Under Variable Speed Conditions
(IEEE, 2021-07) Gupta, Karunesh Kumar
Vibration monitoring has been a reliable source of information for machine fault diagnosis. Several methods are available for bearing fault diagnosis under constant speed condition. A fault diagnosis framework consisting of a novel pre-processing tool, named cumulative distribution sharpness (CDS) profiling is proposed for variable speed conditions. We first provide evidences suggesting that the bearing fault signals follow Laplace distribution. Under the influence of Gaussian noise, however, the sharpness of the distribution decreases. This is helpful in separating the periodic fault and noise regions in the time-domain vibration signal by calculating local CDS values. The proposed CDS profiling (CDSP) is thus obtained by sweeping a window over the vibration signal and estimating the sharpness of cumulative distribution of such windowed signal. For changing noise variance, the monotonous and continuous nature of CDS is ensured to obtain a profile that retains the fault periodicity. A short-time Fourier transform of the CDSP is then calculated, followed by multiple time-frequency curves extraction (MTFCE). Two important fault features - Prominence and Compliance - are proposed in this paper. Finally, a fuzzy inference system is used to obtain diagnosis percentages from the features. Thus, the proposed method can classify the faults into healthy, inner race and outer race faults. The results are then validated on experimental data with variable operating speed. We show that prominence of the fault characteristic frequency improves due to CDSP. The accuracy of the proposed method is found to be better than the benchmark method of MTFCE.
Deep q-learning framework based solar energy generation prediction
(2022) Gupta, Karunesh Kumar
In the recent years, the power system market has seen a huge shift towards the utilisation of Renewable energy sources (RES) as candidates of power generation since they proved to be a great alternative of conventional sources due to its low carbon footprints and less dependency over fossil fuels, thereby increasing the penetration of RES in microgrids. RES sources like Wind, Tidal, Hydro, Solar etc. are widely available today, among which Solar is the most popular source of energy due to its cheap running cost and easy installation. However, Solar faces complications such as intermittency which is a very big drawback to its applicability and reliability thus requiring additional strategies to increase its resiliency. A short term forecasting of solar generation might be a great solution to observe the intermittency and predict the future generation based on various factors. In this research work a Deep Q-learning framework was proposed to predict the Solar Generation and provide predictive results for special months and days like Spring equinox, Summer Solstice, Autumn Equinox and Winter Solstice. The Deep Q-learning (DQNN) framework is an amalgamation of Deep Learning networks and Q-learning technique that exploits the properties of Deep Learning networks and Q-learning technique to map the state-Q-value pair and perform the prediction process. The simulations of DQN network was performed in an open-source platform known as Keras and the prediction results were compared both in simulated and experimental datasets with other well known Deep learning networks such as CNN, LSTM, GRU and CNN-LSTM.
Despeckle and Geographical Feature Extraction in SAR Images by Wavelet Transform
(Elsevier, 2007-12) Gupta, Karunesh Kumar; Gupta, Rajiv
This paper presents a method to despeckle Synthetic Aperture Radar (SAR) image, and then extract geographical features in it. In this research work, speckle is reduced by multiscale analysis in wavelet domain. In terms of geographical feature preservation the result shows that the method is better compared to spatial domain filters, such as Lee, Kuan, Frost, Ehfrost, Median, Gamma filters. The geographical features such as roads, airport runways, rivers and other ribbon-like shape structures are detected by the new wavelet-based method as proposed by Yuan Yan Tang. Experimental results show that the proposed method extracts geographical features of different width as well as different gray levels.
A detailed comparative analysis of automatic neural metrics for machine translation: bleurt & bertscore
(IEEE, 2025-04) Chamola, Vinay; Gupta, Karunesh Kumar
Bleurt a recently introduced metric that employs Bert, a potent pre-trained language model to assess how well candidate translations compare to a reference translation in the context of machine translation outputs. While traditional metrics like Bleu rely on lexical similarities, Bleurt leverages Bert's semantic and syntactic capabilities to provide more robust evaluation through complex text representations. However, studies have shown that Bert, despite its impressive performance in natural language processing tasks can sometimes deviate from human judgment, particularly in specific syntactic and semantic scenarios. Through systematic experimental analysis at the word level, including categorization of errors such as lexical mismatches, untranslated terms, and structural inconsistencies, we investigate how Bleurt handles various translation challenges. Our study addresses three central questions: What are the strengths and weaknesses of Bleurt, how do they align with Bert's known limitations, and how does it compare with the similar automatic neural metric for machine translation, BERTScore? Using manually annotated datasets that emphasize different error types and linguistic phenomena, we find that Bleurt excels at identifying nuanced differences between sentences with high overlap, an area where BERTScore shows limitations. Our systematic experiments, provide insights for their effective application in machine translation evaluation.
Detection of cadmium ion in aqueous medium by simultaneous measurement of piezoelectric and electrochemical responses
(Elsevier, 2018-09) Manjuladevi, V.; Gupta, Raj Kumar; Gupta, Karunesh Kumar
Cadmium is one of the important heavy metals which poses health hazards due to its consumption through potable water. Cadmium is known to form complexes with amine group and also it has good affinity towards carbon nanotubes. The octadecylamine functionalized single-walled carbon nanotubes (ODACNTs) can be employed for sensing cadmium ion in aqueous medium. A thin film of ODACNTs offers not only strong adsorption properties towards cadmium ion but also provides an enormous gain in surface to volume ratio, and good mechanical and chemical stability. Therefore, a sensing layer of ODACNTs was formed on the gold deposited quartz wafer and the sensing towards cadmium ion in the aqueous medium was performed. An experimental setup was designed to record the electrochemical and piezo-responses simultaneously. The piezo and electrochemical responses were found to be linear in the given concentration range. Interestingly, the piezoresponse modulates systematically and repeatedly from a maximum to minimum value due to voltage sweep during cyclic voltammetry indicating the interfacial phenomenon of adsorption and desorption.