Amrit Kumar Paul

Dr. Amrit Kumar Paul


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 January 2024 in Forecasting
Verified
Journal Article
Open access
PDF file
CTC. Tamilselvi
C. Tamilselvi
MYMd Yeasin
Md Yeasin
RPRanjit Kumar Paul
Ranjit Kumar Paul
APAmrit Kumar Paul
Amrit Kumar Paul
Denoising is an integral part of the data pre-processing pipeline that often works in conjunction with model development for enhancing the quality of data, improving model accuracy, preventing overfitting, and contributing to the overall robustness of predictive models. Algorithms based on a combination of wavelet with deep learning, machine learning, and stochastic model have been proposed. The denoised series are fitted with various benchmark models, including long short-term memory (LSTM), support vector regression (SVR), artificial neural network (ANN), and autoregressive integrated moving average (ARIMA) models. The effectiveness of a wavelet-based denoising approach was investigated on monthly wholesale price data for three major spices (turmeric, coriander, and cumin) for various markets in India. The predictive performance of these models is assessed using root mean square error (RMSE), mean absolute percentage error (MAPE), and mean absolute error (MAE). The wavelet LSTM model with Haar filter at level 6 emerged as a robust choice for accurate price predictions across all spices. It was found that the wavelet LSTM model had a significant gain in accuracy than the LSTM model by more than 30% across all accuracy metrics. The results clearly highlighted the efficacy of a wavelet-based denoising approach in enhancing the accuracy of price forecasting.

6 March 2024 in Neural Processing Letters
Verified
Journal Article
Open access
PDF file
SGSandip Garai
Sandip Garai
RPRanjit Kumar Paul
Ranjit Kumar Paul
MYMd Yeasin
Md Yeasin
APAmrit Kumar Paul
Amrit Kumar Paul
Accurate prediction of time series data is crucial for informed decision-making and economic development. However, predicting noisy time series data is a challenging task due to their irregularity and complex trends. In the past, several attempts have been made to model complex time series data using both stochastic and machine learning techniques. This study proposed a CEEMDAN-based hybrid machine learning algorithm combined with stochastic models to capture the volatility of weekly potato price in major markets of India. The smooth decomposed component is predicted using stochastic models, while the coarser components, selected using MARS, are fitted into two different machine learning algorithms. The final predictions for the original series are obtained using optimization techniques such as PSO. The performance of the proposed algorithm is measured using various metrics, and it is found that the optimization-based combination of models outperforms the individual counterparts. Overall, this study presents a promising approach to predict price series using a hybrid model combining stochastic and machine learning techniques, with feature selection and optimization techniques for improved performance.

27 April 2023 in Sustainability
Verified
Journal Article
Open access
PDF file
TSTarun Sharma
Tarun Sharma
TDT. K. Das
T. K. Das
PMPragati Pramanik Maity
Pragati Pramanik Maity
SBSunanda Biswas
Sunanda Biswas
SSSusama Sudhishri
Susama Sudhishri
NRNeelmani Rathi
Neelmani Rathi
Wheat is grown in an area totalling 31.1 million hectares in India. The North-western Indo-Gangetic Plains (IGP) constitutes the major share of area and production of wheat in India and is known as the wheat belt of India. However, sustaining wheat production under declining/lower resource-use efficiency in the existing rice–wheat cropping system has led to considerations about diversifying this system with a pigeon pea–wheat system (PWS) in the IGP of India. However, little or no information is available on the impact of CA-based PWS on weed dynamics, productivity, profitability, and resource-use efficiencies. Therefore, we studied these aspects in wheat under a long-term (~12 years) conservation agriculture (CA)-based PWS. Treatments were conventional till flatbed (CT), ZT permanent narrow beds (PNBR & PNB), broad beds (PBBR & PBB), and flat beds (PFBR & PFB) with and without residue (R) retention and different N levels (75% and 100% of the recommended N). The results showed that the Shannon–Weiner index and the Simpson dominance index were higher under the CA system in 2021–2022 than in 2010–2011 and 2015–2016, indicating a change in weed diversity over the period. Furthermore, the Sorensen similarity index showed that there was not much difference in weed diversity for 2010–2011. However, in 2015–2016 and 2021–2022 respectively, only 89% (0.89) and 62% (0.62) of weed species were common to both CT and CA systems, indicating a shift in weed species in the long-term CA system in 2021–2022. Residue retention and N dose decreased weed density at 30 days after sowing (DAS). All the CA-based (PFBR100N, PBBR100N, PNBR100N, PFBR75N, PBBR75N, and PNBR75N) treatments reduced the weed density and dry weight compared to CT at 30 DAS. Wheat grain yield and net returns increased by 11.6–14.9% and 19.4–23.8% over CT in CA treatments, of which PFBR100N and PBBR100N were superior. The PBBR100N and PBBR75N systems had water productivity significantly higher than CT. Residue retention in ZT permanent beds reduced energy productivity in CA than CT and no residue treatments. In the 12th year, CA with 75% N (PFBR75N, PBBR75N, PNBR75N) resulted in a higher partial factor productivity of N and total NPK applied. Contrast analysis showed that 75% N was comparable with 100% N on crop, water, and energy productivities and 75% N was superior to 100% N on partial factor productivity of N and total NPK. Thus, the permanent broad bed with residue and 100% N in the initial years and 75% N in later years can be adopted in the north-western IGP for better weed suppression, higher yield, profitability, and resource-use efficiency.

14 June 2022 in Agronomy
Verified
Journal Article
Open access
PDF file
RPRanjit Kumar Paul
Ranjit Kumar Paul
SVSengottaiyan Vennila
Sengottaiyan Vennila
MYMd Yeasin
Md Yeasin
SYSatish Kumar Yadav
Satish Kumar Yadav
SNShabistana Nisar
Shabistana Nisar
MPMathyam Prabhakar
Mathyam Prabhakar
Influence of weather variables on occurrence of spiders in pigeon pea across locations of seven agro-climatic zones of India was studied in addition to development of forecast models with their comparisons on performance. Considering the non-normal and nonlinear nature of time series data of spiders, non-parametric techniques were applied with developed algorithm based on combinations of wavelet–regression and wavelet–artificial neural network (ANN) models. Haar wavelet filter decomposed each of the series to extract the actual signal from the noisy data. Prediction accuracy of developed models, viz., multiple regression, wavelet–regression, and wavelet–ANN, tested using root mean square error (RMSE) and mean absolute percentage error (MAPE), indicated better performance of wavelet–ANN model. Diebold Mariano (DM) test also confirmed that the prediction accuracy of wavelet–ANN model, and hence its use to forecast spiders in conjunction with the values of pest–defender ratios, would not only reduce insecticidal sprays, but also add ecological and economic value to the integrated pest management of insects of pigeon pea.

24 March 2023 in Genes
Verified
Journal Article
Open access
PDF file
APAmrit Kumar Paul
Amrit Kumar Paul
HRHimadri Shekhar Roy
Himadri Shekhar Roy
RPRanjit Kumar Paul
Ranjit Kumar Paul
PKPrakash Kumar
Prakash Kumar
MYMd Yeasin
Md Yeasin
In plant and animal breeding, sometimes observations are not independently distributed. There may exist a correlated relationship between the observations. In the presence of highly correlated observations, the classical premise of independence between observations is violated. Plant and animal breeders are particularly interested to study the genetic components for different important traits. In general, for estimating heritability, a random component in the model must adhere to specific assumptions, such as random components, including errors, having a normal distribution, and being identically independently distributed. However, in many real-world situations, all of the assumptions are not fulfilled. In this study, correlated error structures are considered errors that are associated to estimate heritability for the full-sib model. The number of immediately preceding observations in an autoregressive series that are used to predict the value at the current observation is defined as the order of the autoregressive models. First-order and second-order autoregressive models i.e., AR(1) and AR(2) error structures, have been considered. In the case of the full-sib model, theoretical derivation of Expected Mean sum square (EMS) considering AR(1) structure has been obtained. A numerical explanation is provided for the derived EMS considering AR(1) structure. The predicted mean squares error (MSE) is obtained after including the AR(1) error structures in the model, and heritability is estimated using the resulting equations. It is noticed that correlated errors have a major influence on heritability estimation. Different correlation patterns, such as AR(1) and AR(2), can be inferred to change heritability estimates and MSE values. To attain better results, several combinations are offered for various scenarios.