Nippon Datta

Nippon Datta

Auto-generated profile, based on publicly available information

Nippon Datta

Department of Computer Science and Engineering, Chittagong University of Engineering and Technology, Chittagong, Bangladesh

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
11 October 2024 in IEEE Access
Verified
Journal Article
Open access
Tanjim MahmudTanjim Mahmud
Tanjim Mahmud
NDNippon Datta
Nippon Datta
RCRishita Chakma
Rishita Chakma
UDUtpol Kanti Das
Utpol Kanti Das
MAMohammad Tarek Aziz
Mohammad Tarek Aziz
Karl AnderssonKarl Andersson
Karl Andersson
Objectives: The agricultural sector in many South Asian countries, including Bangladesh and India, plays a pivotal role in the economy, with a significant portion of the population dependent on it for livelihood. However, farmers often encounter challenges such as unpredictable weather conditions, soil variability, and natural disasters like floods and erosion, leading to substantial crop losses and financial strain. Despite government subsidies, many farmers struggle to sustain their livelihoods, resulting in a decline in interest in agriculture. Our focus lies on predicting the classification of various crops, including rice, jute, maize, and others, based on a combination of soil and weather features. Soil features, including Nitrogen, Phosphorus, Potassium, and pH levels, along with weather variables such as Temperature, Humidity, and Rainfall, are utilized as inputs for the predictive model. Methods: In this study, we address the critical issue of crop prediction by leveraging advanced machine-learning techniques and integrating genetic algorithms into the predictive model. Our proposed approach employs a hybrid methodology, where a Genetic Algorithm is utilized to optimize the hyperparameters of the model, enhancing its performance and robustness. Specifically, we employ a Random Forest classifier, a powerful ensemble learning technique, to classify the class labels associated with 22 different types of crops. Findings: The model’s accuracy is evaluated extensively, demonstrating a remarkable accuracy rate of 99.3%. Additionally, we utilized Local Interpretable Model-agnostic Explaination(LIME) and SHapley Additive exPlanations(SHAP) Explainable AI (XAI) methods to interpret and validate the model’s predictions. Novelty: The study presents a unique method for crop prediction that combines machine learning (ML) with genetic algorithms (GAs). The goal of this integration is to improve crop forecast models’ interpretability and accuracy. Due to the nature of local approximation LIME may yield contradictory answers. On the other hand, for sophisticated models and extensive datasets, SHAP can be computationally costly. By improving feature selection and model parameters, the integration of GAs with ML models overcomes these drawbacks and produces predictions that are more reliable and accurate. The high accuracy achieved by our system underscores its potential to mitigate crop losses and enhance agricultural productivity, thereby contributing to the sustainability and prosperity of the agricultural sector in any country.

21 November 2025 in Expert Systems with Applications
Verified
Journal Article
Closed access
MDMithun Dutta
Mithun Dutta
UDUtpol Kanti Das
Utpol Kanti Das
NDNippon Datta
Nippon Datta
JDJugal Krishna Das
Jugal Krishna Das