Understanding the Inequalities in Child Health Status: State-Level Insights for Policy Intervention in India Bishweshwar Bhattacharjee, Bireshwar Bhattacharjee, Dibyojyoti Bhattacharjee, Santanu Choudhury International Journal of Social Determinants of Health and Health Services, 2026 The U.N. Sustainable Development Goals highlighted the importance of good health and healthy well-being (SDG 3). Child health is very important for achieving SDG 3; maintaining proper child health is essential for a developing country like India. Against this backdrop, assessing child health across various states is crucial. Thus, the study developed the composite child health index (CHI) using a novel technique for order preference by similarity to ideal solution (TOPSIS)-based, factor analytic multi-criteria decision-making (MCDM) approach. The index was developed using secondary data compiled from the National Family Health Survey from 2015 to 2020 using 35 child health indicators. Hierarchical and K-means were applied to categorize the various states and union territories based on their CHI values. This analysis reveals significant differences in child health outcomes across Indian states, with two states achieving higher levels and 25 states facing lower levels of child health. Among the states, Nagaland tops the list (CHI = 0.57441), indicating better child health conditions, followed by Odisha (CHI = 0.54384). The states with the lowest scores, Andhra Pradesh (CHI = 0.08406) and Manipur (CHI = 0.1065), have more significant challenges in child health. Thus, there is a need for targeted interventions in the most affected areas.
Colour, Texture and Geometric Feature Based Classification of Banana Varieties Using Interpretable Machine Learning Joy Deb, Dibyojyoti Bhattacharjee, Jayasree Chakrabarty Model Assisted Statistics and Applications, 2026 Non-destructive image-based classification of fruit varieties is essential for optimizing cost, nutritional benefits and supply chain management in food system. In this study we propose an interpretable machine learning framework for the multi-class classification of banana varieties using handcrafted image features extracted from colour, texture and geometric properties. A total of 195 banana images from five varieties were collected and expanded the dataset to 669 samples through rotational augmentation to enhance model generalization. Five supervised learning models, viz., k-Nearest Neighbours, Naïve Bayes, Random Forest, Decision Tree, and Support Vector Machine, were implemented using standard evaluation metrics. Among all models, Random Forest demonstrated the highest performance with an accuracy of 98.5 per cent and an MCC of 0.9814. Statistical validation was performed using one-way ANOVA and post-hoc Tukey HSD tests, which confirmed significant difference between model performances. Additionally, SHAP analysis provided insights into feature importance and model decision processes. The findings suggest ensemble learning models, especially Random Forest offer a compelling combination of accuracy and interpretability for agricultural classification tasks. The proposed approach enables applications in automated fruit sorting and mobile based advisory platform in smart agriculture.
Strategic Route Optimization for IPL Teams: Boosting Economic Significance Bireshwar Bhattacharjee, Bishweshwar Bhattacharjee, Dibyojyoti Bhattacharjee, Santanu Choudhury Management and Labour Studies, 2026 In recent years, professional sports leagues have evolved significantly, becoming major economic enterprises for lower-middle income countries through massive revenue generation, job creation and a boost to ancillary industries. Thus, optimizing an efficient travel route is crucial to minimizing the cost of travelling, travel time, travel fatigue, logistical costs and overall economic viability. Efficient route scheduling is a crucial aspect for effectively managing large-scale tournaments, professional events and logistics management. This research attempts to investigate the effectiveness of dynamic programming in scheduling a sports tournament. The usefulness of dynamic programming is demonstrated in the context of the Indian Premier League (IPL), a popular cricket league in India. The findings of this research revealed that travel time in IPL 2023 was reduced by approximately 32% to 47%, while the total travel cost was reduced by 24% to 55% using dynamic programming. These improvements definitely help players manage fatigue, assist organizers in logistic management and enable broadcasters to manage coverage logistics. Thus, the study finds that dynamic programming can effectively enhance the economic viability of various sporting events, such as cricket, football or other large-scale multi-location events.
Applications of higher order Markov models and Pressure Index to strategize controlled run chases in Twenty20 cricket Rhitankar Bandyopadhyay, Dibyojyoti Bhattacharjee International Journal of Sports Science and Coaching, 2026 In limited overs cricket, the team batting first posts a target score for the team batting second to achieve in order to win the match. The team batting second is constrained by decreasing resources in terms of number of balls left and number of wickets in hand in the process of reaching the target as the second innings progresses. The Pressure Index, a measure created by researchers in the past, serves as a tool for quantifying the level of pressure that a team batting second encounters in limited overs cricket. Through a ball-by-ball analysis of the second innings, it reveals how effectively the team batting second in a limited-over game proceeds towards their target. This research employs higher order Markov chains to examine the strategies employed by successful teams during run chases in Twenty20 matches. By studying the trends in successful run chases spanning over 16 years and utilizing a significant dataset of 6537 Twenty20 matches, specific strategies are identified. Consequently, an efficient approach to successful run chases in Twenty20 cricket is formulated, effectively limiting the Pressure Index to [ 0.5 , 3.5 ] or even further down under 0.5 as early as possible. The innovative methodology adopted in this research offers valuable insights for cricket teams looking to enhance their performance in run chases.
Quantifying defensive performance in football: A piecewise parametric survival approach to goal scoring time Anirban Dutta, Jonali Gogoi, Dibyojyoti Bhattacharjee, Hemanta Saikia International Journal of Sports Science and Coaching, 2025 To a significant extent, strategy deployment in sports has become data-driven. This has given rise to the application of data analytics in different sports, and football is no exception. This paper models the performance of selected national football teams, ranked among the highest in the FIFA standings as of June 2023, while playing against significantly lower-ranked opponents (minnows). When minnows play a relatively stronger team, their prime concern is not to concede a goal, thereby organising a deep defensive line, making it difficult for the more vigorous opposition to score. Thus, considering the time to the first goal scored by a stronger team as a time to an event, parametric survival analysis is applied in this study to compare the performance of stronger football teams against minnows. The study finds that the hazard function is neither a monotonic function nor a bathtub curve; instead, it takes a zig-zag form. This calls for a piecewise fitting of the survival distribution, which provides a better fit than any standard survival distribution proposed in the literature. By fitting such piecewise survival curves for each selected national side, one can identify sides that can better handle the minnows in football.
Forecasting the opening goal in second-half of a football match: Bayesian and frequentist perspectives Anirban Dutta, Hemanta Saikia, Jonali Gogoi, Dibyojyoti Bhattacharjee Computational Statistics, 2025 Predicting the timing of the first goal in the second half of a football match can offer valuable insights and strategic implications, as it can inform tactical adjustments at halftime based on first-half performance. This particular issue has not received much attention in sports analytics despite its significance. This study utilises survival analysis techniques to model the time-to-event of the opening goal after halftime using data from the Indian Super League (ISL), focusing on examining how a team’s first-half performance statistics impact their scoring timing in the second half. The extended Cox model revealed that the number of completed passes in the first half is a statistically significant factor that affects the timing of the initial second-half goal. In an effort to enhance the comprehensiveness of the analysis, the study then transits to the Bayesian proportional hazards model and the Bayesian Accelerated Failure Time (AFT) models. It was found that the number of corners and goal saves by the teams were significant indicators of the timing of the opening second-half goal. The unique aspect of this study lies in its innovative application of Bayesian survival modelling techniques to football-related data. A comparison of the models indicates that the Bayesian viewpoint exhibits superiority in this evaluation. Through the quantification of crucial in-game metrics on scoring trends post-halftime, this framework presents a valuable tool for sports analysts and coaches to assess strategic choices during crucial intervals of a match. Furthermore, the methodologies investigated have the potential for extension to other top-tier leagues and sports, paving the way for improved data-informed decision-making and intra-match analysis in professional sports.
An Improved Point System for Cricket’s World Test Championship Bireshwar Bhattacharjee, Dibyojyoti Bhattacharjee, Hemanta Saikia, Bishweshwar Bhattacharjee Management and Labour Studies, 2025 With the advent of formats of limited overs in cricket like the One Day and Twenty-20 Internationals, test cricket, the longest-running version of the game, has witnessed a significant decline in popularity. The World Test Championship (WTC) was launched in 2019 by the International Cricket Council to reignite interest in test cricket. However, the initial point distribution system devised for the inaugural WTC had several shortcomings, which include allocating points based on the outcome of the entire series rather than the number of test matches played, the absence of rewards for teams winning matches away from home, failing to take into consideration the margin of victory (MOV) and not accounting for the relative strength of competing teams. Considering these shortcomings, this article proposes a new point system, thus providing an alternative to the existing one. The point system uses the Elo rating system, including factors such as home-field advantage, impact of the toss and MOV. Statistical analyses were conducted to validate the home-field advantage and toss impact. Subsequently, the proposed model developed was named the points won per match system. The team rankings in the WTC are established based on this proposed model and compared with the actual one.
A Multi-Criteria Decision-Making Approach to Compare the Maternal Healthcare Status of Indian States: An Application of Data Science Statistics and Applications, 2024
Effect of fraction of demand backordered in inventory management while obtaining optimum order quantity and reorder point Songklanakarin Journal of Science and Technology, 2019
A new model for player selection in cricket Hemanta Saikia, Dibyojyoti Bhattacharjee, Unni Krishnan Radhakrishnan International Journal of Performance Analysis in Sport, 2017
A Bayesian approach to compare the statewise dengue death counts in India International Journal of Collaborative Research on Internal Medicine and Public Health, 2011
Awareness level of married couples on HIV/AIDS in northeast india - an empirical analysis International Journal of Collaborative Research on Internal Medicine and Public Health, 2010
