Predictive modeling and analysis of air quality - Visualizing before and during COVID-19 scenarios

Quality air to breathe is the basic necessity for an individual and in recent times, emission from various sources caused by human activities has resulted in substantial degradation in the air quality. This work focuses to study the inadvertent effect of COVID-19 lockdown on air pollution. Pollutants' concentration before- and during- COVID-19 lockdown is captured to understand the variation in air quality. Firstly, multi-pollutant profiling using hierarchical cluster analysis of pollutants' concentration is performed that highlights the differences in the cluster compositions between before- and during-lockdown time periods. Results show that the particulate matter (PM₁₀ and PM_2.5) in air that formed the primary cluster before lock-down, came down to close similarity with other clusters during lockdown. Secondly, predicting air quality index (AQI) based on the forecasts of pollutants' concentration is performed using neural networks, support vector machine, decision tree, random forest, and boosting algorithms. The best-fitted models representing AQI is identified separately for before- and during-lockdown time periods based on its predictive power. While deterministic method reactively evaluates present AQI when current pollutants' concentration at a particular time and place are known, this study uses the best fitted data-driven model to determine future AQIs based on the forecasts of pollutant's concentration accurately (overall RMSE<0.1 for before lockdown scenario and <0.3 for during lockdown scenario). The study contributes to visualize the variation in pollutants' concentrations between the two scenarios. The results show that the reduced economic activities during lockdown period had led to the drop in concentration of PM₁₀ and PM_2.5 by 27% and 50% on an average. The findings of this study have practical and societal implications and serve as a reference mechanism for policymakers and governing bodies to revise their actions plans for regulating individual air pollutants in the atmospheric air.

Analytical modeling of quality parameters in casting process – learning-based approach

Purpose

Foundry produces cast metal components and parts for various industries and drives manufacturing excellence all over the world. Assuring quality of these components and parts is vital for the end product quality. The complexity in foundry operations increases with the complexity in designs, patterns and geometry and the quality parameters of the casting processes need to be monitored, evaluated and controlled to achieve expected quality levels.

Design/methodology/approach

The literature addresses quality improvement in foundry industry primarily focusing on surface roughness, mechanical properties, dimensional accuracy and defects in the cast parts and components which are often affected by numerous process variables. Primary data are collected from the experts working in sand and investment casting processes. The authors perform machine learning analysis of the data to model the quality parameters with appropriate process variables. Further, cluster analysis using k-means clustering method is performed to develop clusters of correlated process variables for sand and investment casting processes.

Findings

The authors identified primary process variables determining each quality parameter using machine learning approach. Quality parameters such as surface roughness, defects, mechanical properties and dimensional accuracy are represented by the identified sand-casting process variables accurately up to 83%, 83%, 100% and 83% and are represented by the identified investment-casting process variables accurately up to 100%, 67%, 67% and 100% respectively. Moreover, the prioritization of process variables in influencing the quality parameters is established which further helps the practitioners to monitor and control them within acceptable levels. Further the clusters of process variables help in analyzing their combined effect on quality parameters of casting products.

Originality/value

This study identified potential process variables and collected data from experts, researchers and practitioners on the effect of these on the quality aspects of cast products. While most of the previous studies focus on a very limited process variables for enhancing the quality characteristics of cast parts and components, this study represents each quality parameter as the function of influencing process variables which will enable the quality managers in Indian foundries to maintain capability and stability of casting processes. The models hence developed for both sand and investment casting for each quality parameter are validated with real life applications. Such studies are scarcely reported in the literature.

Managing the resource allocation for the COVID-19 pandemic in healthcare institutions: a pluralistic perspective

Purpose

As COVID-19 outbreak has created a global crisis, treating patients with minimum resources and traditional methods has become a hectic task. In this technological era, the rapid growth of coronavirus has affected the countries in lightspeed manner. Therefore, the present study proposes a model to analyse the resource allocation for the COVID-19 pandemic from a pluralistic perspective.

Design/methodology/approach

The present study has combined data analytics with the K-mean clustering and probability queueing theory (PQT) and analysed the evolution of COVID-19 all over the world from the data obtained from public repositories. By using K-mean clustering, partitioning of patients’ records along with their status of hospitalization can be mapped and clustered. After K-mean analysis, cluster functions are trained and modelled along with eigen vectors and eigen functions.

Findings

After successful iterative training, the model is programmed using R functions and given as input to Bayesian filter for predictive model analysis. Through the proposed model, disposal rate; PPE (personal protective equipment) utilization and recycle rate for different countries were calculated.

Research limitations/implications

Using probabilistic queueing theory and clustering, the study was able to predict the resource allocation for patients. Also, the study has tried to model the failure quotient ratio upon unsuccessful delivery rate in crisis condition.

Practical implications

The study has gathered epidemiological and clinical data from various government websites and research laboratories. Using these data, the study has identified the COVID-19 impact in various countries. Further, effective decision-making for resource allocation in pluralistic setting has being evaluated for the practitioner's reference.

Originality/value

Further, the proposed model is a two-stage approach for vulnerability mapping in a pandemic situation in a healthcare setting for resource allocation and utilization.

Industry 4.0: key findings and analysis from the literature arena

Purpose

In recent years, a new transformation known as Industry 4.0 has drawn much attention throughout the world, and numerous investigations have fundamentally looked into the uprising concept. However, few have concentrated on the literature review. Taking this as motivation, the authors endeavored to assess the different attributes of Industry 4.0. The paper aims to discuss these issues.

Design/methodology/approach

This review concentrated on linking the articles from different database and distinguishing the attributes of Industry 4.0. The authors assessed 85 articles from scholarly database and peer-reviewed journals on Industry 4.0 through the selection of the Mayring (2004) procedure. The examination included a four-advance process, in particular, material gathering, engaging investigation, classification of the choice and material assessment.

Findings

The study backs experts and readers to comprehend the spread of Industry 4.0 in various ventures. For academicians, this gives an extensive rundown of Industry 4.0 attributes. Besides, the writing review gives a chance to comprehend the idea of Industry 4.0 in detail. Further, the outcome aggregates the success factor, failure factor, business model, potential and difficulties in the context of Industry 4.0.

Research limitations/implications

Many areas such as supply chain, circular economy and healthcare have started exploring Industry 4.0. However, few specific cases have reported about it, and no generic model is found for real-time application.

Practical implications

The study serves as reference material for researchers and practitioners to understand the spread of Industry 4.0 and utilize the concept of Industry 4.0 for real-life application.

Originality/value

The study focuses on reporting the potential, challenges, business model and pre-requites of Industry 4.0.