Intelligent system for occupational safety in retail sector

Funder

Organizational Unit

Publications

Integrated feature selection and classification algorithm in the prediction of work-related accidents in the retail sector: a comparative study

Publication . Sena, Inês; Lima, Laíres; Silva, Felipe G.; Braga, Ana Cristina; Novais, Paulo; Fernandes, Florbela P.; Pacheco, Maria F.; Vaz, Clara; Lima, José; Pereira, Ana I.

Assessing the different factors that contribute to accidents in the workplace is essential to ensure the safety and well-being of employees. Given the importance of risk identification in hazard prediction, this work proposes a comparative study between different feature selection techniques (χ2 test and Forward Feature Selection) combined with learning algorithms (Support Vector Machine, Random Forest, and Naive Bayes), both applied to a database of a leading company in the retail sector, in Portugal. The goal is to conclude which factors of each database have the most significant impact on the occurrence of accidents. Initial databases include accident records, ergonomic workplace analysis, hazard intervention and risk assessment, climate databases, and holiday records. Each method was evaluated based on its accuracy in the forecast of the occurrence of the accident. The results showed that the Forward Feature Selection-Random Forest pair performed better among the assessed combinations, considering the case study database. In addition, data from accident records and ergonomic workplace analysis have the largest number of features with the most significant predictive impact on accident prediction. Future studies will be carried out to evaluate factors from other databases that may have meaningful information for predicting accidents.

2022Conference paper

Open access

Exploring Features to Classify Occupational Accidents in the Retail Sector

Publication . Sena, Inês; Braga, Ana Cristina; Novais, Paulo; Fernandes, Florbela P.; Pacheco, Maria F.; Vaz, Clara B.; Lima, José; Pereira, Ana I.

The Machine Learning approach is used in several application domains, and its exploitation in predicting accidents in occupational safety is relatively recent. The present study aims to apply different Machine Learning algorithms for classifying the occurrence or nonoccurrence of accidents at work in the retail sector. The approach consists of obtaining an impact score for each store and work unit, considering two databases of a retail company, the preventive safety actions, and the action plans. Subsequently, each score is associated with the occurrence or non-occurrence of accidents during January and May 2023. Of the five classification algorithms applied, the Support Vector Machine was the one that obtained the best accuracy and precision values for the preventive safety actions. As for the set of actions plan, the Logistic Regression reached the best results in all calculated metrics. With this study, estimating the impact score of the study variables makes it possible to identify the occurrence of accidents at work in the retail sector with high precision and accuracy.

2024Conference paper

Open access

Predicting Retail Store Transaction Patterns: A Comparison of ARIMA and Machine Learning Models

Publication . Vaz, Clara B.; Sena, Inês; Braga, Ana Cristina; Novais, Paulo; Lima, José; Pereira, Ana I.

Retail transactions represent sales of consumer goods, or final goods, by consumer companies. This sector faces security challenges due to the hustle and bustle of sales, affecting employees’ workload. In this context, it is essential to estimate the number of customers who will appear in the store daily so that companies can dynamically adjust employee schedules, aligning workforce capacity with expected demand. This can be achieved by forecasting transactions using past observations and forecasting algorithms. This study aims to compare the ARIMA time series algorithm with several Machine Learning algorithms to predict the number of daily transactions in different store patterns, considering data variability. The study identifies four typical store patterns based on these criteria using daily transaction data between 2019 and 2023 from all retail stores of the leading company in Portugal. Due to data variability and the results obtained, the algorithm that presents the most minor errors in predicting daily transactions is selected for each store. This study’s ultimate goal is to fill the gap in forecasting daily customer transactions and present a suitable forecasting model to mitigate risks associated with transactions in retail stores.

2024Conference paper

Restricted access

Predicting the probability of occupational accidents occurrence in a Portuguese retail company

Publication . Sena, Inês; Silva, Felipe Gustavo Soares da; Braga, Ana Cristina; Fernandes, Florbela P.; Vaz, Clara B.; Pacheco, Maria F.; Novais, Paulo; Lima, José; Pereira, Ana I.

Workplace accidents are a global problem impacting companies and society, as employee well-being and productivity/profit can be affected. Portugal ranks fifth among European Union countries despite efforts to reduce their frequency. Predictive solutions have demonstrated promising results in several economic sectors, but the retail sector, the country's third-largest in accident records, remains unexplored. This study proposes a predictive model based on the Multilayer Perceptron (MLP) algorithm to calculate the probability of risk situations occurring in a retail company. Ten databases provided by the company were analyzed and combined into a single dataset using impact scores. The predictive model was developed to predict risk situations in all the company's stores throughout two working days, the current and the next, and the four working shifts. The predictive model was implemented and tested in an integrated system for nine months and achieved 92% accuracy and a 29% precision rate in identifying risk situations. It is concluded that this approach provides a practical solution to assist companies and occupational health and safety teams prevent and minimize workplace accidents, contributing to increased safety and well-being.

2025Journal article

Open access