Loading...
13 results
Search Results
Now showing 1 - 10 of 13
- Predicting Retail Store Transaction Patterns: A Comparison of ARIMA and Machine Learning ModelsPublication . 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.
- Trends identification in medical carePublication . Sena, Inês; Pereira, Ana I.Daily health professionals are sought out by patients, motivated by the desire to stay healthy, making numerous diagnoses that can be wrong for various reasons. In order to reduce diagnostic errors, an application was developed to support health professionals, assisting them in diagnoses, assigning a second diagnostic opinion. The application, called ProSmartHealth, is based on intelligent algorithms to identify clusters and patterns in human symptoms. ProSmartHealth uses the classification algorithm, Support Vector Machine, to train and test diagnostic suggestions. This report aims to study the reliability of the application, using two strategies. First, to study the influence of data pre-processing, that is, if the accuracy improves when the data is processed before. The second strategy intends to study whether the number of training data influences accuracy. This study concludes that the use of a database with data pre-processing, and the number of training data used to train the model, influence the accuracy of the model, by improving application accuracy in eight percent.
- Occupational behaviour study in the retail sectorPublication . Sena, Inês; Fernandes, Florbela P.; Pacheco, Maria F.; Pires, Abel A.C.; Maia, Jaime P.; Pereira, Ana I.The health, safety, and well-being of employees, service providers, and customers are important priorities for retail companies. Based on this principle, an intelligent system that contributes to the reduction of accidents at work will be developed, monitoring risk control, preventing work-related illnesses, promoting a culture of zero accidents, and seeking to ensure the health of employees, customers, and stakeholders. In order to achieve such goals, it is necessary to determine the local and global variables (internal and external) that feed the system. This study comprises the first strategy applied to collect the local variables involved in the problem. To obtain this, a data analysis study in a retail store was performed. Data analysis procedures were performed namely clustering analysis with algorithm k-means, correlation procedures, like Pearson coefficient and matrix of correlation, and relationship analysis with parallel coordinate graphs. From the preliminary results, it is possible to indicate a set of local variables that have influence in the occupational behavior and accidents at work.
- ProSmartHealth: uma ferramenta de decisãoPublication . Sena, Inês; Pereira, Ana I.A segurança do paciente constitui um dos grandes desafios dos cuidados de saúde do século XXI. Deste modo um fator importante para estabelecer diagnósticos clínicos e prevenção de erros é a comunicação médico-doente. Diariamente os profissionais de saúde são procurados por pacientes, motivados pela vontade de permanecer saudável, realizando inúmeros diagnósticos que podem estar errados por diversos motivos. O objetivo principal desta dissertação é desenvolver uma aplicação com o intuito de evitar erros no diagnóstico médico, auxiliando assim os profissionais de saúde nos procedimentos de diagnóstico. A aplicação ProSmartHealth é baseada em treinar e testar um procedimento de aprendizagem com o conjunto de dados de saúde para identificar clusters e padrões nos sintomas humanos. No início terá um questionário integrado, onde os profissionais de saúde preenchem perguntas chave com os resultados dos pacientes e, no final, a aplicação indicará uma sugestão de diagnóstico. Até agora, a ProSmartHealth considera o diagnóstico associado a doença cardíaca, cancro da mama e demência. A ProSmartHealth utiliza o algoritmo de classificação Support Vector Machine, do Supervised Learning, para treinar e testar as sugestões de diagnóstico. Neste estudo obteve-se uma precisão média de 84% na identificação das doenças estudadas.
- Data analysis of workplace accidents - a case studyPublication . Sena, Inês; Braun, João; Pereira, Ana I.The welfare and safety of the employees of an enterprise is a great concern and priority in a responsible and successful organization. The identification of patterns of work-related accidents is important to reduce and prevent further mishaps and injuries. To improve the safety of the work environment, accidents related data must be analyzed to identify the possible risk factors and their effects on the type of accident and its level of severity. Thus, data related to workplace accidents in fishmonger stores were collected from a Portuguese retail company where it was analyzed with statistical, clustering, and classification techniques to identify potential underlying correlation and patterns between the data, and in this way, collecting important information to prevent future accident or lesions.
- Occupational behaviour study in the retail sectorPublication . Sena, Inês; Fernandes, Florbela P.; Pacheco, Maria F.; Pires, Abel A.C.; Maia, Jaime P.; Pereira, Ana I.The health, safety, and well-being of employees, service providers, and customers are important priorities for retail companies. Based on this principle, an intelligent system that contributes to the reduction of accidents at work will be developed, monitoring risk control, preventing work-related illnesses, promoting a culture of zero accidents, and seeking to ensure the health of employees, customers, and stakeholders. In order to achieve such goals, it is necessary to determine the local and global variables (internal and external) that feed the system. This study comprises the first strategy applied to collect the local variables involved in the problem. To obtain this, a data analysis study in a retail store was performed. Data analysis procedures were performed namely clustering analysis with algorithm k-means, correlation procedures, like Pearson coefficient and matrix of correlation, and relationship analysis with parallel coordinate graphs. From the preliminary results, it is possible to indicate a set of local variables that have influence in the occupational behavior and accidents at work.
- Learning mechatronics in the MacGyver wayPublication . Coelho, João Paulo; Seixas, InêsThis paper describes a pedagogical methodology used at the Polytechnic Institute of Bragança, in the mechatronics curricular unit of the master’s degree in Industrial Engineering. In order to promote out-of-the-box thinking, a contest was organised where students should use recycled and repurposed materials to build a vehicle that could be used in a hypothetical rescue scenario. By preventing the use of off-the-shelf solutions, creativity and ingenuity in engineering problem solving are promoted. Obtained results suggest that, in the vast majority, students adhere end embrace such a challenge with motivation and enthusiasm. By addressing the mechatronics learning outcomes from a gamification point-of-view, students were able to grasp, in a practical context, key concepts in this curricular unit that would, otherwise, be less evident.
- Clustering analysis – A case studyPublication . Sena, Inês; Mendes, João; Fernandes, Florbela P.; Pacheco, Maria F.; Vaz, Clara B.; Pires, Abel A.C.; Maia, Jaime P.; Pereira, Ana I.In retail sector there is a high number of work accidents causing economic losses, musculoskeletal injuries, among other prob-lems. To avoid future injuries and accidents, it is essential to develop intelligent systems to minimize the risk of accidents, providing a zero accidents culture in these sectors. This work concentrates efforts to highlight the importance of employees’ personal and professional characteristics in preventing accidents, as well as the need to study several stores with different characteristics. Thus, a questionnaire was developed and implemented in two different stores to collect responses. The collected data will be analyzed using the k-means algorithm using Matlab software.
- Integrated feature selection and classification algorithm in the prediction of work-related accidents in the retail sector: a comparative studyPublication . 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.
- External climate data extraction using the forward feature selection method in the context of occupational safetyPublication . Silva, Felipe G.; Sena, Inês; Lima, Laíres; Fernandes, Florbela P.; Pacheco, Maria F.; Vaz, Clara B.; Lima, José; Pereira, Ana I.Global climate changes and the increase in average temperatures are some of the major contemporary problems that have not been considered in the context of external factors to increase accident risk. Studies that include climate information as a safety parameter in machine learning models designed to predict the occurrence of accidents are not usual. This study aims to create a dataset with the most relevant climatic elements, to get better predictions. The results will be applied in future studies to correlate with the accident history in a retail sector company to understand its impact on accident risk. The information was collected from the National Oceanic and Atmospheric Administration (NOAA) climate database and computed by a wrapper method to ensure the selection of the most features. The main goal is to retain all the features in the dataset without causing significant negative impacts on the prediction score.