Coleção de Artigos Acadêmicos
URI permanente para esta coleçãohttps://repositorio.insper.edu.br/handle/11224/3227
Navegar
17 resultados
Resultados da Pesquisa
Artigo Científico Quality Perception of São Paulo Transportation Services: A Sentiment Analysis of Citizens’ Satisfaction Regarding Bus Terminuses(2024) Beck, Donizete; Teixeira, Marco; Maróstica, Juliana; Ferasso, MarcosPurpose: To explore citizens’ satisfaction with all Bus Terminuses (BTs) in São Paulo City, Brazil. Method: This study performed a Sentiment Analysis of citizens' perception of 32 BTs of São Paulo, composed of 8,371 user comments on Google Maps. Originality/Relevance: This study highlights the role of Sentiment Analysis as an optimal tool for Stakeholder Analysis in the Urban Context. Findings: First, Sentiment Analysis is a valuable source for stakeholder oriented urban management. Second, sentiment Analysis provides detailed information about citizen satisfaction, providing valuable cues for urban managers to improve public service quality. Third, Smart Sustainable Cities can provide multiple and massive quantities of data that all kinds of urban stakeholders can use in decision-making processes, which helps perform Sentiment Analysis. Fourth, Sentiment Analysis is helpful for BT managers to improve BT services based on the users' feelings. Finally, further studies should explore sentiment classification in Sentiment Analysis of the critical aspects unfolded in this study as well as for exploring responsiveness of municipal public services. Methodological Contributions: This study demonstrated that Sentiment Analysis can be a method for scrutinizing stakeholders' opinions and perceptions about governmental services at the city level. Practitioner Contributions: Urban Planners, Transportation Policy Makers, and Urban Managers can use Sentiment Analysis to foster stakeholder-oriented management, which in turn fosters democracy and urban performance.Artigo Científico Validação de modelos de machine learning por experimentos estatísticos de campo(2024) Toaldo, Alexsandro; Vallim Filho, Arnaldo Rabello de Aguiar; Oyadomari, José Carlos Tiomatsu; Mendonça Neto, Octavio Ribeiro deObjetivo – Este artigo apresenta uma aplicação prática com o desenvolvimento de um experimento estatístico de campo em uma indústria de latas premium de alumínio nos Estados Unidos, visando validar estatisticamente resultados de modelos de machine learning (ML), previamente construídos. Metodologia: Usou-se conceitos de pesquisa intervencionista, que envolve experimentos de campo onde pesquisador e organização anfitriã atuam em conjunto buscando experimentar no sistema em estudo, e por meio da observação gerar conhecimento. Originalidade/Relevância: Sobre originalidade, não é frequente na literatura modelos de ML validados por experimento planejado de campo, seguido de análise estatística rigorosa. E a relevância da proposta se deve à sua contribuição para a literatura e pelas possibilidades de replicações do estudo em escala maior, na própria empresa ou em qualquer outra com desafios similares. Principais Resultados: Em fase anterior do estudo modelos de ML identificaram as variáveis de maior impacto em ineficiências (geração de sucata) em um processo de produção de latas de alumínio. Essas variáveis foram validadas nesta fase do estudo, através de experimento estatístico de campo, confirmando a significância estatística dos resultados do modelo de ML. Contribuições Teóricas e Práticas: A pesquisa contribui em termos práticos e científicos, pois a validação estatística de modelos de ML por experimentos planejados de campo é uma contribuição para a literatura de ciência aplicada, além de usas possibilidades práticas. Da mesma forma, apesar de amplamente utilizadas em diferentes áreas, pesquisas de cunho intervencionista ainda apresentam lacuna importante nas ciências sociais aplicadas, principalmente na gestão de processos industriais.Artigo Científico Role of Emerging Technologies in Accounting Information Systems for Achieving Strategic Flexibility through Decision-Making Performance: An Exploratory Study Based on North American and South American Firms(2023) Yoshikuni, Adilson Carlos; Dwivedi, Rajeev; Dultra-de-Lima, Ronaldo Gomes; Parisi, Claudio; Oyadomari , José Carlos TiomatsuNowadays, accounting departments highly rely on accounting information systems to make decisions based on current, updated, and contemporary data. And, most accounting practices can be enhanced by emerging technologies coupled with accounting information systems. Therefore, contemporary accounting information systems (AIS) coupled with emerging technologies is the highest priority in organizations to make decisions that can contribute to strategic flexibility and performance of the organizations. The objective of the study is to identify the role of information systems infrastructure integration (ISII) on strategic flexibility and innovation (SFI) through the mediated role of information systems (IS)-enabled strategic enterprise management (IS-SEM) practices and decision-making performance (DMP). The study is based on contemporary literature in the field of emerging Technologies in accounting information systems particularly business intelligence and analytics (BI &A). Resource-based view had been applied to create novel constructs to test the research framework and hypothesis. The research framework and hypothesis are tested based on 388 organizations from Brazil and USA. The results reflect that information systems infrastructure integration impacts strategic flexibility and innovations in organizations. Further, there is no difference observed between North American and South American organizations. The results of the research suggest that accounting information systems (AIS) practitioners and researchers should look beyond emerging technologies investments and shift their attention to how information systems infrastructure integration (ISII) and information systems-enabled strategic enterprise management (IS-SEM) practices can leverage decision-making performance (DMP) and impact on strategic flexibility and innovation.Artigo Científico Audiovisual interactive artwork via web-deployed software: Motus composes Homino-idea(2022) Amstalden, Augusto Piato; TIAGO FERNANDES TAVARES; Costa Neto, Anésio Azevedo; Camarini, Giovana CardiMany art installations rely on camera-based audiovisual interactions, and this commonly requires specialized hardware and software. Consequently, audiovisual installations are usually restricted to wealthier areas, in which the specialized equipment can be afforded and properly hosted. In countries with an evident income unbalance linked to location, the geographic restriction leads to an audience restriction. In this work, we present the development of a web-deployed composition tool for audiovisual interactions that runs on the client side and does not require installing any additional software. Simultaneously, it provides visual feedback that can aid the audience to understand the experience. Consequently, the tool can be used to compose audiovisual interactions that reach a large audience via web. We further explore the tool by composing the audiovisual installation Homino-idea. The installation is inspired by the interactions between humans and the environment, and can be either shown in art venues or used online.Artigo Científico A multi-sensor human gait dataset captured through an optical system and inertial measurement units(2022) Santos, Geise; Wanderley, Marcelo; TIAGO FERNANDES TAVARES; Rocha, AndersonDiferent technologies can acquire data for gait analysis, such as optical systems and inertial measurement units (IMUs). Each technology has its drawbacks and advantages, ftting best to particular applications. The presented multi-sensor human gait dataset comprises synchronized inertial and optical motion data from 25 participants free of lower-limb injuries, aged between 18 and 47 years. A smartphone and a custom micro-controlled device with an IMU were attached to one of the participant’s legs to capture accelerometer and gyroscope data, and 42 refexive markers were taped over the whole body to record three-dimensional trajectories. The trajectories and inertial measurements were simultaneously recorded and synchronized. Participants were instructed to walk on a straight-level walkway at their normal pace. Ten trials for each participant were recorded and pre processed in each of two sessions, performed on diferent days. This dataset supports the comparison of gait parameters and properties of inertial and optical capture systems, whereas allows the study of gait characteristics specifc for each system.Artigo Científico Reliability and generalization of gait biometrics using 3D inertial sensor data and 3D optical system trajectories(2022) Santos, Geise; TIAGO FERNANDES TAVARES; Rocha, AndersonParticularities in the individuals’ style of walking have been explored for at least three decades as a biometric trait, empowering the automatic gait recognition feld. Whereas gait recognition works usually focus on improving end-to-end performance measures, this work aims at understanding which individuals’ traces are more relevant to improve subjects’ separability. For such, a manifold projection technique and a multi-sensor gait dataset were adopted to investigate the impact of each data source characteristics on this separability. Assessments have shown it is hard to distinguish individuals based only on their walking patterns in a subject-based identifcation scenario. In this setup, the subjects’ separability is more related to their physical characteristics than their movements related to gait cycles and biomechanical events. However, this study’s results also points to the feasibility of learning identity characteristics from individuals’ walking patterns learned from similarities and diferences between subjects in a verifcation setup. The explorations concluded that periodic components occurring in frequencies between 6 and 10 Hz are more signifcant for learning these patterns than events and other biomechanical movements related to the gait cycle, as usually explored in the literature.Artigo Científico DSSE: An environment for simulation of reinforcement learning-empowered drone swarm maritime search and rescue missions(2024) Falcão, Renato Laffranchi; Oliveira, Jorás Custódio Campos de; Andrade, Pedro Henrique Britto Aragão; Rodrigues, Ricardo Ribeiro; FABRÍCIO JAILSON BARTH; Brancalion, José Fernando BassoArtigo Científico Proposição e validação de ferramenta de avaliação da desnutrição hospitalar, com base no Global Leadership Initiative on Malnutrition: protocolo do Estudo GLIM-BR(2022) Lopes, Giovanna Guimarães; Piovacari, Silvia Maria Fraga; Pereira, Adriano José; ANDRE FILIPE DE MORAES BATISTAIntrodução: O consenso do Global Leadership Initiative on Malnutrition (GLIM) publicou uma proposta de diretrizes para estruturação de uma ferramenta, composta por critérios diagnósticos fenotípicos e etiológicos. Posteriormente, foi publicado o Guia de Validação do GLIM, que visa estimular e direcionar iniciativas de validação desta nova ferramenta. O objetivo deste artigo é compartilhar o protocolo do Estudo GLIM-BR, em andamento, o qual irá propor e validar um novo instrumento nacional de classificação diagnóstica de desnutrição hospitalar baseado no GLIM, utilizando desfechos clínicos. Método: Estudo de validação prospectivo observacional multicêntrico, dividido em 3 fases, realizado em 4 hospitais brasileiros terciários, com pacientes internados e com expectativa de permanência maior que 48h. Modelos preditivos baseados em aprendizado de máquina/inteligência artificial serão utilizados na definição do conjunto ótimo de variáveis e cutoffs capazes de predizer desfechos clínicos, como óbito e tempo de permanência. Resultados: Na fase 1, das 12 variáveis apresentadas e discutidas no painel de opinião de especialistas, 8 tiveram aprovação sem alteração. As demais variáveis foram ajustadas por meio do consenso Grupo GLIM-BR. Todas as variáveis foram escolhidas com base na literatura atual (racional teórico) e utilizando, sempre que possível, outras ferramentas já validadas. A Fase 2 já possui resultados preliminares (subestudo) apresentados em Congresso internacional (ESPEN) e que serão submetidos para publicação em periódico científico internacional nos próximos meses. A Fase 3 está em curso e as variáveis de interesse selecionadas para serem avaliadas pelo modelo preditivo do estudo GLIM-BR, em cada uma das categorias propostas pelo GLIM, estão divulgadas neste artigo, juntamente com detalhes do protocolo de pesquisa em curso. Conclusão: Almeja-se desenvolver uma ferramenta validada para diagnóstico da desnutrição hospitalar, que contorne limitações identificadas em ferramentas de avaliação nutricional vigentes, prática e pronta para uso pela comunidade de nutricionistas nos serviços hospitalares.Artigo Científico Early identification of older individuals at risk of mobility decline with machine learning(2022) Nascimento, Carla Ferreira do; ANDRE FILIPE DE MORAES BATISTA; Duarte, Yeda Aparecida Oliveira; Chiavegatto Filho, Alexandre Dias PortoBackground: : The early identification of individuals at risk of mobility decline can improve targeted strategies of prevention. Aims: : To evaluate the predictive performance of machine learning (ML) algorithms in identifying older in dividuals at risk of future mobility decline. Methods: : We used data from the SABE Study (Health, Well-being and Aging Study), a representative sample of people aged 60 years and more, living in the Municipality of São Paulo, Brazil. Mobility decline was assessed 5 years after admission in the study by self-reported difficulty to walk a block, climb steps, being able to stoop, crouch and kneel, or lifting or carrying weights greater than 5 kg. Popular machine learning algorithms were trained in 70% of the sample with 10-fold cross-validation, and predictive performance metrics were obtained from applying the trained algorithms to the other 30% (test set). Results: : Of the 1,615 individuals, 48% developed difficulty in at least one of the four tasks, 32% in stooping, crouching and kneeling, and 30% in carrying weights. The random forest algorithm had the best predictive performance for most outcomes. The tasks that the algorithm was able to predict with better performance were crouching and kneeling (AUC-ROC: 0.81[0.76–0.85]), and lifting or carrying weights (AUC-ROC: 0.80 [0.75–0.84]). Age was the most important variable for the algorithms, followed by education and back pain, according to the SHAP (SHapley Additive exPlanations) values. Conclusion: : Applications of ML algorithms are a promising tool to identify older patients at risk of mobility decline, with the potential of improving targeted preventive programs.Artigo Científico Physician preference for receiving machine learning predictive results: A cross-sectional multicentric study(2022) Wichmann, Roberta Moreira; Fagundes, Thales Pardini; Oliveira, Tiago Almeida de; ANDRE FILIPE DE MORAES BATISTA; Chiavegatto Filho, Alexandre Dias PortoArtificial intelligence (AI) algorithms are transforming several areas of the digital world and are increasingly being applied in healthcare. Mobile apps based on predictive machine learning models have the potential to improve health outcomes, but there is still no consensus on how to inform doctors about their results. The aim of this study was to investigate how healthcare professionals prefer to receive predictions generated by machine learning algorithms. A systematic search in MEDLINE, via PubMed, EMBASE and Web of Science was first performed. We developed a mobile app, RandomIA, to predict the occurrence of clinical outcomes, initially for COVID-19 and later expected to be expanded to other diseases. A questionnaire called System Usability Scale (SUS) was selected to assess the usability of the mobile app. A total of 69 doctors from the five regions of Brazil tested RandomIA and evaluated three different ways to visualize the predictions. For prognostic outcomes (mechanical ventilation, admission to an intensive care unit, and death), most doctors (62.9%) preferred a more complex visualization, represented by a bar graph with three categories (low, medium, and high probability) and a probability density graph for each outcome. For the diagnostic prediction of COVID-19, there was also a majority preference (65.4%) for the same option. Our results indicate that doctors could be more inclined to prefer receiving detailed results from predictive machine learning algorithms.