RESUMO
Automatic algorithm configuration (AAC) is becoming a key ingredient in the design of high-performance solvers for challenging optimisation problems. However, most existing work on AAC deals with configuration procedures that optimise a single performance metric of a given, single-objective algorithm. Of course, these configurators can also be used to optimise the performance of multi-objective algorithms, as measured by a single performance indicator. In this work, we demonstrate that better results can be obtained by using a native, multi-objective algorithm configuration procedure. Specifically, we compare three AAC approaches: one considering only the hypervolume indicator, a second optimising the weighted sum of hypervolume and spread, and a third that simultaneously optimises these complementary indicators, using a genuinely multi-objective approach. We assess these approaches by applying them to a highly-parametric local search framework for two widely studied multi-objective optimisation problems, the bi-objective permutation flowshop and travelling salesman problems. Our results show that multi-objective algorithms are indeed best configured using a multi-objective configurator.
Assuntos
Algoritmos , Simulação por Computador , Armazenamento e Recuperação da Informação/métodos , Modelos Teóricos , Reconhecimento Automatizado de Padrão/métodos , Resolução de Problemas , HumanosRESUMO
Mandarine Academy is an Ed-Tech company that specializes in innovative corporate training techniques such as personalized Massive Open Online Courses (MOOCs), web conferences, etc. With more than 550K users spread across 100 active e-learning platforms. The company creates online pedagogical content (videos, quizzes, documents, etc.) on daily basis to support the digitization of work environments and to keep up with current trends. Mandarine Academy provided us with access to Mooc.office365-training.com. A publicly available MOOC in both French and English versions to conduct research on recommender systems in online learning environments. Mandarine Academy collects user feedback using two types of ratings: Explicit (Like Button, Social share, Bookmarks), and Implicit (Watch Time, Page View). Unfortunately, explicit ratings are underutilized. Most users avoid the burden of stating their preferences explicitly. To address this, we shift our attention to implicit interactions, which generate more data that can be significant in some cases. Implicit Ratings are what constitute Mandarine Academy Recommender System (MARS) Dataset. We believe that the degree of viewing has an impact on the overall impression, for this reason, we applied changes to the implicit data and made a part of it similar to the explicit rating format found in other known datasets (e.g., Movielens). This paper presents two real-world dataset variations that consist of 89,000 explicit ratings and 276,000 implicit ratings. Data was collected starting early 2016 until late 2021. Chosen users had rated at least one item. To protect their privacy, sensitive information has been removed. To the best of our knowledge, this is the first publicly available real-world dataset of E-Learning recommendations in both French and English with mixed ratings (implicit and explicit), allowing the research community to focus on pre-and post-COVID-19 behavior in online learning.
RESUMO
Emergency department (ED) overcrowding is an ongoing problem worldwide. Scoring systems are available for the detection of this problem. This study aims to combine a model that allows the detection and management of overcrowding. Therefore, it is crucial to implement a system that can reason model, rank ED resources and ED performance indicators based on environmental factors. Thus, we propose in this paper a new domain ontology (EDOMO) based on a new overcrowding estimation score (OES) to detect critical situations, specify the level of overcrowding and propose solutions to deal with these situations. Our approach is based on a real database created during more than four years from the Lille University Hospital Center (LUHC) in France. The resulting ontology is capable of modeling complete domain knowledge to enable semantic reasoning based on SWRL rules. The evaluation results show that the EDOMO is complete that can enhance the functioning of the ED.
Assuntos
Aglomeração , Serviço Hospitalar de Emergência , França , Hospitais Universitários , HumanosRESUMO
BACKGROUND: Multi-drug resistant (MDR) bacteria are a major health concern. In this retrospective study, a rule-based classification algorithm, MOCA-I (Multi-Objective Classification Algorithm for Imbalanced data) is used to identify hospitalized patients at risk of testing positive for multidrug-resistant (MDR) bacteria, including Methicillin-resistant Staphylococcus aureus (MRSA), before or during their stay. METHODS: Applied to a data set of 48,945 hospital stays (including known cases of carriage) with up to 16,325 attributes per stay, MOCA-I generated alert rules for risk of carriage or infection. A risk score was then computed from each stay according to the triggered rules.Recall and precision curves were plotted. RESULTS: The classification can be focused on specifically detecting high risk of having a positive test, or identifying large numbers of at-risk patients by modulating the risk score cut-off level. For a risk score above 0.85,recall (sensitivity) is 62 % with 69 % precision (confidence) for MDR bacteria, recall is 58 % with 88 % precision for MRSA. In addition, MOCA-I identifies 38 and 21 cases of previously unknown MDR and MRSA respectively. CONCLUSIONS: MOCA-I generates medically pertinent alert rules. This classification algorithm can be used to detect patients with high risk of testing positive to MDR bacteria (including MRSA). Classification can be modulated by appropriately setting the risk score cut-off level to favor specific detection of small numbers of patients at very high risk or identification of large numbers of patients at risk. MOCA-I can thus contribute to more adapted treatments and preventive measures from admission, depending on the clinical setting or management strategy.