Article
Computer Science, Software Engineering
Zikun Deng, Di Weng, Yuxuan Liang, Jie Bao, Yu Zheng, Tobias Schreck, Mingliang Xu, Yingcai Wu
Summary: The article introduces a visual analytics system called VisCas, which aims to mine and interpret cascading patterns in urban contexts. The system combines an inference model with interactive visualizations to empower analysts to infer and interpret latent cascading patterns. It addresses challenges in generalized pattern inference, implicit influence visualization, and multifaceted cascade analysis. The effectiveness of VisCas is demonstrated through case studies on real-world traffic congestion and air pollution datasets.
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
(2022)
Article
Physics, Multidisciplinary
Jie Zeng, Yong Xiong, Feiyang Liu, Junqing Ye, Jinjun Tang
Summary: Understanding the spatiotemporal characteristics of traffic congestion is crucial for generating effective traffic management and control strategies. This study uses large-scale taxi trajectory data to explore the patterns of traffic congestion. By combining map-matching techniques and complex network analysis, the study identifies traffic congestion, analyzes the influence of congestion, and reveals the role of each road segment in the propagation process. The findings suggest that traffic congestion exhibits typical local clustering structures and each community has unique traffic characteristics.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Ruiyu Zhou, Hong Chen, Hengrui Chen, Enze Liu, Shangjing Jiang
Summary: This study analyzed and predicted the traffic conditions within the Third Ring Road in Xi'an using GPS data and time series forecasting models. Suggestions for alleviating traffic congestion were provided, including accelerating urban traffic construction and prioritizing the development of public transportation.
Article
Chemistry, Analytical
Shiting Ding, Zhiheng Li, Kai Zhang, Feng Mao
Summary: This study selects representative sequential pattern mining algorithms and evaluates their performance on taxi trajectory data. The results demonstrate that contiguous constraint-based algorithms show good performance in terms of balanced RAM consumption and execution time.
Article
Chemistry, Analytical
Jongtae Lim, Songhee Park, Dojin Choi, Kyoungsoo Bok, Jaesoo Yoo
Summary: This paper proposes a machine-learning-based road speed prediction scheme that utilizes road environment data analysis. It accurately predicts both average road speed and rapidly changing road speeds by analyzing speed data from the target road and neighboring roads. It considers historical average speed data and events as weights for prediction and uses the LSTM algorithm for sequential data learning.
Article
Computer Science, Artificial Intelligence
Jingyuan Wang, Jiahao Ji, Zhe Jiang, Leilei Sun
Summary: Traffic flow prediction is a fundamental problem in spatiotemporal data mining. Existing studies mainly focus on data-driven approaches and fail to reveal the mechanisms of urban traffic. To address this, we propose the ST-PEF+ model, which applies field theory to interpret urban traffic mechanisms and combines it with data-driven deep learning. The model extracts potential energy fields (PEFs) based on grid-based traffic flow graphs and learns a spatiotemporal deep learning model to predict PEF dynamics, outperforming state-of-the-art baselines.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Environmental Studies
Xiaoxuan Wei, Yitian Ren, Liyin Shen, Tianheng Shu
Summary: This study explores the spatiotemporal pattern of traffic congestion in 77 large Chinese cities using real-time big data. The results show significant variations in traffic congestion performance among different cities on the same day of the week. Cities with advanced urban road networks and well-developed public transportation systems exhibit better traffic performance. Smaller cities with higher per capita road area and fewer vehicles also have smoother traffic congestion. The study provides valuable insights into the varied patterns of traffic congestion in urban China, and offers policy recommendations to alleviate congestion and improve urban well-being.
ENVIRONMENTAL IMPACT ASSESSMENT REVIEW
(2022)
Article
Transportation Science & Technology
Arman Ganji, Mingqian Zhang, Marianne Hatzopoulou
Summary: This study develops a new approach to estimate Annual Average Daily Traffic (AADT) across all roads in an urban area using vehicle detection from aerial images. The method shows high prediction accuracy for daily traffic counts, but lower accuracy for predicting AADT, highlighting the importance of long-term data.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2022)
Article
Computer Science, Information Systems
Xiaojing Yao, Xufeng Jiang, Dacheng Wang, Lina Yang, Ling Peng, Tianhe Chi
Summary: This paper proposes an efficient maximal co-location mining algorithm with directed road-network constraints and spatial-continuity consideration (CMDS) for extracting useful spatial co-location patterns from urban service facilities efficiently and accurately.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Information Systems
Xuesong Wu, Mengyun Xu, Jie Fang, Xiongwei Wu
Summary: In this study, a multiattention tensor completion network (MATCN) is designed to model multidimensional representation for handling missing data. MATCN generates initial schemes through sparse sampling of historical fragments and a gated diffusion convolution layer to address exposure bias in previous models. The architecture utilizes a spatial signal propagation module and a temporal self-attention module to aggregate representations and extract dynamic dependencies at the spatiotemporal level. Experimental results demonstrate the superiority of MATCN over other models in handling complex missing data scenarios.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Environmental Studies
Juan Ignacio Guzman, Alina Karpunina, Constanza Araya, Patricio Faundez, Marcela Bocchetto, Rodolfo Camacho, Daniela Desormeaux, Juanita Galaz, Ingrid Garces, Willy Kracht, Gustavo Lagos, Isabel Marshall, Victor Perez, Javier Silva, Ignacio Toro, Alejandra Vial, Alejandra Wood
Summary: This study aims to assess the competitiveness of copper and lithium production in Chile from a sustainable perspective. The copper industry in Chile ranks third in the world sustainability ranking, while lithium ranks second, indicating room for improvement in sustainability measures such as effective stakeholder communication, knowledge dissemination, state mining policies, stability, sustainable quality branding, and human capital utilization.
Article
Geosciences, Multidisciplinary
Ines Belkacem, Ali Helali, Salah Khardi, Amani Chrouda, Khalifa Slimi
Summary: The human effects and environmental impacts of nanoparticles generated from road traffic have become a topic of concern. However, the knowledge about the influencing variables, monitoring instruments, and regulations for nanoparticles is still limited. This overview provides a comprehensive analysis of the existing knowledge, ongoing research, and emerging priorities in this field, including the sources, influencing parameters, measurement methodologies, and health implications of nanoparticles in road traffic atmosphere.
GEOSCIENCE FRONTIERS
(2022)
Article
Engineering, Civil
Yaochen Li, Haochuan Hou, Zikun Dong, Yujie Zang, Ying Zhang, Yonghong Song
Summary: This paper proposes a new framework for spatiotemporal analysis of static and dynamic traffic elements from road scenes. It applies a hierarchical approach combined with hidden conditional random fields (HCRF) to analyze the static traffic elements, and a lightweight multi-stream 3DCNN network for the behavior classification of dynamic traffic elements. Experimental results demonstrate the effectiveness of the proposed framework.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Green & Sustainable Science & Technology
Hrvoje Vdovic, Jurica Babic, Vedran Podobnik
Summary: The transportation sector significantly contributes to greenhouse gas emissions, and with the help of technology and data science, we can understand driving patterns that impact eco-efficiency. This paper proposes a framework for collecting and enriching automotive data to support interdisciplinary studies in environmental sustainability, automotive engineering, behavioural science, telecommunications, and transportation science.
JOURNAL OF CLEANER PRODUCTION
(2021)
Article
Multidisciplinary Sciences
Melita J. Giummarra, Ben Beck, Belinda J. Gabbe
Summary: The study focused on characterizing crash characteristics of road traffic collisions in Victoria, Australia, and examining the relationship between crash characteristics and fault attribution. Different types of road users show various safety risks in collisions, necessitating targeted engineering and infrastructure controls, as well as interventions targeting or accommodating human behavior.
Article
Environmental Sciences
Miguel G. Silva, Sara C. Madeira, Rui Henriques
Summary: This paper introduces the application of biclustering techniques to water consumption data analysis. By experimenting with data from a real-world water distribution system in Quinta do Lago, Portugal, the proposed approach demonstrates its potential and reliability in discovering consumption patterns.
Article
Green & Sustainable Science & Technology
Joao Tiago Aparicio, Elisabete Arsenio, Francisco C. Santos, Rui Henriques
Summary: This study aims to contribute to more sustainable mobility solutions by proposing robust and actionable methods to assess the resilience of a multimodal transport system. The relevance of the proposed methodology to detect actionable vulnerabilities is illustrated using a specific case study.
Article
Computer Science, Information Systems
Thomas James Tiam-Lee, Rui Henriques, Vasco Manquinho
Summary: Emergency medical services (EMS) worldwide need efficient resource allocation to respond to medical emergencies. This paper proposes DAPI, a tool for analyzing inefficiencies in emergency response datasets, which identifies potential bottlenecks based on ambulance response distribution and statistically assesses them with respect to dispatch station activity levels.
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2022)
Article
Transportation
Joao Tiago Aparicio, Elisabete Arsenio, Rui Henriques
Summary: This research paper proposes methods to assess the robustness of a multimodal transport network and compares them empirically using Lisbon's public transport as a case study. The study finds that methods relying on recalculating network metrics have a greater impact on the network's robustness assessment. Additionally, failures in stations are generally more dangerous than failures in pathways.
EUROPEAN TRANSPORT RESEARCH REVIEW
(2022)
Article
Biochemical Research Methods
Andreia S. Martins, Marta Gromicho, Susana Pinto, Mamede de Carvalho, Sara C. Madeira
Summary: This study proposes using itemset mining and sequential pattern mining to predict the need for non-invasive ventilation treatment in patients with amyotrophic lateral sclerosis. By analyzing static and longitudinal data, disease progression patterns and predictive model features are identified, providing insights for disease management and treatment.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2022)
Article
Computer Science, Interdisciplinary Applications
Diogo F. Soares, Rui Henriques, Marta Gromicho, Mamede de Carvalho, Sara C. Madeira
Summary: In this work, the authors propose a methodology to learn predictive models from static and temporal data by using discriminative patterns obtained via biclustering and triclustering as features within a state-of-the-art classifier. They applied this methodology to predict the need for non-invasive ventilation in patients with ALS, and the results showed an improvement compared to baseline results. Additionally, the bicluster/tricluster-based patterns used by the classifier can provide relevant prognostic information for clinicians.
JOURNAL OF BIOMEDICAL INFORMATICS
(2022)
Article
Energy & Fuels
Marco G. Pinheiro, Sara C. Madeira, Alexandre P. Francisco
Summary: Energy forecasting is crucial for the utility industry, covering a wide range of prediction problems. Short-term load forecasting plays a vital role in network management and planning, addressing challenges in the energy transition. This study proposes a systematic approach considering model performance, applicability, interpretability, and reproducibility, achieving significant improvements compared to benchmark models.
Article
Chemistry, Analytical
Joana Barreto, Rui Henriques, Silvia Cabral, Bruno Pedro, Cesar Peixoto, Antonio Veloso
Summary: A successful high-level gymnastics performance is achieved through coordination and inter-relation of body segments to produce movement prototypes. This study investigates different movement prototypes of the handspring tucked somersault with a half twist (HTB) technique and their relations with judges' scores. Flexion/extension angles of five joints were assessed during fifty trials, and international judges scored all trials for execution. Nine different movement prototypes were identified for the HTB technique, with two associated with higher scores. Strong associations were found between scores and specific movement phases, suggesting the importance of movement variability for success in gymnastics.
Article
Multidisciplinary Sciences
Luis Madeira, Guilherme Queiroz, Rui Henriques
Summary: The consumption of psychotropic drugs in Portugal has increased significantly between 2016 and 2019, leading to a rise in expenditure. This study provides detailed information on the prescription patterns of antidepressant, antipsychotic, and anxiolytic drugs, including their active ingredients, sociodemographics, medical specialties, and costs. The study also reveals disparities in sociodemographic and geographical distribution of prescriptions, highlighting the role of general practitioners and the need for guidelines and initiatives in medical practice and training.
SCIENTIFIC REPORTS
(2023)
Article
Transportation
Joao T. Aparicio, Elisabete Arsenio, Francisco C. Santos, Rui Henriques
Summary: Understanding urban mobility patterns within public transportation systems is crucial for improving services and promoting sustainable transportation. This research explores daily travel patterns of public transportation riders using big data, aiming to analyze when and where people travel. The study also examines the correlation between public transportation usage patterns and the spatial distribution of points of interest, and their impact on the structure of a city. By proposing a new measurement method and conducting a case study, this research confirms the modular structure of public transportation networks.
TRANSPORTATION RESEARCH INTERDISCIPLINARY PERSPECTIVES
(2023)
Review
Computer Science, Artificial Intelligence
Erica Tavazzi, Enrico Longato, Martina Vettoretti, Helena Aidos, Isotta Trescato, Chiara Roversi, Andreia S. Martins, Eduardo N. Castanho, Ruben Branco, Diogo F. Soares, Alessandro Guazzo, Giovanni Birolo, Daniele Pala, Pietro Bosoni, Adriano Chio, Umberto Manera, Mamede de Carvalho, Bruno Miranda, Marta Gromicho, Ines Alves, Riccardo Bellazzi, Arianna Dagliati, Piero Fariselli, Sara C. Madeira, Barbara Di Camillo
Summary: This systematic review focuses on the applications of artificial intelligence (AI) in Amyotrophic Lateral Sclerosis (ALS), especially in the automatic stratification of patients and the prediction of disease progression. The review includes 15 studies on patient stratification, 28 studies on the prediction of ALS progression, and 6 studies that cover both aspects. The results show a lack of validated models for ALS prediction and difficulty in reproducing published studies. While deep learning shows promise in prediction, its superiority over traditional methods is yet to be established. The role of new environmental and behavioral variables collected through real-time sensors remains an open question.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2023)
Article
Multidisciplinary Sciences
Diogo F. Soares, Rui Henriques, Marta Gromicho, Mamede de Carvalho, Sara C. Madeira
Summary: This study proposes a new class of explainable prognostic models using triclusters for longitudinal data classification. The proposed TCtriCluster algorithm finds informative temporal patterns common to a subset of patients and features, and uses them as discriminative features in a classifier. The approach enhances prediction by revealing clinically relevant disease progression patterns and used features, and it outperforms other methods in predicting specific clinical endpoints in ALS patients.
SCIENTIFIC REPORTS
(2023)
Article
Computer Science, Cybernetics
Mariana Carrasco, Antonio Rito Silva, Rui Henriques
Summary: This study proposes a novel and robust method to detect potential fraud acts in online multiple-choice question exams. By statistically assessing the communication probability between examinees based on the concordance of responses and answer time, potential fraud behavior can be identified. The model distinguishes content consumption from production and considers multiwise communication channels. It offers a solid criterion to guide tutors in ascertaining fraud and discouraging communication.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2023)
Article
Biochemistry & Molecular Biology
Daniel M. Goncalves, Rui Henriques, Rafael S. Costa
Summary: Accurate prediction of phenotypes in microorganisms is a major challenge in systems biology. Genome-scale models and constraint-based modeling methods are commonly used for predicting metabolic fluxes, but they require prior knowledge of the metabolic network and appropriate objective functions, limiting their applicability under different conditions. Integrating omics data with supervised machine learning models shows promise in improving phenotype predictions.
COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL
(2023)