Search

Intelligent Transportation Systems generate an unprecedented amount of high-dimensional traffic data. The proper analysis of such data can transform traffic monitoring mechanisms. However, existing monitoring methods for detecting abrupt changes in traffic patterns have two limitations. First, they do not capture the spatiotemporal characteristics of traffic data and are not equipped with a built-in mechanism to handle missing observations. To address these limitations, this study proposes a dynamic, robust tensor completion method to monitor and detect changes in partially observed traffic data streams. The proposed method simultaneously completes and decomposes the partially observed data into a sum of a low-rank tensor that captures the spatiotemporal patterns and a sparse tensor that captures anomalies. Subsequently, the proposed method defines a statistic monitored by an exponentially weighted moving average control chart to detect abrupt temporal changes. The performance of the proposed method is evaluated by simulation and case studies. The simulation results indicate the proposed method outperforms all benchmarks. It can also detect changes more than twice as fast as other benchmarks in terms of average run length in most scenarios. The proposed method is also applied to the traffic data in New York City to evaluate its performance in detecting unusual traffic patterns when Hurricane Sandy hit the city. The experimental results demonstrated the superiority of the proposed method in quickly detecting unusual changes at both network and road segment levels. Particularly, the proposed method detects changes in traffic patterns approximately twelve hours earlier than the next best alternative benchmark method.

Motivated by rapid urbanization and increasing natural hazards, this study aims to develop a data-driven method for detecting urban traffic anomalies during extreme events. Past experiences have shown that abnormal traffic patterns caused by extreme events can disrupt traffic in a large portion of the road network. Timely and reliable traffic monitoring for detection of such anomalies is crucial for congestion mitigation and successful emergency operation plans. An effective traffic monitoring system should detect disruptions at both network and local levels. However, the existing methods are not capable of addressing this need. This study proposes a temporal self-expressive network monitoring method to achieve this purpose. The proposed method first utilizes a temporal self-expressive model to uncover the dynamic interdependencies between local zones of the traffic network. Next, a statistical monitoring method detects network-wide anomalies based on regular traffic interdependencies. Finally, the method identifies the zones most affected by the anomalous event. We applied the proposed method to the road network of Manhattan in New York City to evaluate its performance during Hurricane Sandy. The outcomes confirmed that the temporal self-expressive model, augmented with statistical monitoring tools, could accurately detect anomalous traffic at both network and zone levels.

AbstractModeling temporally irregular electronic health records (EHRs) through computational phenotyping that transforms massive EHR data into clinically meaningful medical concepts has become critical in the healthcare industry. PARAFAC2 tensor factorization has demonstrated effectiveness in extracting phenotypes from such data but is designed to have access to the dataset in a centralized form. The EHR data are often distributed across multiple entities, requiring the PARAFAC2 factorization to be conducted in a silo (separately at each entity) or by pooling the data into a central server. However, the in-silo modeling of data results in a lack of generalizability, and data pooling creates data privacy concerns. To address these challenges, we propose a federated PARAFAC2 factorization to extract interpretable clinical phenotypes when the data are distributed across multiple entities. In the proposed framework, each entity extracts phenotypes locally based on their available data and transfers the intermediary results to a server, aggregating the information to estimate aggregated phenotypes. The Alternating Direction Method of Multipliers (ADMM) algorithm is designed for problem optimization. Experiments on synthetic and real-world EHR datasets (MIMIC-III) demonstrate that the performance of the proposed approach is comparable to the centralized model that uses pooled data regarding phenotype discovery while avoiding direct data sharing.

AbstractComplex systems are generating more and more high-dimensional data for which tensor analysis showed promising results by capturing complex correlation structures of data. Such data is often distributed among various sites creating challenges for developing data-driven models. Specifically, data privacy and security concerns have been exacerbated in recent years and drove the demand to store and analyze data at the edge of networks rather than sharing it with a centralized server. Federated learning frameworks have been introduced as a solution to these concerns. These frameworks allow local clients to learn local models and collaborate with others to develop a more generalizable aggregated model while handling data privacy issues. In this article, we propose a federated generalized scalar-on-tensor regression framework where multiple local tensor models are learned at the edge, and their parameters are shared with and updated by an aggregator. Experiments on synthetic data sets and two real-world data sets from agriculture and manufacturing domains show the superiority of our approach over several benchmarks.

Background:Effective communication as a key component of palliative care requires sufficient knowledge and experience to make nursing interventions successful.Aim:This quasi-experimental study was conducted to determine the effectiveness of the COMFORT communication model as an intervention to improve student nurses’ communication skills while they are under clinical training in specialist palliative care inpatient units.Methods:The population sample included 86 student nurses who were randomly assigned into two groups of 40. The intervention group received training on communication skills using the COMFORT communication model. Nine lectures were delivered online or offline; the lectures lasted between 25 to 60 minutes. The control group received the conventional educational programme about communication with patients and families, according to the curriculum of the bachelor's degree in nursing. Data were collected using the Communication Skills Questionnaire and Communication Skills Attitude Scale and analysed using IBM® SPSS® Statistics 22.0.Results:The findings showed that, after the implementation of COMFORT communication model, there was a statistically significant difference in communication skills between the intervention group (122.95±9.36) and the control group (110.1±8.92). There was also a significant difference in attitudes toward communication skills between the intervention group (90.25±8.86) and the control group (90.85±9.15) (P=0.0001). The findings of the study revealed that the COMFORT Communication model created significant statistical differences in the student's attitude, knowledge and communication skills.Conclusion:Novice nurses sometimes struggle with the level of communication skills needed when caring for patients with an end-stage illness. The implementation of the COMFORT communication model significantly improved communication skills and attitudes toward communication. Due to the need to establish effective communication as the core of nursing practice, the implementation of this training programme is recommended for students and qualified nurses, particularly when providing palliative care.