Taxi demand can be divided into pick-up demand and drop-off demand, which are firmly related to human’s travel habits. Accurately predicting taxi demand is of great significance to passengers, drivers, ride-hailing platforms and urban managers. Most of the existing studies only forecast the taxi demand for pick-up and separate the interaction between spatial correlation and temporal correlation. In this paper, we first analyze the historical data and select three highly relevant parts for each time interval, namely closeness, period and trend. We then construct a multi-task learning component and extract the common spatiotemporal feature by treating the taxi pick-up prediction task and drop-off prediction task as two related tasks. With the aim of fusing spatiotemporal features of historical data, we conduct feature embedding by attention-based long short-term memory (LSTM) and capture the correlation between taxi pick-up and drop-off with 3D ResNet. Finally, we combine external factors to simultaneously predict the taxi demand for pick-up and drop-off in the next time interval. Experiments conducted on real datasets in Chengdu present the effectiveness of the proposed method and show better performance in comparison with state-of-the-art models.

With the rapid development of cyber-physical systems (CPS), building cyber-physical systems with high quality of service (QoS) has become an urgent requirement in both academia and industry. During the procedure of building Cyber-physical systems, it has been found that a large number of functionally equivalent services exist, so it becomes an urgent task to recommend suitable services from the large number of services available in CPS. However, since it is time-consuming, and even impractical, for a single user to invoke all of the services in CPS to experience their QoS, a robust QoS prediction method is needed to predict unknown QoS values. A commonly used method in QoS prediction is collaborative filtering, however, it is hard to deal with the data sparsity and cold start problem, and meanwhile most of the existing methods ignore the data credibility issue. Thence, in order to solve both of these challenging problems, in this paper, we design a framework of QoS prediction for CPS services, and propose a personalized QoS prediction approach based on reputation and location-aware collaborative filtering. Our approach first calculates the reputation of users by using the Dirichlet probability distribution, so as to identify untrusted users and process their unreliable data, and then it digs out the geographic neighborhood in three levels to improve the similarity calculation of users and services. Finally, the data from geographical neighbors of users and services are fused to predict the unknown QoS values. The experiments using real datasets show that our proposed approach outperforms other existing methods in terms of accuracy, efficiency, and robustness.

Background: Mortality prediction is an important task to achieve smart healthcare, especially for the management of intensive care unit. It can provide a reference for doctors to quickly predict the course of disease and customize early intervention programs for the patients in need. With the development of the electronic medical records, deep learning methods are introduced to deal with the prediction task. In the electronic medical records, clinical notes always contain rich and diverse medical information, including the clinical histories and reports during admission. Mortality prediction methods mostly rely on the temporal events such as medical examinations and ignore the related reports and history information in the clinical notes. We hope that we can utilize both temporal events and clinical notes information to get better mortality prediction results. Results: We propose a multimodal temporal-clinical note network to model both temporal and clinical notes. Specifically, the clinical text are further processed for differentiating the chronic illness patients in the historical information of clinical notes from non-chronic illness patients. In order to further mine the information related to the mortality in the text, we learn the time series embedding with Long Short Term Memory networks and the clinical notes embedding with a label aware convolutional neural network. We also propose a scoring function to measure the importance of clinical note sections. Our approach achieved a better AUCPR and AUCROC than competing methods and visual explanations for word importance showed the interpretability improvement of the model. Conclusions: We have tested our methodology on the MIMIC-III dataset. Contributions of different clinical note sections were uncovered by visualization methods. Our work demonstrates that the introduction of the medical history related information can improve the performance of the mortality prediction. Using label aware convolutional neural networks can further improve the results.

With the development of communication technology and artificial intelligence of things (AIoT), transportation systems have become much smarter than ever before. However, the volume of vehicles and traffic flows have rapidly increased. Optimizing and improving urban traffic signal control is a potential way to relieve traffic congestion. In general, traffic signal control is a sequential decision process that conforms to the characteristics of reinforcement learning, in which an agent constantly interacts with its environment, thus providing strategy for optimizing behavior in accordance with feedback in response. In this paper, we propose multiagent reinforcement learning for traffic signals (MARL4TS) to support the control and deployment of traffic signals. First, information on traffic flows and multiple intersections is formalized as input environments for performing reinforcement learning. Second, we design a new reward function to continuously select the most appropriate strategy as control during multiagent learning to track actions for traffic signals. Finally, we use a supporting tool, Simulation of Urban MObility (SUMO), to simulate the proposed traffic signal control process and compare it with other methods. The experimental results show that our proposed MARL4TS method is superior to the baselines. In particular, our method can reduce vehicle delay.

The Industrial Internet of Things (IIoT) represents a sophisticated technology designed to enhance production management and predict output in industrial settings, including machinery fault diagnostics. The precision of fault diagnosis is contingent upon the training efficacy of diagnostic models and their interoperability with models from other industrial facilities. Nonetheless, several critical challenges persist in maintaining these diagnostic models: 1) machinery sensors may generate abnormal data, resulting in suboptimal quality in model training; 2) sensor malfunctions may lead to interruptions in continuous data flow, thus impeding model training; and 3) collaborative interactions with other factories aiming at improving model performance may pose risks of privacy breaches. In this study, we introduce the FCLLM-DT scheme, which integrates the digital twin (DT) methodology to create a physical model of bearing for fixing abnormal sensor data. Additionally, retrieval-augmented generation (RAG)-assisted large language models (LLMs) are utilized to generate virtual datasets in instances of sensor failure. Moreover, for IIoT applications across distributed industrial environments, federated continual learning (FCL) is employed to enhance global model training by aggregating localized models from diverse facilities, thereby improving the accuracy of bearing fault diagnosis while safeguarding data privacy. The experiments on the accuracy of DT for abnormal data fix, RAG-assisted LLM for virtual data generation, and FCL for bearing fault diagnosis are conducted in comparison with three alternative methods across two datasets. The results indicate that our proposed scheme surpasses existing methods in both the enhancement of sensing data quality and the accuracy of bearing fault diagnosis.