Dual‐grained representation for hand, foot, and mouth disease prediction within public health cyber‐physical systems

Abstract

The prediction model is a major component within public health cyber‐physical systems, which supports decisions on prevention and control of diseases. Hand, foot, and mouth disease (HFMD) is one of the most common global infectious diseases with the highest incidence rate. Previous HFMD prediction models are mainly based on the time series that counted in equal‐grained time intervals. However, there are details in the time series counted in fine‐grained time intervals. To benefit from both equal‐grained and fine‐grained data, we proposed a dual‐grained representation (DGR) model. The DGR first represents inputted data to temporal patterns. Then, the represented patterns are consolidated to generate predictions. Experimental comparisons of the short‐term prediction performance are figured out by using real outpatient collections in Xiamen, China.

COVID-19 cases prediction in multiple areas via shapelet learning

“…2a, 2b and 2c, the optimal values of these metrics are found at T = 28, which is shown in the red dash lines. Compared the window size T with some quick onset disease, such as HFMD [28,29] and infectious diarrhea [2], the optimal value T of COVID-19 is larger than the value of other diseases. A possible reason is that the COVID-19 has a longer incubation period than other quick onset diseases, or it can spread to other persons in the incubation period.…”

Software and hardware co‐design for sustainable cyber‐physical systems

“…As artificial intelligence techniques are becoming increasingly vital in CPS, the article 10 proposes a new federated learning‐based scheme to train disease diagnosis models for distributed medical image data from medical CPS. A dual‐grained representation model is built to support the disease prevention and control in public health CPS 11 . For software deployed in automotive CPS, the authors 12 developed a variable consistency check tool to increase the accuracy of variable consistency check, along with a quick check time.…”

Early prediction of atherosclerosis diagnosis with medical ambient intelligence

“…Computer-aided predictive methods are an emerging field of diagnostic research for disease. They not only provide decision support for diagnosing and predicting diseases ( Wang et al, 2021 ; Huang et al, 2022 ), but also reveal potential factors and patterns related to disease ( Zhang et al, 2022 ; Wang et al, 2022 ), which promote the innovation and development of medical knowledge. According to the nature of these methods, they are categorized into model-driven methods, data-driven methods and decision support systems (DSS).…”