A Predictor-Corrector Algorithm Based on Laurent Series for Biological Signals in the Internet of Medical Things

Abstract

In future engineered systems for medical applications, a tight real-time integration between physical and computational processes will be required. That integration is achieved using feedback control loops which need high quality input data streams. However, hardware platforms can barely provide such high-quality data sequences (especially if mobile nodes are considered), and mechanisms to improve and polish physical and biological signals are then necessary. This paper proposes a predictor-corrector algorithm to improve the quality and precision of data (biological) signals in Internet of Medical Things deployments, especially if composed of mobile nodes. The proposed algorithm employs an Artificial Intelligence approach and statistical learning techniques to predict future data samples and correct errors in received information. Employed mathematical models follow a prediction-correction scheme and are based on complex functions, Laurent series and the idea of complex envelope. Simulation techniques are used to evaluate the performance of the proposed solution, showing that it improves the precision of traditional linear interpolation techniques up to 85%, and cubic splines up to 20%. Processing delay during operation is, for the referred precision, around 200ms.

Controlling Supervised Industry 4.0 Processes through Logic Rules and Tensor Deformation Functions

“…To recognize human activities, we are using a two-phase solution composed of different machine learning and pattern recognition layers (Wonham and Cai, 2019). To recognize activities performed by autonomous devices we employed previous works on artificial intelligence mechanisms for Internet-of-Things applications based on signal processing (Bordel et al, 2020b). These components were deployed together with the proposed Table 4 Most common production activities in the experimental validation.…”

“…However, Industry 4.0 scenarios are different. Cyber-Physical Systems and pervasive computing infrastructures are not typically provided with open interfaces, and they tend to act autonomously according to deterministic algorithms or, even, learning technologies (Bordel et al, 2020b). Dense environments where thousands of agents with heterogeneous capabilities are deployed and working together are the most common application scenarios for Industry 4.0.…”

Prediction-Correction Techniques to Support Sensor Interoperability in Industry 4.0 Systems

“…Figure 1 shows the proposed algorithm to find that time series 𝑥 𝑖 * [𝑛], fulfilling the previous conditions ( 13), if it exists. As can be seen (in the initial prediction phase), first, a set of C suitable candidates X to be that curated time series x * i [n] are calculated (14).…”

“…Nevertheless, this seamless integration highly affects the social and economic impact of the Industry 4.0 paradigm, as only some (or even only one) sensor technologies may be employed in each application, as calibration models, compensation algorithms, etc. [14], are totally dependent on the specific sensors and processing algorithms to be integrated. This turns Industry 4.0 into a very rigid and close paradigm, more similar to a proprietary solution than to a flexible, open approach.…”