Industrial production and manufacturing systems require automation, reliability, as well as low-latency intelligent control. Industrial Internet of Things (IIoT) is an emerging paradigm that enables precise, low latency, intelligent computing, supported by cutting-edge technology such as edge computing and machine learning. IIoT provides some of the essential building blocks to drive manufacturing systems to the next level of productivity, efficiency, and safety. Hardware failures and faults in IIoT are critical challenges to be faced. These anomalies can cause accidents and financial loss, affect productivity, and mobilize staff by producing false alarms. In this context, this article proposes a framework called Detection and Alert State for Industrial Internet of Things Faults (DASIF). The DASIF framework applies edge computing to execute highly precise and low latency machine learning models to detect industrial IoT faults and autonomously enforce an adaptive communication policy, triggering a state of alert in case of fault detection. The state of alert is a pre-stage countermeasure where the network increases communication reliability by using data replication combined with multiple-path communication. When the system is under alert, it can process a fine-grained inspection of the data for efficient decison-making. DASIF performance was obtained considering a simulation of the IIoT network and a real petrochemical dataset.

No abstract

Objective: To observe whether the use of WhatsApp™ can contribute to the improvement and retention of ECG knowledge during medical graduation in a period-time of 4 months. Material and Methods: A controlled, quasi-randomized, intention-to-treat, clinical trial. Medical students of the 2nd and 3rd semester attended a 2-hour class on elementar ECG interpretation. A test with 10 ECG tracings covering subjects was applied with a possible 0-10 score at 4 different times: immediately before the lesson (M1), immediately after the lesson (M2), one month after the lesson (M3) and four months after the lesson (M4). Intervention group, formed by 2nd-semester students, were included, shortly after M2, in a WhatsApp™ group, in which final year medical students and a cardiology resident discussed ECG tracings frequently in the absence of a teacher. Control group, formed by 3rd-semester students, was instructed to study on their own. Results: 13 students were included from the 2nd semester and 11 from the 3rd semester. In M1, the intervention and control group obtained a median of 0.0. In M2, both groups presented a similar increase with a median of 4.0 (IIQ=2.8-5.0) for the intervention group and 4.5 (IIQ= 3.3-5.5) for the control group. In M3, there was a difference between group scores, with a median of 6.0 (IIQ= 3.5-7.0) for the intervention group and 2.0 (IIQ=0-4.0) for the control group (p=0.016). In M4, difference was maintained (4.0 for intervention group [IIQ= 3.0-6.3] vs. 1.0 [IIQ= 1.0-3.0] for control group [p= 0.006]). Conclusion: Early-stage medical students learned and retained more elementar ECG knowledge when participating in WhatsApp™ ECG group discussion with more advanced medical students and medical resident, even without a teacher in this group.