Fatigue poses a critical safety risk to civil and military aviation. It may lead to errors that could potentially compromise the safety of the crew and passengers (Pan et al., 2021). For this reason, it is important to study and analyze the effectiveness of various fatigue monitoring systems. To achieve pilot fatigue risk control, health management, and real-time safety warning, the diagnosis of pilot fatigue has a specific value.
The research problem statement of the article is a high level of flight accidents caused by human factors, especially pilot fatigue. In addition to defining the problem and conducting qualitative research, one of the essential tasks for the author remains the correct presentation of ideas to the reader. Critical writing is not just about an event but is itself an encounter between writer and work, reader and text (Schmidt, 2018). The problem statement formulated by the authors of the article concisely, clearly, and effectively communicates the research problem to the reader.
The research question or the article may be phrased as “how to identify the real-time fatigue state of pilots quickly and accurately?”. This research question is directly related to the problem statement of the article, and answering this question is able to resolve the research problem. Determination of the effectiveness of monitoring pilots’ fatigue status based on electrocardiogram signals to reduce flight accidents caused by pilot fatigue has become a core scientific problem that needs to be solved urgently in the field of aviation safety. There are other ways to monitor pilot fatigue, such as Using Deep Contractive Autoencoder Network (Wu et al., 2019). But the authors decided to limit their study to one method in order to conduct the most accurate and detailed analysis.
The research design of the article consists of several sequential processes such as data collection that include fatigue scale and ECG. The next step is the processing and classification of collected data. In the end, there is a discussion of the results obtained, their interpretation, and evaluation of the effectiveness of the practical application of ECG data to monitor pilot fatigue and prevent flight accidents caused by it.
To identify the fatigue state of pilots, ECG data and the Samn–Perelli 7-Level fatigue scale data are collected through flight simulation experiments. The obtained ECG data are preprocessed. Then, the time domain, frequency domain, and the non-linear characteristic indexes of the ECG data are selected and extracted by the Friedman test and PCA. Based on feature selection and extraction results, the pilots’ fatigue state identification model is established using the LVQ neural network. The pilot’s non-fatigue, mild fatigue, and fatigue states are identified. The identification results are compared with those of BPNN, SVM, and other traditional methods.
This research design is correct for the study’s intent and the type of data used. Any research collects and analyzes data in its own way and, depending on the subject and purpose, may be qualitative or quantitative. Qualitative research is used to record data that is not in the form of numbers, such as opinions, feelings, and experiences; quantitative research is used to measure data in the form of numbers (Clark & Vealé, 2018). This article is quantitative because data collection and analysis are based on specific, measurable indicators. This research gathers and assesses the most relevant data for answering the research questions.
This study is of high quality and has value as it lays a foundation for more scholars to identify pilots’ fatigue states based on ECG signals and study pilots’ fatigue mechanisms. The selected fatigue monitoring method has a high identification accuracy. The present results provide a theoretical basis for reducing flight accidents caused by pilot fatigue. At the same time, the results also provide a practical reference for pilot fatigue risk management and the development of intelligent aircraft autopilot systems.
References
Clark, K. R., & Vealé, B. L. (2018). Strategies to enhance data collection and analysis in qualitative research. Radiologic technology, 89(5), 482-485.
Pan, T., Wang, H., Si, H., Li, Y., & Shang, L. (2021). Identification of Pilots’ Fatigue Status Based on Electrocardiogram Signals. Sensors.
Schmidt, T. (2018). How We Talk About The Work Is The Work: Performing critical writing. Performance Research, 23(2), 37-43.
Wu, E. Q., Peng, X. Y., Zhang, C. Z., Lin, J. X., & Sheng, R. S. (2019). Pilots’ fatigue status recognition using deep contractive autoencoder network. IEEE Transactions on Instrumentation and Measurement, 68(10), 3907-3919.