A Knowledge-Based Approach to Automatic Detection of Equipment Alarm Sounds in a Neonatal Intensive Care Unit Environment

• Published in: IEEE journal of translational engineering in health and medicine Vol. 6; pp. 1 - 10
• Main Authors: Raboshchuk, Ganna, Nadeu, Climent, Jancovic, Peter, Lilja, Alex Peiró, KöKüEr, MüNevver, Muñoz Mahamud, Blanca, De Veciana, Ana Riverola
• Format: Journal Article Publication
• Language: English
• Published: United States IEEE 01.01.2018; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Acoustic event detection; Acoustic noise; Acoustical engineering; Acoustics; Acústica; Alarm detection; Alarm systems; Auditory stimuli; Biomedical equipment; Detectors; Enginyeria acústica; Environmental audits; Feature extraction; Física; Intensive care; Medicina intensiva neonatal; Monitoring; Neonatal intensive care unit; Neural networks; Non-negative matrix factorization; Pediatrics; Post-processing; Sinusoid detection; Time-frequency analysis; Àrees temàtiques de la UPC; Acoustic event detection; sinusoid detection; alarm detection; non-negative matrix factorization; neonatal intensive care unit; neural networks
• ISSN: 2168-2372; 2168-2372
• DOI: 10.1109/JTEHM.2017.2781224

A large number of alarm sounds triggered by biomedical equipment occur frequently in the noisy environment of a neonatal intensive care unit (NICU) and play a key role in providing healthcare. In this paper, our work on the development of an automatic system for detection of acoustic alarms in that difficult environment is presented. Such automatic detection system is needed for the investigation of how a preterm infant reacts to auditory stimuli of the NICU environment and for an improved real-time patient monitoring. The approach presented in this paper consists of using the available knowledge about each alarm class in the design of the detection system. The information about the frequency structure is used in the feature extraction stage, and the time structure knowledge is incorporated at the post-processing stage. Several alternative methods are compared for feature extraction, modeling, and post-processing. The detection performance is evaluated with real data recorded in the NICU of the hospital, and by using both frame-level and period-level metrics. The experimental results show that the inclusion of both spectral and temporal information allows to improve the baseline detection performance by more than 60%.