首页|Researchers from VSB-Technical University of Ostrava Provide Details of New Stud ies and Findings in the Area of Artificial Intelligence (Adopting Artificial Int elligence Algorithms for Remote Fetal Heart Rate Monitoring and Classification U sing ...)
Researchers from VSB-Technical University of Ostrava Provide Details of New Stud ies and Findings in the Area of Artificial Intelligence (Adopting Artificial Int elligence Algorithms for Remote Fetal Heart Rate Monitoring and Classification U sing ...)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews-Investigators publish new report on Artificial In telligence. According to news reporting originatingin Ostrava, Czech Republic, by NewsRx journalists, research stated, "Fetal phonocardiography (FPCG) isa non -invasive Fetal Heart Rate (FHR) monitoring technique that can detect vibrations and murmurs inheart sounds. However, acquiring fetal heart sounds from a weara ble FPCG device is challenging due tonoise and artefacts."Funders for this research include European Union (EU), Ministry of Education of the Czechia.The news reporters obtained a quote from the research from the VSB-Technical Uni versity of Ostrava,"This research contributes a resilient solution to overcome the conventional issues by adopting ArtificialIntelligence (AI) with FPCG for a utomated FHR monitoring in an end-to-end manner, named (AI-FHR).Four sequential methodologies were used to ensure reliable and accurate FHR monitoring. The pro posedmethod removes low-frequency noises and high-frequency noises by using Che byshev II high-pass filtersand Enhanced Complete Ensemble Empirical Mode Decomp osition with Adaptive Noise (ECEEMDAN)in combination with Phase Shifted Maximal Overlap Discrete Wavelet Transform (PS-MODWT) filters,respectively. The denois ed signals are segmented to reduce complexity, and the segmentation is performedusing multi-agent deep Q-learning (MA-DQL). The segmented signal is provided to reduce the redundanciesin cardiac cycles using the Artificial Hummingbird Opti mization (AHBO) algorithm. The segmentedand non-redundant signals are converted into 3D spectrograms using a machine learning algorithm calledvariational auto -encoder-general adversarial networks (VAE-GAN). The feature extraction and clas sificationare carried out by adopting a hybrid of the bidirectional gated recur rent unit (BiGRU) and themulti-boosted capsule network (MBCapsNet). The propose d method was implemented and simulated usingMATLAB R2020a and validated by adop ting effective validation metrics. The results demonstrate thatthe proposed met hod performed better than the current method with accuracy (81.34%) , sensitivity (72%), F1- score (83%), Energy (0.808 J) , and complexity index (13.34). Like other optimization methods,AHO needs preci se parameter adjustment in order to function well."
OstravaCzech RepublicEuropeAlgorit hmsArtificial IntelligenceEmerging TechnologiesMachine LearningVSB-Techn ical University of Ostrava
NETL
NSTL
