2024 · 16 citations · 4 references
ComputingCloud ComputingComputer ScienceArtificial IntelligenceInternet Of ThingsMachine LearningDeep LearningElectroencephalographyIot SensorsNeural NetworksPattern RecognitionSmart SensorsDeep Learning For Eeg AnalysisDeep Learning For ElectroencephalogramDeep Learning-based MonitoringEeg Signal ProcessingHealthcare Internet Of ThingsInternet Of Things DevicesSensor Data IntegrationSmart Healthcare Services
Our novel strategy uses IoT-cloud technology to present a cognitive healthcare platform. This framework utilizes deep learning algorithms in conjunction with smart sensor integration to facilitate intelligent decision-making in the setting of smart cities. Our intelligent and cognitive framework provides accurate, efficient, and economical healthcare services by continually monitoring patients’ vital signs in real-time. Here, we provide experimental results on deep learning-based EEG pathology categorization to verify the efficacy of our proposed system. We record and track many healthcare data modalities using a range of smart sensors, such as EEG sensors. Patients’ EEG data are effortlessly sent to the cloud via Internet of Things devices, where a cognitive module processes and analyzes them. Through the analysis of sensor data, including voice, gestures, motions, and EEG signals, this system assesses the patient’s state. Real-time decisions, crucial for determining the appropriate course of action, are made by the cognitive module. Additionally, EEG signals are processed by a deep learning module to classify them as pathological or normal. The insights gleaned from patient monitoring and EEG signal analysis are then shared with healthcare providers. This helps them to precisely evaluate the patient’s state and quickly offer emergency care if needed. Notably, our proposed deep learning model outperforms existing systems in terms of accuracy and reliability, underscoring its potential for transforming healthcare delivery.
4
Modeling Voice Pathology Detection Using Imbalanced Learning
Ziqi Fan, Jinyang Qian, Baoyin Sun et al. · 2020 · 11 citations