China
Africa
Explore chapters and articles related to this topic
An IoT-Based Smart Jacket for Health Monitoring with Real-Time Feedback
Published in Indu Bala, Kiran Ahuja, Harnessing the Internet of Things (IoT) for a Hyper-Connected Smart World, 2023
Anurag Sharma, Anshu Sharma, Mani Raj Paul
ECG is known as electrocardiography that measures the electrical activity of the heart. ECG is a test that tells the functioning of the heart to the patient. It is generally recorded in the form of pulses (heart beat). In ECG graph P, Q, R, S, and T waves are generated from the electrical activity of the human heart as shown in given Figure 4.1 [5]. It measures the electrical pursuit passes across to the heart. A doctor can easily understand the ECG graph for a normal and irregular heartbeat. ECG can easily detect abnormal heart rhythms, chest pain, and heart problems.
Role of IoT, AI, and Big Data Analytics in Healthcare Industry
Published in Pushpa Singh, Divya Mishra, Kirti Seth, Transformation in Healthcare with Emerging Technologies, 2022
P. Sriramalakshmi, Srimathnath Thejasvi Vondivillu, A. Sri Krishna Govind
Intelligent biomedical sensors are used to detect several chronic diseases. A list of sensors available or in development is given below:Cardiovascular heart diseases: sensors strapped to the chest and smartwatches are used for heart rate detection. The electrical activity of the heart is recorded by electrocardiography. Using BlueTooth or onboard wifi, the data is transferred to the device or the cloud for further processing.Asthma: Smartwatches with ECG sensors in addition to carbon monoxide, nitrogen dioxide, and other environmental conditions are monitored and alert medical personnel in case of emergencies.Alzheimer’s, autism, dementia, or other cognitive disorders: GPS Smart Soles are motion sensors used to alert the caretaker or medical professional in case of abnormal situations. Smart Soles work by using geofenced location: if the patient leaves the boundaries, a signal is sent to the necessary personnel. In case of low battery or out-of-service situations, the last recorded location can be configured to be sent to the necessary personnel. These sensors usually work using the ZigBee protocol or GSM to provide real-time information.
A Deep Learning and Multilayer Neural Network Approach for Coronary Heart Disease Detection
Published in Neeraj Mohan, Surbhi Gupta, Chuan-Ming Liu, Society 5.0 and the Future of Emerging Computational Technologies, 2022
Seema Rani, Neeraj Mohan, Surbhi Gupta, Priyanka Kaushal, Amit Wason
There are several benefits of using DL neural networks for detection of CHD. We can use different techniques for the detection of CHD, such as: ElectrocardiographyEchocardiographyTelesonography Electrocardiography is the method of generating an electrocardiogram (ECG), which records the electrical activity of the heart by using electrodes positioned on the skin. An electrocardiogram is also generated by a voltage versus time graph.
An effective ECG signal compression algorithm with self controlled reconstruction quality
Published in Computer Methods in Biomechanics and Biomedical Engineering, 2023
Hardev Singh Pal, A. Kumar, Amit Vishwakarma, Girish Kumar Singh, Heung-No Lee
Electrocardiography (ECG) is a widely used procedure for the detection of heart-related abnormalities. Thus, ECG recording systems are quite popular and frequently used. Long terms recordings of ECG signals generate a huge volume of data as these are recorded at higher data resolutions, which requires an ample amount of storage space and bandwidth for transmission (Gupta et al. 2014). Therefore, data compression techniques are considered an essential part of telemedicine applications for effective utilization of the present resources. It removes redundancies present in raw data and minimizes the required size for storage. In this regard, several compression algorithms have been proposed for ECG signals (Bera et al. 2020; Qian et al. 2020; Banerjee and Singh 2021; C. K. Jha and Kolekar 2021a, 2021b; Pal et al. 2022; Thilagavathy and Venkataramani 2022).
The circadian effect on psychophysiological driver state monitoring
Published in Theoretical Issues in Ergonomics Science, 2021
Sylwia I. Kaduk, Aaron P. J. Roberts, Neville A. Stanton
Electrocardiography (ECG) is a measure of the electrical activity of the heart (Saritha, Sukanya, and Murthy 2008). The states that could be identified with ECG were mental workload, drowsiness, fatigue, behavioural distraction, stress and anger. They were either identified using heart rate (Averty et al. 2002), inter-beat interval (Veltman and Gaillard 1996), heart rate variability (HRV) (Wilson 2002), or machine learning algorithms with multiple heart-related features (Sahayadhas et al. 2015). HRV is a measure of a natural, physiological variation in the heart rate (Roscoe 1992). Drowsiness and fatigue were evidenced to correlate with a decreased (Maglione et al. 2014; Ogorevc et al. 2011), while stress with an increased heart rate (Schreinicke et al. 1990). Both anger and distraction were identified with machine learning algorithms using multiple features (Minhad, Ali, and Reaz 2017; Sahayadhas et al. 2015). The increased mental workload was found to be correlated with increased heart rate (Averty et al. 2002), decreased heart rate variability (Roscoe 1992) and decreased inter-beat interval (Veltman and Gaillard 1996).
Spectral trimming technique: a new approach for suppressing motion artefacts in stress electrocardiography
Published in Journal of Medical Engineering & Technology, 2020
A. S. Lakhe, R. K. Jain, Vineet Sinha, T. S. Anantkrishnan, P. P. Athavale, Bhaimangesh Naik, G. D. Jindal
Electrocardiography (ECG) is recording of electrical activity of the heart by placing electrodes at pre-defined positions on the body. It is a powerful diagnostic tool for diagnosis and management of major cardiac ailments. The signal is prone to various types of noises during recording; power line interference, myographic noise, baseline wander and motion artefacts being the major contributors in addition to inherent electronics noise. Baseline wandering and motion artefact, which are induced due to changes in electrical properties at electrode-skin interface caused by breathing and physical movement are major concern during stress electrocardiography. Substantial research has gone into suppressing these artefacts and restoring the ECG without significant loss of physiological information. Romero et al. [1] have done a comparative study of nine methods, including fixed filters, wavelet denoising, adaptive filtering etc. for removing baseline wander and have reported finite impulse response (FIR) high pass filtering technique to be the best among them. However, the cut-off frequency is shown to be as 0.67 Hz which may result in signal loss, as ECG frequency spectrum is substantially from 0.05 Hz to 150 Hz.