Long-term Wearable Electrocardiogram Signal Monitoring and Analysis Based on Convolutional Neural Network

Liu, Meng; Kang, Ge; Song, Yang; Yang, Dongming; Lin, Zihuai

doi:10.1109/tim.2021.3072144

Cited by 27 publications

(13 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, in the future, additional types of neural network algorithms, such as convolutional neural network and radial basis function algorithms, can be simulated and eval-uated. Furthermore, deep learning algorithms and denoising techniques developed in our existing works, e.g., [31]- [35] can be used to improve the accuracy. Privacy concerns for location-based services [36]- [39] and cellular networks [40]- [48] and sensor networks [49]- [58] based location techniques are also our future plan.…”

Section: B Results Of Coalescent Training (Ct)mentioning

confidence: 99%

Precise Indoor Positioning Based on UWB and Deep Learning

Wang¹,

Lin²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

We examined UWB-based indoor location in conjunction with a fingerprint technique in this work. We built a connection between the measured and real distances for the UWB indoor positioning system. This connection is used to produce a distance database that may be used to generate fringerprints. We created a BP neural network to classify the target node to the relevant fringerpint using the distance database. Our suggested deep learning technology considerably enhances location accuracy when compared to existing trilateration systems.

show abstract

Section: B Results Of Coalescent Training (Ct)mentioning

confidence: 99%

Precise Indoor Positioning Based on UWB and Deep Learning

Wang¹,

Lin²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…An ECG sensor from iRealcare [9]- [13] was used for collecting ECG signals of different emotions from different people. The data collected by the iRealcare ECG sensor can be transmitted to a smart phone APP via Bluetooth Low Energy (BLE) and then to a cloud.…”

Section: Data Collection and Pre-processingmentioning

confidence: 99%

“…In the data collection stage, we collect the ECG signals for four emotions: happy, exciting, calm and tense, respectively. The ECG signals are collected by using a low-cost wearable ECG patch, called iRealcare [9]- [13]. The collected signals are pre-processed by a finite impulse filter to remove noises from raw ECG signals.…”

Section: Introductionmentioning

confidence: 99%

Emotion Recognition using Machine Learning and ECG signals

Sun¹,

Lin²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Various emotions can produce variations in electrocardiograph (ECG) signals, distinct emotions can be distinguished by different changes in ECG signals. This study is about emotion recognition using ECG signals. Data for four emotions, namely happy, exciting, calm, and tense, is gathered. The raw data is then de-noised with a finite impulse filter. We use the Discrete Cosine Transform (DCT) to extract characteristics from the obtained data to increase the accuracy of emotion recognition. The classifiers Support Vector Machine (SVM), Random Forest, and K-NN are explored. To find the optimal parameters for the SVM classifier, the Particle Swarm Optimization (PSO) technique is used. The results of the comparison of these classification methods demonstrate that the SVM approach has a greater accuracy in emotion recognition, which may be applied in practice.

show abstract

“…In the sensing layer, data acquisition devices from various functions carry different types of sensors, which can produce different types of data containing various information and sometimes even affecting each other. This system has established two edge networks based on LoRa and Wi-Fi respectively and has deployed several functional applications based on different wireless protocols, such as indoor positioning [12], [13] based on UWB and BLE, ECG monitoring device [14]- [18] based on Bluetooth, and people flow statistics based on ultrasonic and Wi-Fi. In the future work, radio sensing techniques, e.g., [19]- [22], can also be used in our system.…”

Section: A Sensing Layermentioning

confidence: 99%

Poster Abstract: An Implementation of an Internet of Things System for Smart Hospitals

Leng

Lin

Wang

2020

2020 IEEE/ACM Fifth International Conference on Internet-of-Things Design and Implementation (IoTDI)

Self Cite

View full text Add to dashboard Cite

With the rapid development of smart devices and the Internet of Things (IoT) technology, some traditional scenarios are exploring new possibilities. Especially in the field of healthcare, the mixed and large amount of people, the complex and professional data, and the strict environmental requirements on some medical scenes and equipment, all put forward extremely high requirements on the hospital management. Therefore, an efficient and secure Internet of things system is greatly necessary. This paper develops an IoT system that could be deployed in hospitals for various applications. This system supports LoRa, Wi-Fi and other data collection methods, uploads the data to the cloud platform for further processing through secure connection, and finally feeds back to users in real-time through the user interface. This system supports accurate indoor positioning based on UWB, ECG signal detection, environmental monitoring, people flow statistics and other functions.

show abstract

Long-term Wearable Electrocardiogram Signal Monitoring and Analysis Based on Convolutional Neural Network

Cited by 27 publications

References 39 publications

Precise Indoor Positioning Based on UWB and Deep Learning

Precise Indoor Positioning Based on UWB and Deep Learning

Emotion Recognition using Machine Learning and ECG signals

Poster Abstract: An Implementation of an Internet of Things System for Smart Hospitals

Contact Info

Product

Resources

About