LiteNet: Lightweight Neural Network for Detecting Arrhythmias at Resource-Constrained Mobile Devices

He, Ziyang; Zhang, Xiaoqing; Cao, Yangjie; Liu, Zhi; Zhang, Bo; Wang, Xiaoyan

doi:10.3390/s18041229

Cited by 42 publications

(26 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other research efforts in building network architectures suitable for use on performance restricted environments such as IoT and smartphones have led to another category of models, specifically designed to be computationally efficient. State-of-the-art architectures of this type of models include MobileNet [3], MobileNetV2 [6], ShuffleNet [4], LiteNet [20] and EffNet [5].…”

Section: Related Workmentioning

confidence: 99%

IoTNet: An Efficient and Accurate Convolutional Neural Network for IoT Devices

Lawrence

Zhang

2019

Sensors

View full text Add to dashboard Cite

Two main approaches exist when deploying a Convolutional Neural Network (CNN) on resource-constrained IoT devices: either scale a large model down or use a small model designed specifically for resource-constrained environments. Small architectures typically trade accuracy for computational cost by performing convolutions as depth-wise convolutions rather than standard convolutions like in large networks. Large models focus primarily on state-of-the-art performance and often struggle to scale down sufficiently. We propose a new model, namely IoTNet, designed for resource-constrained environments which achieves state-of-the-art performance within the domain of small efficient models. IoTNet trades accuracy with computational cost differently from existing methods by factorizing standard 3 × 3 convolutions into pairs of 1 × 3 and 3 × 1 standard convolutions, rather than performing depth-wise convolutions. We benchmark IoTNet against state-of-the-art efficiency-focused models and scaled-down large architectures on data sets which best match the complexity of problems faced in resource-constrained environments. We compare model accuracy and the number of floating-point operations (FLOPs) performed as a measure of efficiency. We report state-of-the-art accuracy improvement over MobileNetV2 on CIFAR-10 of 13.43% with 39% fewer FLOPs, over ShuffleNet on Street View House Numbers (SVHN) of 6.49% with 31.8% fewer FLOPs and over MobileNet on German Traffic Sign Recognition Benchmark (GTSRB) of 5% with 0.38% fewer FLOPs.

show abstract

Section: Related Workmentioning

confidence: 99%

IoTNet: An Efficient and Accurate Convolutional Neural Network for IoT Devices

Lawrence

Zhang

2019

Sensors

View full text Add to dashboard Cite

show abstract

“…Most of the traditional solutions use sensors for physiological signal detection, for example, Polysomnography [6] and Electrocardiogram [7]. However, these programs are not suitable for the home environment.…”

Section: Introductionmentioning

confidence: 99%

WiFi-Based Real-Time Breathing and Heart Rate Monitoring during Sleep

Zhang

et al. 2019

2019 IEEE Global Communications Conference (GLOBECOM)

Self Cite

View full text Add to dashboard Cite

Good quality sleep is essential for good health and sleep monitoring becomes a vital research topic. This paper provides a low cost, continuous and contactless WiFi-based vital signs (breathing and heart rate) monitoring method. In particular, we set up the antennas based on Fresnel diffraction model and signal propagation theory, which enhances the detection of weak breathing/heartbeat motion. We implement a prototype system using the off-shelf devices and a real-time processing system to monitor vital signs in real time. The experimental results indicate the accurate breathing rate and heart rate detection performance. To the best of our knowledge, this is the first work to use a pair of WiFi devices and omnidirectional antennas to achieve real-time individual breathing rate and heart rate monitoring in different sleeping postures.

show abstract

“…The Adam optimizer, presented by Kingma and Ba [35], is extensively used for deep learning models requiring first-order gradient-based descent with small memory and the ability to compute adaptive learning rates for different parameters [36]. This method is computationally efficient, easy to implement, and has proven to perform better than the RMSprop and Rprop optimizers [37]. Gradient rescaling is reliant on the magnitudes of parameter updates.…”

Section: Feed Forward Neural Network (Fnn)mentioning

confidence: 99%

Combination of Discrete Element Method and Artificial Neural Network for Predicting Porosity of Gravel-Bed River

Bui

Rutschmann

2019

Water

View full text Add to dashboard Cite

In gravel-bed rivers, monitoring porosity is vital for fluvial geomorphology assessment as well as in river ecosystem management. Conventional porosity prediction methods are restricting in terms of the number of considered factors and are also time-consuming. We present a framework, the combination of the Discrete Element Method (DEM) and Artificial Neural Network (ANN), to study the relationship between porosity and the grain size distribution. DEM was applied to simulate the 3D structure of the packing gravel-bed and fine sediment infiltration processes under various forces. The results of the DEM simulations were verified with the experimental data of porosity and fine sediment distribution. Further, an algorithm was developed for calculating high-resolution results of porosity and grain size distribution in vertical and horizontal directions from the DEM results, which were applied to develop a Feed Forward Neural Network (FNN) to predict bed porosity based on grain size distribution. The reliable results of DEM simulation and FNN prediction confirm that our framework is successful in predicting porosity change of gravel-bed.

show abstract

LiteNet: Lightweight Neural Network for Detecting Arrhythmias at Resource-Constrained Mobile Devices

Cited by 42 publications

References 30 publications

IoTNet: An Efficient and Accurate Convolutional Neural Network for IoT Devices

IoTNet: An Efficient and Accurate Convolutional Neural Network for IoT Devices

WiFi-Based Real-Time Breathing and Heart Rate Monitoring during Sleep

Combination of Discrete Element Method and Artificial Neural Network for Predicting Porosity of Gravel-Bed River

Contact Info

Product

Resources

About