- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Bidirectional Recurrent Auto-Encoder for Photoplethysmogram Denoising
摘要： Photoplethysmography (PPG) has become ubiquitous with the development of smartwatches and the mobile healthcare market. However, PPG is vulnerable to various types of noises which are ever-present in uncontrolled environments, and the key to obtaining meaningful signals depends on successful denoising of PPG. In this context, algorithms have been developed to denoise PPG, but many were validated in controlled settings or are reliant on multiple steps that must all work correctly. This paper proposes a novel PPG denoising algorithm based on bidirectional recurrent denoising auto-encoder (BRDAE) which requires minimal pre-processing steps and have the benefit of waveform feature accentuation beyond simple denoising. The BRDAE was trained and validated on a dataset with artificially augmented noise, and was tested on a large open-database of PPG signals collected from patients enrolled in intensive care units (ICUs) as well as from PPG data collected intermittently during the daily routine of 9 subjects over 24-hours. Denoising with the trained BRDAE improved signal-to-noise ratio of the noise-augmented data by 7.9dB during validation. In the test datasets, the denoised PPG showed statistically significant improvement in heart rate detection as compared to the original PPG in terms of correlation to reference and root-mean-squared error. These results indicate that the proposed method is an effective solution for denoising the PPG signal, and promises values beyond traditional denoising by providing PPG feature accentuation for pulse waveform analysis.
关键词： auto-encoder (AE),denoising,recurrent neural networks (RNN),photoplethysmography (PPG)
更新于2025-09-23 15:23:52
-
[IEEE 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC) - Chicago, IL, USA (2019.6.16-2019.6.21)] 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC) - Oxygen Concentration Dependence of Photovoltaic Properties of Intermediate Band Solar Cells based on Cl-doped ZnTeO
摘要： We present a large-scale study exploring the capability of temporal deep neural networks to interpret natural human kinematics and introduce the first method for active biometric authentication with mobile inertial sensors. At Google, we have created a first-of-its-kind data set of human movements, passively collected by 1500 volunteers using their smartphones daily over several months. We compare several neural architectures for efficient learning of temporal multi-modal data representations, propose an optimized shift-invariant dense convolutional mechanism, and incorporate the discriminatively trained dynamic features in a probabilistic generative framework taking into account temporal characteristics. Our results demonstrate that human kinematics convey important information about user identity and can serve as a valuable component of multi-modal authentication systems. Finally, we demonstrate that the proposed model can also be successfully applied in a visual context.
关键词： recurrent neural networks,mobile computing,biometrics (access control),Authentication,learning
更新于2025-09-23 15:19:57
-
[IEEE 2019 24th Microoptics Conference (MOC) - Toyama, Japan (2019.11.17-2019.11.20)] 2019 24th Microoptics Conference (MOC) - Controlled Generation of Isolated C-points in Few-mode Optical Fiber
摘要： We present a large-scale study exploring the capability of temporal deep neural networks to interpret natural human kinematics and introduce the first method for active biometric authentication with mobile inertial sensors. At Google, we have created a first-of-its-kind data set of human movements, passively collected by 1500 volunteers using their smartphones daily over several months. We compare several neural architectures for efficient learning of temporal multi-modal data representations, propose an optimized shift-invariant dense convolutional mechanism, and incorporate the discriminatively trained dynamic features in a probabilistic generative framework taking into account temporal characteristics. Our results demonstrate that human kinematics convey important information about user identity and can serve as a valuable component of multi-modal authentication systems. Finally, we demonstrate that the proposed model can also be successfully applied in a visual context.
关键词： recurrent neural networks,mobile computing,biometrics (access control),Authentication,learning
更新于2025-09-19 17:13:59
-
[IEEE 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC) - Chicago, IL, USA (2019.6.16-2019.6.21)] 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC) - A simple physical model for three-terminal tandem cell operation
摘要： We present a large-scale study exploring the capability of temporal deep neural networks to interpret natural human kinematics and introduce the first method for active biometric authentication with mobile inertial sensors. At Google, we have created a first-of-its-kind data set of human movements, passively collected by 1500 volunteers using their smartphones daily over several months. We compare several neural architectures for efficient learning of temporal multi-modal data representations, propose an optimized shift-invariant dense convolutional mechanism, and incorporate the discriminatively trained dynamic features in a probabilistic generative framework taking into account temporal characteristics. Our results demonstrate that human kinematics convey important information about user identity and can serve as a valuable component of multi-modal authentication systems. Finally, we demonstrate that the proposed model can also be successfully applied in a visual context.
关键词： recurrent neural networks,mobile computing,biometrics (access control),Authentication,learning
更新于2025-09-19 17:13:59
-
[IEEE 2019 21st International Conference on Transparent Optical Networks (ICTON) - Angers, France (2019.7.9-2019.7.13)] 2019 21st International Conference on Transparent Optical Networks (ICTON) - Machine Learning Based Laser Failure Mode Detection
摘要： Laser degradation analysis is a crucial process for the enhancement of laser reliability. Here, we propose a data-driven fault detection approach based on Long Short-Term Memory (LSTM) recurrent neural networks to detect the different laser degradation modes based on synthetic historical failure data. In comparison to typical threshold-based systems, attaining 24.41% classification accuracy, the LSTM-based model achieves 95.52% accuracy, and also outperforms classical machine learning (ML) models namely Random Forest (RF), K-Nearest Neighbours (KNN) and Logistic Regression (LR).
关键词： degradation,laser,reliability,fault detection,machine learning,recurrent neural networks
更新于2025-09-16 10:30:52
-
[IEEE 2019 IEEE Photonics Conference (IPC) - San Antonio, TX, USA (2019.9.29-2019.10.3)] 2019 IEEE Photonics Conference (IPC) - Optical Sensor Behavior Prediction using LSTM Neural Network
摘要： Optical fiber-based-sensors proved capable of enduring various harsh environments. Long-short-term memory (LSTM) neural-networks are often used for datasets with long- dependences. Here, rare FBG measurements collected from a neutron reactor core were used to build a neural-network capable of predicting the future events inside the reactor.
关键词： Fiber Bragg grating,nuclear reactor core measurements,long-short-term memory,recurrent neural networks
更新于2025-09-11 14:15:04
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - An Hybrid Recurrent Convolutional Neural Network for Crop Type Recognition Based on Multitemporal Sar Image Sequences
摘要： Agriculture monitoring is a key task for producers, governments and decision makers. The analysis of multitemporal remote sensing data provides a cost-effective way to perform this task. Recurrent Neural Networks (RNNs) have been successfully used in temporal modeling problems, while Convolutional Neural Networks (CNNS) are the state-of-the-art in image classification, mainly due to their ability to capture spatial context. In this work, we propose the use of a hybrid network architecture for crop mapping that combines RNNs and CNNs. We evaluate this architecture experimentally upon a Sentinel-1A database from a tropical region in Brazil. The ability of recurrent networks to model temporal context is compared with the conventional image stacking approach. The impact of using CNN learned features rather than context aware handcrafted features is also investigated. In our analysis the hybrid architecture achieved better average class accuracy than alternative approaches based on image stacking and GLCM features.
关键词： Crop Recognition,Convolutional Neural Networks,Recurrent Neural Networks
更新于2025-09-10 09:29:36
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - A Deep Network Approach to Multitemporal Cloud Detection
摘要： We present a deep learning model with temporal memory to detect clouds in image time series acquired by the Seviri imager mounted on the Meteosat Second Generation (MSG) satellite. The model provides pixel-level cloud maps with related confidence and propagates information in time via a recurrent neural network structure. With a single model, we are able to outline clouds along all year and during day and night with high accuracy.
关键词： convolutional neural networks,Seviri,deep learning,Cloud detection,recurrent neural networks
更新于2025-09-09 09:28:46
-
[IEEE 2018 53rd International Universities Power Engineering Conference (UPEC) - Glasgow, United Kingdom (2018.9.4-2018.9.7)] 2018 53rd International Universities Power Engineering Conference (UPEC) - Load and PV Generation Forecast Based Cost Optimization for Nanogrids with PV and Battery
摘要： Power system resiliency and robustness became major concerns of the system operators and researchers after the introduction of the smart grid concept. The improvements in the battery storage systems (BSS) and the photovoltaic (PV) systems encourage power systems operators to enable the use of those systems in resiliency and robustness studies. Utilization of those systems not only contributes to the robustness of the power systems but also decrease the operational costs. There are several methods in literature to operate the grid systems with partitions of PV and BSS in the most economical way. Although these methods are straightforward and work fine, they can not guarantee the most economical result on a daily basis. In this paper, deep learning based PV generation and load forecasts are used to improve the results of optimization in terms of economic aspects in nano-grid applications. In the considered system, there are loads, PV generation units, BSS and grid connection. Bi-directional power flow is permitted between the main grid and the nano-grid system. The forecasting methodologies and used optimization algorithms will be explained in this paper.
关键词： demand-side management,smart grids,mathematical programming,recurrent neural networks,forecasting
更新于2025-09-04 15:30:14