19 October 2020 in IEEE Transactions on Instrumentation and Measurement
Phase-coding methods have been widely used for three-dimensional (3D) shape measurement, which use sinusoidal phase-shifting patterns to recover wrapped phase and the stair phase-coding patterns to determine the fringe order. However, due to the system nonlinearity, random noises and image blurring, the total number of codewords that can be used is limited. In order to increase the number of codewords, this paper presents a two-digit phase-coding (TDPC) strategy, in which each fringe of the sinusoidal phase-shifting patterns corresponds to a two-digit codeword encoded in the phasecoding patterns. In this way, more codewords can be generated without increasing additional patterns. Experiments of the cup and sculptures have been carried out, and the results confirm that the TDPC method can recover the 3D shape of objects more robustly. Meanwhile, the precision experiment of a standard ball proves the high accuracy of the proposed method.
23 October 2024 in IEEE Journal of Selected Areas in Sensors
Ballistocardiograph (BCG) stands out as a non-contact, non-contact technology for heart monitoring, offering a wealth of cardiovascular parameter information. Its applications overshadow traditional electrocardiogram (ECG) particularly for free-living environment such as home monitoring in recent years. However, challenges arise from the susceptibility of BCG signals to positional variations, bodily movements, and systemic noise, posing formidable obstacles for detection algorithms. In this paper, we propose a novel inter-beat interval (IBI) detection approach with Dynamic Bayesian Network (DBN) for multi-channel fusion, in terms of five unique indicators for precise localization of cardiac activity from extracted features. We also introduced a peak detection method to locate the positions of all HIJK complex within BCG segment, and evaluate the generalization of the proposed method in the simulated environment of different noise generation. The results from dataset comprising 36 healthy subjects and 4 cardiovascular disease (CVD) patients, shows that the proposed method exhibits average coverage rate up to 96.15%, mean square error is 0.04 compared with single channel measures, which suggest the potential of our method in assisting the long-term heartbeat monitoring in free-living environments.
9 August 2021 in IEEE Access
Blood pressure (BP) is an important clinical vital sign that varies from beat-to-beat. Nevertheless, these variations cannot be captured by the conventional cuff-based BP monitors. This study proposes and evaluates novel cuffless frameworks to continuously estimate the 10-beat averaged systolic BP (SBP) and diastolic BP (DBP) during dynamic exercise by fusing information from multiple biosensors using five machine learning algorithms. Over 100 thousand beats of data were collected from 62 subjects (aged 59 ± 10 years), each underwent a maximal exercise stress test. The average length of recording for each subject was 35 minutes. The BP ranges were 75-280 mmHg for SBP and 36-157 mmHg for DBP respectively. Multiple physiological parameters were measured continuously and used as inputs to five machine learning algorithms for estimating the 10-beat SBP and DBP averages before, during and after the cycling exercise. The mean absolute error (MAE) of Gaussian process regression (GPR) model was 4.8 mmHg and 3.4 mmHg for SBP and DBP, respectively. The MAE of multiple linear regression (MLR), regression tree (RT), ensemble of trees (ETs), and support vector machine (SVM) models varied from 6.1 mmHg to 17.6 mmHg and from 4.0 mmHg to 9.7 mmHg for SBP and DBP, respectively. The GPR model outperformed the other four models and showed promising results in estimating the 10-beat averages of both SBP and DBP without a cuff in a general elderly population under dynamic conditions.
25 July 2023 in IEEE Transactions on Circuits and Systems for Video Technology
Automatic generation of painting images is an interesting and difficult task, especially for regional traditional paintings with unique cultural styles while lacking large-scale training sets. In this paper, a hierarchical painting generation method is proposed, which can disentangle the generation of content and style. By mimicking the human painting process, the proposed method introduces multiple content blocks first and gradually generates image contents. In each block, a spatial self-modulation module is proposed to inject local details while preserving the global layout. After the preliminary generation of contents, a series of style blocks are presented to gradually adjust the artistic style. In the style block, an edge-oriented style-modulation module is proposed, which focuses on the lines and edges. In addition, edge adversarial training is used to further improve the quality of generated lines. To train and evaluate the proposed method, we construct datasets for five types of Chinese folk paintings. Experimental results demonstrate that the proposed method can generate high-quality and diverse painting images. More importantly, it can disentangle content and style sufficiently, so that the generation of specific contents or styles can be controlled freely. The datasets and source codes is available at https://github.com/Ritsu-mio/HPGN.