Abstract Pose estimation is the detection of human action poses, which is an important task of computer vision. The requirements of tasks such as unmanned driving and intelligent surveillance have also contributed to the development of human pose estimation. In this context, deep learning (DL) has a remarkable impact on human pose estimation. In this study, we investigate a pose estimation algorithm called convolutional pose machines (CPM) and implement it on a mobile platform (i.e., Android). By combining the classical CPM and the mobile deep learning framework Mobile AI Compute Engine (MACE), the model is deployed to the mobile platform to estimate the human pose directly and locally on the mobile phone without relying on the Internet. Thus, the proposed method can achieve effective performance while protecting users’ personal data. Experimental results on real-world data validate that this system has achieved the expected results of accurate recognition of common actions with a simple interface.
In the management of lung nodules, we are desirable to predict nodule evolution in terms of its diameter variation on Computed Tomography (CT) scans and then provide a follow-up recommendation according to the predicted result of the growing trend of the nodule. In order to improve the performance of growth trend prediction for lung nodules, it is vital to compare the changes of the same nodule in consecutive CT scans. Motivated by this, we screened out 4,666 subjects with more than two consecutive CT scans from the National Lung Screening Trial (NLST) dataset to organize a temporal dataset called NLSTt. In specific, we first detect and pair regions of interest (ROIs) covering the same nodule based on registered CT scans. After that, we predict the texture category and diameter size of the nodules through models. Last, we annotate the evolution class of each nodule according to its changes in diameter. Based on the built NLSTt dataset, we propose a siamese encoder to simultaneously exploit the discriminative features of 3D ROIs detected from consecutive CT scans. Then we novelly design a spatial-temporal mixer (STM) to leverage the interval changes of the same nodule in sequential 3D ROIs and capture spatial dependencies of nodule regions and the current 3D ROI. According to the clinical diagnosis routine, we employ hierarchical loss to pay more attention to growing nodules. The extensive experiments on our organized dataset demonstrate the advantage of our proposed method. We also conduct experiments on an in-house dataset to evaluate the clinical utility of our method by comparing it against skilled clinicians.
To improve the image quality of electromagnetic tomography (EMT), a new image reconstruction method of EMT based on a particle filtering algorithm is presented. Firstly, the principle of image reconstruction of EMT is analyzed. Then the search process for the optimal solution for image reconstruction of EMT is described as a system state estimation process, and the state space model is established. Secondly, to obtain the minimum variance estimation of image reconstruction, the optimal weights of random samples obtained from the state space are calculated from the measured information. Finally, simulation experiments with five different flow regimes are performed. The experimental results have shown that the average image error of reconstruction results obtained by the method mentioned in this paper is 42.61%, and the average correlation coefficient with the original image is 0.8706, which are much better than corresponding indicators obtained by LBP, Landweber and Kalman Filter algorithms. So, this EMT image reconstruction method has high efficiency and accuracy, and provides a new method and means for EMT research.
Intelligent transport systems are an advanced technology in the field of regulating traffic and pedestrian flows. And the implementation of new scientific research in this area allows us to develop this technology and implement new transport functionality. The implementation of the functionality of unmanned vehicles and aero-transport in the environment of intelligent transport systems is considered. It is proposed to improve the orientation quality of unmanned vehicles through its interaction with already known intelligent transport systems.
Spherical Harmonic (SH) lighting is widely used for real-time rendering within Precomputed Radiance Transfer (PRT) systems. SH coefficients are precomputed and stored at object vertices, and combined interactively with SH lighting coefficients to enable effects like soft shadows, interreflections, and glossy reflection. However, the most common PRT techniques assume distant, low-frequency environment lighting, for which SH lighting coefficients can easily be computed once per frame. There is currently limited support for near-field illumination and area lights, since it is non-trivial to compute the SH coefficients for an area light, and the incident lighting (SH coefficients) varies over the object geometry. We present an efficient closed-form solution for projection of uniform polygonal area lights to spherical harmonic coefficients of arbitrary order, enabling easy adoption of accurate area lighting in PRT systems, with no modifications required to the core PRT framework. Our method only requires computing zonal harmonic (ZH) coefficients, for which we introduce a novel recurrence relation. In practice, ZH coefficients are built up iteratively, with computation linear in the desired SH order. General SH coefficients can then be obtained by the recently developed sparse zonal harmonic rotation method.
Abstract This paper adopted a multi-objective optimization approach, integrating LCA with TEA, to systematically analyze the relationship between the economic and environmental performance of PV-battery systems at manufacturing facilities. For this purpose, under the inspiration of the ReCiPe life cycle assessment method, information from several sources was compiled and adapted to quantify the different environmental impacts of the manufacturing facility’s energy consumption in the sizing formulation. The other objective function is formulated as the total cost of energy consumption, including the installation, operation, and maintenance cost of the PV-battery system and the cost of energy purchased from the grid. A case study of a PV-battery system at a typical lithium-battery assembly manufacturing facility is presented, with the facility’s energy consumption under a high throughput target simulated as the load profile. The results highlight the trade-offs between minimizing the costs and the environmental impacts of the facility’s energy consumption. It is also found that only considering the environmental impacts during the operation stage can cause underestimation of the impacts and lead to a selection of a more polluting PV-battery sizing configuration. This result further justifies the necessity of considering LCA in the PV-battery sizing problems.
Background: In type 2 diabetes mellitus (T2DM) patients, left ventricular systolic dyssynchrony (LVSD) with normal left ventricular ejection fraction (LVEF) and normal myocardial perfusion could referred to as subclinical myocardial damage, which is difficult to diagnose at an early stage. Epicardial adipose tissue, a distinctive heart-specific visceral fat, is closely related to various cardiovascular diseases. The objective of this study was to investigate the correlation between epicardial fat volume (EFV) and subclinical myocardial damage in T2DM patients. Methods: This retrospective cross-sectional study included 117 T2DM patients with normal myocardial perfusion by single photon emission computed tomography-computed tomography (SPECT-CT) and normal LVEF by echocardiography. The study was conducted from January 2018 to December 2022. Patient data were collected through electronic medical records including basic patient information, medical history, laboratory tests, and medication data. The EFV was quantified through a non-contrast CT scan. Quantitative indicators of LVSD including phase standard deviation (PSD) and phase histogram bandwidth (PBW) were obtained through phase analysis of the gated rest myocardial perfusion imaging (MPI). Additionally, 83 healthy individuals at the same time were selected to gain the reference threshold of LVSD indicators (13.1° for PSD and 37.6° for PBW). Univariate and multivariable logistic regression models were performed to analyze factors influencing LVSD. A generalized additive model (GAM) was applied to explore the relationship between EFV and LVSD. The receiver operating characteristic (ROC) curve was used to analyze the diagnostic value of EFV for LVSD. Results: Among all patients, 32 (27.4%) patients had LVSD. Compared with the non-LVSD group, the body mass index (BMI) and EFV were higher in the LVSD group (25.83±2.66 vs. 23.94±3.13 kg/m2; 142.41±44.17 vs. 108.01±38.24 cm3, respectively, both P<0.05). Multivariate regression analysis revealed that EFV was independently associated with LVSD [odds ratio (OR) =1.19; 95% confidence interval (CI): 1.06–1.34; P=0.003]. Age, BMI, incidence of hypertension, and LVSD were increased with tertiles of EFV (all P<0.05). The GAM indicated a linear association between EFV and LVSD. The ROC curve analysis concluded that the area under the curve (AUC) of EFV for predicting subclinical myocardial damage in T2DM patients was 0.732 (95% CI: 0.633–0.831, P<0.001), with the optimal threshold of 122.26 cm3, sensitivity of 71.9%, and specificity of 69.4%. Conclusions: EFV is an independent risk factor for LVSD in T2DM patients with normal LVEF and normal MPI, which could potentially serve as a novel imaging marker and a potential therapeutic target for subclinical myocardial damage.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)