Yemian Li

Bio: Yemian Li is an academic researcher. The author has contributed to research in topics: Computer science & Pattern recognition (psychology). The author has an hindex of 2, co-authored 6 publications receiving 11 citations.

Infrared and visible image fusion based on QNSCT and Guided Filter

Abstract: Image fusion is the process of fusing multiple images of the same scene to obtain a more informative image for human eye perception. In this paper, a new fusion framework based on Quaternion Non-Subsampled Contourlet Transform (QNSCT) and Guided Filter detail enhancement is designed to address the problems of inconspicuous infrared targets and poor background texture in Infrared and visible image fusion. The proposed method uses the quaternion wavelet transform for the first time instead of the traditional Non-Subsampled Pyramid Filter Bank structure in the Non-Subsampled Contourlet Transform (NSCT). The flexible multi-resolution of quaternion wavelet and the multi-directionality of NSCT are fully utilized to refine the multi-scale decomposition scheme. On the other hand, the coefficient matrix obtained from the proposed QNSCT algorithm is fused using a weight refinement algorithm based on the guided filter. The fusion scheme is divided into four steps. First, the Infrared and visible images are decomposed into multi-directional and multiscale coefficient matrices using QNSCT. The experimental results show that the proposed algorithm not only extracts important visual information from the source image, but also preserves the texture information in the scene better. Meanwhile, the scheme outperforms state-of-the-art methods in both subjective and objective evaluations.

Dual-Band Terahertz Perfect Absorber Based on Metal Micro-Nano Structure

Abstract: We propose a sub-wavelength range-based dual-band tunable ideal terahertz metamaterial perfect absorber. The absorber structure consists of three main layers, with the absorber layer consisting of a metal I-shaped structure. By simulating the incident wave absorbance of the structure, we found that the structure has more than 99% absorption peaks in both bands. In addition, we have investigated the relationship between structural absorbance and the structural geometrical parameters. We have studied the relationship between the thickness of the metal absorber layer hb and the absorbance of the metamaterial structure in the 4–14 THz band. Secondly, we have studied the relationship between the thickness of the SiO2 dielectric layer and structural absorbance. Afterwards, we have studied the relationship between the incident angle of the incident electromagnetic wave and structural absorbance. Finally, we have studied the relationship between the length of the metal structure and structural absorbance. The structure can be effectively used for detectors, thermal emitters, terahertz imaging and detection.

Single Infrared Image Stripe Removal via Residual Attention Network

Abstract: The non-uniformity of the readout circuit response in the infrared focal plane array unit detector can result in fixed pattern noise with stripe, which seriously affects the quality of the infrared images. Considering the problems of existing non-uniformity correction, such as the loss of image detail and edge blurring, a multi-scale residual network with attention mechanism is proposed for single infrared image stripe noise removal. A multi-scale feature representation module is designed to decompose the original image into varying scales to obtain more image information. The product of the direction structure similarity parameter and the Gaussian weighted Mahalanobis distance is used as the similarity metric; a channel spatial attention mechanism based on similarity (CSAS) ensures the extraction of a more discriminative channel and spatial feature. The method is employed to eliminate the stripe noise in the vertical and horizontal directions, respectively, while preserving the edge texture information of the image. The experimental results show that the proposed method outperforms four state-of-the-art methods by a large margin in terms of the qualitative and quantitative assessments. One hundred infrared images with different simulated noise intensities are applied to verify the performance of our method, and the result shows that the average peak signal-to-noise ratio and average structural similarity of the corrected image exceed 40.08 dB and 0.98, respectively.

The association between social engagement and depressive symptoms in middle-aged and elderly Chinese: A longitudinal subgroup identification analysis under causal inference frame

Abstract: Background Studies have suggested that there is a significant association between social engagement and depression symptoms. However, this association may differ in people with different features such as different sociodemographic characteristics and health conditions. Methods Research data were obtained from the CHARLS database. The causal inference was performed with the propensity score. We used the linear mixed-effects model tree algorithm under the causal inference frame for subgroup identification analysis. Results We included 13,521 participants, and the median follow-up time is 4 years. Under the casual inference frame, the association between social engagement and depression symptoms is confirmed for all included individuals (OR = 0.957, P = 0.016; 95%CI: 0.923–0.992). Using the linear mixed-effects model tree, we found two subgroups, including middle-aged and elderly residents who live in rural areas with <6 h of sleep and those living in urban areas, could benefit more from social engagement. After using the propensity score method, all the two subgroups selected are statistically significant (P = 0.007; P = 0.013) and have a larger effect size (OR = 0.897, 95%CI: 0.830–0.971; OR = 0.916, 95%CI: 0.854–0.981) than the whole participants. As for sex difference, this associations are statistically significant in male (OR: 0.935, P = 0.011, 95%CI: 0.888–0.985) but not in female (OR: 0.979, P = 0.399, 95%CI: 0.931–1.029). Conclusions Our findings indicate that social engagement may reduce the risks of depressive symptoms among all individuals. The identified subgroups of middle-aged and elderly residents who live in rural areas with <6 h of sleep and those who live in urban areas may benefit more from the social engagement than the whole participants.

Bloodstain Identification Based on Visible/Near-Infrared Hyperspectral Imaging With Convolutional Neural Network

Abstract: Blood samples are easily damaged in traditional bloodstain detection and identification. In complex scenes with interfering objects, bloodstain identification may be inaccurate, with low detection rates and false-positive results. In order to meet these challenges, we propose a bloodstain detection and identification method based on hyperspectral imaging and mixed convolutional neural networks, which enables fast and efficient non-destructive identification of bloodstains. In this study, we apply visible/near-infrared reflectance hyperspectral imaging in the 380–1000 nm spectral region to analyze the shape, structure, and biochemical characteristics of bloodstains. Hyperspectral images of bloodstains on different substrates and six bloodstain analogs are experimentally obtained. The acquired spectral pixels are pre-processed by Principal Component Analysis (PCA). For bloodstains and different bloodstain analogs, regions of interest are selected from each substance to obtain pixels, which are further used in convolutional neural network (CNN) modeling. After the mixed CNN modeling is completed, pixels are selected from the hyperspectral images as a test set for bloodstains and bloodstain analogs. Finally, the bloodstain recognition ability of the mixed 2D-3D CNN model is evaluated by analyzing the kappa coefficient and classification accuracy. The experimental results show that the accuracy of the constructed CNN bloodstain identification model reaches 95.4%. Compared with other methods, the bloodstain identification method proposed in this study has higher efficiency and accuracy in complex scenes. The results of this study will provide a reference for the future development of the bloodstain online detection system.

Switchable terahertz absorber from single broadband to triple-narrowband

Abstract: We proposed a switchable multifunctional terahertz (THz) absorber based on graphene and vanadium dioxide (VO 2 ), and investigated the absorption properties and the tuning of the absorber by using Computer Simulation Technology (CST) microwave studio. It was found that, when VO 2 is in dielectric phase, the structure shows a single broadband absorption from 0.8 to 2.4 THz range. The amplitude of the absorption can be tuned from 95 % to 20 % by changing the Fermi energy level of the graphene. And the absorption is found to be insensitive to the polarization angle and the incident angle. When VO 2 is in metallic phase, the absorber shows triple narrowband absorption. Utilizing impedance matching theory and transmission line theory, the physical mechanism of the absorber is investigated. • The designed structure is simple and easy to make in practice. • The proposed absorber has high efficient absorptivity. • The absorber enables functional switching between broadband and triple narrowband. • The absorber can achieve dynamic tuning of the single broadband absorptance.

Association between specific social activities and depressive symptoms among older adults: A study of urban-rural differences in China

Abstract: Background Engaging in social activities can help older persons with their depressed symptoms. Few studies, however, have looked into the connection between social interactions and depressed symptoms in Chinese older persons. The aim of this study was to investigate differences in older Chinese individuals' social activity involvement and depressive symptoms across urban and rural settings. Methods A cross-sectional investigation using information from the 2018 China Health and Retirement Longitudinal Study (CHARLS), which was limited to older individuals aged 60 and over. Generalized linear models were constructed to assess the effects of participants' characteristics and specific social activities on CES-D scores. The association between specific social activities and depressed symptoms was investigated using multivariate logistic regression analysis. Results In this study, it was discovered that older individuals had a prevalence of depressed symptoms of 36.2%, with rural older adults having a greater prevalence of depressive symptoms (39.7%) than urban older adults (30.9%). Our results showed that for urban respondents, providing help to others (not regularly. OR = 0.753, 95% CI: 0.579–0.980, P = 0.035), going to a sport (not regularly. OR = 0.685, 95% CI: 0.508–0.924, P = 0.013), and using the Internet (not regular. OR = 0.613, 95% CI: 0.477–0.789, P < 0.001; almost weekly. OR = 0.196, 95% CI: 0.060–0.645, P = 0.007) were all significantly and negatively associated with depressive symptoms, while for rural respondents, interacting with friends (not regularly. OR = 1.205, 95% CI: 1.028–01.412, P = 0.021) and using the Internet (not regularly. OR = 0.441, 95% CI: 0.278–0.698, P < 0.001) were significantly and negatively associated with depressive symptoms. Conclusions According to our research, there is a cross-sectional relationship between participating in a specific social activity and depressed symptoms in Chinese older adults, and this relationship varies across urban and rural older adults. This suggests that taking part in specific social activities may be crucial for reducing depression symptoms in older persons, developing more focused interventions that might support healthy aging, and offering a guide for policymakers and activists working to improve the mental health of seniors.

Application of Machine Learning in Multi-Directional Model to Follow Solar Energy Using Photo Sensor Matrix

Abstract: In this paper, we introduce a deep neural network (DNN) for forecasting the intra-day solar irradiance, photovoltaic PV plants, regardless of whether or not they have energy storage, can benefit from the work being done here. The proposed DNN utilises a number of different methodologies, two of which are cloud motion analysis and machine learning, in order to make forecasts regarding the climatological conditions of the future. In addition to this, the accuracy of the model was evaluated in light of the data sources that were easily accessible. In general, four different cases have been investigated. According to the findings, the DNN is capable of making more accurate and reliable predictions of the incoming solar irradiance than the persistent algorithm. This is the case across the board. Even without any actual data, the proposed model is considered to be state-of-the-art because it outperforms the current NWP forecasts for the same time horizon as those forecasts. When making predictions for the short term, using actual data to reduce the margin of error can be helpful. When making predictions for the long term, however, weather information can be beneficial.