Search

【Objective】In order to meet the growing demand for ultra-gigabit, from gigabit to 10-gigabit, from The 5th Generation Fixed networks (F5G) to F5G-Advanced (F5.5G), 50 Gbit/s Passive Optical Network (PON) is considered to be an important part of F5.5G. This paper conducts a thorough study of 50 Gbit/s PON technology, reflecting the latest advancements in access networks.【Methods】This paper initially addresses the difficulties in achieving high sensitivity in 50 Gbit/s PON, and proposes a solution. 50 Gbit/s Non-Return-to-Zero (NRZ) signals pass through Avalanche Photodiode (APD) detectors to form macroscopic currents that can be detected under strong electric fields. These currents are then amplified by a Transresistance Amplifier (TIA) and converted into voltage outputs. After balancing, the Feed Forward Equalizer (FFE) and Decision Feedback Equalizer (DFE) of optical Digital Signal Processing (oDSP) chip are used to compensate the trailing phenomenon of pulse signal, and the influence of intersymbol interference is minimized by DFE. Then the paper analyses the key technologies such as APD, TIA and oDSP, comparing the reception performance between 25 Gbit/s and 50 Gbit/s APDs.【Results】Experimental test results show that the 25 Gbit/s APD maintains error-free signal reception at -8.48 dBm over 4 minutes, and reaches -26.61 dBm at a Bit Error Rate(BER) of 2.78e-2. The 50 Gbit/s APD exhibits no bit errors at -8.97 dBm and achieves -27.05 dBm at the same BER, with the second 50 Gbit/s APD set demonstrating similar results.【Conclusion】The 50 Gbit/s APD has superior receiving sensitivity and performance, making it highly suitable for 50 Gbit/s PON optical modules to help achieve high receiver sensitivity. The paper suggests a feasible approach for cost reduction in future implementations, focusing on the balance technology and APD.

ObjectiveConducting research on the recognition of yak meat parts can help avoid confusion and substandard parts during the production and sales of yak meat, improve the transparency and traceability of the yak meat industry, and ensure food safety. To achieve fast and accurate recognition of different parts of yak meat, this study proposed an improved residual network model and developed a smartphone based yak meat part recognition software.MethodsFirstly, the original data set of 1960 yak tenderloin, high rib, shank and brisket were expanded by 8 different data enhancement methods, including horizontal flip, vertical flip, random direction rotation 30°, random direction rotation 120°, random direction rotation 300°, contrast adjustment, saturation adjustment and hue adjustment. After expansion, 17,640 yak meat images of different parts were obtained. The expanded yak meat images of different parts were divided according to the 4:1 ratio, resulting in 14,112 yak meat sample images in the training set and 3528 yak meat sample images in the test set. Secondly, the convolutional block attention module (CBAM) was integrated into each residual block of the original network model to enhance the extraction of key detail features of yak images in different parts. At the same time, introducing this mechanism into the network model could achieve greater accuracy improvement with less computational overhead and fewer parameters. In addition, in the original network model, the full connection layer was directly added after all residual blocks instead of global average pooling and global maximum pooling, which could improve the accuracy of the network model, prevent overfitting, reduce the number of connections in subsequent network layers, accelerate the execution speed of the network model, and reduce the computing time when the mobile phone recognized images. Thirdly, different learning rates, weight attenuation coefficients and optimizers were used to verify the influence of the improved ResNet18_CBAM network model on convergence speed and accuracy. According to the experiments, the stochastic gradient descent (SGD) algorithm was adopted as the optimizer, and when the learning rate was 0.001 and the weight attenuation coefficient was 0, the improved ReaNet18_CBAM network model had the fastest convergence speed and the highest recognition accuracy on different parts of yak data sets. Finally, the PyTorch Mobile module in PyTorch deep learning framework was used to convert the trained ResNet18_CBAM network model into TorchScript model and saved it in *.ptl. Then, the yak part recognition App was developed using the Android Studio development environment, which included two parts: Front-end interface and back-end processing. The front-end of the App uses *.xml for a variety of price control layout, and the back-end used Java language development. Then TorchScript model in *.ptl was used to identify different parts of yak meat.Results and Discussions]In this study, CBAM, SENet, NAM and SKNet, four popular attentional mechanism modules, were integrated into the original ResNet18 network model and compared by ablation experiments. Their recognition accuracy on different parts of yak meat dataset were 96.31%, 94.12%, 92.51% and 93.85%, respectively. The results showed that among CBAM, SENet, NAM and SKNet, the recognition accuracy of ResNet18 CBAM network model was significantly higher than that of the other three attention mechanism modules. Therefore, the CBAM attention mechanism module was chosen as the improvement module of the original network model. The accuracy of the improved ResNet18_CBAM network model in the test set of 4 different parts of yak tenderloin, high rib, shank and brisket was 96.31%, which was 2.88% higher than the original network model. The recognition accuracy of the improved ResNet18_CBAM network model was compared with AlexNet, VGG11, ResNet34 and ResNet18 network models on different parts of yak test set. The improved ResNet18_CBAM network model had the highest accuracy. In order to verify the actual results of the improved ResNet18_CBAM network model on mobile phones, the test conducted in Xining beef and mutton wholesale market. In the actual scenario testing on the mobile end, a total of 54, 59, 51, and 57 yak tenderloin, high rib, shank and brisket samples were collected, respectively. The number of correctly identified samples and the number of incorrectly identified samples were counted respectively. Finally, the recognition accuracy of tenderloin, high rib, shank and brisket of yak reached 96.30%, 94.92%, 98.04% and 96.49%, respectively. The results showed that the improved ResNet18_CBAM network model could be used in practical applications for identifying different parts of yak meat and has achieved good results.ConclusionsThe research results can help ensure the food quality and safety of the yak industry, improve the quality and safety level of the yak industry, improve the yak trade efficiency, reduce the cost, and provide technical support for the intelligent development of the yak industry in the Qinghai-Tibet Plateau region.

Identifying of yak is indispensable for individual documentation, behavior monitoring, precise feeding, disease prevention and control, food traceability, and individualized breeding. Aiming at the application requirements of animal individual identification technology in intelligent informatization animal breeding platforms, a yak face recognition algorithm based on transfer learning and multiscale feature fusion, i.e., transfer learning-multiscale feature fusion-VGG(T-M-VGG) was proposed. The sample data set of yak facial images was produced by a camera named GoPro HERO8 BLACK. Then, a part of dataset was increased by the data enhancement ways that involved rotating, adjusting the brightness and adding noise to improve the robustness and accuracy of model. T-M-VGG, a kind of convolutional neural network based on pre-trained visual geometry group network and transfer learning was input with normalized dataset samples. The feature map of Block3, Block4 and Block5 were considered as F3, F4 and F5, respectively. What's more, F3 and F5 were taken by the structure that composed of three parallel dilated convolutions, the dilation rate were one, two and three, respectively, to dilate the receptive filed which was the map size of feature map. Further, the multiscale feature maps were fused by the improved feature pyramid which was in the shape of stacked hourglass structure. Finally, the fully connected layer was replaced by the global average pooling to classify and reduce a large number of parameters. To verify the effectiveness of the proposed model, a comparative experiment was conducted. The experimental results showed that recognition accuracy rate in 38,800 data sets of 194 yaks reached 96.01%, but the storage size was 70.75 MB. Twelve images representing different yak categories from dataset were chosen randomly for occlusion test. The origin images were masked with different shape of occlusions. The accuracy of identifying yak individuals was 83.33% in the occlusion test, which showed that the model had mainly learned facial features. The proposed algorithm could provide a reference for research of yak face recognition and would be the foundation for the establishment of smart management platform.

Given inevitable age-related decreases in physical or mental capacity, studies on health-related behaviour (HRB) clustering in older people provide an opportunity to reduce health-care costs and promote healthy ageing. This study explores the clustering of HRBs and transition probabilities of cluster memberships over time, and compares sociodemographic characteristics of these clusters among Chinese and Japanese middle-aged and older adults. Using the China Health and Retirement Longitudinal Study (CHARLS) from 2011 to 2015 (N = 19614) and the Japanese Study of Ageing and Retirement (JSTAR) from 2007 to 2011 (N = 7,080), Latent Transition Analysis was applied to investigate the clustering and change in clustering memberships of smoking, alcohol consumption, physical activity and body mass index. Multivariate logistic regression was used to explore the sociodemographic characteristics of these longitudinal HRB cluster members. We identified four common clusters in CHARLS and JSTAR: 'smoking', 'overweight or obese', 'healthy lifestyle' and 'current smoking with drinking', and an additional cluster named 'ex-smoking with drinking' in JSTAR. Although HRB cluster members were largely stable in both cohorts, participants in China tended to move towards an unhealthy lifestyle, while participants in Japan did the opposite. We also found that participants who smoked and drank were more likely to be male, younger, less educated and unmarried in both cohorts, but the overweight or obese participants were female, urban and higher income in CHARLS but not JSTAR. Our study not only contributes to the knowledge of longitudinal changes in health-related behavioural clustering patterns in an Asian elderly population, but may also facilitate the design of targeted multi-behavioural interventions to promote healthy lifestyles among older people in both countries. [ABSTRACT FROM AUTHOR]

Objective In order to cope with the growing demand for ultra-gigabit, from gigabit to 10-gigabit, from The 5th Generation Fixed networks(F5G) to F5G-Advanced(F5. 5G), 50 Gbit/s Passive Optical Network (PON) is considered to be an important part of F5. 5G. Therefore, according to the current access network development situation, 50 Gbit/s PON technology is deeply studied in this paper. Methods This paper first introduces the difficulties in achieving high sensitivity of 50 Gbit/s PON, and proposes a solution. 50 Gbit/s Non-Return-Zero (NRZ) signals pass through Avalanche Photodiode (APD) detectors to form macroscopic currents that can be detected under the action of strong electric fields. The current is amplified by a Transresistance Amplifier (TIA) and converted into a voltage output. After balancing, the Feed Forward Equalizer (FFE) and Decision Feedback Equalizer (DFE) of optical Digital Signal Processing (oDSP) chip are used to compensate the trailing phenomenon of pulse signal, and then the influence of intersymbol interference is minimized by DFE. Then the paper analyses the key technologies such as APD, TIA and oDSP, and the receiving performance is compared with that of 25 Gbit/s APD. Results According to the experimental test results of the two groups, the received optical power of the 25 Gbit/s APD in the first group is -8.48 dBm when the receiving signal has no error code during the test time of 4 min, and the received optical power reaches -26.61 dBm when the Bit Error Rate(BER) is 2.78e-2. In the case of 50 Gbit/s APD, the received optical power is - 8.97 dBm when the received signal has no bit error in 4 min, and the received optical power reaches -27.05 dBm when the BER is 2.78e-2. The second set of 50 Gbit/s APD-2 data also achieves the same experimental results. Conclusion In conclusion, 50 Gbit/s APD has higher receiving sensitivity, better performance, and is more suitable for use in 50 Gbit/s PON optical modules to achieve high receiver sensitivity. Finally, a feasible scheme is proposed on the balance technology and APD for future cost reduction. [ABSTRACT FROM AUTHOR]