CSI Feedback Model Based on Multi-Source Characterization in FDD Systems.

In wireless communication, to fully utilize the spectrum and energy efficiency of the system, it is necessary to obtain the channel state information (CSI) of the link. However, in Frequency Division Duplexing (FDD) systems, CSI feedback wastes part of the spectrum resources. In order to save spectrum resources, the CSI needs to be compressed. However, many current deep-learning algorithms have complex structures and a large number of model parameters. When the computational and storage resources are limited, the large number of model parameters will decrease the accuracy of CSI feedback, which cannot meet the application requirements. In this paper, we propose a neural network-based CSI feedback model, Mix_Multi_TransNet, which considers both the spatial characteristics and temporal sequence of the channel, aiming to provide higher feedback accuracy while reducing the number of model parameters. Through experiments, it is found that Mix_Multi_TransNet achieves higher accuracy than the traditional CSI feedback network in both indoor and outdoor scenes. In the indoor scene, the NMSE gains of Mix_Multi_TransNet are 4.06 dB, 4.92 dB, 4.82 dB, and 6.47 dB for compression ratio η = 1/8, 1/16, 1/32, 1/64, respectively. In the outdoor scene, the NMSE gains of Mix_Multi_TransNet are 3.63 dB, 6.24 dB, 4.71 dB, 4.60 dB, and 2.93 dB for compression ratio η = 1/4, 1/8, 1/16, 1/32, 1/64, respectively.

Enhancing kiwifruit flower pollination detection through frequency domain feature fusion: a novel approach to agricultural monitoring.

The pollination process of kiwifruit flowers plays a crucial role in kiwifruit yield. Achieving accurate and rapid identification of the four stages of kiwifruit flowers is essential for enhancing pollination efficiency. In this study, to improve the efficiency of kiwifruit pollination, we propose a novel full-stage kiwifruit flower pollination detection algorithm named KIWI-YOLO, based on the fusion of frequency-domain features. Our algorithm leverages frequency-domain and spatial-domain information to improve recognition of contour-detailed features and integrates decision-making with contextual information. Additionally, we incorporate the Bi-Level Routing Attention (BRA) mechanism with C3 to enhance the algorithm's focus on critical areas, resulting in accurate, lightweight, and fast detection. The algorithm achieves a m A P 0.5 of 91.6% with only 1.8M parameters, the AP of the Female class and the Male class reaches 95% and 93.5%, which is an improvement of 3.8%, 1.2%, and 6.2% compared with the original algorithm. Furthermore, the Recall and F1-score of the algorithm are enhanced by 5.5% and 3.1%, respectively. Moreover, our model demonstrates significant advantages in detection speed, taking only 0.016s to process an image. The experimental results show that the algorithmic model proposed in this study can better assist the pollination of kiwifruit in the process of precision agriculture production and help the development of the kiwifruit industry.

Distribution Characteristics of Nitrogen-Cycling Microorganisms in Deep-Sea Surface Sediments of Western South China Sea.

Nitrogen-cycling processes in the deep sea remain understudied. This study investigates the distribution of nitrogen-cycling microbial communities in the deep-sea surface sediments of the western South China Sea, using metagenomic sequencing and real-time fluorescent quantitative PCR techniques to analyze their composition and abundance, and the effects of 11 environmental parameters, including NH4+-N, NO3--N, NO2--N, PO43--P, total nitrogen (TN), total organic carbon (TOC), C/N ratio, pH, electrical conductivity (EC), SO42-, and Cl-. The phylum- and species-level microbial community compositions show that five sites can be grouped as a major cluster, with sites S1 and S9 forming a sub-cluster, and sites S13, S19, and S26 forming the other; whereas sites S3 and S5 constitute a separate cluster. This is also evident for nitrogen-cycling functional genes, where their abundance is influenced by distinct environmental conditions, including water depths (shallower at sites S1 and S9 against deeper at sites S13, S19, and S26) and unique geological features (sites S3 and S5), whereas the vertical distribution of nitrogen-cycling gene abundance generally shows a decreasing trend against sediment depth. Redundancy analysis (RDA) exploring the correlation between the 11 environmental parameters and microbial communities revealed that the NO2--N, C/N ratio, and TN significantly affect microbial community composition (p < 0.05). This study assesses the survival strategies of microorganisms within deep-sea surface sediments and their role in the marine nitrogen cycle.

Real-time dense small object detection algorithm based on multi-modal tea shoots.

Introduction: The difficulties in tea shoot recognition are that the recognition is affected by lighting conditions, it is challenging to segment images with similar backgrounds to the shoot color, and the occlusion and overlap between leaves. Methods: To solve the problem of low accuracy of dense small object detection of tea shoots, this paper proposes a real-time dense small object detection algorithm based on multimodal optimization. First, RGB, depth, and infrared images are collected form a multimodal image set, and a complete shoot object labeling is performed. Then, the YOLOv5 model is improved and applied to dense and tiny tea shoot detection. Secondly, based on the improved YOLOv5 model, this paper designs two data layer-based multimodal image fusion methods and a feature layerbased multimodal image fusion method; meanwhile, a cross-modal fusion module (FFA) based on frequency domain and attention mechanisms is designed for the feature layer fusion method to adaptively align and focus critical regions in intra- and inter-modal channel and frequency domain dimensions. Finally, an objective-based scale matching method is developed to further improve the detection performance of small dense objects in natural environments with the assistance of transfer learning techniques. Results and discussion: The experimental results indicate that the improved YOLOv5 model increases the mAP50 value by 1.7% compared to the benchmark model with fewer parameters and less computational effort. Compared with the single modality, the multimodal image fusion method increases the mAP50 value in all cases, with the method introducing the FFA module obtaining the highest mAP50 value of 0.827. After the pre-training strategy is used after scale matching, the mAP values can be improved by 1% and 1.4% on the two datasets. The research idea of multimodal optimization in this paper can provide a basis and technical support for dense small object detection.

A national survey on how to improve traditional Chinese medicine learning internationally: Perceptions from both teachers and students.

Background: With the increasing popularity of traditional Chinese medicine (TCM) by the global community, how to teach basic knowledge of TCM to international students and improve the teaching quality are important issues for teachers of TCM. The present study was to analyze the perceptions from both students and teachers on how to improve TCM learning internationally. Methods: A cross-sectional national survey was conducted at 23 universities/colleges across China. A structured, self-reported on-line questionnaire was administered to 34 Chinese teachers who taught TCM course in English and to 1016 international undergraduates who were enrolled in the TCM course in China between 2017 and 2021. Results: Thirty-three (97.1%) teachers and 900 (88.6%) undergraduates agreed Chinese culture should be fully integrated into TCM courses. All teachers and 944 (92.9%) undergraduates thought that TCM had important significance in the clinical practice. All teachers and 995 (97.9%) undergraduates agreed that modern research of TCM is valuable. Thirty-three (97.1%) teachers and 959 (94.4%) undergraduates thought comparing traditional medicine in different countries with TCM can help the students better understand TCM. Thirty-two (94.1%) teachers and 962 (94.7%) undergraduates agreed on the use of practical teaching method with case reports. From the perceptions of the undergraduates, the top three beneficial learning styles were practice (34.3%), teacher's lectures (32.5%), case studies (10.4%). The first choice of learning mode was attending to face-to-face teaching (82.3%). The top three interesting contents were acupuncture (75.5%), Chinese herbal medicine (63.8%), and massage (55.0%). Conclusion: To improve TCM learning among international undergraduates majoring in conventional medicine, integration of Chinese culture into TCM course, comparison of traditional medicine in different countries with TCM, application of the teaching method with case reports, and emphasization of clinical practice as well as modern research on TCM should be fully considered.

[Warm acupuncture on chronic obstructive pulmonary disease with phlegm-turbid obstructing of the lung: a randomized controlled trial].

OBJECTIVE: To verify the effect of warm acupuncture combined with western medicine in patients with acute exacerbation chronic obstructive pulmonary disease (AECOPD) with phlegm-turbid obstructing of the lung. METHODS: Ninety patients with AECOPD were randomly divided into a western medicine group, a warm acupuncture group and a sham acupuncture group, 30 cases in each group. Routine treatment according to the Global initiative for chronic obstructive lung disease (GOLD) guidelines was used in the western medicine group. On the basis of the routine treatment, the warm acupuncture was applied at Fenglong (ST 40), Feishu (BL 13), Zusanli (ST 36) and other acupoints in the warm acupuncture group. In the sham acupuncture group, non-acupoints were taken on the basis of conventional treatment, and superficial acupuncture was performed for 1-3 mm, once a day for 2 weeks. Forced expiratory volume in 1 s (FEV1), forced vital capacity (FVC), FEV1/FVC, cough and sputum assessment questionnaire (CASA), COPD assessment test (CAT), and the change of TCM syndrome score were observed before and after treatment in all groups. RESULTS: After treatment, the FEV1, FVC and FEV1/FVC in each group were higher than those before treatment (P<0.05), there was no significant difference among groups after treatment (P>0.05). The CASA score, CAT score and TCM syndrome score in each group were lower than those before treatment (P<0.05). The change of the scores before and after treatment in the warm acupuncture group was higher than that in the sham acupuncture group and the western medicine group (P<0.05). There was no significant difference between the sham acupuncture group and the western medicine group (P>0.05). CONCLUSION: Warm acupuncture has a significant effect on the improvement of symptoms in patients with AECOPD with phlegm-turbid obstructing of the lung.

Astragaloside suppresses apoptosis of the podocytes in rats with diabetic nephropathy via miR-378/TRAF5 signaling pathway.

AIMS: Apoptosis of podocytes plays a crucial role in diabetic nephropathy (DN) development, and astragaloside (AS-IV) has a significant impact on podocyte apoptosis. This study aims to explore the effect of AS-IV on diabetic nephropathy progression. MATERIALS AND METHODS: The diabetic nephropathy model was established in rats with streptozotocin (STZ) injection. The albuminuria was examined by using the enzyme linked immunosorbent assay (ELISA). The expression of miR-378, tumor-necrosis factor (TNF) receptor (TNFR)-associated factor 5 (TRAF5) mRNA and protein was analyzed by qRT-PCR and western blot, respectively. Cell transfection was conducted for modulating endogenous expression of miR-378. Dual luciferase reporter assay was used to evaluate the interaction between miR-378 and TRAF5. The terminal deoxynucleotidy transferase dUTP nick end labeling (TUNEL) staining assay was performed for apoptosis detection. KEY FINDINGS: AS-IV protected diabetic rats from developing into diabetic nephropathy. The expression of miR-378 was down-regulated in diabetic nephropathy rats, which was reversed by AS-IV. AS-IV enhanced the expression of miR-378 in podocytes treated with high glucose. MiR-378 negatively regulated TRAF5. AS-IV inhibited the expression of TRAF5 through miR-378. AS-IV suppressed apoptosis of podocytes via targeting miR-378. SIGNIFICANCE: AS-IV suppresses apoptosis of the podocytes through the miR-378/TRAF5 signaling pathway, and thereby repressing diabetic nephropathy development.