Search

作为一种前馈神经网络，宽度学习系统因其精度高、训练速度快且能有效代替深度学习方法而备受研究者的关注。然而，宽度学习系统存在对网络中的特征节点个数比较敏感且求伪逆方式易使模型出现过拟合等问题。为此，在宽度学习系统中引入贝叶斯推断和图正则化。一方面，通过引入先验知识进行贝叶斯学习可以有效提高权重的稀疏性，提高模型的稳定性；另一方面，加入图正则化可充分考虑数据内在的图信息，进一步提高模型的泛化能力。在UCI数据集和NORB数据集上对所提模型进行性能评估，实验结果表明，所提的基于图正则化的贝叶斯宽度学习系统模型能进一步提高宽度学习系统的分类精度且具有更好的稳定性。

植株叶片检测是植株科学培育和精准农业过程中重要的环节之一。传统植株叶片检测的做法对操作人员的专业知识提出了较高要求，且人工成本高、耗时周期长。基于此，提出基于多尺度卷积神经网络特征融合（MCFF）的植株叶片检测技术。从深度学习技术辅助植株培育的需求出发，基于多尺度卷积神经网络特征融合，针对莲座模式植物、拟南芥和烟草3种不同类型、不同分辨率的植株进行叶片计数检测。经过与其他主流算法的比较，发现MCFF具备较高的检测精确度，平均精度均值（mAP）为0.662，实现了高度竞争的性能（AP=0.946），各项指标接近实用水平。

目的　探讨超声引导下胸椎旁神经阻滞对老年肝癌手术患者镇痛效果和认知功能的影响。方法　选择 择期行肝癌切除手术的老年患者134例，随机分为观察组和对照组，每组67例。对照组予自控静脉镇痛（托烷司琼 5 mg + 舒芬太尼 0. 2 µg/kg用生理盐水稀释至 100 mL），观察组在此基础上予超声引导下胸椎旁神经阻滞（0. 25% 罗哌卡因0. 5 mg/kg）。比较两组术后1、4、12、24、72 h镇痛效果［采用视觉模拟评分法（VAS）评估］及血清疼痛介质 ［神经肽 Y（NPY）、P 物质（SP）及多巴胺（DA）］水平，术前 1 天与术后 7 天认知功能［采用简易智能精神检查量表 （MMSE）评分评估］及血清认知功能相关指标［脑源性神经营养因子（BDNF）、兴奋性氨基酸（EAA）、缺氧诱导因子 1α（HIF-1α）］水平，以及围手术期不良反应情况。结果　两组术后VAS和血清NPY、SP、DA水平均呈先上升后下降 趋势，并且观察组术后4、12、24、72 h VAS和血清NPY、SP、DA水平均低于对照组同期（P均<0. 05）。观察组与对照 组术后MMSE评分均低于术前，并且观察组术后MMSE评分高于对照组术后（P均<0. 05）。两组术后血清BDNF水 平均低于术前，血清EAA、HIF-1α水平均高于术前（P均<0. 05）；观察组术后血清BDNF水平高于对照组术后，血清 EAA、HIF-1α水平均低于对照组术后（P均<0. 05）。观察组围手术期不良反应发生率低于对照组（P<0. 05）。结论　老年 肝癌手术患者在自控静脉镇痛基础上予超声引导下胸椎旁神经阻滞不仅镇痛效果好，还能减轻术后认知功能损伤， 并且安全性较高。 [ABSTRACT FROM AUTHOR]

The current methods for short-time precipitation nowcasting are based on radar echo extrapolation model, without fully considering the close influence of other meteorological factors on the evolution of precipitation generation and cancellation, thus limiting the accuracy of the forecasts. To address the above issues, this paper produced a short-time precipitation nowcasting dataset, and proposed the MFPNM(multiple factors precipitation nowcasting model). Based on data from the Fengyun4B satellite, the dataset toke quantitative precipitation estimation as the forecast object and contained four background meteorological factors. Taking the TransUNet as the backbone of the model, this model proposed the parallel dual encoder to extract the high-dimensional spatio-temporal features of the forecast object and the background meteorological data, respectively. Besides, it constructed the content coding module to encode the spatial features of the background data as the learnable positional embedding of the high-dimensional feature vectors of the forecast object. It used a Transformer module to construct the global relationship between the high-dimensional features of the sequence data for better sequence prediction. The metrics used in this paper included critical success index, false alarm rate, root-mean-square error, and structural similarity, etc. The MPFNM was evaluated on two datasets (the proposed dataset and an open-source dataset) and outperformed the baseline models, and it was analyzed for explainability through the SHAP technique. The experimental results and explainability analysis show that the model has better forecasting accuracy and reliability. [ABSTRACT FROM AUTHOR]

Objective Based on the technical principle that rapid replenishment of formation energy can improve the degree of CO2 miscibility, the feasibility of the injection method to improve the degree of CO2 immiscible flooding in low-pressure tight sandstone reservoirs in Ordos Basin was studied. Methods In this paper, the effects of CO2 displacement at various injection rates and volumes were compared under reservoir conditions. The changes of formation pressure, oil change rate, recovery degree, gas-oil ratio and extraction parameters also were investigated. Results Compared with the conventional injection rate and volumes, the formation pressure increased by 4.14 MPa, the oil change rate increased by 0.13, the recovery degree increased by 22%, the gas-oil ratio decreased by 50%, the component content of C4—C12 increased significantly, and the content of recombination component decreased significantly. Field tests of the two well groups showed that the monthly oil production of the well group was increased by 78%, the average formation pressure was 5 MPa, the corresponding well oil pressure was increased by 4.5 MPa, the degree of miscibility was increased by 32.81%, and the oil displacement effect was remarkable. Conclusion The injection method can effectively improve the degree of CO2 miscible flooding and the effect of CO2 immiscible flooding in tight sandstone reservoirs. [ABSTRACT FROM AUTHOR]

Copyright of China Condiment is the property of China Condiment and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Chinese Journal of Tissue Engineering Research / Zhongguo Zuzhi Gongcheng Yanjiu is the property of Chinese Journal of Tissue Engineering Research and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Machine Tool & Hydraulics is the property of Guangzhou Mechanical Engineering Research Institute (GMERI) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Electric Drive for Locomotives is the property of Electric Drive for Locomotives Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Ordnance Equipment Engineering is the property of Chongqing University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Acta Agriculturae Zhejiangensis is the property of Acta Agriculturae Zhejiangensis Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Mine Automation is the property of Industry & Mine Automation Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Telecommunications Science is the property of Beijing Xintong Media Co., Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Application Research of Computers / Jisuanji Yingyong Yanjiu is the property of Application Research of Computers Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Southwest China Journal of Agricultural Sciences is the property of Editorial Department of Southwest China Journal of Agricultural Sciences and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Ballistics / Dandao Xuebao is the property of Journal of Ballistics Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Electric Power Automation Equipment / Dianli Zidonghua Shebei is the property of Electric Power Automation Equipment Press and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Transactions of the Chinese Society of Agricultural Engineering is the property of Chinese Society of Agricultural Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of China Mechanical Engineering is the property of Editorial Board of China Mechanical Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The lotus root is one of the most popular food products in the stem of the lotus plant in Asia areas. Mechanical excavators of lotus roots can be expected to save the cost and labor intensity. However, the existing track float self-propelled excavator cannot fully meet the large-scale production, due to the large overall weight. There are also some difficulties in climbing, turning, and slipping vehicles in the field. In this study, the skid support device was designed to treat the high driving resistance and excess sinking of the crawler float-type excavator of lotus root. The device was installed on both sides of the chassis and hydraulically driven up and down to adjust the position. The gravity of the whole machine was supported to reduce the grounding pressure and sinking depth of the crawler. The passability was also improved as well. The driving performance of the crawler float-type excavator chassis was evaluated after the skid support device was added. The chassis of the crawler float-type excavator was taken as the research object. A new model was also established for the driving resistance and tractive force of the chassis. Theoretical analysis was conducted on the extrusion force between the soil and the ground surface at the front of the skid. The sliding-cutting angle α and milter angle φ were determined to be the main structural parameters of the driving resistance. A skid scale model was constructed for the one-third of original size. The single-factor simulation was carried out using the driving speed and sinking depth in EDEM software. A systematic investigation was made on the influence of sliding-cutting angle α, milter angle φ, driving speed v and sinking depth on the forward resistance. The results showed that the forward resistance decreased with the increase of slip angle α, and milter angle φ, whereas, there was an increase with the increase of driving speed v, and sinking depth. The box-Behnken test was also carried out to explore the influence of slipcutting angle, milter angle and forward speed on forward resistance. The influencing factors were taken as the sliding-cutting angle α, milter angle φ, and driving speed v, while the forward resistance was the response index. It was found that the driving speed v shared a very significant effect on the forward resistance (P＜0.01). The significant effect of sliding-cutting angle α, milter angle φ, and the square term v2 of driving speed v on the advancing resistance (0.01＜ P＜ 0.05). The optimal combination of parameters was obtained for the skid structure. Specifically, the least forward resistance was achieved, when the sliding-cutting angle α was 40°, the milter angle φ was 70° and the driving speed v was 0.1 m/s. Correspondingly, the forward resistances were 66.09 and 82.28 N in the simulation and soil bin test, respectively. The soil bin test showed that the skid driving speed and sinking depth had very significant effects on the skid forward resistance (P＜0.01). The skid driving speed and sinking depth were also proportional to the forward resistance, indicating the consistence with the simulation. The field test was carried out on the crawler float-type excavator before and after the skid support device. The resistance torque of the driving motor was reduced by 6.51%, which were 182.15 and 170.30 N·m, respectively. The sinking depth of the chassis was 178.1 and 164.5 mm, respectively, which were reduced by 7.64% than before. The performance of the excavator was outstandingly improved after adding the skid support device. This finding can provide a strong reference for the walking device of the ground machine system in paddy fields. [ABSTRACT FROM AUTHOR]

Copyright of Yellow River is the property of Editorial Board of Yellow River and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Type 1 diabetes is caused by impaired function of pancreatic β-cells and insufficient insulin secretion. Currently, it is primarily managed with exogenous insulin supplementation; however, exogenous insulin cannot precisely regulate blood glucose levels, and severe hypoglycemia can be life-threatening. Islet transplantation serves as an alternative therapy, but faces challenges such as a shortage of organ donors and the risk of cross-species infections from xenogeneic sources of islet β-cells. Thus, obtaining a sufficient and safe supply of islet β-cells remains a significant challenge in cell therapy for type 1 diabetes. This study aims to differentiate human induced pluripotent stem cells (hiPSCs) into islet β-cells in vitro, offering a potential new strategy for treating type 1 diabetes. To achieve this, we utilized a differentiation strategy that combines 2D and 3D culture systems to simulate the in vivo developmental environment of islet β-cells and employed various growth factors to regulate key signaling pathways crucial in pancreatic development and β-cell differentiation, including the Notch, Wnt, and TGF-β/Smad signaling pathways. Our results show that under combined 2D and 3D culture conditions, the expression of specific genes at the stages of definitive endoderm, pancreatic progenitors, pancreatic endocrine cells, and islet β-cells significantly increased (P<0.05). And there was a marked enhancement in insulin content and secretion following glucose stimulation (P<0.05). In summary, this study successfully established a differentiation strategy from hiPSCs to functional islet β-cells, providing a new cell therapy approach for type 1 diabetes. This method not only offers new tools for studying the developmental biology of islet β-cells, but also provides a potential source of islet β-cells for clinical applications, potentially overcoming the limitations of current treatment methods. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Chongqing University of Technology (Natural Science) is the property of Chongqing University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Railway Standard Design is the property of Railway Standard Design Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Southwest China Journal of Agricultural Sciences is the property of Editorial Department of Southwest China Journal of Agricultural Sciences and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Chinese Journal of Tissue Engineering Research / Zhongguo Zuzhi Gongcheng Yanjiu is the property of Chinese Journal of Tissue Engineering Research and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Based on the existing deep soft soil geological conditions in beach area, greater challenges were brought to the construction of cast-in-place box girders. Relying on the first phase project of Shiyitang Expressway in Zhejiang Province, the influence of artificially solidified hard shell layer on bridge pile foundation under preloading load was studied. Based on the soil hardening model, a three-dimensional numerical calculation model was established. The variation law of axial force, lateral friction resistance and horizontal displacement of pile body under different depth of hard shell was compared. The results show that when the thickness of the hard shell is 2 m, the axial force of the pile is reduced by about 16% . The thickness of the hard shell layer will change the transfer depth of the negative friction resistance, which shows that the thicker the thickness of the hard shell layer, the more the neutral point of the pile side resistance moves up. In addition, in a certain depth influence range, the hard shell layer can effectively control the horizontal displacement of the pile top and the pile body at different depths. The larger the thickness of the hard shell layer, the smaller the horizontal displacement of the pile top. Finally, the influence of soil modulus on the horizontal displacement of the pile was analyzed. It is found that the horizontal displacement of the pile will decrease with the increase of the compression modulus of the soil, and the influence of soil unloading / reloading stiffness modulus Eur is higher than that of soil deflection loading stiffness modulus E50 and lateral compression stiffness modulus of soil Eeod . [ABSTRACT FROM AUTHOR]

Copyright of Food Research & Development is the property of Food Research & Development Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Rolling Stock (1002-7602) is the property of Rolling Stock Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Shipin Kexue/ Food Science is the property of Food Science Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Guangdong Architecture Civil Engineering is the property of Guangdong Architecture Civil Engineering Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Mine Automation is the property of Industry & Mine Automation Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Bulletin of the Chinese Ceramic Society is the property of Bulletin of the Chinese Ceramic Society Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Shandong Medical Journal is the property of Shandong Medical Health Newspapers and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Chinese Journal of Tissue Engineering Research / Zhongguo Zuzhi Gongcheng Yanjiu is the property of Chinese Journal of Tissue Engineering Research and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of China Plastics / Zhongguo Suliao is the property of Journal Office of CHINA PLASTICS and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The integrated navigation system (INS), vital in aerospace and ocean exploration, faces challenges in reliability analysis due to its complex operational environment. Addressing this, the finite degradation structures (FDS) method was employed for a thorough examination of the multi-state integrated navigation system. Initial steps involve transforming component fault modes into a state space using the failure mode and effect analysis ( FMEA) method. Subsequently, an abstraction operation establishes the relationship between component states and system states, forming the required FDS model. This model serves as the basis for critical scenario analysis and calculation of reliability indicators. Through this systematic approach, the occurrence probability of various system states can be computed and the sensitivity of individual component states can be assessed. The identifications of the weak points and the degradation boundaries of the system are well demonstrated with illustrative case studies. These results can be seen as insights to guide reliability decisions, including the development of system maintenance strategies and risk prevention schemes. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Ground Improvement is the property of Journal of Ground Improvement Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Henan Agricultural Sciences is the property of Editorial Board of Journal of Henan Agricultural Sciences and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Bulletin of the Chinese Ceramic Society is the property of Bulletin of the Chinese Ceramic Society Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Control Theory & Applications / Kongzhi Lilun Yu Yinyong is the property of Editorial Department of Control Theory & Applications and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Anhui Agricultural Sciences is the property of Journal of Anhui Agricultural Sciences Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Natural Gas Geoscience is the property of Natural Gas Geoscience and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Mine Automation is the property of Industry & Mine Automation Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Arid Land Geography is the property of Chinese Academy of Sciences, Xinjiang Institute of Ecology & Geography and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Food Research & Development is the property of Food Research & Development Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Unmanned aerial vehicle (UAV) remote sensing has the promising potential for the precise and efficient classification and mapping of forest tree species. Deep learning also requires a large number of datasets for training, typically on manual annotation. In this study, the framework of forest tree species classification was proposed to fully utilize a large amount of unlabeled data and a small amount of annotated data using semi-supervised learning. A rapid and accurate classification was also achieved in the high-precision distribution of dominant tree species in forests. The experimental areas were taken as the complex mountainous forest environment in Fujian Province. The composition of tree species was then obtained in a rapid, effective, and cost-saving manner. Taking four experimental areas in Fuzhou, Longyan, and Sanming in Fujian Province as examples, the simplified classification was constructed in the UNet tree species (ResNet14*) model with ResNet18 as the backbone. ResNet14* was different from ResNet18: ResNet14* was used to remove the layer4 part of ResNet18, i.e., the last downsampled cascaded block, which retained slightly higher spatial information; At the end of the layer2 and layer3 sections of ResNet14*, a max pooling layer was added to reduce the training parameters of the neural network while retaining the original features. A joint loss function of cross entropy and Dice coefficient was used to optimize the model parameters. The generalization of Self-training and Mean teacher was evaluated on the classification models with semi-supervised learning using UVA images. The results show that the overall accuracy of the ResNet14* network reached 91.15%, with a Kappa coefficient of 0.827, which was within 1% of the accuracy of the rest ResNet models. At the same time, a smaller number of parameters and the shortest prediction time were achieved to balance the accuracy and efficiency of tree species classification. The best prediction performance of ResNet14* was achieved with the joint loss function weight of 0.5, indicating an overall accuracy of 91.15%. Therefore, the joint loss function weight of 0.5 was an optimal value for semisupervised learning in this case. Self-training and Mean teacher semi-supervised learning were implemented with UNet (ResNet14*) as the main network. The experiment showed that the overall accuracy of the Self-training on the test set reached 91.08%, slightly lower than the original. The higher category accuracy was also achieved in the categories of Schima superba, Pinus massoniana, and Chinese fir with sufficient samples. Furthermore, the overall accuracy of the self-training with pseudo labels was improved among two semi-supervised models in experimental area D, reaching 88.50% compared with the original; There was a significant decrease in the overall accuracy of the Mean teacher model with consistency loss. The total accuracy of the Mean teacher model was 88.56%, where the accuracy was 73.56% in the independent validation area. Accuracy evaluation was also conducted on an independent validation area. The classification accuracy of above 80% was found in the three types of tree species, namely Schima superba, Pinus Massoniana, and Chinese fir. A relatively large area was accounted for to meet the accuracy requirements of tree species mapping in the experimental area. Therefore, the semi-supervised learning of the Selftraining model can be expected to rapidly obtain the composition of tree species in the experimental area. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Modern Laboratory Medicine is the property of Journal of Modern Laboratory Medicine Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)