A hybrid CNN-LSTM model for diagnosing rice nutrient levels at the rice panicle initiation stage

Nitrogen(N)and potassium(K)are two key mineral nutrient elements involved in rice growth.Accurate diagnosis of N and K status is very important for the rational application of fertilizers at a specific rice growth stage.Therefore,we propose a hybrid model for diagnosing rice nutrient levels at the early panicle initiation stage(EPIS),which combines a convolutional neural network(CNN)with an attention mechanism and a long short-term memory network(LSTM).The model was validated on a large set of sequential images collected by an unmanned aerial vehicle(UAV)from rice canopies at different growth stages during a two-year experiment.Compared with VGG16,AlexNet,GoogleNet,DenseNet,and inceptionV3,ResNet101 combined with LSTM obtained the highest average accuracy of 83.81%on the dataset of Huanghuazhan(HHZ,an indica cultivar).When tested on the datasets of HHZ and Xiushui 134(XS134,a japonica rice variety)in 2021,the ResNet101-LSTM model enhanced with the squeeze-and-excitation(SE)block achieved the highest accuracies of 85.38 and 88.38%,respectively.Through the cross-dataset method,the average accuracies on the HHZ and XS134 datasets tested in 2022 were 81.25 and 82.50%,respectively,showing a good generalization.Our proposed model works with the dynamic information of different rice growth stages and can efficiently diagnose different rice nutrient status levels at EPIS,which are helpful for making practical decisions regarding rational fertilization treatments at the panicle initiation stage.

基于语义-注意力机制的方面级情感分类

现有方面级情感分析研究大多数往往从文本数据本身进行情感分析,而没有充分利用领域知识,忽略了语义依存信息的重要性,使得方面表示受噪声信息影响严重,出现噪声词注意权重高的可能。针对以上问题,结合领域知识,提出了一种剪枝算法和语义-注意力机制相结合的方法(Pruning And Semantic At tention,PASA)针对服务领域特定方面进行情感分类。方法一方面结合领域知识对文本对应的语义依存树进行剪枝实现方面信息降噪,另一方面,通过利用语义-注意力机制进行增强并精确捕获方面的上下文描述信息,从而实现对方面情感极性的判断。为了验证所提出方法的正确性和有效性,在物流数据集、酒店评论数据集及SemEval 2014的Restaurant数据集进行了大量实验,结果表明,所提出的方法相对于其它方法具有明显优势,在垂直领域具有较好的应用前景。

Groundwater level prediction of landslide based on classification and regression tree

According to groundwater level monitoring data of Shuping landslide in the Three Gorges Reservoir area, based on the response relationship between influential factors such as rainfall and reservoir level and the change of groundwater level, the influential factors of groundwater level were selected. Then the classification and regression tree（CART） model was constructed by the subset and used to predict the groundwater level. Through the verification, the predictive results of the test sample were consistent with the actually measured values, and the mean absolute error and relative error is 0.28 m and 1.15%respectively. To compare the support vector machine（SVM） model constructed using the same set of factors, the mean absolute error and relative error of predicted results is 1.53 m and 6.11% respectively. It is indicated that CART model has not only better fitting and generalization ability, but also strong advantages in the analysis of landslide groundwater dynamic characteristics and the screening of important variables. It is an effective method for prediction of ground water level in landslides.

Detection of Angioectasias and Haemorrhages Incorporated into a Multi-Class Classification Tool for the GI Tract Anomalies by Using Binary CNNs

The proposed deep learning algorithm will be integrated as a binary classifier under the umbrella of a multi-class classification tool to facilitate the automated detection of non-healthy deformities, anatomical landmarks, pathological findings, other anomalies and normal cases, by examining medical endoscopic images of GI tract. Each binary classifier is trained to detect one specific non-healthy condition. The algorithm analyzed in the present work expands the ability of detection of this tool by classifying GI tract image snapshots into two classes, depicting haemorrhage and non-haemorrhage state. The proposed algorithm is the result of the collaboration between interdisciplinary specialists on AI and Data Analysis, Computer Vision, Gastroenterologists of four University Gastroenterology Departments of Greek Medical Schools. The data used are 195 videos (177 from non-healthy cases and 18 from healthy cases) videos captured from the PillCam(R) Medronics device, originated from 195 patients, all diagnosed with different forms of angioectasia, haemorrhages and other diseases from different sites of the gastrointestinal (GI), mainly including difficult cases of diagnosis. Our AI algorithm is based on convolutional neural network (CNN) trained on annotated images at image level, using a semantic tag indicating whether the image contains angioectasia and haemorrhage traces or not. At least 22 CNN architectures were created and evaluated some of which pre-trained applying transfer learning on ImageNet data. All the CNN variations were introduced, trained to a prevalence dataset of 50%, and evaluated of unseen data. On test data, the best results were obtained from our CNN architectures which do not utilize backbone of transfer learning. Across a balanced dataset from no-healthy images and healthy images from 39 videos from different patients, identified correct diagnosis with sensitivity 90%, specificity 92%, precision 91.8%, FPR 8%, FNR 10%. Besides, we compared the performance of our best CNN algorithm versus our same goal algorithm based on HSV colorimetric lesions features extracted of pixel-level annotations, both algorithms trained and tested on the same data. It is evaluated that the CNN trained on image level annotated images, is 9% less sensitive, achieves 2.6% less precision, 1.2% less FPR, and 7% less FNR, than that based on HSV filters, extracted from on pixel-level annotated training data.

LEVEL SET输运方程的求解方法及其对气-液两相流运动界面数值模拟的影响

用数值模拟方法来研究气-液两相流动与传热现象是当今多相流领域的一个热门课题。由于两相流固有的复杂性,气-液两相流界面迁移现象的数值模拟一直是两相流研究中的一大难点。本文介绍了捕捉气-液两相流相界面运动的水平集方法(LevelSet)及其研究进展,介绍了求解LevelSet输运方程的3种方法,即一般差分格式、Superbee-TVD格式和Runge-Kutta法-5阶WENO组合格式。结合主流场的求解,分别用这3种方法对4种典型相界面在5种流场中的迁移特性进行了模拟计算,并对计算结果进行了比较和分析。结果表明,Runge-Kutta法-5阶WENO组合格式求解LevelSet输运方程的效果最好,在以后的计算中将主要采用这种组合格式来进行气-液相界面输运方程的求解。

FCG-NNER:一种融合字形信息的中文嵌套命名实体识别方法

基于跨度的模型是嵌套命名实体识别的主要方法,其核心是将实体识别问题转化为跨度分类问题。而在中文数据集中,由于中文单词不具有明显的分割符号,导致语义和边界信息不明确,进而造成中文嵌套命名实体识别效果不佳。为了解决这一问题,提出了融合字形信息的基于跨度的中文嵌套命名实体识别算法——FCG-NNER,首先通过卷积神经网络获取汉字的字形信息,其次通过交叉Biaffine双仿射解码层实现原文信息与字形信息融合,然后通过对角融合CNN层获取不同跨度之间的局部相互作用,最后将交叉Biaffine双仿射解码层的输出与对角融合CNN层的输出相加后输入到全连接层中,得到最终的预测结果。采用2个具有代表性的中文嵌套NER数据集(CMeEE和CLUENER2020)用于实验验证。结果显示,FCG-NNER在CMeEE数据集中的精度为65.02%,召回率为67.93%,F1值达到0.664 4;在CLUENER2020数据集中的精度为79.45%,召回率为82.33%,F1值达到0.808 6,证明FCG-NNER算法的性能明显超过2个数据集的基线。

Remote Sensing Image Classification Algorithm Based on Texture Feature and Extreme Learning Machine

With the development of satellite technology,the satellite imagery of the earth’s surface and the whole surface makes it possible to survey surface resources and master the dynamic changes of the earth with high efficiency and low consumption.As an important tool for satellite remote sensing image processing,remote sensing image classification has become a hot topic.According to the natural texture characteristics of remote sensing images,this paper combines different texture features with the Extreme Learning Machine,and proposes a new remote sensing image classification algorithm.The experimental tests are carried out through the standard test dataset SAT-4 and SAT-6.Our results show that the proposed method is a simpler and more efficient remote sensing image classification algorithm.It also achieves 99.434%recognition accuracy on SAT-4,which is 1.5%higher than the 97.95%accuracy achieved by DeepSat.At the same time,the recognition accuracy of SAT-6 reaches 99.5728%,which is 5.6%higher than DeepSat’s 93.9%.

Oxygen Isotope Records of Core 8KL of the South China Sea and Sea - level Change

Based on a comparison between the oxygen isotope records of benthic and plank tonic foraminifers from core 8KL of the South China Sea and sea-level change records derived from the Huon Peninsula, New Guinea, it is found that both records are very similar from 72 K a B.P. to the present, especially for the benthic oxygen isotope record. The linear regression shows that δ18O changes (0.9995‰ for benthic foraminifers and 1.022‰ for planktonic foraminifers) are equal to 100 m in sea-level fluctuation. After making temperature correction in the δ18O record of benthic foraminifers from 72 to 120 Ka B.P., the curve of sea-level oscillation of the South China Sea since 186 Ka B.P. has been reconstructed. The lowermost sea - level that occurred in the last glacial maximum and oxygen isotope stage 6 is approximately - 130 m.

A Multilevel Secure Relation-Hierarchical Data Model for a Secure DBMS

A multilevel secure relation hierarchical data model for multilevel secure database is extended from the relation hierarchical data model in single level environment in this paper. Based on the model, an upper lower layer relationalintegrity is presented after we analyze and eliminate the covert channels caused by the database integrity.Two SQL statements are extended to process polyinstantiation in the multilevel secure environment.The system based on the multilevel secure relation hierarchical data model is capable of integratively storing and manipulating complicated objects ( e.g. , multilevel spatial data) and conventional data ( e.g. , integer, real number and character string) in multilevel secure database.

High levels of Zinc-α-2-Glycoprotein among Omani AIDS patients on combined antiretroviral therapy

Objective:To investigate the levels of zinc-α-2-glycoprotein(ZAG) among Omani AIDS patients receiving combined antiretroviral therapy(cART).Methods:A total of 80 Omani AIDS patients(45 males and 33 females),average age of 36 vears.who were receiving cART at the Saltan Qaboos University Hospital(SQUH).Muscat,Oman,were tested for the levels of ZAG.In addition,SO healthy blood donors(46 males and 34 females),average age of 26 years,attending the SOUH Blood Bank,were tested in parallel as a control group.Measurement of the ZAG levels was performed using a competitive enzyme—linked immunosorbent assay and in accordance with the manufacturer's instructions.Results:The ZAG levels were found to he significantly higher among AIDS patients compared to the healthy individuals(P=0.033).A total of 56(70%) of the AIDS patients were found to have higher levels of ZAG and 16(20%) AIDS patients were found to have high ZAG levels,which are significantly(P>0.031) associated with weight loss.Conclusions:ZAG levels are high among Omani AIDS patients on cART and this necessitales the measurement of ZAG on routine basis,as it is associated with weight loss.

Electrical responses and classification of complex waterflooded layers in carbonate reservoirs: A case study of Zananor Oilfield, Kazakhstan

Experiments of electrical responses of waterflooded layers were carried out on porous,fractured,porous-fractured and composite cores taken from carbonate reservoirs in the Zananor Oilfield,Kazakhstan to find out the effects of injected water salinity on electrical responses of carbonate reservoirs.On the basis of the experimental results and the mathematical model of calculating oil-water relative permeability of porous reservoirs by resistivity and the relative permeability model of two-phase flow in fractured reservoirs,the classification standards of water-flooded layers suitable for carbonate reservoirs with complex pore structure were established.The results show that the salinity of injected water is the main factor affecting the resistivity of carbonate reservoir.When low salinity water(fresh water)is injected,the relationship curve between resistivity and water saturation is U-shaped.When high salinity water(salt water)is injected,the curve is L-shaped.The classification criteria of water-flooded layers for carbonate reservoirs are as follows:(1)In porous reservoirs,the water cut(fw)is less than or equal to 5%in oil layers,5%–20%in weak water-flooded layers,20%–50%in moderately water-flooded layers,and greater than 50%in strong water-flooded layers.(2)For fractured,porous-fractured and composite reservoirs,the oil layers,weakly water-flooded layers,moderately water-flooded layers,and severely water-flooded layers have a water content of less than or equal to 5%,5%and 10%,10%to 50%,and larger than 50%respectively.

基于改进Mask R-CNN的番茄茎秆分类方法

为实现对与背景近色、不规则细长型目标——番茄茎秆的分类,提出了一种基于改进Mask R-CNN的番茄茎秆分类算法.采集日间和夜间番茄植株图像,使用labelme分别制作日间和夜间番茄茎秆分类数据集.结合迁移学习方法,使用两种数据集分别训练Mask RCNN模型.对Mask分支进行了改进,在生成掩膜的同时生成其最小外接矩,并提出了用于评估掩膜边框精确率的评价指标Re及用于综合评估模型性能的像素级评价指标.试验结果显示:夜间及日间茎秆分类模型的像素F1值、像素全类平均正确率分别为48.82%、50.03%和57.76%、56.06%. Mask分支改进后掩膜边框精确率得到了显著提高,平均每幅图像检测耗时0.31 s,满足实际应用对算法实时性的需求,可为植株修剪等工作的智能化提供方法支持.

AOA-BERT:一种基于对抗学习的方面级情感分类方法

方面级情感分类是一种细粒度的情感分析任务,旨在分析出文本不同方面的情感.针对方面级情感分类模型存在分类精度低、泛化性弱等问题,提出基于对抗学习的AOA-BERT方面级情感分类模型(Attention-Over-Attention-BERT for aspect-level sentiment classification model based on adversarial learning,AOA-BERT).首先,将文本和方面词单独建模,通过BERT编码提取隐含层特征.其次,将隐含层特征放入AOA(Attention-Over-Attention)网络提取权重向量.最后,将权重向量与建模后的文本特征向量相乘,并做交叉熵损失、回传参数.此外,通过对抗学习算法生成和学习对抗样本,作为一种文本数据增强方法,优化决策边界.实验结果表明,和大多数深度神经网络情感分类模型相比,AOA-BERT能提升情感分类的准确性.同时,通过消融实验,证明了AOA-BERT结构设计的合理性.

Sentinel-3A卫星测高数据监测长江中下游河流水位变化

河流水位是了解水循环和水资源变化状况的重要参数。新型雷达高度计技术是提取河流水位变化的有利工具。为了验证新型雷达高度计Sentinel-3A/SRAL数据监测河流水位的能力,提高其提取河流水位变化的精度,以长江中下游干流为研究对象,利用重心偏移法、阈值主波峰重跟踪算法(阈值取50%和80%)、重心主波形重跟踪算法和多回波波峰一致重跟踪算法对Sentinel-3A/SRAL L2级数据进行波形重跟踪,提取了长江中下游干流各区域2016—2021年间河流水位,并对比不同算法获取水位的精度,得到最优重跟踪算法,从而提取了12条轨道过境区域的水位变化信息,分析了水位变化规律。结果表明,重心偏移法算法是提取河流水位精度最好的重跟踪算法,各区域虚拟水位与实测水位相比具有最大相关系数(达0.968)、最小均方根误差(达0.680 m);2016—2021年间长江中下游干流水位总体呈上升趋势,年内水位变化呈现明显的季节性。

Development Path of Different County-Level Towns

County-level town is important space carrier of China's urbanization and the emphasis and key of strategic distribution for urbanization. Backwardness of county-level towns limits nearby transfer of surplus labor. To promote development of county-level towns,on the basis of classifying county-level towns,this paper analyzed motive and resistance factors of evolution of different county-level towns using historical data collection and statistical method,comparative approach,typical case study method,and studied development path for different county-level towns. From analysis,it reached the conclusion that industry exerts the most direct and fundamental influence on development of county-level towns,while the industrial development in county-level towns must base on their actual conditions. The county-level towns are not isolated,and their development should be established within the framework of national policy environment and superior and subordinate town system.

Aspect Level Songs Rating Based Upon Reviews in English

With the advancements in internet facilities,people are more inclined towards the use of online services.The service providers shelve their items for e-users.These users post their feedbacks,reviews,ratings,etc.after the use of the item.The enormous increase in these reviews has raised the need for an automated system to analyze these reviews to rate these items.Sentiment Analysis(SA)is a technique that performs such decision analysis.This research targets the ranking and rating through sentiment analysis of these reviews,on different aspects.As a case study,Songs are opted to design and test the decision model.Different aspects of songs namely music,lyrics,song,voice and video are picked.For the reason,reviews of 20 songs are scraped from YouTube,pre-processed and formed a dataset.Different machine learning algorithms—Naïve Bayes(NB),Gradient Boost Tree,Logistic Regression LR,K-Nearest Neighbors(KNN)and Artificial Neural Network(ANN)are applied.ANN performed the best with 74.99%accuracy.Results are validated using K-Fold.

Relation between Baseline Lipid Levels and Effectiveness of HMG-CoA Reductase Inhibitors in Patients with Hyperlipidemia

Objective To evaluate whether the effects of HMG - CoA reductase inhibitors on patients with hyperlipidemia are closely related to baseline lipid levels. Methods The data analyzed originated from 3 separate multicenter clinical trials with similar designs during 1994 to 1999. 166 patients with mean age 58. 9±9. 2 years were involved in Simvastatin Clinical Trial with simvastatin 10 mg once daily for 8 weeks. 146 patients with mean age 57. 9±8. 7years were involved in Lovastatin Clinical Trial with lovastatin 20 mg once daily for 8 weeks. 105 patients with mean age 57. 8±9. 3 years were involved in Atorvastatin Clinical Trial with atorvastatin 10 mg once daily for 6 weeks. Baseline total cholesterol (TC) was more than 5. 98 mmol. L - 1, and baseline triglyceride (TG) was less than 4. 52 mmo. L - 1. The patients were grouped by baseline lipid levels. Results The higher the baseline TC, low density lipoprotein cholesterol (LDL - C) and TG levels were, the more effective the simvastatin, lovastatin, or atorvastatin was in reducing serum TC, LDL - C, and TG, respectively. A positive linear correlation was found between baseline values and effects of simvastatin, lovastatin, or atorvastatin in reducing serum TC, LDL - C, and TG, respectively. Conclusion The changes of reduction on serum lipid with HMG - CoA reductase inhibitors in patients with hyperlipidemia were influenced by baseline lipid levels.

Heath Assessment Method of EMU Trains in Level 3-5 Maintenance and Repair

An accurate and objective assessment of the health status of EMU trains is of great importance.In order to make sure the trains are functional,reliable,and endurable in their full life cycle(FLC),health assessment method for EMU trains after Level 3-5 maintenance and repair is studied.First,the element-selection principles and the assessment rules are defined;second,to present the complex topological relationship between the elements in assessment,a functional logical structure construction method is proposed;third,a health value calculation model is defined based on the element’s characteristics and their logical structures.The health variables of each element is calculated and fitted following the steps in the corresponding weight calculation methods.The assessment method is proved to be applicable and effective.

Investigation on the Structure of Chute-feed and Card Auto-leveller and Their Selection of Technological Processes

Based on the structure of chute - feed and autoleveHer, an analysis of their working principle and the verification of their practical production results have been carried out. Finally, the future investigation direetiom of chute - feed and card autuleveller are put forward.

市县国土空间规划“双层级”村庄分类研究以山南市乃东区为例

科学合理、因地制宜地开展村庄“定型”,是实施分类指导的必要前提。在各地灵活丰富的村庄分类里,介入自然聚落尺度是近期兴起的创新来源。文章以西藏自治区山南市乃东区为例,将传统单纯围绕行政村展开的村庄分类流程,扩展为由自然聚落与行政村尺度共同构成的“双层级”村庄分类技术框架。研究认为,行政村内自然聚落间的强烈异质性及聚落发展的实心化,是应用“双层级”村庄分类理论模型的重要条件。研究提出,“双层级”村庄分类方法由“政策判定+潜力评估+镇村酝酿”的自然聚落分类方法、“占比测算+矩阵构建+系统聚类”的自然聚落→行政村类型转换方法、二次镇村酝酿基础上的行政村分类方案生成方法等共同组成,具体的分类流程需落实聚落定性、聚落测评、聚落分类、类型转换、行政村分类等5项主要环节。理论模型在山南市乃东区国土空间规划中得到了实际应用,识别出5类自然聚落,制定了主导式与并重式的两种行政村类型认定规则,提出了“融保聚改”的四类型行政村分类方案。分类过程及工作成果得到地方积极正面反馈,验证了“双层级”方法的有效性。该研究旨在丰富市县国土空间规划的村庄分类布局思路。