Subjects: Agriculture, Forestry,Livestock & Aquatic Products Science >> Other Disciplines of Agriculture, Forestry,Livestock & Aquatic Products Science submitted time 2023-02-17 Cooperative journals: 《智慧农业（中英文）》
Abstract： Corn and soybean are upland grain in the same season, and the contradiction of scrambling for land between corn and soybean is prominent in China, so it is necessary to explore the price relations between corn and soybean. In addition, agricultural futures have the function of price discovery compared with the spot. Therefore, the analysis and prediction of corn and soybean futures prices are of great significance for the management department to adjust the planting structure and for farmers to select the crop varieties. In this study, the correlation between corn and soybean futures prices was analyzed, and it was found that the corn and soybean futures prices have a strong correlation by correlation test, and soybean futures price is the Granger reason of corn futures price by Granger causality test. Then, the corn and soybean futures prices were predicted using a long short-term memory (LSTM) model. To optimize the futures price prediction model performance, Attention mechanism was introduced as Attention-LSTM to assign weights to the outputs of the LSTM model at different times. Specifically, LSTM model was used to process the input sequence of futures prices, the Attention layer assign different weights to the outputs, and then the model output the prediction results after a layer of linearity. The experimental results showed that Attention-LSTM model could significantly improve the prediction performance of both corn and soybean futures prices compared to autoregressive integrated moving average model (ARIMA), support vector regression model (SVR), and LSTM. For example, mean absolute error (MAE) was improved by 3.8% and 3.3%, root mean square error (RMSE) was improved by 0.6% and 1.8% and mean absolute error percentage (MAPE) was improved by 4.8% and 2.9% compared with a single LSTM, respectively. Finally, the corn futures prices were forecasted using historical corn and soybean futures prices together. Specifically, two LSTM models were used to process the input sequences of corn futures prices and soybean futures prices respectively, two parameters were trained to perform a weighted summation of the output of two LSTM models, and the prediction results were output by the model after a layer of linearity. The experimental results showed that MAE was improved by 6.9%, RMSE was improved by 1.1% and MAPE was improved by 5.3% compared with the LSTM model using only corn futures prices. The results verify the strong correlation between corn and soybean futures prices at the same time. In conclusion, the results verify the Attention-LSTM model can improve the performances of soybean and corn futures price forecasting compared with the general prediction model, and the combination of related agricultural futures price data can improve the prediction performances of agricultural product futures forecasting model.
Subjects: Agriculture, Forestry,Livestock & Aquatic Products Science >> Other Disciplines of Agriculture, Forestry,Livestock & Aquatic Products Science submitted time 2023-02-17 Cooperative journals: 《智慧农业（中英文）》
Abstract： Crop models involve complex plant processes, which can be built in different scales of space and time, from molecule, cell, organ, tissue, individual to stand in space and from second to year in time. Based on different research requirements, switching the model scales can make the applicability of the model more extensive and flexible. How to switch the crop model from stand level to organ level is the content of this research. The DSSAT software (stand level) and functional-structural plant model 'GreenLab' (organ level) were chosen to explore the possibility to switch the crop model from stand to organ level. The DSSAT can simulate the growth and development processes of crops in detail according to the growth period by taking the data of weather, soil, crop management, and observational data as input. The GreenLab can simulate the growth and development and their interaction of crops by considering plant structure, and the model parameters can be estimated according to the measurements. In this study, the experimental data contains two parts: the measurements of four maize cultivars with two treatments (irrigated and rainfed) in DSSAT, and the simulations including the weights of leaves, internodes and fruits per day using DSSAT based on the measurements. The simulation results of DSSAT were used to calibrate the parameters of the environmental (E), sink strength (Po), and remobilization (kb and ki) in GreenLab, and to compute the weights of leaves, internodes and fruits for each phytomer. The simulation results of the GreenLab model were compared and analyzed with the experimental data and the simulations of DSSAT. The consistency of calculation results could be an indicator to explore the method of building an interface between different-scale crop models, and to compare the characteristics of different models. The results showed that the GreenLab model could reproduce the simulation data of the DSSAT and the measurement data, including the leaf area index (LAI) and the total weight of the plants, and further could compute the biomass for each organ (leaf, internode and fruit), and the biomass distribution among organs, the biomass production (Q), the demand (D) and the ratio between Q and D during the growth. Therefore, the detailed information of organ growth and development could be reproduced and the 3D structures of plant could be given. Finally, the advantages and application fields of different-scale model integration were discussed.
Subjects: Agriculture, Forestry,Livestock & Aquatic Products Science >> Other Disciplines of Agriculture, Forestry,Livestock & Aquatic Products Science submitted time 2023-02-17 Cooperative journals: 《智慧农业（中英文）》
Abstract： With the development of smart agriculture, automatic question and answer (Q&A) of agricultural knowledge is needed to improve the efficiency of agricultural information acquisition. Agriculture named entity recognition plays a key role in automatic Q&A system, which helps obtaining information, understanding agriculture questions and providing answer from the knowledge graph. Due to the scarcity of labeled ANE data, some existing open agricultural entity recognition models rely on manual features, can reduce the accuracy of entity recognition. In this work, an approach of model distillation was proposed to recognize agricultural named entity data. Firstly, massive agriculture data were leveraged from Internet, an agriculture knowledge graph (AgriKG) was constructed. To overcome the scarcity of labeled named agricultural entity data, weakly named entity recognition label on agricultural texts crawled from the Internet was built with the help of AgriKG. The approach was derived from distant supervision, which was used to solve the scarcity of labeled relation extraction data. Considering the lack of labeled data, pretraining language model was introduced, which is fine tuned with existing labeled data. Secondly, large scale pretraining language model, BERT was used for agriculture named entity recognition and provided a pretty well initial parameters containing a lot of basic language knowledge. Considering that the task of agriculture named entity recognition relied heavily on low-end semantic features but slightly on high-end semantic features, an Attention-based Layer Aggregation mechanism for BERT(BERT-ALA) was designed in this research. The aim of BERT-ALA was to adaptively aggregate the output of multiple hidden layers of BERT. Based on BERT-ALA model, Bidirectional LSTM (BiLSTM) and conditional random field (CRF) were coupled to further improve the recognition precision, giving a BERT-ALA+BiLSTM+CRF model. Bi-LSTM improved BERT's insufficient learning ability of the relative position feature, while conditional random field models the dependencies of entity recognition label. Thirdly, since BERT-ALA+BiLSTM+CRF model was difficult to serve online because of the extremely high time and space complexity, BiLSTM+CRF model was used as student model to distill BERT-ALA+BiLSTM+CRF model. It fitted the BERT-ALA+BiLSTM+CRF model's output of BiLSTM layer and CRF layer. The experiment on the database constructed in the research, as well as two open datasets showed that (1) the macro-F1 of the BERT-ALA + BiLSTM + CRF model was improved by 1% compared to the baseline model BERT + BiLSTM + CRF, and (2) compared with the model trained on the original data, the macro-F1 of the distilled student model BiLSTM + CRF was increased by an average of 3.3%, the prediction time was reduced by 33%, and the storage space was reduced by 98%. The experimental results verify the effectiveness of the BERTALA and knowledge distillation in agricultural entity recognition.
Subjects: Psychology >> Social Psychology submitted time 2018-09-07 Cooperative journals: 《心理学报》
Abstract： 分别从特质依恋和状态依恋角度考察施助者的依恋安全在求助者面孔可信度与助人行为之间的调节作用。结果发现：(1)求助者面孔可信度影响助人行为, 面孔可信度高的求助者得到的助人行为显著多于面孔可信度低的求助者; (2)施助者的依恋安全调节求助者面孔可信度与助人行为之间的关系, 安全依恋能有效缓冲低面孔可信度带来助人行为下降的趋势。本研究结果表明依恋安全有助于提升社会安全感和促进亲社会行为, 因此应注重依恋安全的培养。
Hits
Hits
Downloads
Comment