Information Processing in Agriculture最新文献

Several internet-based surveillance systems have been created to monitor the web for animal health surveillance. These systems collect a large amount of news dealing with outbreaks related to animal diseases. Automatically identifying news articles that describe the same outbreak event is a key step to quickly detect relevant epidemiological information while alleviating manual curation of news content. This paper addresses the task of retrieving news articles that are related in epidemiological terms. We tackle this issue using text mining and feature fusion methods. The main objective of this paper is to identify a textual representation in which two articles that share the same epidemiological content are close. We compared two types of representations (i.e., features) to represent the documents: (i) morphosyntactic features (i.e., selection and transformation of all terms from the news, based on classical textual processing steps) and (ii) lexicosemantic features (i.e., selection, transformation and fusion of epidemiological terms including diseases, hosts, locations and dates). We compared two types of term weighing (i.e., Boolean and TF-IDF) for both representations. To combine and transform lexicosemantic features, we compared two data fusion techniques (i.e., early fusion and late fusion) and the effect of features generalisation, while evaluating the relative importance of each type of feature. We conducted our analysis using a corpus composed of a subset of news articles in English related to animal disease outbreaks. Our results showed that the combination of relevant lexicosemantic (epidemiological) features using fusion methods improves classical morphosyntactic representation in the context of disease-related news retrieval. The lexicosemantic representation based on TF-IDF and feature generalisation (F-measure = 0.92, r-precision = 0.58) outperformed the morphosyntactic representation (F-measure = 0.89, r-precision = 0.45), while reducing the features space. Converting the features into lower granular features (i.e., generalisation) contributed to improving the results of the lexicosemantic representation. Our results showed no difference between the early and late fusion approaches. Temporal features performed poorly on their own. Conversely, spatial features were the most discriminative features, highlighting the need for robust methods for spatial entity extraction, disambiguation and representation in internet-based surveillance systems.

In response to the challenges in providing real-time extraction of crop biophysical signatures, computer vision in computational crop phenotyping highlights the opportunities of computational intelligence solutions. Shadow and angular brightness due to the presence of photosynthetic light unevenly illuminate crop canopy. In this study, a novel vegetation index named artificial bee colony-optimized visible band oblique dipyramid greenness index (vODGI_abc) was proposed to enhance vegetation pixels by correcting the saturation and brightness levels, and the ratio of visible RGB reflectance intensities. Consumer-grade smartphone was used to acquire indoor and outdoor aquaponic lettuce images daily for full 6-week crop life cycle. The introduced saturation rectification coefficient (Ω), value rectification coefficient (ν), green–red wavelength adjustment factor (α), and green–blue wavelength adjustment factor (β) on the original triangular greenness index resulted in 3D canopy reflectance spectrum with two oblique tetrahedrons formed by connecting the vertices of visible RGB band reflectance and maximum wavelength point map to corresponding saturation and value of lettuce-captured images. Hybrid neighborhood component analysis (NCA), minimum redundancy maximum relevance (MRMR), Pearson’s correlation coefficient (PCC), and analysis of variance (ANOVA) weighted most of the canopy area, energy, and homogeneity. Strong linear relationships were exhibited by using vODGI_abc in estimating lettuce crop fresh weight, height, number of spanning leaves, leaf area index, and growth stage with R² values of 0.936 8 for InceptionV3, 0.957 4 for ResNet101, 0.961 2 for ResNet101, 0.999 9 for Gaussian processing regression, and accuracy of 88.89% for ResNet101, respectively. This low-cost approach on developing greenness index for biophysical signatures estimation proved to be more accurate than the previously established triangular greenness index (TGI) using RGB smartphone camera.

Classification of sheep behaviour from a sequence of tri-axial accelerometer data has the potential to enhance sheep management. Sheep behaviour is inherently imbalanced (e.g., more ruminating than walking) resulting in underperforming classification for the minority activities which hold importance. Existing works have not addressed class imbalance and use traditional machine learning techniques, e.g., Random Forest (RF). We investigated Deep Learning (DL) models, namely, Long Short Term Memory (LSTM) and Bidirectional LSTM (BLSTM), appropriate for sequential data, from imbalanced data. Two data sets were collected in normal grazing conditions using jaw-mounted and ear-mounted sensors. Novel to this study, alongside typical single classes, e.g., walking, depending on the behaviours, data samples were labelled with compound classes, e.g., walking_grazing. The number of steps a sheep performed in the observed 10 s time window was also recorded and incorporated in the models. We designed several multi-class classification studies with imbalance being addressed using synthetic data. DL models achieved superior performance to traditional ML models, especially with augmented data (e.g., 4-Class + Steps: LSTM 88.0%, RF 82.5%). DL methods showed superior generalisability on unseen sheep (i.e., F1-score: BLSTM 0.84, LSTM 0.83, RF 0.65). LSTM, BLSTM and RF achieved sub-millisecond average inference time, making them suitable for real-time applications. The results demonstrate the effectiveness of DL models for sheep behaviour classification in grazing conditions. The results also demonstrate the DL techniques can generalise across different sheep. The study presents a strong foundation of the development of such models for real-time animal monitoring.

Energy consumption in the agricultural sector is significant, reaching 20% of the total energy consumption in China. Agricultural Energy Internet, an important extension of Energy Internet in the agricultural field, significantly contributes to agricultural modernization. Key technologies of Agricultural Energy Internet are vital factors supporting its development. This article systematically reviews the key technologies of Agricultural Energy Internet for two areas: agriculture and fishery. The working mechanisms and power consumption characteristics of some state-of-the-art new-energy agricultural intelligent equipment are described. In addition, the principles and profit methods underlying the agro-industrial complementary operation model are introduced. Moreover, against the Agricultural Energy Internet background, the development trends of some state-of-the-art new energy agricultural intelligent equipment, agro-industrial complementary, and carbon–neutral technology are proposed in this paper, providing novel perspectives on the promotion of the development of Agricultural Energy Internet and related technological innovation research. An unmanned farm is the main form of the future agricultural system, which is powered by the Agricultural Energy Internet based on smart agriculture and a smart grid. It will become the inevitable trend of modern agriculture to replace oil agriculture with electric farms. The electricity in farming is mainly generated by renewable energy. Renewable energy power generation has low carbon emissions and is the future direction for the development of agricultural energy systems. In addition, the Internet of Things will be further strengthened to realize automation and intelligence of agricultural energy systems.

Sugarcane planting is an important and growing activity in Brazil. Thereupon, several techniques have been developed over the years to maximize crop productivity and profit, amongst them, processing of sugarcane field images. In this sense, this research aims to identify and analyze crop rows and measure their gaps from aerial images of sugarcane fields. For this, a small Remotely Piloted Aircraft captured the images, generating orthomosaics of the areas for analysis. Then, each orthomosaic is classified with the K-Nearest Neighbor algorithm to segment regions of interest. Planting row orientation is estimated using the RGB gradient filter. Morphological operations and computational geometry models are then used to detect and map rows and gaps along the planting row segment. To evaluate the results, crop rows are mapped and compared to manually taken measurements. Our technique obtained an error smaller than 2% when compared to gap length in crop rows from an orthomosaic with the area of 8.05 ha (ha). The proposed approach can map the positioning of the automatically generated row segments appropriately onto manually created segments. Moreover, our method also achieved similar results when confronted with a manual technique for differing growth stages (40 and 80 days after harvest) of the sugarcane crop. The proposed method presents a great potential to be adopted in sugarcane planting monitoring.

Oil content estimation in palm fruits is a precious property that significantly impacts oil palm production, starting from the upstream and downstream. This content can be used to monitor the progress of the oil palm fresh fruit bunch (FFB) and be applied to identify product profitability. Based on the near-infrared (NIR) signals, this study proposes an empirical mode decomposition (EMD) technique to decompose signals and predict the oil content of palm fruit. First, 350 palm fruits with Tenera varieties (Elaeis guineensis Jacq. var. tenera), at various ages of maturity, were harvested from the Cikabayan Oil Palm Plantation (IPB University, Indonesia). Second, each sample was sent directly to the laboratory for NIR signal measurements and oil content extraction. Then, the EMD analysis and artificial neural network (ANN) were employed to correlate the NIR signals and oil content. Finally, a robust EMD-ANN model is generated by optimizing the lowest possible errors. Based on performance evaluation, the proposed technique can predict oil content with a coefficient of determination (R²) of 0.933 ± 0.015 and a root mean squared error (RMSE) of 1.446 ± 0.208. These results demonstrate that the model has a good predictive capacity and has the potential to predict the oil content of palm fruits directly, without neither solvents nor reagents, which makes it environmentally friendly. Therefore, the proposed technique has a promising potential to be applied in the oil palm industry. Measurements like this will lead to the effective and efficient management of oil palm production.

A large loss occurs in the combine harvesting of rapeseeds due to the fragility of rapeseed pods, and all the more so with the vibration of the combine header and the collision between the header and plants. Seed loss is greatly affected by the biomechanical properties of ready-to-harvest rapeseed plants. To understand the mechanism of pod cracking and seed loss and to propose measures for alleviating them, it is needed to study the biomechanical properties of ready-to-harvest rapeseed plants. To this end, “Huayouza 62”, a widely planted rapeseed variety in central China, was selected to study the biomechanical properties, including pod-cracking resistance, main stem-shearing resistance and resonant frequencies, of whole plants. The results showed that the distribution of pod-cracking resistance forces was 1.333–6.100 N in the mature stage, and the pod width and thickness had a significant influence on the cracking resistance. The main influencing factor of the main stem-shearing resistance was the stem diameter. A thicker main stem resulted in a larger shearing resistance force but a smaller shear stress. The moisture contents of the main stems varied from 47.71% to 76.13%. However, the varying moisture contents did not show a significant impact on the shearing resistance. The resonant frequencies of whole rapeseed plants ready for harvest ranged from 6.5 Hz to 7.5 Hz, which was close to the excitation frequency of the cutter bar on the 4LL-1.5Y harvester. This study lays a foundation for improving the design and construction of harvesting devices for rapeseed plants to reduce seed loss.

The objective of this study is to investigate the effectiveness of a multi-parameter intelligent fault diagnosis method based on a modified random forest algorithm (RFNB algorithm), so as to reduce the impact of blockage fault on the operation of a silage harvester, thus providing a reference for the intelligent control. In brief, the forward speed, cutting speed, engine speed and engine load were selected as the input variables. Then, a random forest (RF) was used to construct a naive Bayes classifier for each node of the decision tree, and finally the RFNB algorithm constituted based on the naive Bayes tree (NBTree). The results revealed that by improving the classification accuracy of a single decision tree, the fault diagnosis accuracy of the entire RF was improved. When the sample data were consistent, the accuracy of the RFNB algorithm was 97.9%, while that of the RF algorithm was only 93.27%. Besides, the performance of RFNB classifiers was significantly better than that of RF classifiers. In conclusion, the RFNB model can accurately identify the fault status of the silage harvester with its good robustness, which provides a new idea for the fault monitoring and early warning of large agricultural rotating machinery in the future.