首页期刊导航|Computers and Electronics in Agriculture
期刊信息/Journal information
Computers and Electronics in Agriculture
Elsevier Science Publishers
Computers and Electronics in Agriculture

Elsevier Science Publishers

0168-1699

Computers and Electronics in Agriculture/Journal Computers and Electronics in AgricultureSCIEIISTP
正式出版
收录年代

    Soybean seed counting and broken seed recognition based on image sequence of falling seeds

    Chen Z.Fan W.Luo Z.Guo B....
    16页
    查看更多>>摘要：? 2022 Elsevier B.V.Seed counting and broken seed identification are important tasks in evaluating seed quality. In this study, we proposed a computational method designed to perform these two functions. Image sequences of soybean seeds during falling were collected, and their morphologies were examined from different views. An a priori clustering algorithm composed of a support vector machine and k-means clustering algorithm was used to segment touching seeds within images. The morphologies of specific soybean seeds in sequential images were associated based on a forced neighbor association criterion to avoid repeated counting and obtain shape features from multiple views. Based on the areas in different views, the basic shape features in the initial multi-view shape features were sorted to obtain the guided multi-view shape features. The support vector machine was used with the guided multi-view shape feature to classify seeds as intact or broken. The experimental results show that the proposed a priori clustering algorithm accurately segmented touching seeds. The forced nearest-neighbor data association algorithm is insensitive to touching seeds and achieved highly accurate seed counting. Compared with the single-view shape feature, the multi-view shape feature significantly improves the accuracy of seed morphological classification. The proposed method exhibited considerable potential for applications in agricultural engineering.
      原文链接:
    • NSTL
    • Elsevier

    Dynamic algorithmic conversion of compressed sward height to dry matter yield by a rising plate meter

    McSweeney D.O'Brien B.Byrne N.McDonagh J....
    4页
    查看更多>>摘要：? 2022 The AuthorsThe strategic allocation of pasture grazing area to dairy cows is essential for optimal management and increased outputs. Rising plate meters are frequently used to estimate pasture herbage mass, i.e. dry matter yield per hectare, by employing simple regression equations that relate compressed sward height to herbage mass. However, to improve the accuracy and precision of these equations, so that inherent variation of grasslands is captured, there is a need to incorporate differences in grass types and seasonal growth. Using a total of 308 grass plots, the variation of growth for both perennial ryegrass and hybrid ryegrass was recorded over the seven-month growing season, i.e. March–September. From these data three dynamic equations were derived. The models showed reduced levels of error in comparison to most other conventional equations. As such, the derived models represent a considerable advance for predictive assessment of herbage mass and will support more efficient grassland utilisation by farmers. Although all equations were found to be highly accurate and precise, only a single equation was considered the most effective (R2 = 0.7; RMSE = 248.05), allowing herbage mass to be predicted reliably from compressed sward height data in relation to ryegrass type and calendar month. Although further research will be required, the results presented allow farm operators to calculate herbage mass, as well as support the development of decision support tools to improve on-farm grassland management, particularly at the local paddock rather than national level.
      原文链接:
    • NSTL
    • Elsevier

    Artificial neural network to predict traction performance of autonomous ground vehicle on a sloped soil bin and uncertainty analysis

    Badgujar C.Flippo D.Welch S.
    10页
    查看更多>>摘要：? 2022 Elsevier B.V.A fleet of autonomous ground vehicles (AGV) is envisioned to expand farming to arable land suitable for production except for being too steep for conventional equipment. The success of proposed multi-AGV system largely depends on the traction performance of the individual AGVs on unevenly sloped terrain and optimization of the AGVs control variables. Therefore, the drawbar pull performance of a prototype AGV was evaluated in a soil bin at varying slopes, speeds, and drawbar pull (DP). The AGV's traction performance was expressed in three metrics: tractive efficiency (TE), travel reduction ratio (TRR), and power number (PN). Optimizing the control variables is intricate and ill-defined, which requires an accurate model to predict the performance of the proposed multi-AGV system. Hence, this study aims to design an artificial neural network (ANN) to estimate the traction behavior of the AGV on a sloped testbed as a function of AGV's speed, applied DP, and slope. A multi-layer perceptron feed-forward ANN architecture with a single hidden layer trained with a back-propagation algorithm was adopted. A series of ANN models with increasing complexity and different hidden layer activation functions were developed for each response variable, i.e., ANN-TE, ANN-TRR, and ANN-PN. A re-sampling-based method, K-fold cross-validation, was employed to estimate the model generalization error. The model success was evaluated via Mean Squared Error (MSE) and the Coefficient of Determination (R2) against a test set. The final predictive model was trained on the entire data set, and the observed R2 was 0.933, 0.882 and 0.858, respectively, for ANN-TE, ANN-TRR, and ANN-PN. Subsequently, a Monte-Carlo Simulation based uncertainty analysis was carried out to demonstrate the model strength and the degree of uncertainty by constructing a 95% prediction interval. This study shows ANN as a promising, robust, and reliable method to predict traction performance in agricultural tillage-traction studies and developed models can empower the multi-AGV system on steep-uneven slope terrain.
      原文链接:
    • NSTL
    • Elsevier

    Exploring the potential of hyperspectral imaging to detect Esca disease complex in asymptomatic grapevine leaves

    Perez-Roncal C.Arazuri S.Jaren C.Lopez-Maestresalas A....
    12页
      原文链接:
    • NSTL
    • Elsevier

    Cultivating FAIR principles for agri-food data

    Top J.Janssen S.Boogaard H.Knapen R....
    12页
    查看更多>>摘要：? 2022Data generated by the global food system is crucial in the transformation towards sustainable, resilient, and high-quality food production. Although the amount of potentially useful data is growing rapidly, its (re)use is still limited. The FAIR-principles have been developed for making data findable, accessible, interoperable, and reusable both by humans and machines. This paper explores the further operationalization of the FAIR principles in agriculture and food. Experience shows that several conditions must be fulfilled before data can be effectively shared and reused. First, automated tools must be available for data providers and users. Secondly, we need a community-based approach in developing tools and vocabularies. Thirdly, data cannot be shared by an open-by-default policy only. Finally, scientific insight is needed in how data is actually (re)used in scientific communities. We conclude that bringing the FAIR-principles to full maturity requires a fair balance of efforts within the agri-food communities, supported by a proper infrastructure.
      原文链接:
    • NSTL
    • Elsevier

    Fusion of Mask RCNN and attention mechanism for instance segmentation of apples under complex background

    Wang D.He D.
    9页
    查看更多>>摘要：? 2022 Elsevier B.V.It is important to precisely segment apples in an orchard during the growth period to obtain accurate growth information. However, the complex environmental factors and growth characteristics, such as fluctuating illumination, overlapping and occlusion of apples, the gradual change in the ground colour of apples from green to red, and the similarities between immature apples and background leaves, affect apple segmentation accuracy. The purpose of this study was to develop a precise apple instance segmentation method based on an improved Mask region-based convolutional neural network (Mask RCNN). An existing Mask RCNN model was improved by fusing an attention module into the backbone network to enhance its feature extraction ability. A combination of deformable convolution and the transformer attention with the key content only term was used as the attention module in this study. The experimental results showed that the improved Mask RCNN can accurately segment apples under various conditions, such as apples with shadows and different ground colours, overlapped apples, and apples occluded by branches and leaves. A recall, precision, F1 score, and segmentation mAP of 97.1%, 95.8%, 96.4% and 0.917, respectively, were achieved, and the average run-time on the test set was 0.25 s per image. Our method outperformed the two methods in comparison, indicating that it can accurately segment apples in the growth stage with a near real-time performance. This study lays the foundation for realizing accurate fruit detection and long-term automatic growth monitoring.
      原文链接:
    • NSTL
    • Elsevier

    Deep convolution neural network with weighted loss to detect rice seeds vigor based on hyperspectral imaging under the sample-imbalanced condition

    Wu N.Xiao Q.He Y.Weng S....
    11页
    查看更多>>摘要：? 2022Vigor detection of crop seeds before putting them on the market is important for ensuring the yield and quality of the crops. In the actual production, however, different levels tend to vary in the number of samples, leading to the problem of sample imbalance. This study proposed a deep convolution neural network (DCNN) with weighted loss to achieve batch and non-destructive vigor detection of rice seeds based on hyperspectral imaging (HSI) under the sample-imbalanced condition. The true vigor state of seeds with different degrees of artificial aging was labeled by traditional analysis methods. The seeds were first classified into six categories according to the aging time using a constructed DCNN, which was proved to be unreasonable. Then four categories were merged, and the seeds were reclassified into three new categories by a rebuilt DCNN. However, merging categories caused the problem of sample imbalance, leading to much confusion between two aged categories. Thus, a DCNN with weighted loss was further proposed focusing on assigning appropriate weight to each category. Obtaining the highest accuracy and Macro F1 of 97.69% and 97.42%, respectively, it outperformed the DCNN with balanced loss and conventional models. The visualization analysis was conducted using PCA and t-SNE to inspect the aggregation between feature points. The overall results indicated the effectiveness of the proposed DCNN with weighted loss in the vigor detection of rice seeds under the sample-imbalanced condition, which would be conducive to online grading according to seed vigor and other qualities in the actual production.
      原文链接:
    • NSTL
    • Elsevier

    Automatic detection of quality soil spectra in an online vis-NIR soil sensor

    Guerrero A.Mouazen A.M.Javadi S.H.
    11页
    查看更多>>摘要：? 2022 Elsevier B.V.The quality of online visible and near infrared (vis-NIR) soil spectra can be deteriorated by interferences of ambient light, and debris e.g., stones, roots or plant residues among others, which considerably reduces the accuracy of the predictions. Filtering of very noisy and non-soil spectra from good-quality soil spectra needs to be performed prior the modelling. Nevertheless, manual filtering of the large amount of vis-NIR online measurement is a laborious and time-consuming task. This study was conducted to develop an automatic filtering system of very noisy and non-soil spectra. Soil and non-soil spectra obtained during online vis-NIR measurements in four commercial fields in Flanders, Belgium were used to build two databases. The main difference in the databases is that flat spectra, mostly found in wet soil conditions, were considered as non-soil spectra in the first group and as soil spectra in the second group. Similarity algorithms [i.e., Pearson correlation, Spearman correlation, Euclidian distance, cosine distance and principal component analysis (PCA)] and machine learning algorithms (i.e., linear discriminant analysis, support vector machine and K-nearest neighbors) for spectra filtering using the two databases were evaluated and compared. Results suggest that the similarity algorithms were not successful to classify spectra into soil and non-soil classes for both groups, since the best prediction accuracy in cross-validation achieved by the cosine distance algorithm was 76.11%. However, the machine learning algorithms provided high classification accuracies for both databases. For the former database, the best classification result of 98.5% in cross-validation and 98.6% in independent validation was obtained by using the k-nearest neighbor algorithm. While for the latter database, the best result was achieved by the support vector machine algorithm with a gaussian kernel obtaining 81.4% in cross-validation and 82.03% in independent validation. The best performing model was used to build a cleaning function to automatically pre-process and classify spectra into soil or non-soil classes. This automatic spectrum filtering system enables time saving and ensures only high-quality spectra are used for accurate online prediction of soil properties, necessary for sensor-based variable rate applications.
      原文链接:
    • NSTL
    • Elsevier

    Hyperspectral image information fusion-based detection of soluble solids content in red globe grapes

    Gao S.Xu J.-H.
    9页
    查看更多>>摘要：? 2022 Elsevier B.V.The Soluble Solids Content (SSC) of red globe grapes is an important indicator of internal quality. In this paper, 360 red globe grapes in the growing stage were collected as samples and the spectral information and images of the samples were extracted. The Raw spectral (RAW) information was extracted using the one-time dimensionality reduction algorithm (GA, CARS, SPA, UVE) and the combined dimensionality reduction algorithm (CARS-SPA, UVE-SPA) to build the PLSR model of the spectral information. The grey-scale co-occurrence matrix of the image was extracted as the texture feature information of the image and combined with the color information of the image (R, G, B, H, S, V, L, a, b) to form 19 image features to build the PLSR model of the image information. Thus, the PLSR model based on the fusion of hyperspectral image information was built by fusing the spectra extracted with the successive projection algorithm (SPA) feature wavelength and the image information after dimensionality reduction by the principal component analysis algorithm (PCA). The results showed that if only the spectral information was used for modelling, the SPA algorithm effectively extracted the characteristic wavelengths of the red globe grapes of SSC spectral information and improved the prediction performance of the model. If only image information was used for modelling, the PCA algorithm effectively improved the detection performance of the model by dimensionality reduction, but the improved performance was limited. The correlation coefficients of the calibration set and prediction set of the PLSR model were 0.9775 and 0.9762, and the detection effect and stability of the model were greatly improved compared with those built unilaterally based on spectral information or image information, and a new non-destructive detection method was found for the detection about SSC of red globe grapes.
      原文链接:
    • NSTL
    • Elsevier

    Prediction of litter performance in lactating sows using machine learning, for precision livestock farming

    Gauthier R.Dourmad J.-Y.Largouet C.
    10页
    查看更多>>摘要：? 2022 Elsevier B.V.Predicting litter performance in lactating sows is an essential step towards the development of decision support systems for precision feeding in lactating sows. Numerous factors affecting litter performance have been described in literature. However, predictive models working on-farm in real time are not available. The main objectives of this research was to (i) explore 4 different machine learning strategies, and (ii) identify the best supervised learning algorithm in order to obtain reliable predictions of litter performance. This study was carried out with data obtained from 6 experimental farms over the last 20 years. Algorithms were trained to predict the litter weight at weaning using a set of 4 numeric and 3 categorical features, and a method for predicting secondary litter performance and nutrient output in milk from the predicted litter weight at weaning was evaluated. To evaluate the reliability of predictions within each farm, the mean error per farm (MEf) and the mean absolute percentage error per farm (MAPEf) were computed. The best performance for the prediction of litter weight at weaning was obtained with an ensemble algorithm with farm-level training and testing (MEf = ?0.14 kg; MAPEf = 9.01%), but performance with simple linear regression was very close (MAPEf = 9.30%). Learning across all farms only achieved comparable results with the neural networks algorithm, but at higher computational costs. The method for predicting secondary litter performance and nutrient output from the predictions of litter weight at weaning reveals that the MEf remains close to 0, and that the MAPEf only increases by a few percentage points. This study confirms the effect of numerous factors known in the literature to affect litter performance, such as litter size and parity of sows, but also revealed huge variations between farms. According to this study, reliable predictions could be obtained with interpretable supervised algorithms trained at farm level, with features that can be easily measured on-farm. This study thus shows that on-farm data are necessary to accurately train models and make reliable predictions at farm level. These predictions could be used by decision support systems in order to develop precision feeding approaches in lactating sows.
      原文链接:
    • NSTL
    • Elsevier