查看更多>>摘要：? 2022 Elsevier B.V.The detection of pests and diseases is very important for agricultural production. Every year, the economic loss caused by pest infestation is enormous. The traditional methods of applying pesticides and fertilizers have negatively affected the ecological environment and human health. There is an urgent need to develop more environmentally friendly pest detection technologies. Although PCR (Polymerase Chain Reaction)-based pest control technology has high accuracy, it requires sample pretreatment and requires training of operators. In the past few years, the electronic nose (E-nose) technology that imitates the animal olfactory system has developed rapidly, and has early warning functions for pests and diseases. This technology has non-damage detection, low cost, high sensitivity, real-time analysis, simple operation, and convenient portability, etc. During the occurrence of pests, crops will release Volatile Organic Compounds (VOCs) to drive away pests, or release VOCs to attract pests' natural enemies to protect themselves. At this time, E-nose has ability to detect the type and concentration of VOCs to reflect the status of crop diseases and insect pests. Metal Oxide Semiconductor (MOS) gas sensors have the advantages of cross-sensitivity, large response range and low manufacturing price, and their arrays have been used in E-nose applications extensively. This article reviews the principle, technology and application progress of MOS electronic nose technology in detecting crop diseases and insect pests, and hopes to provide valuable information for the research on crop diseases and insect pests protection.
查看更多>>摘要：? 2022 Elsevier B.V.Soybeans are one of the main crops grown in the United States. It is crucial to grasp the distribution of soybean cultivation areas for ensuring food security, eradicating hunger and adjusting crop structures. However, the traditional method of extracting soybean planting areas drains on manpower and material resources and takes a long time. The emergence of high-resolution images, such as Sentinel-2A(S2A), enables the identification of soybean at the field scale, and these images can be applied on a large scale with the support of cloud computing technology. This work proposes a heterogeneous double ensemble algorithm to extract soybean planting area. The crop type dataset from the U.S. Department of Agriculture and S2A dataset are applied in this study. Normalized Difference Vegetation Index (NDVI) and Normalized Difference Water Index (NDWI) calculated from S2A data are used to improve the classification accuracy. The proposed method consists of the following steps. Firstly, the S2A data is processed according to phenological information and spectra characteristics. Secondly, the texture features obtained by the grayscale matrix are integrated with spectral features. Thirdly, in order to remove useless features and improve the classification efficiency, only important bands are retained for the next step through feature importance analysis. Fourthly, Random Forest (RF), Classification And Regression Tree (CART), and Support Vector Machines (SVM) serve as base classifiers to train the above-mentioned features. Finally, result maps are obtained by “voting” on three classification results. In this study, three research areas, Guthrie in Iowa, Clinton in Indiana, and Cuming in Nebraska are utilized to validate the effectiveness of the proposed method. Numerical simulations show the increased performance of classification when using these propositions. When compared with the reference methods, the average increase of the overall accuracy obtained by the proposed algorithm is 1.4%, 3.2%, and 1.7% on the Guthrie data, Clinton data, and Cuming data respectively.
查看更多>>摘要：? 2022 Elsevier B.V.Heavy metal pollution in soil endangers food safety and human health. Thus, it is important to study accurate and rapid detection methods. Here, an efficient nondestructive detection method for mercury (Hg), cadmium (Cd) and copper (Cu) in soils was studied by terahertz (THz) spectroscopy. First, regression equations were established between heavy metal contents and absorption coefficients at the selected frequency points. Then, the pollution type and pollution level of the soils containing three heavy metals were detected at the same time. Reference blank soil was also tested. Probabilistic neural network (PNN) and random forest (RF) models verified the effects of qualitative detection. Next, the contents of the three heavy metals in soils were predicted simultaneously by a backpropagation neural network (BPNN) and an extreme learning machine (ELM). The results showed that the absorption coefficients increased regularly in the THz spectral range from 0.05 THz to 0.7 THz. The average detection result of the PNN model was better than that of RF. The average detection accuracy for heavy metal pollution level and type were all higher than 95%. In addition, the prediction results of heavy metal content showed that BPNN model has better prediction performance. The optimal decision coefficients (DC) of BPNN model for soils containing three heavy metals were 0.95, 0.99 and 0.98, respectively, and their corresponding root mean square errors (RMSE) were 0.37, 0.02 and 2.62, respectively. The results proved that THz spectroscopy has good qualitative and quantitative detection ability for soils contaminated with Hg, Cd and Cu, which could bring new opportunities for detection of heavy metal pollutants in soil.
Van De Looverbosch T.He J.Tempelaere A.Verboven P....
14页
查看更多>>摘要：? 2022 Elsevier B.V.To preserve the quality of fresh fruit after harvest and to meet the year-round demand for high-quality fruit, pears are stored under a controlled atmosphere. However, due to preharvest events or suboptimal storage conditions, internal disorders might develop resulting in severe quality loss. Examples include internal browning and cavities, which are invisible externally. Here, X-ray radiography is investigated as a technique for internal quality inspection. The detection of defect fruit is approached as an anomaly detection (AD) problem, in which a model is constructed using nominal data and an anomaly score is used to identify defect fruit. In this work, multiple deep AD methods are shown to be effective to detect pears with internal cavity and browning disorders using X-ray radiographs (mean area under the receiver operating characteristic curve (AUC) up to 0.962). The best performing methods were found on par with a state-of-the-art multisensor disorder detection method (mean AUC up to 0.966). By investigating AD performance in function of internal disorder severity, it was shown that defect fruit with a cavity volume percentage > 1.0% could be detected 100% accurate using inline X-ray imaging. For lower cavity area percentages, the accuracy depended on the internal browning severity. Additionally, the explainability of the deep AD methods, i.e., how well human interpretable insight can be provided from each method's predictions, were qualitatively evaluated using anomaly heatmaps, which provided useful insight in the execution of the deep learning algorithms.
查看更多>>摘要：? 2022 Elsevier B.V.Controlling soil moisture is crucial in optimizing watering and crop performance. Traditional monitoring systems rely on a single sensor or on a column of sensors that do not allow farmers to properly capture soil moisture dynamics in the soil volume occupied by roots. In this paper we propose PLUTO, an original approach that builds fine-grained 2D and 3D soil moisture profiles by relying on a grid of sensors. Profiles are computed using both interpolation-based and machine learning approaches. Besides the technical description of the approach, the paper reports a set of original visualizations and a large set of tests computed, over two years, on real Kiwi orchards. PLUTO proved to largely overcome the accuracy of profiles obtained with traditional sensor layouts. Considering that the cost of sensors is progressively decreasing, PLUTO provides a cost-effective, operative, and precise solution to moisture monitoring.
查看更多>>摘要：? 2022 Elsevier B.V.Nowadays, pressurized irrigation systems have been developing in farms to increase water use efficiency that are successful when the inflow is accurately supplied from water sources. In large irrigation networks, water conveyance and distribution systems are mainly open channels facing several uncertainties. Therefore, water delivery to farms is of the most important tasks that should be done accurately to supply sufficient water to pressurized irrigation farms, causing desired performance of pressurized systems. To this end, regulating structures within irrigation networks should be controlled. Artificial intelligence, as robust and new technology, has been employed for controlling complex systems in the industry. In this research, a new and robust algorithm, namely Double Q-PI (DQ-PI), was developed with the aim of water management in irrigation canals by controlling water depth. It uses a traditional Q-learning algorithm and a double update matrix to tune PI (Proportional-Integral) gains for controlling check gates. It improves its performance using the receiving signals from the irrigation canal model. The approach was tested using several scenarios and evaluated by standard performance indicators. The results showed acceptable accuracy and a reasonable ability in controlling water depth within the canal's reaches. The maximum and average errors were 11.6% and 10.5%, respectively, resulting in significant improvement in water management. With this degree of accuracy at the canal level, the pressurized systems work properly, and the expected efficiency can be achieved.
查看更多>>摘要：? 2022 Elsevier B.V.Poultry behavior is a critical indicator of its health and welfare. Lameness is a clinical symptom indicating the existence of health problems in poultry. Therefore, lameness detection in the early stages is vital to broiler producers. In this study, a pose estimation-based model was developed to identify lameness in broilers through analyzing video footages for the first time. A deep convolutional neural network was used to detect and track seven key points on the bodies of walking broilers. Then consecutive extracted key points were fed into Long Short-Term Memory (LSTM) model to classify broilers according to a 6-point assessment method. This paper proposes the first large-scale benchmark for broiler pose estimation, consisting of 9,412 images. In addition, the dataset includes 400 videos (36,120 frames in total) of broilers with different gait score levels. The developed LSTM model achieved an overall classification accuracy of 95%, and the average per class classification accuracy was 97.5%. The obtained results prove that the pose estimation-based model as an automatic and non-invasive tool of lameness assessment can be applied to poultry farms for efficient management.
查看更多>>摘要：? 2022 Elsevier B.V.This work presents a new deep learning architecture, SpectraNet–53, for quantitative analysis of fruit spectra, optimized for predicting Soluble Solids Content (SSC, in °Brix). The novelty of this approach resides in being an architecture trainable on a very small dataset, while keeping a performance level on-par or above Partial Least Squares (PLS), a time-proven machine learning method in the field of spectroscopy. SpectraNet–53 performance is assessed by determining the SSC of 616 Citrus sinensi L. Osbeck ‘Newhall’ oranges, from two Algarve (Portugal) orchards, spanning two consecutive years, and under different edaphoclimatic conditions. This dataset consists of short-wave near-infrared spectroscopic (SW-NIRS) data, and was acquired with a portable spectrometer, in the visible to near infrared region, on-tree and without temperature equalization. SpectraNet–53 results are compared to a similar state-of-the-art architecture, DeepSpectra, as well as PLS, and thoroughly assessed on 15 internal validation sets (where the training and test data were sampled from the same orchard or year) and on 28 external validation sets (training/test data sampled from different orchards/years). SpectraNet–53 was able to achieve better performance than DeepSpectra and PLS in several metrics, and is especially robust to training overfit. For external validation results, on average, SpectraNet–53 was 3.1% better than PLS on RMSEP (1.16 vs. 1.20 °Brix), 11.6% better in SDR (1.22 vs. 1.10), and 28.0% better in R2 (0.40 vs. 0.31).
查看更多>>摘要：? 2022 Elsevier B.V.Lameness has a negative effect on the welfare and production of dairy cows. In previous studies of lameness detection in cows based on computer vision, cow walking videos contained considerable irrelevant information, lowering detection accuracy. In this study, we proposed a dairy cattle lameness detection method, namely, the Dimension-Reduced Spatiotemporal Network (DRSN), to reduce the impact of irrelevant information, consisting of video dimensionality reduction and deep learning algorithms. The YOLOv4 algorithm was used to detect the cow's hooves from the video. The video was dimensionally reduced to a spatiotemporal image based on the locations of the cow's legs according to the previous detection, retaining gait information while removing much irrelevant information. Finally, the DenseNet algorithm was used to classify the lameness degree into a locomotion score according to the spatiotemporal image. To evaluate the performance of the algorithm, videos of 456 cows were used as the dataset for testing. After comparing different target tracking and classification algorithms, the YOLOv4 object detection and DenseNet classification algorithms demonstrated the best performance, with target detection and classification accuracies of 92.39% and 98.50%, respectively. The result of video-based lameness classification was compared with our method, and the experimental results showed that our method was more accurate. The newly proposed approach can effectively remove irrelevant information and improve the detection accuracy for lameness in dairy cow walking videos. The method can be further integrated into a system for automatically detecting cow lameness.
查看更多>>摘要：? 2022 Elsevier B.V.Soybean cultivar recognition plays a vital role in cultivar evaluation, selection and production. Recently, there is an increasing interest in taking leaf image patterns as clues for distinguishing soybean cultivars. However, due to the higher inter-class similarity of soybean cultivars over plant species, the cultivar classification accuracies reported by the existing methods are far lower than those published on plant species recognition which make computer vision community have a concern whether leaf image patterns can provide sufficient discriminative information for identifying soybean cultivars. In this paper, we explore fusing deep learning features of leaves from different parts of soybean plants for achieving an accurate cultivar recognition. In our method, the deep learning features of triplet leave image patterns that consists of leaves from the lower, middle, and upper parts of soybean plants are fused by two methods, distance fusion and classifier fusion. In the former, the L1 distance measurements defined on the deep feature spaces of triplet leaf image patterns are fused prior to using 1NN classifier for classification. While in the later, the SVM classifiers trained by the deep features of triple leaf image patterns are combined by sum rule for cultivar prediction. We use the SoyCultivar200 leaf dataset which consists of 6000 samples from 200 soybean cultivars as benchmark. Our method achieves an exciting classification rate of 83.55% which demonstrates that our proposed fusion of deep features of triplet leaf image patterns can provide strong discriminative information for accurately identifying soybean cultivars.
NSTL
Elsevier