Showing papers in "Information Processing in Agriculture in 2021"

TL;DR: A comprehensive review of recent studies carried out in the area of crop pest and disease recognition using image processing and machine learning techniques and reports that recent efforts have focused on the use of deep learning instead of training shallow classifiers using hand-crafted features.

TL;DR: This paper presents the insect pest detection algorithm that consists of foreground extraction and contour identification to detect the insects for Wang, Xie, Deng, and IP102 datasets in a highly complex background and exhibits considerable improvement in classification accuracy, computation time performance, and state-of-the-art classification algorithms.

TL;DR: The paper suggested two approaches based on machine learning and transfer learning for classification of papaya maturity status, i.e. VGG19 based on transfer learning approach achieved 100% accuracy which is 6% more than the existing method.

TL;DR: The RNN model, LSTM model, and GRU model were used to build three DO predicting models and it was concluded that the GRU has overall better performance and can be applied to practical applications.

TL;DR: The research findings show that smart contracts, Internet of Things (IoT), and transaction records are of the highest importance among the blockchain dimensions.

TL;DR: An efficient and effective machine vision system based on the state-of-the-art deep learning techniques and stacking ensemble methods to offer a non-destructive and cost-effective solution for automating the visual inspection of fruits’ freshness and appearance is proposed.

TL;DR: In this article, an improved monitoring and data-driven modelling of the dynamics of parameters affecting the irrigation of a mustard leaf plant is presented using ESPresso Lite V20 module interfaced with different soil moisture sensors (VH-400), flowmeter (YF-S201) as well as Davis vantage pro 2 weather station to measure soil moisture content, irrigation volume, and computation of the reference evapotranspiration (ETo) The data collected including plant images were transmitted to the Raspberry Pi 3 controller for onward online storage and the data are displayed on the IoT dashboard

TL;DR: In this paper, a study has been carried out to define the model of evapotranspiration estimation that best adapts to the semi-arid region in South India.

TL;DR: Novel ResTS architecture incorporates the residual connections in all the constituents and it executes batch normalization after each convolution operation which is dissimilar to the formerly proposed Teacher/Student architecture for plant disease diagnosis.

TL;DR: An effective and practical system capable of segmenting and classifying different types of leaf lesions and estimating the severity of stress caused by biotic agents in coffee leaves using convolutional neural networks is presented.

TL;DR: In this paper, a gradient boost decision tree (GBDT) model based on the newly developed Light Gradient Boosting Machine algorithm (LightGBM or LGBM) was proposed to model the internal temperature of a greenhouse.

TL;DR: A classification algorithm based on the fine-tuned AlexNet model and feature of the spectrogram, with the advantages of the convolutional neural network in image recognition, is proposed to provide a highly accurate pig cough recognition method for the respiratory disease alarm system.

TL;DR: This work proposes a segmentation method based on the combination of semantic segmentation and K-means algorithms for the segmentation of crops and weeds in color images that provided more accurate segmentation in comparison to other methods.

TL;DR: Analysis and comparison of these two methods reveals that current agricultural disease data resources make transfer learning the better option for agricultural disease image recognition.

TL;DR: Wang et al. as discussed by the authors proposed a new classification method for the early soybean mosaic virus disease (SMV), dividing its severity into grades 0, 1 and 2, and used a combined convolutional neural network and support vector machine (CNN-SVM) method for early detection of SMV.

TL;DR: The results suggest that the dimensionality reduction algorithm based on self-organized maps is an efficient approach compared with other popular algorithms, due to the ability of self- organized maps to automatically detect (self-organizing) relationships within the set of input patterns, which provides flexibility to deal with the special features of the hyperspectral images.

TL;DR: In this paper, the authors used a combined model (behavioral and geographical) to adopt rural technology, which has presented a better understanding of adoption in the rural population of Iran.

TL;DR: The results of this study demonstrated the effectiveness and feasibility of the proposed method for fault diagnosis of tractor auxiliary gearbox.

TL;DR: In this article, the hydration characteristics of green chickpea (GC) using mathematical modelling and examine predictive ability of artificial neural network (ANN) modelling were examined. And the results showed that the LOGSIGMOID transfer function showed better performance when used at the hidden layer input node in conjunction to both PURELIN and TANSIGMOIDs.

TL;DR: The results showed the proposed monitoring system stability for overall operation and accuracy data transmission, which can support the actual hydroponics and aquaculture production management.

TL;DR: The survey reveals limitations in image processing techniques for cereal crop monitoring such as lack of robustness to lighting conditions, camera position, and self-obstruction.

TL;DR: A comprehensive survey on recent machine vision methods for plant trait estimation and classification is presented and future research directions related to the use of deep learning based machine vision algorithms for structural, physiological and temporal trait estimation, and classification studies in plants are presented.

TL;DR: In this article, the functional link artificial neural network (FLANN) was used to estimate daily pan evaporation in three agro-climatic zones (ACZs) of Chhattisgarh state in east-central India.

TL;DR: An autonomous navigation algorithm using visual cues and fuzzy control is proposed for Wolfberry orchards that meets the requirements of automatic picking of wolfberry picking robot in real-world environments and has good robustness and real-time performance.

TL;DR: To generate smooth trajectories for fruit-picking robot manipulators using shortcuts that are constrained in velocity, acceleration and jerk, the idea is to build shorter and collision-free shortcuts that replace the intermediate motion between two randomly-picked points on the trajectory.

TL;DR: The nondestructive instrumental researches in the field of firmness assessment for apple fruit discussed, which consist of acoustic and mechanical vibration methods, optical methods such as hyperspectral scattering imaging, near infrared, ultrasound and other methods, suitable for online applications.

TL;DR: In this paper, a measurement model, the distribution profiles of temperature, and a preliminary assessment of the geothermal potential in the shallow zone at depths of 0.1 m to 3.6 m in Shouguang City, Shandong Province, eastern China were presented.

TL;DR: In this paper, the authors proposed a soft computing method to predict the ammonia nitrogen content in aquaculture water in real time using EMD, improved particle swarm optimization (IPSO), and extreme learning machine (ELM).

TL;DR: A light trap based four-layer deep neural network with search and rescue optimization (DNN-SAR) method to identify leaf folders and yellow stemborers that outperformed the existing methods and achieved 98.29% pest detection accuracy.

TL;DR: In this article, the FAO AquaCrop model was used to model the effects of water and different levels of nitrogen on evapotranspiration and water productivity of rainfed soybeans.