Computers and Electronics in Agriculture (COMPUT ELECTRON AGR )

Publisher: Elsevier


Computers and Electronics in Agriculture provides international coverage of advances in the application of computer hardware, software and electronic instrumentation and control systems to agriculture, forestry and related industries. The latter include horticulture (in both its food and amenity aspects), forest products, aquaculture, animal/livestock science, veterinary medicine and food processing.The journal publishes original papers, reviews, applications notes and book reviews on topics including computerized decision-support aids (e.g., expert systems and simulation models) pertaining to any aspect of the aforementioned industries; electronic monitoring or control of any aspect of livestock/crop production (e.g. soil and water, environment, growth, health, waste products) and post-harvest operations (such as drying, storage, production assessment, trimming and dissection of plant and animal material). Relevant areas of technology include artificial intelligence, sensors, machine vision, robotics and simulation modelling.

  • Impact factor
    Show impact factor history
    Impact factor
  • 5-year impact
  • Cited half-life
  • Immediacy index
  • Eigenfactor
  • Article influence
  • Website
    Computers and Electronics in Agriculture website
  • Other titles
    Computers and electronics in agriculture (Online)
  • ISSN
  • OCLC
  • Material type
    Document, Periodical, Internet resource
  • Document type
    Internet Resource, Computer File, Journal / Magazine / Newspaper

Publisher details


  • Pre-print
    • Author can archive a pre-print version
  • Post-print
    • Author can archive a post-print version
  • Conditions
    • Voluntary deposit by author of pre-print allowed on Institutions open scholarly website and pre-print servers
    • Voluntary deposit by author of authors post-print allowed on institutions open scholarly website including Institutional Repository
    • Deposit due to Funding Body, Institutional and Governmental mandate only allowed where separate agreement between repository and publisher exists
    • Set statement to accompany deposit
    • Published source must be acknowledged
    • Must link to journal home page or articles' DOI
    • Publisher's version/PDF cannot be used
    • Articles in some journals can be made Open Access on payment of additional charge
    • NIH Authors articles will be submitted to PMC after 12 months
    • Authors who are required to deposit in subject repositories may also use Sponsorship Option
    • Pre-print can not be deposited for The Lancet
  • Classification
    ​ green

Publications in this journal

  • [Show abstract] [Hide abstract]
    ABSTRACT: Visual discrimination between barley varieties is difficult, and it requires training and experience. The development of automatic methods based on computer vision could have positive implications for the food processing industry. In the brewing industry, varietal uniformity is crucial for the production of high quality malt. The varietal purity of thousands of tons of grain has to be inspected upon purchase in the malt house. This paper evaluates the effectiveness of identification of barley varieties based on image-derived shape, color and texture attributes of individual kernels. Varieties can be determined by means of discriminant analysis, including reduction of feature space dimensionality, linear classifier ensembles and artificial neural networks, with high balanced accuracy ranging from 67% to 86%. The study demonstrated that classification results can be significantly improved by standardizing individual kernel images in terms of their anteroposterior and dorsoventral orientation and performing additional analyses of wrinkled regions.
    Computers and Electronics in Agriculture 01/2015; 110:1–8.
  • [Show abstract] [Hide abstract]
    ABSTRACT: The subject of this study was to investigate the possibility of using artificial neural networks as a tool for classification, designed to identify apple orchard pests. The paper presents a classification neural model using optimized learning sets acquired on the basis of the information encoded in the form of digital images of selected pests. This study predominantly deals with the problem of the identification of 6 selected apple pests which are most commonly found in Polish orchards. Neural modeling techniques, including digital image analysis, were used to classify the pests. The qualitative analysis of neural models produced, indicates that multi-layered perceptron (MLP) neural network topology achieve the best classification ability. Representative features, allowing for effective pest identification are 23 visual parameters in the form of 7 selected coefficients of shape and 16 color characteristic of pests. The dominant input variables of a neural model, determining the correct identification of the features, contain information about the color of pests. Our results support the hypothesis that artificial neural networks are an effective tool that supports the process of identification of pests in apple orchards. The resulting neural classifier has been created to assist in the decision-making processes that take place during the production of apples, in the context of protection against pests.
    Computers and Electronics in Agriculture 01/2015; 110:9–16.
  • G. Kharmanda, M-H. Ibrahim, A. Abo Al-kheer, F. Guerin, A. El-Hami
    Computers and Electronics in Agriculture 11/2014; 109:162-171.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Monitoring the feeding pattern of a pig enables early detection of diseases and other problems. To monitor the individual feeding pattern of group-housed pigs, it has been suggested to equip the pigs with High Frequency Radio Frequency Identification (HF RFID) tags and the feeding trough with an antenna. The detection range of the HF RFID system is crucial to guarantee that all feeding pigs are detected without detecting the pigs located further from the feeder. The current study examines the factors that influence whether an antenna attached to a round feeding trough (such as those used in group housing of growing–finishing pigs) detects stationary HF RFID tags placed in various orientations and distances from the antenna. Four experiments were performed using a custom-built test set-up that allowed determining the RFID registrations for 70 tag positions, at seven distances from the antenna and for seven orientations of the tags in relation to the antenna. In the first experiment there was determined that which tag side is closest to the antenna had very little influence on the range of registration. The results of the second experiment revealed that all eight HF RFID antennas in the pig house performed similarly, with symmetry observed in their range of registration. In the third experiment the range of the HF RFID system was measured while accounting for tag, tag position and tag orientation, whilst the last experiment was designed to test the effect of interference between tags. Reproducibility between (the order of) the tags and the average agreement between five repetitions of all tests was very high. In total, the sensitivity was 51.0%, with a standard deviation of 43.1 percentage point (pp). The specificity was 87.1% with a standard deviation of 19.4 pp. It was concluded that the performance of the HF RFID system in terms of sensitivity and specificity of the range depends greatly on the height and orientation of the tags. This causes irregular gaps to appear between subsequent RFID registrations of a feeding pig. To improve the performance of the system in practice, it is suggested to adjust the height of the antenna to better match the size of the pigs and to develop algorithms and criteria to merge raw RFID registrations into relevant feeding variables for individual pigs.
    Computers and Electronics in Agriculture 10/2014; 108:209-220.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Currently, the process of accrediting a certain crop to become a Protected Designation of Origin (PDO) valid one for the fabrication of Sidra de Asturias implies the visual inspection of the crop by technicians who ensure that there are only PDO valid varieties. It becomes then necessary a rapid, non-destructive, easy-to-use, cheap, trustable and efficient method to objectively classify the crop in order to detect possible frauds or human unintentional errors in the identification. Rapid methods for identification of different apple varieties based on Attenuated Total Reflectance (ATR)–Fourier Transform Infrared fingerprint spectroscopy assisted by Linear Discriminant Analysis (LDA) and by Artificial Neural Networks (ANN) have been developed. For each assayed variety, different sections of clean apple skins were selected and scanned from 600 cm�1 to 4000 cm�1. Apple data extracted from FTIR spectroscopy were gathered, analyzed and the final 372 reduced spectra were randomly distributed into training data sets (70%) and test data sets (30%). The classification results based on the LDA model gave a higher success rate (95.0%) than the ANN algorithm (85.5%) in the test data sets, although ANN presented a lower incorrect classification rate (1.9%) vs. LDA (5.0%). The ATR–FTIR technique coupled to chemometric approaches demonstrated to be useful, rapid, cheap and easy-to-use for identifying apple varieties. Success rate is better in LDA than in ANN, although ANN has a lower error rate because of its ability to detect ‘unclassifiable’ samples. These methods may be a helpful industrial approach to ensure the adequate selection of apple varieties to obtain a perfectly-balanced product under the PDO standards.
    Computers and Electronics in Agriculture 10/2014; 108:166-172.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Accurate estimation of reference evapotranspiration (ET0) values is of crucial importance in hydrology, agriculture and agro-meteorology issues. The present study reports a comprehensive comparison of empirical and semi empirical ET0 equations with the corresponding Heuristic Data Driven (HDD) models in a wide range of weather stations in Iran. Artificial Neural Networks (ANNs), Adaptive Neuro-Fuzzy Inference System (ANFIS), Support Vector Machine (SVM) and Gene Expression Programming (GEP) techniques are applied for modeling ET0 values considering different data management scenarios, and compared with corresponding Hargreaves–Samani (HS), Makkink (MK), Priestley–Taylor (PT), and Turc (T) ET0 models as well as their linear and non-linear calibrated versions along with the regression-based Copais algorithm. The obtained results confirm the superiority of GEP-based models. Further, the HDD models generally outperform the applied empirical models. Among the empirical models, the calibrated HS model found to give the most accurate results in all local and pooled scenarios, followed by the Copais and the calibrated PT models. In both local and pooled applications, the calibrated HS equation should be applied when no training data are available for the use of HDD models. The best results of the models correspond to the humid regions, while the arid regions provide the poorest estimates. This may be attributed to higher ET0 values associated with these stations and the high advective component of these locations.
    Computers and Electronics in Agriculture 09/2014; 108:230-241.
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, the discriminative capability of a combination of biological and shape features for fish age classification are analyzed. In particular, the usefulness of otolith weight in several species, in combination with other features such as otolith shape features and biological features such fish length, weight and sex is evaluated. The classification performance for different state-of-the-art statistical learning classifiers (i.e. several non-linear, non-parametric classifiers such different types of multi-class support vector machines) using an Atlantic cod database has been tested in which otolith weight has shown to be a powerful characteristic for classification purposes but the greatest accuracy is achieved when it is used simultaneously with other features.
    Computers and Electronics in Agriculture 09/2014; 107:1–7.
  • [Show abstract] [Hide abstract]
    ABSTRACT: The weight or mass of a pig is of great importance for farmers and stockmen to monitor performance, health and market weight of animals. The paper presents a prototype for pig weighing based on the Microsoft Kinect camera technology, utilizing the infrared depth map images and the simple statistical relationship between the depth map and weight. The system successfully estimated the weight of two different purebred breeds, landrace and duroc with an error estimate of 4 - 5 % of mean weight. The depth map images require less calibration, are less prone to background (i.e. floor) noise compared to visible light camera systems and seem to be more robust between breeds due to additional information from height (depth map) of animals.
    Computers and Electronics in Agriculture 08/2014; 109:32-35.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Segmentation is one of the main steps in image processing, as it influences the accuracy of other processes such as feature selection and classification. In this study, an effective method based on a combined image processing and machine learning was presented and evaluated for segmenting almond images with different classes such as normal almond, broken and split almond, shell of almond, wrinkled almond and doubles or twins almond. One of the major difficulties encountered in segmenting almonds was the existence of shadow on the background of the acquired images. Another difficulty was separating almonds with various shapes and colors from input images. To implement an effective algorithm, initially a suitable set of color features was extracted from the images. Then, sensitivity analysis was used to select the best features. Finally, artificial neural networks (ANNs) were adopted to classify the images into three categories, namely, object, shadow and background. The optimum ANN classifier had a 8-5-3 structure, i.e., it was consisted of an input layer with eight input variables, one hidden layer with five neurons and three neurons as output. To evaluate the performance of the proposed method, the results of our optimum ANN model were compared with Otsu, dynamic thresholding and watershed methods. The mean values of sensitivity, specificity and accuracy for object class (detected almonds from images) achieved by using the proposed method were 96.88, 99.21 and 98.82, respectively. It gave a better accuracy than the mentioned methods. In addition, the proposed method was able to separate the almonds from the background and shadows more efficiently. The processing time of the proposed method was 1.35 seconds which makes it possible for real time applications.
    Computers and Electronics in Agriculture 05/2014; 105(3):34-43.
  • Computers and Electronics in Agriculture 04/2014; 103:63–74.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Determining the best way to allocate limited water resources, for food and energy-dedicated crops, has become crucial due to the rise in extreme events (floods/droughts) and higher variability in rainfall attributed to global climate change. Changing climate conditions will require new crops to be adapted to a changing agricultural environment. Crop growth curves, based on evapotranspiration with associated uncertainty/confidence ranges, could reliably guide regional crop adaptation decisions. Given that crop growth is strongly coupled to soil moisture, developing reliable crop curves require a detailed understanding of soil moisture at the field-scale. It is especially difficult to sample soil moisture in order to obtain the best field-scale representation of the spatial distribution and the growing season dynamics. A novel way to address soil moisture monitoring challenges is through an integrated, agro-ecosystemslevel approach using an integrated sensing system that can link data from multiple platforms (wireless sensors, satellites, airborne imagery, near real-time climate stations). Assimilated data can, then, be input into predictive models to generate reference crop growth curves and predict regionally-specific yield potentials. However, integrated sensing requires interagency cooperation, common data processing standards and long-term, timely access to data. Large databases need to be reusable by various organizations and accessible, in the future, with comprehensive metadata. During the 2012 growing season a feasibility study was conducted which involved measuring field-scale soil moisture with wireless sensor based technology. The experiment utilized a radial-based sensor sampling design for tracking in-season soil moisture. OpenGIS-compliant services and standards were utilized to provide long-term access to sensor data and construct corresponding metadata. Sensor Model Language, an inter-operable metadata format, was used to create documentation for the sensor system and sensing components. Two different third party implementations of the Sensor Observation Service were tested for providing long-term access to the data. This work discusses a set of key recommendations for monitoring field-scale soil moisture dynamics and integration with remote sensing and models. 1) In-situ sensing technology advancements that would allow for less restrictive soil sampling designs. 2) Integration of field-scale in-situ networks with regional remote sensing monitoring. 3) The development of software and web services to integrate data from multiple sources with models for decision support.
    Computers and Electronics in Agriculture 03/2014;
  • [Show abstract] [Hide abstract]
    ABSTRACT: Closing a shellfish farm due to pollutants usually after high rainfall and hence high river flow is an important activity for health authorities and aquaculture industries. Towards this problem, a novel application of time series classification to predict shellfish farm closure for aquaculture decision support is investigated in this research. We exploit feature extraction methods to identify characteristics of both univariate and multivariate time series to predict closing or re-opening of shellfish farms. For univariate time series of rainfall, auto-correlation function and piecewise aggregate approximation feature extraction methods are used. In multivariate time series of rainfall and river flow, we consider features derived using cross-correlation and principal component analysis functions. Experimental studies show that time series without any feature extraction methods give poor accuracy of predicting closure. Feature extraction from rainfall time series using piecewise aggregate approximation and auto-correlation functions improve up to 30% accuracy of prediction over no feature extraction when a support vector machine based classifier is applied. Features extracted from rainfall and river flow using cross-correlation and principal component analysis functions also improve accuracy up to 25% over no feature extraction when a support vector machine technique is used. Overall, statistical features using auto-correlation and cross-correlation functions achieve promising results for univariate and multivariate time series respectively using a support vector machine classifier.
    Computers and Electronics in Agriculture 03/2014; 102:85–97.