Search

International audience; This study aims at evaluating the environment quality scientifically and providing the corresponding optimization methods for facilities upgrade of enclosed henhouse with four overlap tiers cages. The intelligent environmental monitoring device for laying hens breeding was developed based on Internet of things to measure environmental parameters, including temperature, relative humidity, light intensity and CO2 concentration, wind speed, dust concentration and other environmental parameters in winter, and to analyze their impact on the laying rate and egg quality. The results showed that the environmental parameters in henhouse different measuring points were different. The height of different hens cages have a certain effect with egg-laying rate and egg weight. It can be seen that the contradiction between ventilation and heat preservation should be coordinated in winter. On the premise of keeping suitable temperature, the ventilation should be increased to provide a good production environment for laying hens.

International audience; A new method for nondestructive measurement of moisture content of particulate agricultural products is developed using microwave mixing technique. A double horn system with a relative vertical distance of one-fourth wavelengths is designed to measure the reflected microwave signals. The particulate materials are interacted with microwave at a frequency of 10.5 GHz, and the reflected microwave signal is mixed with the launch signal. Corns with different moisture contents are chosen as samples. Calibration models for moisture content are proposed in accordance with the measurement of the differential attenuation of the microwave mixing signal. A moisture content from 6.8% to 30.1% is obtained with a coefficient of determination of 0.98 and a standard error of calibration value of 1.12%.

International audience; The spectral characteristics of agriculture water can reflect the water quality indirectly. How to observe the spectrum quickly and accurately is basis of evaluating aquaculture water quality by remote sensing technology. Many investigations indicate that the spectrum of several specific bands can reflect some water quality conditions. In this article, a real-time and automatic spectrum observation system is built based on high-precision optical sensor, flash storage technology, GPRS and RS485 wireless data transmission technology to observe the spectrum of specific bands. Through continuous observation of 5 ponds, the data is compared with data measured by ASD spectrometer in bands 680 nm, 700 nm and 769 nm. The data measured by ASD spectrometer is set as the standard value. The accuracy of the data measured by this system is above 98%. The result shows that, this system could take the place of spectrometer to measure the spectrum of specific bands. It can realize remote, real-time data observation.

International audience; Soil nutrients play an important role in crop growth, and traditional monitoring methods are still the first choice for high precision measurement. However, it is necessary to have a quicker and simpler way to improve the efficiency of soil nutrient monitoring because of its long monitoring time, pollution and high labor cost. Near infrared spectroscopy has become the focus of its research because of its rapid and pollution-free advantages. At present, using near infrared spectroscopy to distinguish soil types, soil heavy metal pollution technology has become increasingly mature, but the soil nutrients, such as monitoring of soil organic matter, available phosphorus, available potassium, available nitrogen is still in the research stage. This paper reviews the recent research results of soil nutrients in near infrared spectrum monitoring technology based on collation, summary and key technology of common data processing method, and analysis the advantages and disadvantages of different detection methods for soil nutrient direction of near infrared spectroscopy technology put forward suggestions to further research.

International audience; Many variable fertilization approaches based on ‘real-time’ crop N status were developed for making N fertilizer management in precision agriculture. Unfortunately, to date, only few papers reported the effect of variable fertilization algorithms on the spatial and temporal variability of crop parameters. Based on these problems, this study designed three different variable fertilization algorithms based on vegetation index (Y), SPAD (S) and crop growth model (Z), respectively, with uniform fertilization and no fertilization as controls. Results showed that wheat growth had strong spatial dependence, which become stronger after fertilization. Wheat yield also had strong spatial dependence. There were some similar spatial distribution between NDVIs, soil TN and yield, indicating that spatial variability of yield had strong relationship with crop growth status and soil TN content. The site-specific fertilization treatment based on crop growth model (Z) had the best adjustment capacity to promote crop growth and yield, and reduce their spatial variation, compared with other fertilization treatments.

International audience; It is still a challenge for fruit robot to automatic detecting young green apples in a complex grove environment due to color similarity with the background and varying illumination conditions. The purpose of this study was developing a robust method to detect young green apples in the tree canopy from low-cost color images acquired with diverse fruit sizes and under varying light circumstances. Adaptive green and blue chromatic aberration map was designed and combined with the iterative threshold segmentation algorithm to detect the region of interest contains potential apple fruits pixels. Then every potential fruit was identified by using an improved circular Hough transformation after morphological operation and blob analysis of the ITS outs which kept as many potential apple fruits pixels as possible. Finally, a kernel support vector machine classifier optimized by using grid search algorithm was built and combined with histogram of oriented gradients feature descriptor to distinguish and remove false fruit objects. The experimental result shows that the proposed method has better detection performance for young green apples.

International audience; Visible and near-infrared reflectance spectroscopy based soil properties estimation is an alternative to traditional laboratory analysis. The calibration model is a main factor influencing predictive performance. In this study, a large scale soil database, which contains 19,036 soil samples, was compared to its subsets to validate the effect of sample size on predictive performance. Four regression techniques based on linear model, namely, multiple linear regression (MLR), principal components regression (PCR), partial least squares regression (PLSR), and stepwise regression (SR) were compared to identify suitable models to predict the content of organic carbon in soil samples. The impact of derivatives or the raw spectra as predictor variables, and the interval of spectra were also studied. The best predictions were obtained using SR and MLR on raw spectra, yielding root mean square of error of cross validation (RMSECV) and coefficient of determination (R2) values of 25.3912, 25.4254 and 0.9227, 0.9225, indicating excellent models.

In view of the complexity of information dissemination in agriculture and the uncertainty of farmers’ demand for scientific and technological information, this paper makes a comprehensive and accurate analysis for the dissemination network of scientific and technological information of agriculture based on complex network technology. Firstly, this paper researches the characteristics of the peak degree distribution, average path length and clustering coefficient of a complex network established by the agricultural information dissemination network. Through the research on the three basic characteristics, this paper confirms that the agriculture information dissemination network has the characteristics of scale-free network and small-world network. The method of node research is analyzed by using a complex network. That is that this paper makes a comprehensive analysis for the information propagation speed, scope, analysis and application of dissemination network of agricultural scientific and technological information from degree centrality, betweenness centrality and relationship strength theory. The research results show that the degree centrality can accelerate the information dissemination and be conducive to the accuracy of the information; the betweenness centrality can quickly expand the information dissemination and accurately grasp the degree of control for information resources; the relationship strength theory can reduce the cost of information dissemination and improve the degree of information adoption. This conclusion proves that the application of the analysis method of complex network can effectively improve the speed and quality of agricultural information dissemination network and better serve the agricultural production and farmers’ life.

International audience; The Objective of the study is to Analyze and mining rice breeding data with data explore and machine learning algorithms to discover how rice biological characters influence the economic characters, explore effective methods and technologies for breeders and help them find appropriate breeding parents, and provide tools for parental selection in rice breeding. The author developed a B/S application with Python and Django, which implement real-time data mining of rice breeding data. Data analysis and processing result generated from decision tree algorithm can find effective breeding knowledge and patterns, and spectral biclustering algorithm can find required varieties with their local features follow certain patterns. The system can help breeders find useful knowledge and patterns more quickly, and improves the accuracy and efficiency of crop breeding.

The RGP transgenic plants show good resistance to drought especially reflected in corn yield. However, little is known about root traits which contribute to drought resistance. Here, we characterized root anatomy in the transgenic plants based on micro-CT scanning. Quantitative analysis of root anatomical traits showed that the drought-resistant RGP transgenic plants had larger root and stele cross-sectional areas in the fourth and the fifth whorls of nodal roots. The metaxylem vessel number and total area of metaxylem vessels was higher or larger in the fifth and the sixth whorls of nodal roots from RGP transgenic plants.

International audience; Biomass and the chlorophyll content are important indicators to measure the growth and development of grasslands. Modeling using hyperspectral data is an important means to monitor grassland growth and development. In this paper, we studied Mexican maize grass, hybrid Pennisetum and hybrid Sudan grass under different soil texture treatments and determined the correlation between the canopy reflectance spectrum and plant growth status in different soil textures based on hyperspectral data. Our results showed that, under different soil texture treatments, the emergence rate of Mexican maize grass and hybrid Pennisetum did not differ significantly, whereas that of hybrid Sudan grass indicated a significant difference. Under different soil texture treatments, the trend of plant height variation was consistent. In terms of different types of grassland, it is generally feasible to establish a grassland yield spectral model based on the vegetation indexes NDVI and RVI, and the leaf SPAD values of the three types of grassland best fit the spectral parameter red edge area.

International audience; As a new information carrier, the scientific data carries a lot of information. People who work in scientific research are more or less likely to search scientific data for work. We investigate the retrieval behavior of researchers in the process of searching data through questionnaires. The survey included the selection of searching data channels, using the clues and criterion in the process of retrieving data and some difficulties in the retrieval process. The results show that the retrieval behavior of scientific data users is influenced by educational background and retrieval ability. The education determines the breadth and depth of the data requirements, and the retrieval ability determines the access to data and the amount of data to use. So, in the process of designing data retrieval system, it is necessary to meet the needs of users in different cognitive contexts.

International audience; Several design parameters of flail chopper were studied under a wide range of field and crop conditions to improve chopper performance. However, the effects of parameters on the internal straw flow characteristics that influence straw chopping and spreading performance are still unknown. In this paper, Computational Fluid Dynamics (CFD) were used to analyze the influence of three operating parameters (rotor speed, forward speed and hood clearance) and two structural parameters (fan blade number and flail tip clearance) on the flow characteristic in the tractor powered flail chopper. The pressure contours, maximum negative pressure and flow rate at the machine inlet were considered in the analysis of feeding performance. Velocity at 21 sampling points, area weighted and maximum velocities at the outlet were also considered for straw spreading performance. Streamlines from three sampling sections were analyzed for straw flow-ability.

International audience; Nowadays application scopes of deep learning research in the machine learning subfield have been gradually expanded, mainly in the field of computer vision and natural language processing. However, in the latter NLP field, there is very little semantic excavation research on agricultural literature data. This paper bases on the attempting to combine relevant paradigms of semantic mining techniques and characteristics of agricultural digest data, for the service of providing new methods and technologies of information acquisition and analysis in the agricultural information domain. Data cleaning methods and data mining experiment are mainly based on deep learning algorithms, which are Seq2Seq and attention mechanism. Finally, through qualitative evaluation and quantitative evaluation of the experimental results, which based on the ROUGE evaluation index system, the experiment shows that the semantic mining model has reached the optimal level of model evaluation in the certain range.

International audience; Studying the spatial distribution characters of rubber yield and soil nutrients and the rule of spatial variability are important for suitable fertilization strategy in rubber plantation. This paper selected Hongquan Branch, Guangba Branch and Gongai Branch of Guangba Farm in Hainan province as study area and total of 327 samples were selected in the rubber plantation. The spatial distribution characters of rubber yield and five soil nutrients, including organic matter (OM), total nitrogen (TN), available phosphorus (AP), available potassium (AK), exchangeable calcium (Ga), were studied using traditional analysis method and geo-statistics analysis method. The results showed that: (1) The average value of rubber yield was 3.55 kg/hm2 with moderate spatial variability and the average values of OM, N, P, K and Ga were 11.65 g/kg, 0.07%, 16.23 mg/kg, 49.65 mg/kg and 84.44 mg/kg, respectively. Soil OM, TN, AK and Ga had moderate spatial variability but AP had strong spatial variability. (2) Rubber yield and soil total nitrogen (N) nutrient had strong spatial dependence; soil OM, AP, AK and Ga had moderate spatial dependence. (3) Based on the previous reports of normal range of soil nutrients, soil OM and TN nutrient content were very low in the studied rubber plantation of Guangba Farm. Therefore, more nitrogen fertilizer should be applied in the rubber plantation in future.

The pathology and virus isolation are the mainly diagnostic approaches for swine flu currently. Although the diagnosis rate is high, it is not conducive to detecting and intervening the infected pigs timely because of the serious time delay. Therefore, this paper proposed a novel framework method for the early detection and warned of swine influenza. The Jilin landrace are as the subjects of the experiment in this paper. Firstly, the body temperature changes were monitored compared between healthy and infected pigs respectively. And then the machine vision method was used to identify the basic pre-defined behavior of the landrace. Afterward, the behavior of the healthy and infected pigs were determined the abnormality or not. In the experiments, the results showed that the temperature of the infected pigs increased from 1–2 h to 40.3–41.5 ℃ and the lying status of the sick pigs was significantly increased compared to other activities such as feeding and drinking water. The experimental results showed that this method was effective for early detection of swine flu.

International audience; Automatic detection of mature apples in a complex agricultural condition is still a challenge for an autonomous picking robot due to the influence from overlapping. In order to detecting overlapped apples in tree canopy using a low-cost camera, a robust apples detection and reconstruction approach based on improved K-means and distance least square algorithm was studied. Firstly, the region of potential apple objects was extracted by using improved K-means algorithm. Then, the contours of apples were obtained by utilizing Canny edge detection algorithm on the V component map and the intact contour of unobscured apple was separated from overlapped apples contour after Y-junction searching. Finally, the contour of obscured apple was reconstructed by use of the distance least square circle fitting algorithm. The proposed method was compared with Hough transform method and the experimental result indicated that the proposed method could get much better performance for overlapped apples detection than Hough transform method. Thus it could be concluded that the proposed method is available for robotic apple picking in overlapped fruits scene with low cost.

International audience; With the rapid development of computer virtual technology and agricultural information technology, crop Three-Dimensional (3D) visualization plays an increasingly important part in predicting crop growth dynamic, planting management, and crop breeding. Due to the complexity of wheat morphological structure, as well as big difference on morphological characteristics at different stages, it is a big challenge to build the wheat growth 3D visualization. In this study, the field experiments were carried out from 2015 to 2016 at Tianjin in China, including 3 wheat cultivars under 3 nitrogen application levels. Based on the field experiment, the wheat morphological data, such as length, width, bending angle of leaf, stem and leaf angle, stem diameter, etc., were collected periodically. Then, the quantitative relationship between wheat morphological data and effective accumulated temperature was analyzed, and the growth simulation models of leaf length, maximum leaf width, leaf height and plant height were built by logistic equation. Based the mode test, the logistic model could predicate the wheat leaf growth precisely. Based on the wheat morphological characteristic parameters and topology structure, we established construction algorithm of wheat leaf main vein control point using parameterized modeling method based on curve and curved surface. With the aid of Non-Uniform Rational B-Splines (NURBS) technology and OpenGL graphics library, the wheat organs geometric models were constructed, such as leaf, leaf sheath, stem etc. As a result, Wheat growth simulation model, which was constructed by the effective accumulated temperature, could better predict wheat growth status. Combined with wheat morphological structure model, growth visualization of different varieties wheat under different nitrogen levels was realized, and 3D visualization of wheat growth process was finally realized. The 3D visualization mode can provide wheat crop growth dynamic prediction, cultivation management control and crop plant type design, provide strong technical support for wheat crop ideal plant type screening, high yield, high efficiency, lodging resistance, etc.

International audience; In order to alleviate the difficulties in collecting indexes for the analysis of farmland weed communities, we implemented a computer vision technology-based method for the identification of farmland weeds at the species level. By using the super-green and maximum interclass difference methods to obtain a green vegetation binary image, we were able to separate weeds from cultivated crops through multiple etching and the removal of small areas. A BP (back propagation) neural network was used for weed recognition, and the morphological characteristics of the weeds and each region were selected following etching to construct the input matrix of the recognition model for training and testing the BP network. After experimenting with the computational vision method for the identification of five weed species, we discovered that the recognition accuracy rate reached 96%. The results showed that the computer vision method could quickly and accurately extract a weed community analysis index, thereby providing a reference for the intelligent analysis of weed communities.

International audience; Yellow rust (YR) is one of the most destructive diseases of wheat. We introduced the Bayesian network analysis as a core method and develop a large-scale YR forecasting model based on several important meteorological variables that associate with disease occurrence. To guarantee an effective model calibration and validation, we used multiple years (2010–2012) of meteorological data and the ground survey data in Gansu Province where the YR intimidated most severely in China. The validation results showed that the disease forecasting model is able to produce a reasonable risk map to indicate the disease pressure across the region. In addition, the temporal dispersal of YR can also be delineated by the model. Through a comparison with some classic methods, the Bayesian network outperformed BP neutral network and FLDA in accuracy, which thereby suggested a great potential of Bayesian network in disease forecasting at a regional scale.

International audience; An ejection mechanism consisting four reset springs, an electromagnet and a seed disk was designed for tray seeder. The motion conditions of seeds in the seed disk were theoretical analyzed and intensity and height of seed ejection were calculated. The motions of the seeds and seed disk were multi-body dynamic simulated using Cosmos modules plug-in SolidWorks software package. The simulation results showed the consistence with the theoretical analysis.

International audience; With the urgent demand of agricultural information for farmers and quick development of telecommunications industry in china, the convenience, quickness and validity of agricultural information service are becoming more important. Now, the problem of the digital divide between rural and urban areas comes from the shortage of effective information transmission means. But the agricultural information services limited by network bandwidth and geography will be changed completely with the mobile phone network coverage to rural areas, especially TD-SCDMA network into rural areas in china. The paper will introduce the development of the 3G technologies-based effect on the agriculture informationization, and discuss the problems of agricultural information resource integration and service adapted to 3G technologies in detail, based on which a 3G technologies-based agricultural information resource application mobile service hierarchy (3GAIMSH) is provided.

International audience; An information collection system which was used to group characteristics of pleurotus eryngii was introduced. The group characteristics of pleurotus eryngii were quantified using machine vision in order to inspect and control the pleurotus eryngii house environment by an automated system. Its main contents include the following: collection of pleurotus eryngii image; image processing and pattern recognition. Finally, by analysing pleurotus eryngii image, the systems for group characteristics of pleurotus eryngii are proved to be greatly effective.

International audience; Crop simulation model has been becoming the core of agricultural production management and resource optimization management. Displaying crop growth process makes user observe the crop growth and development intuitionisticly. On the basis of understanding and grasping the occurrence condition, popularity season, key impact factors for main wheat diseases of stripe rust, leaf rust, stem rust, head blight and powdery mildew from research material and literature, we designed 3D visualization model for wheat growth and diseases occurrence. The model system will help farmer, technician and decision-maker to use crop growth simulation model better and provide decision-making support. Now 3D visualization model for wheat growth on the basis of simulation model has been developed, and the visualization model for primary wheat diseases is in the process of development.

International audience; This article analyzes the Internet basic theory, the network foundation environment and the user behavior change and so on, Which analyzes the development tendency of existing partial Internet products in the future Internet environment. The article also hot on the concept of cloud computing, Demonstrates the relation between Cloud Computing and Web 2.0 from the angle of Cloud-based end-user applications, The possibly killing application in the future was discussed.

International audience; Food safety is a widely concerned problem in current world. Traceability technology is an effective measure to solve the problem. This paper describes the study of the traceability of grain and oil products. Include the study contents, and a system we developed for traceability of grain and oil products, and the demonstration of the study. The system we developed was used in Luhua group and some supermarkets and get good feedbacks.

International audience; An overview of non-destructive detection in quality of post-harvest fruit was presented in this paper, and the research and application were discussed. This paper elaborated the fruit quality detection methods which were based on one of the following properties: optical properties, sonic vibration, machine vision technique, nuclear magnetic resonance (NMR), electronic noses, electrical properties, computed tomography. At last, the main problems of non-destructive detection in application were also explained.

International audience; A quantification model of transient heat conduction was provided to simulate apple fruit temperature distribution in the cooling process. The model was based on the energy variation of apple fruit of different points. It took into account, heat exchange of representative elemental volume, metabolism heat and external heat. The following conclusions could be obtained: first, the quantification model can satisfactorily describe the tendency of apple fruit temperature distribution in the cooling process. Then there was obvious difference between apple fruit temperature and environment temperature. Compared to the change of environment temperature, a long hysteresis phenomenon happened to the temperature of apple fruit body. That is to say, there was a significant temperature change of apple fruit body in a period of time after environment temperature dropping. And then the change of temerature of apple fruit body in the cooling process became slower and slower. This can explain the time delay phenomenon of biology. After that, the temperature differences of every layer increased from centre to surface of apple fruit gradually. That is to say, the minimum temperature differences closed to centre of apple fruit body and the maximum temperature differences closed to the surface of apple fruit body. Finally, the temperature of every part of apple fruit body will tend to consistent and be near to the environment temperature in the cooling process. It was related to the metabolism heat of plant body at any time.

International audience; This paper is the use of modern information technology, research the quality of bee product tracking and traceability system based on Agent. On the one hand, through establish the quality of bee product tracking and traceability system, to provide a technical support and general-purpose tools, it includes bee products from production to sales for the entire process digital, visual expression, design, control and management. On the other hand, as a key technology research and exploration, the use of Agent technology, proposed intelligence and cooperative control methods about the quality and safety of bee products, and for the control of the quality and safety of bee products to provide new methods and ideas.

International audience; Mechanical fruit grading and automatic fruit grading have been detailed in this paper. The studies and applications of mechanical fruit grading, and computer visual and automatic fruit grading were also particularized. Computer vision technology for detecting fruit size, color, bruise and surface defects and evaluation of fruit overall quality were discussed. The primary problems and development in the future in application of automatic fruit grading in China were pointed out in the end.

International audience; Most of the domestic designed hydraulic excavators adopt the constant power design method and set 85%~90% of engine power as the hydraulic system adoption power, it causes high energy loss due to mismatching of power between the engine and the pump. While the variation of the rotational speed of engine could sense the power shift of the load, it provides a new method to adjust the power matching between engine and pump through engine speed. Based on negative flux hydraulic system, an intelligent hydraulic excavator control system was designed based on rotational speed sensing method to improve energy efficiency. The control system was consisted of engine control module, pump power adjusted module, engine idle module and system fault diagnosis module. Special PLC with CAN bus was used to acquired the sensors and adjusts the pump absorption power according to load variation. Four energy saving control strategies with constant power method were employed to improve the fuel utilization. Three power modes (H, S and L mode) were designed to meet different working status; Auto idle function was employed to save energy through two work status detected pressure switches, 1300rpm was setting as the idle speed according to the engine consumption fuel curve. Transient overload function was designed for deep digging within short time without spending extra fuel. An increasing PID method was employed to realize power matching between engine and pump, the rotational speed's variation was taken as the PID algorithm's input; the current of proportional valve of variable displacement pump was the PID's output. The result indicated that the auto idle could decrease fuel consumption by 33.33% compared to work in maximum speed of H mode, the PID control method could take full use of maximum engine power at each power mode and keep the engine speed at stable range. Application of rotational speed sensing method provides a reliable method to improve the excavator's energy efficiency and realize power match between pump and engine.

International audience; Excessive water is used by farm field in Tarim river basin, it is very important to deep study on the relation between area of farm field and natural vegetation in recent 50 years. Collecting and processing various decades of remote sensing data, and got area of farm field, grass, forest, town and non-serviceable field. These results indict that: Because of the high flow period between 1950 and 1972, a part of grassland converts forest. From 1972 to 1990, because of increase of farm field, limited water isn't enough to grassland and forest, and a fraction of forest area converts grassland again. With rapid increase of area of farm field, more water need from the river and underground, which causes water level depression, and natural ecology becomes deteriorative from 1990 to 2000. Comprehensive analysis indicts that agriculture control implemented by government is necessary to recovery of ecology, or farm field also would be lost eventually with destruction of natural ecology.

International audience; In this paper, a system for analyzing the strategic adjustment of regional agricultural industries in China is briefly introduced, particularly on several system functions of database, region selection, statistics, comparative analysis and result presentation in terms of their technical realizations. The introduction is focused on the realized comparative advantageous agricultural analysis computation methods and assessment recommendations. From this paper, we can see an application of a knowledge based system for regional advantageous agriculture analysis. Technical process of system analysis and system design for developing such a knowledge-based system is presented.

International audience; The Broadcast and Television coverage has increased to more than 98% in china. Information services by radio have wide coverage, low cost, easy-to-grass-roots farmers to accept etc. characteristics. In order to play the better role of broadcast information service, as well as aim at the problem of lack of information resource in rural, we R & D the text-to-speech system. The system includes two parts, software and hardware device, both of them can translate text into audio file. The software subsystem was implemented basic on third-part middleware, and the hardware subsystem was realized with microelectronics technology. Results indicate that the hardware is better than software. The system has been applied in huailai city hebei province, which has conversed more than 8000 audio files as programming materials for the local radio station.