Xinting Yang

Near-infrared imaging to quantify the feeding behavior of fish in aquaculture

Delaunay Triangulation was applied to the extraction of behavioral characteristics.Support Vector Machine was used to classify the reflective frame.Serious reflection frames were removed and new data were fitted.The linear correlation coefficient between FIFFB and human expert can reach 0.945. In aquaculture, fish feeding behavior under culture conditions holds important information for the aquaculturist. In this study, near-infrared imaging was used to observe feeding processes of fish as a novel method for quantifying variations in fish feeding behavior. First, images of the fish feeding activity were collected using a near-infrared industrial camera installed at the top of the tank. A binary image of the fish was obtained following a series of steps such as image enhancement, background subtraction, and target extraction. Moreover, to eliminate the effects of splash and reflection on the result, a reflective frame classification and removal method based on the Support Vector Machine and Gray-Level Gradient Co-occurrence Matrix was proposed. Second, the centroid of the fish was calculated by the order moment, and then, the centroids were used as a vertex in Delaunay Triangulation. Finally, the flocking index of fish feeding behavior (FIFFB) was calculated to quantify the feeding behavior of a fish shoal according to the results of the Delaunay Triangulation, and the FIFFB values of the removed reflective frames were fitted by the Least Squares Polynomial Fitting method. The results show that variations in fish feeding behaviors can be accurately quantified and analyzed using the FIFFB values, for which the linear correlation coefficient versus expert manual scoring reached 0.945. This method provides an effective method to quantify fish behavior, which can be used to guide practice.

Farm and environment information bidirectional acquisition system with individual tree identification using smartphones for orchard precision management

A bidirectional acquisition system on smart phones.Farm information collection flow on tree identification with QR code.Sensors search rule on tree position and multi-point environment value model. An orchard precision management system plays an important role in improvement at the management level and the enhancement of decision abilities. A single orchard tree or an orchard tree microcommunity is the basic management unit, and bidirectional information on the environment and plants is the important content for precision management. A type of RFID label was applied with a UHF chip in the core and a QR code in the surface for single tree identification. A bidirectional acquisition system for orchard production, which included farming information collection for the forward direction and environmental information acquisition for the backward direction, was designed with smart phones. In the farming information collection part, information collection flow that included QR code image acquisition, image preprocessing, barcode decoding and farming information collection was established. An improved local threshold method was adopted to improve the QR code identification rate in the smart phone platform. In the environment information acquisition part, a sensor search rule on the single tree position and a multi-point environment value model were designed. The orchard information bidirectional acquisition system was developed on an Android platform with the Java language, which has the function of QR decoding, farm record information collection, environment information acquisition, data uploading and statistical analysis. The system was tested in an apple orchard. A total of 144 trees were chosen to decode the QR codes in the tree label. The success rate was approximately 96.52%. The identification time of 85% of the trees was less than 4s for the 20 chosen trees. In taking the temperature, for example, the difference between the computed temperature value and the measured temperature value around each tree was small. The system could decrease the cost of the professional equipment, such as portable RFID readers and writers, which was a low-cost and high-efficiency solution for orchard production information collection.

Apple Fruit Diameter and Length Estimation by Using the Thermal and Sunshine Hours Approach and Its Application to the Digital Orchard Management Information System

In apple cultivation, simulation models may be used to monitor fruit size during the growth and development process to predict production levels and to optimize fruit quality. Here, Fuji apples cultivated in spindle-type systems were used as the model crop. Apple size was measured during the growing period at an interval of about 20 days after full bloom, with three weather stations being used to collect orchard temperature and solar radiation data at different sites. Furthermore, a 2-year dataset (2011 and 2012) of apple fruit size measurements were integrated according to the weather station deployment sites, in addition to the top two most important environment factors, thermal and sunshine hours, into the model. The apple fruit diameter and length were simulated using physiological development time (PDT), an indicator that combines important environment factors, such as temperature and photoperiod, as the driving variable. Compared to the model of calendar-based development time (CDT), an indicator counting the days that elapse after full bloom, we confirmed that the PDT model improved the estimation accuracy to within 0.2 cm for fruit diameter and 0.1 cm for fruit length in independent years using a similar data collection method in 2013. The PDT model was implemented to realize a web-based management information system for a digital orchard, and the digital system had been applied in Shandong Province, China since 2013. This system may be used to compute the dynamic curve of apple fruit size based on data obtained from a nearby weather station. This system may provide an important decision support for farmers using the website and short message service to optimize crop production and, hence, economic benefit.

Near infrared computer vision and neuro-fuzzy model-based feeding decision system for fish in aquaculture

Near infrared vision was used to quantify feeding behavior of fish.Fish feeding decision was realized using the neuro-fuzzy model.The method performance was evaluated by accuracy, fish growth and water quality.The proposed method can save feed costs and reduce water pollution. In aquaculture, the feeding efficiency of fish is of great significance for improving production and reducing costs. In recent years, automatic adjustments of the feeding amount based on the needs of the fish have become a developing trend. The purpose of this study was to achieve automatic feeding decision making based on the appetite of fish. In this study, a feeding control method based on near infrared computer vision and neuro-fuzzy model was proposed. The specific objectives of this study were as follows: (1) to develop an algorithm to extract an index that can describe and quantify the feeding behavior of fish in near infrared images, (2) to design an algorithm to realize feeding decision (continue or stop) during the feeding process, and (3) to evaluate the performance of the method. The specific implementation process of this study was as follows: (1) the quantitative index of feeding behavior (flocking level and snatching strength) was extracted by Delaunay Triangulation and image texture; (2) the adaptive network-based fuzzy inference system (ANFIS) was established based on fuzzy control rules and used to achieve automatically on-demand feeding; and (3) the performance of the method was evaluated by the specific growth rate, weight gain rate, feed conversion rate and water quality parameters. The results indicated that the feeding decision accuracy of the ANFIS model was 98%. In addition, compared with the feeding table, although this method did not present significant differences in promoting fish growth, the feed conversion rate (FCR) can be reduced by 10.77% and water pollution can also be reduced. This system provides an important contribution to realizing the real-time control of fish feeding processes and feeding decision on demand, and it lays a theoretical foundation for developing fine feeding equipment and guiding practice.

An adaptive image enhancement method for a recirculating aquaculture system

Due to the low and uneven illumination that is typical of a recirculating aquaculture system (RAS), visible and near infrared (NIR) images collected from RASs always have low brightness and contrast. To resolve this issue, this paper proposes an image enhancement method based on the Multi-Scale Retinex (MSR) algorithm and a greyscale nonlinear transformation. First, the images are processed using the MSR algorithm to eliminate the influence of low and uneven illumination. Then, the normalized incomplete Beta function is used to perform a greyscale nonlinear transformation. The function’s optimal parameters (α and β) are automatically selected by the particle swarm optimization (PSO) algorithm based on an image contrast measurement function. This adaptive image enhancement method is compared with other classic enhancement methods. The results show that the proposed method greatly improves the image contrast and highlights dark areas, which is helpful during further analysis of these images.

A deterministic sensor node deployment method with target coverage and node connectivity

The paper proposes a deterministic node deployment method based on grid scan to achieve targets coverage and nodes connectivity. Target area is divided into girds from which the most suitable one is selected to place the next node. In the coverage phase, the grid where the sensor node can sense the most targets and have the best coverage level is selected to place the next sensor node. To make the sensor nodes connected, first, the sensor nodes are divided into connected groups, then, the grid where the relay node can connect the most groups and have the best connectivity level is selected to place the next relay node. Simulation experimental results show that the method can achieve target coverage with the least sensor nodes and sensor node connectivity to a great extent.

Towards Developing an Early Warning System for Cucumber Diseases for Greenhouse in China

The integrated management of cucumber (Cucumis sativus L.) diseases play a key role in guaranteeing the high quality and security of cucumber production in greenhouse, moreover, the early warning of cucumber diseases is the chief precondition for IPM (Integrated Pest Management). This paper describes an attempt to develop an early warning system for cucumber diseases in greenhouse. By analysing plant disease epidemiology and early warning theory, the conceptual model of early warning on cucumber disease of greenhouse is developed. The data collection, data transfer system, database system, forecast system, warning system, and so on are integrated and an early warning system for cucumber diseases in greenhouse has been designed.

Towards Developing a Web-based Gap Management Information System for Cucumber in China

The integrated management of Good Agricultural Practices (GAP) for cucumber (Cucumis sativus L.) plays a key role in guaranteeing the high quality and safety of cucumber production. This paper describes an attempt to develop a web-based GAP management information system for cucumber. Through applying the system methodology and mathematical modeling technique to analyzing the dynamic relationships between control point of GAP and produce process of cucumber, self-assessments algorithm was established. Based on the algorithm, Web-based GAP management information system for cucumber (Cucumber-GAPS) with the functions of data manage, criterion query, GAP self-check, model manage and so on was designed with the web structure of Browse/Server, and it has been applied successfully in China.

Developing a machine vision system for simultaneous prediction of freshness indicators based on tilapia (Oreochromis niloticus) pupil and gill color during storage at 4 °C

The study assessed the feasibility of developing a machine vision system based on pupil and gill color changes in tilapia for simultaneous prediction of total volatile basic nitrogen (TVB-N), thiobarbituric acid (TBA) and total viable counts (TVC) during storage at 4°C. The pupils and gills were chosen and color space conversion among RGB, HSI and L∗a∗b∗ color spaces was performed automatically by an image processing algorithm. Multiple regression models were established by correlating pupil and gill color parameters with TVB-N, TVC and TBA (R2=0.989-0.999). However, assessment of freshness based on gill color is destructive and time-consuming because gill cover must be removed before images are captured. Finally, visualization maps of spoilage based on pupil color were achieved using image algorithms. The results show that assessment of tilapia pupil color parameters using machine vision can be used as a low-cost, on-line method for predicting freshness during 4°C storage.

Nondestructive determination of freshness indicators for tilapia fillets stored at various temperatures by hyperspectral imaging coupled with RBF neural networks

This study develops a reliable radial basis function neural networks (RBFNNs) to estimate freshness for tilapia fillets stored under non-isothermal conditions by using optimal wavelengths from hyperspectral imaging (HSI). The results show that, for tilapia fillet stored at -3, 0, 4, 10, and 15 °C and non-isothermal conditions, total volatile basic nitrogen (TVB-N), total aerobic counts (TAC), and the K value increase whereas sensory scores decrease with increasing storage time. To simplify the models, nine optimal wavelengths were selected by using the successive projections algorithm (SPA), following which SPA-RBFNN models were built based on the selected wavelengths and the values of TVB-N, TAC, K, and sensory evaluations for tilapia fillets store isothermally. The ability of the models based on HSI to predict the freshness indicators were verified for tilapia fillets stored under non-isothermal conditions. HSI thus has an excellent potential for nondestructive determination of freshness in tilapia fillets.