Search

Swift, non-destructive detection approaches should address the problem of insufficient sensitivity when attempting to obtain and perceive live crab information in low-light environments caused by the crab’s phototaxis. We propose a learning-based low-illumination image enhancer (LigED) for effective enhanced lighting and elimination of darkness in images. The camera response function was combined with the reflectance ground-truth mechanism of image decomposition. Self-attention units were then introduced in the reflectance restoration network to adjust the illumination to avoid visual defects, thus jointly strengthening the adaptability of dark-light enhancement and ability to perceive crab information. Convolutional neural network (CNN)-based detection methods can further enhance the algorithm’s robustness to light and adaptability to different environments, which motivated the development of a scalable lightweight live crab detector (EfficientNet-Det0) utilizing the two-stage compound scaling CNN approach. The lightness order error and natural image quality evaluator based on the proposed methods were 251.26 and 11.60, respectively. The quality of average precision detection increased by 13.84–95.40%. The fastest detection speed of a single image was 91.74/28.41 f·s−1 using a common GPU/CPU, requiring only 15.1 MB of storage, which advocates for the utilization of LigED and EfficientNet-Det0 for the efficient detection of underwater live crabs.

Objective To explore the survival value of lymph node dissection (LND) in elderly patients with T3-T4 laryngeal cancer, analyze the risk factors of lymph node metastasis, and construct a preoperative prediction model. Materials and Methods The study included 996 patients aged ≥65 years with laryngectomy confirmed T3-T4 laryngeal cancer queried from Surveillance, Epidemiology and End Results (SEER) database between 2010 and 2017. Propensity score matching (PSM) was applied to balance the effects of confounding factors. Kaplan–Meier (K–M) analysis and competitive risk model were used to compare the overall survival (OS) and cancer-specific survival (CSS) between LND and no-LND (N-LND) group. Combined with risk factors of multivariate logistic regression, a nomogram was built to predict lymph node metastasis preoperatively. The performance was assessed in the training set and the validation set, and internal validation was assessed. Results Among the cohort, 822 patients underwent LND and 410 patients had positive lymph nodes. The OS and CSS of patients who underwent LND were not better than that of N-LND patients (P>0.05). The prognosis of patients with lymph node metastases was significantly worse than that of negative patients (P 5cm and grade 3–4 classification were associated with significantly greater odds of lymph node metastasis. The nomogram showed favorable predictive efficacy and good calibration (in the training cohort C-index=0.700; in the validation cohort C-index=0.721). Conclusion For elderly patients with T3-T4 laryngeal cancer, LND did not bring significant survival values. Supraglottis cancer, tumor size >5cm and grade 3–4 classification were independent risk factors of lymph node metastasis, which means poor prognosis. The nomogram developed was an easy-to-use tool for lymph node prediction.

This study focuses on establishing apple viscoelastic finite element complex model to estimate apple stress variation during grasping with its own characteristics of constant velocity and continuous energy input. The deformation resistance of apple is calculated by MATLAB based on apple viscoelastic Burgers model and stage dynamic characteristics of grasping process, and used for defining the load function in ANSYS. Then, the layered solid model consisted by skin, flesh, core of apple is established in ANSYS and simulation carries out. Solution results of designed model show that maximum equivalent stress and maximum deformation of apple are 0.42 MPa and 0.72 mm respectively at grasping velocity of 3 mm/s, after that apple skin starts to have grasping damage prior to the flesh and core of apple due to plastic deformation occurring. Lastly, the actual experiment to verify the reliability of designed model was carried out. This study proposes an effective complex model to estimate apple stress from the perspective of grasping velocity by general finite element software.

In the green pepper harvesting robot, the color of green pepper is similar to that of leaves, which makes it difficult to recognize the green pepper target. In order to solve this problem, a green pepper recognition method based on least-squares support vector machine optimized by the improved particle swarm optimization (IPSO-LSSVM) is proposed in this paper. Firstly, the green pepper images are segmented by K-Means method under the Lab color space, and the segmentation images of the target and background are obtained. The processed green pepper image was divided into training and testing samples. Then, the shape and texture features of green pepper targets are extracted separately from the training sample using the hu invariant moment and Tamura texture feature. Meanwhile, in order to reduce the complexity of data calculations and improve the efficiency, the extracted feature vectors are normalized. The feature vector is used as the input eigenvector of the least-squares support vector machine (LSSVM). The particle swarm optimization algorithm is used to obtain the optimal regularization parameter and the kernel function width. In order to maintain the particle activity, the mutation strategy is introduced to improve the particle swarm optimization algorithm. The experimental results show that the recognition rate of IPSO-LSSVM is higher than that of other methods, and the recognition accuracy is 89.04%. It could meet the requirements of green pepper identification.

The cucumber fruits have the same color with leaves and their shapes are all long and narrow, which is different from other common fruits, such as apples, tomatoes, and strawberries, etc. Therefore, cucumber fruits are more difficult to be detected by machine vision in greenhouses for special color and shape. A pixel-wise instance segmentation method, mask region-based convolutional neural network (Mask RCNN) of an improved version, is proposed to detect cucumber fruits. Resnet-101 is selected as the backbone of Mask RCNN with feature pyramid network (FPN). To improve the detection precision, region proposal network (RPN) in original Mask RCNN is improved. Logical green ( LG ) operator is designed to filter non-green background and limit the range of anchor boxes. Besides, the scales and aspect ratios of anchor boxes are also adjusted to fit the size and shape of fruits. Improved Mask RCNN has a better performance on test images. The test results are compared with that of original Mask RCNN, Faster RCNN, you only look once (YOLO) V2 and YOLO V3. The $F_{1}$ score of improved Mask RCNN in test results reaches 89.47%, which is higher than the other methods. The average elapsed time of improved Mask RCNN is 0.3461 s, which is only lower than the original Mask RCNN. Meanwhile, the mean value and standard deviation of location deviation in improved Mask RCNN are 2.10 pixels and 1.73 pixels respectively, which are lower than the other methods.

The skins of most mature apple fruits are incompletely red and also include green and pale yellow color, which increases the difficulty of fruit detection by machine vision. A detection method based on color and shape features is proposed for this kind of apple fruits. Simple linear iterative clustering (SLIC) is adapted to segment images taken in orchards into super-pixel blocks. The color feature extracted from blocks is used to determine candidate regions, which can filter a large proportion of non-fruit blocks and improve detection precision. Next, the histogram of oriented gradient (HOG) is adopted to describe the shape of fruits, which is applied to detect fruits in candidate regions and locate the position of fruits further. The proposed method was tested by images taken under different illuminations. The average values of recall, precision, and F1 reach 89.80%, 95.12%, and 92.38% respectively. The performance of detecting fruits covered at different levels is also tested. The values of the recall are all more than 85%, which indicates that proposed method can detect a great part of covered fruits. Compared with pedestrian detection method and faster region-based convolutional neural network (RCNN), the proposed method has the best performance and higher than faster RCNN slightly. However, the proposed method is not robust to noise and its elapsed time of one image is 1.94 s and less than faster RCNN.

In order to improve the harvesting efficiency of apple harvesting robot, this article presents an apple recognition method based on pulse coupled neural network and genetic Elman neural network (GA-Elman). Firstly, we use pulse coupled neural network to segment the captured 150 images, respectively, and extract six color features of R, G, B, H, S, and I and 10 shape features of circular variance, density, the ratio of perimeter square to area, and Hu invariant moments of segmented images, and these 16 features are considered as the inputs of Elman neural network. In order to overcome some defects of Elman neural network, such as, trapping local minimum easily and determining the number of hidden neurons difficultly; in this article, genetic algorithm is introduced to optimize it, and new optimization way is designed, that is, the connection weights and number of hidden neurons separate encoding and evolving simultaneously, in the process of structural evolution at the same time the learning of connection weights is completed, and then the operating efficiency and recognition precision of Elman model are improved. In order to get more precision neural network, and avoid the influence of fruit recognition caused by branches or leaves shadow, apple along with branches and leaves is allowed to train. The results of experiments show that compared with the traditional back-propagation, Elman neural network, and other two recognition algorithms of obscured fruit. the genetic Elman neural network algorithm is the optimal method which successful training rate can reach to 100%, recognition rate of overlapping fruit and obscured fruit can reach to 88.67% and 93.64%, respectively, and the total recognition rate reaches to 94.88%.

Cabled intelligent systems bring with them the complexities of structures, the complications of data measurements and transmission, and a limited scale of application. A wireless sensor network is used to eliminate these disadvantages, however reliability of data transmission and energy saving in a wireless sensor network are two challenges that still need to be addressed. The design information on three types of nodes in a wireless sensor network is described in detail. Tree topology for WSN is adopted to decrease the packet loss rate and improve reliability of data transmission. Allowing sensor nodes to sleep and reorganising the data frames are the two approaches used to achieve energy-saving. The experimental results demonstrate the usefulness of these approaches in solving the challenges.

In order to address the issues of nonuniform feeding and high labor cost plaguing the process of farming Chinese river crabs, the present study proposes a multifunctional automatic river crabs feeding boat based on Advanced RISC Machine (ARM) and Global Positioning System / Inertial Navigation System (GPS/INS) integrated navigation. This paper proposes a new calculation method based on real time point insertion. This method calculates the current target position of the boat in the real time according to the position of the boat and the turning points of the current route. A new turning and route-switching strategy is also presented in this paper to improve the ship's operational efficiency and prevent the ship from veering off the target route due to its high speed. Considering the boat's unique movement characteristics including non-linearity, large delay and underdamped nature, a route-speed dual-loop control algorithm is designed based on fuzzy Proportion Integration Differentiation (PID) method. Through analyzing the bait distribution associated with the feeding machine, the present study proposes an inner-spiral-based full coverage traversal method and a travel distance optimization model so as to improve the uniformity of the automatic feeding. Results show that the speed overshoot is no more than 5% and the steady-state error can be kept within 3%. Compared with the finite point method, the real time point insertion method decreases the peak route deviation errors by 82.82% and 84.14% while turning and going straight.

Virtual synchronous generator (VSG) possesses the advantage of friendly interaction with power grid by simulating synchronous generator characteristics. However, its low-voltage ride through (LVRT) capability is insufficient. The excessive output current of VSG easily causes wind turbines to break away from the power grid, which will exacerbate the negative impact of grid fault. Thus, a new LVRT control strategy is proposed based on the analysis of excitation state for VSG. The droop characteristic, reactive power loop and active power loop of the VSG are improved, respectively, by specifically analysing the response characteristics of VSG. Moreover, the additional current loop is redesigned to assist the system operating in the under excitation state and suppress unbalanced currents without changing the original VSG characteristics. Furthermore, a new orientation method is adopted to accelerate the transient process and achieve better transient performance. It is worth noting that the proposed control strategy does not need switch control algorithm with smooth handoff algorithm under grid fault, and it can deal with both symmetric and asymmetric grid voltage drop problems at the same time. The correctness and feasibility of proposed scheme are verified by rigorous theoretical deduction and complete simulation verification.

The recognition of apple fruits in plastic bags is easy to be affected by reflected and refracted light. In order to weaken the influence of light, a method based on block classification is proposed. The method adopts watershed algorithm to segment original images into irregular blocks based on edge detection results of R–G grayscale images firstly. Compared with the watershed algorithm based on gradient images, the segmentation method can preserve fruits edge and reduce the number of blocks by 20.31%, because graying image method, R–G, filters most of leaves and edge detection operator insures that the edge of fruits are detected accurately. Next, these blocks are classified into fruit blocks and non-fruit blocks by support vector machine on the basis of the color and texture features extracted from blocks. Compared with the image recognition method based on pixel classification, the proposed method can restrain the interference of light caused by plastic bags effectively. The false negative rate (FNR) and false positive rate (FPR) of the method based on pixel classification are 21.71 and 14.53% respectively. The FNR and FPR of the proposed method are 4.65 and 3.50% respectively.

This paper proposes a robust model predictive control (RMPC) approach for the automatic operation boats to cast baits evenly along desired paths. The difficulties in the control design come from the control system model, which is nonlinear, underactuated, input saturated, and disturbed by time-varying signals. The RMPC overcomes these difficulties by the receding horizon optimization explicitly considering the input saturation and using the mixed H 2 / H ∞ cost function. To decrease computational complexity of the RMPC, a polyhedral model is constructed as the predictive model based on dynamics of the path-following error. The feasibility and effectiveness of the proposed path-following control is verified by theoretical analysis and illustrated by simulations and experiments.

Aiming at identifying for tree branches obstacle in navigation automatically and picking process of agricultural harvesting robots, an iterative threshold segmentation of apple branch images based on contrast limited adaptive histogram equalization (CLAHE) is proposed. Firstly, the RGB color space of the branch images are converted to the XYZ and I1I2I3 color space by transformation formula, and the X-Y and I2 color factor of the apple branch images are extracted to analyze their gray-level difference. Then, The CLAHE is applied to the images whose gray-level difference is not intensity before iterative threshold. Finally, the apple branches are segmented from the original images by the iterative threshold. To verify the validity of the proposed method, 100 testing images in size of 1280 × 960 pixels under different illumination are utilized to compare the proposed method with other famous approaches, such as OTSU and histogram algorithm. Experimental results show that 94% of the apple branch images are correctly recognized and the segmentation quality of the proposed method is better than other approaches, which implies that the proposed method is effective for the tree branch segmentation.

Effective biomass detection methods utilizing computer vision techniques should be capable of handling large differences in object posture and various degrees of mutual overlap/occlusion in object scenes. We propose an automatic coarse-to-fine joint detection and instance segmentation network (JDSNet) that can perform real-time detection and instance segmentation on underwater non-structural live crabs in real-time. The method was adapted to non-structural objects and mobile devices by applying the anchor-free mechanism and center-ness strategy of the fully convolutional one-stage prediction head and the improved energy-efficient backbone IVoVNet-19-DW with identity mapping and channel attention. This approach avoided the complicated computations related to the anchor-based mechanism and effectively generated the features of various receiving domains, jointly improving the memory access speed and accuracy of predicting the bounding boxes of different instances. A novel spatial attention-guided mask branch was then added to focus on irregular occluded object pixels and conduct precise pixel-level mask segmentation within the predicted coarse instance-aware rectangular-bounding boxes. The experimental analysis using the proposed method resulted in a quality of detection F1 and segmentation Dic of 97.7% and 94.6%, respectively. The fastest detection speed of a single image was 48.07/13.32 fps (~10 times faster than the existing network Mask RCNN) on a commonly configured GPU/CPU, requiring only 7.04 MB of storage (~25 times smaller than Mask RCNN). It indicates that JDSNet can segment various non-structural live crabs and perform biomass statistics robustly and efficiently, exhibiting significance for precision feeding applications in automatic feeding boats.

Display OmittedThis paper's Graphical abstractWhen using the RBF neural network to deal with small samples with high feature dimension and few numbers, too many inputs are difficult to determine the numbers of hidden layer neurons, it influences the design structure of the network, the redundancies or correlative data will influence the training of the network, and relatively few number of samples make network train non-completed or over-fitted, thereby affecting the operating efficiency and recognition accuracy of neural network.For the problem of small sample classification, two aspects of RBF neural network are optimized. Firstly, the original data reduces their feature dimension by PLS algorithm, then the low dimensional data is used as network input, it regard as external optimization. And then, using genetic algorithm to optimize RBF, the optimization way adopts hybrid coding and simultaneous evolving for hidden layer neurons and connection weights, this step regard as internal optimization. By these two consecutive optimizations, an optimized RBF neural network algorithm based on PLS and GA (PLS-GA-RBF algorithm) for small sample is established, which facilitates the hidden layer of network design, and improves the network training speed and generalization ability, thereby improving the operating efficiency and recognition accuracy of the network.The new algorithm is ingenious combination of the advantages of three algorithms, it realize the external optimization by PLS and internal optimization by GA. PLS-GA-RBF algorithm can fit more complex nonlinear recognition problems, and is more suitable for the small sample classification, which with high feature dimension and fewer numbers.In order to verify the reliability of the PLS-GA-RBF algorithm, multiple instances is used to validate and analysis. In this paper, four different experiments are arranged; among them are three small sample test and one large sample test. The purpose of the arrangement large sample test is to compare of validation. The result is satisfactory, which means the new algorithm has unique superiority in dealing with the small sample. The nature of small sample is well-analyzed.PLS is employed to reduce feature dimension of small sample, which obtained the relatively ideal low-dimensional data as the inputs of neural network.Unlike previous studies, the optimized GA-RBF algorithm is adopts the way of hybrid coding and simultaneous evolving for hidden layer neurons and connection weights.By two consecutive optimization, combining the advantages of three algorithms of PLS, GA, and RBF, a reliable small sample classification algorithm (PLS-GA-RBF) is established.Four different groups of experiments are arranged to valuate the classification ability of PLS-GA-RBF algorithm. Radial basis function (RBF) neural network can use linear learning algorithm to complete the work formerly handled by nonlinear learning algorithm, and maintain the high precision of the nonlinear algorithm. However, the results of RBF would be slightly unsatisfactory when dealing with small sample which has higher feature dimension and fewer numbers. Higher feature dimension will influence the design of neural network, and fewer numbers of samples will cause network training incomplete or over-fitted, both of which restrict the recognition precision of the neural network. RBF neural network has some drawbacks, for example, it is hard to determine the numbers, center and width of the hidden layer's neurons, which constrain the success of training. To solve the above problems, partial least squares (PLS) and genetic algorithm(GA)are introduced into RBF neural network, and better recognition precision will be obtained, because PLS is good at dealing with the small sample data, it can reduce feature dimension and make low-dimensional data more interpretative. In addition, GA can optimize the network architecture, the weights between hidden layer and output layer of the RBF neural network can ease non-complete network training, the way of hybrid coding and simultaneous evolving is adopted, and then an accurate algorithm is established. By these two consecutive optimizations, the RBF neural network classification algorithm based on PLS and GA (PLS-GA-RBF) is proposed, in order to solve some recognition problems caused by small sample. Four experiments and comparisons with other four algorithms are carried out to verify the superiority of the proposed algorithm, and the results indicate a good picture of the PLS-GA-RBF algorithm, the operating efficiency and recognition accuracy are improved substantially. The new small sample classification algorithm is worthy of further promotion.

Crab farming mainly adopts the pattern of aquatic feeding, which is a hard work for farmers. To reduce the labor intensity and production costs for farmers, it is great significance to develop an automatic aquatic-cleaning boat with visual navigation. In visual navigation system, image segmentation is a difficult problem. In this paper, we combine the advantages of pulse coupled neural network in image segmentation with the global optimization characteristic of harmony search algorithm, an image segmentation algorithm of optimized pulse coupled neural network based on harmony search (HS-PCNN) is proposed. In order to improve the operating efficiency and segmentation accuracy of PCNN, this new algorithm can optimize the weighted combination of PCNN maximum Shannon entropy and minimum cross entropy by harmony search (HS), and evaluate the optimization effect of parameters by using yield function. Experimental results show that the proposed method can provide a more effective method for the aquatic image segmentation in crab pond.

This paper presents a grid-connected dual stator-winding induction generator (DWIG) wind power system suitable for wide wind speed ranges. The parallel connection via a unidirectional diode between dc buses of both stator-winding sides is employed in this DWIG system, which can output a high dc voltage over wide wind speed ranges. Grid-connected inverters (GCIs) do not require booster converters; hence, the efficiency of wind energy utilization increases, and the hardware topology and control strategy of GCIs are simplified. In view of the particularities of the parallel topology and the adopted generator control strategy, we propose a novel excitation–capacitor optimization solution to reduce the volume and weight of the static excitation controller. When this excitation–capacitor optimization is carried out, the maximum power tracking problem is also considered. All the problems are resolved with the combined control of the DWIG and GCI. Experimental results on the platform of a 37 kW/600 V prototype show that the proposed DWIG wind power system can output a constant dc voltage over wide rotor speed ranges for grid-connected operations and that the proposed excitation optimization scheme is effective.

BPNN is used to classify pixels based on their color and position.The main body and edge of fruits are recognized respectively.The position information is represented as the relativity of adjacent pixels.The method can reduce the influence of Shadows and faculae effectively. This paper proposes a method to segment apples on trees at night for apple-harvesting robots based on color and position of pixels. Images of apples acquired under artificial light with low illumination at night include less color information than daytime images, so it is necessary to take position of pixels into consideration. The new method has two main steps. Firstly, color components of sampled pixels in RGB and HSI color space are used to train a neural network model to segment the apples. However, the segmentation results are incomplete and not able to guide apple-harvesting robots accurately, because partial edge regions of apples are dark in shadows and difficult to be recognized due to uneven illumination. Secondly, the color and position of pixels around segmented regions and pixels on the boundary of segmented regions are taken into consideration to segment the edge regions of apples. The union of two segmentation results is the final result. The complete recognition can increase the accuracy of location by about 6.5%, which verified the validity and feasibility of the method.

In order to solve the problem of the recognition of green pepper harvesting robot in the near color background, a target recognition method based on manifold ranking is proposed in this paper. After pepper image enhancement by the local contrast enhancement algorithm, super-pixels extracted via energy-driven sampling (SEEDS) is used to construct super-pixel blocks of the enhanced image, the upper, lower, left and right boundary query nodes are used to query the boundary of the super pixel block image respectively. Then the manifold ranking is used to sort the image boundaries to obtain four saliency maps, and the final saliency map is obtained by fusion. Finally, the noise is removed by morphological operations and the contour of green pepper target is obtained to realize the recognition of green pepper in complex environment. Compared with classification and regression tree (CART), conditional random fields (CRF) and threshold, the proposed method can effectively identify the green pepper target, with the recognition accuracy of 83.6% and recall rate of 81.2%. The performance index is obviously better than the other three methods, which can meet the requirements of the actual operation of the harvesting robot.

The bait feeding of river crab farming needs to be covered evenly on the whole pond. At present, feeding is mainly carried out by manual driving or remote control ship-borne feeding machine on the pond. The feeding accuracy and efficiency are relatively low, and it is difficult to guarantee feeding effect. In view of the above situation, based on the mobile automatic feeding boat equipped with GPS, this paper proposes a complete coverage trajectory planning method with irregular quadrilateral pond, and a trajectory planning system based on SuperMap Objects is designed to generate reciprocating traverse feeding trajectory automatically. The simulation is performed to verify the feasibility of the trajectory planning method. The results show that the trajectory planning system can meet the requirements of automatic and uniform feeding on the crab pond.

It has been more than 30 years since the French pioneered the research of the apple harvesting robot, and with the joint efforts of scholars all around the world, a variety of prototypes have been developed. However, the existing apple harvesting robot prototype is still in the experimental research stage because of its low harvesting efficiency. With the help of information technology, the related research has ushered in a milestone development, and it is full of opportunities and challenges for apple harvesting robotic researchers. In this article, it briefly introduced the development history, structure, and composition of apple harvesting robots and the operation process, which makes readers have a clear understanding of apple harvesting robot and its harvesting principle. Then systematically summarizing the research results of apple harvesting robots both at domestic and at foreign, we carried out in following three aspects: rapid and accurate recognition and positioning of target fruit, all-weather operation mode, and application of intelligent computing theory in apple harvesting robots, and it analyzes the research progress of apple harvesting robot in detail. The results show that improving the harvesting efficiency is the key and hot spot for the research on apple harvesting robots. Under the impetus of information technology, how to achieve fast and accurate recognition of the fruits of multienvironment and multiple information, obtain reasonable path planning, and further optimization of control strategies are all important research directions.

Image analysis technology has drawn dramatic attention and developed rapidly because it enables a non-extractive and non-destructive approach to data acquisition of crab aquaculture. Owing to the irregular shape, multi-scale posture and special underwater environment, it is very challenging to adopt the traditional image recognition methods to detect crabs quickly and effectively. Consequently, we propose a real-time and robust object detector, Faster MSSDLite, for detecting underwater live crabs. Lightweight MobileNetV2 is selected as the backbone of a single shot multi-box detector (SSD), and standard convolution is replaced by depthwise separable convolution in the prediction layers. A feature pyramid network (FPN) is adopted at low extra cost to improve the detection precision of multi-scale crabs and make up for the deficiency of SSD to force different network layers to learn the same features. More significantly, the unified quantized convolutional neural network (Quantized-CNN) framework is applied to quantify the error correction of the improved detector for further accelerating the computation of convolutional layers and compressing the parameters of fully-connected layers. The test results show that Faster MSSDLite has better performance than traditional SSD. The average precision (AP) and F1 score of detection are 99.01% and 98.94%, respectively. The detection speed can reach 74.07 frames per second in commonly configured microcomputers (~8× faster than SSD). The computation amount of floating-point numbers required by the detection is reduced to only 0.32 billion (~49× smaller than SSD), and the size of the model is compressed into 4.84 MB (~28× smaller than SSD). The model is also more robust, which can stably detect underwater live crabs in real-time, estimate the live crab biomass in water bodies automatically, and provide reliable feedback information for the fine feeding of automatic feeding boats.

Chinese river crabs are important aquatic products in China, and the accurate operation of aquatic plants cleaning workboat is an urgent need for solving various problems in the aquaculture process. In order to achieve the accurate navigation positioning, this article introduces the visual-aided navigation system and combines the advantages of particle filter in nonlinear and non-Gaussian systems. Meanwhile, the generalized regression neural network is used to adjust the particle weights so that the samples are closer to the posterior density, thus avoiding the phenomenon of particle degradation and keeping the diversity of particles. In order to improve the network performance, the fruit fly optimization algorithm is introduced to adjust the smoothing factor of transfer function for the generalized regression neural network model layer. On this basis, the location filtering navigation method based on fruit fly optimization algorithm-generalized regression neural network-particle filter is proposed. According to the simulation results, the meanR of root-mean-square error of the proposed fruit fly optimization algorithm-generalized regression neural network- particle filter method decreases by 12.39% and 6.87%, respectively, compared with those of particle filter and generalized regression neural network methods, and the meanT of running time decreases by 16.04% and 9.14%, respectively. From the repeated experiments on the aquatic plants cleaning workboat in crab ponds, the latitude error of the proposed method decreases by 23.45% and 12.68%, respectively, and that the longitude error decreases by 29.11% and 17.65%, respectively, compared with those of particle filter and generalized regression neural network methods. It is proved that our proposed method can effectively improve the navigation positioning accuracy of aquatic plants cleaning workboat.

In view of the slowing expansion problem for the past harvesting robot’s electric push rod joint.This paper will adopt pneumatic draw stem instead of the original electric putter to improve the rapidity of servo system. Using VFW(Video for Windows) image acquisition system to access to the video buffer without generating the intermediate files,which can ensure high real-time performance. By monocular vision system to realize cylinder tracking control experiments for the fruit center position. Experiments verified the quickness and accuracy of the pneumatic servo positioning system.

For the agricultural vehicle straight-line tracking system, three control algorithms based upon the finite-time control technique have been proposed to force the vehicle to track a straight line. Without considering the lumped disturbance, a backstepping-like finite-time state-feedback controller is first developed. On this basis, an adaptive state-feedback controller in conjunction with integral sliding mode is further developed in the presence of the lumped disturbance. Finally, a sliding mode disturbance observer is given to estimate the lumped disturbance, and the composite control scheme is presented. Under the composite controller, the lumped disturbance can be compensated and thus the disturbance rejection property has been significantly improved. Simulation results verify the proposed control algorithms.

The aim of this study was to investigate the effects of erythropoietin (EPO) on the impairment of autophagy induced by lipopolysaccharide (LPS) in primary cultured rat glomerular mesangial cells (GMCs). Rat GMCs were isolated and cultured in normal glucose, high-glucose, LPS or LPS + EPO medium. At 24 and 72 h of culture, the cells were examined for expression levels of the autophagy markers LC3 and p62/sequestosome-1 (SQSTM1) using western blot analysis. At 24 h, no significant difference in the expression of LC3 and p62/SQSTM1 was observed among the groups; however, the cells exposed to high-glucose medium for 72 h showed downregulated LC3 expression and upregulated p62/SQSTM1 expression. The cells exposed to LPS (10 ng/ml) for 72 h showed upregulated LC3 expression and upregulated p62/SQSTM1 expression. These changes were reversed in the LPS + EPO group at 72 h. In conclusion, EPO can inhibit LPS-induced autophagy in rat GMCs.

Aiming at the problem of apple branch obstacle localization in fruit picking process of harvesting robot manipulator, in order to obtain three-dimensional information of the apple branch obstacle, the binocular stereo vision localization method of apple branch obstacle is proposed. Firstly, branch skeleton is extracted by morphological thinning method and then the feature skeleton is obtained after removing the false branch and recovering the occluded branch. After that, the endpoints and bifurcation points regarded as match feature points are extracted from skeleton, and the stereo matching algorithm based on features is adopted. Then, the depth information of branch obstacle is obtained on the basis of triangulation theory. Finally, the experiment results for apple tree branches localization show that the error lies in ±6.2 mm. Moreover, the error is merely ±1.5 mm when the distance between the object and the binocular camera is 1000 mm, which meets with localization accuracy requirements of apple harvesting robot visual system.

This paper presents relevant methods on navigation accuracy improvement of agricultural vehicle focusing on positioning accuracy and control precision. An adaptive kalman filtering, combination of Sage_Husa adaptive filtering and strong tracking kalman filtering based on strict convergence criterion, is adopted to improve filtering accuracy with strong ability of adaptive filtering and restraining filter divergence. A new variable-structure switching method to prevent PID controller from integrator windup can effectively solve the integral saturation phenomenon, which adopts a kind of adaptive adjustment rate to adjust the integral term of PID control algorithm. Finally, this paper puts the improved adaptive filtering and anti-windup variable-structure PID control technique into combination to effectively restrain interference and integral saturation, so as to achieve the purpose of improving system stability and control precision. The simulation and experiment results show that methods described above greatly enhance the capabilities of restraining filtering divergence and improving control precision.

Using the neural network to deal with complex data, because the pending sample with many variables, aiming at this nature of the pending sample and the structure properties of the BP neural network, in this paper, we propose the new BP neural network algorithm base on principal component analysis (PCA-BP algorithm). The new algorithm through PCA dimension reduction for complex data, got the low-dimensional data as the BP neural networks input, it will be beneficial to design the hidden layer of neural network, save a lot of storage space and computing time, and conductive to the convergence of the neural network. In order to verify the validity of the new algorithm, compared with the traditional BP algorithm, through the case analysis, the result show that the new algorithm improve the efficiency and recognition precise, worthy of further promotion.

By applying data fusions from GPS and MEMS sensors to plan and track path, and achieve the goal of mobile robot autonomous navigation. An improved filtering method based on Sage_Husa filtering is described, which can effectively restrain the filtering divergence, improve dynamic performance of filter, enhance stability and adaptability of filter, and improve navigation precision. With fuzzy adaptive PID control, the stability of control system is guaranteed with control strategy adjustment in real time. Finally, it is programmed that converting the fusion of high-precision GPS and attitude information into control command so as to succeed in robot navigation and real-time display on map. The feasibility and effectiveness of methods described above are verified and proved by experiments and MATLAB simulation.

This paper uses TMS320F28335 DSP and MAX3032S CPLD as the controller of the 6/4 pole switched reluctance motor (SRM), and controls the motor by the method of current chopping control (CCC) in low speed and the method of angle position control (APC) in high speed. About the optimization of turn-on angle and turn-off angle when SRM is controlled by the method of APC, this paper discusses the optimal design of the two parameters by ways of theory research, simulation and experimental testing. The results show optimal switching angle can make speeded-up of the motor better and improve the performance of SRM.

For monitoring the water quality in river, and improving the accuracy of the transmission in network, the remote monitoring system based on wireless sensor network is designed. The topology of cluster for the wireless sensor network was adopted, and the amendment version of LEACH-H protocol is also designed based on LEACH. The circuit design of sensor for concentration of nitrite and DO is also presented. For the remote wireless communications between the sink node and remote control center, the GPRS module is adopted. The test show that communications among the system are realized reliably and the requirements are met respectively. The application of the system can well meet the demands of remote monitoring system for water quality.

This paper designs a multi parameter real-time water quality on-line monitoring system for aquaculture water. This system achieves the online monitoring among temperature, turbidity, DO (dissolved oxygen), pH and electrical conductivity. The crosstalk, produced by the simultaneous measurement with DO and pH sensors, will affect accuracy and stability of monitoring results. This paper analyzes the source of crosstalk, describes a circuit model of causing crosstalk, and designs an isolated circuit between powers and signals as well. The experimental results show that, the real-time monitoring of DO and pH has the characteristics of speediness, high precision, small error and low noise.

Sparse representation direction-of-arrival (DOA) estimation methods exhibit many advantages over other DOA estimation methods. However, they suffer from a high computational complexity. This letter describes a real-valued sparse representation method through utilizing a unitary transformation that can convert complex-valued manifold matrices of uniform linear arrays (ULAs) into real ones. Due to this transformation, the computational complexity is decreased by a factor of at least four. The letter also shows that the proposed method has a better noise suppression because of exploiting an additional real structure. Therefore, it outperforms the original method, especially when signal-to-noise ratio (SNR) is low. Simulation results verify the performance improvement of the proposed method.

A new optimization algorithm of the path planning for spray painting robot of workpiece surfaces is proposed. This paper first provides the paint deposition rate function on a plane according to the experiment data. And the model of film thickness on surface is discussed. A multiobjective constraint optimization problem is formulated. An optimal tool path with an optimal time and film quantity deviation is generated. And the min-max method is adopted here to calculate the values. A workpiece, which is a free-form surface, is used to test the scheme. The results of experiments have shown that the path optimization algorithm achieves satisfactory performance. This algorithm can also be extended to other applications.

This paper proposes a vision-aided navigation system based on GPS navigation system, aimed at achieving the function of target positioning for the fully automatic workboat of crab breeding. The system gets the exact coordinates of the target through combining its GPS coordinates with its relative coordinates obtained by camera calibration in Kalman filtering algorithm after segmenting and identifying the target in HSI color space of the image. Experimental results show that the proposed vision-aided navigation system can improve the navigation accuracy and robustness of the automatic navigation system of the fully automatic workboat.

In order to resolve the poor real-time performance problem of the normalized cut (Ncut) method in apple vision recognition of picking robots, a fast segmentation method of colour apple images based on the adaptive mean-shift and Ncut methods is proposed in this paper. Firstly, the traditional Ncut method based on pixels is changed into the Ncut method based on regions by the adaptive mean-shift initial segmenting. In this way, the number of peaks and edges in the image is dramatically reduced and the computation speed is improved. Secondly, the image is divided into regional maps by extracting the R-B colour feature, which not only reduces the quantity of regions, but also to some extent overcomes the effect on illumination. On this basis, every region map is expressed by a region point, so the undirected graph of the R-B colour grey-level feature is attained. Finally, regarding the undirected graph as the input of Ncut, we construct the weight matrix W by region points and determine the number of clusters based on the decision-theoretic rough set. The adaptive clustering segmentation can be implemented by an Ncut algorithm. Experimental results show that the maximum segmentation error is 3% and the average recognition time is less than 0.7s, which can meet the requirements of a real-time picking robot.

In order to meet the speed requirements of harvesting robot, a method of tracking and recognition of overlapping apples is proposed in this paper. First of all, the first image should be segmented and denoised, the center and the radius is determined, the template which is used for matching is extracted according to the center and radius. Then, determine the center of ten images which are taken continuously, fit motion path of the robot according to the center of each image and predict subsequent motion path. The next processing area is determined according to the radius and predicted path. Finally, overlapping apples are identified by fast normalized cross correlation match method. Experiments prove that the new method can locate the center and radius of overlapping apples correctly. Besides, matching time is reduced by 48.1 % compared with the original one.

Recently the picking technology of high value crops has become a new research hot spot, and the image segmentation and recognition are still the key link of fruit picking robot. In order to realize the lotus image recognition, this paper proposes a new feature extraction method combined with shape and color, and uses the K-Means clustering algorithm to get lotus recognition model. Before the feature extraction, the existing pulse coupled neural network segmentation algorithm, combined with morphological operation, is used to achieve nice segmentation image, including lotus, lotus flower, lotus leaf and stems. Then in the feature extraction processing, the chromatic aberration method and the moment invariant algorithm are selected to extract the color and shape features of the segmented images, in which principal component analysis algorithm is selected to reduce the dimension of the color and shape features to achieve principal components of lotus, lotus flower, lotus leaf and stems. In the experiment, K-Means clustering algorithm is used to get lotus recognition model and four clustering centers according to above principal components of training samples about lotus, lotus flower, lotus leaf and stems; then the testing experiment is applied to validate the recognition model. Experimental results shows that the correct recognition rate is 90.57 % about 53 testing samples of lotus, and the average recognition time is 0.0473 s, which further indicates that the feature extraction algorithm is applicable to lotus feature extraction, and K-Means algorithm is simple, reliable and feasible, providing a theoretical basis for positioning and picking of lotus harvest robot.

In apple harvesting robot, the first key part is the machine vision system, which is used to recognize and locate the apples. In this paper, the procedure on how to develop an automatic recognition vision system guided for apple harvesting robot, is proposed. We first use a color charge coupled device camera to capture apple images, and then utilize an industrial computer to process images for recognising fruit. Meanwhile, the vector median filter is applied to remove the color images noise of apple, and images segmentation method based on region growing and color feature is investigated. After that the color feature and shape feature of image are extract, a new classification algorithm based on support vector machine for apple recognition is introduced to improve recognition accuracy and efficiency. Finally, these procedures proposed have been tested on apple harvesting robot under natural conditions in September 2009, and showed a recognition success rate of approximately 89% and average recognition time of 352ms.

The line of sight (LOS) stabilization control based on gyro stabilized platform is required to isolate the LOS from the disturbance and vibration of carrier and ensure pointing and tracking for target in electro-optical tracking system. A composite adaptive fuzzy proportional-integral-derivative (PID) control with hysteresis-band switching is developed to achieve real-time and high stabilization precision for this nonlinear uncertainty servo system. First of all, in the adaptive fuzzy controller, the pre-designed self-tuning factors are able to modify the parameters of fuzzy controller online, and a new learning algorithm of fuzzy rules modifier is proposed to adjust control efforts. Then, an improved PID controller is chosen to restrain motor saturation and eliminate the static error originated from the fuzzy controller, and fulfill non-error control. The hysteresis-band switching strategy is given to deal with jitter caused by single-point switching condition. The experimental results in four-axis servo turntable show that the proposed method can achieve nice control performance and is proved to be effective in bating carrier disturbances within the scope of definite noise and sensitivity to acceleration.

Aiming at the lack of all-purpose and effective planning study for apple picking robot’s end-effector during the grasping process, which has caused great inconvenient in the accuracy of fruit picking process and design of end-effector. This paper studies the contact process of three-finger end-effector with apples. Taking contact of apples with fingers as point contact of friction between hard objects, and based on the fact that the contact force is decomposed into the orthogonal operating force component and internal force component, the regulation of internal force on contact stability is discussed. Stability would be attributed to the existence of the internal force of concurrent polygon and the position of the internal force concurrent node within the concurrent polygon. Regarding the circle center of concurrent polygon of the maximum inscribed circle as the intersection of three internal force action lines, we get the size of each internal force, and calculate the internal force meeting the friction cone constraints to avoid complex operation such as matrix operation. Eventually, a numerical example shows the feasibility of the method.

In order to enhance the applicability and efficiency of harvesting robot to ensure that people can timely pick ripe fruit, the robot need to have an ability of continuous recognition and harvest at night. For some disadvantages of night vision images, Retinex algorithm for image enhancement based on bilateral filter is presented. Bilateral filter which has a function of edge preservation is adopted to improve the smooth, evaluate the illumination and remove unfavorable illumination effects from the original image. Then the reflectance of the image from above that contains just the characteristics of the object itself can be obtained. Finally, apple nighttime image enhancement is implemented. The experimental results show that the above method can more accurately evaluate the illumination of high-contrast edge regions, to suppress noise, enhance image contrast and improve overall visual effects of the image.

To explore the mechanism whereby stem cell factor (SCF) and granulocyte colony-stimulating factor (G-CSF) jointly mobilize bone marrow stem cells (BMSCs) and promote kidney repair, male Sprague-Dawley rats were randomly assigned into 4 groups. In the treatment control group, rats were administered SCF (200 μg·kg(-1)·day(-1)) and G-CSF (50 μg·kg-1·day-1) for 5 days. In the treatment group, RIRI models were established, and 6 h later, SCF (200 μg·kg(-1)·day(-1)) and G-CSF (50 μg·kg(-1)·day(-1)) were administered for 5 days. In the model and treatment groups, tubular epithelial cell degeneration and necrosis were noticed, but the extent of repair in the treatment group was significantly better than in the model group. Five days after the operation, renal tissue CD34+ cells significantly increased in the model and treatment groups compared with the control and treatment control groups. HIF-1α, VEGF, and EPO expression in treatment groups increased significantly compared with the other groups. HIF- 1α, VEGF, EPO expression in the treatment control group increased significantly compared with the control group. Joint use of SCF and G-CSF increased the number of BMSCs in damaged kidney tissue and reduced the degree of renal tissue damage. BMSCs promote increased HIF-1α expression in renal tissue. Increased kidney tissue HIF- 1α and its target gene products VEGF and EPO expression possibly induce SCF and G-CSF to promote acute tubular necrosis repair.

In order to improve the image denoising ability, the wavelet transform (WT) and independent component analysis (ICA) are both introduced into image denoising in this paper. Although these two algorithms have their own advantages in image denoising, they are unable to reduce noises completely, which makes it difficult to achieve ideal effect. Therefore, a new image denoising method is proposed based on the combination of WT with ICA (WT-ICA). For verifying the WT-ICA denoising method, we adopt four image denoising methods for comparison: median filtering (MF), wavelet soft thresholding (WST), ICA, and WT-ICA. From the experimental results, it is shown that WT-ICA can significantly reduce noises and get lower-noise image. Moreover, the average of WT-ICA denoising image’s peak signal to noise ratio (PSNR) is improved by 20.54% compared with noisy image and 11.68% compared with the classical WST denoising image, which demonstrates its advantage. From the performance of texture and edge detection, denoising image by WT-ICA is closer to the original image. Therefore, the new method has its unique advantage in image denoising, which lays a solid foundation for the realization of further image processing task.

According to the grasping damage of apple during the process of robot picking apple, the variation of interior tensions inside the apple skin in the grasping process of apple with different type finger of robot end-effector is researched. The finite element model for apple is established by ANSYS. Some simulations for the grasping process of apple with plane and arc-shaped finger are carried out. The Von Mises stress nephograms of apple different tissue under different load force by different type fingers are obtained. The experimental results show that the apple cortex is more easily to get damaged due to its small failure stress. And the deformation and stress of apple caused by arc-shaped finger are smaller than by plane finger. At last, the actual experiment for apple grasping damage of end-effector with arc-shaped finger validates the reliability of simulated results. The research results demonstrated that the finite element method can make accurate evaluation for apple damage. Practical applications A major problem associated with robot harvesting is the mechanical damage of apple caused by end-effector of robot. When the apple is grasped by the end-effector, the mechanical damage is often occurred underneath apple skin thus, which is difficult to find by the naked eye immediately. The results in our paper can accurate evaluation for apple damage and provide a foundational basis to develop an injury-reduce device of apple harvesting robot.

The aim of the present study was to observe the mobilisation effects of stem cell factor (SCF) and granulocyte colony-stimulating factor (G-CSF) on bone marrow stem cells (BMSCs) in rats with renal ischaemia-reperfusion injury. In addition, the effects of the BMSCs on the expression levels of hepatocyte growth factor (HGF) and epidermal growth factor (EGF) were investigated, with the aim to further the understanding of the protective mechanisms of SCF and G-CSF in renal ischaemia-reperfusion injury. The model and treatment groups were established using a model of unilateral renal ischaemia-reperfusion injury, in which the treatment group and the treatment control group were subcutaneously injected once a day with 200 µg/kg SCF and 50 µg/kg G-CSF, 24 h after the modelling, for five consecutive days. The CD34+ cell count was measured in the peripheral blood using flow cytometry. The mRNA expression levels of HGF and EGF were determined using polymerase chain reaction analysis, while the protein expression levels of HGF and EGF were detected using immunohistochemistry. The CD34+ cell count in the peripheral blood of the treatment and treatment control groups was significantly higher compared with that in the model group (P

Using the neural network to classify the data which has higher dimension and fewer samples means overmuch feature inputs influence the structure design of neural network and fewer samples will generate incomplete or overfitting phenomenon during the neural network training. All of the above will restrict the recognition precision obviously. It is even better to use neural network to classify and, therefore, propose a neural network ensemble optimized classification algorithm based on PLS and OLS in this paper. The new algorithm takes some advantages of partial least squares (PLS) algorithm to reduce the feature dimension of small sample data, which obtains the low-dimensional and stronger illustrative data; using ordinary least squares (OLS) theory determines the weights of each neural network in ensemble learning system. Feature dimension reduction is applied to simplify the neural network’s structure and improve the operation efficiency; ensemble learning can compensate for the information loss caused by the dimension reduction; on the other hand, it improves the recognition precision of classification system. Finally, through the case analysis, the experiment results suggest that the operating efficiency and recognition precision of new algorithm are greatly improved, which is worthy of further promotion.