In this paper, a new method is proposed for simulating the motions of reconfigurable machines. When a reconfigurable machine is reconfigured, the relative poses between adjacent modules must be redefined. Unlike the traditional modelling method that re-sets the local coordinate frames for each module relative to the preceding module, the proposed method is to define all the modules with respect to a single global coordinate frame. As such, machine modules can be readily linked through a graph-based topology platform to form an assembled reconfigurable machine and then to automatically generate the equations of motion.

A motion simulation method for reconfigurable machines

The reconfigurable tracked mobile robot was developed for all-terrain recon. Based on the unique characters of reconfigurable robot, modular mechanical and electrical structure and control method were all discussed. The tracked robot was composed of four basic locomotion modules, three joint rods and two rotational articulations. By the different configurations of all the modules, the mechanical reconfiguration of the tracked vehicle was realized. The master-slave control system was adopted. Based on the ARM real time embedded control system, the reconfiguration was realized when the mechanical structure of the robot was reconfigured. The tracked robot was validated that it has the excellent adaptable ability in complex terrain and has easy and simple reconfigurable performance when it executed recon in the building interior simulating the real task.

Reconfiguration Research on Modular Mobile Robot

The evaluation of mutton adulteration faces new challenges because of mutton flavour essence, which achieves a similar flavour between the adulterant and mutton. Hence, methods for classifying and quantifying the adulterated mutton under the effect of mutton flavour essence, based on near-infrared hyperspectral imaging (NIR-HSI, 1000–2500 nm) combined with machine learning (ML) and sparrow search algorithm (SSA), were proposed in this study. After spectral preprocessing via first derivative combined with multiple scattering correction (1D + MSC), classification and quantification models were established using back propagation neural network (BP), extreme learning machine (ELM) and support vector machine/regression (SVM/SVR). SSA was further used to explore the global optimal parameters of these models. Results showed that the performance of models improves after optimisation via the SSA. SSA-SVM achieved the optimal discrimination result, with an accuracy of 99.79% in the prediction set; SSA-SVR achieved the optimal prediction result, with an RP2 of 0.9304 and an RMSEP of 0.0458 g·g−1. Hence, NIR-HSI combined with ML and SSA is feasible for classification and quantification of mutton adulteration under the effect of mutton flavour essence. This study can provide a theoretical and practical reference for the evaluation and supervision of food quality under complex conditions.

https://www.mdpi.com/2304-8158/11/15/2278/pdf?version=1659403724

Evaluation of Mutton Adulteration under the Effect of Mutton Flavour Essence Using Hyperspectral Imaging Combined with Machine Learning and Sparrow Search Algorithm

We present here a methodology for the development of automation modules that is based in the use of basic modules named Intelligent Actuators. We describe the characteristics of these modules and we describe also here how this methodology is applied to design and to implement a single model and a more complex system. All these modules have the properties of plug and solve systems. Main improvement with respect to other approaches is that they are implemented using low-cost platforms, like the Arduino board. Such a system can reduce time spent in the system design phase and also the costs associated to its installation and maintenance.

Methodology for modular automation system design

The proliferation of grassland rodents has aggravated the degradation process of desert grassland. Additionally, it carries many viruses that threaten human and animal health. Accurate spatial distribution in grassland between rodent populations, vegetation, and bare soil is essential for developing rodent control measures. However, the traditional survey method of grassland rodent pest information is time-consuming and costly, and the period is long. In addition, satellite remote sensing cannot meet the accuracy requirements for the identification of grassland rat holes due to the limitation of spatial resolution. To realize intelligent grassland rodent infestation monitoring, this paper adopts an unmanned aerial vehicle hyperspectral remote sensing platform for data acquisition. Meanwhile, a transformer attention network (TAN) is proposed for grassland rodent infestation information extraction. The network adopts a two-stage feature extraction structure that effectively improves the classification performance of the model. In each stage, first, local features are extracted by a fixed convolution kernel to enhance detailed texture features; second, the extracted local features are refined using the contour convolution module to enrich feature information at the edges of the feature map; finally, the transformer attention module is used to focus on the global pixels, thus suppressing background information and enhancing effective information output. The results show that the overall accuracy (OA), average accuracy, and kappa coefficient of the TAN network can reach 97.71%, 98.44%, and 0.9538, respectively. Compared with several networks, such as two-dimensional CNN, three-dimensional CNN, HybridSN, and CTN, the OA values of the TAN network were improved by 2.59%, 2.45%, 2.94%, and 1.03%, respectively. The results of this study effectively improve the efficiency of the grassland rodent information survey and provide a solid theoretical basis for the investigation and statistics of grassland rodent infestation. 

Transformer attention network and unmanned aerial vehicle hyperspectral remote sensing for grassland rodent pest monitoring research

Abstract The quality of milk is largely determined by the protein content. The feasibility of predicting the protein content of milk by hyperspectral image has attracted more attentions from researchers for minor detection cost and high efficiency. In this paper, a prediction modeling method based on improved sparrow search algorithm (SSA) and optimized back propagation (BP) neural network is proposed, in which sine chaotic map is introduced to initialize the population position to improve the optimization performance of SSA. In the experiment, hyperspectral images of each kind of milk were collected by visible/near infrared hyperspectral imaging system to acquire hyperspectral data, then the spectral data were pretreated by Savitzky–Golay smoothing, and the competitive adaptive reweighted sampling combined with successive projections algorithm to select 13 characteristic bands. Subsequently, the spectral data corresponding to the characteristic bands are used as the input of back propagation neural network, optimized by the improved sparrow search algorithm for the initial weight and threshold of BP neural network, to establish three prediction models(BP model, the BP model based on SSA optimization and the BP model based on improved SSA optimization).Experimental results demonstrate that the BP model based on improved SSA optimization has better fitting ability and higher prediction accuracy for milk protein content. This research provides algorithm support and theoretical basis for the rapid nondestructive detection of milk protein content based on BP neural network.

Prediction of milk protein content based on improved sparrow search algorithm and optimized back propagation neural network

In order to achieve fast localization and detection of dog face in intelligent dog management system, a dog face detection algorithm based on improved Faster RCNN was proposed. To obtain the feature extraction backbone network suitable for small size targets, the algorithm extracts the features of the detection target by constructing the residual convolution network, and fuses the features of different layers of the convolution network with the feature pyramid structure. Then, the region proposal network is used to generate and filter the possible regions of the target, and the bilinear interpolation method is used to calculate the bounding box coordinate values to achieve accurate location. Using Tsinghua dog image dataset to train the model, an improved Faster RCNN model adapted to small scale targets is obtained. The experimental results show that the improved method proposed in this paper maintains high precision in the detection of small size dog face, and can realize the detection of different scale objects, which has certain engineering practical value.

Small scale dog face detection using improved Faster RCNN

Modular, self-reconfigurable robots(MRR) show the promise of great versatility, simplicity, robustness and low cost However, control system is one of the most important components of the robotic systems It will depend on the control system to realize those promises In this paper, we present a master/slave distributed control system for this type of robot Because of excellent performance and high integration, the DSP controller-TMS320LF2406 is selected to compose the smallest system for the module DC motor control, with the individual controllers communicating with other modules and the master using a controller area network(CAN)

Distributed control system for modular self-reconfigurable robots

ABSTRACT In recent years, the classification of hyperspectral images (HSI) has received extensive research attention. As compared with traditional HSI classification, which only uses spectral information, it is found that spatial information is also essential in HSI classification. To effectively utilize the spectral and spatial information of HSI, this paper proposes a triple-branch ternary-attention mechanism network with deformable 3D convolution (D3DTBTA). In D3DTBTA, three branches, i.e. the spectral, spatial-X, and spatial-Y branches, are combined with the attention mechanism in three directions, which can better capture the vector features of three dimensions in HSI. Furthermore, considering the adaptation of scale and receptive field size in the convolution operation, our method uses deformable convolution to enable D3DTBTA to enhance feature extraction. Our experimental results show that the framework outperforms existing algorithms on four hyperspectral datasets, especially when the training samples are limited.

Triple-branch ternary-attention mechanism network with deformable 3D convolution for hyperspectral image classification

Wavelength selection is one of the key steps in quantitative spectral analysis, which reduces the computation time while also improving the prediction accuracy of the model. In this paper, we propose a wavelength selection algorithm based on the ant colony optimization (ACO), in which the absolute value of the regression coefficient of the multiple linear regression (MLR) model is used as the basis for evaluating the importance of wavelengths, and the absolute value of the regression coefficient after full wavelength MLR modeling is used as the initial pheromone value of the ant colony optimization (MLR-ACO). In each iteration, the absolute value of the regression coefficient corresponding to each wavelength of the individual with the highest fitness value is used as the basis for a pheromone update. The crossover operator is introduced in MLR-ACO (MLR-ACO-GA), and the individuals with the top 100 fitness values in MLR-ACO are used as the initial population of the genetic algorithm (GA). A selected frequency of wavelengths greater than the threshold among MLR-ACO individuals is calculated. A number of coarse interval points are generated according to the selected frequency, and a coarse crossover operation is performed at the coarse interval points. Fine crossover points are randomly generated within the coarse interval, and fine crossover operations are performed within the coarse interval to exploit the potential of combining excellent individuals in MLR-ACO with each other as much as possible. MLR-ACO can well solve the problem of traditional ACO initial pheromone scarcity, and MLR-ACO-GA can avoid MLR-ACO falling into a local optimum to a certain extent and be more flexible in the selection of the number of wavelengths, which can give full play to the advantages of MLR-ACO.

/pdf/a-new-method-for-spectral-wavelength-selection-based-on-3tfgfj0n.pdf

Jiangping Liu

Papers

Prediction of milk protein content based on improved sparrow search algorithm and optimized back propagation neural network

Small scale dog face detection using improved Faster RCNN

Distributed control system for modular self-reconfigurable robots

Triple-branch ternary-attention mechanism network with deformable 3D convolution for hyperspectral image classification

A New Method for Spectral Wavelength Selection Based on Multiple Linear Regression Combined with Ant Colony Optimization and Genetic Algorithm