The large data size and dimensionality of hyperspectral data demands complex processing and data analysis. Multispectral data do not suffer the same limitations, but are normally restricted to blue, green, red, red edge, and near infrared bands. This study aimed to identify the optimal set of spectral bands for nitrogen detection in grape leaves using ensemble feature selection on hyperspectral data from over 3,000 leaves from 150 ‘Flame Seedless’ table grapevines. Six machine learning base rankers were included in the ensemble: random forest, LASSO, SelectKBest, ReliefF, SVM-RFE, and chaotic crow search algorithm (CCSA). The pipeline identified less than 0.45% of the bands as most informative about grape nitrogen status. The selected violet, yellow-orange, and shortwave infrared bands lie outside of the typical blue, green, red, red edge, and near infrared bands of commercial multispectral cameras, so the potential improvement in remote sensing of nitrogen in grapevines brought forth by a customized multispectral sensor centered at the selected bands is promising and worth further investigation. The proposed pipeline may also be used for application-specific multispectral sensor design in domains other than agriculture.

In this study, kinematics design, dynamics modeling and verification of a compounded serial-parallel wheeled mobile robot is elaborated. The proposed novel kinematic structure is best suited to fulfill stable motion of the robotic system when handling heavy objects by manipulators mounted on mobile platforms. The proposed system is made of a differentially-driven wheeled platform, a planar parallel manipulator, which is called here as Star-Triangle (ST) mechanism, and a serial Puma-type manipulator arm. The suggested structure adopts the advantages of both serial and parallel robots, to move the base point of the serial robot with respect to the mobile platform to fulfill the system stability after grasping heavy objects. In order to investigate the comprehensive kinematics model of the robot, after introducing its novel structure it is divided into three modules, i.e. a mobile platform, a parallel ST mechanism, and a serial robot. Next, a closed-form dynamics model is derived for the whole hybrid system based on a combined Newton-Euler and Lagrange formulation. The proposed method presents the mutual dynamic interaction wrenches between the integrated platform and the serial manipulator which can be exploited for the tip-over stability analysis of the mobile robotic system. Then, to verify the obtained mathematical model, several benchmark actuating inputs are applied to the model and the system responses are analyzed.