Object-based classification of hyperspectral data using Random Forest algorithm

This paper presents a new framework for object-based classification of high-resolution hyperspectral data.This multi-step framework is based on multi-resolution segmentation(MRS)and Random Forest classifier(RFC)algorithms.The first step is to determine of weights of the input features while using the object-based approach with MRS to processing such images.Given the high number of input features,an automatic method is needed for estimation of this parameter.Moreover,we used the Variable Importance(VI),one of the outputs of the RFC,to determine the importance of each image band.Then,based on this parameter and other required parameters,the image is segmented into some homogenous regions.Finally,the RFC is carried out based on the characteristics of segments for converting them into meaningful objects.The proposed method,as well as,the conventional pixel-based RFC and Support Vector Machine(SVM)method was applied to three different hyperspectral data-sets with various spectral and spatial characteristics.These data were acquired by the HyMap,the Airborne Prism Experiment(APEX),and the Compact Airborne Spectrographic Imager(CASI)hyperspectral sensors.The experimental results show that the proposed method is more consistent for land cover mapping in various areas.The overall classification accuracy(OA),obtained by the proposed method was 95.48,86.57,and 84.29%for the HyMap,the APEX,and the CASI datasets,respectively.Moreover,this method showed better efficiency in comparison to the spectralbased classifications because the OAs of the proposed method was 5.67 and 3.75%higher than the conventional RFC and SVM classifiers,respectively.

The Effect of Saddle-Assistive Device on Improving the Gait Parameters of Patients with the Lower Limbs Weakness:A Pilot Study

To help walking,using assistive devices can be considered to reduce the loads caused by weight and to effectively decrease the propulsive forces.In this study,a mobility Saddle-Assistive Device(S-AD)supporting body weight while walking was evaluated on two healthy volunteers.This device is based on the support of body weight against gravity with the help of a saddle,which is not used in other passive mobility assistive devices.To prove the efficiency of this device,the experimental results obtained while walking with this device were compared with those related to walking without the assistive device.The results showed that this device could significantly reduce the forces and torque of the lower and upper limbs when walking.By distributing the load on the saddle,the vertical force and the propulsive force in the best conditions were decreased to 46.7%and were increased to 13.7%in body weight,respectively.Using a S-AD can help patients with lower limbs weakness and elderly people to walk.

3D numerical analysis of drilling process： heat, wear, and built-up edge

In this study, a 3D finite element model is developed to investigate the drilling process of AISI 1045 steel, and particularly, the heat and wear on the drill faces. To model drill wear, a modified Usui flank wear rate is used. Experiments are used for the verification of the simulated model and the evaluation of the surface rough- ness and built-up edge. A comparison of the predicted and experimental thrust forces and flank wear rates revealed that the predicted values had low errors and were in good agreement with the experimental values, which showed the utility of the developed model for further analysis. Accordingly, a heat analysis indicated that approximately half the generated heat in the cutting zone was conducted to the drill bit. Furthermore, material adhesion occurred in localized heat areas to a great extent, thus resulting in wear acceleration. A maximum flank wear rate of 0.026 1 mm/s was observed when the rotary speed and feed rate were at the lowest and highest levels, respectively. In the reverse cutting condition, a minimum flank wear rate of 0.016 8 mm/s was observed.