Reducing the dimensionality of the original pattern space in a definition of feature space while maintaining discriminatory power for classification is a general goal in pattern recognition. To accomplish this goal in the area of ear biometrics a highly recognized work was proposed by D. Hurley in 2D space. We were inspired by his work and developed a new method for 3D data. In a different way to Hurley’s work we obtain a potential energy surface from 3D depth image which underlies the force field and associated vector field has its own characteristics. Our feature extraction is conducted by combining two different approaches; an algorithmic approach as well as an analytical approach, both are based on the vector force field and geometrical approach which is based on 3D ear surface. To validate the technique, the ICP algorithm is used. This work differs from Hurley’s work not only because of the algorithm, but also because of the nature of the 3D data which delivers topological information of the images. We exploit geometry to acquire surface information of the ear which yields richer features than the original work. The performance of the proposed method was evaluated using the University of Notre Dame (UND) collection J2 database and MATLAB has been used as the software package. / phone number: 0700099273

<div>Polymer nanocomposites (PNC) have an excellent potential for in-situ strain sensing applications in static and dynamic loading scenarios. These PNCs have a polymer matrix of polyvinylidene fluoride (PVDF) with a conductive filler of multi-walled carbon nanotubes (MWCNT) and have both piezoelectric and piezoresistive characteristics. Generally, this composite would accurately measure either low-frequency dynamic strain using piezoresistive characteristic or high-frequency dynamic strains using piezoelectric characteristics of the MWCNT/PVDF film sensor. Thus, the frequency bands of the strain sensor are limited to either piezoresistive or piezoelectric ranges. In this study, a novel weighted fusion technique, called Piezoresistive/Piezoelectric Fusion (PPF), is proposed to combine both piezoresistive and piezoelectric characteristics to capture the wide frequency bands of strain measurements in real-time. This fuzzy logic (FL)-based method combines the salient features (i.e., piezoresistive and piezoelectric) of the nanocomposite sensor via reasonably accurate models to extend the frequency range over a wider band. The FL determines the weight of each signal based on the error between the estimated measurements and the actual measurements. These weights indicate the contribution of each signal to the final fused measurement. The Fuzzy Inference System (FIS) was developed using both optimization and data clustering techniques. In addition, a type-2 FIS was utilized to overcome the model’s uncertainty limitations. The developed PPF methods were verified with experimental data at different dynamic frequencies that were obtained from existing literature. The fused measurements of the MWCNT/PVDF were found to correlate very well with the actual strain, and a high degree of accuracy was achieved by the subtractive clustering PPF’s FISs algorithm. <br></div><div><br></div><div>3D force sensors have proven their effectiveness and relevance for robotics applications. They have also been used in medical and physical therapy applications such as surgical robots and Instrument Assisted Soft Tissue Manipulation (IASTM). The 3D force sensors have been utilized in robot-assisted surgeries and modern physical therapy devices to monitor the 3D forces for improved performances. The 3D force sensor performance and specifications depend on different design parameters, such as the structural configuration, placement of the sensing elements, and load criterion. In this work, different bioinspired structure configurations have been investigated and analyzed to obtain the optimal 3D force sensor configuration in terms of structural integrity, compactness, the safety factor, and strain sensitivity. A Finite Element Analysis (FEA) simulation was used for the analysis to minimize the time of the development cycle.</div><div><br></div><div><br></div><div>A tree branch design was used as the 3D force sensor’s elastic structure. The structure was made of aluminum with a laser-cutting fabrication process. The PVDF/MWCNT films contained piezoresistive and piezoelectric characteristics that allowed for static/low strain measurements and dynamic strain measurements, respectively. Two compositions with 0.1 wt.% and 2 wt.% PVDF/MWCNT sensing elements were selected for piezoelectric and piezoresistive strain measurements, respectively. These characteristic measurements were investigated under different vibration rates in a supported beam experiment. The 3D force sensor was tested under dynamic excitation in the Z-direction and the X-direction. A Direct Piezoresistive/Piezoelectric Fusion (DPPF) method was developed by fusing the piezoresistive and piezoelectric measurements at a given frequency that overcomes the limited frequency ranges of each of the strain sensor characteristics. The DPPF method is based on a fuzzy inference system (FIS) which is constructed and tuned using the subtractive clustering technique. Different nonlinear Hammerstein-Wiener (nlhw) models were used to estimate the actual strain from piezoresistive and piezoelectric measurements at the 3D force sensor. The DPPF method was tested and validated for different strain signal types using presumed Triangle and Square signal waves data. The DPPF has proven its effectiveness in fusing piezoresistive and piezoelectric measurements with different types of signals. In addition, an Extended Direct Piezoresistive/Piezoelectric Fusion (EPPF) is introduced to enhance the DPPF method and perform the fusion in a range of frequencies instead of a particular one. The DPPF and EPPF methods were implemented on the 3D force sensor data, and the developed fusion algorithms were tested on the proposed 3D force sensor experimental data. The simulation results show that the proposed fusion methods have been effective in achieving lower Root Mean Square Error (RMSE) than those obtained from the tuned nlhw models at different operating frequencies.</div>