Adaptive phase control impact device (APCID) was developed for performing in-service modal analysis using impact synchronous modal analysis. However, this device is large and heavy, making it unsuitable for real world applications. This automated impact device can be replaced with human hand but the randomness in human behavior can reduce the accuracy of APCID control scheme. To replace APCID with a smart semi-automated device while still using APCID control scheme, machine learning models are presented in this paper to recognize human behavior by classifying 13 different impact types and predicting impact time using the impact classification. The impact classification model gave classification accuracy of over 96% with 130 real time impacts. With successful classification of different impact types, randomness in human behavior can be reduced by two to three times by associating a range of impact time with each impact type. However, the impact time ranges may differ person to person. To address this issue and to further reduce variations in impact time, a time prediction machine learning model was developed to make compensations in the control scheme of APCID by predicting impact time. The model gave reasonable accuracy with mean prediction errors of 5.2% in real time testing compared to measured time for 100 impacts.
Abstract Recent years have shown increased interest in improving the efficiency of piezoelectric vibration-based energy harvesters (PVEH). The most common boundary condition of a PVEH is the clamped-end or cantilever with rigid supports, making it to perform efficiently at the resonant frequencies of the first two bending modes that are usually at a higher frequency range. The generated output voltage and power is also limited to the deformation from the bending modes of the cantilever PVEH. Thus, to lower the resonant frequencies for practicality in real ambient vibrations and to further increase the generated energy output, this paper proposed a spring boundary condition cantilever PVEH, where the rigid support of a cantilever PVEH was replaced with springs. A clamped-end cantilever PVEH was used as the benchmark for comparison. The springs were computationally modelled as a combination of a tension and a torsional spring to investigate the effect of tension and torsional spring stiffness in reducing the resonant frequencies of the cantilever PVEH using computational methods. To validate the proposed boundary conditions in reducing the resonant frequencies and increasing the generated voltage and power output of a cantilever PVEH, the vibration characteristics of the spring-based cantilever PVEH were extracted numerically and experimentally using amplitude-fluctuation electronic speckle pattern interferometry (AF-ESPI), laser Doppler vibrometer (LDV), and impedance analysis, and were compared with the clamped-end cantilever PVEH. Results showed that the spring boundary condition can effectively reduce the resonant frequencies and increase the maximum voltage and power output of the cantilever PVEH due to the increased displacement from the spring supports in the bending modes. The first three resonant frequencies of the cantilever PVEH were reduced from 73Hz, 284Hz, and 452Hz to 15Hz, 127Hz, and 439Hz. The maximum voltage output was increased from 3.1V to 9.3V, and the maximum power was increased from 0.093mW to 8.316mW, thus making it more practical to be used at a lower or ambient frequency range.
Current methods of evaluating the performance of a runner using an energy return prosthesis often rely on a physiological methodology, making the differentiation between the contributions from the biological and the prosthetic elements of the below-knee amputee athlete difficult. In this paper a series of mass and composite foot systems were used to evaluate the effect that gravity, mass, stiffness and inertia have on the dynamic characteristics of a prosthesis. It is demonstrated that if the natural characteristics of a system are identified and synchronised with the physiological gait behaviour of a runner, performance enhancement can occur, resulting in a faster take off speed and in storing extra energy in the system that can later be recovered. Therefore, a bi-lateral amputee athlete with near symmetrical gait can recover the stored energy during the steady state or latter phases of a running event.
Current method of enhancing the performance of a bilateral amputee runners using energy return prosthesis is rarely linked to the system dynamics. In this paper a simple simulation is used to show that if a self selected running step frequency could be synchronized with dynamic elastic response of a mass spring system extra gain in height or faster take off velocity can be achieved which results is higher state of energy equilibrium that is more favourable to running activity. Current method often relies on physiological methodology, making the differentiation between the contributions from the biological and the prosthetic element of the below-knee amputee athlete difficult. In this paper a series of mass and composite foot system are modelled based on a combination of mass, spring and damper arrangement to study the effect of gravity, mass, stiffness, damping and inertia on the dynamics characteristics of prosthesis and how human can instinctively detect the natural elastic response of such system both to cyclic excitation and impulse through self selection of frequency or impulse.It will be demonstrated that if the natural characteristics of a system are identified and synchronised with the physiological gait behaviour of a runner, performance enhancement could occur that can be stored and controlled at will by the user. In the case of a bi-lateral amputee athlete with near symmetrical gaitit can result in steady state running which can be beneficial over longer distances.
Keywords: Amputee, Prosthesis, Lower-Limb, Foot, Energy
Alzheimer’s disease (AD) is an irreversible neurological disorder that affects the vast majority of dementia cases, leading patients to experience gradual memory loss and cognitive function decline. Despite the lack of a cure, early detection of Alzheimer’s disease permits the provision of preventive medication to slow the disease’s progression. The objective of this project is to develop a computer-aided method based on a deep learning model to distinguish Alzheimer’s disease (AD) from cognitively normal and its early stage, mild cognitive impairment (MCI), by just using structural MRI (sMRI). To attain this purpose, we proposed a multiclass classification method based on 3D T1-weight brain sMRI images from the ADNI database. Axial brain images were extracted from 3D MRI and fed into the convolutional neural network (CNN) for multiclass classification. Three separate models were tested: a CNN built from scratch, VGG-16, and ResNet-50. As a feature extractor, the VGG-16 and ResNet-50 convolutional bases trained on the ImageNet dataset were employed. To achieve classification, a new densely connected classifier was implemented on top of the convolutional bases.
ABSTRACT Most vibration-based energy harvesters, including piezoelectric harvester system, perform efficiently at only its resonant frequency as linear resonators, usually at very high frequency which are out of the range of frequency of interest. In real life applications, these linear resonators are impractical since real ambient vibrations are simply having varying lower frequencies. Hence, design a tuneable vibration energy harvester at a lower and useful frequency range of interest are essential in allowing promising energy output to meet intended power input at a more practical approach. In this paper, the piezoelectric voltage energy harvester (PVEH) was designed with a flexible fixture with the aim to reduce its first fundamental natural frequency. Two thickness of elastic fixtures were applied to generate power on PVEH. Three experimental techniques were used to measure the vibration characteristics of PVEH. First, the full-field optical technique, amplitude-fluctuation electronic speckle pattern interferometry (AF-ESPI) measured simultaneously the resonant frequencies and mode shapes. This is followed by the pointwise measurement system, laser Doppler vibrometer (LDV) in which the resonant frequencies were measured by dynamic signal swept-sine analysis. The resonant frequencies and anti-resonant frequencies were also obtained by impedance analysis. The results obtained from experimental measurements were compared with finite element numerical calculation. It is found that the boundary conditions under the elastic fixtures can effectively reduce the resonant frequency of the PVEH with a reasonable voltage output. The fundamental natural frequency of PVEH with the thickness of 0.58-mm elastic fixture is reduced to 37 Hz maintaining at 7.1 volts (1.2 mW), in comparison with the natural frequency on cantilevered PVEH at 78 Hz that produces 7.7 volts (6.5 mW).
'/%3e%3cuse xlink:href='%23a' transform='translate(0 -400)'/%3e%3cuse xlink:href='%23a' transform='translate(0 -600)'/%3e%3cuse xlink:href='%23a' transform='translate(0 -800)'/%3e%3cuse xlink:href='%23a' transform='translate(0 -1000)'/%3e%3cuse xlink:href='%23a' transform='translate(0 -1200)'/%3e%3cpath d='M0 0h1400v800H0z' style='fill:%23010066'/%3e%3cpath d='M576 100c-166.146 0-301 134.406-301 300s134.854 300 301 300c60.027 0 115.955-17.564 162.927-47.783-27.353 9.44-56.71 14.602-87.271 14.602-147.327 0-266.897-119.172-266.897-266.01 0-146.837 119.57-266.01 266.897-266.01 32.558 0 63.746 5.815 92.602 16.468C696.217 118.91 638.305 100 576 100z' style='fill:%23fc0'/%3e%3cpath d='m914.286 471.429-99.538-53.25 29.43 108.982-66.575-91.165-20.77 110.96-20.428-111.024-66.857 90.96L699.314 418l-99.701 52.943 74.065-85.192-112.8 4.441 103.694-44.62-103.555-44.94L673.8 305.42 600 220l99.538 53.25-29.43-108.982 66.575 91.165 20.77-110.96 20.428 111.023 66.857-90.959L814.97 273.43l99.702-52.944-74.065 85.193 112.8-4.441-103.694 44.62 103.555 44.94-112.785-4.79z' style='fill:%23fc0' transform='matrix(1.2738 0 0 1.2423 -89.443 -29.478)'/%3e%3c/svg%3e)
'%3e%3cpath fill='%23012169' d='M0 0v30h60V0z'/%3e%3cpath stroke='%23fff' stroke-width='6' d='m0 0 60 30m0-30L0 30'/%3e%3cpath stroke='%23C8102E' stroke-width='4' d='m0 0 60 30m0-30L0 30' clip-path='url(%23b)'/%3e%3cpath stroke='%23fff' stroke-width='10' d='M30 0v30M0 15h60'/%3e%3cpath stroke='%23C8102E' stroke-width='6' d='M30 0v30M0 15h60'/%3e%3c/g%3e%3c/svg%3e)