Convolution Neural Networks (CNN) have evolved to be the state-of-art technique for machine learning tasks. However, CNNs bring a significant increase in the computation and parameter storage costs, which makes it difficult to deploy on embedded devices with limited hardware resources and a tight power budget. In recent years, people focus on reducing these overheads by compressing the CNN models, such as pruning weights and pruning filters. Compared with the method of pruning weights, the method of pruning filters does not result in sparse connectivity patterns. And it is conducive to the parallel acceleration on hardware platforms. In this paper, we proposed a new method to judge the importance of filters. In order to make the judgement more accurate, we use the standard deviation to represent the amount of information extracted by the filter. In the process of pruning, the unimportant filters can be removed directly without loss in the test accuracy. We also proposed a multilayer pruning method to avoid setting the pruning rate layer by layer. This holistic pruning method can improve the pruning efficiency. In order to verify the effectiveness of our algorithm, we do experiments with simple network VGG16 and complex networks ResNet18/34. We re-trained the pruned CNNs to compensate the accuracy loss caused by the pruning process. The results showed that our pruning method can reduce inference cost by up to 50% for VGG16 and 35% for ResNet18/34 on CIFAR10 with little accuracy loss.
Discriminative Correlation Filters based tracking algorithms exploiting conventional handcrafted features have achieved impressive results both in terms of accuracy and robustness. In this paper, to achieve an efficient tracking performance, we propose a novel visual tracking algorithm based on a complementary ensemble model with multiple features. Additionally, to improve tracking results and prevent targets drift, we introduce an effective fusion method by exploiting relative entropy to coalesce all basic response maps and get an optimal response. Furthermore, we suggest a simple but efficient update strategy to boost tracking performance. Comprehensive evaluations are conducted on two tracking benchmarks demonstrate and the experimental results demonstrate that our method is competitive with numerous state-of-the-art trackers. Our tracker achieves impressive performance with faster speed on these benchmarks.
Recently Fractional Fourier transform (FrFT) has got a variety of applications in digital signal and image processing. This paper presents a novel hardware architecture for real-time computation of Discrete Fractional Fourier Transform (DFrFT), which can easily be extended to other fractional transforms. The proposed architecture has been verified on Xilinx FPGA(XC6VLX240T), which can run at a frequency up to 291MHz while with high accuracy.
Recent researches on dynamic behavior of micro cantilevers indicate that the flexural resonance frequencies of
piezoelectric microcantilever sensors (PEMS) could be influenced by air in which it immersed as a result of viscous
damping effect, which reduces the accuracy of the PEMS. A detailed theoretical analysis of the frequency response of a
PEM immersed in air and excited by an arbitrary driving force is presented in this paper, in which the couple stress
theory (Cosserat theory) is introduced to the dynamic deflection function of a PEM to explain the size effect. Numerical
results have shown a good agreement with the experiments. Methods for prediction of dynamic characteristics of long
beam-like micro components could be easily derived based on the presented theory, which is of value to users and
designers of micro-electro-mechanical systems (MEMS).
KEYWORDS: Atomic force microscopy, Microfluidics, Silicon, Sensors, Finite element methods, Testing and analysis, Numerical simulations, Atomic force microscope, Numerical analysis, Scanning electron microscopy
Micro cantilevers in atomic force microscopy are important force sensors in nano research, and the Young's modulus is
one of the most important parameters of the cantilevers. Normal testing methods are not suitable for the Young's
modulus detecting of micro cantilevers according to the strict scale of the cantilevers, and new methods are needed to the
study of micro cantilevers. A new method for determination of Young's modulus of micro cantilevers based on
combining the numerical simulation and frequency measurements is presented in this article. The new method involves
three steps, the first step is developing the vibration model of the micro cantilever studied immersed in air; the second
step is analyzing the vibration behavior of the corresponding cantilevers with the same geometry but different Young's
modulus. The third step is measuring the resonate frequencies of the micro cantilevers immersed in viscous fluid such as
air, and comparing the experimental results with the numerical results to determine the Young's modulus of the
cantilever. Experiments on a commercial rectangular cantilever have been done to validate the method presented in this
article.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.