Visual tracking using convolutional features with sparse coding

Artificial Intelligence Review - Visual object tracking has become one of the most active research topics in computer vision, and it has been applied in several commercial...     

Speech enhancement with an adaptive Wiener filter

This paper proposes an adaptive Wiener filtering method for speech enhancement. This method depends on the adaptation of the filter transfer function from sample to sample based on the speech signal statistics; the local mean and the local variance. It is implemented in the time domain rather than in the frequency domain to accommodate for the time-varying nature of the speech signals. The proposed method is compared to the traditional frequency-domain Wiener filtering, spectral subtraction and wavelet denoising methods using different speech quality metrics. The simulation results reveal the superiority of the proposed Wiener filtering method in the case of Additive White Gaussian Noise (AWGN) as well as colored noise.     

Flexible multibody simulation using hybrid integration scheme

One issue in the dynamic simulation of flexible multibody system is poor computation efficiency, which is due to high frequency components in the solution associated with a deformable body. Standard explicit numerical methods should take very small time steps in order to satisfy the absolute stability condition for the high frequency components and, in turn, the computational efficiency deteriorates. In this study, a hybrid integration scheme is applied to solve the equations of motion of a flexible multibody system for achieving better computational efficiency. The computation times and simulation results are compared between the hybrid scheme and conventional methods. The results demonstrate that the efficiency of a flexible multibody simulation can be improved by using the hybrid scheme.     

An efficient singular value decomposition algorithm for digital audio watermarking

The singular value decomposition (SVD) mathematical technique is utilized, in this paper, for audio watermarking in time and transform domains. Firstly, the audio signal in time or an appropriate transform domain is transformed to a 2-D format. The SVD algorithm is applied on this 2-D matrix, and an image watermark is added to the matrix of singular values (SVs) with a small weight, to guarantee the possible extraction of the watermark without introducing harmful distortions to the audio signal. The transformation of the audio signal between the 1-D and 2-D formats is performed in the well-known lexicographic ordering method used in image processing. A comparison study is presented in the paper between the time and transform domains as possible hosting media for watermark embedding. Experimental results are in favor of watermark embedding in the time domain if the distortion level in the audio signal is to be kept as low as possible with a high detection probability. The proposed algorithm is utilized also for embedding chaotic encrypted watermarks to increase the level of security. Experimental results show that watermarks embedded with the proposed algorithm can survive several attacks. A segment-by-segment implementation of the proposed SVD audio watermarking algorithm is also presented to enhance the detectability of the watermark in the presence of severe attacks.     

Challenges in Liquid‐Phase Exfoliation,Processing, and Assembly of Pristine Graphene

Recent developments in the exfoliation, dispersion, and processing of pristine graphene (i.e., non‐oxidized graphene) are described. General metrics are outlined that can be used to assess the quality and processability of various “graphene” products, as well as metrics that determine the potential for industrial scale‐up. The pristine graphene production process is categorized from a chemical engineering point of view with three key steps: i) pretreatment, ii) exfoliation, and iii) separation. How pristine graphene colloidal stability is distinct from the exfoliation step and is dependent upon graphene interactions with solvents and dispersants are extensively reviewed. Finally, the challenges and opportunities of using pristine graphene as nanofillers in polymer composites, as well as as building blocks for macrostructure assemblies are summarized in the context of large‐scale production.     

Enhancing level set brain tumor segmentation using fuzzy shape prior information and deep learning

Magnetic resonance imaging (MRI) brain tumor segmentation is a crucial task for clinical treatment. However, it is challenging owing to variations in type, size, and location of tumors. In addition, anatomical variation in individuals, intensity non-uniformity, and noises adversely affect brain tumor segmentation. To address these challenges, an automatic region-based brain tumor segmentation approach is presented in this paper which combines fuzzy shape prior term and deep learning. We define a new energy function in which an Adaptively Regularized Kernel-Based Fuzzy C-Means (ARKFCM) Clustering algorithm is utilized for inferring the shape of the tumor to be embedded into the level set method. In this way, some shortcomings of traditional level set methods such as contour leakage and shrinkage have been eliminated. Moreover, a fully automated method is achieved by using U-Net to obtain the initial contour, reducing sensitivity to initial contour selection. The proposed method is validated on the BraTS 2017 benchmark dataset for brain tumor segmentation. Average values of Dice, Jaccard, Sensitivity and specificity are 0.93 ± 0.03, 0.86 ± 0.06, 0.95 ± 0.04, and 0.99 ± 0.003, respectively. Experimental results indicate that the proposed method outperforms the other state-of-the-art methods in brain tumor segmentation.     

Fabrication and electrical characterization of integrated nano-scale fluidic channels

We present the fabrication and characterization of nanoscale fluidic channels with embedded electrodes. Arrays of 2.25 μm long and 60 nm tall nanochannels with widths ranging from 60 to 500 nm were microfabricated in SiO₂ with Au electrodes embedded inside and outside of the nanochannels. The built-in electrodes were able to probe nanochannel conductance via a redox reaction of \textFe(\textCN)₆^{3 - /4 -} {\text{Fe}}({\text{CN}})_{6}^{3 - /4 - } . Amperometric characterization showed that conductance of nanochannel arrays varied linearly both with the width and number of nanochannels and was in the 10–100 pS range. Further, we show that electrical current was largely diffusion based and could be predicted from channel geometry using standard diffusion equations. We also discuss the potential of such nanochannel arrays as electronic biomolecular sensors and show preliminary streptavidin detection results.