2020/1

Browse

Now showing 1 - 5 of 30

Reliable Estimation of the Intra-Voxel Incoherent Motion Parameters of Brain Diffusion Imaging Using θ-Teaching-Learning-Based Optimization
(Společnost pro radioelektronické inženýrství, 2020-04) Ghassemi, Afrooz; Kazemi, Kamran; Sefidbakht, Sepideh; Danyali, Habibollah
Intra-voxel incoherent motion (IVIM) imaging can characterize diffusion and perfusion of tissues. Traditionally, the least-square method has been used to determine IVIM parameters consisting of pure diffusion coefficient (D), pseudo-diffusion coefficient (D*) and the micro-vascular volume fraction (f). This paper proposes an accurate estimation method for IVIM parameters in human brain tissues using θ-teaching-learning-based-optimization (θ-TLBO). θ-TLBO as an evolutionary algorithm provides high quality solutions for parameter estimations in curve fitting problems. Evaluation of the proposed method was performed on simulated data with different levels of noise and experimental data. The estimated parameters were compared with the results of TLBO and three conventional algorithms: Segmented-Unconstrained (“SU”), Segmented-Constrained (“SC”) and “Full”. The results show that the proposed θ-TLBO has higher accuracy, precision and robustness than other methods in estimating parameters of simulated and experimental data in human brain images especially in low SNR images according to analysis of variance (ANOVA), coefficient of variation (CV), relative bias and relative root mean square errors.
Automatic Image Matting of Synthetic Aperture Radar Target Chips
(Společnost pro radioelektronické inženýrství, 2020-04) Amin, Benish; Riaz, M. Mohsin; Ghafoor, Abdul
A matting technique to extract the targets from synthetic aperture radar (SAR) images is presented. Binary segmentation is performed initially for rough identification of target boundaries. Trimap is then estimated by combining the boundary structures of the input and segmented images using guided filter. In order to improve the accuracy of estimated trimap, super-pixels based segmentation is performed. A propagation based matting algorithm is then applied to separate the target from non-target region. Simulations conducted on different SAR images from MSTAR database show significance of proposed technique.
Facial Expression Recognition Based on Multi-dataset Neural Network
(Společnost pro radioelektronické inženýrství, 2020-04) Yang, Bin; Li, Zhenyu; Cao, Enguo
Facial activity is the most powerful and natural means for understanding emotional expression for humans. Recent years, extensive efforts have been devoted to facial expression recognition by using neural networks. However, automated emotion recognition in the wild from facial images remains a challenging problem. In this paper, an effective facial expression recognition scheme is proposed. A multi-dataset neural network is developed to learn facial expression features in several different but related datasets. The novel multi-dataset network fuses the intermediate layers of a deep convolutional neural network (CNN) by using separate CNNs and a multi-dataset loss function. Experimental results performed on emotion database demonstrate that our proposed method outperforms state-of-the-art.
Efficiency of Supervised Machine Learning Algorithms in Regular and Encrypted VoIP Classification within NFV Environment
(Společnost pro radioelektronické inženýrství, 2020-04) Ilievski, Gjorgji; Latkoski, Pero
Cloudification of all computing environments is an undergoing process. The process has overpassed the classical Virtual Machines (VM) and Software-Defined Networking (SDN) approach and has moved towards dockerizing, microservices, app functions, network functions etc. 5G penetration is another trend, and it is built on such platforms. In this environment we are investigating the efficiency of supervised machine learning algorithms for classification of regular and encrypted Voice over IP (VoIP) traffic that 5G relies on, within a virtualized Network Functions Virtualization (NFV) environment and an east-west based network traffic. We are using statistical methods for classification of network packets without the need of inspecting the payload data and without the source, destination and port information of the packets. The efficiency is analyzed from a point of precision of the classification, but also from a point of time consumption, as adding delay to the original traffic may cause a problem, especially within 5G environments where packet delay is crucial.
DAB+ Network Implementation in the Czech Republic and Impact of the Audio Coding on Subjective Perception of Sound Quality
(Společnost pro radioelektronické inženýrství, 2020-04) Zyka, Karel
Digital Audio Broadcasting (DAB+) is becoming a reality in the Czech Republic. The first nationwide DAB+ network, based on the regular broadcasting, is being completed. This paper presents the principles that were used to achieve a quick and efficient penetration of the DAB+ signal in the Czech population and the highways. Attention is focused on practical experience with the use of High-Efficiency Advanced Audio Coding (HE-AAC) emphasizing maximum efficiency of the multiplex. This is done with respect to the subjective perception of sound quality by the audience. Final audio processing and appropriate signal pre-processing are considered. The paper also focuses on how to use Forward Error Correction (FEC) coding to increase the reach of transmitters and the reasons for employing the specific transmitter network configuration, including indoor reception. The results of this complex method are demonstrated on the network rollout in particular periods, while the key assumptions were verified. The entire development process can be monitored on the maps of coverage.

Browse

Recent Submissions