Aijun Liu

FEATURE EXTRACTION OF BRAIN MRI BY STATIONARY WAVELET TRANSFORM AND ITS APPLICATIONS

Wavelet transform is widely used in feature extraction of magnetic resonance imaging. However, the traditional discrete wavelet transform (DWT) suffers from translation variant property, which may extract significantly different features from two images of the same subject with only slight movement. In order to solve this problem, this paper utilizes stationary wavelet transform (SWT) to extract features instead of DWT. Experiments on a normal brain MRI demonstrate that wavelet coefficients via SWT are superior to those via DWT, in terms of translation invariant property. In addition, we applied SWT to normal and abnormal brain classification. The results demonstrate that SWT-based classifier is more accurate than that of DWT.

Application of stationary wavelet entropy in pathological brain detection

Labeling brain images as healthy or pathological cases is an important procedure for medical diagnosis. Therefore, we proposed a novel image feature, stationary wavelet entropy (SWE), to extract brain image features. Meanwhile, we replaced the feature extraction procedure in state-of-the-art approaches with the proposed SWE. We found the classification performance improved after replacing wavelet entropy (WE), wavelet energy (WN), and discrete wavelet transform (DWT) with the proposed SWE. This proposed SWE is superior to WE, WN, and DWT.

Abnormal Breast Detection in Mammogram Images by Feed-forward Neural Network Trained by Jaya Algorithm

(Aim) Abnormal breast can be diagnosed using the digital mammography. Traditional manual interpretation method cannot yield high accuracy. (Method) In this study, we proposed a novel computer-aided diagnosis system for detecting abnormal breasts in mammogram images. First, we segmented the region-of-interest. Next, the weighted-type fractional Fourier transform (WFRFT) was employed to obtain the unified time-frequency spectrum. Third, principal component analysis (PCA) was introduced and used to reduce the spectrum to only 18 principal components. Fourth, feed-forward neural network (FNN) was utilized to generate the classifier. Finally, a novel algorithm-specific parameter free approach, Jaya, was employed to train the classifier. (Results) Our proposed WFRFT + PCA + Jaya-FNN achieved sensitivity of 92.26%±3.44%, specificity of 92.28%±3.58%, and accuracy of 92.27%±3.49%. (Conclusions) The proposed CAD system is effective in detecting abnormal breasts and performs better than 5 state-of-the-art systems. Besides, Jaya is more effective in training FNN than BP, MBP, GA, SA, and PSO. ∗Address for correspondence: Jiangsu Key Laboratory of 3D, Printing Equipment and Manufacturing, Nanjing, Jiangsu 210042, China 192 S. Wang et al. / Abnormal Breast Detection in Mammogram Images by Feed-forward Neural Network Trained

CRC Code Design for List Decoding of Polar Codes

Cyclic redundancy check (CRC) assisted list successive cancellation decoding (SCLD) makes polar codes competitive with the state-of-art codes. In this letter, we try to find the optimal CRC for polar codes to further improve its performance. We first analyze the undetected error probability of CRC-aided SCLD as well as the characteristics of Hamming weight distribution of polar codes. Based on these characteristics, a multilevel SCLD-based searching strategy with moderate list size is proposed to compute the minimum Hamming weight distribution (MHWD) of different CRC-concatenated polar codes. Using the searched MHWD, the optimal CRC for polar codes are presented in this letter. Simulation results show that the performance of optimal CRC-aided SCLD significantly outperforms the standard one, especially at high code rate.

A Novel Compressed Sensing Method for Magnetic Resonance Imaging: Exponential Wavelet Iterative Shrinkage-Thresholding Algorithm with Random Shift

Aim. It can help improve the hospital throughput to accelerate magnetic resonance imaging (MRI) scanning. Patients will benefit from less waiting time. Task. In the last decade, various rapid MRI techniques on the basis of compressed sensing (CS) were proposed. However, both computation time and reconstruction quality of traditional CS-MRI did not meet the requirement of clinical use. Method. In this study, a novel method was proposed with the name of exponential wavelet iterative shrinkage-thresholding algorithm with random shift (abbreviated as EWISTARS). It is composed of three successful components: (i) exponential wavelet transform, (ii) iterative shrinkage-thresholding algorithm, and (iii) random shift. Results. Experimental results validated that, compared to state-of-the-art approaches, EWISTARS obtained the least mean absolute error, the least mean-squared error, and the highest peak signal-to-noise ratio. Conclusion. EWISTARS is superior to state-of-the-art approaches.

Tea Category Identification using Computer Vision and Generalized Eigenvalue Proximal SVM

(Objective) In order to increase classification accuracy of tea-category identification (TCI) system, this paper proposed a novel approach. (Method) The proposed methods first extracted 64 color histogram to obtain color information, and 16 wavelet packet entropy to obtain the texture information. With the aim of reducing the 80 features, principal component analysis was harnessed. The reduced features were used as input to generalized eigenvalue proximal support vector machine (GEPSVM). Winner-takes-all (WTA) was used to handle the multiclass problem. Two kernels were tested, linear kernel and Radial basis function (RBF) kernel. Ten repetitions of 10-fold stratified cross validation technique were used to estimate the out-of-sample errors. We named our method as GEPSVM + RBF + WTA and GEPSVM + WTA. (Result) The results showed that PCA reduced the 80 features to merely five with explaining 99.90% of total variance. The recall rate of GEPSVM + RBF + WTA achieved the highest overall recall rate of 97.9%. (Conclusion) This was higher than the result of GEPSVM + WTA and other five state-of-the-art algorithms: back propagation neural network, RBF support vector machine, genetic neural-network, linear discriminant analysis, and fitness-scaling chaotic artificial bee colony artificial neural network. ∗Address for correspondence: School of Electronic Science and Engineering, Nanjing University, Nanjing, Jiangsu 210046, China 326 S. Wang et al. / Tea Category Identification using CV and GEPSVM

A Practical Construction Method for Polar Codes

In this paper, a practical construction method is proposed for polar codes over binary-input channels. Unlike the existing construction methods, we use a Bhattacharyya parameter bound to select the bit-channels over which the information bits are transmitted. We first derive the expression of the Bhattacharyya parameter bound, and introduce a method to achieve its exact value. Then, we present our construction method for different binary-input channels. Numerical results show that, the achievable rate of our method approaches the theoretical value, and its performance is better than that of some existing methods, while the complexity is O(N log N) (N is codeword length), which indicates its effectiveness.

Novel Two-Phase Approach for Process Optimization of Customer Collaborative Design Based on Fuzzy-QFD and DSM

In response to fast-growing and rapidly changing global markets, launching new products faster than competitors does not only assist enterprises in acquiring a larger market share, but also in reducing development lead time. However, owing to the intrinsically uncertain properties of new product development management, manufacturing companies often struggle with the dilemma of whether to increase product variety or control manufacturing complexity. This paper proposes a novel two-phase method to assist an enterprise in achieving a customer collaborative product design. In the first phase, quality function deployment, which is based on fuzzy multicriteria decision making and suppliers’ budget constraints, is presented to maximize customers’ satisfaction. In the second phase, an effective approach is proposed to determine the appropriate sequence of several coupled activities with the minimum total feedback time in a design structure matrix. Finally, a real case is used to illustrate the overall applicability of the approach. The optimization results show the effectiveness and superiority of the proposed method over other reported methods in the literature.

Scheduling optimization of task allocation in integrated manufacturing system based on task decomposition

How to deal with the collaboration between task decomposition and task scheduling is the key problem of the integrated manufacturing system for complex products. With the development of manufacturing technology, we can probe a new way to solve this problem. Firstly, a new method for task granularity quantitative analysis is put forward, which can precisely evaluate the task granularity of complex product cooperation workflow in the integrated manufacturing system, on the above basis; this method is used to guide the coarse-grained task decomposition and recombine the subtasks with low cohesion coefficient. Then, a multi-objective optimieation model and an algorithm are set up for the scheduling optimization of task scheduling. Finally, the application feasibility of the model and algorithm is ultimately validated through an application case study.

Optimization of Power Allocation for Multiusers in Multi-Spot-Beam Satellite Communication Systems

In recent years, multi-spot-beam satellite communication systems have played a key role in global seamless communication. However, satellite power resources are scarce and expensive, due to the limitations of satellite platform. Therefore, this paper proposes optimizing the power allocation of each user in order to improve the power utilization efficiency. Initially the capacity allocated to each user is calculated according to the satellite link budget equations, which can be achieved in the practical satellite communication systems. The problem of power allocation is then formulated as a convex optimization, taking account of a trade-off between the maximization of the total system capacity and the fairness of power allocation amongst the users. Finally, an iterative algorithm based on the duality theory is proposed to obtain the optimal solution to the optimization. Compared with the traditional uniform resource allocation or proportional resource allocation algorithms, the proposed optimal power allocation algorithm improves the fairness of power allocation amongst the users. Moreover, the computational complexity of the proposed algorithm is linear with both the numbers of the spot beams and users. As a result, the proposed power allocation algorithm is easy to be implemented in practice.