Automatic detection of breast cancers in mammograms using structured support vector machines

Breast cancer is one of the most common cancers diagnosed in women. Large margin classifiers like the support vector machine (SVM) have been reported effective in computer-assisted diagnosis systems for breast cancers. However, since the separating hyperplane determination exclusively relies on support vectors, the SVM is essentially a local classifier and its performance can be further improved. In this work, we introduce a structured SVM model to determine if each mammographic region is normal or cancerous by considering the cluster structures in the training set. The optimization problem in this new model can be solved efficiently by being formulated as one second order cone programming problem. Experimental evaluation is performed on the Digital Database for Screening Mammography (DDSM) dataset. Various types of features, including curvilinear features, texture features, Gabor features, and multi-resolution features, are extracted from the sample images. We then select the salient features using the recursive feature elimination algorithm. The structured SVM achieves better detection performance compared with a well-tested SVM classifier in terms of the area under the ROC curve.     

Analysis of application patterns of Z-type MEMS microspring

In this paper, we design a Z-type microspring, which consists of several “Z” type micromechanical beams within mutual connection. With good mechanical performance and mature LIGA fabrication technology, Ni is chosen as the material of Z-type MEMS microspring. The mechanical properties of electroformed Ni have been tested by the Micro Hardness Tester, and the Young’s modulus is 219 GPa. Different from traditional springs, microsprings can be divided into three application patterns in direction x, y, and z to study. Applying the Castigliano second theorem of energy method in macro theory, the formulas used to calculate the spring constant of Z-type microspring in the directions of the three application patterns were derived, and verified by the ANSYS finite element method. Using the Tytron250 micro force test machine, the experiments of the Z-type microspring deformation properties were carried out. The spring constant, rupture force and rupture strength of Z-type microspring in direction y are 3821 N/m, 1.64 N and 1.61 GPa, respectively. The experimental results agree with the theoretical analysis. Based on the analysis above, the change laws of the spring constant of microspring in the three application patterns are summarized.     

Picture or it didn’t happen: catch the truth for events

Multimedia Tools and Applications - Pictures spreading on the Internet are essential for the authenticity of events. Each day, huge amounts of data are published on social media, and many of them...     

基于跳频和同步捕获技术的水下无线通信技术研究

本文所阐述的水下无线技术即基于跳频技术和同步捕获技术的水声通信,由于声波在海水中的传播特性显著优越于电磁波和可见光,使得水声技术成为海洋高技术的主要研究领域之一 ,在国防领域也具有十分重要的研究意义.本文主要论述了水声通信中跳频技术和同步捕获技术的原理、具体算法的实现方案以及部分硬件设施的使用简述,并通过展示实验结果验证算法的可行性.     

Real time 3D simulation for nose surgery and automatic individual prosthesis design

This paper presents an intuitive nose surgery planning and simulation system, using 3D laser scan image and lateral X-ray image, to provide high quality prediction of the postoperative appearance, and design the patient specific prosthesis model automatically. After initial registration, the internal surface of soft tissue at the nose region was generated by the statistical data for soft tissue thickness adapted by the individual thickness information from the X-ray image. Then, the sketch contour of the 3D scan data on the lateral X-ray image was modified manually or adjusted automatically according to some aesthetic statistical data, to drive the simulation in real time by the state-of-the-art Laplacian surface deformation method. When satisfied with the 3D postoperative appearance, the deformation was mapped to the internal surface of soft tissue, and the change before and after simulation was utilized to generate the patient specific prosthesis model automatically. The surgeons who used the system confirmed that this planning system is attractive and has potential for daily clinical practice.     

基于Hypermesh的车架结构模态分析

应用Hypermesh分析某中型载货汽车车架的固有频率,验证与外部激励发生共振的可能性,同时得出分析结论。     

Blind Source Extraction for Noisy Mixtures by Combining Gaussian Moments and Generalized Autocorrelations

In the blind source extraction problem, the concept of generalized autocorrelations has been successfully used when the desired signal has special temporal structures. However, their applications are only limited to noise-free mixtures, which is not realistic. Therefore, this paper addresses the extraction of the noisy model based on these temporal characteristics of sources. An objective function, which combines Gaussian moments and generalized autocorrelations, is proposed. Maximizing this objective function, we present a blind source extraction algorithm for noisy mixtures. Simulations on synthesized signals, images, artificial electrocardiogram (ECG) data and the real-world ECG data show the better performance of the proposed algorithm. Moreover, comparisons with the existing algorithms further indicate its validity and also show its robustness to the estimated error of time delay.     

Cross-Layer Optimization for State Update in Mobile Gaming

In a large-scale mobile gaming environment with limited wireless network bandwidth, efficient mechanisms for state update are crucial to allow graceful real-time interaction for a large number of players. By using the state updating threshold as a key parameter that bridges the resulting state distortion and the network traffic, we are able to study the fundamental traffic-distortion tradeoffs via both theoretical modeling and numerical analysis using real game traces. We consider a WiMAX link model, where the bandwidth allocation is driven by the underlying physical layer link quality as well as application layer gaming behaviors. Such a cross-layer optimization problem can be solved using standard convex programming techniques. By exploring the temporal locality of gaming behavior, we also propose a prediction method for on-line bandwidth adaptation. Using real data traces from a multiplayer driving game, TORCS, the proposed network-aware bandwidth allocation method (NABA) is able to achieve significant reduction in state distortion compared to two baselines: uniform and proportional policies.     

Robust tracking control design for uncertain robotic systems with persistent bounded disturbances

In this study, a robust nonlinear L_∞‐gain tracking control design for uncertain robotic systems is proposed under persistent bounded disturbances. The design objective is that the peak of the tracking error in time domain must be as small as possible under persistent bounded disturbances. Since the nonlinear L_∞ ‐gain optimal tracking control cannot be solved directly, the nonlinear L_∞ ‐gain optimal tracking problem is transformed into a nonlinear L_∞ ‐gain tracking problem by given a prescribed disturbance attenuation level for the L_∞ ‐gain tracking performance. To guarantee that the L_∞ ‐gain tracking performance can be achieved for the uncertain robotic systems, a sliding‐mode scheme is introduced to eliminate the effect of the parameter uncertainties. By virtue of the skew‐symmetric property of the robotic systems, sufficient conditions are developed for solving the robust L_∞ ‐gain tracking control problems in terms of an algebraic equation instead of a differential equation. The proposed method is simple and the algebraic equation can be solved analytically. Therefore, the proposed robust L_∞ ‐gain tracking control scheme is suitable for practical control design of uncertain robotic systems. Copyright © 2008 John Wiley and Sons Asia Pte Ltd and Chinese Automatic Control Society