Cardiovascular disease is a life-threatening condition, and more than 20 million people die from heart disease. Therefore, developing an objective and efficient computeraided tool for diagnosis of heart disease has become a promising research topic. In this paper, we design a multiscale shared convolution kernel model. In this model, two paths are designed to extract the features of electrocardiogram(ECG). The two paths have different convolution kernel sizes, which are 3×1 and 5×1 , respectively. Such multi-scale design enables the network to obtain different receptive fields and capture information at different scales, which significantly improves the classification effect. And squeeze-and-excitation networks (SE-Net) are added to every path of the model. The attention mechanism of SE-Net learns feature weights according to loss, which makes the effective feature maps have large weights and the ineffective or low-effect feature maps have small weights. Our team name is CQUPT_ECG. Our approach achieved a challenge validation score of 0.640, and full test score of 0.411, placing us 8 out of 41 in the official ranking.

No abstract

Minimum variance distortionless response (MVDR) beamformer is an adaptive beamforming technique that provides a method for separating the desired signal from interfering signals. Unfortunately, the MVDR beamformer may have unacceptably low nulling level and high sidelobes, which may lead to significant performance degradation in the case of unexpected interfering signals such as the rapidly moving jammer environments. Via support vector machine regression (SVR), a novel beamforming algorithm (named as SVR-CMT algorithm) is presented for controlling the sidelobes and the nullling level. In the proposed method, firstly, the covariance matrix is tapered based on Mailloux covariance matrix taper (CMT) procedure to broaden the width of nulls for interference signals. Secondly, the equality constraints are modified into inequality constraints to control the sidelobe level. By the ε-insensitive loss function for the sidelobe controller, the modified beamforming optimization problem is formulated as a standard SVR problem so that the weight vector can be obtained effectively. Compared with the previous works, the proposed SVR-CMT method provides better beamforming performance. For instance, (1) it can effectively control the sidelobe and nullling level, (2) it can improve the output signal-to-interference-and-noise ratio (SINR) performance even if the direction-of-arrival (DOA) errors exist. Simulation results demonstrate the efficiency of the presented approach.

A system dynamics model of urban sustainable development is provided, and the impact of different development modes on the city system is explored. Statistical data of Yinchuan, a city in northwest China, is utilized to build the model which shows the population-economy- environment relationship. Four development modes are proposed, and they are maintaining the status quo, developing secondary industry, developing tertiary industry, developing economy and society together. The system dynamics model is employed to analyze the interaction between population, economy and environment. According to simulation of the system dynamics model, impact of development modes on the city system is predicted. Furthermore, suggestions on improving the sustainability of urban development are put forward. In a word, the paper presents a new idea for the study on urban sustainable development in northwest China.

No abstract