Search

The brain is an energy-consuming organ that heavily relies on the heart for energy supply. Heart abnormalities detected by electrocardiogram (ECG) might provide diagnostic indicators for brain dysfunctions such as stroke. Diagnosis of brain diseases by ECG requires proficient domain knowledge, which is both time and labor consuming. Deep learning is capable of constructing a nonlinear correlation between ECG and stroke without prior expert knowledge. Here, we propose a data-driven classifier-Dense convolutional neural Network (DenseNet) for stroke prediction based on 12-leads ECG data. With our finely-tuned model, we obtain the training accuracy of 99.99% and the prediction accuracy of 85.82%. To our knowledge, this is the first report studying the correlation between stroke and ECG with the aid of deep learning. The results indicate that ECG is a valuable complementary technique for stroke diagnostics.

In recent years, with the vigorous development of the Internet and multimedia technology, the application of Computer-assisted Instruction (CAI) in education has become more and more extensive. The use of new media and new technology to strengthen aerobics teaching and education can activate the classroom atmosphere on the premise of improving the quality of teaching, and it is self-evident to the importance of aerobics teaching. The purpose of this article is to study the application and design of CAI system in aerobics teaching. This article firstly analyzes the functional and non-functional requirements of the CAI system in the teaching of aerobics from the method of teaching needs. Then the system design of the administrator subsystem, the teacher subsystem and the student subsystem in the functional design of the system modules are carried out, and the feasibility and reliability of the system are determined through the function and performance test of the system. Finally, through observation method and questionnaire survey method, the two classes of CAI and traditional teaching are analyzed systematically. Survey data shows that about 90% of students in CAI classes are focused, while only 70% of students in traditional teaching classes are focused; traditional teaching classes account for 21% of participants, while CAI participation is about 42%. It shows that CAI is generally better than traditional teaching in terms of students' classroom performance.

With the rapid development of the express delivery industry, the environmental issues of express packaging waste (EPW) have gradually attracted public attention worldwide. As important participants, consumers' behaviors and attitudes will play a vital role in solving the problem. This study uses the conditional value method (CVM) to evaluate the differences in the attitudes and willingness to pay of urban and rural residents toward EPW in Guangdong Province, China. The results show that the respondents have limited knowledge of the recycling situation, relevant policies and environmental impacts of express delivery packaging, although more than 60% of respondents do think that there is a problem with excessive packaging. The low recycling rate for packaging materials is mainly attributed to the lack of recycling facilities and publicity on environmental issues. The differences between urban and rural residents are mainly over disposal methods, the views on excessive packaging and willingness to pay (WTP) for EPW. Finally, the WTP values of urban and rural residents choosing a “deposit” system are 1.58 ($0.24) and 1.79 yuan ($0.28) per piece, respectively, while the WTP values (for increased fees) are 0.64 yuan ($0.10) and 0.60 yuan ($0.09) per piece, respectively. The obtained results may serve as a reference for different regional responses to the promotion and improvement of EPW management in the future.

This paper presents a novel dataset for hand gesture estimation. As we know, there lacks a well-designed hand gesture database so far, which greatly impedes the development of distinctive hand gesture estimation. In order to facilitate the research of hand gesture estimation, we build a new dataset of hand gestures. Our dataset contains about 5K labeled and 1K unlabeled single hand images. All the images are separated into 50 varieties according to the types of hand gestures. For each type of hand gesture, occlusion, light, shadow and background are all considered. We hope that the novel dataset would promote the development of distinctive hand gesture estimation from images.

Objective Ethanol treatment induces an increase in oxidative stress. As licorice compounds are potent antioxidants, our aim was to examine whether magnesium isoglycyrrhizinate attenuated lipid peroxidation, the major end-point of oxidative damage resulting from ethanol administration. Methods Four groups(18 animals in each group) of male Kunming mice were used. The first group served as control and received 0.4 ml normal saline daily for 18 days orally. The second group of mice was given 56% ethanol at 16 ml/kg body weight per day for 18 days orally. The third group was given the same dose of ethanol and administrated magnesium isoglycyrrhizinate (15 mg/kg.d, i.p.) for 18 days. The fourth group was given the same dose of ethanol and administrated with magnesium isoglycyrrhizinate (45 mg/kg.d, i.p.) for 18 days. Twenty four hours after 9 days or 18 days of treatment the mice were sacrificed using 10% chloral hydrate. Sperm counts and motility in the epididymis were assessed. The lipid peroxidation and antioxidants of testicular mitochondria were also determined. The pathological changes of testicle tissue of the mice were observed by light microscopy. Results Magnesium isoglycyrrhizinate effectively prevented the ethanol-induced seminiferous epithelium disorganization and degeneration of Sertoli cells and germ cells. Sperm counts and motility of the magnesium isoglycyrrhizinate treated groups were higher than those of the alcohol treated group, but were lower than those of the control group. The drug exhibited an ability to counteract ethanol induced oxidative challenge as it effectively reduced testicular malondialdehyde (MDA) and increased the activities of superoxide dismutase and glutathione peroxidase. Conclusion Magnesium isoglycyrrhizinate is able to inhibit the ethanol-induced lipid peroxidation and has a protective effect against testicular oxidative injury.

The conventional mathematic model of PV (Photovoltaic) cells contains logarithmic terms, which is not conducive to derivation calculation in small-signal modeling. The parameters of PV system are coupling due to its double-loop control method, and it's hard to precisely choose controller parameters. To solve these two problems above, this paper is based on PV system connected to an infinite power grid, uses the linear-fitting model of PV cells which is conducive to derivation instead of the original engineering one in small-signal modeling, and analyses the small-signal stability of the entire system. Meanwhile, a global-planning design for controller parameters is proposed to globally provide the optimal controller parameters. Simulation results show that the linear-fitting model of PV cells is very similar to the original engineering one, and the proposed design for controller parameters can provide a solution to calculate the global optimization.

Heterogeneous network (HetNet) has been studied as a promising technology to boost the system throughput. A new upper boundary of coverage probability (CP) is derived, which is the one of cooperative communication between two base stations (BSs) for downlink HetNet. For the tractability, only the cooperation between two base stations in the same tier of HetNet is considered and a model is set up, in which each randomly chosen user located in the cooperation zones can communicate with at most one couple of BSs, due to the threshold of Signal-to-Interference-Ratio (SIR). Stochastic geometry theory is used to establish the model of HetNet. Simulation results show that the upper boundary of CP for cooperative communication between two BSs in the same tier is decreasing when the SIR threshold for macrocell tier is increasing. The increasing density of low power BSs can increase the performance of cooperative communication in the same tier, as well as reducing the cooperative SIR threshold for low power BSs tier.

The relationship of the weighted mean temperature and the surface temperature was obtained using the radiosonde observation in Anqing from 2004 to 2007. The weighted mean temperature estimated from the regressed formula is higher than that from the Bevis formula when the surface temperature increases, which introduces the difference of approximate 1.9% of the GPS precipitable water vapor when the surface temperature gets to 40degC, and smaller difference in the lower surface temperature. The different regressions between different years induce the difference of 0.72% of the GPS PWV when the surface temperature reaches 40degC, and the difference of 2.17% of the GPS PWV in the surface temperature of -10degC. It suggests that the regressed formula to estimate the weighted mean temperature will be beneficial for the estimation of the GPS PWV in the summer, while it has little positive impact on the estimation in the winter.