With heart health issues attracting much attention, wearable electrocardiogram (ECG) monitoring devices show a broad market prospect. This paper develops a generic ECG pre-processing algorithm and proposes a method for the single-lead ECG classification problem based on model stacking. Features such as RR-intervals, power spectrum, and higher-order statistics are computed and grouped into three classes. The support vector machine (SVM) classifier is trained separately based on each class of features, and subsequently, a fourth SVM classifier is trained on the prediction results of the three SVM classifiers at the first layer. To obtain more realistic results and better comparisons with previous studies, the algorithm follows the ANSI/AAMI EC57:2012 standard and is tested on a real ECG database. The experimental results show that the algorithm in this paper better overcomes the impact of the data imbalance problem and obtains good results.

Crowd collaboration system, originating from cooperation among animals in nature, is composed of intelligent subjects, characterized by complex dynamic interactions, and has many applications in daily life. In the fields of psychology and computing, scientists have tried to quantify individual intelligence with performance on tasks. In this paper, we explore the main factors affecting group performance for small production factories from the perspective of intelligence. Based on the individual daily efficiency and the average process efficiency, we evaluate individual intelligence level and interaction intensity by integrating group size and efficiency difference, and thus propose crowd intelligence evaluation method. The rationality of the method is analyzed from overall group performance and change in the average individual performance. In the future, the intelligence evaluation method can be applied to more general production scenarios, and the impact of external uncertainty on the intelligence can be studied with simulation to achieve real-time and quantitative optimization of intelligence level of the crowd collaboration system.

Human society is evolving toward the future network information society. In this paper, we identify the interconnected level as the key factor driving the evolution of human society and incorporate it into our proposed evolutionary model of social formation. We show the entire process of social formation evolution at the interconnected level through theoretical analysis and simulation. Our result is consistent with what human beings have gone through. By contrast, the result presents the following four characteristics of the future network information society: the personalization of goods or services, the downsizing of enterprises or organizations, the decentralization of production or life, and the sharing of production or living tools. We regard the future network information society as a deeply interconnected “primitive society”.

When consumers make purchase decisions, they generally refer to the reviews generated by other consumers who have already purchased similar products in order to get more information. Online transaction platforms provide a highly convenient channel for consumers to generate and retrieve product reviews. In addition, consumers can also vote reviews perceived to be helpful in making their decision. However, due to diverse characteristics, consumers can have different preferences on products and reviews. Their voting behavior can be influenced by reviews and existing review votes. To explore the influence mechanism of the reviewer, the review, and the existing votes on review helpfulness, we propose three hypotheses based on the consumer perspective and perform statistical tests to verify these hypotheses with real review data from Amazon. Our empirical study indicates that review helpfulness has significant correlation and trend with reviewers, review valance, and review votes. In this paper, we also discuss the implications of our findings on consumer preference and review helpfulness.

E-commerce has grown extraordinarily since the emergence of the internet, and many types of services are employed to accelerate this process. Service quality and productivity are two critical indicators to evaluate the competitiveness of e-commerce companies. Deciding which provision mode of e-commerce services (buy, sell, or self-provide) to adopt is a key operational strategy issue. This paper investigates the conditions and limitations of e-commerce services’ optimal supply modes, and proposes a cost oriented infra-marginal model where service demand is considered an exogenous variable due to its non-elastic and unprofitable characteristics. By analyzing the main impact factors of this model, this paper infers provision mode selection strategies, which are determined by four factors: transaction cost, service price, service demand, and competitive advantages. Decision trees are derived from these strategies to help e-commerce companies make appropriate decisions. Finally, the proposed model’s feasibility is verified by two case studies.