The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Ensemble clustering is to fuse several basic partitions to find a single best cluster structure of data. With the prevalence of heterogeneous data rising from various application domains, ensemble clustering has become a state-of-the-art solution for cluster analysis due to its robustness and generalizability. However in the area of fuzzy systems, systematic research along this line is still in its...
Stock market prediction has attracted much attention from academia as well as business. However, it is a challenging research topic, in which many advanced computational methods have been proposed, but not yet attained a desirable and reliable performance. This study proposes a new method for stock market prediction, which adopts the Long Short-Term Memory (LSTM) neural network and incorporates investor...
Recommendation system becomes popular in recent years, because it provides more information about products which consumers are more likely to be interested in. However, bundling module, as one way of recommendations, does not appear on any product's page. In this paper, we will explore the impact of product characteristics on the bundling strategy implemented by recommendation system. We found that...
Effectively identifying the potential risk sources in the emergency process of the petroleum storage and transportation is the key to realize the essential safety design of the whole life cycle of petroleum products. In this paper, from the perspective of emergency process safety, the risk source identification method in the emergency process is discussed. For the accident occurred, based on the event...
Membrane computing also called P system, seeks to discover new computational models from the study of cellular membranes. In this study, we reported our initial efforts to classify Macao visitor expenditure profile using a membrane computing approach. Specifically, we designed a novel P system including specific membrane structure and membrane rules to realize an improved k-medoids clustering algorithm...
Sentiment analysis is an important task in natural language processing, which has promises great value to areas of interests such as business, politics and other fields. The prevalence of the internet has caused people to prefer expressing their opinion and sentiment on the Internet via methods such as tweeting on social media and commenting on products. However, the discourse of users on social media...
With more attention to environmental issues, tradeable carbon emission permits become a new type of firm's business resource. Many firms take emission permits into consideration in the original raw materials-products (services) production process when making operational decisions. Therefore, based on carbon emission permits trading, this paper studies the emission reduction decision for firms along...
This paper constructs a two-tier supply chain consisting of one brand-owner and the one electronic commerce company. The brand-owner has strategic decision ability to decide when and how to introduce electronic platform to sell products. We discuss brand-owner's pricing decisions in three models based on fixed pricing strategy or dynamic pricing strategy. We find some interesting conclusions: i)....
Accompany with the growth of Sina-Weibo users, mendacious Bot users also emerge, which lead to network environment pollution and lower management efficiency. This paper focuses on Sina-Weibo users, extracts the effective features of Bot user through behavior analysis and features study. Then based these features, Bot user identification model is trained by machine learning process and model performance...
According to annual list of the top 250/225 international contractors published by Engineering News-Record(ENR) from 2007 to 2016, the paper filters thousands of data related to power engineering contract. On this basis, the business scale, growth rate and changing trend of international power engineering contract market are first analyzed. Then, with the introduction of a series of indicators, such...
From operations management's point of view, the nature of business models is the tool for knowing data, processing data and extracting value from data. Recently many studies advocate big data research which one common object to bring in intelligence from the huge amount of data. Nevertheless, owing to the characteristics of unstructured data, extracting the value in the big data still requires further...
The reliability of a product is not only important for customers to choose optimal products, but also necessary for manufacturers to design warranty strategies. While predicting the reliability of products accurately is always difficult. Several arithmetic was developed in the existed literature, such as Poisson models, Kalman filter etc. However, these methods hypotheses the distribution of the model,...
Friend recommendation service is a common and important demand for the users on various online platforms. Current studies mainly focus on making predictions with the neighborhood and path information derived from the personal relationship networks. However, the formed links do not indicate that two users are familiar with each other nor have intimate connections. Selective treatments are made according...
With the K-means clustering and Logistic model, we forecasted the carbon emissions in 30 provinces and autonomous regions in China from 2014 to 2023 based on the data of 30 provinces from 2005 to 2013. First, 5 indicators were selected, which include GDP, urbanization rate, the proportion of the second industry, the energy efficiency and the carbon emission intensity. Secondly, K-means cluster analysis...
The adjustment of global power structure will have effects on business model of power contracting service industry. According to the research scheme of “characteristic analysis-current situation analysis-mode selection” firstly, we adopt concentration rate index to summarize market characteristics. Then, to clarify current situation of power market development, it analyzes the influencing factors...
As more and more companies become aware of the benefits of collecting and analyzing data, hiring employee with data analytics expertise is a key issue faced by HR practitioners. Although previous research empirically highlighted the differences of knowledge and skill requirements between big data (BD) and business intelligence (BI) in English-speaking countries, limited similar study is conducted...
This paper mainly studies on how to distribute the blood items among different departments within a hospital. The improper allocation of blood in hospital at present could cause severe shortage and wastage of blood resource, which may endanger patient's lives and impose considerable costs on hospital. In order to solve this problem, we investigate the novel allocation method by centralizing the blood...
Service characteristic of invisibility, heterogeneity, concurrency, which increases the chance of failures, existing research thinks that good customer relationship can influence customer behavior after the service failure, ease service failure loss, but there are also study points out the customer relationship will strengthen negative reaction of service failure. Based on two-dimensional construct...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.