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.
Learning of prediction error (PE), including reward PE and risk PE, is crucial for updating the prediction in reinforcement learning (RL). Neurobiological and computational models of RL have reported extensive brain activations related to PE. However, the occurrence of PE does not necessarily predict updating the prediction, e.g., in a probability-known event. Therefore, the brain regions specifically...
In this paper, we propose the first deep reinforce-ment learning framework to estimate the optimal Dynamic Treat-ment Regimes from observational medical data. This framework is more flexible and adaptive for high dimensional action and state spaces than existing reinforcement learning methods to model real life complexity in heterogeneous disease progression and treatment choices, with the goal to...
In this paper, we present a possible fusion of rough sets and multiple soft sets. According to the theory of soft rough sets we propose the concepts of the multi-granularity soft rough sets (MGSR-sets) and multi-granularity soft approximation space. Based on these, we consider the multi-granularity soft rough approximation operators and discuss some important properties of them by some illustrative...
Aiming at the interval rough numbers of multiple attribute decision making (MADM) problems, a method of ranking interval rough numbers based on possibility degree is proposed. First, the deviation degree for interval rough numbers is given, and then an optimal model with maximum deviation to solve the attribute weights is set up. Second, a possibility degree formula of interval rough numbers is proposed...
HIV related stigma is regarded as one of the major barriers that prevent PLWHA from returning back to normal life. The current study builds on previous research regarding barriers to employment among PLWHA by investigating the role of perceived incompetence in addition to the fear of contagion from the viewpoint of employers in charge of recruiting new employees, which is crucial in verifying the...
The traditional Chinese medicine industry is a field that has unique advantage and national characteristics in the industrial field of our country. The evaluation of the enterprise core competence plays an important role in the rapid development of the traditional Chinese medicine industry. In this paper, a comprehensive evaluation model of the Chinese medicine enterprise core competence is proposed...
With economic globalization and the rapid development of e-commerce, customer relationship management (CRM) has become the core of growth of the company. Data mining, as a powerful data analysis tool, extracts critical information supporting the company to make better decisions by processing a large number of data in commercial databases. This paper introduced the basic concepts of data mining and...
The execution process is critical to the success of a software outsourcing service. It defines the major roles and activities involved in delivering the outsourced software. This paper presents a process-oriented software outsourcing decision approach, which helps a client selecting appropriate vendors and defining the execution process that both the client and the vendors should comply with during...
For the situation that urban emergency system needs to handle a large number of implicit and vague knowledge, this paper applies BP Neural Network to urban Emergency System, presents the system architecture of urban Emergency System which included neural network, and implements a specific application that determining the public emergency rank based on BP neural network. The method brings some new...
Developing product family is one of the most promising approaches in the mass customization paradigm. In the product family perspective, the understanding of product family metrics and modeling is crucial for decision support and analysis. Most of the current product family modeling representation is meant solely for physical product configuration. Therefore, the current product family modeling approaches...
At the knowledge-based economy age, technological innovation is promoting the reform of global economy and society by a revolutionary mode, its profound influence reflects in the process of development of global economy and society, promoting technological innovation has been the inevitable trend of the development of global social economy, also, technological innovation capability is the driving...
Selection of suppliers is the precondition and foundation of supply chain operation. It is an important aspect to choose the best supplier for supply chain management. This paper is aimed to present a fuzzy decision-making approach to deal with the supplier selection problem in supply chain system. In this paper, we can convert the decision matrix into a fuzzy decision matrix and then we use fuzzy...
Selection of Logistics Service Provider is the precondition and foundation of supply chain operation. It is an important aspect to choose the best supplier for supply chain management. But in the selection course of suppliers, some index can’t be expressed by certain number, just only expressed by linguistic words, under this situation, we must use fuzzy decision making method. In this paper, we set...
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.