Search results

The purpose of this paper is to propose an attention alignment method for opinion mining of massive open online course (MOOC) comments. Opinion mining is essential for MOOC applications. In this study, the authors analyze some of bidirectional encoder representations from transformers (BERT’s) attention heads and explore how to use these attention heads to extract opinions from MOOC comments.

The approach proposed is based on an attention alignment mechanism with the following three stages: first, extracting original opinions from MOOC comments with dependency parsing. Second, constructing frequent sets and using the frequent sets to prune the opinions. Third, pruning the opinions and discovering new opinions with the attention alignment mechanism.

The experiments on the MOOC comments data sets suggest that the opinion mining approach based on an attention alignment mechanism can obtain a better F1 score. Moreover, the attention alignment mechanism can discover some of the opinions filtered incorrectly by the frequent sets, which means the attention alignment mechanism can overcome the shortcomings of dependency analysis and frequent sets.

To take full advantage of pretrained language models, the authors propose an attention alignment method for opinion mining and combine this method with dependency analysis and frequent sets to improve the effectiveness. Furthermore, the authors conduct extensive experiments on different combinations of methods. The results show that the attention alignment method can effectively overcome the shortcomings of dependency analysis and frequent sets.

The purpose of this paper is to find the problems in the establishment of Chinese digital publishing policies and regulations system.

The research is through analysis the digital publishing policies and regulations in China referring to digital publishing macro policies, e-book policies, digital music policies, network animated cartoon policies, network game policies, as well as through examining the legal system (law, administrative regulation, departmental rules, judicial interpretation) in China.

The paper concludes that the framework of this system should contain three layers, and Chinese digital publishing policies and regulations system will continue to be improved and digital publishing market will be standardized operation. The digital publishing industry policies, digital publishing resource policies, digital technology policies, copyright policies and personnel training policies need for further investigation and research.

Because of the coverage of digital publishing industry is so wide, the policies and regulations which the paper analyzed were not so comprehensive.

It can help the Chinese government make more comprehensive and rational policies and regulations for digital publishing industry and ensure the sustainable development of digital publishing industry.

The sound of digital publishing policies and regulations system could create a regular and healthful environment for social community participating spiritual creating and sharing.

The paper proposes that the government should first make clear the basic objectives of the digital publishing policies and regulations system in China and then determine the content of the system. It has a positive significance to promote the establishment the system of policies and regulations in China and can ensure the sustainable development of digital publishing industry.

For many pattern recognition problems, the relation between the sample vectors and the class labels are known during the data acquisition procedure. However, how to find the useful rules or knowledge hidden in the data is very important and challengeable. Rule extraction methods are very useful in mining the important and heuristic knowledge hidden in the original high-dimensional data. It can help us to construct predictive models with few attributes of the data so as to provide valuable model interpretability and less training times.

In this paper, a novel rule extraction method with the application of biclustering algorithm is proposed.

To choose the most significant biclusters from the huge number of detected biclusters, a specially modified information entropy calculation method is also provided. It will be shown that all of the important knowledge is in practice hidden in these biclusters.

The novelty of the new method lies in the detected biclusters can be conveniently translated into if-then rules. It provides an intuitively explainable and comprehensive approach to extract rules from high-dimensional data while keeping high classification accuracy.

The purpose of this paper is with robust control problem for event-triggered networked control systems (NCSs) with actuator failures and time-varying transmission delays.

A random sequence is introduced to describe the actuator faults, and a novel event-triggering communication scheme is adopted in the sensor-to-controller channel. By taking the event-triggered mechanism and network transmission delay into consideration, a delay system model is constructed.

Based on Lyapunov stability theory and free weighting matrix method, the feasibility criteria for co-designing both the controller gain and the trigger parameters are derived. Finally, a simulation example is exploited to demonstrate the effectiveness of the proposed linear matrix inequalities (LMIs) approach.

The introduced approach is interesting for NCSs with actuator failures and time-varying transmission delays.

As main mode of modern service industry and future economy society, the research on crowd network can greatly facilitate governances of economy society and make it more efficient, humane, sustainable and at the same time avoid disorders. However, because most results cannot be observed in real world, the research of crowd network cannot follow a traditional way. Simulation is the main means to put forward related research studies. Compared with other large-scale interactive simulations, simulation for crowd network has challenges of dynamic, diversification and massive participants. Fortunately, known as the most famous and widely accepted standard, high level architecture (HLA) has been widely used in large-scale simulations. But when it comes to crowd network, HLA has shortcomings like fixed federation, limited scale and agreement outside the software system.

This paper proposes a novel reflective memory-based framework for crowd network simulations. The proposed framework adopts a two-level federation-based architecture, which separates simulation-related environments into physical and logical aspect to enhance the flexibility of simulations. Simulation definition is introduced in this architecture to resolve the problem of outside agreements and share resources pool (constructed by reflective memory) is used to address the systemic emergence and scale problem.

With reference to HLA, this paper proposes a novel reflective memory-based framework toward crowd network simulations. The proposed framework adopts a two-level federation-based architecture, system-level simulation (system federation) and application-level simulation (application federations), which separates simulation-related environments into physical and logical aspect to enhance the flexibility of simulations. Simulation definition is introduced in this architecture to resolve the problem of outside agreements and share resources pool (constructed by reflective memory) is used to address the systemic emergence and scale problem.

Simulation syntax and semantic are all settled under this framework by templates, especially interface templates, as simulations are separated by two-level federations, physical and logical simulation environment are considered separately; the definition of simulation execution is flexible. When developing new simulations, recompile is not necessary, which can acquire much more reusability, because reflective memory is adopted as share memory within given simulation execution in this framework; population can be perceived by all federates, which greatly enhances the scalability of this kind of simulations; communication efficiency and capability has greatly improved by this share memory-based framework.

Inspired by the development of eco-friendly flexible electronics, this paper aims to present a series of paper-based electronics drawn by pencils, which can be used as favorable sensing elements in daily life.

Pencil traces are deposited on the porous surface of Xerox paper by the mechanical exfoliation during writing process, which can be used as basic components to construct functional electronics for daily sensing applications. By changing pencil grade, the obtained traces can work as conductive wires, electrodes, resistors and piezoresistive gauges.

The experimental results confirm their practical applications in sensing several daily activities, including finger motion, touching and the temperature of water in paper cup. Moreover, the used electronics can be easily handled and recycled.

The shortage in functionality, reliability and performance consistency induced by manual operation is an evident challenge, which makes the pencil-on-paper devices more suitable to work as a temporary solution to satisfying the demands from emergency circumstances.

The pencil-on-paper devices, motivated by the electroconductibility and piezoresistivity of pencil trace, can be explored as sensing prototypes in detecting daily activities. Meantime, their advances in easy accessibility, rapid fabrication, low cost and eco-fitness endow them excellent capacity of meeting the “on-site, real-time” demands.

The purpose of this study is to investigate the mechanism of shared leadership on team members’ innovative behavior.

Paired questionnaires were collected from 89 scientific research teams in the Beijing-Tianjin-Hebei region of China at two-time points with a time lag of 4 months. Then multilevel structural equation model method was applied to analyze the multiple mediating effects.

This study finds that: the form of shared leadership in scientific research teams of universities; shared leadership has a positive impact on team members’ innovative behavior; there are multiple mediations in the relationship including synchronization and sequence of creative self-efficacy and achievement motivation.

According to the “stimulus-organism-response” model, this paper has constructed a multi-level theoretical model that shared leadership influences individual innovation behavior and reveals the “black box” from the perspective of psychological mechanism. It not only verifies that “can-do” shapes “willing to do” but also makes up for the gap of an empirical test of the effectiveness of shared leadership in scientific research teams of universities. Besides, the formal scale of shared leadership in the Chinese situation is revised, which can provide a reference for future empirical research on shared leadership. The research conclusions provide new ideas for improving the management of scientific research teams in universities.

The purpose of this paper is to present a new plan approach for optimal allocation water resources in social‐economic‐environmental complex system in order to achieve human and nature coordinated development.

By integrating the system dynamics (SD) and multi‐objective programming (MOP), the new approach which is termed SD‐MOP model is proposed. The model is characterized by fully reflecting the initial trends of the system development, accurately explaining both of the structure and function of the system, objectively finding the sensible points of the system, and achieving the optimum solutions of the model, the according the solutions the optimal plan can be designed according practical situation.

By applying SD‐MOP integrated model, the designed planning proposal can be guaranteed operable, available, and optimal level.

SD‐MOP integrated model is a very useful support tool in optimal decision making.

The new planning approach of SD‐MOP integrated model can be used in regional resources planning, especially in formulating sustainable development strategies. In addition, the model can be used to estimate the trends of the system development when the planning program has been implemented.

Simulation is a well-known technique for using computers to imitate or simulate the operations of various kinds of real-world facilities or processes. The facility or process of interest is usually called a system, and to study it scientifically, we often have to make a set of assumptions about how it works. These assumptions, which usually take the form of mathematical or logical relationships, constitute a model that is used to gain some understanding of how the corresponding system behaves, and the quality of these understandings essentially depends on the credibility of given assumptions or models, known as VV&A (verification, validation and accreditation). The main purpose of this paper is to present an in-depth theoretical review and analysis for the application of VV&A in large-scale simulations.

After summarizing the VV&A of related research studies, the standards, frameworks, techniques, methods and tools have been discussed according to the characteristics of large-scale simulations (such as crowd network simulations).

The contributions of this paper will be useful for both academics and practitioners for formulating VV&A in large-scale simulations (such as crowd network simulations).

This paper will help researchers to provide support of a recommendation for formulating VV&A in large-scale simulations (such as crowd network simulations).

Over the past decades, there has been significant research effort dedicated to the development of autonomous vehicles. The decision-making system, which is responsible for driving safety, is one of the most important technologies for autonomous vehicles. The purpose of this study is the use of an intensive learning method combined with car-following data by a driving simulator to obtain an explanatory learning following algorithm and establish an anthropomorphic car-following model.

This paper proposed car-following method based on reinforcement learning for autonomous vehicles decision-making. An approximator is used to approximate the value function by determining state space, action space and state transition relationship. A gradient descent method is used to solve the parameter.

The effect of car-following on certain driving styles is initially achieved through the simulation of step conditions. The effect of car-following initially proves that the reinforcement learning system is more adaptive to car following and that it has certain explanatory and stability based on the explicit calculation of R.

The simulation results show that the car-following method based on reinforcement learning for autonomous vehicle decision-making realizes reliable car-following decision-making and has the advantages of simple sample, small amount of data, simple algorithm and good robustness.