The field of social computing emerged more than ten years ago. During the last decade, researchers from a variety of disciplines
have been closely collaborating to boost the growth of social computing research. This paper aims at identifying key researchers
and institutions, and examining the collaboration patterns in the field. We employ co-authorship network analysis at different
levels to study the bibliographic information of 6 543 publications in social computing from 1998 to 2011. This paper gives
a snapshot of the current research in social computing and can provide an initial guidance to new researchers in social computing. 相似文献
Lake water resources operation and water quality management come up with higher challenges due to climate change. The frequency and intensity of extreme hydrological events are increasing under global warming, which may directly lead to more uncertainty and complexity for hydrodynamic and water-quality conditions in large shallow lake. However, studies about effects of climate change on lake hydrodynamic and water-quality conditions are not enough. Thus, a coupled model is es-tablished to investigate the potential responses of lake water level, flow field and pollutant migra-tion to the changing climatic factors. The results imply that water flow capacity and self-purification in the Hongze Lake can be improved by west, northwest, north, south and southeast winds indi-cating wind filed change has a great effect on the hydrodynamic and water-quality conditions in large shallow lake. It is further observed that both hydrodynamics and water quality are more sensitive to rainfall change than to temperature change; compared to the effect from temperature and rainfall, the effect from wind field appear to be more pronounced. Moreover, the results verify the feasibility of coupling basin hydrological model with lake hydrodynamic and water quality model. To the best of knowledge, the coupled model should not be used until independent calibra-tions and verifications for hydrodynamics and water quality modeling, the hydrological model and the coupled model.
The rapidly increasing popularity of mobile devices has changed the methods with which people access various network services and increased network traffic markedly. Over the past few decades, network traffic identification has been a research hotspot in the field of network management and security monitoring. However, as more network services use encryption technology, network traffic identification faces many challenges. Although classic machine learning methods can solve many problems that cannot be solved by port- and payload-based methods, manually extract features that are frequently updated is time-consuming and labor-intensive. Deep learning has good automatic feature learning capabilities and is an ideal method for network traffic identification, particularly encrypted traffic identification; Existing recognition methods based on deep learning primarily use supervised learning methods and rely on many labeled samples. However, in real scenarios, labeled samples are often difficult to obtain. This paper adjusts the structure of the auxiliary classification generation adversarial network (ACGAN) so that it can use unlabeled samples for training, and use the wasserstein distance instead of the original cross entropy as the loss function to achieve semisupervised learning. Experimental results show that the identification accuracy of ISCX and USTC data sets using the proposed method yields markedly better performance when the number of labeled samples is small compared to that of convolutional neural network (CNN) based classifier. 相似文献
Journal of Mathematical Imaging and Vision - Different from the traditional watermarking schemes, zero-watermarking schemes are lossless embedding methods, which are applicable to be used in... 相似文献
In the context of human-robot and robot-robot interactions, the better cooperation can be achieved by predicting the other party’s subsequent actions based on the current action of the other party. The time duration for adjustment is not sufficient provided by short term forecasting models to robots. A longer duration can by achieved by mid-term forecasting. But the mid-term forecasting models introduce the previous errors into the follow-up forecasting and amplified gradually, eventually invalidating the forecasting. A new mid-term forecasting with error suppression based on restricted Boltzmann machine(RBM) is proposed in this paper. The proposed model can suppress the error amplification by replacing the previous inputs with their features, which are retrieved by a deep belief network(DBN). Furthermore, a new mechanism is proposed to decide whether the forecasting result is accepted or not. The model is evaluated with several datasets. The reported experiments demonstrate the superior performance of the proposed model compared to the state-of-the-art approaches.
Applied Intelligence - Personnel performance is a key factor to maintain core competitive advantages. Thus, predicting personnel future performance is a significant research domain in human... 相似文献
Applied Intelligence - With the development of the Internet, the recommendation based on Quality of Service(QoS) is proven to be an efficient way to deal with the ever-increasing web services in... 相似文献