No abstract

The rapid adoption of mobile devices has dramatically changed the access to various networking services and led to the explosion of mobile service traffic. Mobile service traffic classification has been a crucial task that attracts strong interest in mobile network management and security as well as machine learning communities for past decades. However, with more and more adoptions of encryption over mobile services, it brings a lot of challenges about mobile traffic classification. Although classical machine learning approaches can solve many issues that port and payload-based methods cannot solve, it still has some limitations, such as time-consuming, costly handcrafted features, and frequent features update. With the excellent ability of automatic feature learning, Deep Learning (DL) undoubtedly becomes a highly desirable approach for mobile services traffic classification, especially encrypted traffic. This survey paper looks at emerging research into the application of DL methods to encrypted traffic classification of mobile services and presents a general framework of DL-based mobile encrypted traffic classification. Moreover, we review most of the recent existing work according to dataset selection, model input design, and model architecture. Furthermore, we propose some noteworthy issues and challenges about DL-based mobile services traffic classification.

Abstract:In the analysis, we integrated stakeholder and agency theories to explore the connection between corporate social responsibility (CSR) and sustainable financial development by considering the moderating effect of ownership structure. After empirical analysis, we found the following conclusions. First, the short-term and long-term economic performance is positively affected by CSR, which leads to sustainable financial development. Second, ownership circulation has a positive relationship with economic performance in the short run, which short-term profit increases as ownership circulation strengthens. Third, the effect of CSR on short-term economic performance is moderated by ownership structure. Excessive concentrated ownership may lead to decisions that do not satisfy all key stakeholders and may reduce the positive effect of CSR on economic performance. Finally, we suggest that Chinese energy companies should pay more attention to improving corporate social responsibility to maintain good economic performance and develop sustainable competitive advantage. Meanwhile, companies should optimize ownership concentration to avoid weakening the positive effects of social responsibility on short-term economic performance.

To reduce the increasingly congestion in cities, it is essential for intelligent transportation system (ITS) to accurately forecast the short-term traffic flow to identify the potential congestion sites. In recent years, the emerging deep learning method has been introduced to design traffic flow predictors, such as recurrent neural network (RNN) and long short-term memory (LSTM), which has demonstrated its promising results. In this paper, different from existing work, we study the temporal convolutional network (TCN) and propose a deep learning framework based on TCN model for short-term city-wide traffic forecast to accurately capture the temporal and spatial evolution of traffic flow. Moreover, we design the model with the Taguchi method to develop an optimized structure of the TCN model, which not only reduces the number of experiments, but also yields high accuracy of forecasting results. With the real-world traffic flow data collected from highways in Birmingham City of U.K., we compare our model with four deep learning based models including LSTM models, GRU models, SAE models, DeepTrend and CNN-LSTM models in terms of the mean absolute error (MAE) and mean relative error (MRE) regarding the actual flow data. The experimental results demonstrate that our framework achieves the state-of-art performance with superior accuracy in short-term traffic flow forecasting. INDEX TERMS Deep learning, temporal convolutional networks, short-term forecasting.

Smart homes have attracted much attention due to the expanding of Internet-of-Things (IoT) and smart devices. In this paper, we propose a smart gateway platform for data collection and awareness in smart home networks. A smart gateway will replace the traditional network gateway to connect the home network and the Internet. A smart home network supports different types of smart devices, such as in home IoT devices, smart phones, smart electric appliances, etc. A traditional network gateway is not capable of providing quality-of-service measurement, user behavioral analytics, or network optimization. Such tasks are traditionally performed with measurement agents such as optical splitters or network probes deployed in the core network. Our proposed platform is a lightweight plug-in for the smart gateway to accomplish data collection, awareness and reporting. While the smart gateway is able to adjust the control policy for data collection and awareness locally, a cloud-based controller is also included for more refined control policy updates. Furthermore, we propose a multi-dimensional awareness framework to achieve accurate data awareness at the smart gateway. The efficiency of data collection and accuracy of data awareness of the proposed platform is demonstrated based on the tests using actual data traffic from a large number of smart home users.

No abstract

With the development of the Internet of Things (IoT) and the widespread use of electric vehicles (EV), vehicle-to-grid (V2G) has sparked considerable discussion as an energy-management technology. Due to the inherently high maneuverability of EVs, V2G systems must provide on-demand service for EVs. Therefore, in this work, we propose a hybrid computing architecture based on fog and cloud with applications in 5G-based V2G networks. This architecture allows the bi-directional flow of power and information between schedulable EVs and smart grids (SGs) to improve the quality of service and cost-effectiveness of energy service providers. However, it is very important to select an EV suitable for scheduling. In order to improve the efficiency of scheduling, we first need to determine define categories of target EV users. We found that grouping on the basis of EV charging behavior is one effective method to identify target EVs. Therefore, we propose a hybrid artificial intelligence classification method based on the charging behavior profile of EVs. Through this classification method, target EVs can be accurately identified. The results of cross-validation experiments and performance evaluations suggest that this method is effective.

No abstract