Time-series anomaly detection is an important research topic in data mining, popular in both academia and industry. Recently, unsupervised anomaly detection draws considerable attention, since it can detect anomalies without parameter tuning on labels and meets the demands of industrial applications. Time-series representation learning plays a vital role in addressing unsupervised anomaly detection. However, it remains challenging to learn a unified representation model with diverse distributions and handle multivariate times-series with various features.To alleviate these challenges, we propose a novel representation strategy, termed CAT-AD, for unsupervised time-series anomaly detection. It learns characteristic-aware priors for representations of time-series by incorporating embeddings of broad characteristics and is capable of handling diverse anomaly detection tasks, regardless of their lengths and dimensions.Our proposed strategy is simple yet effective, which has been verified on two univariate datasets and five multivariate datasets from public sources.

The capacity of Non-Terrestrial Networks (NTN) technology to offer coverage throughout a broad spectrum of locations, including locations that are impossible to access using conventional terrestrial communications methods, such as high altitudes, oceans and seas, and airborne places, is one of the most significant benefits of this technology. This study focuses on the process of standardization of NTN networks, particularly the creation of Star-Land Convergence in 3GPP, ITU, and CCSA organizations that are responsible for standards. As part of the introduction of the wireless technologies, the star-terrestrial cooperative access technology and mobility management technology are discussed.

Since 5G networks are expensive in terms of equipment, require large investments during construction, consume large amounts of power and have high operating costs, co-location and sharing have become a new approach to operator network development and operation. This paper first introduces the networking architecture and interoperability interface of inter-network roaming in core networks, followed by the key procedures and specifications of inter-network roaming, and then analyzes the registration procedures and terminal mobility management in roaming areas. Finally, a proposal for inter-network roaming commercialization is presented, and the correctness and feasibility of the scheme are verified through interactive experiments between home 4G and visited 5G as well as between home 5G and visited 5G.

In this paper, a D-S evidence theory information fusion method is proposed along with the basic concept of D-S evidence theory and the synthesis law. By applying this information fusion method to the condition monitoring of generating units through simulation experiments, the real-time operating status of the units can be reflected from different aspects, and a comprehensive and correct understanding of the environment or characteristics can be derived to make more accurate and complete estimates and decisions, thus improving the robustness of the whole system. From the experimental results, it can be seen that the D-S evidence theory information fusion method effectively reduces the uncertainty of fault diagnosis and improves the credibility of fault state identification.

5G is a next-generation broadband mobile communication technology with high speed, low latency and expansive connectivity that has been widely adopted and used in China. In recent years, natural disasters and other catastrophes have become increasingly common, and since emergency communications are key to responding to disasters and emergencies, it is critical to examine how 5G can be used more effectively for emergency communications. To meet the demand for emergency communication in the 5G era where multiple new technologies are naturally combined, the paper proposes the use of new technologies such as high-throughput satellites, 5G, and edge computing to improve the emergency disaster relief system. The system combines the advantages of the above three new technologies, integrates more terminal devices into the access, and can transmit audio and video from the scene, rapidly back to the rear command center through satellite links, realizing the goal of becoming air-ground integrated and service interoperable, effectively solving the needs of front and rear communications. The article finally verifies the correctness and effectiveness of the scheme through experiments.

Mobile network investment, coverage, capacity and quality are all directly impacted by the non-renewable and limited availability of wireless spectrum. The lack of sufficient 5G spectrum resources necessitates the recultivation of 4G spectrum. However, since 4G services are still available at the start of 5G, the spectrum cannot be fully converted to 5G. DSS technology improves the spectrum replenishment process, allowing 4G users to continue using the original spectrum and 5G to add additional low frequency spectrum to fully utilize the available spectrum resources. The ability to implement 5G NR coverage in the low-band is enabled by 4G/5G spectrum sharing technology, which allows operators to seamlessly switch from 4G to 5G customers. Strategies for 2.1GHz spectrum rearming are discussed in this work, and current networks are tested in 40MHz NR scenario, 20MHz LTE+20MHz NR scenario and 40MHz DSS scenario, such that the experimental data can be used as a benchmark for the smooth advancement of subsequent 2.1GHz.

SA is the target network architecture of 5G network evolution and development, which adopts a brand new network deployment. But it will coexist with current LTE networks for quite a long time. In order to ensure that UE enjoy uninterrupted service in the mobile procedure, the network needs to provide efficient mobility management. Mobility management can be divided into cell reselection, handover, and redirection based on UE state. And it can be divided into intra-system mobility management and inter-system mobility management according to whether the service cells cross the system. To achieve the 0ms interruption delay of handover, R16 had proposed several mobility management enhancement solutions. The paper mainly introduced the mobility management between NR cells, the interoperability between 4G/5G cells and the mobility management enhancement solutions in R16, which provided a reference for the mobility management optimization of 5G SA network.

For social bots, smooth emotional transitions are essential for delivering a genuine conversation experience to users. Yet, the task is challenging because emotion is too implicit and complicated to understand. Among previous studies in the domain of retrieval-based conversational model, they only consider the factors of semantic and functional dependencies of utterances. In this paper, to implement a more empathetic retrieval-based conversation system, we incorporate emotional factors into context-response matching from two aspects: 1) On top of semantic matching, we propose an emotion-aware transition network to model the dynamic emotional flow and enhance context-response matching in retrieval-based dialogue systems with learnt intrinsic emotion features through a multi-task learning framework; 2) We design several flexible controlling mechanisms to customize social bots in terms of emotion. Extensive experiments on two benchmark datasets indicate that the proposed model can effectively track the flow of emotions throughout a human-machine conversation and significantly improve response selection in dialogues over the state-of-the-art baselines. We also empirically validate the emotion-control effects of our proposed model on three different emotional aspects. Finally, we apply such functionalities to a real IoT application.

A storyboard is a sequence of images to illustrate a story containing multiple sentences, which has been a key process to create different story products. In this paper, we tackle a new multimedia task of automatic storyboard creation to facilitate this process and inspire human artists. Inspired by the fact that our understanding of languages is based on our past experience, we propose a novel inspire-and-create framework with a story-to-image retriever that selects relevant cinematic images for inspiration and a storyboard creator that further refines and renders images to improve the relevancy and visual consistency. The proposed retriever dynamically employs contextual information in the story with hierarchical attentions and applies dense visual-semantic matching to accurately retrieve and ground images. The creator then employs three rendering steps to increase the flexibility of retrieved images, which include erasing irrelevant regions, unifying styles of images and substituting consistent characters. We carry out extensive experiments on both in-domain and out-of-domain visual story datasets. The proposed model achieves better quantitative performance than the state-of-the-art baselines for storyboard creation. Qualitative visualizations and user studies further verify that our approach can create high-quality storyboards even for stories in the wild.

We tackle Attitude Detection, which we define as the task of extracting the replier's attitude, i.e., a target-polarity pair, from a given one-round conversation. While previous studies considered Target Extraction and Polarity Classification separately, we regard them as subtasks of Attitude Detection. Our experimental results show that treating the two subtasks independently is not the optimal solution for Attitude Detection, as achieving high performance in each subtask is not sufficient for obtaining correct target-polarity pairs. Our jointly trained model AD-NET substantially outperforms the separately trained models by alleviating the target-polarity mismatch problem. Moreover, we proposed a method utilising the attitude detection model to improve retrieval-based chatbots by re-ranking the response candidates with attitude features. Human evaluation indicates that with attitude detection integrated, the new responses to the sampled queries from are statistically significantly more consistent, coherent, engaging and informative than the original ones obtained from a commercial chatbot.

Abstract Large networks are often partitioned by the network operators into several smaller networks when deploying software‐defined networks (SDNs). Additionally, a dedicated network operating system (NOS) is deployed for each of these SDNs. Each NOS can learn the local network view that enables control of how data packets are forwarded within its network. Controlling the flow of data packets in an entire network requires each NOS to have a global network view to determine the next NOS hop. Hence, NOSes are required to share or exchange reachability and topological information. How such information is efficiently exchanged has not been well addressed so far, especially in the case of multi‐vendor NOSes. This paper proposes a west–east bridge mechanism for distributed heterogeneous NOSes to cooperate in enterprise/data center/intra‐autonomous system networks. We propose to simplify physical networks into virtual networks and only exchange the simplified virtual network information to construct the global network view. To achieve a resilient peer‐to‐peer control plane of distributed heterogeneous NOSes, we propose a “maximum connection degree”‐based connection algorithm. Considering the security issue, we adopt controller identity authentication. We implement the west–east bridge and analyze the performance obtained: about 100% of enterprises and data centers, and about 99.5% of autonomous systems can adopt to this solution. The deployment in three SDNs (CERNET, Internet2, and CSTNET) proves the feasibility. Copyright © 2014 John Wiley & Sons, Ltd.

No abstract available.

In this paper, we proposal an content provider mobility solution of Named Data Networking (NDN) [1]. Here content provider means the host of NDN network which provide content originally. We add a Locator are to the Interest packet [2]. Mapping System also introduced into the network, which maps identifier to locator. The original name is used as identifier. Thus, matching lookup in Content Store (CS) and Pending Interest Table (PIT) employs identifier, while forwarding lookup in Forwarding Information Base (FIB) employs locator. In reality, Mapping System should be a DNS-like distributed system, so the record updating has time latency. It's hard to solve provider mobility when there is no explicit "where" information, that's why locator is imported in NDN, however, "where" still serves as the secondary information of the network.

Software Defined Networking (SDN) is considered as a promising method to re-construct the architecture of Internet. At present, the programs of network protocols are mixed together in SDN controller. However, in the production network, an isolated network environment with private resources is needed for each network protocol running on the same SDN controller. It is therefore necessary to design a practical virtualization cloud platform on the SDN network operating system (NOS). In this paper, we introduce a virtualization cloud platform for SDN production network. A prototype is implemented and two cases are performed to show the feasibility and the effectiveness of our proposed framework.