Xiang Fei

Platform as a service gateway for the Fog of Things

Abstract Internet of Things (IoT), one of the key research topics in recent years, together with concepts from Fog Computing, brings rapid advancements in Smart City, Monitoring Systems, industrial control, transportation and other fields. These applications require a reconfigurable sensor architecture that can span multiple scenarios, devices and use cases that allow storage, networking and computational resources to be efficiently used on the edge of the network. There are a number of platforms and gateway architectures that have been proposed to manage these components and enable application deployment. These approaches lack horizontal integration between multiple providers as well as higher order functionalities like load balancing and clustering. This is partly due to the strongly coupled nature of the deployed applications, a lack of abstraction of device communication layers as well as a lock-in for communication protocols. This limitation is a major obstacle for the development of a protocol agnostic application environment that allows for single application to be migrated and to work with multiple peripheral devices with varying protocols from different local gateways. This research looks at existing platforms and their shortcomings as well as proposes a messaging based modular gateway platform that enables clustering of gateways and the abstraction of peripheral communication protocol details. These novelties allow applications to send and receive messages regardless of their deployment location and destination device protocol, creating a more uniform development environment. Furthermore, it results in a more streamlined application development and testing while providing more efficient use of the gateway’s resources. Our evaluation of a prototype for the system shows the need for the migration of resources and the QoS advantages of such a system. The examined use case scenarios show that clustering proves to be an advantage in certain use cases as well as presenting the deployment of a larger testing and control environment through the platform.

A topic community-based method for friend recommendation in large-scale online social networks

Online social networks (OSNs) have become more and more popular and have attracted a great many users. Friend recommendation, which is one of the important services in OSN, can help users discover their interested friends and alleviate the problem of information overload. However, most of existing recommendation methods only consider either user link or content information and hence are not effective enough to provide high quality recommendations. In this paper, we propose a topic community‐based method via Nonnegative Matrix Factorization (NMF). This method first applies joint NMF model to mine topic communities existing in OSN by combing link and content information. Then it computes user pairwise similarities and makes friends recommendation based on topic communities. Furthermore, this method can be implemented using the MapReduce distributed computing framework. Extensive experiments show that our proposed method not only has better recommendation performance than state‐of‐the‐art methods but also has good scalability to deal with the problem of friend recommendation in large‐sale OSNs. Moreover, the application case demonstrates that it can significantly improve friend recommendation service in the real world OSN. Copyright

A method of demand-driven and data-centric Web service configuration for flexible business process implementation

ABSTRACT Facing the rapidly changing business environments, implementation of flexible business process is crucial, but difficult especially in data-intensive application areas. This study aims to provide scalable and easily accessible information resources to leverage business process management. In this article, with a resource-oriented approach, enterprise data resources are represented as data-centric Web services, grouped on-demand of business requirement and configured dynamically to adapt to changing business processes. First, a configurable architecture CIRPA involving information resource pool is proposed to act as a scalable and dynamic platform to virtualise enterprise information resources as data-centric Web services. By exposing data-centric resources as REST services in larger granularities, tenant-isolated information resources could be accessed in business process execution. Second, dynamic information resource pool is designed to fulfil configurable and on-demand data accessing in business process execution. CIRPA also isolates transaction data from business process while supporting diverse business processes composition. Finally, a case study of using our method in logistics application shows that CIRPA provides an enhanced performance both in static service encapsulation and dynamic service execution in cloud computing environment.

A Topic Community-Based Method for Friend Recommendation in Online Social Networks via Joint Nonnegative Matrix Factorization

Online social networks (OSN) have become more and more popular and have accumulated a great many users. Friend recommendation can help users discover their interested friends and alleviate the problem of information overload. However, most of existing recommendation methods only consider user link or content information and hence are not effective enough to provide high quality recommendations. In this paper, we propose a topic community-based method via nonnegative matrix factorization (NMF). This method first applies joint NMF model to mine topic community existing in OSN by combing link and content information. Then it makes friend recommendation based on topic community. Experiments show that our method can reflect user preferences on friend selection more appropriately and has better recommendation performance than traditional methods. Moreover, our application case also demonstrates that it can obviously improve friend recommendation service in the real world OSN.

Community Discovery in Large-Scale Complex Networks Using Distributed SimRank Nonnegative Matrix Factorization

Nonnegative Matrix Factorization (NMF) has become a powerful model for community discovery in complex networks. Existing NMF-based methods for community discovery often factorize the corresponding adjacent matrix of complex networks to obtain their community indicator matrices, which can provide intuitive interpretation for the community membership of nodes in complex networks. However, the adjacent matrix cannot represent the global structure feature of complex networks very well, and hence decreases the quality of discovered communities. Aiming at solving this problem, in this paper we investigate several representative similarity measures of graph nodes and propose an NMF-based method for community discovery using SimRank similarity measure. Additionally, to improve the scalability of our method, we implement its key components using MapReduce distributed computing framework, including computing SimRank feature matrix and iteratively solving the NMF-based model for community discovery. We conduct extensive experiments on several complex networks. The results show that our method can obtain better results of community discovery than NMF-based methods using other similarity measures. Moreover, our method presents good scalability and can be used to discover communities in the large-scale complex networks.

Towards a Hybrid Deep-Learning Method for Music Classification and Similarity Measurement

Large repository of music that can be accessed or downloaded over the Internet, provides a new way of trading or sharing. However, the technologies for features based Music Information Retrieval (MIR), which is a multidisciplinary field of research, are not well established. Existing MIR techniques and products suffer from either limited capabilities or poor performance. In this paper, we proposed a data model that describes the music information using both Music Definition Language (MDL) and Music Manipulation Language (MML), and supports extensible hybrid methods for music classification and similarity measurement. With proposed musical data model, we further developed a hybrid method that combines both contour and rhythm features, and employed an Artificial Neural Network (Unsupervised Kohonen Self-Organized Map) based classification mechanism that maps variations of music pieces to their corresponding originals using a new vector/matrix format defined as MDL. The proposed hybrid method based on a deep-learning mechanism and a new similarity measurement method has been introduced to fulfil analysis on the music classification and their similarity scores. The test results demonstrate that an accuracy of around 70% in the experiments has been achieved.

Graph Analysis of Fog Computing Systems for Industry 4.0

Increased adoption of Fog Computing concepts into Cyber Physical Systems (CPS) is a driving force for implementing Industry 4.0. The modern industrial environment focuses on providing a flexible factory floor that suits the needs of modern manufacturing through the reduction of downtimes, reconfiguration times, adoption of new technologies and the increase of its production capabilities and rates. Fog Computing through CPS aims to provide a flexible orchestration and management platform that can meet the needs of this emerging industry model. Proposals on Fog Computing platform and Software Defined Networks (SDN) for Industry allow for resource virtualization and access throughout the system enabling large composite application systems to be deployed on multiple nodes. The increase of reliability, redundancy and runtime parameters as well as the reduction of costs in such systems are of key interest to Industry and researchers as well. The development of optimization algorithms and methods is made difficult by the complexity of such systems and the lack of real-world data on fog systems resulting in algorithms that are not being designed for real world scenarios. We propose a set of use-case scenarios based on our Industrial partner that we analyze to determine the graph based parameters of the system that allows us to scale and generate a more realistic testing scenario for future optimization attempts as well as determine the nature of such systems in comparison to other networks types. To show the differences between these scenarios and our real-world use-case we have selected a set of key graph characteristics based on which we analyze and compare the resulting graphs from the systems.

A Multi-View Clustering Method for Community Discovery Integrating Links and Tags

Community discovery is a popular research problem in the realm of complex network analysis and many methods have been proposed to solve it. However, most of the existing methods only consider the usage of links information and ignore tags information of complex networks. As a result, the quality of their discovered communities is often poor owing to the sparse and noisy data existing in links information. Actually, both links and tags contain noisy but complementary information with each other. In this paper, we propose a multi-view clustering method for community discovery, which is based on multi-view Nonnegative Matrix Factorization (NMF) model and can provide a unified framework to integrate links and tags information. Its key idea is to build a joint NMF process with the constraint that pushes community indicator matrices of links view and tags view towards a common consensus matrix, which can uncover the common latent community structure shared by links view and tags view. Under the optimization framework of multiplicative update rules, we devise the corresponding community discovery algorithm, which can be used to obtain higher quality communities. We conduct extensive experiments on several real datasets and the results demonstrate the effectiveness of our method.

Dust and Reflection Removal from Videos Captured in Moving Car

The quality of videos captured in moving cars suffer from dust on the wind screen glass. Dust contaminates the captured videos and makes the videos blurred. Removing dust and restoring high quality dust-free and reflection-free video is a challenging task in the field of video stream processing. In this work, we present a pipeline of dust and reflection removal from the corrupted video streams. To the best of our knowledge, this paper is the first study how to effectively remove dust from video streams captured in a moving car. The pipeline is comprises of two steps. In the first step, it uses the state of the art image matting to model and resolve the captured frames as the merging result of a dust layer, a background layer and a matte layer. To refine the result, the second step employs variances of pixel streams to constrain the matte layer and optimizes the extracted dust layer, background layer and matte layer to make them spatially and temporally consistent in the streams. The test results demonstrate that our proposed method can effectively remove the dust and reflections in the video streams captured in moving cars.

CPS data streams analytics based on machine learning for Cloud and Fog computing: a survey

Abstract Cloud and Fog computing has emerged as a promising paradigm for the Internet of things (IoT) and cyber–physical systems (CPS). One characteristic of CPS is the reciprocal feedback loops between physical processes and cyber elements (computation, software and networking), which implies that data stream analytics is one of the core components of CPS. The reasons for this are: (i) it extracts the insights and the knowledge from the data streams generated by various sensors and other monitoring components embedded in the physical systems; (ii) it supports informed decision making; (iii) it enables feedback from the physical processes to the cyber counterparts; (iv) it eventually facilitates the integration of cyber and physical systems. There have been many successful applications of data streams analytics, powered by machine learning techniques, to CPS systems. Thus, it is necessary to have a survey on the particularities of the application of machine learning techniques to the CPS domain. In particular, we explore how machine learning methods should be deployed and integrated in Cloud and Fog architectures for better fulfilment of the requirements of mission criticality and time criticality arising in CPS domains. To the best of our knowledge, this paper is the first to systematically study machine learning techniques for CPS data stream analytics from various perspectives, especially from a perspective that leads to the discussion and guidance of how the CPS machine learning methods should be deployed in a Cloud and Fog architecture.