DNN Partitioning for Inference Throughput Acceleration at the Edge

Deep neural network (DNN) inference on streaming data requires computing resources to satisfy inference throughput requirements. However, latency and privacy sensitive deep learning applications cannot afford to offload computation to remote clouds because of the implied transmission cost and lack of trust in third-party cloud providers. Among solutions to increase performance while keeping computation on a constrained environment, hardware acceleration can be onerous, and model optimization requires extensive design efforts while hindering accuracy. DNN partitioning is a third complementary approach, and consists of distributing the inference workload over several available edge devices, taking into account the edge network properties and the DNN structure, with the objective of maximizing the inference throughput (number of inferences per second). This paper introduces a method to predict inference and transmission latencies for multi-threaded distributed DNN deployments, and defines an optimization process to maximize the inference throughput. A branch and bound solver is then presented and analyzed to quantify the achieved performance and complexity. This analysis has led to the definition of the acceleration region, which describes deterministic conditions on the DNN and network properties under which DNN partitioning is beneficial. Finally, experimental results confirm the simulations and show inference throughput improvements in sample edge deployments.

View this article on IEEE Xplore


Federating Cloud Systems for Collaborative Construction and Engineering

The construction industry has undergone a transformation in the use of data to drive its processes and outcomes, especially with the use of Building Information Modelling (BIM). In particular, project collaboration in the construction industry can involve multiple stakeholders (architects, engineers, consultants) that exchange data at different project stages. Therefore, the use of Cloud computing in construction projects has continued to increase, primarily due to the ease of access, availability and scalability in data storage and analysis available through such platforms. Federation of cloud systems can provide greater flexibility in choosing a Cloud provider, enabling different members of the construction project to select a provider based on their cost to benefit requirements. When multiple construction disciplines collaborate online, the risk associated with project failure increases as the capability of a provider to deliver on the project cannot be assessed apriori. In such uncontrolled industrial environments, “trust” can be an efficacious mechanism for more informed decision making adaptive to the evolving nature of such multi-organisation dynamic collaborations in construction. This paper presents a trust based Cooperation Value Estimation (CoVE) approach to enable and sustain collaboration among disciplines in construction projects mainly focusing on data privacy, security and performance. The proposed approach is demonstrated with data and processes from a real highway bridge construction project describing the entire selection process of a cloud provider. The selection process uses the audit and assessment process of the Cloud Security Alliance (CSA) and real world performance data from the construction industry workloads. Other application domains can also make use of this proposed approach by adapting it to their respective specifications. Experimental evaluation has shown that the proposed approach ensures on-time completion of projects and enhanced

View this article on IEEE Xplore

Cloud – Fog – Edge Computing in Cyber-Physical-Social Systems (CPSS)

Submission Deadline: 01 February 2020

IEEE Access invites manuscript submissions in the area of Cloud – Fog – Edge Computing in Cyber-Physical-Social Systems (CPSS).

Cyber-Physical-Social Systems (CPSS) integrates the cyber, physical and social spaces together. One of the ultimate goals of cyber-physical-social systems (CPSS) is to make our lives more convenient and intelligent by providing prospective and personalized services for users. To achieve this goal, a wide range of data in CPSS are employed as the starting point for research, since the data contains the user’s historical behavior trajectory and the user’s demand preference. Generated and collected from social and physical spaces and integrated in the cyber space, CPSS data are complex and heterogeneous, recording all aspects of users’ lives in the forms of image, audio, video and text. Generally, the collected or generated data in CPSS satisfies 4Vs (volume, variety, velocity, and veracity) of big data. Thus, how to deal with CPSS big data efficiently is the key to provision services for users.

From another perspective, CPSS big data are specified as the global historical data and the local real-time data. Cloud computing, as a powerful paradigm for implementing the data-intensive applications, has an irreplaceable role in processing global historical data. On the other hand, with the increasing computing capacity and communication capabilities of mobile terminal devices, fog-edge computing, as an important and effective supplement of cloud computing, has been widely used to process the local real-time data. Therefore, how to systematically and efficiently process the CPSS big data (including both the global historical data and the local real-time data) in CPSS has become the key for providing services in CPSS.

This Special Section in IEEE Access aims to share and discuss recent advances and future trends of Cloud-Fog-Edge Computing in CPSS, and to bring academic researchers and industry developers together. Articles on practical as well as on theoretical topics and problems about proximity services are invited.

The topics of interest include, but are not limited to:

  • Cloud computing for big data processing in CPSS
  • Big data management framework for CPSS in cloud-fog-edge environment
  • Security and privacy issues for CPSS in fog/edge computing
  • Computation offloading for edge computing in CPSS
  • Dynamic resource provisioning for CPSS in cloud-fog-edge computing
  • CPSS big data mining in cloud-fog-edge computing
  • Service composition for CPSS in cloud-fog-edge computing
  • Big data applications in CPSS

We also highly recommend the submission of multimedia with each article as it significantly increases the visibility, downloads, and citations of articles.


Associate Editor:  Md Arafatur Rahman, University Malaysia Pahang, Malaysia

Guest Editors:

    1. Zahir Tari, Royal Melbourne Institute of Technology University, Australia
    2. Dakai Zhu, University of Texas at San Antonio, USA
    3. Francesco Piccialli, University of Naples FEDERICO II, Italy
    4. Xiaokang Wang, St. Francis Xavier University, Canada


Relevant IEEE Access Special Sections:

  1. Advanced Data Mining Methods for Social Computing
  2. Distributed Computing Infrastructure for Cyber-Physical Systems
  3. Innovation and Application of Intelligent Processing of Data, Information and Knowledge as Resources in Edge Computing

IEEE Access Editor-in-Chief:
  Prof. Derek Abbott, University of Adelaide

Article submission: Contact Associate Editor and submit manuscript to:

For inquiries regarding this Special Section, please contact:  arafatur@ump.edu.my.

Most Cited Article of 2017: Fog of Everything: Energy-Efficient Networked Computing Architectures, Research Challenges, and a Case Study

Fog computing (FC) and Internet of Everything (IoE) are two emerging technological paradigms that, to date, have been considered standing-alone. However, because of their complementary features, we expect that their integration can foster a number of computing and network-intensive pervasive applications under the incoming realm of the future Internet. Motivated by this consideration, the goal of this position paper is fivefold. First, we review the technological attributes and platforms proposed in the current literature for the standing-alone FC and IoE paradigms. Second, by leveraging some use cases as illustrative examples, we point out that the integration of the FC and IoE paradigms may give rise to opportunities for new applications in the realms of the IoE, Smart City, Industry 4.0, and Big Data Streaming, while introducing new open issues. Third, we propose a novel technological paradigm, the Fog of Everything (FoE) paradigm, that integrates FC and IoE and then we detail the main building blocks and services of the corresponding technological platform and protocol stack. Fourth, as a proof-of-concept, we present the simulated energy-delay performance of a small-scale FoE prototype, namely, the V-FoE prototype. Afterward, we compare the obtained performance with the corresponding one of a benchmark technological platform, e.g., the V-D2D one. It exploits only device-to-device links to establish inter-thing “ad hoc” communication. Last, we point out the position of the proposed FoE paradigm over a spectrum of seemingly related recent research projects.

View this article on IEEE Xplore

Most Cited Article of 2017: A Survey on Software-Defined Wireless Sensor Networks: Challenges and Design Requirements

Software defined networking (SDN) brings about innovation, simplicity in network management, and configuration in network computing. Traditional networks often lack the flexibility to bring into effect instant changes because of the rigidity of the network and also the over dependence on proprietary services. SDN decouples the control plane from the data plane, thus moving the control logic from the node to a central controller. A wireless sensor network (WSN) is a great platform for low-rate wireless personal area networks with little resources and short communication ranges. However, as the scale of WSN expands, it faces several challenges, such as network management and heterogeneous-node networks. The SDN approach to WSNs seeks to alleviate most of the challenges and ultimately foster efficiency and sustainability in WSNs. The fusion of these two models gives rise to a new paradigm: Software defined wireless sensor networks (SDWSN). The SDWSN model is also envisioned to play a critical role in the looming Internet of Things paradigm. This paper presents a comprehensive review of the SDWSN literature. Moreover, it delves into some of the challenges facing this paradigm, as well as the major SDWSN design requirements that need to be considered to address these challenges.

View this article on IEEE Xplore

Most Cited Article of 2017: A Survey on Mobile Edge Networks: Convergence of Computing, Caching and Communications

As the explosive growth of smart devices and the advent of many new applications, traffic volume has been growing exponentially. The traditional centralized network architecture cannot accommodate such user demands due to heavy burden on the backhaul links and long latency. Therefore, new architectures, which bring network functions and contents to the network edge, are proposed, i.e., mobile edge computing and caching. Mobile edge networks provide cloud computing and caching capabilities at the edge of cellular networks. In this survey, we make an exhaustive review on the state-of-the-art research efforts on mobile edge networks. We first give an overview of mobile edge networks, including definition, architecture, and advantages. Next, a comprehensive survey of issues on computing, caching, and communication techniques at the network edge is presented. The applications and use cases of mobile edge networks are discussed. Subsequently, the key enablers of mobile edge networks, such as cloud technology, SDN/NFV, and smart devices are discussed. Finally, open research challenges and future directions are presented as well.

View this article on IEEE Xplore

Most Popular Article of 2017: Internet of Things for Smart Healthcare: Technologies, Challenges, and Opportunities

Internet of Things (IoT) technology has attracted much attention in recent years for its potential to alleviate the strain on healthcare systems caused by an aging population and a rise in chronic illness. Standardization is a key issue limiting progress in this area, and thus this paper proposes a standard model for application in future IoT healthcare systems. This survey paper then presents the state-of-the-art research relating to each area of the model, evaluating their strengths, weaknesses, and overall suitability for a wearable IoT healthcare system. Challenges that healthcare IoT faces including security, privacy, wearability, and low-power operation are presented, and recommendations are made for future research directions.

View this article on IEEE Xplore

SmartCityWare: A Service-Oriented Middleware for Cloud and Fog Enabled Smart City Services

Smart cities are becoming a reality. Various aspects of modern cities are being automated and integrated with information and communication technologies to achieve higher functionality, optimized resources utilization, and management, and improved quality of life for the residents. Smart cities rely heavily on utilizing various software, hardware, and communication technologies to improve the operations in areas, such as healthcare, transportation, energy, education, logistics, and many others, while reducing costs and resources consumption. One of the promising technologies to support such efforts is the Cloud of Things (CoT). CoT provides a platform for linking the cyber parts of a smart city that are executed on the cloud with the physical parts of the smart city, including residents, vehicles, power grids, buildings, water networks, hospitals, and other resources. Another useful technology is Fog Computing, which extends the traditional Cloud Computing paradigm to the edge of the network to enable localized and real-time support for operating-enhanced smart city services. However, proper integration and efficient utilization of CoT and Fog Computing is not an easy task. This paper discusses how the service-oriented middleware (SOM) approach can help resolve some of the challenges of developing and operating smart city services using CoT and Fog Computing. We propose an SOM called SmartCityWare for effective integration and utilization of CoT and Fog Computing. SmartCityWare abstracts services and components involved in smart city applications as services accessible through the service-oriented model. This enhances integration and allows for flexible inclusion and utilization of the various services needed in a smart city application. In addition, we discuss the implementation and experimental issues of SmartCityWare and demonstrate its use through examples of smart city applications.

View this article on IEEE Xplore

A Method for 3-D Printing Patient-Specific Prosthetic Arms With High Accuracy Shape and Size

Limb amputation creates serious emotional and functional damage to the one who lost a limb. For some upper limb prosthesis users, comfort and appearance are among the desired features. The objective of this paper is to develop a streamlined methodology for prosthesis design by recreating the shape and size of an amputated arm with high accuracy through 3-D printing and silicone casting. To achieve this, the computer tomography (CT) images of the patient’s affected and non-affected arms were scanned. Next, the geometry of the socket and the prosthetic arm were designed according the mirrored geometry of the non-affected arm through computer-aided design software. The support structure and the moulds were 3-D printed, and the prosthetic arm was casted with a silicone material. To validate the replication, the shape of the socket and prosthetic arm were quantitatively compared with respect to the source CT scan from the patient. The prosthetic arm was found to have high accuracy on the basis of the Dice Similarity Coefficient (DSC; 0.96), percent error (0.67%), and relative mean distance (0.34 mm, SD = 0.48 mm). Likewise, the socket achieved high accuracy based on those measures: DSC (0.95), percent error (2.97%), and relative mean distance (0.46 mm, SD = 1.70 mm) The liner, socket, and prosthetic arm were then shipped to the patient for fitting. The patient found the fit of the socket and the replication of the shape and the size of the prosthesis to be desirable. Overall, this paper demonstrates that CT imaging, computed-aided design, desktop 3-D printing, and silicone casting can achieve patient-specific cosmetic prosthetic arms with high accuracy.

View this article on IEEE Xplore

Linguistic Feature Based Filtering Mechanism for Recommending Posts in a Social Networking Group

Online social networks have spawned myriads of online social groups, where people can interact and exchange their ideas. However, the major issues that interfere with the user security and comfort are privacy breach, groups without opt-in options, clutter created out of numerous groups in which a user is a member of and difficulty in managing group principles. This can be lessened to an extent by an automated filtering mechanism capable of categorizing members within a group based on their pattern of response. In our proposed method, the posts within a group are clustered based on stylistic, thematic, emotional, sentimental, and psycholinguistic aspects. Then the members of the group are categorized based on their response to the posts belonging to different aspects as mentioned above. This results in categories of individuals within a group, who are like minded. The categorization caters to the most important issues related to soft security , such as the clutter associated with irrelevant notifications received from multiple groups, by suggesting the users, posts that are likely to be of interest to them. It also helps to identify the group members intended towards spreading posts that violate group policies. The categorization exhibits satisfiable performance in case of large number of candidate members in a populous group by performing clustering based on linguistic features. The double level of clustering, based on the posts and response of users based on the aspects of the posts, enhances the performance of the system, hence outperforming traditional recommender systems. The system has been tested on Facebook group data, where it offers a significant solution to an unaddressed problem associated with social networking groups.

View this article on IEEE Xplore