Journal Contents

2017:
Volume 1 Issue 1, 2017[Full Issue PDF]

=======================

Volume 1 Issue 1, 2017 [Full Issue PDF]

  • Internet Of Things Solutions

  • Should be cited as: [ paper pdf download]

    Liang-Jie Zhang, Cheng Li, "Internet Of Things Solutions ", Services Transactions on Internet of Things (STIOT), 1(1), 2017, pp. 1-22, doi:10.29268/stiot.2017.1.1.1.

    Abstract:

    In the field of Internet of Things (IoT), technology is becoming more and more mature, but still lacking of practical application of commercial solutions. This paper presents a set of principles for the solution of the Internet of Things solution, and establishes the reference architecture of the IoT solution according to the principle. The architecture covers a wide range of aspects of IoT technology and applications, and has significant implications for building practical IoT applications.

  • A Systematic Framework For Designing Iot-enabled Systems

  • Should be cited as: [ paper pdf download]

    Jing Zeng, Jiang-Song Min, "A Systematic Framework For Designing Iot-enabled Systems ", Services Transactions on Internet of Things (STIOT), 1(1), 2017, pp. 23-31, doi:10.29268/stiot.2017.1.1.2.

    Abstract:

    The IoT-enabled systems (IoTES) have significantly revolutioned the computing pardigm that sharply affects future technologies development. However, the design of IoTES sytems still involves various challenges. a) they are inherently complicated, residing in varying environment with multiple devices and networks, resulting in huge design diffculty. b) they lack effective approaches and tools to guarantee the design performance of IoTES at complicated environment. c) the design period hardly meets time-to-market needs, which are diffcult to satisfy the users’ demands . To address these challenges, in this article, we present a systematic design framework for IoTES which can refine the system specification defined by formal lanuage into underlying architecture at given platform and constraints leveraging a unified representation model. The system specfiication firstly be transformed into task decision set by task ontology and task library. Subsequently, the task set is precisely deposited into architecture platform at given platform library and space model constraints, the design flow can include object emplacement, system synthesis and preference synthesis. The final output of design consists of object location (location of phyiscal objects and cyber objects ), system configuration (netowork configuration and hardware platform selection) and user satisfaction to generated design solutions. Also, we demonstrate design framework with a smart meeting room case.

  • A Deep Learning Approach For Condition-based Monitoring And Fault Diagnosis Of Rod Pump

  • Should be cited as: [ paper pdf download]

    Hangqi Zhao, Jian Wang, Peng Gao, " A Deep Learning Approach For Condition-based Monitoring And Fault Diagnosis Of Rod Pump ", Services Transactions on Internet of Things (STIOT), 1(1), 2017, pp. 32-42, doi:10.29268/stiot.2017.1.1.3.

    Abstract:

    Petrochemical industry is one of the key industry areas where Internet of Things (IoTs) and big data analytics could be widely applied to support smarter production and maintenance. In oil and gas exploitation, sucker-rod pumping systems are used in approximately 90 percent of artificially lifted wells. An automatic pipeline is crucial for real-time condition monitoring and fault detection of the system to save costs. Here we used convolutional neural network (CNN), a deep learning framework, to identify the working conditions of pump wells based on dynamometer cards and the corresponding sensor data. Two schemes, namely, data-based CNN and image-based CNN are proposed and compared with traditional machine learning algorithms such as k-Nearest Neighbors and Random Forests. Through experiments on a real dataset from oil fields, we show that CNN based approach could significantly outperform traditional methods without any need of manual feature engineering that requires domain expertise. Besides, we proposed a semi-automatic method for labeling big datasets of dynamometer cards, which could significantly reduce the labor work by manual labeling. Our work provides a feasible and efficient method for fault detection in oil pump systems and paves the way to applying deep learning techniques in IoTs related industries.

  • Trust As A Service For Soa-based Iot Systems

  • Should be cited as: [ paper pdf download]

    Ing-Ray Chen, Jia Guo, Jeffrey J.P. Tsai, " Trust As A Service For Soa-based Iot Systems ", Services Transactions on Internet of Things (STIOT), 1(1), 2017, pp. 43-52, doi:10.29268/stiot.2017.1.1.4.

    Abstract:

    A future SOA-based Internet of Things (IoT) system will consist of a huge number of autonomous IoT devices capable of providing services upon request. We propose a cloud-based scalable trust management protocol for supporting Trust as a Service (TaaS). In our trust protocol design, each user will map to a home cloud server using its unique id based on Distributed Hash Table techniques to achieve load balancing among all cloud servers. TaaS is realized by following a simple report-and-query paradigm. Specifically, a user upon a service completion will report to its home cloud server of the user satisfaction result. To know if another IoT device is trustworthy in providing a service, a user will send a query to its home cloud server even if the user has not had any service experience with the IoT device. The server will return a trust value formed by considering self-observations from the user as well as recommendations from other users sharing similar social interests. We demonstrate the feasibility by applying TaaS to a real-world SOA-based IoT application. The results support its superiority over contemporary distributed IoT trust management protocols in selecting trustworthy nodes and resulting in the highest application utility score.

Services Transactions on Internet of Things (STIOT) looks forward to your contributions.

Contact Information

If you have any questions or queries on the Services Transactions on Internet of Things (STIOT), please send email to stiot DOT HiPore AT gmail.com.