Forthcoming articles

 


International Journal of Internet Manufacturing and Services

 

These articles have been peer-reviewed and accepted for publication in IJIMS, but are pending final changes, are not yet published and may not appear here in their final order of publication until they are assigned to issues. Therefore, the content conforms to our standards but the presentation (e.g. typesetting and proof-reading) is not necessarily up to the Inderscience standard. Additionally, titles, authors, abstracts and keywords may change before publication. Articles will not be published until the final proofs are validated by their authors.

 

Forthcoming articles must be purchased for the purposes of research, teaching and private study only. These articles can be cited using the expression "in press". For example: Smith, J. (in press). Article Title. Journal Title.

 

Articles marked with this shopping trolley icon are available for purchase - click on the icon to send an email request to purchase.

 

Articles marked with this Open Access icon are freely available and openly accessible to all without any restriction except the ones stated in their respective CC licenses.

 

Register for our alerting service, which notifies you by email when new issues of IJIMS are published online.

 

We also offer RSS feeds which provide timely updates of tables of contents, newly published articles and calls for papers.

 

International Journal of Internet Manufacturing and Services (40 papers in press)

 

Regular Issues

 

  • Application of Optical Character Recognition with Tesseract in Logistics Management   Order a copy of this article
    by Sigurd Anders Berg, Soo-Yeon Seo, Richard Hau Yue So 
    Abstract: Warehouse and inventory management poses many challenges, for example in carton handling when upstream suppliers use labelling systems that are incompatible with a companys downstream system. In such cases, information is digitised using manual labour: this process can often become a bottleneck and, eventually, a source of handling errors. In this paper, the feasibility of applying Optical Character Recognition (OCR) technology in carton handling is assessed, and a prototype based on the open-source engine Tesseract is described in detail. Its performance on both printed and handwritten text is quantified, as well as the impact of turning the problem into a matching problem rather than a pure recognition problem.
    Keywords: Optical character recognition; OCR; binarisation; Tesseract; logistics management; pattern recognition; image processing; warehouse material handling; business rule; data capturing; data integration.

  • Analysis of scientific and technological innovation influence factors affect enterprise performance   Order a copy of this article
    by Jun Ma, Mingshun Guo 
    Abstract: With the development of the society, science & technology innovation becomes the development foundation of the equipment manufacturing industry enterprises. According to the questionnaires of 29 equipment manufacturing industries in Shenyang, the paper summarizes the factors that affect the enterprise performance based on Grounded Theory. In order to study the relationships between the influencing factors and enterprise performance, multiple linear regression analysis is conducted by Statistical Product and Service Solutions (SPSS) software.
    Keywords: Enterprise Performance;Innovation;Influence Factor;Multiple Regression Analysis.

  • Factors Affecting Users' Stickiness in Online Car-hailing Platforms: An Empirical Study   Order a copy of this article
    by Tete Lv, Xiyan Lv 
    Abstract: This study investigated factors that affected users stickiness and interrelationships among confirmation, perceived usefulness, satisfaction, continuance intention and users' stickiness in online car-hailing platforms. An empirical approach was adopted through online questionnaire survey to find out the formation mechanism of users stickiness. The results indicated that perceived usefulness and satisfaction were positively associated with continuance intention, thereby leading to the increase of users stickiness. And perceived usefulness also affected the satisfaction positively. Whats more, confirmation was found to be the strongest predictor of perceived usefulness. The findings of this study may not only verify the Extended Model of IT Continuance, but provide managerial guidelines for online car-hailing platform, thereby enhancing users stickiness.
    Keywords: car-hailing platform; users' stickiness; affecting factors; empirical study; managerial guidelines.

  • Using Artificial Neural Networks to forecast producer price index for New Zealand   Order a copy of this article
    by Lin Lin Zhao, Bill Wang, Jasper Mbachu, Temitope Edbelakin 
    Abstract: Trend in the producer price is of much value to the central bank authorities in identifying the cost-push inflation that can improve their understanding of future directions of inflation in the aggregate economy and in formulating sound policies and macroeconomic plans. Forecasting of the producer price movement is complex; the popular use of conventional methods is fraught with inaccuracies which often produces misleading results and unreliable forward macroeconomic planning and control intent. This study explored the reliability and accuracy of the use of artificial neural networks (ANNs) for modelling and predicting producer price index (PPI) trend in New Zealand. Archival research method was used, which involved access and SPSS-based analysis of timeseries data maintained by the New Zealand Statistics and the Treasury over the period January 1990 March 2017. Input variables in the ANNs model comprised trade weighted index (TWI), interest rate/ official cash rate (OCR), and consumer price index (CPI). Lagged values of the PPI constituted the output variables. The study also compared ANNs results with those produced by the autoregressive integrated moving average (ARIMA) as an alternative. Results showed that the ANNs model outperformed the ARIMA model as a more reliable and accurate tool for timeseries data prediction. It was found that PPI timeseries data exhibited non-linear characteristics, making their prediction more suited to ANNs technique than the linear assumption, which underlie the conventional approach used in practice for such analysis. The results therefore revealed the key causes of inaccuracies and uncertainties surrounding existing timeseries model prediction efforts. The methodology developed could guide economists and macroeconomic policy makers in making more accurate forecasts and in formulating more workable policies and action plans targeted at cost-push inflation control. A strawman model of the potential causal relationships between producer price trend as exogenous variable, and the productivity and operating financial performance of manufacturing firms was proposed for further investigations. The proposed model recognises the uptake of industrial internet technologies as the mediating variable in the envisaged relationships in a multivariate setting.
    Keywords: Artificial neutral networks; autoregressive integrated moving average (ARIMA); consumer price index; producer price index; trade weighted index.

  • Selection of Resource Service Chain with Conflict-Free Dependencies in Cloud Manufacturing Systems   Order a copy of this article
    by Haibo Li, Juncheng Tong 
    Abstract: In cloud manufacturing (CMfg), to improve the efficiency of a whole business process, all distributed manufacturing resources services should be selected as service flows, called Resource-Service Chain (RSC). However, selecting an RSC with conflict-free dependency is more difficult in collaborative manufacturing than in a centralized one, as resource services are usually selected independently by different organizations. To overcome this shortcoming, an algorithm based evolutionary algorithm is proposed. First, five common types of dependencies are defined after analyzing the relationship among manufacturing resources. Then, genetic algorithm (GA) is applied to find the optimal set of RSCs, in which the dependencies among resource services are considered as constraint rules. Finally, a collaborative business process is taken as an instance to verify the selection of RSCs with conflict-free dependency. The results show that it can improve the efficiency of resource service selection.
    Keywords: cloud manufacturing; resource-service chain; conflict; dependency; genetic algorithm; evolutionary algorithm.

  • A novel comprehensive evaluation method for science and technology insurance under internet environment   Order a copy of this article
    by Zhiming Zeng 
    Abstract: Manufacturing industry plays an important role in the national economy. However, it is worth noting that scientific and technological innovation in manufacturing industry is accompanied by risks. One of the important ways to solve technological risks is science and technology insurance. In this paper, we first analyze the development status of science and technology insurance in China, and then establish an index evaluation system by using the analytic hierarchy process (AHP) and the fuzzy comprehensive evaluation method. The index evaluation system includes three layers and selects 24 indicators, which can help the insurance companies to scientifically and quantitatively evaluate high-tech manufacturing companies. It also can avoid subjective and difficult-to-quantify problems in the past evaluation process. Finally, an empirical study is showed to explain how to quantify these indicators and how to calculate the weight coefficient values for each indicator. Our findings can provide relevant countermeasures and suggestions for insurance companies, high-tech manufacturing companies, and governments.
    Keywords: Science and technology insurance; intelligent manufacturing; analytic hierarchy process; fuzzy comprehensive evaluation; evaluation index system.

  • SOA-based distributed fault prognostic and diagnosis framework: An application for preheater cement cyclones   Order a copy of this article
    by Chouhal Ouahiba 
    Abstract: Complex engineering manufacturing systems require efficient on-line fault diagnosis methodologies to improve safety and reduce maintenance costs. Traditionally, diagnosis and prognosis approaches are centralized, but these solutions are difficult to implement on increasingly prevalent distributed, networked embedded systems; whereas a distributed approach of multiple diagnosis and prognosis agents can offer a solution. Also, having the capability to control and observe process plant of a manufacturing system from a remote location has several benefits including the ability to track and to assist in solving a problem that might arise. This paper presents a distributed and over prognosis and diagnosis approach for physical systems basing on multi agent system and Service-Oriented Architecture. Specifics prognostic and diagnostic procedures and key modules of the architecture for Web Service-based Distributed Fault Prognostic and Diagnosis framework are detailed and developed for the preheater cement cyclones in the workshop of SCIMAT clinker. The experimental case study, reported in the present paper, shows encouraging results and fosters industrial technology transfer.
    Keywords: Iintelligent Fault Diagnosis; E-diagnosis; Remote Fault Prognosis; Web Services; SOA; Preheater cement cyclone; SMA.

  • Research on the FJSS problem with discrete equipment capability in cloud manufacturing environment   Order a copy of this article
    by Hongguo Zhang, Chao Ma, Shuli Zhang, Shenghui Liu 
    Abstract: In the cloud manufacturing environment, the flexible job shop scheduling needs to handle the online task and offline tasks simultaneously, which make the processing time of equipment become from continuous to discrete. For solving this issue, a mathematical model considering discrete equipment capability was proposed. In this model, the additional profits constraint and the equipment capability conflict constraint are introduced. The former was used to promise the optimal solution is profitable for the manufacturing enterprise; the latter was used to promise the online task coming from the other manufacturing enterprises can be processed. Then an improved ant colony algorithm is adopted to solve this problem. Finally, the experimental results show that the flexible job shop scheduling problem with discrete equipment capability in cloud manufacturing environment could be solved effectively.
    Keywords: cloud manufacturing; flexible job shop scheduling; discrete equipment capability; mathematical model; ant colony algorithm.
    DOI: 10.1504/IJIMS.2019.10018379
     
  • Wolf pack algorithm for optimisation of cutting parameters in WEDM using Taguchi method   Order a copy of this article
    by Yanqiu Xiao, Wuyi Ming, Dili Shen, Wenbin He, Jun Ma, Jianqiang Jiao 
    Abstract: The optimisation of cutting parameters for wire electrical discharge machining (WEDM) is one the most difficult combinatorial optimisation problems, due to their complicated, coupled and nonlinear nature of the input-output variables of them. An exact solution for a WEDM optimisation problem cannot be easily obtained within a reasonable amount of time. Therefore, a meta heuristic algorithm is required [e.g., genetic algorithm (GA), particle swarm optimisation (PSO), wolf pack algorithm (WPA), etc.)]. The objective of this paper is to develop a robust approach using WPA to obtain the optimised combination of cutting parameters for the process of WEDM. Hence, a Taguchi orthogonal array is proposed instead of a full factorial experimental design for determining the parameters of the WPA. The effects of the WPA parameters on optimising the cutting parameters are disclosed and an analysis of variance is performed to investigate significance factors on the results. By experiments of WEDM, an application was presented to illustrate the effectiveness of the proposed approach. Compared with the S/N ratio statistical method of reported previously, the performance of Ra and material removal rate (MRR) were improved by 12% and 3.99%, respectively.
    Keywords: combinatorial optimisation; wolf pack algorithm; WPA; Taguchi orthogonal method; wire electrical discharge machining; WEDM.
    DOI: 10.1504/IJIMS.2019.10018380
     
  • Indirect effect mechanism of supply chain relationship quality on supply chain performance   Order a copy of this article
    by Xiaoping Li, Haishui Li, Lijuan Xie 
    Abstract: This paper built the conceptual model of supply chain relationship quality through information sharing or supply chain logistics capability effect on supply chain performance indirectly. By using structural equation 227 manufacturing enterprises' survey data has been analysed in Jiangsu Province and is concluded that in addition to the supply chain relationship quality through information sharing or supply chain logistics capability effect on supply chain performance actively, also, in turn, through information sharing, supply chain logistics capabilities effect on supply chain performance indirectly.
    Keywords: supply chain relationship quality; supply chain logistics capability; information sharing; supply chain performance.
    DOI: 10.1504/IJIMS.2019.10018381
     
  • Business intelligence for order fulfilment management in small and medium enterprises   Order a copy of this article
    by Danny C.K. Ho, Daniel Y.W. Mo, Eugene Y.C. Wong, Simon M.K. Leung 
    Abstract: In this study, we investigate business intelligence (BI) tools that help a small and medium enterprise (SME) to improve its supplier order fulfilment management. Making use of the huge amount of data in its enterprise resource planning system, the company can seek opportunities for building collaborative supplier relationships to implement a just-in-time strategy. The proposed BI tools are developed to select suppliers with whom to form collaborative relationships. In addition, a BI dashboard is developed for the company to manage the cash conversion cycle of its supply chain. Developing BI tools that make use of limited information technology resources, we address the business and technical challenges of large unstructured datasets and lengthy computation time. The results show that SMEs can benefit from BI tools at an affordable cost, joining the emergent trend of deploying business analytics to make systematic innovation.
    Keywords: business intelligence; BI; small and medium enterprise; SME; order fulfilment management.
    DOI: 10.1504/IJIMS.2019.10018382
     
  • Research on value co-creation behaviour in service industry based on the theory of planned behaviour   Order a copy of this article
    by Meng Xiao, Qinhai Ma, Man Li 
    Abstract: With the transformation of social development and customer needs, the traditional model of value creation has been unable to adapt to market environment evolving. In order to enhance the core competitiveness of the firms, and meet the customers' needs, the value co-creation model was proposed and has achieved some good results. In the value co-creation model, customers and firms are brought into the process of production and consumption, and drawing support from the value proposition offered by firms. The business value and customer value are created together. Based theory of planned behaviour (TPB), the behaviour mechanism of value co-creation activities in the service industry between the customers and the firms are analysed in detail. Through the literature review, the theoretical model reflecting the relations among the concepts is established. In this study, the data were collected by the survey method. The structural equation model was used in the data analysis. The results showed that value co-creation attitude, subjective norm, and perceived behavioural control could truly affect the customers' co-creation behaviour. Finally, some suggestions and countermeasures that could effectively manage and motivate the value co-creation behaviour of the customers in the service industry were put forward.
    Keywords: theory of planned behaviour; TPB; value co-creation behaviour; value co-creation attitude; subjective norm; perceived behavioural control.
    DOI: 10.1504/IJIMS.2019.10018384
     

Special Issue on: Data Intensive Services based Applications

  • Automatic Service Abstraction through Data, Information and Knowledge Prioritization   Order a copy of this article
    by Yucong Duan 
    Abstract: Web service is a popular solution to integrate components when building a software system, or to allow communication between a system and third-party users, providing a flexible and reusable mechanism to access its functionalities. Scientists have been proposing numerous models for defining anything as a service (aaS), including discussions of products, processes, data and information management, and security as a service. Various web service based systems are prevailing in health service, personalized recommendation provision. We propose a framework towards constructing and searching typed resources in terms of data, information and knowledge through a hierarchy composing Data Graph, Information Graph and Knowledge Graph in order to improve performance in accessing and processing resources. We use cases to illustrate the mechanism of the framework.
    Keywords: service abstraction; data graph; information graph; knowledge graph.

  • Deep Well Construction of Big Data Platform Based on Multi-Source Heterogeneous Data Fusion   Order a copy of this article
    by Yanping Bai 
    Abstract: Abstract: At present, energy saving and emission reduction had become a problem of great concern for mankind. People all over the world were actively developing the economy of energy saving and emission reduction. At the same time, there were some problems in the mining industry, such as waste of resources, low efficiency and easy occurrence of industrial accidents. Therefore, this paper, based on the national key research plan - basic theory and key technology of deep well construction and lifting in coal mine, had designed a set of deep well big data system based on multi-source heterogeneous data fusion, and had set up a deep well construction big data platform. The high precision and bear great pressure sensors were added to the system to solved the difficult problem of collecting information in deep wells by ordinary sensors. The multi-source heterogeneous data fusion algorithm was added to the system to solve the problem that the format of the data acquisition was different. The big data information technology was used to store and manage the data to solve the problem of processing efficiency of massive data. At the same time, the platform could process and track data, and show the relevance of data more intuitively, which provided a basis for experts to predict and predict. In conclusion, the completion of the platform could achieve data monitoring in the process of mine completion. It not only helps to enhance the safety of mine construction, but also provides data and analytical tools for further theoretical research of mine construction, and lays the foundation for research.
    Keywords: Deep well; Multi-source data fusion; Big data.

  • Research on collaborative filtering recommendation algorithm based on social network   Order a copy of this article
    by Tian Zhang 
    Abstract: For users of social-based social networking services, we propose a local random walk based friend recommendation approach by bringing together social network and tie strength. We firstly construct a weighted friend network as the basis for friend recommendation. Then, users similarity is determined by a local random walk based similarity measure on a weighted friend network. Experiments show that we use real social network data to evaluate the new method, the validity of the method is illustrated.
    Keywords: Friend recommendation; social networking services;collaborative filtering.

  • Research on collaborative Filtering Recommendation Algorithm based on user interest for cloud computing   Order a copy of this article
    by Kun He 
    Abstract: Aiming to resolve the mobile commerce scenario suggested problems, cloud computing technology and mobile user context are combined to propose a collaborative filtering model based on user interest in mobile scenarios. Through computing the scene similarity based on mobile users, we find similar scenarios constructed target user set current situation, and then establish the item scoring scene and scoring matrix. Based on Map Reduce, we propose a collaborative filtering recommendation method to realize parallel recommendation.
    Keywords: mobile commerce; recommendation model; cloud computing; Map Reduce.

  • Towards Business Process Recommendation based Collaborative Filtering   Order a copy of this article
    by Wei Luo, Zhihao Peng, Ansheng Deng, Xiaoming Bi 
    Abstract: Existing process recommendation methods cannot meet the various needs of personalized users. To address this problem, this paper proposed a personalized process recommendation method that is based on user behavior preference. This method combines traditional process recommendation with user behavior similarity and mines user behavior preference according to the historical tracks of processes that were performed by users. In the execution of a process, the execution trace of a behavior-similar user and executable candidate activities to be recommended that are provided by conventional process recommendation are analyzed. Then, activities or recommended activities for the current user are selected to realize the automatic construction of the entire process to meet the personalized needs of users. The experimental results show that the proposed method outperforms other methods in terms of accuracy and efficiency.
    Keywords: Business Process Recommendation; Flow Similarity; User Preferences; Collaborative Filtering; Personalized Process Recommendation.

  • A Classification Algorithm Based on Weighted ML-kNN for Multi-label Data   Order a copy of this article
    by Ming Jiang, Lian Du, Jianping Wu, Min Zhang, Zexin Gong 
    Abstract: The ML-kNN algorithm uses naive Bayesian classification to modify the traditional kNN algorithm to solve multi-label classification problems. However, the ML-kNN algorithm is prone to misjudgment or incomplete judgment of the unseen instance's label set in two special cases: when the number of labels in the training set is not balanced and when the training instances are unevenly distributed in space. Therefore, a weighted ML-kNN algorithm (i.e., wML-kNN) is proposed in this paper. The main idea is to assign different weights to each label according to the proportion of labels and the mutual information of the spatial distribution of unseen instances to training instances. This method can reduce the probability of misjudgment of the unseen instance's label set. A comparative study was conducted on four multi-label datasets that included review classification and three other published benchmark multi-label datasets: yeast gene function analysis, natural scene classification, and musical sentiment classification. The results show that the performance of the wML-kNN algorithm is better than the other four multi-label learning algorithms, including ML-kNN.
    Keywords: multi-label learning; weighted multi-label kNN; k-nearest neighbor; ML-kNN.

Special Issue on: Symposium on Intelligent Supply Chain Management 2017 Digitalisation and Innovation in Logistics Management

  • Bluetooth-based positioning techniques for the cold chain application   Order a copy of this article
    by Y.P. Tsang, K.L. Choy, C.H. Wu, H.Y. Lam, G.T.S. Ho, P.S. Koo 
    Abstract: In cold chains, the essentials of cold storage are the chilling and freezing storage sections. Due to occupational safety concerns for the warehouse workers in such a cold environment, this paper describes a Bluetooth-based Access Management and Positioning System (BAMPS) to monitor worker location and movement in chillers and freezers, inspired by the growth of Internet of Things. In complying with the ISO11079, their occupational safety in term of exposure duration and recovery time in cold environments can be controlled. The Bluetooth Low Energy module is used for the transmitting and receiving sensing data in the cold storage environment. The positioning module is designed using Kalman filtering to eliminate signal variations instead of pre-requested calibration. Hence, the workplace ergonomics and monitoring in cold storage environment are enhanced. The significance of BAMPS is in exploring occupational safety management and real-time positioning in cold storage facilities.
    Keywords: positioning techniques; occupational safety; cold chain; Bluetooth Low Energy; Kalman filtering.

  • Business Intelligence for Service Parts Logistics Management   Order a copy of this article
    by Nicole K. Y. Chan 
    Abstract: Many leading companies now offer global customers better spare parts services for system maintenance through a complex service logistics network, which extends traditional on-site stocking management to boost profit margins. The major challenge that spare parts service providers face is how to achieve desired service levels at a low cost and minimise excess inventory in the global spare parts supply chain. To address this issue, we demonstrate an inventory redeployment strategy that transforms a conventional spare parts supply chain into a closed-loop, multi-echelon service network capable of redeploying inventory from overstocked to understocked facilities, and thus reducing purchases of high-value spare parts. To assess the quality of our novel approach, we used a network flow optimisation model to analyse the proposed excess inventory redeployment strategy based on an international companys service parts operations. Significant inventory cost savings were identified.
    Keywords: Inventory management; service logistics network design; network flow model; spare parts.

  • Design of Intelligent Transportation Systems for Accessible Transportation Services   Order a copy of this article
    by Tin Lun Louis Man 
    Abstract: The demand for public transportation designed for people with mobility issues has grown rapidly in recent years, but service capacity has not increased at the pace of demand. Demands for major increases in service capacity have strengthened in recent years. In this paper, we study the design of an intelligent transportation system for accessible transportation services to enhance user experience and organisation operational efficiency. Our proposed system includes the components of data visualisation, real-time tracking via a mobile app and a vehicle scheduling optimisation mechanism. These three components are integrated in offline and online platforms. We illustrate the design and benefits of the proposed system through a case study.
    Keywords: Intelligent Transportation System; Vehicle Routing Problem; Mobile Apps; Process Flow.

  • Simulation Analysis of a Manufacturing Company   Order a copy of this article
    by Tommy Cheung 
    Abstract: Traditionally, many manufacturing companies focused more on the higher level of operation management, like assigning tasks to workers, and work scheduling. They often ignored low level operations and their timing optimization. As a result, a lot of these manufacturers suffer from inefficient and uncoordinated operations. Bottleneck would inevitably occur at some stages of the production, which caused the work-in-process goods to build up everywhere in the production plant. This paper used a simulation approach to analyse the low level manufacturing operations in details with the objective to identify the bottleneck and resolve the work-in-process inventory problem, without production out degradation.
    Keywords: Simulation; Manufacturing; Process; Work-in-Process.

Special Issue on: ICSS 2018 Service Science Meets Artificial Intelligence and Big Data

  • Research on Symbiosis State between Manufacturing and Producer Services Industry   Order a copy of this article
    by Xueyuan Wang, Weirui Ma, Ting He 
    Abstract: The producer services industry and the manufacturing industry are interconnected; subdivision industries of producer services industry have different effects on the manufacturing industry. In order to accurately determine the relationship among them, and to guide China government to correctly make industrial planning, a variable analysis model is built based on theoretical analysis. From the viewpoint of time series, the first period state of their relation is compared with the whole period, the reasons for changes are analysed. In addition, the balance of industrial relation is forecasted. Using increased value of industry to calculate their interacting relation after data smoothness treatment based on Lotka-Volterra model and Eviews software. The result shows that the relationship between manufacturing, technology services, and finance is predator-prey relation, while manufacturing and transportation & warehousing are in mutually reinforcing and symbiosis condition. After discovering their current relationship, recommendations for optimizing industrial relations in order to achieve industrial cooperation and mutual development are brought forward.
    Keywords: manufacturing industry; service industry; symbiosis; Lotka-volterra model; competition; cooperation; financing; predator-prey; Scientific research; transportation.

  • Fog-Cloud task scheduling of Energy consumption Optimization with deadline consideration   Order a copy of this article
    by Jiuyun Xu, Xiaoting Sun, Ruru Zhang, Hongliang Liang, Qiang Duan 
    Abstract: The emerging IoT introduces many new challenges that cannot be adequately addressed by the current "cloud-only" architectures. The cooperation of the fog and cloud is considered to be a promising architecture, which efficiently handles IoTs data processing and communications requirements. However, how to schedule tasks to better adapt to IoT real-time needs and reduce the energy in the fog-cloud system is not well addressed. In this paper, we first model the energy consumption of the fog and cloud, respectively, and formulate a task scheduling problem into a constrained optimization problem in Fog-Cloud Computing System. Then, an efficient deadline-energy scheduling algorithm based on ant colony optimization(DEACO) is put forward to tackle this problem,which achieves to reduce energy consumption on the condition of satisfying the task deadline. Finally, algorithms have been simulated on the extended Cloudsim simulator. The experimental results have shown that our scheduling approach reduces energy more effective.
    Keywords: IoT; Cloud Computing; Fog Computing; Energy consumption; Task scheduling; optimal ant colony algorithm.

  • An Approach to Discovering Event Correlations among Edge Sensor Services   Order a copy of this article
    by Chen Liu, Yunmeng Cao, Yanbo Han 
    Abstract: In an IoT environment, a surge in sensor data volume has exposed the shortcomings of cloud computing, particularly the limitation of network transmission capability and centralized computing resources. To handle these issues, this paper proposes a service-oriented framework, called as INFOG, to support the dynamic cooperation among sensors with the fog computing paradigm. Proactive data services and service hyperlinks, which are our previous work, are two key abstractions for the INFOG framework. The services are software-defined abstraction of physical sensors. They are deployed in edge nodes in INFOG. And service hyperlinks, encapsulation of service correlations, enable the cooperation of sensors at the software layer. We also propose a frequent sequential pattern based approach to effectively discover service hyperlinks. Based on the dataset from a real power plant as well as several synthetic datasets, we do lots of experiments to verify the effectiveness and efficiency of our algorithm.
    Keywords: fog computing; sensor data; event correlation; proactive data service; service hyperlinks.

  • A Topic-Enhanced Recurrent Autoencoder Model for Sentiment Analysis of Short Texts   Order a copy of this article
    by Shaochun Wu, Ming Gao, Qifeng Xiao, Guobing Zou 
    Abstract: This paper presents a topic-enhanced recurrent autoencoder model to improve the accuracy of sentiment classification of short texts. First, the concept of recurrent autoencoder is proposed to tackle the problems in recursive autoencoder including increasing in computation complexity and ignoring the natural word order. Then, the recurrent autoencoder model is enhanced with the topic and sentiment information generated by Joint Sentiment-Topic (JST) model. Besides, in order to identify the negations and ironies in short texts, sentiment lexicon is utilized to add feature dimensions for sentence representations. Experiments are performed to determine the feasibility and effectiveness of the model. Compared with recursive autoencoder model, the classification accuracy of our model is improved by about 7.7%.
    Keywords: short texts;sentiment analysis;word embedding;recurrent autoencoder;recurrent neural network;recursive autoencoder;joint sentiment-topic model.

  • A Multidimensional Service Template for Data Analysis in Highway Domain   Order a copy of this article
    by Weilong Ding, Jie Zou, Zhuofeng Zhao 
    Abstract: In highway domain, business analyses are always multidimensional on massive data for the traffic monitor and control. It is tedious to develop data analysis jobs from scratch and is hardly to consider comprehensive factors from requirements. In this paper, we propose a domain specific service template on massive toll data in highway domain. Based on the service template, abundant multidimensional analysis jobs as services can be built and managed flexibly. In a practical project, our method proves the feasibility and advantages by exhaustive experiments and case studies.
    Keywords: highway; service template; data analysis; spatio-temporal data.

  • State prediction and servitization of manufacturing processing equipment resources in smart cloud manufacturing   Order a copy of this article
    by Shenghui Liu, Xin Hao, Shuli Zhang, Chao Ma 
    Abstract: With the evolution from cloud manufacturing to smart cloud manufacturing, the manufacturing resources need not only to realize the networking and servitization, but also need to realize the intellectualization. So, for enabling the manufacturing processing equipment resources to intelligently perceive its own operating state in the machining workshop of manufacturing enterprise, the paper put forward an integrated prediction method based on combined BP neural network. In this method by combining the clustering ability of SOM neural network and the classification ability of BP neural network together, an integrated intelligent prediction model with the ability of both qualitative and quantitative analysis is defined and used to realize the accurate prediction of the operating state of manufacturing processing equipment resources. Next, the service encapsulation specification for the various algorithms and model in the integrated prediction method are given. These algorithms and models are encapsulated as a set of cloud services and then published to the smart cloud manufacturing service platform, so as to enable the virtualized manufacturing processing equipment resources in the smart manufacturing cloud pool combine their own processing ability and the intelligent perception ability of these cloud services together by carrying out service composition. The above process realized the networking, servitization, and intellectualization of manufacturing processing equipment resources in smart cloud manufacturing. Finally, experimental results demonstrate the effectiveness of the proposed method.
    Keywords: Smart Cloud Manufacturing; Integrated Prediction Model; Combined BP Neural Network; Servitization; Intellectualization.

  • A Case Study of MapReduce Based Expressway Traffic Data Analysis and Service System   Order a copy of this article
    by Jia Liu, Zhilong Hong, Tong Mo, Weilong Ding, Jian Zhang, Weiping Li 
    Abstract: The scale of expressway information networking is constantly expanding. Currently the existing analysis system is still built on the relational database. Traffic data produced by the system has reached a data volume of 3 million items monthly. The performance requirements, including high concurrency, massive throughput, visualization, and scalability, are difficult to be satisfied. The Expressway Traffic Data Analysis System (ETDAS) is designed to meet the needs of the collection, analysis and visualization of increasing expressway traffic data by means of the distributed frameworks. The new system is expected to help regulate the road network traffic flow, reduce traffic congestion, and provide analytical support for the optimization strategy of road network. ETDAS has been deployed online.
    Keywords: Expressway Traffic Data Analysis System; Big Data; Hadoop; MapReduce; Data Visualization.

  • A CNN-based Temperature Prediction Approach for Grain Storage   Order a copy of this article
    by Liang Ge, Caiyuan Chen, Yiyu Li, Tong Mo 
    Abstract: Temperature prediction has a pivotal role in the grain storage phase. Accurate prediction results can optimize the effect of ventilation decisions and reduce the losses of stored grain. Most existing studies have only focused on layer temperature predictions whose predict particle size is very large. In contrast, this paper attempts to use Convolutional Neural Network (CNN) to predict the point temperature of grain piles. The CNN-based approach uses multiple convolution kernels that share weights to capture the characteristics of grain temperature at different locations, which make full use of the temperature information around the target point. Experiments on real business data show that compared to other conventional algorithms, CNN has the best prediction effect on point temperature prediction problems.
    Keywords: Grain Storage; Temperature Prediction; Convolutional Neural Network; Point Prediction.

Special Issue on: Recent Technologies and Applications in Big Data-Inspired Data Acquisition, Processing and Analysis for Wireless Sensor Networks

  • Design of candidate schedules for applying iterative ordinal optimization for scheduling technique on cloud computing platform   Order a copy of this article
    by Monika Yadav, Atul Mishra, BALAMURUGAN BALUSAMY 
    Abstract: In cloud computing, distributed resources are used on demand basis without having the physical infrastructure at the client end. Cloud has a large number of users and to deal with large number of task, so scheduling in cloud plays a vital role for task execution. Scheduling of various multitask jobs on clouds is considered as an NP-hard problem [1]. In order to reduce the large scheduling search space, an iterative ordinal optimization (IOO) method has already proposed. In this paper, a set of 30 candidate schedules denoted by set U are created. The set U is used in the exhaustive search of the best schedule. After analyzing the set U, an ordered schedule vs. makespan graph is plotted. So in this work, set U is defined and created a base for applying IOO method to get optimal schedules. In this work, CloudSim version 3.0 has been used to test and analyze policies.
    Keywords: Cloud computing; iterative ordinal optimization; makespan; CloudSim; Schedules.

  • Mobile Self-organizing Network Positioning Algorithm Based on Node Clustering   Order a copy of this article
    by Jian Feng Cui 
    Abstract: It is not possible to correct the position of the node's space for traditional mobile self-organizing network positioning algorithms, which lead to low positioning accuracy. Based on the DV-hop algorithm, node clustering is used to optimize the DV-hop algorithm, and it is applied to node location of mobile self-organizing network. The narrative principle of mobile self-organizing network based on node clustering is completed by building RSSI ranging model. Combined RSSI technology to build a three-dimensional mobile self-organizing network model, we can obtain the strength of the mobile self-organizing network transmission signal and calculate the propagation loss of the mobile self-organizing network signal. Then, the transmission loss is converted into the node propagation distance, and the node position of the mobile self-organizing network is calculated. The DV-hop algorithm is used for positioning by the distance between nodes and the position of the anchor point. Node clustering is used to correct the spatial position of the node. Without increasing the hardware overhead of the mobile ad hoc network space node, the positioning accuracy is improved and the positioning range is expanded. The simulation experiment results show that node coverage of DV-hop positioning algorithm is higher than traditional algorithm. Besides, the spatial localization of mobile self-organizing network nodes is conducive to expanding the network space node coverage rate, thereby improving the positioning accuracy.
    Keywords: Node clustering; Mobile self-organizing network; Spatial location; Algorithm.

  • The Information Security Scheduling Method of Vehicle Self-organizing System for Wireless Sensor   Order a copy of this article
    by Ming-cheng Peng 
    Abstract: During the process of self-organizing scheduling and control of vehicles, uncertainties often affect the operation of emergency vehicle road traffic. The traditional system cannot determine the road network connectivity, resulting in mismatch of transport routes and transportation vehicles, resulting in traffic congestion. To solve this problem, this paper proposes a wireless sensor-based information security scheduling method for vehicle self-organizing systems. Firstly, overall system is designed. Meanwhile, system hierarchy diagram and various modules of vehicle self-organizing system are introduced; Then, vehicle self-organizing scheduling model is established and design process of source code is provided. Finally, compared with differences of dispatch route length and management time of traffic dispatch for traditional neural network system and our proposed system security scheduling method, the superiority of our proposed method is reflected. Experimental results show that schedule length obtained by our proposed method is at least 200m shorter than those results obtained by the traditional method in the comparison of evacuation dispatch route length of traffic jam. At the same time, time consuming is at least shorter than those results obtained by the traditional method in the comparison of evacuation dispatch management time for traffic jams. Therefore, our proposed method is more efficient in slowing the congestion of vehicle self-organizing system networks.
    Keywords: Security scheduling; Wireless sensor; Vehicle self-organizing system; Network congestion.

  • Research on Algorithm of Information Transmission Path Planning in Big Data Environment   Order a copy of this article
    by Yun Fan Lu, Zhenjia Zhu, Xu Tan 
    Abstract: The information transmission path planning is conducive to the improvement of efficiency of information transmission, which matches requests of development of era. However, most of the information transmission path plans select transmission paths based on ID format. Although this algorithm can make nodes in big data environment reach the optimal path of sink node, it has high computational complexity. Therefore, an information transmission path planning algorithm based on an ingress-priority under big data environment is proposed. Based on this algorithm, a method for evaluating the information transmission path planning is obtained. Then analysis model of the information transmission path planning is constructed. Based on these, dynamic information transmission path planning is implemented by utilizing priority multi-actuators. Experiments show that our proposed method can effectively improve the efficiency of information transmission path planning, ensure the accuracy of information after transmission and improve the quality of information transmission. Therefore, our proposed method is significant in application.
    Keywords: Big data; Information transmission; Path planning.

  • Research on Virus Diffusion Prevention Method for Computer Singularity in Complex Sensor Networks   Order a copy of this article
    by Lei Ma 
    Abstract: In the current virus propagation defense methods, the case of immunization failure of singularity virus and the influ-ence of the combination of infectious vector and propagation delay in the process of propagation are not considered. It is hard to control the propagation of computer singularity virus with the current methods and the ability of defense is poor. For the case of infectious vector and propagation delay, a new SIS propagation model is proposed based on mean field theory. The influence of computer virus infectious vector and propagation delay in complex sensor net-works on the propagation property is analyzed. A new cellular automata model is built to simulate the whole process of computer virus propagation. By the information of abstraction layer from computer singularity virus detection model based on immunization principle, a fusion method for the singularity virus detection is proposed. Through the fusion of detection results of different antigen presentation gene library, the ability of defense of computer singularity virus propagation is improved. Experimental results show that target immune network connectivity factor ratio of our method is only 0.18, lower than 0.37 multiples of nearest neighbor immunity. Which indicates that viral immune infection density of our method is low. Therefore, our method can effectively inhibit the spread of the virus.
    Keywords: Complex sensor network; Computer; Singularity; Virus Propagation Defense.

  • Outlier data mining of multivariate time series based on association rule mapping   Order a copy of this article
    by Yong-jun QIN, Arun Kumar Sangaiah 
    Abstract: In the outlier data mining with traditional methods, as the data is complex, the outlier data is not effectively classified, which increase the complexity of data classification and reduce the precision of data mining. In this paper, an outlier data mining method of time series based on association mapping is proposed. By using association rule mapping between data sets, the association rule of data sets is determined. The mining factor and relative error are introduced to improve the precision of data mining. The shuffled frog leaping clustering algorithm is applied to cluster the mining factor. The cluster-based multivariate time series classification is used for classification of clusters based on training set category of time series combined with modified K-nearest neighbor algorithm to achieve classification of time series data and outlier data mining. Experimental results show that running time is only 12.9s when the number of data sets is 200. Compared with traditional methods, our proposed method can effectively improve the precision of data mining.
    Keywords: Association rule mapping; multivariate; time series; data mining; k nearest neighbor algorithm; clustering.

  • RELIABILITY IN IoUT ENABLED UNDERWATER SENSOR NETWORKS USING DYNAMIC ADAPTIVE ROUTING PROTOCOL   Order a copy of this article
    by Jasem M. Alostad 
    Abstract: In recent years, the applications of the Internet of Underwater Things (IoUT) have meant under water wireless sensor networks (UWSN) are suffering mainly from a reduced network lifetime. Other challenges in the underwater sensor network include: limited bandwidth, high attenuation, high path loss, limited battery life and so on. The main focus of this paper is to consider a trade-off between the energy consumption and network lifetime. This paper proposes an optimal routing protocol called the Energy Dynamic Adaptive Routing (DAR) protocol. The DAR protocol maintains a trade-off between the reliability or packet delivery ratio (PDR) of sensor nodes and bit error ratio (BER) using an optimal dynamic adaptive routing approach. The proposed approach operates on three different phases, namely: initialization, dynamic routing and transmission. During the initial phase, all the nodes in the UWSN share location and residual energy information among all the nodes in the network. During the dynamic routing phase, an optimal directed acyclic graph (DAG) based route selection is exploited to select the neighbour and successor nodes. This facilitates the successive routing to transmit the packets from one node to another. Here, the cost function with a directed acyclic graph is utilized for better transmission of packets. The experimental results with BEAR show that the proposed method deals with the issues raised in the conventional protocol and improve the reliability of packets with higher BER.
    Keywords: Under Water Sensor Network; Internet of Things; Directed Acyclic Graph; Dynamic Adaptive Routing.

  • Trust based Fruit Fly Optimization Algorithm (TFOA) for Task Scheduling in a Cloud Environment   Order a copy of this article
    by Priya Govindaraj, Jaisankar Natarajan 
    Abstract: Efficient task scheduling plays a critical role in cloud computing environment.In this paper, we proposed a novel trust based fruit fly optimization(TFOA) algorithm for task scheduling .Even though traditional scheduling algorithms, namely First come First serve, Round Robin, Ant colony optimization and so on are used broadly in cloud computing process but still efficient scheduling is not achieved. In general cloud service provider desires to receive the customer task in a faster rate and the resource allocation to the task is to be done in a proper way. In this proposed work, tasks are allocated on the most trustworthy resource by using TFOA. Simulation outcomes show that the proposed algorithm performs better than the existing transitional algorithms like Round robin and Particle Swarm Optimization (PSO) in terms of reduced makespan and turnaround time and efficient resource utilization.
    Keywords: Task scheduling; Fruit Fly optimization; Trust; Makespan; Turnaround time;.

  • Multi-source Remote Sensing Image Big Data Classification System Design in Cloud Computing Environment   Order a copy of this article
    by Xuan Yue Tong 
    Abstract: Due to the problems of poor classification and time-consuming in traditional multi-source remote sensing image big data classification system, it cannot meet the standard requirements for image big data classification in related fields. To solve the above problems, the multi-source remote sensing image data classification system under cloud computing environment is optimized. Following the line string transmission protocol architecture, relevant information is processed, transformed and fused. Data are transported to the host through protocol transmission. Based on above principle, the system hardware and software are designed. Detailedly, designing hardware system refers to designing image sensor interface and system processing interface. The design of the system software part can be divided into two parts, including the two-wire serial protocol formulation and the image big data classification algorithm that provides users with initialization operations. At the same time, the image is sharpened and the pixels are improved. Experimental verification results show that the system has good processing effect and short time consumption.
    Keywords: Cloud computing environment; Multi-source remote sensing; Image big data; Classification system.

  • Research and Analysis on Sensitive Data Encryption Method in Accounting Information Processing System   Order a copy of this article
    by Heng Li 
    Abstract: In order to protect the confidentiality and integrity of sensitive data in accounting information processing system, it was necessary to study the sensitive data encryption method. The current encryption method was mainly used different technology to make encryption for the sensitivity of sensitive data, which caused a problem of poor security. In order to improve the security of encryption, a hybrid encryption method for sensitive data of accounting information processing system was proposed. Firstly, the sensitive data was preprocessed. Then, based on the elliptic curve encryption mechanism, the additive and multiplicative homomorphic encryption methods of sensitive data were constructed respectively. Experimental results showed that the cryptographic running time obtained by our proposed method was relatively small and the increase in decryption computation overhead was smaller than the traditional method. Which was good to improve encryption security.
    Keywords: Accounting information processing system; sensitive data; encryption methods; homomorphic encryption; elliptic curve encryption mechanism.