Forthcoming articles

International Journal of Spatio-Temporal Data Science

International Journal of Spatio-Temporal Data Science (IJSTDS)

These articles have been peer-reviewed and accepted for publication 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 Articles will not be published until the final proofs are validated by their authors.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.

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

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

International Journal of Spatio-Temporal Data Science (8 papers in press)

Regular Issues

    by S.B. Goyal, Pradeep Bedi 
    Abstract: In the last decade, major complications of big-data-to-IoT are data-management, security and time-management and thus the objective of the research is recognizing with the problems in big data to extend IoT. In order to accord with the data-management problem an ontology-based matching using H matching algorithm is implementing subsequent to Pillar k-means clustering algorithm that segregates meaningful and meaningless information. The time management problem is recognizing with the aid of Hadoop with mapreduce that specifies the location hitherto. Consequently, Triple DES algorithm with WPA is utilized and that is accountable for providing security by the usage of three keys for both the encryption-decryption. On the other hand, WPA is employed to the data integrity to substantiate whether the data is altered. We have applied ontology based on H-Matching algorithm proposed in the sequence of steps: the stop word removal, stemming process, grouping process and the ontolog making for matching. We have proposed the methodology to handle three parameters: Confidentiality, Integrity and Authenticity in the context of Big-data.
    Keywords: Big data and IoT; ontology-based H-matching algorithm; Pillar k-means clustering algorithm; Hadoop framework; Triple-DES (Data Encryption Standard) algorithm; Wireless-Protected-Access (WPA).

  • Post Classification Change Detection based on Feature based Ensemble Classifiers   Order a copy of this article
    by Sowmya D R 
    Abstract: Change detection is a challenging task in the field of remote sensing. Mainly, the change map is used for disaster assessment, monitoring deforestation and urban studies. In this paper, we present a novel method for post classification change detection. Google earth images of 2011 and 2016 of Bangalore East are used for the study. Multiple features such as texture features, morphological features are extracted using Gray Level Co-occurrence Matrix (GLCM) and morphological operations respectively. Linear Discriminant Analysis (LDA) is used to reduce the dimension of the selected features for the training set. Proposed Ensemble Classifier System (ECS) exploits K-Nearest Neighbor (KNN), Support Vector Machine (SVM) and Maximum Likelihood Classifier (MLC). The proposed method adopts the subsample kernel based subtraction technique to find the difference image, this method greatly reduces data complexity compared to per-pixel based image subtraction method.
    Keywords: Change Detection; Dimensionality Reduction Technique; Ensemble Classifier; Feature Extraction; Image Difference.

  • Predictive Reinforcement Learning Algorithm for Unstructured Business Process Optimization: Case of Human Resources Process   Order a copy of this article
    by Samia Chehbi Gamoura 
    Abstract: While many industrial companies have agreed on Business Process Management (BPM) to deal with the collaborative and transversal activities, research efforts remain in premature junctures where some technical defies persevere, particularly in the Unstructured Business Processes (UBP). Companies today face increasing complexities that are root causes for various problems such as time-consuming tasks, exceptions' handling in processes, and continuous changes in activities. This paper introduces a new Machine Learning approach in such a challenging context, with a threefold purpose: decreasing the unexpected actions in processes, reducing the time-consuming of tasks, and increasing the availability of service during the execution of the processes. This paper's research sheds a new insight into UBP, where mutations remain poorly understood in the academic literature but seem to lag behind industrial applications' progress. The methodology proposes a new variant of Reinforcement Learning based on a version-oriented reasoning algorithm to predict the best action to undertake. The experimentation includes validation on an industrial case study about the Human Resources process of recruitment. The preliminary results obtained from the simulation validate the proposed approach's potentiality and reveal how it can maintain its robustness despite unexpected changes during execution. Besides, this research provides a rich literature examination and an in-depth research analysis about the topic to be considered, at least, as a research background for further research works.
    Keywords: unstructured business process; prediction; Machine Learning; Reinforcement Learning.

  • Enforcing IoT Data Verification and Privacy Using Origin Identification Traceability   Order a copy of this article
    by Richard Lomotey 
    Abstract: The Internet of Things (IoT) are addressable objects with built-in sensors that have the ability to collect and transfer data over the Internet. IoT is now widely used across many different industries; and especially in healthcare it helps them with medical process efficiency, enhanced patient service delivery, real-time decision making, and increased care value. These devices continuously deliver data to backend systems for further analysis before intelligent decisions are made. As more devices communicate with each other via the Internet, there is need to determine the origins of the data especially, in situations where trust is paramount such as wearable IoT. It is however difficult to determine data origins in IoT architectures due to the inherent sporadic nature of wireless networks. Also, multiple IoT devices can be generating similar content and it is important to identify individual data sources transparently. Some previous works focus on the request perspective and employed provenance techniques to determine data sources. However, some of these solutions are not robust for a complete message and data exchanges; especially in a request-response scenario where IoT devices are involved. Thus, this paper proposes a combination of policy-based provenance and modelled the peer-to-peer IoT device communication as a graph network. Using the Floyds algorithm, we are able to verify data origins in shortest paths between interconnected IoT devices. The results from multiple practical and real-world evaluations prove the superiority of the proposed work.
    Keywords: Internet of Things (IoT); Sensors; Mobile devices; Floyd’s Algorithm; Wearables; Provenance; Privacy; Verification.

  • Using Blockchain for Trustworthy Mobile Contact Tracing   Order a copy of this article
    by Richard Lomotey, Emmanuel Kaku 
    Abstract: As the number of COVID-19 cases continue to climb globally, lots of public healthcare safety measures are being proposed. Apart from safety measures such as social distancing, mask wearing, and personal hygiene, technological interventions have also been put forward to mitigate the escalating incidents. One of these technological solutions is the deployment of mobile contact tracing applications, which are software deployed on smartphones and sensors with the capability to detect proximate devices using networks such as Bluetooth/Bluetooth Low Energy, Wi-Fi, and GPS. The information collected by the mobile devices are then used to notify custodians who might have come into close contact with an infectious person. However, a major challenge that faces the deployment and acceptance of mobile contact tracing applications by the public is privacy concerns. Some find it intrusive while others are not comfortable with their personal data being collected. In some previous studies, blockchain techniques have been adopted to create privacy-preserving applications that guarantee anonymity. Thus, in our research, we proposed and developed a mobile contact tracing architecture that is blockchain driven with the main aim of ensuring users privacy. The proposed system uses uniquely generated IDs and Bluetooth Low Energy to identify proximate devices that are in close contact. The adoption of blockchain facilitates consensus between the proximate devices so that the system can efficiently keep track of all close contacts. We also used data provenance techniques to keep track of all updates from users based on their COVID-19 health status. Preliminary results from the evaluation of the proposed system shows high accuracy for the determination of close contacts.
    Keywords: Blockchain; Mobile; Trust; Contact Tracing; COVID-19; Provenance; Privacy.

  • A Machine Learning Based Predictive Model for Time-Series Modelling and Analysis   Order a copy of this article
    by Qasem Abu Al-Haija 
    Abstract: Time series modelling and forecasting is an essential field of supervised machine learning because of its appreciated contributions into numerous research and real-life applications including the corporate, commercial, science and engineering applications. Therefore, substantial contributions have been devoted to developing competent predictive models. In this paper, we propose an inclusive time-series predictive model using two modelling techniques, namely; multi-layer feedforward neural networks (FFNN) based delta learning rule model and non-linear auto-regression neural network (NARX) based external input model. The developed models have been trained with least possible prediction error for the 10th order one step ahead predictor for FFNN model and the 50th order two-step ahead predictor for NARX model. As a case study, we have employed the stationary time-series for yearly averaged sunspot activity during the period from 1719-2018. To evaluate the performance of the predictive models, the models have been trained for more than 1000 epochs and have scored the maximum prediction accuracy of more than 99% after 405 epochs recording a mean square error of (2.2 ~6.5)
    Keywords: Data Science; Time-Series; Regression; Forecasting; Neural Network; Generalized Delta Rule; NARX Model; Autocorrelation Function (AFC); Cross-Correlation Function (CCF); prediction accuracy.

Special Issue on: COER-ICAIA-2019 Artificial Intelligence and Applications in Data Science

  • Optimization of Friction Stir Welding Parameters using Combined Taguchi L9 and Genetic Algorithm   Order a copy of this article
    by Devaki Nandan Sharma, Maneesh Tewari 
    Abstract: FSW Friction stir welding is an eco-friendly, energy-efficient solid-state welding procedure invented for highly strength alloys as well as materials that are otherwise difficult for welding through the traditional fusion welding methods. This research paper elaborates on a hybrid Taguchi-Genetic algorithm that optimizes the FSW process parameters to yield favorable electrical conductivity of aluminum alloy AA1350. The optimization parameters considered are travel speed, rotational speed and tool tilt angle. First, the Taguchi method is applied to reduce the number of design experiments and find the optimal set for quality parameters of the system. Subsequently, the genetic algorithm is employed to search for the optimum set of design parameters by using Taguchi solution as the initial population. The results obtained by the proposed method were compared to the outcomes of the conventional Taguchi L9 method and the simple genetic algorithm. The best performance was obtained by the proposed method in 51 iterations, whereas simple genetic algorithm used 182 iterations for the same.
    Keywords: Friction Stir Welding; Optimization; Taguchi Method; Genetic Algorithm.

  • Review of SCADA Based Hybrid Renewable Energy Source Integration   Order a copy of this article
    by AVINASH KALDATE, Amarsingh Kanase-Patil, Shashikant Lokhande 
    Abstract: It is very difficult to meet the energy requirements using a single renewable energy source; it will be easier to build a hybrid system using multiple renewable energy sources. Therefore, a hybrid system may play an important role in the future. But in this it is very important to control all the parameters of the system, so a system that controls all these parameters is essential. Controlling all factors of renewable energy sources is a future requirement, so proper control systems must be implemented on the controllers. The SCADA (Supervisory Control and Data Acquisition system has ability to control the factors of hybrid renewable energy systems. SCADA) provide Human Machine Interface, data acquisition and control over a system. PLC is an element that helps to automate the entire hybrid system. In Renewable sources integration, SCADA and PLC will provide solutions to streamline the system and implement decisions made by the controller. This paper reviews the various benefits of SCADA in making decisions for energy management systems, energy availability, financial and security energy supply to consumers.
    Keywords: SCADA; PLC; Renewable Energy; Web SCADA.