The Experts below are selected from a list of 5913 Experts worldwide ranked by ideXlab platform

Deepak Divan - One of the best experts on this subject based on the ideXlab platform.

  • reducing energy consumption in industrial plants using behind the meter conservation voltage reduction
    European Conference on Cognitive Ergonomics, 2018
    Co-Authors: Sathish Jayaraman, Mohammadreza Miranbeigi, Prasad Kandula, Trevor L Grant, Deepak Divan
    Abstract:

    This paper explores the benefits of behind the meter conservation voltage reduction (CVR) in industrial environment. It discusses how the energy savings are realized with AC motors – the predominant load in industrial plants, through simulation and experimental results. The paper presents two methods to measure conservation voltage reduction factor (CVR f ) levels at the customer end. The first approach that is purely based on ambient feeder measurements to investigate CVR factor levels is discussed and an experimentally validated Analytics Technique is applied to extract CVR factor from high-resolution field data from an industrial plant. The second method based on a ‘clamp-on voltage injection’ approach to investigate CVR factor levels precisely at the point of change is also discussed. Experimental validation of the ‘clamp-on’ voltage injection device has been shown. Such methods can be used to evaluate potential energy savings in a plant before the installation of a CVR implementation device.

  • reducing energy consumption in industrial plants using behind the meter conservation voltage reduction
    European Conference on Cognitive Ergonomics, 2018
    Co-Authors: Sathish Jayaraman, Mohammadreza Miranbeigi, Prasad Kandula, Trevor L Grant, Deepak Divan
    Abstract:

    This paper explores the benefits of behind the meter conservation voltage reduction (CVR) in industrial environment. It discusses how the energy savings are realized with AC motors – the predominant load in industrial plants, through simulation and experimental results. The paper presents two methods to measure conservation voltage reduction factor (CVR f ) levels at the customer end. The first approach that is purely based on ambient feeder measurements to investigate CVR factor levels is discussed and an experimentally validated Analytics Technique is applied to extract CVR factor from high-resolution field data from an industrial plant. The second method based on a ‘clamp-on voltage injection’ approach to investigate CVR factor levels precisely at the point of change is also discussed. Experimental validation of the ‘clamp-on’ voltage injection device has been shown. Such methods can be used to evaluate potential energy savings in a plant before the installation of a CVR implementation device.

Ana Reyesmenendez - One of the best experts on this subject based on the ideXlab platform.

  • comparing a traditional approach for financial brand communication analysis with a big data Analytics Technique
    IEEE Access, 2019
    Co-Authors: Jose Ramon Saura, Beatriz Rodriguez Herraez, Ana Reyesmenendez
    Abstract:

    Although large amounts of data are now available to companies, mere possession of these data is not sufficient, and for better business decisions, it is necessary to perform thorough data analysis. Nowadays, social networks services (SNS) have become important data sources. The rapid growth of SNS has led to their wide use in various research trends in social sciences. In this paper, we aim to enhance the current understanding of the possibilities offered by social data for brand communication analysis in the financial sector. To this end, a traditional methodology and a digital methodology are used to investigate the brand image of the financial entities. The traditional methodology is the Periodic Evaluation of the Image (PEI). The digital methodology is sentiment analysis, a machine learning Technique for big data Analytics in social sciences using an algorithm developed in Python. The data are analyzed using both methodologies, and then, their results are compared. The findings suggest that while the results obtained using the method based on big data are consistent with the results obtained with the traditional methodology, the former method allows for easier and faster data analysis. The limitations of this paper relate to the size of the sample, the studied sector, and the scope of the reviewed literature.

Periklis Andritsos - One of the best experts on this subject based on the ideXlab platform.

  • a process mining based model for customer journey mapping
    Conference on Advanced Information Systems Engineering, 2017
    Co-Authors: Gaël Bernard, Periklis Andritsos
    Abstract:

    Customer journey maps (CJMs) are used to understand customers’ behavior, and ultimately to better serve them. This new approach is used in numerous disciplines for different purposes. As a response, several software applications have emerged. Although they provide interfaces to understand CJMs, they lack measures to assist in decision making. We contribute by proposing a CJM model. We show its potential by using it with process mining, a data Analytics Technique that we leverage to assess the impact of the journey’s duration on the customer experience. The model brings data scientists and customer journey planners closer together, the first step in gaining a better understanding of customer behavior. This study also highlights the prospective value of process mining for CJM analysis.

Atif Alamri - One of the best experts on this subject based on the ideXlab platform.

  • harnessing the power of big data Analytics in the cloud to support learning Analytics in mobile learning environment
    Computers in Human Behavior, 2019
    Co-Authors: Mohammad Shorfuzzaman, Shamim M Hossain, Amril Nazir, Ghulam Muhammad, Atif Alamri
    Abstract:

    Abstract Technology enhanced learning (TEL) such as online learning environment with adaptive technologies has gained growing interest in recent past in the field of teaching and learning. In this context, mobile learning has got much momentum and is exemplified by diverse characteristics associated with the technologies and devices used, the enormous size of data generated throughout a learning session, and the interactions among the learners that occur outside the classroom. Consequently, sophisticated data analysis Techniques are required to handle the intricacy of mobile learning and analyze the vast amount of datasets to enhance the learning experiences of mobile learners. This has led to the adoption of big data Analytics for efficient processing of big learning data to add value to the mobile learning environments. Yet limited processing capability of the mobile devices is another key challenge faced by such big data Analytics in mobile learning environments. To overcome this limitation, certain heavy computational parts could be offloaded to the cloud which can provide enough computation and storage resources. To this end, this paper presents a cloud based mobile learning framework that utilizes big data Analytics Technique to extract values from huge volume of mobile learners' data. Finally, we investigate learners' readiness and driving factors of mobile learning adoption in higher education institutions. In particular, we propose a hypothesized model for mobile learning adoption built on a locally extended technology acceptance model (TAM).

Worring Marcel - One of the best experts on this subject based on the ideXlab platform.

  • Visual Analytics for Temporal Hypergraph Model Exploration
    'Institute of Electrical and Electronics Engineers (IEEE)', 2021
    Co-Authors: Fischer, Maximilian T., Arya Devanshu, Streeb Dirk, Seebacher Daniel, Keim, Daniel A., Worring Marcel
    Abstract:

    Many processes, from gene interaction in biology to computer networks to social media, can be modeled more precisely as temporal hypergraphs than by regular graphs. This is because hypergraphs generalize graphs by extending edges to connect any number of vertices, allowing complex relationships to be described more accurately and predict their behavior over time. However, the interactive exploration and seamless refinement of such hypergraph-based prediction models still pose a major challenge. We contribute Hyper-Matrix, a novel visual Analytics Technique that addresses this challenge through a tight coupling between machine-learning and interactive visualizations. In particular, the Technique incorporates a geometric deep learning model as a blueprint for problem-specific models while integrating visualizations for graph-based and category-based data with a novel combination of interactions for an effective user-driven exploration of hypergraph models. To eliminate demanding context switches and ensure scalability, our matrix-based visualization provides drill-down capabilities across multiple levels of semantic zoom, from an overview of model predictions down to the content. We facilitate a focused analysis of relevant connections and groups based on interactive user-steering for filtering and search tasks, a dynamically modifiable partition hierarchy, various matrix reordering Techniques, and interactive model feedback. We evaluate our Technique in a case study and through formative evaluation with law enforcement experts using real-world internet forum communication data. The results show that our approach surpasses existing solutions in terms of scalability and applicability, enables the incorporation of domain knowledge, and allows for fast search-space traversal. With the proposed Technique, we pave the way for the visual Analytics of temporal hypergraphs in a wide variety of domains.publishe

  • Visual Analytics for Temporal Hypergraph Model Exploration
    2020
    Co-Authors: Fischer, Maximilian T., Arya Devanshu, Streeb Dirk, Seebacher Daniel, Keim, Daniel A., Worring Marcel
    Abstract:

    Many processes, from gene interaction in biology to computer networks to social media, can be modeled more precisely as temporal hypergraphs than by regular graphs. This is because hypergraphs generalize graphs by extending edges to connect any number of vertices, allowing complex relationships to be described more accurately and predict their behavior over time. However, the interactive exploration and seamless refinement of such hypergraph-based prediction models still pose a major challenge. We contribute Hyper-Matrix, a novel visual Analytics Technique that addresses this challenge through a tight coupling between machine-learning and interactive visualizations. In particular, the Technique incorporates a geometric deep learning model as a blueprint for problem-specific models while integrating visualizations for graph-based and category-based data with a novel combination of interactions for an effective user-driven exploration of hypergraph models. To eliminate demanding context switches and ensure scalability, our matrix-based visualization provides drill-down capabilities across multiple levels of semantic zoom, from an overview of model predictions down to the content. We facilitate a focused analysis of relevant connections and groups based on interactive user-steering for filtering and search tasks, a dynamically modifiable partition hierarchy, various matrix reordering Techniques, and interactive model feedback. We evaluate our Technique in a case study and through formative evaluation with law enforcement experts using real-world internet forum communication data. The results show that our approach surpasses existing solutions in terms of scalability and applicability, enables the incorporation of domain knowledge, and allows for fast search-space traversal. With the Technique, we pave the way for the visual Analytics of temporal hypergraphs in a wide variety of domains.Comment: 11 pages, 6 figures, IEEE VIS VAST 2020 - Proceedings of IEEE Conference on Visual Analytics Science and Technology (VAST), 202