ISSN: 2312-8623
Submit Article
Submission Instructions
Open Access Information
Ethics and Malpractice Statement
Most Recent Issue
2020
Issue 14Issue 13
2017
Issue 12Issue 11
2016
Issue 10Issue 9Issue 8Issue 7
2015
Issue 6Issue 5Issue 4Issue 3Issue 2Issue 1

EAI Endorsed Transactions on Collaborative Computing is an open access, peer-reviewed scholarly journal focused on theoretical foundations, methodologies, and algorithms supporting collaborative networks, applications, and work-sharing. The journal publishes research articles, review articles, commentaries, editorials, technical articles, and short communications with a triannual frequency. Authors are not charged for article submission and processing.

Editor(s)-in-Chief: Honghao Gao and Xinheng Wang

With the recent advances in computing and information technologies, we are seeing unprecedented opportunities for increased electronic collaborations among individuals and distributed teams of humans, computer systems and applications, and/or a highly heterogeneous set of computing devices. Computing technologies have continued to evolve from standalone tools, to open systems and from general purpose tools to specialized collaboration grids and infrastructures that facilitate intensive collaboration in multi-organizational settings, as well as in the context of global scale social interactions and worksharing.

Such collaborations are enabling large and globally dispersed organizations to achieve a much higher level of productivity and jointly produce innovative and powerful products that would be impossible to develop without the contributions of multiple collaborators. Novel collaboration solutions that fully realize the promises of electronic collaboration, and pushes the limits of human endeavor, productivity and discovery require innovations and advancements in broad areas of computing including networking, systems and applications, user interfaces and interaction paradigms, and seamless interoperation among system, network and application-specific components and tools.

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

  • Theoretical foundations and algorithms for collaborative networks, applications, and worksharing
  • Architectures, protocols, and enabling technologies for collaborative networks, systems and applications
  • Autonomic computing and quality of services in collaborative networks, systems, and applications
  • Collaboration in context-aware, pervasive, cloud computing, social networking, and cyber physical environments
  • Collaborative multimedia systems/applications, large scale databases and Big Data
  • Collaboration in e-health, e-learning, e-government, and digital libraries
  • Collaborative network infrastructures such as body area networks, wireless sensor networks, VANETS, mobile networks, etc.
  • Models and mechanisms for real-time and large scale collaboration, information sharing and worksharing
  • Security, privacy, resiliency/survivability and trust management in collaborative networks, systems, and applications
  • Simulation, performance evaluation, experiments, and case studies of collaborative environments
  • Collaborative web services technologies, business processes, workflows, and service-oriented systems and architectures

.

Song Guo (The University of Aizu) Kui Wu (University of Victoria) Cong Wang (City University of Hong Kong) Robert Birke (IBM Research Zurich) Dimitrios Koutsonikolas (University at Buffalo, SUNY) Andreas Petlund (Simula Research Laboratory) Shervin Shirmohammadi (University of Ottawa) Razib Iqbal (Missouri State University) Aiman Erbad (Qatar University) Ali A Nazari Shirehjini (Sharif University of Technology) Dewan Ahmed (University of North Carolina at Charlotte) Edith Ngai (Uppsala University) Xiaoxian Yang (SSPU)

.


  • A Hybrid Service Ranking Based Collaborative Filtering Model on Cloud Web Service Data

    Appears in:
    cc 21(14): e4

    Authors:
    Y. Prasanth, Suvarna S. Pawar

    Published:
    26th Oct 2021

    Abstract:
    INTRODUCTION: Trust is an important indicator in the cloud computing environment for service selection and recommendation. It is a difficult task to create a composite value-added service from several candidate services for the desired objectives due to the dramatic growth in services that have similar functionalities. OBJECTIVES: This research aims to design a hybrid service feature ranking; cloud service ranking are computed using the advanced contextual service ranking measures. A hybrid collaborative approach is totally based on confidence to the QoS web service prediction. METHODS: A new service ranking similarity computation is optimized for the cloud-based service selection. This collaborative filtering measure is used to check the top k customer selection by performing the top-k customer selection estimation on the cloud service ranking. RESULTS: The proposed method is useful in the prediction of QoS values and helps with optimal service ranking. As a result, similar/ relating cloud services are increasing, making it extremely complex to select the best cloud service among the relevant / similar services available. CONCLUSION: The state-of the-art approaches are proposed and tested on a mathematical QoS-Aware assessment framework. The use of semantic matching technique and QoS for web service ranking satisfies user requirements for web service recommendations. In addition, users require a web service not only based on functionality, but also based on high quality.

  • Seizure Classification Using Person-Specific Triggers

    Appears in:
    cc 21(14): e3

    Authors:
    Y. Zhang, M. Zolgharni, J. Pordoy, N. Matoorian

    Published:
    4th Feb 2021

    Abstract:
    Introduction: With advancements in personalised medicine, healthcare delivery systems have moved away from the one-size-fits-all approach, towards tailored treatments that meet the needs of individuals and specific subgroups. As nearly one-third of those diagnosed with epilepsy are classed as refractory and are resistant to antiepileptic medication, there is need for a personalised method of detecting epileptic seizures. Epidemiological studies show that up to 91% of those diagnosed identify one or more epilepsy related trigger as the causation behind their seizure onset. These triggers are person-specific and affect those diagnosed in different ways dependent on their idiosyncratic tolerance and threshold levels. Whilst these triggers are known to induce seizure onset, only a few studies have even considered their use as a preventive component, and whether they could be used as an additional sensing modality for non-EEG detection mechanisms. Objectives: 1. To record person-specific triggers (PST) from participants using IoT-enabled sensors and smart devices. 2. To train and test several dedicated machine learning models using a single participants data, 3. To conduct a comparative analysis and evaluate the performance of each model, 4. Formulate a conclusion as to whether PST could be used to improve on current methods of non-EEG seizure detection. Methodology: This study uses a precision approach combined with machine learning, to train and test several dedicated algorithms that can predict epileptic seizures. Each model is designed for a single participant, enabling a personalised method of classification unseen in non-EEG detection research. Results: Our results show accuracy, sensitivity, and specificity scores of 94.73%, 96.90% and 93.33% for participant 1 and 96.87%, 96.96% and 96.77% for participant 2, respectively. Conclusion: To conclude, this preliminary study has observed a noticeable correlation between the documented triggers and each participants seizure onset, indicating that PST have the potential to be used as an additional non-EEG sensing modality when classifying epileptic seizures.

  • A computing method of predictive value based on fitting function in linear model

    Appears in:
    cc 20(14): e2

    Authors:
    Hao Zhong, Fei Jia, Huibing Zhang

    Published:
    2nd Oct 2020

    Abstract:
    Linear models are common prediction models in collaborative computing, which mainly generates fitting function to express the relationship between feature vectors and predictive value. In the process of computing the predictive value according to the fitting function and feature vector, this paper mainly conducted the following researches. Firstly, this paper defines a change interval of predictive value according to training set. Secondly, in this paper, the change interval of predictive value corresponding to feature vector in test setis computed. Finally, according to distribution of training set in the changing interval, the predictive values corresponding to feature vectors in test set are computed. Standard data sets are used in experiment, and MAE(Mean Absolute Error) and RMSE(Root Mean Square Error) are used to evaluate the prediction results. The experimental results show that the method proposed in this paper can improve the prediction error to acertain extent.

  • VTWM: An Incremental Data Extraction Model Based on Variable Time-Windows

    Appears in:
    cc 20(14): e1

    Authors:
    Jie Liu, Guiling Wang, Weixing Jia, Yang Xu

    Published:
    9th Sep 2020

    Abstract:
    Continuously extracting and integrating changing data from various heterogeneous systems based on an appropriate data extraction model is the key to data sharing and integration and also the key to building an incremental data warehouse for data analysis. The traditional data capture method based on timestamp changes is plagued with anomalies in the data extraction process, which leads to data extraction failure and affects the efficiency of data extraction. To address the above problems, this paper improves the traditional data capture model based on timestamp increments and proposes VTWM, an incremental data extraction model based on variable time-windows, based on the idea of extracting a small number of duplicate records before removing duplicate values. The model reduces the influence of abnormalities on data extraction, improves the reliability of the traditional data extraction ETL processes, and improves the data extraction efficiency.

  • VTWM: An Incremental Data Extraction Model Based on Variable Time-Windows

    Appears in:
    cc 20(14): e1

    Authors:
    Jie Liu, Guiling Wang, Weixing Jia, Yang Xu

    Downloads:
    12

    Abstract:
    Continuously extracting and integrating changing data from various heterogeneous systems based on an appropriate data extraction model is the key to data sharing and integration and also the key to building an incremental data warehouse for data analysis. The traditional data capture method based on timestamp changes is plagued with anomalies in the data extraction process, which leads to data extraction failure and affects the efficiency of data extraction. To address the above problems, this paper improves the traditional data capture model based on timestamp increments and proposes VTWM, an incremental data extraction model based on variable time-windows, based on the idea of extracting a small number of duplicate records before removing duplicate values. The model reduces the influence of abnormalities on data extraction, improves the reliability of the traditional data extraction ETL processes, and improves the data extraction efficiency.

  • A Hybrid Service Ranking Based Collaborative Filtering Model on Cloud Web Service Data

    Appears in:
    cc 21(14): e4

    Authors:
    Suvarna S. Pawar, Y. Prasanth

    Downloads:
    8

    Abstract:
    INTRODUCTION: Trust is an important indicator in the cloud computing environment for service selection and recommendation. It is a difficult task to create a composite value-added service from several candidate services for the desired objectives due to the dramatic growth in services that have similar functionalities. OBJECTIVES: This research aims to design a hybrid service feature ranking; cloud service ranking are computed using the advanced contextual service ranking measures. A hybrid collaborative approach is totally based on confidence to the QoS web service prediction. METHODS: A new service ranking similarity computation is optimized for the cloud-based service selection. This collaborative filtering measure is used to check the top k customer selection by performing the top-k customer selection estimation on the cloud service ranking. RESULTS: The proposed method is useful in the prediction of QoS values and helps with optimal service ranking. As a result, similar/ relating cloud services are increasing, making it extremely complex to select the best cloud service among the relevant / similar services available. CONCLUSION: The state-of the-art approaches are proposed and tested on a mathematical QoS-Aware assessment framework. The use of semantic matching technique and QoS for web service ranking satisfies user requirements for web service recommendations. In addition, users require a web service not only based on functionality, but also based on high quality.

  • A computing method of predictive value based on fitting function in linear model

    Appears in:
    cc 20(14): e2

    Authors:
    Hao Zhong, Fei Jia, Huibing Zhang

    Downloads:
    6

    Abstract:
    Linear models are common prediction models in collaborative computing, which mainly generates fitting function to express the relationship between feature vectors and predictive value. In the process of computing the predictive value according to the fitting function and feature vector, this paper mainly conducted the following researches. Firstly, this paper defines a change interval of predictive value according to training set. Secondly, in this paper, the change interval of predictive value corresponding to feature vector in test setis computed. Finally, according to distribution of training set in the changing interval, the predictive values corresponding to feature vectors in test set are computed. Standard data sets are used in experiment, and MAE(Mean Absolute Error) and RMSE(Root Mean Square Error) are used to evaluate the prediction results. The experimental results show that the method proposed in this paper can improve the prediction error to acertain extent.

  • Seizure Classification Using Person-Specific Triggers

    Appears in:
    cc 21(14): e3

    Authors:
    Y. Zhang, M. Zolgharni, J. Pordoy, N. Matoorian

    Downloads:
    4

    Abstract:
    Introduction: With advancements in personalised medicine, healthcare delivery systems have moved away from the one-size-fits-all approach, towards tailored treatments that meet the needs of individuals and specific subgroups. As nearly one-third of those diagnosed with epilepsy are classed as refractory and are resistant to antiepileptic medication, there is need for a personalised method of detecting epileptic seizures. Epidemiological studies show that up to 91% of those diagnosed identify one or more epilepsy related trigger as the causation behind their seizure onset. These triggers are person-specific and affect those diagnosed in different ways dependent on their idiosyncratic tolerance and threshold levels. Whilst these triggers are known to induce seizure onset, only a few studies have even considered their use as a preventive component, and whether they could be used as an additional sensing modality for non-EEG detection mechanisms. Objectives: 1. To record person-specific triggers (PST) from participants using IoT-enabled sensors and smart devices. 2. To train and test several dedicated machine learning models using a single participants data, 3. To conduct a comparative analysis and evaluate the performance of each model, 4. Formulate a conclusion as to whether PST could be used to improve on current methods of non-EEG seizure detection. Methodology: This study uses a precision approach combined with machine learning, to train and test several dedicated algorithms that can predict epileptic seizures. Each model is designed for a single participant, enabling a personalised method of classification unseen in non-EEG detection research. Results: Our results show accuracy, sensitivity, and specificity scores of 94.73%, 96.90% and 93.33% for participant 1 and 96.87%, 96.96% and 96.77% for participant 2, respectively. Conclusion: To conclude, this preliminary study has observed a noticeable correlation between the documented triggers and each participants seizure onset, indicating that PST have the potential to be used as an additional non-EEG sensing modality when classifying epileptic seizures.
Publisher
EAI
ISSN
2312-8623
Number of Volumes
4
Last Published
2022-08-02
EAI Logo

About EAI

Community

Publish with EAI