JBJohn Byabazaire

John Byabazaire

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


John Byabazaire has a total of 24 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A low-cost modular precision irrigation system for resource-constrained environments

    by Benedict Oyo, Allan Junior Asiku, Daniel Ogenrwot, Victor Paul Kawagga, John Byabazaire, Christine Kalumera Akello


  • Split Learning Based GAN Training for Non-IID Federated Learning

    by Joana Tirana, Andreas Chouliaras, Theodoros Aslanidis, John Byabazaire, Spyridon Mastorakis, Dimitris Chatzopoulos

  • Open Access

    A Comprehensive Approach to Assessing Yield Map Quality in Smart Agriculture: Void Detection and Spatial Error Mapping

    by John Byabazaire, Gregory M. P. O’hare, Rem Collier, Chamil Kulatunga, Declan Delaney

    Smart agriculture relies on accurate yield maps as a crucial tool for decision-making. Many yield maps, however, suffer from spatial errors that can compromise the quality of their data, while several approaches have been proposed to address some of these errors, detecting voids or holes in the maps remains challenging. Additionally, the quality of yield datasets is typically evaluated based on root mean squared errors after interpolation. This evaluation method relies on weighbridge data, which can occasionally be inaccurate, impacting the quality of decisions made using the datasets. This paper introduces a novel algorithm designed to identify voids in yield maps. Furthermore, it maps three types of spatial errors (GPS errors, yield surges, and voids) to two standard data quality dimensions (accuracy and completeness). Doing so provides a quality score that can be utilized to assess the quality of yield datasets, eliminating the need for weighbridge data. The paper carries out three types of evaluations: (1) evaluating the algorithm’s efficacy by applying it to a dataset containing fields with and without voids; (2) assessing the benefits of integrating void detection and other spatial error identification techniques into the yield data processing chain; and (3) examining the correlation between root mean squared error and the proposed quality score before and after filtering out spatial errors. The results of the evaluations demonstrate that the proposed algorithm achieves a 100% sensitivity, 91% specificity, and 82% accuracy in identifying yield maps with voids. Additionally, there is a decrease in the root mean squared error when various spatial errors, including voids after applying the proposed data pre-processing chain. The inverse correlation observed between the root mean squared error and the proposed quality score (−0.577 and −0.793, before and after filtering spatial errors, respectively) indicates that the quality score can effectively assess the quality of yield datasets. This assessment enables seamless integration into real-time big data quality assessment solutions based on various data quality dimensions.


  • Open Access

    IoT Data Quality Assessment Framework Using Adaptive Weighted Estimation Fusion

    by John Byabazaire, Gregory M. P. O’hare, Rem Collier, Declan Delaney

    Timely data quality assessment has been shown to be crucial for the development of IoT-based applications. Different IoT applications’ varying data quality requirements pose a challenge, as each application requires a unique data quality process. This creates scalability issues as the number of applications increases, and it also has financial implications, as it would require a separate data pipeline for each application. To address this challenge, this paper proposes a novel approach integrating fusion methods into end-to-end data quality assessment to cater to different applications within a single data pipeline. By using real-time and historical analytics, the study investigates the effects of each fusion method on the resulting data quality score and how this can be used to support different applications. The study results, based on two real-world datasets, indicate that Kalman fusion had a higher overall mean quality score than Adaptive weighted fusion and Naïve fusion. However, Kalman fusion also had a higher computational burden on the system. The proposed solution offers a flexible and efficient approach to addressing IoT applications’ diverse data quality needs within a single data pipeline.


  • Open Access

    End-to-End Data Quality Assessment Using Trust for Data Shared IoT Deployments

    by John Byabazaire, Gregory M.P. O'HAre, Declan T. Delaney

    Continued development of communication technologies has led to widespread Internet-of-Things (IoT) integration into various domains, including health, manufacturing, automotive, and precision agriculture. This has further led to the increased sharing of data among such domains to foster innovation. Most of these IoT deployments, however, are based on heterogeneous, pervasive sensors, which can lead to quality issues in the recorded data. This can lead to sharing of inaccurate or inconsistent data. There is a significant need to assess the quality of the collected data, should it be shared with multiple application domains, as inconsistencies in the data could have financial or health ramifications. This article builds on the recent research on trust metrics and presents a framework to integrate such metrics into the IoT data cycle for real-time data quality assessment. Critically, this article adopts a mechanism to facilitate end-user parameterization of a trust metric tailoring its use in the framework. Trust is a well-established metric that has been used to determine the validity of a piece or source of data in crowd-sourced or other unreliable data collection techniques such as that in IoT. The article further discusses how the trust-based framework eliminates the requirement for a gold standard and provides visibility into data quality assessment throughout the big data model. To qualify the use of trust as a measure of quality, an experiment is conducted using data collected from an IoT deployment of sensors to measure air quality in which low-cost sensors were colocated with a gold standard reference sensor. The calculated trust metric is compared with two well-understood metrics for data quality, root mean square error (RMSE), and mean absolute error (MAE). A strong correlation between the trust metric and the comparison metrics shows that trust may be used as an indicative quality metric for data quality. The metric incorporates the additional benefit of its ability for use in low context scenarios, as opposed to RMSE and MAE, which require a reference for comparison.


  • Open Access

    Data Quality and Trust: Review of Challenges and Opportunities for Data Sharing in IoT

    by John Byabazaire, Gregory O’hare, Declan Delaney

    Existing research recognizes the critical role of quality data in the current big-data and Internet of Things (IoT) era. Quality data has a direct impact on model results and hence business decisions. The growth in the number of IoT-connected devices makes it hard to access data quality using traditional assessments methods. This is exacerbated by the need to share data across different IoT domains as it increases the heterogeneity of the data. Data-shared IoT defines a new perspective of IoT applications which benefit from sharing data among different domains of IoT to create new use-case applications. For example, sharing data between smart transport and smart industry can lead to other use-case applications such as intelligent logistics management and warehouse management. The benefits of such applications, however, can only be achieved if the shared data is of acceptable quality. There are three main practices in data quality (DQ) determination approaches that are restricting their effective use in data-shared platforms: (1) most DQ techniques validate test data against a known quantity considered to be a reference; a gold reference. (2) narrow sets of static metrics are used to describe the quality. Each consumer uses these metrics in similar ways. (3) data quality is evaluated in isolated stages throughout the processing pipeline. Data-shared IoT presents unique challenges; (1) each application and use-case in shared IoT has a unique description of data quality and requires a different set of metrics. This leads to an extensive list of DQ dimensions which are difficult to implement in real-world applications. (2) most data in IoT scenarios does not have a gold reference. (3) factors endangering DQ in shared IoT exist throughout the entire big-data model from data collection to data visualization, and data use. This paper aims to describe data-shared IoT and shared data pools while highlighting the importance of sharing quality data across various domains. The article examines how we can use trust as a measure of quality in data-shared IoT. We conclude that researchers can combine such trust-based techniques with blockchain for secure end-to-end data quality assessment.


  • Using Trust as a Measure to Derive Data Quality in Data Shared IoT Deployments

    by John Byabazaire, Gregory O'Hare, Declan Delaney

    Recent developments in Internet of Things have heightened the need for data sharing across application domains to foster innovation. As most of these IoT deployments are based on heterogeneous sensor types, there is increased scope for sharing erroneous, inaccurate or inconsistent data. This in turn may lead to inaccurate models built from this data. It is important to evaluate this data as it is collected to establish its quality. This paper presents an analysis of data quality as it is represented in Internet of Things (IoT) systems and some of the limitations of this representation. The paper then introduces the use of trust as a heuristic to drive data quality measurements. Trust is a well-established metric that has been used to determine the validity of a piece or source of data in crowd sourced or other unreliable data collection techniques. The analysis extends to detail an appropriate framework for representing data quality within the big data model. To demonstrate the application of a trust backed framework, we used data collected from a IoT deployment of sensors to measure air quality in which a low cost sensor was co-located with a gold reference sensor. Using data streams modeled based on a dataset from an IoT deployment, our initial results show that the framework’s trust score are consistent with the accuracy measure of the machine learning models.


  • Data Quality and Trust : A Perception from Shared Data in IoT

    by John Byabazaire, Gregory O'Hare, Declan Delaney

    Internet of Things devices and data sources areseeing increased use in various application areas. The pro-liferation of cheaper sensor hardware has allowed for widerscale data collection deployments. With increased numbers ofdeployed sensors and the use of heterogeneous sensor typesthere is increased scope for collecting erroneous, inaccurate orinconsistent data. This in turn may lead to inaccurate modelsbuilt from this data. It is important to evaluate this data asit is collected to determine its validity. This paper presents ananalysis of data quality as it is represented in Internet of Things(IoT) systems and some of the limitations of this representation. The paper discusses the use of trust as a heuristic to drive dataquality measurements. Trust is a well-established metric that hasbeen used to determine the validity of a piece or source of datain crowd sourced or other unreliable data collection techniques. The analysis extends to detail an appropriate framework forrepresenting data quality effectively within the big data modeland why a trust backed framework is important especially inheterogeneously sourced IoT data streams.


  • Top Cited Papers
    Open Access

    Machine learning based fog computing assisted data-driven approach for early lameness detection in dairy cattle

    by Mohit Taneja, John Byabazaire, Nikita Jalodia, Alan Davy, Cristian Olariu, Paul Malone


  • Connected Cows: Utilizing Fog and Cloud Analytics toward Data-Driven Decisions for Smart Dairy Farming

    by Mohit Taneja, Nikita Jalodia, Paul Malone, John Byabazaire, Alan Davy, Cristian Olariu

    The Internet of Things (IoT) is about connecting people, processes, data, and things, and is changing the way we monitor and interact with things. An active incorporation of information and communication technology coupled with sophisticated data analytics approaches has the potential to transform some of the oldest industries in the world, including dairy farming. It presents a great opportunity for verticals such as the dairy industry to increase productivity by getting actionable insights to improve farming practices, thereby increasing efficiency and yield. Dairy farms have all the constraints of a modern business -- they have a fixed production capacity, a herd to manage, expensive farm labor, and other varied farm-related processes to take care of. In this technology-driven era farmers look for assistance from smart solutions to increase profitability and to help manage their farms well. We present an end-to-end IoT application system with fog assistance and cloud support that analyzes data generated from wearables on cows' feet to detect anomalies in animal behavior that relate to illness such as lameness. The solution leverages behavioral analytics to generate early alerts toward the animals' well being, thus assisting the farmer in livestock monitoring. This in turn also helps in increasing productivity and milk yield by identifying potential diseases early on. The project specializes in detecting lameness in dairy cattle at an early stage, before visible signs appear to the farmer or an animal expert. Our trial results in a real-world smart dairy farm setup, consisting of a dairy herd of 150 cows in Ireland, demonstrate that the designed system delivers a lameness detection alert up to three days in advance of manual observation.