Pub Date : 2023-08-03DOI: 10.1109/icABCD59051.2023.10220478
Sithembiso Dyubele, S. Soobramoney, D. Heukelman
Increased functionalities of smartphones, such as providing easy access to the internet, have offered multiple learning opportunities, especially in a world surrounded by unprecedented periods like COVID'19. Despite the benefits of smartphones mentioned above, academics still have significant concerns about the effective utilisation of these technological devices by students for learning purposes. This paper aims to examine the factors affecting the use of smartphones for learning. The study utilised a quantitative method to pursue its aim and objectives. Data were gathered from 80 academic staff members from five Departments under the Faculty of Accounting & Informatics. A stratified sampling approach was applied to ensure a more realistic and accurate estimation of the population had been used. After applying the above approach, a simple random sampling method was used for this population according to the number of academic staff members in the above-mentioned departments. The data were analysed to ensure reliability and validity, and descriptive statistics were applied, and correlations identified to develop the proposed model. The outcomes indicate that academic staff members believe that Attitudes towards Smartphones, Facilitating Conditions, Perceived Ease of Use, Perceived Usefulness, and Performance Expectations significantly impact the use of smartphones for learning. This study was limited to academic staff from five departments of a single faculty at a South African University of Technology.
{"title":"Factors Affecting the use of Smartphones for Learning: A Proposed Model","authors":"Sithembiso Dyubele, S. Soobramoney, D. Heukelman","doi":"10.1109/icABCD59051.2023.10220478","DOIUrl":"https://doi.org/10.1109/icABCD59051.2023.10220478","url":null,"abstract":"Increased functionalities of smartphones, such as providing easy access to the internet, have offered multiple learning opportunities, especially in a world surrounded by unprecedented periods like COVID'19. Despite the benefits of smartphones mentioned above, academics still have significant concerns about the effective utilisation of these technological devices by students for learning purposes. This paper aims to examine the factors affecting the use of smartphones for learning. The study utilised a quantitative method to pursue its aim and objectives. Data were gathered from 80 academic staff members from five Departments under the Faculty of Accounting & Informatics. A stratified sampling approach was applied to ensure a more realistic and accurate estimation of the population had been used. After applying the above approach, a simple random sampling method was used for this population according to the number of academic staff members in the above-mentioned departments. The data were analysed to ensure reliability and validity, and descriptive statistics were applied, and correlations identified to develop the proposed model. The outcomes indicate that academic staff members believe that Attitudes towards Smartphones, Facilitating Conditions, Perceived Ease of Use, Perceived Usefulness, and Performance Expectations significantly impact the use of smartphones for learning. This study was limited to academic staff from five departments of a single faculty at a South African University of Technology.","PeriodicalId":51314,"journal":{"name":"Big Data","volume":"1 1","pages":"1-7"},"PeriodicalIF":4.6,"publicationDate":"2023-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79004119","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-03DOI: 10.1109/icABCD59051.2023.10220492
Bh Chiloane, S. Akilimalissiga, N. Sukdeo, I. Ohiomah
As the world changes with technological innovation, the retail industry strives to keep up with emerging technologies to remain relevant in the market. Most industries are shifting towards a more automated environment framed by loT applications. Hence, the retail industry is not immune to these innovative applications in order to meet consumers' ever-changing needs and preferences. The South African retail industry is expected to upgrade its systems and advance to technologically advanced retail systems, which have already been implemented in various countries globally. With the implementation of loT technologies around the world, South African retailers are expected to follow suit with the new changes and face the challenges that may arise as a result of the implementation. loT technologies through digital transformation have been portrayed worldwide as an advantageous practice and competition-leveraging tool to promote business agility and capabilities, improve business processes, and, ultimately, enhance customer satisfaction. The purpose of this paper is to assess the level of readiness of the South African retail industry when it comes to moving away from a conventional functional system to a system mainly dominated by advanced technology-based practices. This paper will also examine the specifics and challenges of adopting loT applications from the South African retail industry's standpoint. Hence, the analysis of the acquired results revealed that the South African retail's readiness still has ground to cover to execute loT integration, and this state is orchestrated by various factors.
{"title":"Evaluating the Readiness of Integrating loT into the South African Retail Industry","authors":"Bh Chiloane, S. Akilimalissiga, N. Sukdeo, I. Ohiomah","doi":"10.1109/icABCD59051.2023.10220492","DOIUrl":"https://doi.org/10.1109/icABCD59051.2023.10220492","url":null,"abstract":"As the world changes with technological innovation, the retail industry strives to keep up with emerging technologies to remain relevant in the market. Most industries are shifting towards a more automated environment framed by loT applications. Hence, the retail industry is not immune to these innovative applications in order to meet consumers' ever-changing needs and preferences. The South African retail industry is expected to upgrade its systems and advance to technologically advanced retail systems, which have already been implemented in various countries globally. With the implementation of loT technologies around the world, South African retailers are expected to follow suit with the new changes and face the challenges that may arise as a result of the implementation. loT technologies through digital transformation have been portrayed worldwide as an advantageous practice and competition-leveraging tool to promote business agility and capabilities, improve business processes, and, ultimately, enhance customer satisfaction. The purpose of this paper is to assess the level of readiness of the South African retail industry when it comes to moving away from a conventional functional system to a system mainly dominated by advanced technology-based practices. This paper will also examine the specifics and challenges of adopting loT applications from the South African retail industry's standpoint. Hence, the analysis of the acquired results revealed that the South African retail's readiness still has ground to cover to execute loT integration, and this state is orchestrated by various factors.","PeriodicalId":51314,"journal":{"name":"Big Data","volume":"81 1","pages":"1-6"},"PeriodicalIF":4.6,"publicationDate":"2023-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90944031","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-03DOI: 10.1109/icABCD59051.2023.10220449
G. Nhinda, Fungai Bhunu Shava
Globally, Information Communication Technology (ICT) device usage has seen a steep rise over the last few years. This also holds in developing countries, which have embarked on connecting the unconnected or previously disadvantaged parts of their populations. This connectivity enables people to interact with cyberspace, which brings opportunities and challenges. Opportunities such as the ability to conduct business online, attend online education, and perform online banking activities. Challenges experienced are the cost of Internet access and more worrying cyber-risks and potential for exploitation. There remain pockets of communities that experience sporadic connectivity to cyberspace, these communities tend to be more susceptible to cyber-attacks due to issues of lack/limited awareness of cyber secure practices, an existent culture that might be exploited by cybercriminals, and overall, a lackluster approach to their cyber-hygiene. We present a qualitative study conducted in rural Northern Namibia. Our findings indicate that both secure and insecure cybersecurity practices exist. However, through the Ubuntu and Uushiindaism Afrocentric lenses, practices such as sharing mobile devices without passwords among the community mirror community unity. Practices such as this in mainstream research can be considered insecure. We also propose interrogating “common” secure cybersecurity practices in their universality of applicability.
{"title":"Cybersecurity Practices of Rural Underserved Communities in Africa: A Case Study from Northern Namibia","authors":"G. Nhinda, Fungai Bhunu Shava","doi":"10.1109/icABCD59051.2023.10220449","DOIUrl":"https://doi.org/10.1109/icABCD59051.2023.10220449","url":null,"abstract":"Globally, Information Communication Technology (ICT) device usage has seen a steep rise over the last few years. This also holds in developing countries, which have embarked on connecting the unconnected or previously disadvantaged parts of their populations. This connectivity enables people to interact with cyberspace, which brings opportunities and challenges. Opportunities such as the ability to conduct business online, attend online education, and perform online banking activities. Challenges experienced are the cost of Internet access and more worrying cyber-risks and potential for exploitation. There remain pockets of communities that experience sporadic connectivity to cyberspace, these communities tend to be more susceptible to cyber-attacks due to issues of lack/limited awareness of cyber secure practices, an existent culture that might be exploited by cybercriminals, and overall, a lackluster approach to their cyber-hygiene. We present a qualitative study conducted in rural Northern Namibia. Our findings indicate that both secure and insecure cybersecurity practices exist. However, through the Ubuntu and Uushiindaism Afrocentric lenses, practices such as sharing mobile devices without passwords among the community mirror community unity. Practices such as this in mainstream research can be considered insecure. We also propose interrogating “common” secure cybersecurity practices in their universality of applicability.","PeriodicalId":51314,"journal":{"name":"Big Data","volume":"31 1","pages":"1-7"},"PeriodicalIF":4.6,"publicationDate":"2023-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72963314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-03DOI: 10.1109/icABCD59051.2023.10220544
Joseph Tafataona Mtetwa, K. Ogudo, S. Pudaruth
This paper presents a novel coupled Generative Adversarial Network (GAN) for the optimization of algorithmic trading techniques, termed Visio- Temporal Conditional Generative Adversarial Network (VTCGAN). The termed Visio- Temporal Conditional Generative Adversarial Network combines an Image Generative Adversarial Network and a Multivariate Time Series Generative Adversarial Network, offering an innovative approach for producing realistic and high-quality financial time series and chart patterns. By utilizing the generated synthetic data, the resilience and flexibility of algorithmic trading models can be enhanced, leading to improved decision-making and decreased risk exposure. Although empirical analyses have not yet been conducted, the termed Visio- Temporal Conditional Generative Adversarial Network shows promise as a valuable tool for optimizing algorithmic trading techniques, potentially leading to better performance and generalizability when applied to actual financial records.
{"title":"VTCGAN: A Proposed Multimodal Approach to Financial Time Series and Chart Pattern Generation for Algorithmic Trading","authors":"Joseph Tafataona Mtetwa, K. Ogudo, S. Pudaruth","doi":"10.1109/icABCD59051.2023.10220544","DOIUrl":"https://doi.org/10.1109/icABCD59051.2023.10220544","url":null,"abstract":"This paper presents a novel coupled Generative Adversarial Network (GAN) for the optimization of algorithmic trading techniques, termed Visio- Temporal Conditional Generative Adversarial Network (VTCGAN). The termed Visio- Temporal Conditional Generative Adversarial Network combines an Image Generative Adversarial Network and a Multivariate Time Series Generative Adversarial Network, offering an innovative approach for producing realistic and high-quality financial time series and chart patterns. By utilizing the generated synthetic data, the resilience and flexibility of algorithmic trading models can be enhanced, leading to improved decision-making and decreased risk exposure. Although empirical analyses have not yet been conducted, the termed Visio- Temporal Conditional Generative Adversarial Network shows promise as a valuable tool for optimizing algorithmic trading techniques, potentially leading to better performance and generalizability when applied to actual financial records.","PeriodicalId":51314,"journal":{"name":"Big Data","volume":"34 1","pages":"1-5"},"PeriodicalIF":4.6,"publicationDate":"2023-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84437815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-03DOI: 10.1109/icABCD59051.2023.10220564
Zahir Toufie, Boniface Kabaso
Web browsers have for long been wanting to host and execute feature-rich, compute-intensive, and complex applications or simply Compute-Intensive Applications (CIAs), within their Execution Environment (EE), with native desktop performance. There was Adobe Shockwave, Macromedia Flash, Java Applets, JavaScript Programming Language (JS) and recently WebAssembly Programming Language (WASM), but also short-lived relationships, such as Microsoft ActiveX, Silverlight and Apple Quicktime. One hindrance to web browsers hosting and executing CIAs with native desktop performance is that currently there is no web browser technology with the software architecture and design that can support them. This paper aims to review the evolution of the Web as an application platform since the rise of WASM, over the last decade or so, within the context of application performance relative to that of native desktop application performance. As well as to propose where researchers should focus their efforts in order to advance the Web as an application platform that is capable of executing CIAs. In future work, we plan to extend our study to include theoretical contributions, such as providing insights into how to improve the performance of web applications based on various software architectures and designs for web browser EEs, methodological contributions, such as providing methods and approaches developed, adapted or enhanced which detail the software architecture and design for web browser EEs that have higher performance than currently available, and practical contributions that will lay the groundwork for a production-ready web browser EE based on the prototype web browser EE produced by our study.
{"title":"The Next Evolution of Web Browser Execution Environment Performance","authors":"Zahir Toufie, Boniface Kabaso","doi":"10.1109/icABCD59051.2023.10220564","DOIUrl":"https://doi.org/10.1109/icABCD59051.2023.10220564","url":null,"abstract":"Web browsers have for long been wanting to host and execute feature-rich, compute-intensive, and complex applications or simply Compute-Intensive Applications (CIAs), within their Execution Environment (EE), with native desktop performance. There was Adobe Shockwave, Macromedia Flash, Java Applets, JavaScript Programming Language (JS) and recently WebAssembly Programming Language (WASM), but also short-lived relationships, such as Microsoft ActiveX, Silverlight and Apple Quicktime. One hindrance to web browsers hosting and executing CIAs with native desktop performance is that currently there is no web browser technology with the software architecture and design that can support them. This paper aims to review the evolution of the Web as an application platform since the rise of WASM, over the last decade or so, within the context of application performance relative to that of native desktop application performance. As well as to propose where researchers should focus their efforts in order to advance the Web as an application platform that is capable of executing CIAs. In future work, we plan to extend our study to include theoretical contributions, such as providing insights into how to improve the performance of web applications based on various software architectures and designs for web browser EEs, methodological contributions, such as providing methods and approaches developed, adapted or enhanced which detail the software architecture and design for web browser EEs that have higher performance than currently available, and practical contributions that will lay the groundwork for a production-ready web browser EE based on the prototype web browser EE produced by our study.","PeriodicalId":51314,"journal":{"name":"Big Data","volume":"183 1","pages":"1-7"},"PeriodicalIF":4.6,"publicationDate":"2023-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76639144","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-03DOI: 10.1109/icABCD59051.2023.10220479
Tinashe Crispen Gadzirai, W. T. Vambe
Pneumonia remains the most common reason for inpatient stays and fatalities among adults and children in the world. It became worse during Covid 19 pandemic. Most African countries like South Africa were and are still seriously affected. The situation is worse in rural areas because of several reasons, among them; not having enough X-rays machines, having no or few radiologists to analyze and interpret the X-ray pictures to determine if the pictures are normal pictures or pneumonia. The ability to accurately classify these two types of pneumonia can guarantee effective treatment which will boost survival chances. Artificial Intelligence (AI) is a cost-effective approach and can play a pivotal role in easily analyzing and interpreting X-ray images. This research used CRoss Industry Standard Process for Data Mining methodology in developing a simple Rest API model that would classify the chest X-ray image if it were normal, the person has pneumonia caused by bacteria or virus. Multi-Layer Perceptron (MLP) model had a training accuracy of 73.89%, validation accuracy of 75.46%, and test accuracy of 75.46% whereas LeNet had 78.49%, 76.51%, and 76,51%, respectively. This study demonstrated to the public that AI models may be developed to aid health professionals in the early diagnosis, classification, analysis, and interpretation of X-ray images for pneumonia. In the future, the model created should convert the English interpretations into South African local languages like isiXhosa, Zulu, Venda, and many others. Thus, making it easier for the local communities to understand giving them a sense of belonging.
{"title":"A Rest API to Classify Pneumonia Infection From Chest X-ray Images Using Multi-Layer Perceptron and LeNet","authors":"Tinashe Crispen Gadzirai, W. T. Vambe","doi":"10.1109/icABCD59051.2023.10220479","DOIUrl":"https://doi.org/10.1109/icABCD59051.2023.10220479","url":null,"abstract":"Pneumonia remains the most common reason for inpatient stays and fatalities among adults and children in the world. It became worse during Covid 19 pandemic. Most African countries like South Africa were and are still seriously affected. The situation is worse in rural areas because of several reasons, among them; not having enough X-rays machines, having no or few radiologists to analyze and interpret the X-ray pictures to determine if the pictures are normal pictures or pneumonia. The ability to accurately classify these two types of pneumonia can guarantee effective treatment which will boost survival chances. Artificial Intelligence (AI) is a cost-effective approach and can play a pivotal role in easily analyzing and interpreting X-ray images. This research used CRoss Industry Standard Process for Data Mining methodology in developing a simple Rest API model that would classify the chest X-ray image if it were normal, the person has pneumonia caused by bacteria or virus. Multi-Layer Perceptron (MLP) model had a training accuracy of 73.89%, validation accuracy of 75.46%, and test accuracy of 75.46% whereas LeNet had 78.49%, 76.51%, and 76,51%, respectively. This study demonstrated to the public that AI models may be developed to aid health professionals in the early diagnosis, classification, analysis, and interpretation of X-ray images for pneumonia. In the future, the model created should convert the English interpretations into South African local languages like isiXhosa, Zulu, Venda, and many others. Thus, making it easier for the local communities to understand giving them a sense of belonging.","PeriodicalId":51314,"journal":{"name":"Big Data","volume":"1 1","pages":"1-6"},"PeriodicalIF":4.6,"publicationDate":"2023-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84198355","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-03DOI: 10.1109/icABCD59051.2023.10220512
Lusani Mamushiane, A. Lysko, H. Kobo, Joyce B. Mwangama
Field trials and experimentation are crucial for accelerating the adoption of standalone (SA) 5G in Africa. Traditionally, only network operators and vendors had the opportunity for practical experimentation due to proprietary systems and licensing restrictions. However, the emergence of open source cellular stacks and affordable software-defined radio (SDR) systems is changing this landscape. Although these technologies are not yet fully developed for complete 5G systems, their progress is rapid, and the research community is using them to test different use cases like network slicing. Building a 5G network is complex, especially in uncontrolled RF environments with fluctuating physical conditions such as noise and interference. This necessitates proper RF planning and performance optimization. The complexity is further compounded by the variety of 5G end-user devices, each with unique configurations and integration requirements. Some devices are network locked and require rooting to connect to a 5G testbed, while others need expert APN configurations or have specific compatibility specifications like sub-carrier spacing (SCS) and duplex mode. Unfortunately, vendors often provide limited information about RF compatibility, making trial-and-error techniques necessary to uncover compatibility details. This paper presents best practices for deploying and configuring a 5G SA testbed, focusing on the integration challenges of consumer-grade devices, specifically 5G mobile phones connected to a 5G testbed. Additionally, the paper offers solutions for troubleshooting integration errors and performance issues, as well as a brief discussion on the realization of basic network slicing in a 5G SA network.
{"title":"Deploying a Stable 5G SA Testbed Using srsRAN and Open5GS: UE Integration and Troubleshooting Towards Network Slicing","authors":"Lusani Mamushiane, A. Lysko, H. Kobo, Joyce B. Mwangama","doi":"10.1109/icABCD59051.2023.10220512","DOIUrl":"https://doi.org/10.1109/icABCD59051.2023.10220512","url":null,"abstract":"Field trials and experimentation are crucial for accelerating the adoption of standalone (SA) 5G in Africa. Traditionally, only network operators and vendors had the opportunity for practical experimentation due to proprietary systems and licensing restrictions. However, the emergence of open source cellular stacks and affordable software-defined radio (SDR) systems is changing this landscape. Although these technologies are not yet fully developed for complete 5G systems, their progress is rapid, and the research community is using them to test different use cases like network slicing. Building a 5G network is complex, especially in uncontrolled RF environments with fluctuating physical conditions such as noise and interference. This necessitates proper RF planning and performance optimization. The complexity is further compounded by the variety of 5G end-user devices, each with unique configurations and integration requirements. Some devices are network locked and require rooting to connect to a 5G testbed, while others need expert APN configurations or have specific compatibility specifications like sub-carrier spacing (SCS) and duplex mode. Unfortunately, vendors often provide limited information about RF compatibility, making trial-and-error techniques necessary to uncover compatibility details. This paper presents best practices for deploying and configuring a 5G SA testbed, focusing on the integration challenges of consumer-grade devices, specifically 5G mobile phones connected to a 5G testbed. Additionally, the paper offers solutions for troubleshooting integration errors and performance issues, as well as a brief discussion on the realization of basic network slicing in a 5G SA network.","PeriodicalId":51314,"journal":{"name":"Big Data","volume":"390 1","pages":"1-10"},"PeriodicalIF":4.6,"publicationDate":"2023-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80438244","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-03DOI: 10.1109/icABCD59051.2023.10220560
Yolo Madani, Adeyinka K. Akanbi, Mpho Mbele, M. Masinde
The application of modern technologies in the environmental monitoring domain through the deployment of interconnected Internet of Things (loT) sensors, legacy systems, and enterprise networks has become an invaluable component of realising an efficient environmental monitoring system. Monitoring systems' requirements are extremely different depending on the environment, leading to ad-hoc implementations and integration of heterogeneous systems and applications. The resulting distributed systems lack flexibility with inherent issues such as data incompatibility, lack of data integration, and systems interoperability. Semantic representation of data is necessary to combine data from heterogeneous sources for consolidation into meaningful and valuable information and unlock the reusability of data between the monitoring systems. This research explores how a scalable semantic framework can ensure data representation using machine-readable languages for seamless data integration and interoperability of other heterogeneous sub-systems in a Multi-Hazard Early Warning System (MHEWS) as a case study. The study hypothesises that the challenge of ensuring data representation, data integration, and system interoperability within an MHEWS can be overcome through the application of semantic middleware.
{"title":"A Scalable Semantic Framework for an Integrated Multi-Hazard Early Warning System","authors":"Yolo Madani, Adeyinka K. Akanbi, Mpho Mbele, M. Masinde","doi":"10.1109/icABCD59051.2023.10220560","DOIUrl":"https://doi.org/10.1109/icABCD59051.2023.10220560","url":null,"abstract":"The application of modern technologies in the environmental monitoring domain through the deployment of interconnected Internet of Things (loT) sensors, legacy systems, and enterprise networks has become an invaluable component of realising an efficient environmental monitoring system. Monitoring systems' requirements are extremely different depending on the environment, leading to ad-hoc implementations and integration of heterogeneous systems and applications. The resulting distributed systems lack flexibility with inherent issues such as data incompatibility, lack of data integration, and systems interoperability. Semantic representation of data is necessary to combine data from heterogeneous sources for consolidation into meaningful and valuable information and unlock the reusability of data between the monitoring systems. This research explores how a scalable semantic framework can ensure data representation using machine-readable languages for seamless data integration and interoperability of other heterogeneous sub-systems in a Multi-Hazard Early Warning System (MHEWS) as a case study. The study hypothesises that the challenge of ensuring data representation, data integration, and system interoperability within an MHEWS can be overcome through the application of semantic middleware.","PeriodicalId":51314,"journal":{"name":"Big Data","volume":"54 1","pages":"1-6"},"PeriodicalIF":4.6,"publicationDate":"2023-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90753084","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-03DOI: 10.1109/icABCD59051.2023.10220456
H. Orovwode, Ibukun Deborah Oduntan, J. Abubakar
Deafness and voice impairment have been persistent disabilities throughout history, hindering individuals from engaging in verbal communication and leading to their isolation from the predominantly vocally communicating society. Sign language has emerged as the primary mode of communication for people with these disabilities. However, it presents a language barrier as it is not commonly understood by those who can hear. To address this issue, various methods for recognizing sign language have been proposed. This paperaims to develop a machine learning-based system that can recognize sign language in real-time. The paper involved the acquisition of a dataset consisting of 44,654 images representing the static American Sign Language (ASL) alphabet signs. The HandDetector module was utilized to detect and capture images of the signer's hand forming each sign through a PC webcam. The dataset was split into three sets: training data (20,772 cases), validation data (8,903 cases), and test data (14,979 cases). Image pre-processing techniques were implemented on the images and a convolutional neural network (CNN) model was trained and compiled. The CNN utilized in the paper comprised of three convolutional layers and a SoftMax output layer and it was compiled using the Adam optimizer and categorical cross-entropy loss function. The performance of the system was evaluated using the test dataset. Notably, the system achieved remarkable accuracy rates, having a training accuracy of 99.86%, a validation accuracy of 99.94%, and a test accuracy of 94.68%. The results obtained from this study demonstrated significant advancements in sign language recognition, surpassing previous findings in the literature.
{"title":"Development of a Sign Language Recognition System Using Machine Learning","authors":"H. Orovwode, Ibukun Deborah Oduntan, J. Abubakar","doi":"10.1109/icABCD59051.2023.10220456","DOIUrl":"https://doi.org/10.1109/icABCD59051.2023.10220456","url":null,"abstract":"Deafness and voice impairment have been persistent disabilities throughout history, hindering individuals from engaging in verbal communication and leading to their isolation from the predominantly vocally communicating society. Sign language has emerged as the primary mode of communication for people with these disabilities. However, it presents a language barrier as it is not commonly understood by those who can hear. To address this issue, various methods for recognizing sign language have been proposed. This paperaims to develop a machine learning-based system that can recognize sign language in real-time. The paper involved the acquisition of a dataset consisting of 44,654 images representing the static American Sign Language (ASL) alphabet signs. The HandDetector module was utilized to detect and capture images of the signer's hand forming each sign through a PC webcam. The dataset was split into three sets: training data (20,772 cases), validation data (8,903 cases), and test data (14,979 cases). Image pre-processing techniques were implemented on the images and a convolutional neural network (CNN) model was trained and compiled. The CNN utilized in the paper comprised of three convolutional layers and a SoftMax output layer and it was compiled using the Adam optimizer and categorical cross-entropy loss function. The performance of the system was evaluated using the test dataset. Notably, the system achieved remarkable accuracy rates, having a training accuracy of 99.86%, a validation accuracy of 99.94%, and a test accuracy of 94.68%. The results obtained from this study demonstrated significant advancements in sign language recognition, surpassing previous findings in the literature.","PeriodicalId":51314,"journal":{"name":"Big Data","volume":"15 1","pages":"1-8"},"PeriodicalIF":4.6,"publicationDate":"2023-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82770967","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-03DOI: 10.1109/icABCD59051.2023.10220532
Feliciana M. E. Manuel, S. Saide, Felermino M. D. A. Ali, Sanae Lotfi
Ocular cataract is among diseases that result in blindness if not treated in time. It affects people worldwide, primarily in underdeveloped countries. This health problem affects the quality of patients' lives. However, early diagnosis avoids blindness and allows the patient to have appropriate treatment. Developing countries, especially those with low income, have a precarious health system, even in the ophthalmology sector, where equipment is lacking. This research aims to develop a deep learning-based model to detect ocular cataracts based on retinal images. We collect 1000 retinal images from Kaggle, which are then equally divided into two classes: with and without cataracts. We then use several neural architectures to correctly classify these images, including ResNet18, ResNet34, InceptionResNetV2, and InceptionV4. We demonstrate that ResNet18 outperforms the other architectures, reaching 95.5% accuracy score. Our results suggest that deep convolutional neural networks can achieve a significant performance in ocular cataracts classification using retinal images.
{"title":"Ocular Cataract Identification Using Deep Convolutional Neural Networks","authors":"Feliciana M. E. Manuel, S. Saide, Felermino M. D. A. Ali, Sanae Lotfi","doi":"10.1109/icABCD59051.2023.10220532","DOIUrl":"https://doi.org/10.1109/icABCD59051.2023.10220532","url":null,"abstract":"Ocular cataract is among diseases that result in blindness if not treated in time. It affects people worldwide, primarily in underdeveloped countries. This health problem affects the quality of patients' lives. However, early diagnosis avoids blindness and allows the patient to have appropriate treatment. Developing countries, especially those with low income, have a precarious health system, even in the ophthalmology sector, where equipment is lacking. This research aims to develop a deep learning-based model to detect ocular cataracts based on retinal images. We collect 1000 retinal images from Kaggle, which are then equally divided into two classes: with and without cataracts. We then use several neural architectures to correctly classify these images, including ResNet18, ResNet34, InceptionResNetV2, and InceptionV4. We demonstrate that ResNet18 outperforms the other architectures, reaching 95.5% accuracy score. Our results suggest that deep convolutional neural networks can achieve a significant performance in ocular cataracts classification using retinal images.","PeriodicalId":51314,"journal":{"name":"Big Data","volume":"259 1","pages":"1-5"},"PeriodicalIF":4.6,"publicationDate":"2023-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77104460","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：