Pub Date : 2024-02-04DOI: 10.23919/ICACT60172.2024.10471764
Ekaterina Kuzmina, Meriem Tefikova, A. Volkov, A. Muthanna, Abdelhamied A. Ateya, A. Koucheryavy
This paper provides a real-time fog computing model based on a microservice architecture that enables testing and modeling of eventual implementations of ultra-reliable low-latency communications (uRLLC) services. The work provides fog-based architecture for sixth-generation cellular (6G) applications, including telepresence and uRLLC. A testbed of a robot swarm was developed to prototype the proposed network architecture. Computing tasks are offloaded and handled based on a proposed microservice scheme introduced to meet the 6G requirements. Furthermore, we developed a novel migration scheme for the proposed architecture to support the mobility of end devices. The optimum server for migrating computing tasks is allocated by solving a proposed optimization problem using particle swarm optimization (PSO). All proposed algorithms were implemented in the developed prototype. The proposed work is introduced to provide an architectural foundation for testing fog-based 6G applications and services and to implement and test novel network methods in the future.
{"title":"Microservice-Based Fog Testbed for 6G Applications","authors":"Ekaterina Kuzmina, Meriem Tefikova, A. Volkov, A. Muthanna, Abdelhamied A. Ateya, A. Koucheryavy","doi":"10.23919/ICACT60172.2024.10471764","DOIUrl":"https://doi.org/10.23919/ICACT60172.2024.10471764","url":null,"abstract":"This paper provides a real-time fog computing model based on a microservice architecture that enables testing and modeling of eventual implementations of ultra-reliable low-latency communications (uRLLC) services. The work provides fog-based architecture for sixth-generation cellular (6G) applications, including telepresence and uRLLC. A testbed of a robot swarm was developed to prototype the proposed network architecture. Computing tasks are offloaded and handled based on a proposed microservice scheme introduced to meet the 6G requirements. Furthermore, we developed a novel migration scheme for the proposed architecture to support the mobility of end devices. The optimum server for migrating computing tasks is allocated by solving a proposed optimization problem using particle swarm optimization (PSO). All proposed algorithms were implemented in the developed prototype. The proposed work is introduced to provide an architectural foundation for testing fog-based 6G applications and services and to implement and test novel network methods in the future.","PeriodicalId":518077,"journal":{"name":"2024 26th International Conference on Advanced Communications Technology (ICACT)","volume":"101 ","pages":"174-182"},"PeriodicalIF":0.0,"publicationDate":"2024-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140528306","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-04DOI: 10.23919/ICACT60172.2024.10471968
A. S. Ismail, Ammar Hawbani, Xingfu Wang, Samah Abdel Aziz, Liang Zhao, Nasir Saeed
Due to the challenging conditions of underwater environments, such as node mobility and large-scale networks, achieving localization in large-scale mobile underwater sensor networks (UWSN) is a difficult task. This paper introduces a scheme known as the Flexible Localization Method with Mobility Estimation (FLMME) for UWSNs by utilizing the expected mobility patterns of underwater objects. FLMME performs localization hierarchically by splitting the process into anchor and ordinary node localization. Each node estimates its next mobility pattern based on previous location information, enabling estimates about its next location. Anchor nodes, holding known locations, manage the localization process to balance accuracy and error trade-offs. Extensive simulations demonstrate that FLMME reduces localization errors and hence increases localization accuracy.
{"title":"Flexible Localization Method with Motion Estimation for Underwater Wireless Sensor Networks","authors":"A. S. Ismail, Ammar Hawbani, Xingfu Wang, Samah Abdel Aziz, Liang Zhao, Nasir Saeed","doi":"10.23919/ICACT60172.2024.10471968","DOIUrl":"https://doi.org/10.23919/ICACT60172.2024.10471968","url":null,"abstract":"Due to the challenging conditions of underwater environments, such as node mobility and large-scale networks, achieving localization in large-scale mobile underwater sensor networks (UWSN) is a difficult task. This paper introduces a scheme known as the Flexible Localization Method with Mobility Estimation (FLMME) for UWSNs by utilizing the expected mobility patterns of underwater objects. FLMME performs localization hierarchically by splitting the process into anchor and ordinary node localization. Each node estimates its next mobility pattern based on previous location information, enabling estimates about its next location. Anchor nodes, holding known locations, manage the localization process to balance accuracy and error trade-offs. Extensive simulations demonstrate that FLMME reduces localization errors and hence increases localization accuracy.","PeriodicalId":518077,"journal":{"name":"2024 26th International Conference on Advanced Communications Technology (ICACT)","volume":"58 ","pages":"354-359"},"PeriodicalIF":0.0,"publicationDate":"2024-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140528317","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-04DOI: 10.23919/ICACT60172.2024.10471916
Sikandar Ali, Samman Fatima, Ali Hussain, Maisam Ali, Muhammad Yaseen, Tagne Poupi Theodore Armand, Hee-Cheol Kim
Gastric cancer is one of the leading health issues that contributes to cancer related deaths. The tricky thing about cancer is that it often goes undetected until at higher stages, which makes treatment less effective. The significant death rate from gastric cancer highlights the importance of a precise and prompt diagnosis. This paper aims to tackle this problem by proposing an approach to classify the early and advanced stages of gastric cancer. This importance of this study stems from its two-pronged strategy, which provides a deeper understanding of stomach cancer stages using texture analysis and deep learning. We take advantage of the strengths of deep learning features, Gray Level Co-occurrence Matrix (GLCM) features, and machine learning algorithm to create a diagnostic tool that is more precise and accurate. Medical images from gastric cancer dataset showing early and advanced stages of gastric cancers carcinoma are included to develop this model. Our method combines the effectiveness of texture features extracted from GLCM combined with deep semantic features and classify the stages with machine learning model. We carefully evaluated Machine learning classifiers namely Support Vector Machine (SVM), Decision Tree (DT), and K-nearest neighbour (KNN) to classify the early and advanced stages. Each classifier was evaluated with different performance measures. The Support Vector Machine (SVM) classifier demonstrated the best performance with an accuracy of 96.93%. This highlights the potential of SVM for diagnosing different cancer stages, which could have positive implications, for clinical practice.
{"title":"Classifying Gastric Cancer Carcinoma Stages with Deep Semantic Features and GLCM Texture Features","authors":"Sikandar Ali, Samman Fatima, Ali Hussain, Maisam Ali, Muhammad Yaseen, Tagne Poupi Theodore Armand, Hee-Cheol Kim","doi":"10.23919/ICACT60172.2024.10471916","DOIUrl":"https://doi.org/10.23919/ICACT60172.2024.10471916","url":null,"abstract":"Gastric cancer is one of the leading health issues that contributes to cancer related deaths. The tricky thing about cancer is that it often goes undetected until at higher stages, which makes treatment less effective. The significant death rate from gastric cancer highlights the importance of a precise and prompt diagnosis. This paper aims to tackle this problem by proposing an approach to classify the early and advanced stages of gastric cancer. This importance of this study stems from its two-pronged strategy, which provides a deeper understanding of stomach cancer stages using texture analysis and deep learning. We take advantage of the strengths of deep learning features, Gray Level Co-occurrence Matrix (GLCM) features, and machine learning algorithm to create a diagnostic tool that is more precise and accurate. Medical images from gastric cancer dataset showing early and advanced stages of gastric cancers carcinoma are included to develop this model. Our method combines the effectiveness of texture features extracted from GLCM combined with deep semantic features and classify the stages with machine learning model. We carefully evaluated Machine learning classifiers namely Support Vector Machine (SVM), Decision Tree (DT), and K-nearest neighbour (KNN) to classify the early and advanced stages. Each classifier was evaluated with different performance measures. The Support Vector Machine (SVM) classifier demonstrated the best performance with an accuracy of 96.93%. This highlights the potential of SVM for diagnosing different cancer stages, which could have positive implications, for clinical practice.","PeriodicalId":518077,"journal":{"name":"2024 26th International Conference on Advanced Communications Technology (ICACT)","volume":"103 ","pages":"211-215"},"PeriodicalIF":0.0,"publicationDate":"2024-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140528286","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The performance analysis of battlefield communication network has been more and more complex and difficult with its increasing scale, heterogeneity and geographical distribution of nodes. Computer simulation technology is considered as a potential technology to efficiently and accurately solve this problem. This paper focuses on the simulation requirements of anti-interference performance of battlefield communication networks in complex electromagnetic environments, and designs reconnaissance interference and frequency hopping models based on QuaINet simulation software. The model introduces scout and jammer nodes in the communication network, which can conduct reconnaissance and directional interference on communication nodes in the network. Other nodes can set frequency hopping parameters to achieve anti-interference. In addition, a data interaction interface for the distributed simulation system is designed based on the DDS specification, and a structure definition file is designed according to the data interaction requirements to achieve dynamic control of the QualNet simulation model by external control modules. Finally, this article tested the functionality of the communication countermeasure model and conducted a delay test on the data interaction interface. The experimental results verify the functionality of the designed model and the high real time of the interface, which is of great significance to the anti-interference performance assessment of the battlefield communication network.
{"title":"Design of Communication Countermeasure Simulation Model and Data Interaction Interface for Battlefield Network Based on QualNet","authors":"Wenyi Li, Peng Gong, Weidong Wang, Yu Liu, Jianfeng Li, Xiang Gao","doi":"10.23919/ICACT60172.2024.10471951","DOIUrl":"https://doi.org/10.23919/ICACT60172.2024.10471951","url":null,"abstract":"The performance analysis of battlefield communication network has been more and more complex and difficult with its increasing scale, heterogeneity and geographical distribution of nodes. Computer simulation technology is considered as a potential technology to efficiently and accurately solve this problem. This paper focuses on the simulation requirements of anti-interference performance of battlefield communication networks in complex electromagnetic environments, and designs reconnaissance interference and frequency hopping models based on QuaINet simulation software. The model introduces scout and jammer nodes in the communication network, which can conduct reconnaissance and directional interference on communication nodes in the network. Other nodes can set frequency hopping parameters to achieve anti-interference. In addition, a data interaction interface for the distributed simulation system is designed based on the DDS specification, and a structure definition file is designed according to the data interaction requirements to achieve dynamic control of the QualNet simulation model by external control modules. Finally, this article tested the functionality of the communication countermeasure model and conducted a delay test on the data interaction interface. The experimental results verify the functionality of the designed model and the high real time of the interface, which is of great significance to the anti-interference performance assessment of the battlefield communication network.","PeriodicalId":518077,"journal":{"name":"2024 26th International Conference on Advanced Communications Technology (ICACT)","volume":"23 6","pages":"01-08"},"PeriodicalIF":0.0,"publicationDate":"2024-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140528126","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-04DOI: 10.23919/icact60172.2024.10471910
{"title":"Session 2A: Wireless Communication 2","authors":"","doi":"10.23919/icact60172.2024.10471910","DOIUrl":"https://doi.org/10.23919/icact60172.2024.10471910","url":null,"abstract":"","PeriodicalId":518077,"journal":{"name":"2024 26th International Conference on Advanced Communications Technology (ICACT)","volume":"77 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140528293","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-04DOI: 10.23919/ICACT60172.2024.10472009
J. Llovido, Michael Angelo D. Brogada, Floradel S. Relucio, Lea D. Austero, Lany L. Maceda, Mideth B. Abisado
Digital citizen participatory toolkits are gaining interest among researchers and practitioners for their crucial role in empowering citizens, promoting accountability, and ensuring diverse voices are heard in policymaking. This study aims to develop and implement BOSESKO: Building on Opinions and Sentiments for Sustainability and Knowledge Opportunities (formerly known as Kalahok) - a multilingual, inclusive, deliberative, synoptic, digital participatory toolkit that digitized data collection and analysis to engage communities in governance using technology-based methodologies. BOSESKO is available in English, Filipino, Ilokano, and Bikol versions for web and mobile devices. It primarily encourages public feedback on disaster preparedness and Universal Access to Quality Tertiary Education (UAQTE) implementation in the Philippines. Its adaptable design extends its utility beyond its initial scope. BOSESKO explored machine learning, natural language processing, and software integration for data gathering, processing, visualization, and system development while employing a hybrid approach with Extreme Programming (XP) and Scrum, Significant findings demonstrated that BOSESKO enabled the orderly solicitation and submission of inputs from local communities through the creation, management, consolidation, analysis, and visualization of responses. The result of the analysis based on the performance of BOSESKO's web application and mobile application 4.78 and 4.40, respectively, and this can guide agencies in formulating data-driven policies for UAQTE, Disaster Risk Reduction Management, Climate Adaptation (DRRM/CA), among others.
{"title":"BOSESKO: Designing A Synoptic Multi-Platform Digital System for Citizen Participation","authors":"J. Llovido, Michael Angelo D. Brogada, Floradel S. Relucio, Lea D. Austero, Lany L. Maceda, Mideth B. Abisado","doi":"10.23919/ICACT60172.2024.10472009","DOIUrl":"https://doi.org/10.23919/ICACT60172.2024.10472009","url":null,"abstract":"Digital citizen participatory toolkits are gaining interest among researchers and practitioners for their crucial role in empowering citizens, promoting accountability, and ensuring diverse voices are heard in policymaking. This study aims to develop and implement BOSESKO: Building on Opinions and Sentiments for Sustainability and Knowledge Opportunities (formerly known as Kalahok) - a multilingual, inclusive, deliberative, synoptic, digital participatory toolkit that digitized data collection and analysis to engage communities in governance using technology-based methodologies. BOSESKO is available in English, Filipino, Ilokano, and Bikol versions for web and mobile devices. It primarily encourages public feedback on disaster preparedness and Universal Access to Quality Tertiary Education (UAQTE) implementation in the Philippines. Its adaptable design extends its utility beyond its initial scope. BOSESKO explored machine learning, natural language processing, and software integration for data gathering, processing, visualization, and system development while employing a hybrid approach with Extreme Programming (XP) and Scrum, Significant findings demonstrated that BOSESKO enabled the orderly solicitation and submission of inputs from local communities through the creation, management, consolidation, analysis, and visualization of responses. The result of the analysis based on the performance of BOSESKO's web application and mobile application 4.78 and 4.40, respectively, and this can guide agencies in formulating data-driven policies for UAQTE, Disaster Risk Reduction Management, Climate Adaptation (DRRM/CA), among others.","PeriodicalId":518077,"journal":{"name":"2024 26th International Conference on Advanced Communications Technology (ICACT)","volume":"16 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2024-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140528305","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the development of online courses, students' discussion texts in online forums and communication groups are increasing. Teachers can use these texts to monitor student learning so that they can adapt the pace of instruction accordingly. And textual topics, as the important information of the text, can be extracted from the text by topic modeling. Currently, a Latent Dirichlet Allocation (LDA) method has been used to identify the critical main topics discussed by students. However, LDA is based on word frequency and ignores semantic information. In this study, we propose a model for fusing semantic information into LDA. To verify the validity of our model, we collected two MOOC datasets for testing and conducted an ablation study using Silhouette Coefficient value and Calinski-Harabasz score as the criterion. The results show that our method is scientifically feasible and better than LDA in the field of educational topic modeling. Thus, our method is able to perform topic modeling more accurately compared to LDA. It can be used by teachers to automatically analyze large amounts of student discussion data to guide personalized learning paths.
{"title":"An Enhanced Topic Modeling Method in Educational Domain by Integrating LDA with Semantic","authors":"Ruofei Ding, Pucheng Huang, Shumin Chen, Jiale Zhang, Jingxiu Huang, Yunxiang Zheng","doi":"10.23919/icact60172.2024.10471952","DOIUrl":"https://doi.org/10.23919/icact60172.2024.10471952","url":null,"abstract":"With the development of online courses, students' discussion texts in online forums and communication groups are increasing. Teachers can use these texts to monitor student learning so that they can adapt the pace of instruction accordingly. And textual topics, as the important information of the text, can be extracted from the text by topic modeling. Currently, a Latent Dirichlet Allocation (LDA) method has been used to identify the critical main topics discussed by students. However, LDA is based on word frequency and ignores semantic information. In this study, we propose a model for fusing semantic information into LDA. To verify the validity of our model, we collected two MOOC datasets for testing and conducted an ablation study using Silhouette Coefficient value and Calinski-Harabasz score as the criterion. The results show that our method is scientifically feasible and better than LDA in the field of educational topic modeling. Thus, our method is able to perform topic modeling more accurately compared to LDA. It can be used by teachers to automatically analyze large amounts of student discussion data to guide personalized learning paths.","PeriodicalId":518077,"journal":{"name":"2024 26th International Conference on Advanced Communications Technology (ICACT)","volume":"45 ","pages":"01-06"},"PeriodicalIF":0.0,"publicationDate":"2024-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140528119","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-04DOI: 10.23919/ICACT60172.2024.10472011
Volkov Artem, Varvara Mineeva, A. Muthanna, A. Koucheryavy
This paper deals with the problem of traffic typing and telepresence services, presents the results of analysis of existing methods based on DiffServ mechanisms such as Behavior Aggregate, Interface-based, MultiField. An extended traffic typing method based on LSTM networks is presented, a neural network for traffic recognition service in 6G networks is developed, promising directions such as the concept of 2030 networks and telepresence services are discussed, software-defined networking and virtualization of network functions are investigated. In this study, data obtained from an SDN flow table containing information about network traffic characteristics were used to train the ANN. To evaluate the effectiveness of the extended method, a special stand was developed to test and evaluate the quality of traffic typing. The stand includes the necessary hardware and software for conducting experiments and collecting data.
{"title":"Traffic Type Recognition in 6G Software-Defined Networking for Telepresence Services","authors":"Volkov Artem, Varvara Mineeva, A. Muthanna, A. Koucheryavy","doi":"10.23919/ICACT60172.2024.10472011","DOIUrl":"https://doi.org/10.23919/ICACT60172.2024.10472011","url":null,"abstract":"This paper deals with the problem of traffic typing and telepresence services, presents the results of analysis of existing methods based on DiffServ mechanisms such as Behavior Aggregate, Interface-based, MultiField. An extended traffic typing method based on LSTM networks is presented, a neural network for traffic recognition service in 6G networks is developed, promising directions such as the concept of 2030 networks and telepresence services are discussed, software-defined networking and virtualization of network functions are investigated. In this study, data obtained from an SDN flow table containing information about network traffic characteristics were used to train the ANN. To evaluate the effectiveness of the extended method, a special stand was developed to test and evaluate the quality of traffic typing. The stand includes the necessary hardware and software for conducting experiments and collecting data.","PeriodicalId":518077,"journal":{"name":"2024 26th International Conference on Advanced Communications Technology (ICACT)","volume":"28 2","pages":"01-06"},"PeriodicalIF":0.0,"publicationDate":"2024-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140528124","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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：