|
||||
Net-Centric 2022 Call for Presentation Abstract Proposals Submission due date: August 13, 2022. Nowadays ICT systems are indispensable as mission-critical infrastructure in digitalized societies. However, with the integration of fixed/mobile networks and cloud/edge computing, ICT systems are becoming more and more complex. The spatio-temporal demand fluctuations caused by massive mobile devices including smartphones and IoT devices need to be taken into account in fixed/mobile networking while dynamic resource provisioning, aka auto-scaling, and self-healing mechanisms from service failures in cloud/edge computing are implemented in container/VM orchestrators such as Kubernetes and OpenStack. Monitoring and analysis of various performance metrics, traffic measurements, and log data is a key issue for quality assurance and reliable service delivery. Traffic monitoring, log data analysis, and forensic analysis are key challenges for cyber security and we have mainly relied on tailor-made specific algorithms. However, research in machine learning algorithms has made significant progress in recent years. Unlike traditional algorithms that can be thought of as a set of rules or instructions specified by a computer programmer that the computer can process and need to be programmed for a specific task in a hand-crafted manner, machine learning algorithms learn from experience, represented as datasets, and learn in different learning modes such as unsupervised learning, supervised learning, and reinforcement learning to improve the performance of tasks such as classification, regression, anomaly detection, and synthesis. Recent advances in machine learning are largely due to advances in software technology. Programming frameworks such as pytorch, tensorflow, scikit-learn, etc. can reduce the workload for researchers and engineers to develop and implement state-of-the-art machine learning algorithms. In addition, various open source software for data collection, visualization, dashboarding such as Prometheus, Kafka, eBPF, fluentd, grafana, Thingsobard, etc., are available. For a successful project, skills in the above three areas, i.e., network computing technology, machine learning technology, and software technology, are required simultaneously. With this in mind, we invite experts to share their experience, lessons learned, and ideas in the following subjects (but not limited to): Topics
Please submit your presentation abstract (including your name, affiliation, and email address) to cfp2021[at]isocore.com. For further information please see www.isocore.com/2021/ or contact: Dr. Kohei Shiomoto at: shiomoto[at]tcu.ac.jp. Please contact us if you have further questions. |
||||
© 2001-2022 ISOCORE CORP. ALL RIGHTS RESERVED | Sitewide Privacy Statement | Contact the Webmaster | Contact Info