Special Issue on Machine Learning Algorithms for Mobile Edge Computing and IoT
摘要截稿:
全文截稿: 2018-10-31
影响因子: 3.111
期刊难度:
CCF分类: B类
中科院JCR分区:
• 大类 : 计算机科学 - 3区
• 小类 : 计算机:硬件 - 3区
• 小类 : 计算机:信息系统 - 3区
• 小类 : 工程:电子与电气 - 3区
• 小类 : 电信学 - 3区
Overview
The Internet of Things (IoT) is the inter-networking of various physical devices, objects, and people. It progressively advances and covers a variety of wired and wireless technologies through embedded devices, smart objects, and smart users. The integration of these technologies along with the rapid development in Wireless Sensor Networks (WSN) based on new Bluetooth standards, such as Bluetooth Low Energy (BLE) 4.0 and ZigBee, opens new doors of evolving IoT in future generations of networks. Edge computing pushes the generation, collection, and analysis of data out to the point of origin, rather than to a data center or cloud. In the case of the IoT, this means it takes place at the devices and sensors. Edge computing provides a greater surface area for computation to occur. This enables data processing and analytics as well as knowledge generation to occur at the source of the data. Machine learning is a branch of artificial intelligence (AI) that focuses on enabling machines to learn for themselves without the need for human intervention or to be explicitly programmed to do so. Machine learning on IoT devices such as smartphones allows for learning secure models directly on the devices themselves, removing the need to send data to the cloud or externalize it in anyway.
Moreover, IoT devices generate a massive volume of data in a continuous manner. In general, a cluster of clouds is used to store and compute such large volume of IoT sensor data. This does create even more challenges in data storage and the integration between IoT devices. In order to overcome this problem, Mobile-Edge Computing (MEC) was developed, extending cloud-computing capabilities and services to the edge of the network. The objective of MEC is to provide smart services and applications with an improved Quality-of-Service (QoS) and reduced latency. Thus, MEC is becoming a significant platform for enabling consumer-centric IoT services and applications that demand real-world applications. The most familiar applications of MEC-enabled IoT include smart home, mobility, content distribution, smart vehicles, wearable health monitoring system, smart cities, and location-based services. The data processing and computation at MEC is much more, when compared with the operations performed on IoT devices. Machine learning algorithms have a capability to process streaming data generated at the edge of the network and IoT devices. This special issue focuses on challenges and problems in machine learning algorithms for processing and discovering knowledge patterns from IoT devices and edge of the network.
Topic includes but not limited to
• Supervised, unsupervised and reinforcement learning in MEC
• Industrial edge computing methods for IoT
• Big data processing in edge computing for IoT
• Interoperability and mobility for Edge to IoT connectivity
• Emerging Edge commuting services and applications for IoT
• New algorithms and architectures for embedded devices in IoT paradigm
• Emerging technologies and its integration with the embedded devices
• Integration of embedded devices in smart homes, smart traffic monitoring, smart health, smart education and smart manufacturing
• Machine learning algorithms for memory management in IoT
• Open standards and application programming interfaces for MEC
• Applications of Mobile Edge Computing (i.e., Content Delivery, Edge Video Caching, Mobile Big Data Analytics, Computational Offloading, Collaborative Computing)
• Dimension reduction and Information fusion in the IoT based real-time Big Data analytics
• Descriptive, diagnostic and predictive analytics in MEC
• Monte Carlo Sampling for IoT based real-time Big Data analytics
• Scalable, online, active, decentralized, deep learning and optimization in MEC
• In-memory analytical techniques and databases for IoT data analytics
• Simulating and emulating environments as well as experimental results on high quality data sensing and processing for edge computing
• Machine learning algorithms for intrusion and threat detection in edge computing
• Deep learning and online algorithms for energy efficient data sensing and processing in MEC