Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Unmanned aerial vehicles (UAVs) have enormous potential in the public and civil domains. These are particularly useful in applications, where human lives would otherwise be endangered. Multi-UAV systems can collaboratively complete missions more efficiently and economically as compared to single UAV systems. However, there are many issues to be resolved before effective use of UAVs can be made to provide stable and reliable context-specific networks. Much of the work carried out in the areas of mobile ad hoc networks (MANETs), and vehicular ad hoc networks (VANETs) does not address the unique characteristics of the UAV networks. UAV networks may vary from slow dynamic to dynamic and have intermittent links and fluid topology. While it is believed that ad hoc mesh network would be most suitable for UAV networks yet the architecture of multi-UAV networks has been an understudied area. Software defined networking (SDN) could facilitate flexible deployment and management of new services and help reduce cost, increase security and availability in networks. Routing demands of UAV networks go beyond the needs of MANETS and VANETS. Protocols are required that would adapt to high mobility, dynamic topology, intermittent links, power constraints, and changing link quality. UAVs may fail and the network may get partitioned making delay and disruption tolerance an important design consideration. Limited life of the node and dynamicity of the network lead to the requirement of seamless handovers, where researchers are looking at the work done in the areas of MANETs and VANETs, but the jury is still out. As energy supply on UAVs is limited, protocols in various layers should contribute toward greening of the network. This paper surveys the work done toward all of these outstanding issues, relating to this new class of networks, so as to spur further research in these areas.

Survey of Important Issues in UAV Communication Networks

Power Aware Routing in Mobile Ad Hoc Networks

Deep learning is a promising approach for extracting accurate information from raw sensor data from IoT devices deployed in complex environments Because of its multilayer structure, deep learning is also appropriate for the edge computing environment Therefore, in this article, we first introduce deep learning for IoTs into the edge computing environment Since existing edge nodes have limited processing capability, we also design a novel offloading strategy to optimize the performance of IoT deep learning applications with edge computing In the performance evaluation, we test the performance of executing multiple deep learning tasks in an edge computing environment with our strategy The evaluation results show that our method outperforms other optimization solutions on deep learning for IoT

/pdf/learning-iot-in-edge-deep-learning-for-the-internet-of-18jz5dyghh.pdf

Learning IoT in Edge: Deep Learning for the Internet of Things with Edge Computing

The Internet of Things (IoT) now permeates our daily lives, providing important measurement and collection tools to inform our every decision. Millions of sensors and devices are continuously producing data and exchanging important messages via complex networks supporting machine-to-machine communications and monitoring and controlling critical smart-world infrastructures. As a strategy to mitigate the escalation in resource congestion, edge computing has emerged as a new paradigm to solve IoT and localized computing needs. Compared with the well-known cloud computing, edge computing will migrate data computation or storage to the network “edge,” near the end users. Thus, a number of computation nodes distributed across the network can offload the computational stress away from the centralized data center, and can significantly reduce the latency in message exchange. In addition, the distributed structure can balance network traffic and avoid the traffic peaks in IoT networks, reducing the transmission latency between edge/cloudlet servers and end users, as well as reducing response times for real-time IoT applications in comparison with traditional cloud services. Furthermore, by transferring computation and communication overhead from nodes with limited battery supply to nodes with significant power resources, the system can extend the lifetime of the individual nodes. In this paper, we conduct a comprehensive survey, analyzing how edge computing improves the performance of IoT networks. We categorize edge computing into different groups based on architecture, and study their performance by comparing network latency, bandwidth occupation, energy consumption, and overhead. In addition, we consider security issues in edge computing, evaluating the availability, integrity, and the confidentiality of security strategies of each group, and propose a framework for security evaluation of IoT networks with edge computing. Finally, we compare the performance of various IoT applications (smart city, smart grid, smart transportation, and so on) in edge computing and traditional cloud computing architectures.

A Survey on the Edge Computing for the Internet of Things

The Great East Japan Earthquake and Tsunami drastically changed Japanese society, and the requirements for ICT was completely redefined. After the disaster, it was impossible for disaster victims to utilize their communication devices, such as cellular phones, tablet computers, or laptop computers, to notify their families and friends of their safety and confirm the safety of their loved ones since the communication infrastructures were physically damaged or lacked the energy necessary to operate. Due to this drastic event, we have come to realize the importance of device-to-device communications. With the recent increase in popularity of D2D communications, many research works are focusing their attention on a centralized network operated by network operators and neglect the importance of decentralized infrastructureless multihop communication, which is essential for disaster relief applications. In this article, we propose the concept of multihop D2D communication network systems that are applicable to many different wireless technologies, and clarify requirements along with introducing open issues in such systems. The first generation prototype of relay by smartphone can deliver messages using only users' mobile devices, allowing us to send out emergency messages from disconnected areas as well as information sharing among people gathered in evacuation centers. The success of field experiments demonstrates steady advancement toward realizing user-driven networking powered by communication devices independent of operator networks.

Relay-by-smartphone: realizing multihop device-to-device communications

Due to physical limitations, mobile devices are restricted in memory, battery, processing, among other characteristics. This results in many applications that cannot be run in such devices. This problem is fixed by Edge Cloud Computing, where the users offload tasks they cannot run to cloudlet servers in the edge of the network. The main requirement of such a system is having a low Service Delay, which would correspond to a high Quality of Service. This paper presents a method for minimizing Service Delay in a scenario with two cloudlet servers. The method has a dual focus on computation and communication elements, controlling Processing Delay through virtual machine migration and improving Transmission Delay with Transmission Power Control. The foundation of the proposal is a mathematical model of the scenario, whose analysis is used on a comparison between the proposed approach and two other conventional methods; these methods have single focus and only make an effort to improve either Transmission Delay or Processing Delay, but not both. As expected, the proposal presents the lowest Service Delay in all study cases, corroborating our conclusion that a dual focus approach is the best way to tackle the Service Delay problem in Edge Cloud Computing.

Hybrid Method for Minimizing Service Delay in Edge Cloud Computing Through VM Migration and Transmission Power Control

With the widespread adoption of the Internet of Things (IoT), the number of connected devices is growing at an exponential rate, which is contributing to ever-increasing, massive data volumes. Real-time analytics on the massive IoT data, referred to as the “real-time IoT analytics” in this paper, is becoming the mainstream with an aim to provide an immediate or non-immediate actionable insights and business intelligence. However, the analytics network of the existing IoT systems does not adequately consider the requirements of the real-time IoT analytics. In fact, most researchers overlooked an appropriate design of the IoT analytics network while focusing much on the sensing and delivery networks of the IoT system. Since much of the IoT analytics network has often been taken as granted, the survey, in this paper, we aim to review the state-of-the-art of the analytics network methodologies, which are suitable for real-time IoT analytics. In this vein, we first describe the basics of the real-time IoT analytics, use cases, and software platforms, and then explain the shortcomings of the network methodologies to support them. To address those shortcomings, we then discuss the relevant network methodologies which may support the real-time IoT analytics. Also, we present a number of prospective research problems and future research directions focusing on the network methodologies for the real-time IoT analytics.

A Survey on Network Methodologies for Real-Time Analytics of Massive IoT Data and Open Research Issues

Environmental genomics can describe all forms of organisms—cellular and viral—present in a community. The analysis of such eco-systems biology data relies heavily on reference databases, e.g., taxonomy or gene function databases. Reference databases of symbiosis sensu lato, although essential for the analysis of organism interaction networks, are lacking. By mining existing databases and literature, we here provide a comprehensive and manually curated database of taxonomic links between viruses and their cellular hosts.

/pdf/linking-virus-genomes-with-host-taxonomy-4x9hefecpm.pdf

Linking Virus Genomes with Host Taxonomy

In LTE-Advanced networks, besides the overall coverage provided by traditional macrocells, various classes of low-power nodes (e.g., pico eNBs, femto eNBs, and relays) can be distributed throughout the macrocells as a more targeted underlay to further enhance the area?s spectral efficiency, alleviate traffic hot zones, and thus improve the end-user experience. Considering the limited backhaul connections within lowpower nodes and the imbalanced traffic distribution among different cells, it is highly possible that some cells are severely congested while adjacent cells are very lightly loaded. Therefore, it is of critical importance to achieve efficient load balancing among multi-tier cells in LTEAdvanced networks. However, available techniques such as smart cell and biasing, although able to alleviate congestion or distribute traffic to some extent, cannot respond or adapt flexibly to the real-time traffic distributions among multi-tier cells. Toward this end, we propose in this article a device-to-device communicationbased load balancing algorithm, which utilizes D2D communications as bridges to flexibly offload traffic among different tier cells and achieve efficient load balancing according to their real-time traffic distributions. Besides identifying the research issues that deserve further study, we also present numerical results to show the performance gains that can be achieved by the proposed algorithm.

Hiroki Nishiyama

Papers

Relay-by-smartphone: realizing multihop device-to-device communications

Hybrid Method for Minimizing Service Delay in Edge Cloud Computing Through VM Migration and Transmission Power Control

A Survey on Network Methodologies for Real-Time Analytics of Massive IoT Data and Open Research Issues

Linking Virus Genomes with Host Taxonomy

Device-to-device communications achieve efficient load balancing in LTE-advanced networks