The Internet of Things is a novel paradigm with access to wireless communication systems and artificial intelligence technologies, which is considered to be applicable to a variety of promising fields and applications. Meanwhile, the development of the fifth-generation cellular network technologies creates the possibility to deploy enormous sensors in the framework of the IoT and to process massive data, challenging the technologies of communications and data mining. In this article, we propose a novel paradigm, 5G Intelligent Internet of Things (5G I-IoT), to process big data intelligently and optimize communication channels. First, we articulate the concept of the 5G I-IoT and introduce three major components of the 5G I-IoT. Then we expound the interaction among these components and introduce the key methods and techniques based on our proposed paradigm, including big data mining, deep learning, and reinforcement learning. In addition, an experimental result evaluates the performance of 5G I-IoT, and the effective utilization of channels and QoS have been greatly improved. Finally, several application fields and open issues are discussed.

From IoT to 5G I-IoT: The Next Generation IoT-Based Intelligent Algorithms and 5G Technologies

| All drivers have habits behind the wheel. Different drivers vary in how they hit the gas and brake pedals, how they turn the steering wheel, and how much following distance they keep to follow a vehicle safely and comfortably. In this paper, we model such driving behaviors as car-following and pedal operation patterns. The relationship between following distance and velocity mapped into a two-dimensional space is modeled for each driver with an optimal velocity model approximated by a nonlinear function or with a statistical method of a Gaussian mixture model (GMM). Pedal operation patterns are also modeled with GMMs that represent the distributions of raw pedal operation signals or spectral features extracted through spectral analysis of the raw pedal operation signals. The driver models are evaluated in driver identification experiments using driving signals collected in a driving simulator and in a real vehicle. Experimental results show that the driver model based on the spectral features of pedal operation signals efficiently models driver individual differences and achieves an identification rate of 76.8% for a field test with 276 drivers, resulting in a relative error reduction of 55% over driver models that use raw pedal operation signals without spectral analysis.

Driver modeling based on driving behavior and its evaluation in driver identification : Analysis of car-pedal use and car-following habits may allow the help offered by intelligent driver assistance systems to be customized for individual drivers

Tra'c congestion has been one of major issues that most metropolises are facing. It is believed that identication of congestion is therst step for selecting appropriate mitigation measures. Congestion - both in perception and in reality - impacts the movement of people. Tra'c congestion wastes time, energy and causes pollution. �ere are broadly two factors, which e±ect the congestion; (a) micro-level factors (b) macro-level factors that relate to overall demand for road use. Congestion is 'triggered' at the 'micro' level (e.g. on the road), and 'driven' at the 'macro' level. �e micro level factors are, for example, many people want to move at the same time, too many vehicles for limited road space. On the other side, macro level factors are e.g. land-use paerns, car ownership trends, regional economic dynamics, etc. �is paper gives an overview and presents the possible ways to identify and measure metrics for urban arterial congestion. A systematic review is carried out, based on measurement metrics such as speed, travel time/delay and volume and level of service. �e review covers distinct aspects like denition; measurement criteria followed by di±erent countries/organizations. �e strengths and weaknesses of these measures are discussed. Further, a short critique of measurement criteria is presented.

/pdf/measuring-urban-traffic-congestion-a-review-3i6jk5zxrw.pdf

Measuring Urban Traffic Congestion - A Review

Practical real-time intrusion detection using machine learning approaches

Understanding the variability of Internet traffic in backbone networks is essential to better plan and manage existing networks, as well as to design next generation networks. However, most traffic analyses that might be used to approach this problem are based on detailed packet or flow level measurements, which are usually not available throughout a large network. As a result there is a poor understanding of backbone traffic variability, and its impact on network operations (e.g. on capacity planning or traffic engineering).This paper introduces a metric for measuring backbone traffic variability that is grounded on simple but powerful traffic theory. What sets this metric apart, however, is that we present a method for making practical measurements of the metric using widely available SNMP traffic measurements. Furthermore, we use a novel method to overcome the major limitation of SNMP measurements -- that they only provide link statistics. The method, based on a "gravity model", derives an approximate traffic matrix from the SNMP data. In addition to simulations, we use more than 1 year's worth of SNMP data from an operational IP network of about 1000 nodes to test our methods. We also delve into the degree and sources of variability in real backbone traffic, providing insight into the true nature of traffic variability.

/pdf/experience-in-measuring-backbone-traffic-variability-models-1k4xhszrry.pdf

Experience in measuring backbone traffic variability: models, metrics, measurements and meaning

This paper presents the design and implementation of an authorization mechanism for MQTT-based Internet of Things (IoT). The design is based on OAuth 1.0a, which is an open authorization standard for web applications. Some redesign and modification have been made to the based framework to fit it within the MQTT environment. Several considerations are taken into account, including limited node resources, lack of node's user interface, and key/secret distribution and management. The design is implemented on a real MQTT-based IoT service platform and demonstrated that it works as intended. Authorization delay and message overhead are minimal. Security issues are analyzed along with discussion for future work.

Authorization mechanism for MQTT-based Internet of Things

This study investigates an alternative way to estimate degrees of road traffic congestion based on routine GPS measurements from main roads in urban areas of Bangkok, Thailand. We classify three levels of traffic congestion according to the weighted exponential moving averages of measured GPS speed. Human perception is used to obtain classification thresholds and evaluated the performance of the proposed method. The benefits of our proposed method over existing techniques is that it is simple, easy to understand, and compatible with existing traffic report systems in Bangkok

Estimating Road Traffic Congestion using Vehicle Velocity

This paper presents a road-traffic evaluation system from image processing data using manually tuned fuzzy logic and adaptive neuro-fuzzy techniques. The system is designed to emulate human's expertise on specifying three levels of traffic congestion within Bangkok Metropolitan Area. The traffic information comes from a vehicle detection and tracking software, which takes a road-traffic video signal as an input and computes vehicle volume and velocity. We verify accuracy of our system by comparing outputs of the system with opinions of volunteers who watch the same traffic video. Results show that manually tuned fuzzy logic achieves 88.79% accuracy, while the adaptive neuro-fuzzy technique achieves only 75.43% accuracy.

Evaluation of road traffic congestion using fuzzy techniques

We propose a system that can record driving events and detect unsafe driving behaviors. Three sensors, an engine control unit (ECU) reader, a 3-axis accelerometer, and a camera are used, in which they represent the car, the passenger, and the driverpsilas perspective. Our system combines data from these three sensors with a fuzzy inference system to identify an event of hazardous driving. The output of the system is the driving risk level ranging from 1 to 3, where 1 is the safest. The output of the system was verified by comparison with a questionnaire from three passengers in a test run experiment.

P. Pongpaibool

Papers

Authorization mechanism for MQTT-based Internet of Things

Estimating Road Traffic Congestion using Vehicle Velocity

Evaluation of road traffic congestion using fuzzy techniques

Detection of hazardous driving behavior using fuzzy logic

Providing end-to-end service level agreements across multiple ISP networks