nach oben

2017 | Buch

Kapitel lesen Erstes Kapitel lesen

Industrial Networks and Intelligent Systems

Second International Conference, INISCOM 2016, Leicester, UK, October 31 – November 1, 2016, Proceedings

herausgegeben von: Leandros A. Maglaras, Helge Janicke, Kevin Jones

Verlag: Springer International Publishing

Buchreihe : Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten

Über dieses Buch

This book constitutes the thoroughly refereed post-conference proceedings of the Second International Conference on Industrial Networks and Intelligent Systems, INISCOM 2016 held in Leicester, UK, October 31 – November 1, 2016.
The 15 revised full papers carefully reviewed and selected from 22 submissions. The papers cover topics on industrial networks and applications, intelligent systems, information processing and data analysis, hardware and software design and development, security and privacy.

Inhaltsverzeichnis

Frontmatter

Spatial Keyword Query Processing in the Internet of Vehicles

Abstract

This paper takes the first step to address the issue of processing Spatial Keyword Queries (SKQ) in the Internet of Vehicles (IoV) environment. As a key technique to obtain location-aware information, the Spatial Keyword Query (SKQ) is proposed. It can search qualified objects based on both keywords and location information. In the IoV, with the popularity of the GPS-enabled vehicle-mounted devices, location-based information is extensively available, and this also enables location-aware queries with special keywords to improve user experience. In this study, we focus on Boolean kNN Queries. And a Spatial Keyword query index for IoV environment (SKIV) is proposed as an important part of the algorithm design to be used to improve the performance of this type of SKQ. Extensive simulation is conducted to demonstrate the efficiency of the SKIV based query processing algorithm.

Yanhong Li, Lei Shu, Jianjun Li, Rongbo Zhu, Yuanfang Chen

Recovering Request Patterns to a CPU Processor from Observed CPU Consumption Data

Abstract

Statistical queuing models are popular to analyze a computer systems ability to process different types requests. A common strategy is to run stress tests by sending artificial requests to the system. The rate and sizes of the requests are varied to investigate the impact on the computer system. A challenge with such an approach is that we do not know if the artificial requests processes are realistic when the system are applied in a real setting. Motivated by this challenge, we develop a method to estimate the properties of the underlying request processes to the computer system when the system is used in a real setting. In particular we look at the problem of recovering the request patterns to a CPU processor. It turns out that this is a challenging statistical estimation problem since we do not observe the request process (rate and size of the requests) to the CPU directly, but only the average CPU usage in disjoint time intervals.

In this paper we demonstrate that, quite astonishingly, we are able to recover the properties of the underlying request process (rate and sizes of the requests) by using specially constructed statistics of the observed CPU data and apply a recently developed statistical framework called Approximate Bayesian Computing.

Hugo Lewi Hammer, Anis Yazidi, Alfred Bratterud, Hårek Haugerud, Boning Feng

Impacts of Radio Irregularity on Duty-Cycled Industrial Wireless Sensor Networks

Abstract

With rapid adoption of advanced wireless sensors in last decades, industrial wireless sensor networks (IWSNs) are increasingly deployed in the industries for various applications. Sleep scheduling is a common approach in IWSNs to overcome network lifetime problem due to energy-constrained sensor nodes. However, in real-environment, node’s transmit power varies in different directions due to non-isotropic nature of electromagnetic transmission, path-loss, noise, and temperature. Thus, radio irregularity results in link asymmetry, thereafter, affects the performance of sleep scheduling in IWSNs. In this paper, we evaluate the impacts of radio irregularity on sleeping probability and lifetime performances of well-known connected k-neighborhood (CKN)-based sleep scheduling algorithms in duty-cycled IWSNs. We derive the upper-limit of sleep probability with radio irregularity variables. From the extensive simulations, we show that radio irregularity increases the number of awake nodes in duty-cycled sensor networks, therefore, network lifetime decreases with increasing values of link asymmetry parameters. Finally, an adverse impact of radio irregularity is observed in higher k-value in CKN-based algorithm due to more awake nodes to satisfy the k-connectivity in presence of link asymmetry.

Mithun Mukherjee, Lei Shu, Likun Hu, Der-Jiunn Deng

Security Visualization: Detecting Denial of Service

Abstract

Denial Of Service attacks are notorious attack methods used to target servers of IT systems and Industrial Control Systems to prevent them from working or to reduce efficiency, hence decreasing user experience. Visualization is the method of taking data, processing and displaying data in an easy to view format. Visualization could be used to identify Denial Of Service attacks by monitoring the data sent to clients and being displayed to the users. Manipulating the type of data shown and the format it is shown in can help users spot potential attacks by seeing outliers in the data sets. This research develops novel software that can run on an web server. It processes the web access logs, displays the data to users and identify potential attacks in access logs. The software has been tested, with the majority of tests passing. Further development of the project is discussed and the main areas for development are also explored.

Glen Hawthorne, Ying He, Leandros Maglaras, Helge Janicke

Latency in Cascaded Wired/Wireless Communication Networks for Factory Automation

Abstract

Unlike in the areas of process automation and condition monitoring, current wireless technologies cannot be used for many closed-loop control applications in factory automation. These applications require shorter cycle times, precise synchronicity in the microseconds range and higher reliability with low packet error rates. Furthermore, established Industrial Ethernet communication systems will not be completely replaced in the near future. Therefore, a wireless communication system for factory automation also requires seamless integration into existing networks.

However, a resulting cascaded network will lead to additional latencies, which have a negative effect on the overall real-time performance. In this paper, we analyze the effect of frame structure conversion for different subnetworks with respect to the additional latencies they introduce. Therefore, we introduce an abstracted network model representing various subnetworks. We exemplify different protocol implementations and discuss them in terms of the resulting latencies and optimizations.

Steven Dietrich, Gunther May, Johannes von Hoyningen-Huene, Andreas Mueller, Gerhard Fohler

Network Topology Exploration for Industrial Networks

Abstract

Large industrial networks (e.g., plants and grids) are usually characterized by numerous sectors of responsibility and multiple suppliers. Managing these networks is a challenge and requires concrete knowledge of the current network state in terms of device influence and network activities. Here, automated topology exploration is a valuable and very performant measure to provide a wide range of information about devices and their communication relations. Existing exploration methods mostly use active, intrusive methods which have no chance to be applied in sensitive or critical industrial networks. In this paper we present a completely passive approach. It is supplier-independent and provides information that has not been explored before using passive methods.

Andreas Paul, Franka Schuster, Hartmut König

An Improved Robust Low Cost Approach for Real Time Vehicle Positioning in a Smart City

Abstract

The Global Positioning System (GPS) aided low cost Dead Reckoning (DR) system can provide without interruption the vehicle position for efficient fleet management solutions in smart cities. The Extended Kalman Filter (EKF) is generally applied for data fusion using the sensor’s measures and the GPS position as a helper.

However, the EKF depends on the vehicle dynamic variations and may quickly diverge during periods of GPS signal loss.

In this paper, we present a robust low cost approach using EKF and neural networks (NN) with Particle Swarm Optimization (PSO) to reliably estimate the real time vehicle position. While GPS signals are available, we train the NN with PSO on different dynamics and outage times to learn the position errors so we can correct the future EKF predictions during GPS signal outages. We obtain empirically an improvement of up to 94% over the simple EKF predictions in case of GPS failures.

Ikram Belhajem, Yann Ben Maissa, Ahmed Tamtaoui

Effect of Network Architecture Changes on OCSVM Based Intrusion Detection System

Abstract

Intrusion Detection Systems are becoming an important defense mechanism for (supervisory control and data acquisition (SCADA) systems. SCADA systems are likely to become more dynamic leading to a need for research into how changes to the network architecture that is monitored, affect the performance of defense mechanisms. This article investigates how changes in the network architecture of the SCADA system affect the performance of an IDS that is based on the One class Support Vector Machine (OCSVM). Also the article proposes an adaptive mechanism that can cope with such changes and can work in real time situations.

Barnaby Stewart, Luis Rosa, Leandros Maglaras, Tiago J. Cruz, Paulo Simões, Helge Janicke

Smart Behavioural Filter for SCADA Network

Abstract

Industrial Control Systems (ICS) are jeopardized from a large set of threat vectors, which exploit their vulnerabilities in order to impact the physical Critical Infrastructures they control. The Information Technology (IT) classical approach to cyber attacks can not be applied to ICS due to their extreme differences from main priorities to resource constrains. Therefore, innovative approaches and equipment must be developed in order to suit with ICS world.

In this paper, a Smart Behavioural Filter (SBF) for the PLCs/RTUs is proposed aiming to secure the PLC/RTU itself against logic attacks, that are stealth for other more classical security approaches. Those logic attacks are usually anomaly behaviours, for instance a large number of open/close commands towards a valve. This smart field equipment can communicate with other equipment like itself in order to react in short time to cyber attacks and increase the resilience of the physical system. It can also generate alarms for the local Intrusion Detection System (IDS) The proposed equipment has been developed and validated in a real test-bed within the FP7 CockpitCI project. The results are promising.

Giovanni Corbò, Chiara Foglietta, Cosimo Palazzo, Stefano Panzieri

Adaptive Down-Sampling and Super-Resolution for Additional Video Compression

Abstract

While almost all down-sampling based video codecs gain additional compression at the expense of image degradation, we set a good example of achieving both large compression and even better reconstruction quality. Such progress is realized by: (i) minimizing the introduction of information loss with a proposed decomposition-based adaptive down-sampling method so that more reserved pixels can be allocated to image details where human visual perception is more sensitive. Specifically, a modified content complexity measurement is put forward and the optimum down-sampling rate is adaptively selected with a customized formula; (ii) maximizing the information compensation via a content-adaptive super-resolution algorithm, which is accelerated and optimized by two stages of pruning to select the closest correlated dictionary pairs. Extensive experiments support that, by using prevailing H.264 codec as benchmark, the proposed scheme achieves 5 times more of additional compression and the reconstruction quality outperforms other state-of-the-art approaches, and even better than decoded non-shrunken frames in human visual perception.

Bin Zhao, Jianmin Jiang

Improving Classification of Tweets Using Linguistic Information from a Large External Corpus

Abstract

The bag of words representation of documents is often unsatisfactory as it ignores relationships between important terms that do not co-occur literally. Improvements might be achieved by expanding the vocabulary with other relevant word, like synonyms.

In this paper we use word-word co-occurence information from a large corpus to expand the vocabulary of another corpus consisting of tweets. Several different methods on how to include the co-occurence information are constructed and tested out on the classification of real twitter data. Our results show that we are able to reduce the number of erroneous classifications by 14% using co-occurence information.

Hugo Lewi Hammer, Anis Yazidi, Aleksander Bai, Paal Engelstad

Walking into Panoramic and Immersive 3D Video

Abstract

To enable viewers to perceive the video content as if he or she is walking inside the video scenes, we need to have two essential video technologies. One is to present the audience with panoramic videos with 360°, and the other is view-adaptive video playback, i.e. presenting video scenes in accordance with the change of viewing angles. For the first technology, we propose a fast video stitching algorithm via exploiting the audio information for frame synchronization, and for the second, we propose a Fake-3D and True-3D mix method to immerse viewers inside the video scene via its dynamic playback of panoramic videos, adaptive to multi-view changes. Our proposed technologies have great potential in practical applications, such as virtual reality gaming and new concept movie shows etc.

Yingbin Nie, Jianmin Jiang

Mobile Agent Itinerary Planning Approaches in Wireless Sensor Networks- State of the Art and Current Challenges

Abstract

A ubiquitous embedded network, such as wireless sensor network (WSN), is characterised by its capability to carry out common tasks by sharing resources that are placed in-node or in-network domains. One of the most critical properties of mobile agent (MA) based wireless sensor network is how to design the itinerary through the WSN for mobile agent. In addition to that, a huge amount of redundant data is generated by sensors due to node density and placement. This consumes network resources such as bandwidth and energy, thus decreasing the life time of sensor network. Several studies have demonstrated the benefits of using mobile agent technology as an effective technique to overcome these limitations. MA itinerary planning techniques can be classified into three categories depending on the factors that define the route of the MA: static-itinerary, dynamic-itinerary, and hybrid-based. This paper presents a survey of the state-of-the-art MA itinerary planning techniques in WSN. The benefits and shortcomings of different MA itinerary planning approaches are presented as motivation for future work into energy efficient MA itinerary planning mechanism.

Tariq Alsboui, Mustafa Alrifaee, Rami Etaywi, Mohammad Abdul Jawad

Mood-Based On-Car Music Recommendations

Abstract

Driving and music listening are two inseparable everyday activities for millions of people today in the world. Considering the high correlation between music, mood and driving comfort and safety, it makes sense to use appropriate and intelligent music recommendations based on the mood of drivers and songs in the context of car driving. The objective of this paper is to present the project of a contextual mood-based music recommender system capable of regulating the driver’s mood and trying to have a positive influence on her driving behaviour. Here we present the proof of concept of the system and describe the techniques and technologies that are part of it. Further possible future improvements on each of the building blocks are also presented.

Erion Çano, Riccardo Coppola, Eleonora Gargiulo, Marco Marengo, Maurizio Morisio

Automatic Detection of Hateful Comments in Online Discussion

Abstract

Making violent threats towards minorities like immigrants or homosexuals is increasingly common on the Internet. We present a method to automatically detect threats of violence using machine learning. A material of 24,840 sentences from YouTube was manually annotated as violent threats or not, and was used to train and test the machine learning model. Detecting threats of violence works quit well with an error of classifying a violent sentence as not violent of about 10% when the error of classifying a non-violent sentence as violent is adjusted to 5%. The best classification performance is achieved by including features that combine specially chosen important words and the distance between those in the sentence.

Hugo Lewi Hammer

Backmatter

Titel: Industrial Networks and Intelligent Systems
herausgegeben von: Leandros A. Maglaras
Helge Janicke
Kevin Jones
Verlag: Springer International Publishing
Electronic ISBN: 978-3-319-52569-3
Print ISBN: 978-3-319-52568-6
DOI: https://doi.org/10.1007/978-3-319-52569-3