PECCS 2014 Abstracts


Area 1 - Mobile and Pervasive Computing

Full Papers
Paper Nr: 15
Title:

Dynamic Graphical User Interface Generation for Web-based Public Display Applications

Authors:

Jorge C. S. Cardoso

Abstract: Public digital displays are moving towards open display networks, resulting in a shift in the focus from single-purpose public displays that are developed with a single task or application in mind, to general-purpose displays that can run several applications, developed by different vendors. In this new paradigm, it is important to facilitate the development of interactive public display applications and provide programmers with toolkits for incorporating interaction features. An important function of such toolkits is to support interaction with public displays through a users' smartphone, allowing users to discover and interact with the public display applications configured in a given display. This paper describes our approach to providing dynamically generated graphical user interfaces for public display applications that is part of the PuReWidgets toolkit.

Paper Nr: 26
Title:

Smartphone-based Activity Recognition using Hybrid Classifier - Utilizing Cloud Infrastructure for Data Analysis

Authors:

Bingchuan Yuan, John Herbert and Yalda Emamian

Abstract: Learning and recognizing the activities of daily living (ADLs) of an individual is vital when providing an individual with context-aware at-home healthcare. In this work, unobtrusive detection of inhabitants’ activities in the home environment is implemented through the smartphone and wearable wireless sensor belt solution. A hybrid classifier is developed by combining threshold-based methods and machine learning mechanisms. Features extracted from the raw inertial sensor data are collected from a Body Area Network (BAN) (consisting of the Zephyr BioHarness sensor and an Android smartphone), and are used to build classification models using different machine learning algorithms. A cloud-based data analytics framework is developed to process different classification models in parallel and to select the most suitable model for each user. The evolving machine learning mechanism makes the model become customizable and self-adaptive by utilizing a cloud infrastructure which also overcomes the limitation of the computing power and storage of a smartphone. Furthermore, we investigate methods for adapting a universal model, which is trained using the data set of all users, to an individual user through an unsupervised learning scheme. The evaluation results of the experiments conducted on eight participants indicate that the proposed approach can robustly identify activities in real-time across multiple individuals: the highest recognition rate achieved 98% after a few runs.

Short Papers
Paper Nr: 13
Title:

Activity Recognition Using Non-intrusive Appliance Load Monitoring

Authors:

Olaf Wilken, Oliver Kramer, Enno-Edzard Steen and Andreas Hein

Abstract: The recognition of sequences via non-intrusive appliance load monitoring has an important part to play for various applications in healthcare. In our work, we present a system for the detection of daily activities based on the use of appliances. The objective of our activity monitoring system is to maximize the time elder people can stay in their own domestic environment. We propose a system that is able to detect comparably complex activities that may be interrupted by other activities. In the experimental part of our work, a one-month and a half-year field study demonstrate the capabilities of the proposed approach.

Paper Nr: 27
Title:

Privacy in Pervasive Video Surveillance - Trust through Technology and Users Cooperation

Authors:

Antoni Martínez-Ballesté, Agusti Solanas, Marc Vives and Hatem A. Rashwan

Abstract: During the last decades, video surveillance systems (VSS) have become popular and, nowadays, they can be found almost everywhere. When those systems were initially deployed, they were mainly used by authorities only and, people tend to accept to be surveilled for the sake of security. Currently, VSS are located in public places and controlled by governmental agencies, but some others are placed in private spaces and controlled by corporations, banks, and so on. In addition, VSS have gained computational capabilities and, nowadays, off-the-shelf cameras are able to record high quality digital video that can be easily shared by means of private networks or even the Internet. Trust is strictly related to the operators of those VSS and their behaviour. Hence, it is necessary to define a comprehensive model for trustworthy video surveillance, aiming at preserving the right to privacy of citizens. In this article we present a platform for trustworthy video surveillance. Our model is based on the use of real-time and accurate techniques, and the active cooperation of people using mobile applications.

Paper Nr: 43
Title:

Taxonomy for Internet of Things - Tools for Monitoring Personal Effects

Authors:

Leon Barker, Martin White, Mairead Curran, Zeeshan Patoli, Benji Huggins, Tudor Pascu and Natalia Beloff

Abstract: Human capacities to track and identify peers, products and activities have benefited from the wide proliferation of networked electronic devices; developments in smart-materials, near-field communication and computervision technology further advance these capabilities. During this investigation into The Internet of Things (IoT) a new taxonomy was created together with a set of prototype applications and accompanying architecture. In addition to presenting these taxonomies the creation of a peer-to-peer network with a distributed database is discussed. The development of a system that enables users to track and exchange objects or services using a secure and robust data repository model is also proposed.

Posters
Paper Nr: 8
Title:

An Automatic Vision System using Optical Scanning Mechanism with Near-infrared Optics for Solar Cell Wafer

Authors:

Gyung-bum Kim

Abstract: In this paper, an automatic vision system based on optical scanning mechanism is developed for solar cell wafer. It consists of optical scanning mechanism with near-infrared(NIR) camera optics, machinery and control system, algorithm of defect detection and software. Optical scanning mechanism is composed of geometrical camera optics and structured hybrid illumination system(SHIS). It is used to inspection of surface defects. Also, NIR camera optics is used for inspection of defects inside solar cell wafer. It is shown that the automatic inspection system give satisfactory performance for micro defects in solar cell wafer.

Paper Nr: 10
Title:

A Mobile Multi Agent System for Routing in Adhoc Network

Authors:

M. A. Riahla, K. Tamine, A. Mifdal and M. Mezghiche

Abstract: Dynamic networks are a challenge for the deployment of distributed applications on autonomous machines. But, these networks can meet problems with implementation of services such as routing and security in general. In this sense, the multi-agent systems are well suited for the design of distributed systems where several autonomous agents interact or work together to perform some set of tasks or satisfy some set of goals and moving the problem of analyzing from a global level to a local level and then reduce the complexity of the design (Ferber, 1997) In this paper we present a generic model Multi Agent system that we adapt to develop a new routing protocol for ad hoc networks. Wireless ad hoc networks are infrastructureless networks that comprise wireless mobile nodes able to communicate each other outside wireless transmission range. Due to frequent network topology changes in one hand and the limited underlying bandwidth in the other hand, routing becomes a challenging task. In this paper we present a novel routing algorithm devoted for mobile ad hoc networks. It entails both reactive and proactive components. More precisely, the algorithm is based on ant general behavior, but differs from the classic ant methods inspired from Ant-Colony-Optimization algorithm (Dorigo, Birattari and Stutzle, 2006). We do not use, during the reactive phase, a broadcasting technique that exponentially increases the routing overhead, but we introduce a new reactive route discovery technique that considerably reduces the communication overhead.

Paper Nr: 37
Title:

Simulated Framework for the Development and Evaluation of Redundant Robotic Systems

Authors:

Ioannis Iossifidis

Abstract: In the current work we present a simulated environment for the development and evaluation of multi redundant open chain manipulators. The framework is implemented in Matlab and provides solutions for the kinematics and dynamics of an arbitrary open chain manipulator. For a anthropomorphic trunk-shoulder-arm configuration with in total nine degree of freedoms, a closed form solution of the inverse kinematics problem is derived. The attractor dynamics approach to motion generation was evaluated within this framework and the results are verified on the real anthropomorphic robotic assistant Cora.

Paper Nr: 39
Title:

Development of a Haptic Interface for Safe Human Roobt Collaboration

Authors:

Ioannis Iossifidis

Abstract: In the context of the increasing number of collaborative workplaces in industrial environments, where humans and robots sharing the same workplace, safety and intuitive interaction is a prerequisite. This means, that the robot can (1) have contact with his own body and the surrounding objects, (2) the motion of the robot can be corrected online by the human user just by touching his artificial skin or (3) interrupt the action in dangerous situations. In the current work we introduce a haptic interface (artificial skin) which is utilized to cover the arms of an anthropomorphic robotic assistant. The touched induced input of the artificial skin is interpreted and fed into the motor control algorithm to generate the desired motion and to avoid harm for human and machine.

Paper Nr: 45
Title:

Pervasive Ambient Intelligence Platforms in the IOT Era based on a Ubiquitous User Model Ontology - An Implementation Account

Authors:

Alfio Costanzo, Alberto Faro and Daniela Giordano

Abstract: This paper presents how ambient data integration is obtained in Wi-City, i.e. a project promoted by the Regional Government of Sicily that aims at supporting mobile people activities by means of intelligent applications able to generate personalized recommendations that take into account both personal and context parameters. The paper shows how this is made possible by the decreasing cost of the monitoring systems in the IOT era and by the availability of ontology engineering methods to data integration. In particular, aim of the paper is to illustrate a pervasive platform consisting of environmental sensors readily installable on the city and body sensors easily wearable by people that cooperate by means of an ambient data ontology to better support the user decisions in a smart city. Examples of how embedded consumer electronics products are used to monitor the user ambient and how developing an effective ambient data ontology are illustrated to give an implementation account of the proposed platform.

Area 2 - Digital Signal Processing

Full Papers
Paper Nr: 16
Title:

Iterative Bit- and Power Allocation in Correlated MIMO Systems

Authors:

Francisco Cano-Broncano, Andreas Ahrens and César Benavente-Peces

Abstract: In this contribution a novel iterative bit- and power allocation (IBPA) approach has been developed when transmitting a given bit/s/Hz data rate over a correlated frequency non-selective (4×4) Multiple-Input Multiple- Output (MIMO) channel. The iterative resources allocation algorithm developed in this investigation is aimed at the achievement of the minimum bit-error rate (BER) in a correlated MIMO communication system. In order to achieve this goal, the available bits are iteratively allocated in the MIMO active layers which present the minimum transmit power requirement per time slot.

Short Papers
Paper Nr: 12
Title:

Towards Embedded Robot Vision for Multi-scale Object Recognition - Repeatability of Interest Points Detected in Half-octave Binomial Pyramids

Authors:

Peter Andreas Entschev and Hugo Vieira Neto

Abstract: The construction of multi-scale image pyramids is used in state-of-the-art methods that perform robust object recognition, such as SIFT and SURF. However, building such image pyramids is computationally expensive, especially when implementations in embedded systems with limited computing resources are considered. Therefore, the use of alternative less expensive approaches are necessary if near real-time operation is desired. Previous work has reported that using binomial filters to construct half-octave multi-scale pyramids consumes only 1=4 of the processing time of the Gaussian pyramid originally used in the SIFT framework. Here we investigate how interest points detected using the binomial approach behave when compared to the Gaussian approach, focusing on repeatability. Experimental results show that in average up to 86% of interest points detected with the original SIFT pyramid building scheme are also detected when using the binomial method, despite of large gains in processing time. When rotation of image features is considered, experimental results demonstrate that slightly superior repeatability of interest points is achieved using the binomial pyramid.

Paper Nr: 19
Title:

Formatting Bits to Better Implement Signal Processing Algorithms

Authors:

Benoit Lopez, Thibault Hilaire and Laurent-Stéphane Didier

Abstract: This article deals with the fixed-point computation of the sum-of-products, necessary for the implementation of several algorithms, including linear filters. Fixed-point arithmetic implies output errors to be controlled. So, a new method is proposed to perform accurate computation of the filter and minimize the word-lengths of the operations. This is done by removing bits from operands that don’t impact the final result under a given limit. Then, the final output of linear filter is guaranteed to be a faithful rounding of the real output.

Posters
Paper Nr: 31
Title:

The Battle of the Giants - A Case Study of GPU vs FPGA Optimisation for Real-time Image Processing

Authors:

Lars Struyf, Stijn De Beugher, Dong Hoon Van Uytsel, Frans Kanters and Toon Goedemé

Abstract: This paper focuses on a thorough comparison of the two main hardware targets for real-time optimization of a computer vision algorithm: GPU and FPGA. Based on a complex case study algorithm for threaded isle detection, implementation on both hardware targets is compared in terms of resulting time performance, code translation effort, hardware cost, power efficiency and integrateability. A real-life case study as described in this paper is a very useful addition to discussions on a more theoretical level, going beyond artificial experiments. In our experiments, we show the speed-up gained by porting our algorithm to FPGA using manually written VHDL and to a heterogeneous GPU/CPU architecture with the OpenCL language. Also, issues and problems occurring during the code porting are detailed.

Area 3 - Embedded Systems Design

Short Papers
Paper Nr: 20
Title:

Electromagnetic Emission of an Optical-to-BroadR-Reach Converter

Authors:

Dennis Degueldre, Thomas Waas and Markus Kucera

Abstract: The automotive solution for Ethernet is BroadR-Reach, which cannot be found as a common Ethernet-interface in the consumer industry. Hence a media converter from IEEE 802.3 Ethernet to BroadR-Reach is needed to debug and test the communication of automotive devices under test (DUT). If the functionality of a BroadR-Reach connection has to be tested for electromagnetic compatibility (EMC), a BroadR-Reach to optical media converter is needed, which has to comply to the same EMC test specifications as the DUT. This research explains the internal structure of a media converter and defines a test setup for copper bound emission test of BroadR-Reach. By using a standardized stripline measurement like it is common for electromagnetic emission test, it could be shown, that the tested Technica/Tinytron media converter can safely be used inside an EMC chamber.

Paper Nr: 32
Title:

Combinatorial Approaches for Low-power and Real-time Adaptive Reconfigurable Embedded Systems

Authors:

Hamza Chniter, Fethi Jarray and Mohamed Khalgui

Abstract: This paper describes an optimisation-oriented approach to dynamic reconfiguration of embedded systems with real-time and power consumption constraints. A reconfiguration scenario is assumed to be any run-time operation allowing the addition-removal-update of OS tasks to adapt the system to its environment under well-defined conditions. The problem is that any reconfiguration can lead the system to an unfeasible state where temporal properties are violated or the energy consumption is well-increased. Two methods, integer programming and simulated annealing, are used to that purpose. The methods have been validated using analysis tools to evaluate the whole contribution.

Paper Nr: 35
Title:

Towards New Interface for Non-volatile Memory Storage

Authors:

Shuichi Oikawa

Abstract: Non-volatile memory (NVM) storage is rapidly dominating the high end markets of enterprise storage, which requires high performance, and mobile devices, which require lower power consumption. As NVM storage becomes more popular, its form evolves from that of HDDs into those that fit the market requirements more appropriately. Such evolution also stimulates the performance improvement because it leads to the changes of the interface that connects NVM storage with systems. There is a claim that the further improvement of NVM storage performance makes it better to poll a storage device to sense completion of access requests rather than to use interrupts. Polling based storage can expand to become main memory based on NVM storage since there is no complex mechanism required to enable interrupts and access requests are processed one by one. This paper predicts that NVM storage will be in a form of main memory, and proposes constructing a file system directly on it in order to overcome its drawbacks when used simply as main memory. The performance projection of the proposed architecture is that accessing files on such a file system can reduce the overhead introduced by handling block devices.

Paper Nr: 48
Title:

Preemptive Hard Real-time Scheduling of Reconfigurable OS Tasks on Multiprocessors Embedded Control Systems

Authors:

Hamza Gharsellaoui, Mohamed Khalgui and Samir Ben Ahmed

Abstract: The paper deals with the real-time scheduling of reconfigurable embedded multiprocessor systems which can change their behaviors at run-time by adding, removing, or also updating OS tasks according to external events or also user requirements. We propose a new approach to check the system’s feasibility of the tasks that we assume periodic while minimizing their response times. An agent-based architecture is proposed to provide run-time technical solutions for users in order to reach again the system’s feasibility after any reconfiguration scenario. The effectiveness and the performance of the designed approach is evaluated through simulation studies.

Paper Nr: 53
Title:

Code Size and Accuracy-aware Synthesis of Fixed-point Programs for Matrix Multiplication

Authors:

Matthieu Martel, Amine Najahi and Guillaume Revy

Abstract: In digital signal processing, many primitives boil down to a matrix multiplication. In order to enable savings in time, energy consumption, and on-chip area, these primitives are often implemented in fixed-point arithmetic. Various conflicting goals undermine the process of writing fixed-point codes, such as numerical accuracy, runtime latency, and size of the codes. In this article, we introduce a new methodology to automate the synthesis of small and accurate codes for matrix multiplication in fixed-point arithmetic. Our approach relies on a heuristic to merge matrix rows or columns in order to reduce the synthesized code size, while guaranteeing a target accuracy. We suggest a merging strategy based on finding closest pairs of vectors, which makes it possible to address in a few seconds problems such as the synthesis of small and accurate codes for size-64 and more matrix multiplication. Finally, we illustrate its efficiency on a set of benchmarks, and we show that it allows to reduce the synthesized code size by more than 50% while maintaining good numerical properties.

Posters
Paper Nr: 9
Title:

Adaptive GP-based Algorithm for Hardware/Software Co-design of Distributed Embedded Systems

Authors:

Adam Górski and Maciej Ogorzalek

Abstract: In this work, a novel adaptive approach to co-design of embedded systems is presented. The approach is based on developmental genetic programming. Unlike most of existing algorithms, presented methodology involves evolving co-synthesis process, not the system architecture directly. Genotype is a tree which nodes include system construction options. The system can adapt to the environment by increasing chromosomes which give better results in each situations. Half of the next populations is created using genetic operators (crossover, mutation, reproduction). Second half is obtained by generating additional solutions but with different probability of the options.

Paper Nr: 23
Title:

nSHIELD-Gateway - A Hybrid FPGA-Microprocessor based Architecture to Foster the Interconnection of Embedded Systems

Authors:

Marco Aiello, Antonio Bruscino, Antonio Di Marzo and Michele Paragliola

Abstract: The complexity of Embedded Systems (ESs) is greatly increased due to their hyper-connectivity. Nowadays resources and data are shared among ESs to create new systems, services and applications. The design of a dynamically composable ES has several pitfalls such as security, safety and privacy that are not easy to handle due to the shortage of tools and standard design methodologies. In such a context an FPGA IP core, based on nSHIELD methodology (EU-FP6-project) and on Xilinx Zynq SoC, has been developed and tested, to mitigate the aforementioned issues and to foster the evolution of the future dynamic composable embedded systems.

Paper Nr: 25
Title:

Use of Partial Reconfiguration for the Implementation and Embedding of the Artificial Neural Network (ANN) in FPGA

Authors:

Carlos Alberto de Albuquerque Silva, Anthony Andrey Ramalho Diniz, Adrião Duarte Dória Neto and Jose Alberto Nicolau de Oliveira

Abstract: This paper is focused on partial reconfiguration of Field Programmable Gate Arrays (FPGAs) Virtex$\circledR$-6, produced by Xilinx$\circledR$, and its application implementing Artificial Neural Networks (ANNs) of Multilayer Perceptron (MLP) type. This FPGA can be partially reprogramed without suspending operation in other parts that do not need reconfiguration. It can be performed by specifying the Modular Project’s flow, where the modules that compose the project can be synthesized separately, and, after that, reunited in another module of highest hierarchical level. Alternatively, it is possible developing reconfigurable modules inserted in partial bitstreams and, later, downloading partial bitstreams successively in hardware. Therefore, it is possible configuring topologies of different MLP networks by using partial bitstreams in reconfigurable areas. It is expected that, in this kind of hardware, applications with MLP ANNs be easily embedded, and also allow easily configuration of many kinds of MLP networks in field.

Paper Nr: 33
Title:

New Reconfigurable Middleware for Feasible Adaptive RT-Linux

Authors:

Imen Khemaissia, Olfa Mosbahi, Mohamed Khalgui and Walid Bouzayen

Abstract: This paper is interested in reconfigurable real-time embedded OS for microprocessors. Our study concerns specifically RT-Linux. Since the latter is not designed to be reconfigurable, we propose to develop an intermediate layer to play the role of middleware that will be in interaction with the kernel Linux. This layer will manage the addition/removal/update of the periodic and also aperiodic tasks sharing resources and with precedence constraints. These tasks should respect their deadlines after any reconfiguration scenario. The proposed middleware will divide the hardware execution into several virtual processors as time slots. The decomposition is done based on the task’s category. The first virtual processor executes dependent periodic tasks, the second one executes dependent aperiodic tasks with hard deadlines and the third virtual processor executes dependent aperiodic tasks with soft deadlines. After applying a reconfiguration scenario, some tasks may miss their deadlines and the power consumption may increase. In order to re-obtain the feasibility of the system after a such scenario, an agent-based-architecture is defined to modify the parameters of the tasks. The different services offered by this middleware are developed. A simulation study is done in order to highlight the performance of our proposed solutions.

Paper Nr: 34
Title:

Towards a Flexible and Secure Runtime for Embedded Devices

Authors:

Albert Royo Manjon, Eric Simon and Sebastien Jean

Abstract: Advancing towards the Internet of Things, a need for bigger connectivity between every time smaller embedded devices is foreseen. In the near future, heterogeneous resource-restricted devices will probably have a set of services with a strong need for connection. Two needs are envisioned as mandatory: flexibility and security. There is firstly a need for some degree of isolation between services but there is also a need for services to be able to have their runtime altered without having to stop the whole platform. This generates a clash of interests and needs, since achieving both flexibility and security balanced is apparently incompatible. The purpose of this article is to explain the needs and requirements that such systems will most surely have, as well as inspiring technologies and related works, in order to advance towards a platform with flexible and secure services that will add bigger capabilities to the devices.

Paper Nr: 36
Title:

Appropriate Multi-core Architecture for Safety-critical Aerospace Applications - Certifiable Real-time Switching Network

Authors:

Stephan C. Stilkerich, Christian Siemers and Christian Ristig

Abstract: The continues improvement of aircraft’s as well as the steady optimization of the overall air traffic during the last decade increased the demand for processing power in the aircraft and on ground, simultaneously. Multi-Core platforms could offer the demanded processing power and form factor, but today’s multi-core components are principally not usable for any safety critical industry and especially not usable for the avionic domain, because these components are optimized for average case performance and not for full fledged predictability. This is especially true for the inter-core communicaton network. We argue that a regular and low overhead Beneš-Network communication structure between the cores and between the cores and the shared resources, can smoothly pave the way for certification of multi-core architectures in the avionic domain. The presented details on the regular structure of the network, the scheduling variants discussed in the paper and the currently on-going research work to proof profound theoretical limits, bounds etc. substantiate our claim for an utilization of multi-cores in the avionic domain and with respect to the valid regulations for airborne equipment.

Paper Nr: 47
Title:

Developing an Initial Model of Cat Robot Utilizing an Eco-friendly Materials for the Use of Early Treatment of Children with Autism Spectrum Disorder

Authors:

Ja Young Kwon, Keum-hi Mun, Bo Hee Lee and Jin Soun Jung

Abstract: The purpose of this research is to develop an initial model for the use of early treatment that will improve the social interactions of children with Autism Spectrum Disorder (ASD). Researchers from the department of social welfare, electrical engineering, industrial design, and fashion design carried out a fusion research for this purpose. The department of social welfare conducted a survey with professional therapists in order to first find out the necessary treatment components of the cat robot. The department of electrical engineering gave technical suggestions on the practical functions of the robot such as movements and emotional exchanges with humans. In addition, the department of industrial design proposed the robot’s exterior, movement, and character designs. Considering that the robot will be used as a therapeutic medium for children, they also developed an eco-friendly material in order to prevent infection and other hygienic problems and also improve the therapeutic effects of the robot. A follow-up study is proposed.

Paper Nr: 52
Title:

Using a Cyclic Executive in a Data Acquisition for Testing Solar Thermal Systems and Components

Authors:

João Carlos Rodrigues, Ricardo Amorim and Maria João Carvalho

Abstract: This paper presents a real-time control and data acquisition approach, used in our laboratory testbeds for testing of solar thermal system components, accordingly to the European standards EN 12975, EN 12977-3, EN 12977-4 and EN 12976. This approach uses a cyclic scheduler to fulfill different task period requirements at run-time. A tool with a graphical user interface and editing facilities helps the user to find feasible schedulers. Found schedulers can be inserted in the run-time environment, automatically. Cyclic schedulers has been mainly used in safety critical systems, however, they are a valuable support, even in soft real-time systems. Some advantages of using a cyclic scheduler in a soft real-time system are highlighted in the paper. The system architecture used in our testbeds is based on a PC and Agilent 34972A and/or Keithley 2700 commercial data loggers. All the applications software has been developed to fulfil our laboratory requirement procedures. This approach can easily be ported to other environments and architectures.