Search

It is evident that High-Definition Maps (HD Maps) are key enablers of autonomous driving systems, since they enable them to understand the nearby road structure in order to generate a localized corridor. However, the huge cost incurred in creating and maintaining HD Maps is being recognized as a big challenge. To deal with this problem, some researchers have been studying HD Map independent approaches such as online corridor estimation. They tend to require optimistic observations such as tracklets of surrounding vehicles. In this paper, we consider the use of self-driven trajectories, because they represent strong evidence that ego-vehicle could travel along. Based on this consideration, a concept of exemplary trajectory (or exemplar) generation by recombining parts of different trajectories is introduced. The recombination is achieved using genetic algorithm followed by a final selection. The crossover and selection operators are designed to preserve characteristics of parents; with the possibility to simultaneously maintain multiple exemplars covering different lanes. The final selection eliminates redundancy and provides the minimum set of exemplars. Our implementation demonstrated the effectiveness and usefulness of the proposed method.

Today, learning methods and approaches are experiencing great development through technology. Among these methods, we found mobile learning. This type of learning is based on mobile learners who learn in many contexts and environments. Hence the name of context-aware mobile learning systems. In addition, flipped learning is also a new method of learning that consists of inverting the classroom tasks with those done at home. In this paper, we present a context-aware mobile learning approach that provides learners with an adapted course content format. This approach is applied in the context of the flipped classroom.

We propose a novel method called Short-/Long-term Hybrid Prediction (SLHP) that predicts short-term and long-term trajectories of surrounding objects while estimating their future influences on an autonomous ego-vehicle for both types of trajectories. Recently, long-term prediction methods based on trajectory sample generation and verification with road environments and/or interactions have been proposed; however, they entail high computational costs because they need to generate and verify multiple trajectory samples for multiple objects. Therefore, they are not appropriate in scenes where short-term prediction is required such as for sudden motions by surrounding objects. In contrast, our SLHP consists of a hybrid prediction based on short-term and long-term trajectory predictors. SLHP provides flexible predictions that are appropriate to scenes caused by objects' motions, road environments, interactions, and so on. In this paper, we apply and evaluate our method to cut-in prediction as a typical prediction task by using the public road dataset that includes various cut-in events. Experimental results show that SLHP achieves a correctness rate of F-measure = 0.86 for cut-in prediction. Additionally, we confirmed the effectiveness of our hybrid prediction method that provides prediction as early as 3.57 s and 4.82 s before the cut-in event for short-term and long-term trajectory predictions, respectively.

The number of ontologies used for different purposes, such as data integration, information retrieval or search optimization, is constantly increasing. Therefore, it is crucial that ontologies can be developed and explored in an easy way by humans, and are accessible by intelligent agents. To this end, we created VoColReg on top of the VoCol platform. VoColReg provides an integrated registry that hosts VoCol instances, allowing the community to access, browse, reuse, and improve ontologies in a collaborative fashion. VoColReg integrates several improved features, such as syntax validation realized by RDFDoctor, which is able to simultaneously identify a comprehensive list of syntax errors and automatically correct a subset of them. Currently, the VoColReg platform hosts more than 21 ontologies from various domains, where nine of them are publicly available. We analyzed those nine ontologies to discover different facts about them such as hosting platforms used, expressivity of the ontologies, number of triples and modules.

Moving ideation from a closed paradigm (companies) to an open one (crowd) yields several benefits: (1) the crowd allows the generation of a large number of ideas and (2) its heterogeneity increases the potential in obtaining creative ideas. In practice, however, the crowd often fails at generating innovative solutions, leading to duplicate or ideas that use each other's description. Thus, it is practically and economically unfeasible to sift through this large number of ideas to select valuable ones. One promising solution to overcome this issue is identifying relationships between idea text descriptions, such as duplicate, generalize, disjoint, alternative solution. Existing approaches rely either on human judgment, which is expensive and requires domain experts or automatic approaches which compute similarity i.e. one dimension and do not consider other relations. To find complex relationships between idea texts, a first logical step is to fully structure ideas into logic-based representation. However, logic-based representations are very expensive to obtain since ideas' texts do not adhere to any specific structure. Our goal is then to come up with a representation that can be learned by the machine, while still being expressive to allow establishing relationships between ideas. This research in progress introduces an approach based on a sequence-to-sequence learning approach, which allows the machine to learn a lightweight structural representation that is used next to establishing multidimensional relationships between ideas (i.e. different kind of relations between ideas). Based on our investigation, we found out that ideas contain the following patterns: what the idea is about (e.g. window with heat-sensitive material), how it works (e.g. it lights up) and when it works (e.g. in case of fire). Those extracted patterns are then compared with the corresponding patterns of other ideas to establish relations. Our preliminary investigation shows promising results to learn such lightweight structural representation and leverages it in identifying complex relationships between ideas.

This paper proposes the application of a dynamic voltage restorer (DVR) to enhance the power quality and improve the low voltage ride through (LVRT) capability of a three-phase medium-voltage network connected to a hybrid distribution generation system. In this system, the photovoltaic (PV) plant and the wind turbine generator (WTG) are connected to the same point of common coupling (PCC) with a sensitive load. The WTG consists of a DFIG generator connected to the network via a step-up transformer. The PV system is connected to the PCC via a two-stage energy conversion (dc–dc converter and dc–ac inverter). This topology allows, first, the extraction of maximum power based on the incremental inductance technique. Second, it allows the connection of the PV system to the public grid through a step-up transformer. In addition, the DVR based on fuzzy logic controller is connected to the same PCC. Different fault condition scenarios are tested for improving the efficiency and the quality of the power supply and compliance with the requirements of the LVRT grid code. The results of the LVRT capability, voltage stability, active power, reactive power, injected current, and dc link voltage, speed of turbine, and power factor at the PCC are presented with and without the contribution of the DVR system.

Microgrids are, as their name implies, real-time networks operating between producers, distribution companies and consumers. The climate of the Sahara is hot, sunny and arid. This part of Algeria is a hot desert, located on both sides of a tropic. Daytime temperatures are very high, can exceed 50°C, and the thermal amplitude between day and night is often higher than 350 C or 400C. Addition to this, there are many microclimates which are characterized by very high wind speed. It means that both of wind and photovoltaic energies are widely suitable in this area. Aim of this work is to model and simulate operation of microgrids in these areas, including micro power plants, photovoltaic panels, wind farms, diesel power and storage energy, and finally we will apply the model in Real time simulation thanks to MEGASIM of the RT-LAB platform. Results obtained by this tool will allow us to have a very accurate vision of Microgrids operation, in term of power flow or default responses.

A human driver determines his/her driving action by predicting future behavior of other road users based on the consideration of relative relationships and reactions between all players. To get as close as possible to human driving behavior, it is important to predict the early and long-term behavior of other road users. For this sake, many motion-based methods has been proposed, although only for short-term prediction. On the other hand, reasoning-based methods for long-term prediction have been proposed recently. However, they can only predict the latest behavior to the observation and do not consider uncertainty, which is necessary to realize smooth autonomous driving behavior. Therefore, we propose a method that predicts long-term behavior of other road users with estimated probabilities based on semantic reasoning that considers interactions among various players. For this purpose, we define an ontology that provides a conceptual description of all road users with their interactions, and infer the likely behaviors with their associated probabilities using Markov Logic Network (MLN). This framework is used with a actual vehicle as it approaches intersections, to demonstrate its applicability. Results from the real-time implementation on the vehicle, operating under controlled conditions, indicate that the proposed approach predicts a sequence of behavioral possibilities with their associated probabilities as expected.

This paper presents an offline ground truth generation method using LIDAR(Light Detection and Ranging) scans and odometry. The generated ground truth allows quantitative evaluation of the performance of self-localization methods in urban areas where GNSS(Global Navigation Satellite System) cannot be trusted. The proposed method determines the vehicle pose (position and orientation) by aligning the LIDAR input with previously collected point cloud data. However, as alignment convergences are affected by the environment around the vehicle during each LIDAR scan, it can be erroneous. Incorrect estimates are removed and poses are interpolated by relying on odometry; which is locally accurate. A step by step optimization approach is adopted to yield the most accurate result. Experiments performed in a typical urban environment, with many buildings and surrounding obstacles, demonstrated the effectiveness of the proposed method.

The Global Navigation Satellite System (GNSS) is by far the most used system for vehicle self-localization. However, it often fails in urban environments because of signal outages and other interference. To overcome this issue, roof-mounted LiDARs are often used by autonomous driving system developers. From a design point of view, such sensors are not appealing to the public users. Body-embedded sensors do not provide enough information because of placement and size constraints. In this paper, we show how to overcome all these constraints and achieve highly acceptable accuracy allowing reliable autonomous behavior. The proposed method's validity was demonstrated by an autonomous vehicle run in a typical urban environment.

Videoconferencing is increasingly required by a variety of clients and organizations. This technology saves travel time and increases the number of participants with negligible costs. However, the quality of service (QoS) of this technology depends primarily on the network to which participants are connected. Dynamic Multipoint Virtual Private Network (DMVPN) technology is the most requested to interconnect a set of sites in a secure, automatic and on demand manner. In this paper, we will evaluate the performance of videoconferencing in a DMVPN network. The evaluation will focus on the impact of the number of sites, the number of participants per site, and the routing protocols. The evaluation is done under the Riverbed Modeler simulator, the evaluation criteria are: the variation of the delays, the end-to-end delay, the quantity of the received and sent traffic, the rate of the losses, and the duration of convergence of the routing protocols.

An important cornerstone of data processing is the ability to efficiently capture structure in data and perform data classification. More recently, memristive technologies enabled the incorporation of continuous tuneable resistive elements directly in hardware, thus increasing the efficiency of reconfigurable systems power and area-wise. Memristors are a promising candidate for reconfigurable circuits capable of carrying out classification with physical computing, such as dot-product vector multiplication and accumulation technique. In this work, we demonstrate a novel proof-of-concept memristor-based Digital-In-Analogue-Out logic circuit and present preliminary results highlighting the effect of non-uniform non-linear memristor IV characteristics that result in device-to-device behavioural variation.

We consider long-term planning problems for autonomous vehicles in complex traffic scenarios where vehicles and pedestrians interact. The decisions of an autonomous vehicle can influence surrounding other participants in these scenarios. Therefore, planning algorithms that preprocess the long-term prediction of other participants restrict freedom in action. In this paper, we process both problems of long-term planning and prediction at the same time. Our approach which we call DDT (Deep Driving Tree) is based on game tree accumulating a short-term prediction. Machine learning techniques are applied to this short-term prediction instead of model-based techniques that depends on domain knowledge. In contrast to Q-learning, this prediction part is trained off-line and does not require feedback from collision data. Our approach using a game tree models multiple future states of other participants to decide a proactive action taking uncertainties of their intentions into consideration. This approach is demonstrated in a left turning scenario at an intersection of left-hand traffic with oncoming vehicles without V2V communication.

Integration of renewable energy sources (RESs) into power systems has been a popular topic for a long time. Due to government policies and incentives, it will be more popular in the future since it is a free and environment-friendly nature. Besides its advantages, photovoltaic (PV) generation causes some serious problems to the grid. Since PV generation directly depends on the solar irradiance, cloud movements can cause sudden changes on the output of PV power and this results in some power issues in the system such as voltage violations, reverse power flow, voltage fluctuations. These types of issues complicate to maintain voltage within compulsory levels at customer sides. Thus, cloud-induced transients in PV power are seen as a potential handicap for the future expansion of renewable energy resources. This study investigates effects of instantaneous changes in PV power on the customer side voltage levels. Daily PV power output and voltage profiles were simulated using a real-world microgrid design that will be implemented in the Malta College of Arts Science and Technology (MCAST) Campus.

We demonstrate an environmental control system for testing Resistive Random Access Memory technologies under accurately controlled humidity and temperature. The demonstrated system compresses the functionality of existing environmental control systems into a low cost, desktop-size solution, aimed at providing results quickly and with minimum installation and running overheads.

A 12-pulse HVDC (High Voltage direct current) system is modelled and studied in this paper based on real time simulation using RT-lab platform Hypersim OP-5600. AC fault represent the most common unsymmetrical fault in the power systems. Therefore, understanding the HVDC system fault behavior is very important for modelling, design and validation of the control system. The HVDC inverter is connected to a weak AC system and a single phase to ground AC fault is applied to the inverter bus in the goal to test the influence of the DC control on the recovery from commutation failure in front of two different values of time rising of the mechanism addressed to maintain stability, to ensure a good recovery from the fault and also inhibiting the commutation failures at the HVDC inverter valves. The results are validated by mean of digital Real time simulator HYPERSIM (OP-5600) using the Simulation In the Loop SIL approach. The performance of the HVDC system is investigated and shows the DC control influence to maintain a good and a safe stability of the system during and after the perturbation.

2018 International Conference on Smart Energy Systems and Technologies (SEST) Ancillary services are all services required by the transmission (TSO) or distribution system operator (DSO) to maintain the integrity and stability of the transmission or distribution system as well as the power quality. Ancillary services that can be provided by a microgrid in grid-connected operation are frequency control support, voltage control support, congestion management, reduction of grid losses, and improvement of power quality. This paper presents the optimization problems used in the 3DMicroGrid project to determine the set-points of the different resources present in the microgrid to provide ancillary services to the power system in grid-connected operation: frequency control, voltage control and load curtailment. Results of the optimization of the pilot microgrid used in 3DMicroGrid are presented.

With the recent advances of the emerging memories technologies, research are able to implement novel circuits, systems and computer architectures towards the design of high-performance and low-power electronic systems able to accelerate and/or optimize the functionality of many computer workflows. One emerging technology, the ReRAM/memristor is gathering attention due to its inherent advantages for logic and memory computing systems. At the same time, CMOS circuit design seems to have reached a limit, where easily optimized circuit solutions cannot be found. Thus, further research towards novel logic gate families, such as Threshold Logic Gates (TLGs), a logic family known for its high-speed and low power consumption, is needed. Although many implementation concepts of TLG circuit are using memristors, few of these implementations are based on physical ReRAM devices. In this work we are proposing a memristor-based threshold logic gate design towards the optimization of computer workflows. The presented results include a physical implementation of the proposed circuits which supports the concept of memory-based reconfigurable computing circuits and systems.

Environmental conditions can greatly affect the performance of semiconductor devices. Great sophistication has thus gone into developing versatile systems that allow benchmarking of operating characteristics under a variety of temperature and humidity conditions. Recently, Resistive Random Access Memory (RRAM) technologies, also known as memristors, have received a lot of attention for memory and computing applications. This interest is showcased by several reports on technology and applications developments, as well as developments on the underpinning infrastructure, i.e. models and characterization tools, that renders such technologies useful. Several international research groups and companies are nowadays using ArC OneTM, a versatile instrument that allows en masse characterization of RRAM technologies, as has been presented previously in several demo sessions at ISCAS. In this work, we present a newly developed module that expands ArC OneTM capabilities through incorporating an environmental control system. The proposed module condenses the functionality of significantly larger, more complex and higher cost systems into a low cost, small form-factor and user friendly desktop-operated device. The system allows for temperature, atmospheric composition and humidity control and can be used for studying the impact of such settings on the electrical characteristics of RRAM technologies.

In this work we present an evaluation routine aimed towards assessing the multibit capability of Resistive Random Access Memory (RRAM) technologies. We illustrate a characterization methodology for the maximum possible exploitation of the resistive states of a RRAM cell. Our characterization routine consists of a three phase algorithm: during the first it infers the polarity needed to induce a change in the device's conductance; the second stabilizes the resistive states of the device into a baseline resistance and during the third a sequence of pulses of increasing amplitude is used to determine the actual resistive states. This technology-agnostic methodology allows for efficient and high resolution partitioning of the cell's resistive operating range allowing them to operate in a truly analogue fashion. Demonstrating the maximum potential of RRAM cells in terms of closely packed resistive states can open new avenues for research in non-volatile memories, reconfigurable electronics and neuromorphic applications.

Once a company is located on several sites, the communication between these sites would be critical for its activity, regardless of its size. VPN technology allows the connection between these different sites, while giving the user the benefit of the security. New Generation VPN technologies allow to create multiple virtual tunnels between various devices in a fast, automatic and dynamic manner. However, existing technologies represent limitations of reliability, which means, the security policy deployed in a domain or a cloud, will be applied on all sorts of traffic whatever its type. This paper proposes a new model of adaptive security that we have called Smart Security Management for New Generation VPN. This model allows to generate security policies in an automatic, intelligent and adapted way to the performances of the transported applications and the network status. That is, if the network is overloaded and the flow to be transported is of real-time type, then generate a policy of medium, low security level or even not secure if the organization allows it in the contract.

In this work, we present a parameter extraction method for TiO2 memristive devices that applies on a resistive switching rate model which embodies only four parameters for each voltage biasing polarity. The simple form of the model functions allows the derivation of a predictive analytical resistive state response expression under constant bias voltage. By employing corresponding experimental testing on the devices, we fit such constant bias responses exhibited by physical memristor samples on this analytical expression. Next, we apply a simple algorithm that extracts the suitable model parameters that capture the switching rate behavior of the characterized device in its voltage range of operation.

The world currently has a strong trend towards homogeneous wireless networks, thanks to the mobility service that they offer, unlike wired networks. However, in homogeneous wireless networks several limits are required, like the transition from one network to another. This transition was often accompanied by a short connection failure due to the change of IPv4 addresses. However, in the presence of real-time applications, this network change delay is not accepted. The MIPv6 solution mitigates this deficiency by maintaining the same IPv6 address when moving from one network to another. In this paper, we will study MIPv6, and we will evaluate the Voice over IP (VOIP) performance with its two SIP and H.323 architectures. The study will be performed in a homogeneous 802.11e network in the context of a horizontal handover taking into account the MIPv6 technology. The evaluation criteria are: the call set-up time, the end-to-end delay, the loss rate and the jitter.

The sensitivity of a recently proposed spike detector exploiting the volatile properties of memristive device is optimised. A 200 nm × 200 nm TiOx memristive device in volatile region is biased with sub-threshold, unipolar and bipolar neural events. The input neural signal is pre-processed using different amplification settings. The resistive state response of the test device in response to the input events is analysed and it is found that inclusion of events in positive polarity leads to subsequent increase in the number of false events when benchmarked against state-of-the-art spike detector (template matching system). The performance of the system is thereafter optimised by determining optimum amplification settings and employing an offset such that positive polarity events in the input signal are minimised.

We demonstrate a desktop platform which has the ability of modeling ReRAM TiO2 samples in a highly automated manner. The system consists of a bespoke RRAM characterization instrument that hosts packaged RRAM devices and is operated via a PC. The system's python-based software includes a module that automatically applies strategically chosen sequences of pulses to a test device and then extracts the suitable parameter values for a resistive switching model from the elicited response.