ISEP – CISTER – Comunicações em eventos científicos
Permanent URI for this collection
Browse
Browsing ISEP – CISTER – Comunicações em eventos científicos by Title
Now showing 1 - 10 of 317
Results Per Page
Sort Options
- Abstract Timers and their Implementation onto the ARM Cor tex-M family of MCUsPublication . Lindgren, Per; Fresk, Emil; Lindner, Marcus; Lindner, Andreas; Pereira, David; Pinho, Luís MiguelReal-Time For the Masses (RTFM) is a set of languages andto ols b eing develop ed to facilitate emb edded software development and provide highly efficient implementations gearedto static verification. The RTFM-kernel is an architecturedesigned to provide highly efficient and predicable Stack Resource Policy based scheduling, targeting bare metal (singlecore) platforms.We contribute b eyond prior work by intro ducing a platform independent timer abstraction that relies on existingRTFM-kernel primitives. We develop two alternative implementations for the ARM Cortex-M family of MCUs: ageneric implementation, using the ARM defined SysTick-/DWT hardware; and a target sp ecific implementation, using the match compare/free running timers. While sacrificing generality, the latter is more flexible and may reduceoverall overhead. Invariants for correctness are presented,and metho ds to static and run-time verification are discussed. Overhead is b ound and characterized. In b oth casesthe critical section from release time to dispatch is less than2us on a 100MHz MCU. Queue and timer mechanisms aredirectly implemented in the RTFM-core language and canb e included in system-wide scheduling analysis.
- Active Flow Control for Aerospace Operations by means of a Dense Wireless Sensor and Actuator NetworkPublication . Robles, Ramiro; Loureiro, João; Tovar, Eduardo; Viana, Júlio; Cintra, João; Rocha, AndréThis paper presents the design of an active flow control (AFC) system for commercial aircraft based on a dense wired/wireless sensor and actuator network. The goal is to track gradients of pressure across the surface of the fuselage of commercial aircraft. This collected information will be used to activate a set of actuators that will attempt to reduce the skin drag effect produced by the separation between laminar and turbulent flows. This will be translated into increased lift-off forces, higher speeds, longer ranges and reduced fuel consumption. The paper describes the architecture of the system in the context of the European research project DEWI (dependable embedded wireless infrastructure) using the concept of the DEWI Bubble. A simulator architecture is also proposed to model each process of the AFC system and the DEWI Bubble. To the best of our knowledge this is the first approach towards the use of wireless sensor technologies in the field of active flow control.
- Activity Monitoring of Islamic Prayer (Salat) Postures using Deep LearningPublication . Koubaa, Anis; Ammar, Adel; Benjdira, Bilel; Al Hadid, Abdullatif; Kawaf, Belal; Al Yahri, Saleh Ali; Babiker, Abdelrahman; Assaf, Koutaiba; Ba Ras, MohannadIn the Muslim community, the prayer (i.e. Salat) is the second pillar of Islam, and it is the most essential and fundamental worshiping activity that believers have to perform five times a day. From a gestures' perspective, there are predefined human postures that must be performed in a precise manner. However, for several people, these postures are not correctly performed, due to being new to Salat or even having learned prayers in an incorrect manner. Furthermore, the time spent in each posture has to be balanced. To address these issues, we propose to develop an artificial intelligence assistive framework that guides worshippers to evaluate the correctness of the postures of their prayers. This paper represents the first step to achieve this objective and addresses the problem of the recognition of the basic gestures of Islamic prayer using Convolutional Neural Networks (CNN). The contribution of this paper lies in building a dataset for the basic Salat positions, and train a YOLOv3 neural network for the recognition of the gestures. Experimental results demonstrate that the mean average precision attains 85% for a training dataset of 764 images of the different postures. To the best of our knowledge, this is the first work that addresses human activity recognition of Salat using deep learning.
- AdaptC: programming adaptation policies for WSN applicationsPublication . Gaur, Shashank; Almeida, Luis; Tovar, EduardoEvolution in both hardware and software technologies has enabled Wireless Sensor Networks(WSNs) to target a multiplicity of domains. Programming for such advanced WSNs remains a challenging process for users, especially as the WSN may need to make changes as per outcomes from different scenarios during execution. Usually, various adaptation policies are written while programming such applications to enable changes. However it is difficult for the programmer to anticipate changes for new scenarios. It also becomes difficult to reuse these adaptation policies. In this paper, we propose AdaptC, an abstraction for such adaptation policies that facilitates re-usability and expansion across various WSNs. We also present concepts for the design and implementation of AdaptC. We evaluate the abstraction for multiple use cases and compare it against existing work.
- Adaptive Terminal-Integral Sliding Mode Force Control of Elastic Joint Robot Manipulators in the Presence of HysteresisPublication . Taher Azar, Ahmad; Serrano, Fernando E.; Koubaa, Anis; Ahmad Kamal, Nashwa; Vaidyanathan, Sundarapandian; Fekik, ArezkiIn this paper, an adaptive terminal-integral sliding mode force control of elastic joint robot manipulators in the presence of hysteresis is proposed. One of the most important issues that is solved in this study is that the hysteresis phenomenon is considered something that provokes losses in the manipulator motion and controller errors. Force control is necessary because it can be implemented and very useful in the area of industrial robotics such as collaborative and cooperative robotics. Therefore, it can be implemented for precise control in which robot-operator or robot-robot interaction is needed. An adaptive terminal-integral sliding mode force control is proposed by considering the hysteresis and the effects between the end effector and a flexible environment. Force control has not been studied extensively nowadays and even less for elastic joint robot manipulators. Thus, to improve the system precision control, the adaptive sliding mode controller (ASMC) is designed by a Lyapunov approach obtaining the adaptive and controller laws, respectively. As an experimental case study, two links elastic joint robot manipulator is considered by obtaining the elastic joint model with hysteresis using a Bouc-Wen model.
- Adding local priority-based dispatching mechanisms to P-NET networks: a fixed priority approachPublication . Tovar, Eduardo; Vasques, Francisco; Burns, AlanIn this paper we address the real-time capabilities of P-NET, which is a multi-master fieldbus standard based on a virtual token passing scheme. We show how P-NET’s medium access control (MAC) protocol is able to guarantee a bounded access time to message requests. We then propose a model for implementing fixed prioritybased dispatching mechanisms at each master’s application level. In this way, we diminish the impact of the first-come-first-served (FCFS) policy that P-NET uses at the data link layer. The proposed model rises several issues well known within the real-time systems community: message release jitter; pre-run-time schedulability analysis in non pre-emptive contexts; non-independence of tasks at the application level. We identify these issues in the proposed model and show how results available for priority-based task dispatching can be adapted to encompass priority-based message dispatching in P-NET networks.
- Adding Quality in the User Requirements Specification A first approachPublication . Guerra-García, César; Caballero, Ismael; Cardenas-Juarez, Marco; Robles, RamiroUsers need trusting in data managed by software applications that are part of Information Systems (IS), which supposes that organizations should assuring adequate levels of quality in data that are managed in their IS. Therefore, the fact that an IS can manage data with an adequate level of quality should be a basic requirement for all organizations. In order to reach this basic requirement some aspects and elements related with data quality (DQ) should be taken in account from the earliest stages of development of software applications, i.e. “data quality by design”. Since DQ is considered a multidimensional and largely context-dependent concept, managing all specific requirements is a complex task. The main goal of this paper is to introduce a specific methodology, which is aimed to identifying and eliciting DQ requirements coming from different viewpoints of users. These specific requirements will be used as normal requirements (both functional and non-functional) during the development of IS awareness of data quality.
- AI-based Pilgrim Detection using Convolutional Neural NetworksPublication . Jabra, Marwa Ben; Ammar, Adel; Koubaa, Anis; Cheikhrouhou, Omar; Hamam, HabibPilgrimage represents the most important Islamic religious gathering in the world where millions of pilgrims visit the holy places of Makkah and Madinah to perform their rituals. The safety and security of pilgrims is the highest priority for the authorities. In Makkah, 5000 cameras are spread around the holy mosques for monitoring pilgrims, but it is almost impossible to track all events by humans considering the huge number of images collected every second. To address this issue, we propose to use an artificial intelligence technique based on deep learning and convolutional neural networks to detect and identify Pilgrims and their features. For this purpose, we built a comprehensive dataset for the detection of pilgrims and their genders. Then, we develop two convolutional neural networks based on YOLOv3 and Faster-RCNN for the detection of Pilgrims. Experiment results show that Faster RCNN with Inception v2 feature extractor provides the best mean average precision over all classes (51%). A video demonstration that illustrates a real-time pilgrim detection using our proposed model is available at [1].
- Allocation of Parallel Real-Time Tasks in Distributed Multi-core Architectures supported by an FTT-SE NetworkPublication . Martínez, Ricardo Garibay; Nelissen, Geoffrey; Ferreira, Luís Lino; Pinho, Luís MiguelDistributed real-time systems such as automotive applications are becoming larger and more complex, thus, requiring the use of more powerful hardware and software architectures. Furthermore, those distributed applications commonly have stringent real-time constraints. This implies that such applications would gain in flexibility if they were parallelized and distributed over the system. In this paper, we consider the problem of allocating fixed-priority fork-join Parallel/Distributed real-time tasks onto distributed multi-core nodes connected through a Flexible Time Triggered Switched Ethernet network. We analyze the system requirements and present a set of formulations based on a constraint programming approach. Constraint programming allows us to express the relations between variables in the form of constraints. Our approach is guaranteed to find a feasible solution, if one exists, in contrast to other approaches based on heuristics. Furthermore, approaches based on constraint programming have shown to obtain solutions for these type of formulations in reasonable time.
- An analysis of the impact of bus contention on the WCET in multicoresPublication . Dasari, Dakshina; Nélis, VincentThe use of multicores is becoming widespread inthe field of embedded systems, many of which have real-time requirements. Hence, ensuring that real-time applications meet their timing constraints is a pre-requisite before deploying them on these systems. This necessitates the consideration of the impact of the contention due to shared lowlevel hardware resources like the front-side bus (FSB) on the Worst-CaseExecution Time (WCET) of the tasks. Towards this aim, this paper proposes a method to determine an upper bound on the number of bus requests that tasks executing on a core can generate in a given time interval. We show that our method yields tighter upper bounds in comparison with the state of-the-art. We then apply our method to compute the extra contention delay incurred by tasks, when they are co-scheduled on different cores and access the shared main memory, using a shared bus, access to which is granted using a round-robin arbitration (RR) protocol.