Anis Koubaa
Instituto Politecnico do Porto, Cs, Department Member
Research Interests:
Research Interests:
Research Interests:
This paper presents a viable solution for the development of service robots by leveraging cloud and Web services technologies, modular software architecture design, and Robot Operating System (ROS). The contributions of this paper are... more
This paper presents a viable solution for the development of service robots by leveraging cloud and Web services technologies, modular software architecture design, and Robot Operating System (ROS). The contributions of this paper are twofolded (1) Design of ROS Web services to provide new abstract interfaces to service robots that makes easier the interaction with and the development of service robots applications, and (2) Integration of the service robot to the cloud using the ROSLink protocol. We demonstrate through real-world implementation on the MyBot robot the effectiveness of these software abstraction layers in developing applications for service robots through the Internet and the cloud, and in accessing them through Internet. We believe that this work represents an important step towards a more popular use of service robots.
Research Interests: Engineering and ROBOTICA
The COVID-19 disease has spread all over the world, representing an intriguing challenge for humanity as a whole. The efficient diagnosis of humans infected by COVID-19 still remains an increasing need worldwide. The chest X-ray imagery... more
The COVID-19 disease has spread all over the world, representing an intriguing challenge for humanity as a whole. The efficient diagnosis of humans infected by COVID-19 still remains an increasing need worldwide. The chest X-ray imagery represents, among others, one attractive means to detect COVID-19 cases efficiently. Many studies have reported the efficiency of using deep learning classifiers in diagnosing COVID-19 from chest X-ray images. They conducted several comparisons among a subset of classifiers to identify the most accurate. In this paper, we investigate the potential of the combination of state-of-the-art classifiers in achieving the highest possible accuracy for the detection of COVID-19 from X-ray. For this purpose, we conducted a comprehensive comparison study among 16 state-of-the-art classifiers. To the best of our knowledge, this is the first study considering this number of classifiers. This paper’s innovation lies in the methodology that we followed to develop t...
Research Interests:
Research Interests:
Unmanned Aerial Vehicles (UAVs) have been very effective in collecting aerial images data for various Internet-of-Things (IoT)/smart cities applications such as search and rescue, surveillance, vehicle detection, counting, intelligent... more
Unmanned Aerial Vehicles (UAVs) have been very effective in collecting aerial images data for various Internet-of-Things (IoT)/smart cities applications such as search and rescue, surveillance, vehicle detection, counting, intelligent transportation systems, to name a few. However, the real-time processing of collected data on edge in the context of the Internet-of-Drones remains an open challenge because UAVs have limited energy capabilities, while computer vision techniquesconsume excessive energy and require abundant resources. This fact is even more critical when deep learning algorithms, such as convolutional neural networks (CNNs), are used for classification and detection. In this paper, we first propose a system architecture of computation offloading for Internet-connected drones. Then, we conduct a comprehensive experimental study to evaluate the performance in terms of energy, bandwidth, and delay of the cloud computation offloading approach versus the edge computing appro...
Research Interests:
Smart agriculture is an evolving trend in the agriculture industry, where sensors are embedded into plants to collect vital data and help in decision-making to ensure a higher quality of crops and prevent pests, disease, and other... more
Smart agriculture is an evolving trend in the agriculture industry, where sensors are embedded into plants to collect vital data and help in decision-making to ensure a higher quality of crops and prevent pests, disease, and other possible threats. One of the most critical pests of palms is the red palm weevil, which is an insect that causes much damage to palm trees and can devastate vast areas of palm trees. The most challenging problem is that the effect of the weevil is not visible by humans until the palm reaches an advanced infestation state. For this reason, there is a pressing need to use advanced technology for early detection and prevention of infestation propagation. In this project, we have developed an IoT-based smart palm monitoring prototype as a proof-of-concept that (1) allows monitoring palms remotely using smart agriculture sensors, (2) contribute to the early detection of red palm weevil infestation. Users can use web/mobile applications to interact with their pa...
Research Interests:
Wearable technology plays a key role in smart healthcare applications. Detection and analysis of the physiological data from wearable devices is an essential process in smart healthcare. Physiological data analysis is performed in fog... more
Wearable technology plays a key role in smart healthcare applications. Detection and analysis of the physiological data from wearable devices is an essential process in smart healthcare. Physiological data analysis is performed in fog computing to abridge the excess latency introduced by cloud computing. However, the latency for the emergency health status and overloading in fog environment becomes key challenges for smart healthcare. This paper resolves these problems by presenting a novel tri-fog health architecture for physiological parameter detection. The overall system is built upon three layers as wearable layer, intelligent fog layer, and cloud layer. In the first layer, data from the wearable of patients are subjected to fault detection at personal data assistant (PDA). To eliminate fault data, we present the rapid kernel principal component analysis (RK-PCA) algorithm. Then, the faultless data is validated, whether it is duplicate or not, by the data on-looker node in the ...
Research Interests: Psychology, Psychoanalysis, Health Psychology, Artificial Intelligence, Medical Sciences, and 15 moreMachine Learning, Wearable Computing, Medical Education, Electronics, The Internet of Things, Wearable Technologies, Internet of Things, Medical and Research ethics, Deep Learning, Wearable Technology, Internet of Things (IoT), Fog Computing, Coronavirus COVID-19, CoVid, and COVID-19 PANDEMIC
Acute lymphoblastic leukemia is a well-known type of pediatric cancer that affects the blood and bone marrow. If left untreated, it ends in fatal conditions due to its proliferation into the circulation system and other indispensable... more
Acute lymphoblastic leukemia is a well-known type of pediatric cancer that affects the blood and bone marrow. If left untreated, it ends in fatal conditions due to its proliferation into the circulation system and other indispensable organs. All over the world, leukemia primarily attacks youngsters and grown-ups. The early diagnosis of leukemia is essential for the recovery of patients, particularly in the case of children. Computational tools for medical image analysis, therefore, have significant use and become the focus of research in medical image processing. The particle swarm optimization algorithm (PSO) is employed to segment the nucleus in the leukemia image. The texture, shape, and color features are extracted from the nucleus. In this article, an improved dominance soft set-based decision rules with pruning (IDSSDRP) algorithm is proposed to predict the blast and non-blast cells of leukemia. This approach proceeds with three distinct phases: (i) improved dominance soft set...
Research Interests:
Despite the significant advances noted in semantic segmentation of aerial imagery, a considerable limitation is blocking its adoption in real cases. If we test a segmentation model on a new area that is not included in its initial... more
Despite the significant advances noted in semantic segmentation of aerial imagery, a considerable limitation is blocking its adoption in real cases. If we test a segmentation model on a new area that is not included in its initial training set, accuracy will decrease remarkably. This is caused by the domain shift between the new targeted domain and the source domain used to train the model. In this paper, we addressed this challenge and proposed a new algorithm that uses Generative Adversarial Networks (GAN) architecture to minimize the domain shift and increase the ability of the model to work on new targeted domains. The proposed GAN architecture contains two GAN networks. The first GAN network converts the chosen image from the target domain into a semantic label. The second GAN network converts this generated semantic label into an image that belongs to the source domain but conserves the semantic map of the target image. This resulting image will be used by the semantic segment...
Research Interests:
The combination of wireless sensor networks (WSNs) and 3D virtual environments opens a new paradigm for their use in natural disaster management applications. It is important to have a realistic virtual environment based on datasets... more
The combination of wireless sensor networks (WSNs) and 3D virtual environments opens a new paradigm for their use in natural disaster management applications. It is important to have a realistic virtual environment based on datasets received from WSNs to prepare a backup rescue scenario with an acceptable response time. This paper describes a complete cloud-based system that collects data from wireless sensor nodes deployed in real environments and then builds a 3D environment in near real-time to reflect the incident detected by sensors (fire, gas leaking, etc.). The system’s purpose is to be used as a training environment for a rescue team to develop various rescue plans before they are applied in real emergency situations. The proposed cloud architecture combines 3D data streaming and sensor data collection to build an efficient network infrastructure that meets the strict network latency requirements for 3D mobile disaster applications. As compared to other existing systems, the...
Segmenting aerial images is of great potential in surveillance and scene understanding of urban areas. It provides a mean for automatic reporting of the different events that happen in inhabited areas. This remarkably promotes public... more
Segmenting aerial images is of great potential in surveillance and scene understanding of urban areas. It provides a mean for automatic reporting of the different events that happen in inhabited areas. This remarkably promotes public safety and traffic management applications. After the wide adoption of convolutional neural networks methods, the accuracy of semantic segmentation algorithms could easily surpass 80% if a robust dataset is provided. Despite this success, the deployment of a pretrained segmentation model to survey a new city that is not included in the training set significantly decreases accuracy. This is due to the domain shift between the source dataset on which the model is trained and the new target domain of the new city images. In this paper, we address this issue and consider the challenge of domain adaptation in semantic segmentation of aerial images. We designed an algorithm that reduces the domain shift impact using generative adversarial networks (GANs). In ...
Research Interests:
Energy efficiency in a data center is a challenge and has garnered researchers interest. In this study, we addressed the energy efficiency issue of a small scale data center by utilizing Single Board Computer (SBC)-based clusters. A... more
Energy efficiency in a data center is a challenge and has garnered researchers interest. In this study, we addressed the energy efficiency issue of a small scale data center by utilizing Single Board Computer (SBC)-based clusters. A compact layout was designed to build two clusters using 20 nodes each. Extensive testing was carried out to analyze the performance of these clusters using popular performance benchmarks for task execution time, memory/storage utilization, network throughput and energy consumption. Further, we investigated the cost of operating SBC-based clusters by correlating energy utilization for the execution time of various benchmarks using workloads of different sizes. Results show that, although the low-cost benefit of a cluster built with ARM-based SBCs is desirable, these clusters yield low comparable performance and energy efficiency due to limited onboard capabilities. It is possible to tweak Hadoop configuration parameters for an ARM-based SBC cluster to eff...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Abstract في الآونة الأخيرة، يشهد مفهوم الحوسبة والمعلومات في مجال علوم الحاسب تغيرات جذرية من معلومات مبنية على بيانات رقمية تقليدية إلى معلومات حول البيئة المادية المحيطة بالإنسان والأحداث الفيزيائية كنتيجة لتطور تقنيات الاتصال والنظم... more
Abstract في الآونة الأخيرة، يشهد مفهوم الحوسبة والمعلومات في مجال علوم الحاسب تغيرات جذرية من معلومات مبنية على بيانات رقمية تقليدية إلى معلومات حول البيئة المادية المحيطة بالإنسان والأحداث الفيزيائية كنتيجة لتطور تقنيات الاتصال والنظم المدمجة. ويأتي هذا التغير لمفهوم ...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Although there exist efficient methods to determine an optimal path in a graph, such as Dijkstra and A* algorithms, large instances of the path planning problem need more adequate and efficient techniques to obtain solutions in reasonable... more
Although there exist efficient methods to determine an optimal path in a graph, such as Dijkstra and A* algorithms, large instances of the path planning problem need more adequate and efficient techniques to obtain solutions in reasonable time. We propose two new time-linear relaxed versions of Dijkstra (RD) and A* (RA*) algorithms to solve the global path planning problem in large grid environments. The core idea consists in exploiting the grid-map structure to establish an accurate approximation of the optimal path, without visiting any cell more than once. We conducted extensive simulations (1290 runs on 43 maps of various types) for the proposed algorithms, both in four-neighbor and eight-neighbor grid environments, and compared them against original Dijkstra and A* algorithms with different heuristics. We demonstrate that our relaxed versions exhibit a substantial gain in terms of computational time (more than 3 times faster in average), and in most of tested problems an optimal solution (in at least 97 % of cases for RD and 82 % for RA*) or a very close one is reached (at most 9 % of extra length, and less than 2 % in average). Besides, the simulations also show that RA* provides a better trade-off between solution quality and execution time than previous bounded relaxations of A* that exist in the literature.
Research Interests:
ABSTRACT The Internet of Things (IoT) has emerged as a paradigm over the last few years as a result of the tight integration of the computing and the physical world. The requirement of remote sensing makes low-power wireless sensor... more
ABSTRACT The Internet of Things (IoT) has emerged as a paradigm over the last few years as a result of the tight integration of the computing and the physical world. The requirement of remote sensing makes low-power wireless sensor networks one of the key enabling technologies of IoT. These networks encompass several challenges, especially in communication and networking, due to their inherent constraints of low-power features, deployment in harsh and lossy environments, and limited computing and storage resources. The IPv6 Routing Protocol for Low Power and Lossy Networks (RPL) [1] was proposed by the IETF ROLL (Routing Over Low-power Lossy links) working group and is currently adopted as an IETF standard in the RFC 6550 since March 2012. Although RPL greatly satisfied the requirements of low-power and lossy sensor networks, several issues remain open for improvement and specification, in particular with respect to Quality of Service (QoS) guarantees and support for mobility.
Research Interests:
We consider the problem of link quality estimation in wireless sensor networks. Existing link quality estimators (e.g. PRR, ETX, Four-bit, and LQI) are only able to assess a single link property, thus providing a partial view on the link... more
We consider the problem of link quality estimation in wireless sensor networks. Existing link quality estimators (e.g. PRR, ETX, Four-bit, and LQI) are only able to assess a single link property, thus providing a partial view on the link quality. It is therefore important, yet challenging, to design link quality estimators that perform holistic link characterization by considering several properties. In this poster, we propose F-LQE, a novel link quality estimator, that estimates link quality on the basis of four link quality prop-erties namely, packet delivery, asymmetry, stability, and channel quality. Combination of link properties is performed using Fuzzy Logic. We show through extensive TOSSIM simulation that F-LQE outperforms existing link quality estimators.
Research Interests:
ABSTRACT Radio link quality estimation is essential for protocols and mechanisms such as routing, mobility management and localization, particularly for low-power wireless networks such as wireless sensor networks. Commodity Link Quality... more
ABSTRACT Radio link quality estimation is essential for protocols and mechanisms such as routing, mobility management and localization, particularly for low-power wireless networks such as wireless sensor networks. Commodity Link Quality Estimators (LQEs), e.g. PRR, RNP, ETX, four-bit and RSSI, can only provide a partial characterization of links as they ignore several link properties such as channel quality and stability. In this paper, we propose F-LQE (Fuzzy Link Quality Estimator, a holistic metric that estimates link quality on the basis of four link quality properties—packet delivery, asymmetry, stability, and channel quality—that are expressed and combined using Fuzzy Logic. We demonstrate through an extensive experimental analysis that F-LQE is more reliable than existing estimators (e.g., PRR, WMEWMA, ETX, RNP, and four-bit) as it provides a finer grain link classification. It is also more stable as it has lower coefficient of variation of link estimates. Importantly, we evaluate the impact of F-LQE on the performance of tree routing, specifically the CTP (Collection Tree Protocol). For this purpose, we adapted F-LQE to build a new routing metric for CTP, which we dubbed as F-LQE/RM. Extensive experimental results obtained with state-of-the-art widely used test-beds show that F-LQE/RM improves significantly CTP routing performance over four-bit (the default LQE of CTP) and ETX (another popular LQE). F-LQE/RM improves the end-to-end packet delivery by up to 16%, reduces the number of packet retransmissions by up to 32%, reduces the Hop count by up to 4%, and improves the topology stability by up to 47%.
Research Interests:
ABSTRACT This paper investigates the capabilities of tabu search for solving the global path planning problem in grid maps. Accordingly, a tabu search system model is designed and a tabu search planner algorithm for solving the path... more
ABSTRACT This paper investigates the capabilities of tabu search for solving the global path planning problem in grid maps. Accordingly, a tabu search system model is designed and a tabu search planner algorithm for solving the path planning problem is proposed. A comprehensive simulation study is conducted using the proposed model and algorithm, in terms of solution quality and execution time. A comparison between our results with those of A* and genetic algorithms (GA) is presented for small, medium and large-scale grid maps. Simulation results show that the tabu search planner is able to find the optimal solution for small scale environments. However, for large scale maps, it provides near-optimal solutions with small gap while ensuring shorter execution times as compared to the A* Algorithm. A discussion about the advantages and limitations of TS for solving a path planning problem is also presented.
Research Interests:
Research Interests:
AbstractMonitoring of Wireless Sensor Networks (WSNs) is a fundamental task to track the network behavior and measure its performance in real-world deployments. In this paper, we present Z-Monitor, a monitoring and a protocol ana-lyzer... more
AbstractMonitoring of Wireless Sensor Networks (WSNs) is a fundamental task to track the network behavior and measure its performance in real-world deployments. In this paper, we present Z-Monitor, a monitoring and a protocol ana-lyzer solution to control and debug ...
Research Interests:
ABSTRACT Low power and lossy networks (LLNs) require efficient routing protocols that should meet the requirements of the critical applications, such as real-time, reliability and high availability. RPL has been recently proposed by the... more
ABSTRACT Low power and lossy networks (LLNs) require efficient routing protocols that should meet the requirements of the critical applications, such as real-time, reliability and high availability. RPL has been recently proposed by the ROLL working group as a tree routing protocol specifically designed for LLNs. It relies on objective functions to construct routes that optimize or constrain a routing metric on the paths. However, the working group did not specify the set of metrics and/or constraints to be used to specify the preferred path, and left it open to implementations. In this paper, we design OF-FL, a novel objective function that combines a set of metrics in order to provide a configurable routing decision based on the fuzzy parameters. OF-FL has the advantage to consider the application requirements in order to select the best paths to the destination. Our evaluation with a large-scale testbed in ContikiOS reveals that OF-FL can achieve remarkable performance of the RPL-based LLNs in comparison with the existing objective functions, and appropriately satisfy the quality of service contract of the different applications.