Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Faraz Malik Awan has a total of 7 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Towards synthetic sensing for smart cities : a machine/deep learning-based approach

    by Faraz Malik Awan

    Vers une détection synthétique pour les villes intelligentes : une approche basée sur la machine et l'apprentissage profond: Nous avons travaillé sur l'un des axes de recherche les plus importants de la ville intelligente, à savoir les systèmes de transport intelligents (STI). Les ITS englobent plusieurs domaines, tels que les systèmes de notification électronique des véhicules, les informations sur le trafic, le stationnement intelligent et l'environnement. Cependant, dans cette thèse, nous ciblons deux de ses domaines importants : i) le stationnement intelligent et ii) le trafic routier. Nous avons commencé notre recherche par le cas d'utilisation du stationnement intelligent. En effectuant une revue de la littérature, nous avons réalisé que différentes approches de Machine Learning (ML) et de Deep Learning (DL) ont été utilisées pour des solutions de stationnement intelligent. Dans la plupart de ces approches proposées, les zones de stationnement fermées ont été ciblées avec différents ensembles de caractéristiques pour prédire le "taux d'occupation" dans les zones de stationnement. Cela nous a incités à effectuer une analyse comparative pour répondre aux questions suivantes : compte tenu du cas d'utilisation de la prédiction de stationnement, comment les modèles ML traditionnels se comportent-ils par rapport aux modèles DL complexes ? Avec des données volumineuses, les modèles ML traditionnels moins complexes peuvent-ils surpasser les modèles DL complexes ? Quelle est la performance de ces modèles pour prédire la disponibilité des places de stationnement individuelles dans la rue plutôt que de prédire le taux d'occupation global d'une zone de stationnement fermée. Pour répondre à ces questions, nous avons choisi cinq algorithmes ML classiques bien connus (K-Nearest Neighbours, Random Forest, Decision Tree) et un algorithme DL (Multilayer Perceptron). Pour approfondir notre étude, nous formons un modèle d'apprentissage d'ensemble, dans lequel nous combinons tous les modèles ML et DL susmentionnés. Nous avons utilisé un énorme ensemble de données sur les pa rkings de la ville de Santander, en Espagne, qui comprend environ 25 millions d'enregistrements. Nous proposons également de recommander des places de stationnement disponibles en fonction de l'emplacement actuel du conducteur. En poursuivant nos objectifs de recherche, nous avons effectué une revue de la littérature sur le trafic routier et avons constaté que le trafic routier est souvent associé à la pollution atmosphérique et à la pollution sonore. Cependant, à notre connaissance, la pollution atmosphérique et la pollution sonore n'ont jamais été utilisées dans le problème de la prédiction du trafic. Dans cette partie de notre recherche, nous avons d'abord utilisé la pollution de l'air (CO, NO, NO2, NOx, et O3) avec les variables atmosphériques, telles que la vitesse et la direction du vent, la température et la pression pour améliorer la prévision du trafic dans la ville de Madrid. Cette expérience réussie nous a incités à étendre notre étude à un autre facteur, qui est égalemen t fortement corrélé au trafic routier, à savoir la pollution sonore. Ainsi, dans le prolongement de nos travaux précédents, nous utilisons dans cette partie de notre recherche la pollution sonore pour améliorer la prévision du trafic dans la ville de Madrid.

  • Using Noise Pollution Data for Traffic Prediction in Smart Cities: Experiments Based on LSTM Recurrent Neural Networks

    by Faraz Malik Awan, Roberto Minerva, Noel Crespi

    Traffic prediction is one of the most important use cases for smart cities. Accurate traffic information is key to managing traffic issues. Many approaches that use traffic time series data to predict traffic flow have been proposed. In addition to traffic-specific parameters, some other features (called signatures) may be associated with road traffic, i.e., air and noise pollution. In this paper, we show how noise pollution and traffic time-series data were used to train Long-Short Term Memory (LSTM) Recurrent Neural Networks (RNNs), which led to better traffic prediction on major roads in Madrid. This approach has already been used with pollution signatures. This work addresses a new potential investigation path closely related to the use of signature profiles and Artificial Intelligent techniques as a way to reduce the specialization of sensing infrastructure.


  • Exploiting Digital Twins as Enablers for Synthetic Sensing

    by Roberto Minerva, Faraz Malik Awan, Noel Crespi

    The Digital Twin has the ability to store historical and current data about the physical object. In IoT, the concept of general-purpose sensing is aiming at determining a set of basic sensing capabilities from which deriving, by means of Artificial Intelligence algorithms and techniques (termed Synthetic Sensing), relevant information for describing an environment. This paper explores the possible relationships and the feasibility of integration of Synthetic Sensing within a Digital Twin framework. The relevant concepts and associated technologies, the challenges, and some of the enabled scenarios that this integration can bring are presented. This approach is in its infancy and there is a strong need to validate and assess its viability, feasibility, and benefits. The paper identifies some challenges and validation steps that can lead to consolidation and broad adoption of this approach. Finally, the paper presents some future work that aiming at proving the approach


  • Open Access

    Applying Convolutional Neural Networks With Different Word Representation Techniques to Recommend Bug Fixers

    by Syed Farhan Alam Zaidi, Faraz Malik Awan, Minsoo Lee, Honguk Woo, Chan-Gun Lee

    Bug triage processes are intended to assign bug reports to appropriate developers effectively, but they typically become bottlenecks in the development process—especially for large-scale software projects. Recently, several machine learning approaches, including deep learning-based approaches, have been proposed to recommend an appropriate developer automatically by learning past assignment patterns. In this paper, we propose a deep learning-based bug triage technique using a convolutional neural network (CNN) with three different word representation techniques: Word to Vector (Word2Vec ), Global Vector (GloVe), and Embeddings from Language Models (ELMo). Experiments were performed on datasets from well-known large-scale open-source projects, such as Eclipse and Mozilla, and top-k accuracy was measured as an evaluation metric. The experimental results suggest that the ELMo-based CNN approach performs best for the bug triage problem. GloVe-based CNN slightly outperforms Word2Vec-based CNN in many cases. Word2Vec-based CNN outperforms GloVe-based CNN when the number of samples per class in the dataset is high enough.


  • Open Access

    Improving Road Traffic Forecasting Using Air Pollution and Atmospheric Data: Experiments Based on LSTM Recurrent Neural Networks

    by Faraz Malik Awan, Roberto Minerva, Noel Crespi

    Traffic flow forecasting is one of the most important use cases related to smart cities. In addition to assisting traffic management authorities, traffic forecasting can help drivers to choose the best path to their destinations. Accurate traffic forecasting is a basic requirement for traffic management. We propose a traffic forecasting approach that utilizes air pollution and atmospheric parameters. Air pollution levels are often associated with traffic intensity, and much work is already available in which air pollution has been predicted using road traffic. However, to the best of our knowledge, an attempt to improve forecasting road traffic using air pollution and atmospheric parameters is not yet available in the literature. In our preliminary experiments, we found out the relation between traffic intensity, air pollution, and atmospheric parameters. Therefore, we believe that addition of air pollutants and atmospheric parameters can improve the traffic forecasting. Our method uses air pollution gases, including C O , N O , N O 2 , N O x , and O 3 . We chose these gases because they are associated with road traffic. Some atmospheric parameters, including pressure, temperature, wind direction, and wind speed have also been considered, as these parameters can play an important role in the dispersion of the above-mentioned gases. Data related to traffic flow, air pollution, and the atmosphere were collected from the open data portal of Madrid, Spain. The long short-term memory (LSTM) recurrent neural network (RNN) was used in this paper to perform traffic forecasting.


  • Open Access

    A Comparative Analysis of Machine/Deep Learning Models for Parking Space Availability Prediction

    by Faraz Malik Awan, Yasir Saleem, Roberto Minerva, Noel Crespi

    Machine/Deep Learning (ML/DL) techniques have been applied to large data sets in order to extract relevant information and for making predictions. The performance and the outcomes of different ML/DL algorithms may vary depending upon the data sets being used, as well as on the suitability of algorithms to the data and the application domain under consideration. Hence, determining which ML/DL algorithm is most suitable for a specific application domain and its related data sets would be a key advantage. To respond to this need, a comparative analysis of well-known ML/DL techniques, including Multilayer Perceptron, K-Nearest Neighbors, Decision Tree, Random Forest, and Voting Classifier (or the Ensemble Learning Approach) for the prediction of parking space availability has been conducted. This comparison utilized Santander’s parking data set, initiated while working on the H2020 WISE-IoT project. The data set was used in order to evaluate the considered algorithms and to determine the one offering the best prediction. The results of this analysis show that, regardless of the data set size, the less complex algorithms like Decision Tree, Random Forest, and KNN outperform complex algorithms such as Multilayer Perceptron, in terms of higher prediction accuracy, while providing comparable information for the prediction of parking space availability. In addition, in this paper, we are providing Top-K parking space recommendations on the basis of distance between current position of vehicles and free parking spots.