Title: On the Evaluation of Security and Privacy in Smart Cities

Principal Investigator: Bechara AL BOUNA, PhD

Funding Agency: CNRS-L/UA

In today's world, we find ourselves surrounded by many IoT-based cyber-physical systems that silently track our activities and collect sensitive information about us. Among the most prominent examples, we cite smart environments (e.g., smart homes and cities), quantified self-technologies, smart energy meters, etc. While such systems promise to ease our lives, they raise major privacy concerns for their users, as the data collected is often privacy-sensitive, such as location of individuals, patients' vital signs. In this work, we will investigate the methodology to empower users to protect their privacy by themselves. That is, users should be able, before sharing a private data item (or a combination of data items) with a data consumer, to

Title: Data Mining and Machine Learning to Extract Important Markers to Improve Medical Monitoring Platforms

Principal Investigator: George BADR, PhD

Funding Agency: CNRS-L/UA

"The World Health Organization (WHO) accords that about 31 % of deaths worldwide are caused by heart diseases every year”. Data mining is a process of extracting interesting non-trivial, previously unknown and potentially useful information from huge amount of data. Medical data mining is the science of investigating medical data (i.e. vital signs) to explore significant information. Analyzing and interpreting the huge amount of complicated data into an appropriate therapeutic diagnosis with the right results is quite challenging task. Still, the fact that it is possible to combine these factors up to a certain point and extract a usually successful treatment, prevention and recovery plan is a sign of the good things to come. Thanks to that, it is now possible to improve patients’ quality of life, prevent condition worsening while maintaining medical costs at the decrease. This explains the increasing popularity in the usage and application of machine learning techniques to analyze, predict and classify medical data.

This project is about one of the heart diseases: The heart Failure. It is when the heart does not pump enough blood to the organs. The quality of life of a heart failure patient decreases dramatically and he has to go to the hospital every short period for the rest of his life. In this context, five parameters were extracted from patients over the course of a year. The parameters: are Heart Rate, Oxygen saturation, Diastolic and systolic blood pressure and weight. Other parameters were also generated consisting of the difference of each parameter over 1, 3 and 7 days. Some medical information are provided including the correlation between some parameters and the risk of the patient when two or more parameters are combined.

For example, if the weight of the patient increases suddenly (i.e. 2 to 3 kg in 2 days) this could mean water retention due to heart failure. The project is about mining the data in order to extract useful information and especially to predict the heart failure at least 15 days before it happens."

Title: Design of Phase-shifting cell by additive manufacturing for purely metallic eflectarray antennas.

Principal Investigator: Tony MAKDISSY, PhD

Funding Agency: AUF/CNRS-L

Microstrip printed reflectarrays have become a new generation of high gain antennas with many desirable features, such as high efficiency, versatile radiation performance, low profile, lightweight and ease of deployment. These electrical and mechanical advantages make them suitable for a variety of applications, such as satellite communications, direct broadcasting services, etc.

To fabricate a conventional reflectarray with microstrip technology, a high-performance and specifically low-loss dielectric substrate is required. This dielectric is the most expensive component for large-aperture reflectarrays, and its cost sometimes makes it impossible to produce such an antenna.

With the advent of additive manufacturing technology, the production of fully metallic or metallized plastic 3D objects has become quite feasible. This leads antenna designers to believe that a solution to the problem of dielectric losses has emerged.

In this project, we wish to take advantage of additive manufacturing to design purely metallic phase-shifting cells for reflectarray antennas. In order to demonstrate the feasibility of this new manufacturing technique, existing cell topologies will be used and adapted to the technological constraints imposed. Then, a new optimal topology will be proposed, taking full advantage of this experience. Finally, a small demonstrator will be manufactured and tested in order to evaluate the performance on a global antenna.

Title: Design of reconfigurable reflectarray antenna based on varicap diodes

Principal Investigator: Tony MAKDISSY, PhD

Funding Agency: CNRS-L/UA

Reflectarray forms a new family of antenna inheriting its properties from reflector antennas and from phased array antennas. A reflectarray consists of a primary source (typically a horn antenna) illuminating a flat panel of radiating elements called “phase-shifting cells”. The shape of the resulting radiation pattern is obtained by controlling the phase of the wave reflected by these cells.

The investigation on active techniques to control the reflected phase (using control elements such as MEMS switches, PIN diodes or varicap diodes) opens the field of reconfigurable reflectarrays. The main challenge while designing a reconfigurable reflectarray is to design a phase-shifting cell loaded with a limited number of control elements. In addition, the cell must be able to provide uniformly distributed phase states (or continuous variation of the phase) over 360 degrees. Finally, the variation of the different phase states with the frequency must be linear and parallel with low frequency dispersion to ensure a wideband behavior.

This project aims to design two phase-shifting cells loaded with varicap diodes for single and dual linear polarizations reflectarray. The designed cells will be tested on real reflectarrays in order to demonstrate the configurability of the radiation pattern.

Title: Mixed Reality for home Kinesitherapy rehabilitation

Principal Investigator: Anthony TANNOURY, PhD

Funding Agency: AUF

Information and Communication Technologies (ICTs) now represent an integral part and a lever in the advances related to services to help people become independent and improve their quality of life. The aim of this project is to use the virtual reality technique in the context of a treatment

Kinesitherapy or by physical activity adapted for health. This with the aim of a better follow-up of patients at home in order to improve considerably the efficiency and precision of their treatments.

It is a mixed virtual simulation of the environment of a physiotherapy clinic, very similar to the one in reality. One of the added values of this project is that the 3D content is reconstructed in real time, using 2D images/videos captured from a couple of multimedia sensors deployed in the physio clinic. The efficiency translates into the interaction that takes place between the patient and the scene, using another sensor mounted on the Virtual Reality (VR) headset, which detects the patient's movements. It then displays an interface to the patient and gives recommendations to perform the physical exercises correctly.

Note that this project does not seek to replace the physiotherapist, but it is a platform to help patients to be autonomous in part, of their monitoring and to the physiotherapists in order to give them information for a more adapted treatment.

This project will address the complete chain from the acquisition of 360° images to reproduce the physiotherapist's treatment environment as faithfully as possible. These images require post-processing in order to be used efficiently. Subsequently, compression and quality control steps make data manipulation easier since the physical size of the images becomes affordable. These images are integrated into a virtual reality environment with the addition of an avatar and the creation of scenarios corresponding to the physiotherapist's exercises. Finally, the pooling of the various tools developed in the framework of this project will make it possible to begin the therapeutic validation phase with the help of the physiotherapists and their patients.

Title: Preserving multimedia data quality and privacy

Principal Investigator: Chady ABOU JAOUDE, PhD

Funding Agency: CNRS-L/UA

Nowadays, social media runs a significant portion of people’s daily lives. Millions of people use social media applications to share photos. The huge volume of images shared on social media presents serious challenges and requires large computational infrastructure to ensure successful data processing. However, image gets distorted somehow during the processing, transmission, sharing or from a combination of many factors. So, our goal is to guarantee an acceptable delivery content, especially for image processing applications. For this purpose, we focus in our work on processing a large number of images in real-time while estimating the image quality using several objective image quality assessment methods (for example: Structural Similarity Index, Content Based Image Retrieval, etc.…).

Title: Analysis of daily stress in blind people

Principal Investigator: Youssef BOU ISSA, PhD

Funding Agency: CNRS-L/UA

This project is part of the smart Cities/buildings framework to improve the quality of life of blind people. In fact, our goal is to study the stress of blind people in their daily life by analyzing their activities during the different periods of the day. This analysis is carried out following the collection, processing and fusion of data from body sensor networks. These sensors allow real-time retrieval of data related to the intensity of a person's physical and cerebral activity. The analyzed data will allow us to define stress indicators and influencing factors. Moreover, this work is a continuation of a previous work on stress analysis for sighted employees using sensor networks. Subsequently, we will be able to conduct a comparative study of stress for sighted and blind employees.

Title: Mašriq Traditional Modal Monodies Encoding in the Music Encoding Initiative (MEI)

Principal Investigator: Talar ATECHIAN, PhD

Funding Agency: CNRS-L/UA

Music encoding is a representation of music sheets or music transcriptions to machine-readable structure. In this project, traditional Mašriq’s modal monodies transcriptions are encoded using Music Encoding Initiative (MEI) standard. In addition to the fundamental music elements encoded in the transcriptions, Modal Semiotic Theory [1] is used, providing a new encoding dimension. Thus, a generative grammar is proposed in the Theory to enrich the encoding process and to provide a detailed interpretation of the analyzed modal monodies. A semi-automated algorithm is implemented to encode in MEI standard modal monodies transcriptions. The prototype returns as a result, encoded music transcriptions accompanied by a detailed semiotic analysis. Experimentations are conducted, and still in progress, to evaluate the performance of the proposed algorithm, and the quality of the returned analysis. As a second phase of the project, we aim to develop a fully automated algorithm for the modal monodies encoding. Mathematical models and machine learning algorithms will be implemented. The fully automated open source prototype will be developed and musicologists will evaluate the performance the accuracy of the returned results.

Title: e-Health Monitoring using real-time Wireless Body Sensor Network

Principal Investigator: Rony DARAZI, PhD

Funding Agency: CEDRE Program

The main objective of this project is to design and implement a real-time system for patient health monitoring. This system uses connected sensors with an integrated coordinator (e.g. smart phone) that are connected to a central node installed at the medical center. The coordinator monitors the the patient health status by analyzing a number of vital signs that are collected. Based on the analysis, the patient is subject to be alerted and the vital signs are sent directly to the medical operator that can provide advice to the patient.

To achieve a functional architecture, making it possible to monitor patients and reduce the cost of stay in hospitals or specialized centers, many scientific obstacles remain to be overcome. This project focuses on: (i) studying the architecture of the system, (ii) collecting and reducing data for an efficient representation necessary for the transmission of data, analysis and storage of data, (iii) confidentiality of personal data, (iv) data analysis using deep learning techniques for automatic detection of emergencies.

Title: e-platform for collective taxi access – e-PTC

Principal Investigator: Rony DARAZI, PhD

Funding Agency: AUF

« e-PTC: a platform for optimizing and promoting the use of public transportation". Nowadays, transportation operators to put in place advanced information systems to help passengers travel around cities have conducted several initiatives. In Lebanon, there are three modes of public transportation: buses, shared taxis (known as “Service”) and private taxis (such as Uber and Carreem). One of the main issues is how to promote the accessibility of the passengers and the existing public transportation means. This project aims to develop a platform, which connects passengers with available transportation means in Lebanon. It is essentially based on the mode of shared taxis. This mode of transportation is characterized by the absence of fixed transit times and well-defined stations. Thus, our main objective is to develop the front-end and the back-end part of this platform backed by a mobile application, which optimizes and promotes the use of these shared public taxis. The proposed work offers a passenger several route alternatives between a departure point and a final destination. These choices can be classified according to criteria defined by the passenger. As a first prototype considering the case of Beirut city, the proposed solution aims to improve the organization of public taxis, makes them more attractive by giving them greater visibility, and encourage tourism.

Title: Study Of The Gait Classification For The Development Of The Best Strategy To Reduce The Risk Of Falling In The Elderly

Principal Investigator: Kabalan CHACCOUR, PhD

Funding Agency: CEDRE Program

The project aims to assist healthcare professionals to enable them to develop the best fall risk reduction strategy. It is a question of offering them a system to model and analyze the gait associated with a tool to assess the risk. The system will be based on the gait analysis platform that has been already developed. This platform combines several connected devices (insoles with pressure sensors and slabs with infrared sensors) to trace the relevant information characterizing the actimetric profile of the person. This information will help model the walk and help define a classification of the risk for an understanding of the complexity of walking in the elderly.