Resume

Table of Contents

• Employment
• Education
• Awards
• Portfolio
• Technical Skills
• Languages
• Publications

For an updated CV please click here

Employment

• Jun 2023 - Present: Machine Learning and Computer Vision Principal Investigator, EssilorLuxottica, Milan, Italy
  • Research machine learning models optimized for embedded deployment on microcontrollers, focusing on context recognition for smart eyewear.
  • Lead 7 projects and the computer vision team, guiding research for smart eyewear technologies.
  • Focus on efficient deployment of computer vision applications for edge devices.
  • Identify potential patents for innovative works (submitted 6 patents).
  • Author papers on novel research in the field of machine learning and computer vision (3 papers).
• June 2021 - Present: Machine Learning Research Associate, Imperial College London, UK.
  • Developed applications in PyTorch and Tensorflow of deep learning models (LSTM, Autoencoders) to time-series personalised data collected from remotely monitored environments for detecting health-related episodes in people with dementia.
  • Improved the quality of the data, reducing missing data by 5% within a few weeks.
  • Assisted the laboratories for Machine Learning for Neuroscience module and marked the assignments. Material available on Github.
• September 2018 - December 2023: Teaching Assistant, Queen Mary University of London, UK.
  • Delivered lectures, practical sessions and marked assignments on Machine Learning and Data Mining to classes from 30 to 200 undergraduate and postgraduate students.
  • Led small group tutorials and provided one-on-one support to students, helping them to understand complex concepts and apply them in practical settings.
• February 2020 - May 2020: Computer Vision Intern, Tokyo University of Agriculture and Technology, Japan.
  • Developed a Tensorflow multi-modal fusion model for object detection (Faster R-CNN), combining visual and tactile features, resulting in two publications.
• May 2019 - June 2019: Machine Learning Assistant, Ocado Technology, UK.
  • Labelled videos human-robots interactions for use in maintenance assistance robot projects.
• July 2017 - June 2018: Machine Learning Assistant, Haute école spécialisée de Suisse occidentale, Switzerland.
  • Applied machine learning and computer vision techniques to healthcare projects:
    1. Developed Hololyo, an Augmented Reality environment using Unity and Microsoft Hololens, to provide visual feedback to amputees during the training of arm prostheses. Utilised IMU data from MYO bracelets to control a virtual rigged hand.
    2. Investigated the repeatability of hand movement recognition for the control of robotic prostheses using sEMG data and machine learning classification techniques.
    3. Applied image segmentation techniques to more than 2000 CT lung images for medical imaging analysis, extracting features using Matlab to identify patterns that could be used for cancer prediction.
• October 2016 - January 2017: Machine Learning Intern, Haute école spécialisée de Suisse occidentale, Switzerland.
  • Collaborated with the MeganePro project team. Acquired an openly available database of sEMG data, consisting of a total of 100 acquisitions from 10 subjects.
  • Applied preprocessing techniques, synchronised and filtered the data, and applied machine learning classification techniques (Random Forest).
  • Published a paper in rank A conference. Finalist for the Best Student Award.

Education

• July 2018 - September 2022: Ph.D. PhD Fellow in Electronics Engineering and Computer Science, Advanced Robotics Laboratory, Queen Mary University of London, UK.
  • Collaborated with the National Centre for Nuclear Robotics for developing a multi-modal robotic surface exploration algorithm for detecting and characterising fractures in extreme environments.
  • Implemented object detection algorithms (Faster R-CNN, YOLO) in Tensorflow to localise a crack in the environment using the video stream from a camera.
  • Developed an OpenCV algorithm for extracting a skeleton version from an image of a crack and using a minimum spanning tree graph to calculate the shortest path for exploring the crack.
  • Implemented the algorithm in Python and C++, and used machine learning techniques (Faster R-CNN, YOLO, CNN, Random Forest) to localise the crack and classify the data acquired via a force and proximity robotic sensor.
  • PhD representative for the 20 students in the Advanced Robotics Laboratory, organised biweekly meetings and mentored three master students during their final projects.
  • Participated in the Google Get Ahead 2020 program, an invitation-only program.
  • Presented demos and projects in outreach activities (Strategy 2030 and Open Days) to promote STEM to the public.
• January 2015 - May 2017: M.Sc. in Artificial Intelligence and Robotics, University of Rome “La Sapienza”, Italy, Mark 110/110.
  • Implemented machine learning techniques (feature extraction, classification) to analyse the repeatability of grasp recognition for robotic hand control based on surface electromyography data.
  • Developed a mobile application for Android that allows the user to send vocal commands and control a Nao Robot, through a client-server connection.
  • Developed “The Little Knight”, a videogame based on WebGL using the Javascript library (Three.js).
  • Developed an algorithm for controlling the pose of a Kuka manipulator via Mutual-Information Based on Visual Servoing.
• October 2011 - December 2014: B.Sc. in Computer and Automation Engineering, University of Rome “La Sapienza”, Rome, Italy, Italian Mark 95/110, 2010-2014
  • Analysis and development of spiking neural network Izhikevich models

Awards

• Data Visualisation Competition, UKDRI, April 2022:
  • Awarded first prize for the data visualisation competition.
• CORSMAL Challenge 2020, ICPR 2020, November 2020:
  • Awarded first prize as a member of a four-person team. Accurately estimated containers’ capacity via computer vision and machine learning techniques. Led the team in organising meetings and managing workload to complete the project.
• Japan Student Services Organization (JASSO) Scholarship, Tokyo University of Agriculture and Technology, February 2020:
  • Awarded scholarship of 2400£ to cover expenses for three months internship at the Tokyo University of Agriculture and Technology.
• Award for best Master Thesis on disability, University of Rome “La Sapienza”, January 2019:
  • Awarded best Master Thesis on disability among a total of 15 students across all faculties at the University.
• Programmer Award, VVV18, February 2018:
  • Awarded first prize for Group Project at the VVV18 International Winter School on Humanoid Robot Programming, organised by the IIT iCub Facility and the IEEE Robotics and Automation Society.
• Travel grant, VVV18, February 2018:
  • Awarded travel grant cover for alla expenses to participate in the International Winter School on Humanoid Robot Programming.
• Swiss-European Mobility Programme and Hes-So grant, HES-SO, Sierre, October 2016.
  • Awarded scholarship of 3300CHF to cover expenses for three months internship at the HES-SO Haute école spécialisée de Suisse occidentale.

Portfolio

For a complete list of my projects, please refer to the projects page.

• Developed an online application for video animation using the algorithm first order motion model for image animation by Aliaksandr Siarohin et al

Technical Skills

Languages

• Italian (Native)
• English (Advanced)
• French (Intermediate)
• Japanese (Basic)

Publications

For a full list of publications, please refer to my Google Scholar Profile.

Below a list of my most recents publications:

1. Capstick, A., Palermo, F., & Barnaghi, P. (2022). Loss Adapted Plasticity in Deep Neural Networks to Learn from Data with Unreliable Sources. arXiv preprint arXiv:2212.02895.
2. Palermo, F. (2022). Robotic surface exploration with vision and tactile sensing for cracks detection and characterisation. .
3. Omarali, B., Palermo, F., Althoefer, K., Valle, M., & Farkhatdinov, I. (2022). Tactile Classification of Object Materials for Virtual Reality based Robot Teleoperation. 2022 International Conference on Robotics and Automation (ICRA).
4. Xompero, A., Donaher, S., Iashin, V., Palermo, F., Solak, G., Coppola, C., Ishikawa, R., Nagao, Y., Hachiuma, R., & Liu, Q. (2022). The CORSMAL benchmark for the prediction of the properties of containers. IEEE Access.
5. Palermo, F., Li, H., Capstick, A., Fletcher-Lloyd, N., Zhao, Y., Kouchaki, S., Nilforooshan, R., Sharp, D., & Barnaghi, P. (2021). Designing A Clinically Applicable Deep Recurrent Model to Identify Neuropsychiatric Symptoms in People Living with Dementia Using In-Home Monitoring Data. Research2Clinics WS @ NeurIPS 2021, arXiv preprint arXiv:2110.09868.
6. Vitanov, I., Farkhatdinov, I., Denoun, B., Palermo, F., Otaran, A., Brown, J., Omarali, B., Abrar, T., Hansard, M., & Oh, C. (2021). A suite of robotic solutions for nuclear waste decommissioning. Robotics.
7. Palermo, F., Rincon-Ardila, L., Oh, C., Althoefer, K., Poslad, S., Venture, G., & Farkhatdinov, I. (2021). Multi-modal robotic visual-tactile localisation and detection of surface cracks. 2021 IEEE 17th International Conference on Automation Science and Engineering (CASE).
8. Xompero, A., Donaher, S., Iashin, V., Palermo, F., Solak, G., Coppola, C., Ishikawa, R., Nagao, Y., Hachiuma, R., & Liu, Q. (2021). Multi-modal estimation of the properties of containers and their content: survey and evaluation. IEEE TRANSACTIONS ON MULTIMEDIA.
9. Palermo, F., Oh, C., Althoefer, K., Poslad, S., & Farkhatdinov, I. (2021). Investigation of images of cracks via graph theory for developing an optimal exploration algorithm for a robotic manipulator. .
10. Iashin, V., Palermo, F., Solak, G., & Coppola, C. (2021). Top-1 CORSMAL challenge 2020 submission: Filling mass estimation using multi-modal observations of human-robot handovers. Pattern Recognition. ICPR International Workshops and Challenges: Virtual Event, January 10-15, 2021, Proceedings, Part VIII.
11. Palermo, F., Konstantinova, J., Althoefer, K., Poslad, S., & Farkhatdinov, I. (2020). Automatic fracture characterization using tactile and proximity optical sensing. Frontiers in Robotics and AI.
12. Palermo, F., Konstantinova, J., Althoefer, K., Poslad, S., & Farkhatdinov, I. (2020). Implementing tactile and proximity sensing for crack detection. 2020 IEEE international conference on robotics and automation (ICRA).
13. Omarali, B., Palermo, F., Valle, M., Poslad, S., Althoefer, K., & Farkhatdinov, I. (2019). Position and velocity control for telemanipulation with interoperability protocol. Towards Autonomous Robotic Systems: 20th Annual Conference, TAROS 2019, London, UK, July 3–5, 2019, Proceedings, Part I 20.
14. Palermo, F., Cognolato, M., Eggel, I., Atzori, M., & Müller, H. (2019). An augmented reality environment to provide visual feedback to amputees during sEMG Data Acquisitions. Towards Autonomous Robotic Systems: 20th Annual Conference, TAROS 2019, London, UK, July 3–5, 2019, Proceedings, Part II 20.
15. Palermo, F., Cognolato, M., Gijsberts, A., Müller, H., Caputo, B., & Atzori, M. (2017). Repeatability of grasp recognition for robotic hand prosthesis control based on sEMG data. 2017 International Conference on Rehabilitation Robotics (ICORR).