Integrated Master-PhD Track | Data Science, Signal and Image Processing

Course content in the M1 and M2 years is based on the Master's specialism - Data Science, Signal and Image Processing - whereby Integrated Master-PhD Track students have a (limited) choice of modules, plus a research module and supervised research project. Full details below.

Data Science, Signal and Image Processing

M1 Year

30 ECTS Credits per semester.
Language of instruction: English

Autumn Semester

Core Courses	ECTS
Algorithmics and programming	4
Artificial Intelligence	6
Classical Linear Control	5
Mathematical Tools for Signals and Systems	4
Embedded Computing	4
Signal Processing	5
Research Seminar	0
Language Courses (1 out of 3)*
French as Foreign Language	2
Cultural and Communicational English	2
Spanish	2

* 'French as Foreign Language' except for French native speakers who will study 'Cultural and Communicational English' or Spanish (depending on sufficient demand).

In addition to the courses, students will attend scientific seminars to gain an overview of research activities in the field of control and robotics. This will enable them to identify the areas in which they wish to focus their research activities for the remainder of the programme.

Spring Semester

Core Courses	ECTS
Ethics in Research and Research Methodology	4
Research project 1	7
Elective Courses (choose 4 out of 5)
Computer Vision	4
Image Processing	5
Optimization Techniques	5
Systems Identification and Signal Filtering	4
Spectral and Time Frequency Analysis	4
Language Courses (1 out of 3)*
French as Foreign Language	2
Cultural and Communicational English	2
Spanish	2

* 'French as Foreign Language' except for French native speakers who will study 'Cultural and Communicational English' or Spanish (depending on sufficient demand).

NB Course content may be subject to minor changes

M2 Year

30 ECTS Credits per semester.
Language of instruction: English

Autumn Semester

Core Courses	ECTS
Research project 2	8
Elective Courses (choose 5 out of 6)
Biomedical signals, images and methods	4
Design of signal and image representations	4
Machine learning, data analysis and information retrieval	4
Mathematical tools for signal and image processing	4
Signal and image restoration, inversion methods	4
Statistical signal processing and estimation theory	4
Language Courses (1 out of 3)*
French as Foreign Language	2
Cultural and Communicational English	2
Spanish	2

* 'French as Foreign Language' except for French native speakers who will study 'Cultural and Communicational English' or Spanish (depending on sufficient demand).

Spring Semester

	ECTS
Master Thesis/Internship	30

NB Course content may be subject to minor changes

Download syllabus | Integrated Master-PhD Track - Data Science, Signal and Image Processing

• M1 Year
• M2 Year

This programme relies on Centrale Nantes’ faculty and the research facilities of the Laboratory of Digital Sciences of Nantes (LS2N).

About the LS2N

The LS2N Laboratory was launched with a single objective: bring together Nantes' research expertise in computer science and cybernetics to develop digital sciences, inclusive of other disciplines and taking account of the social challenges involved. The five areas of research expertise:
 

• Industry of the future | systems engineering, control, human factors, management, software engineering, robotics
• Management of energy and environmental impact  | embedded systems design, eco-design of robots, power grids, adaptable data centres
• Life Sciences  | medical imaging, neuronal signal processing, genomic data analysis,  biological network modelling, artificial organ design, automation of hospital equipment
• Vehicle and mobility | global vehicle automation, behavioural and usage modelling, traffic optimization
• Design, culture and digital society  | system design for the digital society, design of new interactions and links with digital artefacts, analysis of practices and interaction with digital artefacts

Major Research Projects

► MILCOM - Develop machine learning methods for the acquisition, annotation and analysis of medical images
The MILCOM project combines data sciences and health, and focuses on the application of machine learning to analyse multimodal medical images for the validation and identification of biomarkers in oncology.
The research work is being carried out by a multidisciplinary team from the LS2N, in collaboration with the Nuclear Medicine Department at Nantes University Hospital and the CRCINA team at Inserm, and is supervised by Diana Mateus, professor at Centrale Nantes and member of the Signal, Image and Sound (SIMS) team at LS2N.
The project aims to develop machine learning methods for the acquisition, annotation and analysis of medical images to assist doctors in their decision-making. Ultimately, the MILCOM project should help oncologists to diagnose and provide personalised treatment for patients suffering from diseases such as multiple myeloma. Learn more

►OWL (Operating Within Limits)  - Develop new algorithms for circadian AI
The OWL Project proposes a new model of computation for more frugal intelligent autonomous sensors: circadian artificial intelligence (AI). The targeted applications are in the field of environmental monitoring, especially bioacoustic and its application in conservation ecology.  This model is particularly well suited for sensors without batteries that are intermittently powered by ambient energy. The great promises of these systems is the extension of their lifetime without the need for human intervention allowing for long-term biostatistics observation missions, and a lower impact on the environment thanks to the absence of battery.
Circadian AI is interested in observing phenomena that have a period of one day, such as the activity of birds or the pollution associated with traffic in a metropolis. It exploits the fact that this period is shared with the availability of solar energy, which is used to power the sensors. This correlation allows the systems to temporally shift the costly computations required to perform the AI functions to times when the observed phenomenon is at rest and energy is abundant.
The project proposes two main contributions. The first is to propose new algorithms for circadian AI that allows for this temporal shift in computation. The second is to provide the software and hardware infrastructure necessary to run circadian AI on intermittently powered sensors.
OWL is funded by the French National Research Agency as part of the Specific Topics in Artificial Intelligence (TSIA 2023) programme.

Research Facilities

• Fast ultrasound imaging methods for non-destructive testing of attenuating and scattering materials ► Learn more
• Analysis and synthesis of urban sound scenes using deep learning techniques ► Learn more
• Deep learning for computer-aided early diagnosis of breast cancer ► Learn more
• Probabilistic models based on EMG decomposition for prosthetic control ► Learn more
• On-line decomposition of iEMG signals using GPU-implemented Bayesian filtering ► Learn more
• Improvement of the quantification of yttrium-90 PET images ► Learn more

Osimone, PhD Student 2023-2026 | MSc Signal and Image Processing, Class of 2022

Yuxin, PhD Student 2021-2024 | MSc Signal and Image Processing, Class of 2021

Why did you decide to come to Centrale Nantes for your MSc Programme in Signal and Image Processing?
"During my final undergraduate year, I was an exchange student at ECN, where I discovered it to be an excellent choice, both for its quality of life and academic offerings. As I reconsidered my original major and contemplated a switch, ECN provided a relaxed environment for me to weigh my options and explore various fields. Ultimately, I found that signal and image processing aligned best with my interests."

When and why did you decide to pursue your PhD here?
"During the final semester of my master's program, my laboratory internship provided me with a preliminary insight into the world of research. It was during this time that I developed a keen interest in the field of medical imaging. Motivated by the desire to delve deeper into this domain and experience the authentic lifestyle of a researcher, I decided to pursue a Ph.D. program."

What are you working on for your PhD?
"For my Ph.D., I am engaged in research on 'Medical Ultrasound Imaging with Deep Learning'. This involves exploring innovative applications of deep learning techniques in the realm of medical ultrasound imaging."

How would you rate the research facilities and support?
"Our laboratory LS2N is well-equipped with the necessary machinery and facilities for experiments. We maintain a close relationship with the companies that provide the machines. In terms of computational resources for deep learning, besides the GPU available on my workstation, we also have access to a high-performance computing cluster."

What do you plan to do after graduation?
"After graduation, I hope to join a company specializing in medical ultrasound imaging, where I can actively contribute by addressing specific challenges and solving real-world problems for end-users."

Any advice for future applicants?
"I advise prospective applicants to identify their genuine interests and suitable pursuits as early as possible. When considering an application, it's crucial to gather comprehensive information, including course structures, graduation requirements, and employment prospects. Ideally, early awareness of the core competencies each program cultivates can guide applicants in making informed choices that align with their future goals."

Pierre-Emmanuel Hladik is an Assistant Professor at Centrale Nantes and he carries out his research activity at the Laboratory of Digital Sciences of Nantes (LS2N) in the STR team. He previously spent 14 years in Toulouse at the Laboratory of Architecture and Analysis of Systems (LAAS-CNRS). He teaches in the field of autonomous embedded systems. His research interests deal with the modelling and verification of constraint concurrent systems, and in particular scheduling and methods to design safe systems.