Les commentaires sont clos.

Offre de stage suivi d'une thèse doctorale

6 Novembre 2022

Catégorie : Stagiaire

R&D Data Science Master internship



Bipolar disorder, also called manic depression, is a mental health disorder that causes extreme mood swings that include abnormally emotional highs (mania or hypomania) and lows (depression). According to the World Health Organization, 46 million people around the world, including 2.8% of the U.S. population, have bipolar disorder.

The risk of suicide is high; over a period of 20 years, 6% of those with bipolar disorder died by suicide, while 30–40% engaged in self-harm. Bipolar disorder (BD) is a significant public health issue and computer-aided diagnosis systems are needed for the diagnosis and the follow-up of patients. In this master internship and later in the PhD thesis, we aim to propose innovative deep learning based approaches for the diagnosis and the home monitoring of BD patients using video. In a preliminary work to this thesis, we have proposed a new Transformer-based approach for BD classification based on audio data. Our proposed approach outperforms all existing approaches for BD classification on the turkish audio-visual bipolar disorder corpus and it achieves an accuracy of 88.2% and a F1-score of 87.8%. This project is in collaboration with Sejong University, Korea and it will be co-supervised by Dr. Mustaqueem Khan.

Please refer to our previous publications on AI for Mental Health and for psychiatry (



We are seeking bright and highly motivated master students, who can work in the field of artificial intelligence. The project will develop innovative deep learning approaches for computer-aided diagnosis tools for Bipolar Disorder using Video. An innovative deep learning-based approach will be proposed. More details about the project will be given during the interview for confidentiality reasons.

The selected candidate will have the chance to work in an interdisciplinary team. This internship will lead to a PhD scholarship.



  • The candidate must be an M2 Master student or in 5th year of an engineering school.
  • Has done M1 in computer science, applied mathematics or electrical engineering, with a focus on machine learning.
  • Experience in Deep learning and data analysis.
  • Experience in signal and image processing.
  • Demonstrated record of high-performance programming skills in python.
  • Demonstrated analytical, verbal, and scientific writing skills in English.



Internship duration will be 6 months starting from January 2023 at an early date to start. The latest date to start the internship will be April 2023.

Location: Université Paris-Est Créteil, Laboratoire Images, Signaux et Systèmes Intelligents (LISSI), 122 rue Paul Armangot, 94400 Vitry sur Seine



Please send your CV + transcripts + cover letter + recommendation letters to (before December 30, 2022).



1. URL

2. URL

3. URL Brief-Mental health-2022.1

4. Abaei, N., Al Osman, H.: A hybrid model for bipolar disorder classification from visual information. In: ICASSP, vol. 2020, pp. 4107–4111 (2020)

5. Amiriparian, S., Awad, A., Gerczuk, M., Stappen, L., Baird, A., Ottl, S., Schuller, B.: Audio-based recognition of bipolar disorder utilising capsule networks. In: 2019 International Joint Conference on Neural Networks (IJCNN), pp. 1–7. IEEE (2019)

6. Baevski, A., Zhou, H., Mohamed, A., Auli, M.: wav2vec 2.0: A framework for self-supervised learning of speech representations (2020). DOI 10.48550/ARXIV.2006.11477. URL

7. Divya, M., Ankalkoti, P.: Bipolar classification methodology deep learning

8. Du, Z., Li, W., Huang, D., Wang, Y.: Bipolar disorder recognition via multi-scale discrimi-native audio temporal representation. In: Proceedings of the 2018 on Audio/Visual Emotion Challenge and Workshop, pp. 23–30 (2018)

9. Ebrahim, M., Al-Ayyoub, M., Alsmirat, M.: Determine bipolar disorder level from patient interviews using bi-lstm and feature fusion. In: 2018 Fifth International Conference on Social Networks Analysis, Management and Security (SNAMS), pp. 182–189. IEEE (2018)

10. Fernandes, B.S., Karmakar, C., Tamouza, R., Tran, T., Yearwood, J., Hamdani, N., Laouamri, H., Richard, J.R., Yolken, R., Berk, M., et al.: Precision psychiatry with immunological and cognitive biomarkers: a multi-domain prediction for the diagnosis of bipolar disorder or schizophrenia using machine learning. Translational psychiatry 10(1), 1–13 (2020)

11. Lin, E., Lin, C.H., Lane, H.Y.: Precision psychiatry applications with pharmacogenomics: Artificial intelligence and machine learning approaches. International journal of molecular sciences 21(3), 969 (2020)

12. Muzammel, M., Salam, H., Hoffmann, Y., Chetouani, M., Othmani, A.: Audvowelconsnet: A phoneme-level based deep cnn architecture for clinical depression diagnosis. Machine Learning with Applications 2, 100,005 (2020)

13. Muzammel, M., Salam, H., Othmani, A.: End-to-end multimodal clinical depression recognition using deep neural networks: A comparative analysis. Computer Methods and Programs in Biomedicine 211, 106,433 (2021)

14. Othmani, A., Kadoch, D., Bentounes, K., Rejaibi, E., Alfred, R., Hadid, A.: Towards robust deep neural networks for affect and depression recognition from speech. In: International Conference on Pattern Recognition, pp. 5–19. Springer (2021)

15. Othmani, A., Zeghina, A.O.: A multimodal computer-aided diagnostic system for depression relapse prediction using audiovisual cues: A proof of concept. Healthcare Analytics 2, 100,090 (2022)

16. Ren, Z., Han, J., Cummins, N., Kong, Q., Plumbley, M.D., Schuller, B.W.: Multi-instance learning for bipolar disorder diagnosis using weakly labelled speech data. In: Proceedings of the 9th International Conference on Digital Public Health, DPH2019, p. 79–83. Association for Computing Machinery, New York, NY, USA (2019). DOI 10.1145/3357729.3357743. URL

17. Ringeval, F., Schuller, B., Valstar, M., Cowie, R., Kaya, H., Schmitt, M., Amiriparian, S., Cummins, N., Lalanne, D., Michaud, A., et al.: Avec 2018 workshop and challenge: Bipolar disorder and cross-cultural affect recognition. In: Proceedings of the 2018 on audio/visual emotion challenge and workshop, pp. 3–13 (2018)

18. Syed, Z.S., Sidorov, K., Marshall, D.: Automated screening for bipolar disorder from audio/visual modalities. In: Proceedings of the 2018 on Audio/Visual Emotion Challenge and Workshop, pp. 39–45 (2018)

19. Xing, X., Cai, B., Zhao, Y., Li, S., He, Z., Fan, W.: Multi-modality hierarchical recall based on gbdts for bipolar disorder classification. In: Proceedings of the 2018 on Audio/Visual Emotion Challenge and Workshop, pp. 31–37 (2018)

20. Yang, L., Li, Y., Chen, H., Jiang, D., Oveneke, M.C., Sahli, H.: Bipolar disorder recognition with histogram features of arousal and body gestures. In: Proceedings of the 2018 on Audio/Visual Emotion Challenge and Workshop, pp. 15–21 (2018)

21. Zhang, Z., Lin, W., Liu, M., Mahmoud, M.: Multimodal deep learning framework for mental disorder recognition. In: 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020), pp. 344–350. IEEE (2020)

22. Çiftçi, E., Kaya, H., Güleç, H., & Salah, A. A. (2018, May). The turkish audio-visual bipolar disorder corpus. In 2018 First Asian Conference on Affective Computing and Intelligent Interaction (ACII Asia) (pp. 1-6). IEEE.