Multi-modal Anomaly Detection in Emotions Using Deep Learning Techniques H/F CEA

GENERAL INFORMATION ORGANISATION The French Alternative Energies and Atomic Energy Commission (CEA) is a key player in research, development and innovation in four main areas : * defence and security, * nuclear energy (fission and fusion), * technological research for industry, * fundamental research in the physical sciences and life sciences. Drawing on its widely acknowledged expertise, and thanks to its 16000 technicians, engineers, researchers and staff, the CEA actively participates in collaborative projects with a large number of academic and industrial partners. The CEA is established in ten centers spread throughout France REFERENCE 2022-20321 POSITION DESCRIPTION CATEGORY Information system CONTRACT Internship JOB TITLE Multi-modal Anomaly Detection in Emotions Using Deep Learning Techniques H/F SUBJECT Detecting anomalous emotions from multi-modal data CONTRACT DURATION (MONTHS) 5 to 6 JOB DESCRIPTION The field of affective computing is concerned with the design of computer systems capable of analyzing, recognizing, and simulating human emotions. Given the modernization of the world and the integration of computers in our daily life, the need for automatic human emotion recognition is increasingly gaining importance. In our lab LSSC (Laboratoire Signaux et Systèmes de Capteurs) at CEA, we are interested in detecting anomalous emotions such as depression, anxiety, etc. Detection of such emotions can help in monitoring mental health. Since emotions can be recognized through several modalities, the fusion of multimodal information plays an important role. To this end, we explore using several modalities (speech, physiological signals, text ..). The internship will consist of choosing the best signals to detect anomalies in emotions, extract useful features from the raw data. Apply traditional and deep learning anomaly detection methods on each modality. To obtain a final decision, implement a fusion method for all modalities Tasks :  Bibliography  Extracting useful features for anomaly detection from raw data  Developping traditional ML and DL algorithms  Report Contact : Salam Hamieh – salam.hamieh@cea.fr – Christelle Godin – christelle.godin@cea.fr – 0438784067 Vincent Heiries – vincent.heiries@cea.fr – 0438785520 APPLICANT PROFILE * Level of study : Bac+5 * Experience in Python * Experience in DeepLearning * Practical knowledge experience working with ML tools like TensorFlow, Keras, or Pytorch * Fluent in English POSITION LOCATION SITE Grenoble JOB LOCATION France, Auvergne-Rhône-Alpes, Isère (38) LOCATION Grenoble CANDIDATE CRITERIA LANGUAGES English (Fluent) REQUESTER POSITION START DATE 01/03/2022