Our team

Dr. Abdelaziz Triki

Dr Abdelaziz Triki is a computer scientist specialising in machine learning, computer vision, and image processing. His doctoral research was conducted as part of a collaborative project between the Friedrich Schiller University Jena and the German Centre for Integrative Biodiversity Research (iDiv) in Leipzig, in partnership with the University of Sfax. His work focused on developing advanced AI methodologies for data-driven analysis. Dr Triki has extensive experience across both academia and the technology industry, contributing significantly to AI-driven innovations in healthcare.

Overview

Following his doctoral studies, Dr Triki began his postdoctoral research at Otto von Guericke University (OvGU), where he led the development of a smart ICT-based rollator aimed at enhancing elderly care. He designed several AI-based applications, including a facial recognition system for monitoring the well-being of elderly users, integrating advanced AI techniques for patient classification. At OvGU, Dr Triki also holds a lecturer position, where he mentors and supervises students on projects and theses, fostering academic growth and innovation. He collaborates closely with industry partners to incorporate real-world applications into his teaching, enhancing the practical knowledge and employability of his students. Additionally, he organises workshops and seminars on emerging AI technologies and engages in grant writing and fundraising to support departmental research initiatives.

As a lecturer in Artificial Intelligence and Data Science at the Swiss Digital Network in Basel, Dr Triki played an instrumental role in designing and updating course syllabi to align with academic and industry standards. He also conducted assessments to evaluate and improve student learning outcomes and developed specialised coursework in AI and data analytics.

Dr Triki has applied his expertise in the technology sector to develop advanced AI and machine learning solutions for analysing and predicting a wide range of data types. His contributions include improving nanomaterial identification accuracy, automating industrial quality control through computer vision, and optimising healthcare monitoring platforms. These innovations have advanced predictive analytics in public health and facilitated real-time decision-making through sophisticated data visualisation tools.

Areas of expertise

Artificial Intelligence for Healthcare and Biomedical Applications
Deep Learning and Computer Vision for Medical and Environmental Data
Multimodal Machine Learning and Sensor Fusion
AI for Biodiversity Informatics and Ecological Monitoring
Human–Computer Interaction and Assistive Robotics
Conversational AI and Intelligent Chatbot Systems

Awards and Honours

Secured Competitive Funding:
• BMBF Research Grant (01DH21023A) – Innovative ICT-based Rollator for Active and Healthy Ageing (2022–present)
• DAAD Project – Promoting Engineering and Digital Technology for Physical and Mental Health (2019–2020)
• BMBF Project (01D16009) – Managing Multimedia Data for Science (MAMUDS) (2016–2019)

These awards demonstrate Dr Triki’s consistent collaboration with German federal research programmes and international institutions.

Research interests

Artificial Intelligence for Healthcare and Biomedical Applications
Deep Learning and Computer Vision for Medical and Environmental Data
Multimodal Machine Learning and Sensor Fusion
AI for Biodiversity Informatics and Ecological Monitoring
Human–Computer Interaction and Assistive Robotics
Conversational AI and Intelligent Chatbot Systems

Publications

Mild cognitive impairment classification based on a deep learning approach using EEG data
A Deep Learning-Based Approach for Detecting Plant Organs from Digitised Herbarium Specimen Images
Deep Learning-Based Approach for Digitised Specimen Segmentation
PhenoDeep: A Deep Learning-Based Approach for Detecting Reproductive Organs from Digitised Herbarium Specimen Images
Deep Leaf: Mask R-CNN-Based Leaf Detection and Segmentation from Digitised Herbarium Specimens
Deep Learning-Based Approach for Segmenting and Counting Reproductive Organs from Digitised Herbarium Specimens Using Refined Mask Scoring R-CNN
Object Detection from Digitised Herbarium Specimens Based on Improved YOLOv3
Comprehensive Leaf Size Traits Dataset for Seven Plant Species from Digitised Herbarium Specimen Images Covering More Than Two Centuries
Measuring Morphological Functional Leaf Traits from Digitised Herbarium Specimens Using TraitEx Software
Specimen-GT Tool: Ground Truth Annotation Tool for Herbarium Specimen Images

Conferences, Talks, and Speaking Engagements

• University Lecturer, Otto von Guericke University Magdeburg (2022–2024)
Delivered lectures and seminars on Deep Learning Applications in Healthcare and Assistive Robotics as part of the ICT-Rollator project funded by the BMBF.

• Lecturer and Guest Speaker, Swiss Digital Network, Basel (2020–2021)
Delivered specialised sessions on Machine Learning for Biomedical Data Integration and AI-Based Gene Expression Analysis as part of the AI and Data Science training series, bridging academic research with industry practice.

• Research Presentation, German Centre for Integrative Biodiversity Research (iDiv), Leipzig (2017–2020)
Presented PhD research on AI-Based Functional Trait Extraction from Digitised Herbarium Specimens within the BMBF-funded MAMUDS project.

• Speaker, DAAD Workshop: Promoting Engineering and Digital Technology for Physical and Mental Health (2020)
Shared insights on Machine Learning Techniques for Cognitive Health Assessment.

• Conference Contributor, IEEE and Springer-Indexed International Conferences (2019–2022)
Presented papers on Deep Learning for Plant Trait Detection and AI-Based Classification of EEG Data.

Technical Skills

• Programming Languages: Python, C++, Java, JavaScript
• AI and Machine Learning: TensorFlow, PyTorch, Keras, CUDA for GPU-accelerated computing
• High-Performance Computing (HPC): Expertise in parallelising deep learning model training using HPC clusters
• Cloud Computing: Experienced with Google Cloud Platform, AWS, and IBM Cloud for deploying scalable AI solutions