Multi-Modal Anomaly Detection in Human Behavior using Deep Learning and large Language Models (PhD)

Program Overview

This PhD project aims to develop a comprehensive system for detecting anomalies in human behavior by leveraging both visual and textual data. The project will combine deep learning models for image and video analysis with large language models for natural language understanding, creating a multi-modal approach to enhance the accuracy and interpretability of anomaly detection in various scenarios. The successful candidate will have access to state-of-the-art facilities and work with a strong AI research team, with potential applications in security, surveillance, healthcare monitoring, and other domains.

Program Outline

Degree Overview:

This PhD research project aims to develop a comprehensive system for detecting anomalies in human behavior by leveraging both visual and textual data. The project will combine deep learning models for image and video analysis with large language models for natural language understanding, creating a multi-modal approach to enhance the accuracy and interpretability of anomaly detection in various scenarios.

Outline:

The project will involve the following components and research topics: Visual Anomaly Detection: Utilize convolutional neural networks (CNNs) and recurrent neural networks (RNNs) for analyzing video streams or image sequences to identify abnormal patterns in human behavior. Diverse scenarios can be crowded environments, public spaces, workplace or healthcare settings. Multi-Modal Fusion: Develop a fusion mechanism to combine the outputs of the visual and language models effectively. E.g. Real-Time Processing: Design the system to operate in real-time.

Teaching:

The successful candidate will have access to robotics and AI laboratories, high-spec computing facilities (e.g., A100 GPUs), HPC, and £5.8M DigLabs, complementing a £9m investment in research and teaching. You will have regular supervision meetings and work with a strong AI research team including over 30 PhDs/PDRAs/academic staff in the department. You will take part in various outreach and impact generation activities, and develop your career profile throughout your PhD study.

Careers:

This research has the potential to advance the field of anomaly detection by providing a more holistic understanding of human behavior through the integration of visual and textual data. The proposed system can find applications in security, surveillance, healthcare monitoring, and various other domains where detecting anomalous behavior is crucial for ensuring safety. The outcomes include well-performing AI models, learning algorithms, and data fusion strategies for the potential applications of multi-modal anomaly detection in real-world scenarios.

Other:

Loughborough University is one of UK top universities in research and innovation in science and engineering fields. 94% of Loughborough’s research impact is rated world-leading or internationally excellent in most recent Research Excellence Framework (REF 2021) assessment. Loughborough University has been awarded gold for student experience, gold for student outcomes and gold overall in the 2023 Teaching Excellence Framework- Triple Gold in TEF 2023. The Department of Computer Science has an excellent research record in AI, machine learning, robotics, computer vision and data science.

UK fee £4,712 Full-time degree per annum International fee £26,000 Full-time degree per annum 2024-25 tuition fees are applicable to projects starting in October 2024, January 2025, April 2025 and July 2025. University fees and charges can be paid in advance and there are several methods of payment, including online payments and payment by instalment. Fees are reviewed annually and are likely to increase to take into account inflationary pressures.