The availability of educational data in novel ways and formats brings new opportunities to students with special education needs (SEN), whose behaviour and learning are highly sensitive to their body conditions and surrounding environments. Multimodal learning analytics (MMLA) captures learner and learning environment data in various modalities and analyses them to explain the underlying educational insights. In this work, we applied MMLA to predict SEN students’ behaviour change upon their participation in applied behaviour analysis (ABA) therapies, where ABA therapy is an intervention in special education that aims at treating behavioural problems and fostering positive behaviour changes. Here we show that by inputting multimodal educational data, our machine learning models and deep neural network can predict SEN students’ behaviour change with optimum performance of 98% accuracy and 97% precision. We also demonstrate how environmental, psychological, and motion sensor data can significantly improve the statistical performance of predictive models with only traditional educational data. Our work has been applied to the Integrated Intelligent Intervention Learning (3I Learning) System, enhancing intensive ABA therapies for over 500 SEN students in Hong Kong and Singapore since 2020.

Children with intellectual disabilities (ID), especially those who fail to communicate with normal speech, suffer from various limitations in their social functioning. They often rely on alternate methods to supplement or replace verbal communication. There is a rapidly growing number of augmentative and alternative communication (AAC) mobile applications available over recent years. However, the operation of these applications remains a challenge for users with ID since they may not have the sufficient cognitive proficiency to cope with the application interface. In this paper, we present the design, implementation, and evaluation of a Bluetooth low energy (BLE) based context-aware AAC system. Our system facilitates daily communication for nonverbal school children with moderate ID in order to address their learning and communication needs. We have piloted and evaluated our system at a special education school in Hong Kong. Our technical contribution is twofold. First, we introduce BLE technology to the AAC field and show its effectiveness on users with ID. Second, by converting conventionally standalone AAC software into a service system and empowering it with Internet of Things functionality, we open up many new opportunities brought by the system-of-systems (SoS) paradigm for the intellectually disabled population.

Applied behavior analysis (ABA) has become a popular behavioral therapy in the special education needs (SEN) community. ABA is used to manage SEN students’ behaviors by solving problems in socially important settings, and puts emphasis on having precise measurements on physical and observable events. In this work, we present how Internet of Things (IoT) technologies can be applied to enhance ABA therapy in normal SEN classroom settings. We measured (1) learning performance data, (2) learners’ physiological data, and (3) learning environment sensors’ data. Upon preliminary analysis, we have found that learners’ physiological data is highly diverse, while learner performance seems to be related to learners’ electrodermal activity. Our preliminary findings suggest the possibility of enhancing ABA for SEN with IoT technologies.

We propose ABA-RAG, a retrieval-augmented generation (RAG) framework specifically tailored for applied behavior analysis (ABA) interventions, which integrates real-time emotional and behavioral data from Internet-of-Things (IoT) wearable devices. In ABA-RAG, we systematically retrieve semantically relevant prompts from a structured ABA task repository using embedding-based semantic search and dynamically construct context-aware prompts by incorporating IoT-derived predictions of learners’ emotional and behavioral states. To efficiently adapt large language model (LLM) to ABA contexts, we evaluate and compare several low-rank fine-tuning methods—including Low-Rank Adaptation (LoRA), Butterfly Orthogonal Fine-Tuning (BOFT), and LoRA with Gradient Approximation (LoRA-GA). Among these techniques, LoRA-GA demonstrates the best balance between computational efficiency and generation quality, making it particularly suitable for resource-constrained environments. Comprehensive experiments, validated through rigorous quantitative metrics and expert ABA practitioner evaluations, demonstrate that ABA-RAG significantly reduces manual workload while enhancing the precision, contextual relevance, and clinical utility of generated ABA tasks. Integrated into a practical web-based system, ABA-RAG provides ABA professionals with a scalable and real-time platform to generate individualized interventions.

In this work-in-progress, an action research was performed in a taught postgraduate engineering course during the global pandemic of COVID-19 in Spring 2020. Due to the social distancing policy, all courses offered by the authors’ university must be delivered online. In addition to the synchronous online lectures delivered through ZOOM, the course instructor (first author) established a class blogging community as an innovative practice to promote students’ social epistemic cognition (SEC) under physical isolation. The current action research focuses on course design, with a disposition that students’ SEC can be enhanced by collaborative learning in form of a class blogging community. The action research consisted of three implementation loops. The first author reflected her teaching in the end of each loop, and modified her practice in the next loop. A summative evaluation was conducted in the end of the semester. Our results suggest that the class blogging community, together with teacher’s action research and students’ social network analysis, are effective strategies in enhancing engineering students’ collaborative learning under nearly completed physical isolation.