This final installment in our e-learning series offers a comprehensive look at the current impact and future potential of data science across industries. Using real-world examples like medical image analysis and operational efficiencies at Rotterdam The Hague Airport, we showcase data science’s transformative capabilities. The video also introduces the promise of Large Language Models (LLMs) such as Chat GPT and the simplification brought by Automated Machine Learning (AutoML). Emphasizing the blend of technology and human insight, we explore the evolving landscape of AI and data science for businesses.
VIDEO
Purpose: Most speech-language pathologists (SLPs) working with children with developmental language disorder (DLD) do not perform language sample analysis (LSA) on a regular basis, although they do regard LSA as highly informative for goal setting and evaluating grammatical therapy. The primary aim of this study was to identify facilitators, barriers, and needs related to performing LSA by Dutch SLPs working with children with DLD. The secondary aim was to investigate whether a training would change the actual performance of LSA. Method: A focus group with 11 SLPs working in Dutch speech-language pathology practices was conducted. Barriers, facilitators, and needs were identified using thematic analysis and categorized using the theoretical domain framework. To address the barriers, a training was developed using software program CLAN. Changes in barriers and use of LSA were evaluated with a survey sent to participants before, directly after, and 3 months posttraining. Results: The barriers reported in the focus group were SLPs’ lack of knowledge and skills, time investment, negative beliefs about their capabilities, differences in beliefs about their professional role, and no reimbursement from health insurance companies. Posttraining survey results revealed that LSA was not performed more often in daily practice. Using CLAN was not the solution according to participating SLPs. Time investment remained a huge barrier. Conclusions: A training in performing LSA did not resolve the time investment barrier experienced by SLPs. User-friendly software, developed in codesign with SLPs might provide a solution. For the short-term, shorter samples, preferably from narrative tasks, should be considered.
Post-training quantization reduces the computational demand of Large Language Models (LLMs) but can weaken some of their capabilities. Since LLM abilities emerge with scale, smaller LLMs are more sensitive to quantization. In this paper, we explore how quantization affects smaller LLMs’ ability to perform retrieval-augmented generation (RAG), specifically in longer contexts. We chose personalization for evaluation because it is a challenging domain to perform using RAG as it requires long-context reasoning over multiple documents. We compare the original FP16 and the quantized INT4 performance of multiple 7B and 8B LLMs on two tasks while progressively increasing the number of retrieved documents to test how quantized models fare against longer contexts. To better understand the effect of retrieval, we evaluate three retrieval models in our experiments. Our findings reveal that if a 7B LLM performs the task well, quantization does not impair its performance and long-context reasoning capabilities. We conclude that it is possible to utilize RAG with quantized smaller LLMs.
MULTIFILE
The increasing amount of electronic waste (e-waste) urgently requires the use of innovative solutions within the circular economy models in this industry. Sorting of e-waste in a proper manner are essential for the recovery of valuable materials and minimizing environmental problems. The conventional e-waste sorting models are time-consuming processes, which involve laborious manual classification of complex and diverse electronic components. Moreover, the sector is lacking in skilled labor, thus making automation in sorting procedures is an urgent necessity. The project “AdapSort: Adaptive AI for Sorting E-Waste” aims to develop an adaptable AI-based system for optimal and efficient e-waste sorting. The project combines deep learning object detection algorithms with open-world vision-language models to enable adaptive AI models that incorporate operator feedback as part of a continuous learning process. The project initiates with problem analysis, including use case definition, requirement specification, and collection of labeled image data. AI models will be trained and deployed on edge devices for real-time sorting and scalability. Then, the feasibility of developing adaptive AI models that capture the state-of-the-art open-world vision-language models will be investigated. The human-in-the-loop learning is an important feature of this phase, wherein the user is enabled to provide ongoing feedback about how to refine the model further. An interface will be constructed to enable human intervention to facilitate real-time improvement of classification accuracy and sorting of different items. Finally, the project will deliver a proof of concept for the AI-based sorter, validated through selected use cases in collaboration with industrial partners. By integrating AI with human feedback, this project aims to facilitate e-waste management and serve as a foundation for larger projects.
Developing a framework that integrates Advanced Language Models into the qualitative research process.Qualitative research, vital for understanding complex phenomena, is often limited by labour-intensive data collection, transcription, and analysis processes. This hinders scalability, accessibility, and efficiency in both academic and industry contexts. As a result, insights are often delayed or incomplete, impacting decision-making, policy development, and innovation. The lack of tools to enhance accuracy and reduce human error exacerbates these challenges, particularly for projects requiring large datasets or quick iterations. Addressing these inefficiencies through AI-driven solutions like AIDA can empower researchers, enhance outcomes, and make qualitative research more inclusive, impactful, and efficient.The AIDA project enhances qualitative research by integrating AI technologies to streamline transcription, coding, and analysis processes. This innovation enables researchers to analyse larger datasets with greater efficiency and accuracy, providing faster and more comprehensive insights. By reducing manual effort and human error, AIDA empowers organisations to make informed decisions and implement evidence-based policies more effectively. Its scalability supports diverse societal and industry applications, from healthcare to market research, fostering innovation and addressing complex challenges. Ultimately, AIDA contributes to improving research quality, accessibility, and societal relevance, driving advancements across multiple sectors.
De bereikbaarheid en beschikbaarheid van de ambulancezorg staat onder druk. Een belangrijke ingangsklacht van de mensen die 112 bellen is een kortdurende bewusteloosheid. Als deze bewusteloosheid het gevolg is van een verminderde bloedtoevoer in de hersenen noemen we het syncope. Syncope kan onschuldig of ernstig van aard zijn. De risico-inschatting en besluitvorming bij patiënten met syncope in de ambulancezorg is complex. Ambulanceprofessionals moeten in een kort tijdsbestek en onder hoge druk, met veel onderliggende informatie en onzekerheden risico’s inschatten en besluiten of een patiënt ingestuurd moet worden naar de spoedeisende hulp. Bij twee-derde van de ingestuurde syncope patiënten blijkt het niet ernstig te zijn. Twee HAN lectoraten ontwikkelden praktische en onderbouwde handvatten voor de praktijk (RAAK.PUB05.017 en RAAK.IMP.01.036). Deze zijn sinds juli 2022 onderdeel van de landelijke werkwijze. In vervolg hierop heeft de praktijk de lectoraten gevraagd om te kijken of de inzet van digitale- en informatietechnologie, specifiek generatieve kunstmatige intelligentie (AI) op basis van Large Language Models (LLM), hen nog verder kan ondersteunen bij het inschatten van risico’s en besluiten maken bij patiënten met syncope in de ambulancezorg. Deze KIEM-aanvraag is een proof of concept studie. We onderzoeken in hoeverre generatieve AI op basis van LMM technisch goed tekstbestanden kan analyseren op belangrijke medische- en omgevingsfactoren bij patiënten met een syncope. We kiezen voor een pilot concurrente validatiestudie door kwalitatieve tekstanalyse, in combinatie met aanvullende focusgroepinterviews voor de interpretatie van de uitkomsten. Voor de pilot concurrente validatiestudie gebruiken we tekstbestanden uit de Safe End studie. De eerdere analyse van deze tekstbestanden uit de Safe End studie fungeert als de gouden standaard. Zo wordt de validiteit van de generatieve AI-analyse op basis van LMM vastgesteld. In focusgroepinterviews bespreken we de impact en ethische aspecten van de bevindingen voor de praktijk, wetenschap, onderwijs en de (door)ontwikkeling van beslissingsondersteuningsinstrumenten voor de toekomst.
