The first is recording patient-doctor consultations: transcription using audio-to-text models, and then summarising and reformatting into professional clinical documentation using LLMs. The second is using NLP and vector databases to do efficient search of clinical guideline documents, and ability to interact with the guidelines using NLP.
talk-data.com
Activities tracked
7
Data Science Retreat presents 7 Machine Learning prototypes and projects by Batch 34 participants. The event is free to attend, thanks to VINTED for hosting us.
Agenda:
17:30 - Drinks and Networking
18:00 - Welcome & Introduction
Followed by Project Presentations
PROJECT IDEAS:
1. MAG (Medical Advice Generator) Project by Kátia Mendes de Barros, Andrew Rosenswie and Juan Brugada
We are developing a LLM that uses medical question-answer pairs from PubMedQA: Jin et al., 2019, MedQA: Jin et al., 2020, and MMLU: Hendrycks et al., 2020. This model is mainly aimed as an instructional tool for non-EU doctors who want to become licensed doctors in Germany.
2. Berlin Computer Vision Bike Routing Project by Monika Graumann, Edith Hoffmann and Archibald Campbell Binning
Love cycling, hate cobblestones? This project uses recent street view images of Berlin to help people plot the best bicycle route from A to B.
3. Natural Maps Project by Justin Zarb, Pasquale Anthony Zito and Adam Hughes
NaturalMaps is an attempt to explore maps with natural language, such as “Find all the quietest coffee shops in Berlin that open before 8 AM and are in close proximity to a library.” At the moment, this is readily accessible open data, but going beyond simple queries requires expert know-how. We are exploring ways to make this information and analysis more accessible to the user
4. AI-Powered Video Analytics Project by Eugene Chepil
Leveraging Computer Vision for People Tracking and Object Detection. The application tracks and analyze people’s movements in various environments such as retail stores, shopping malls, warehouses, public spaces, airports, etc The Key Features: count people, create heatmaps, detect queues, track movement patterns, space occupancy analysis, zone-specific analytics, and customer movement patterns, providing valuable insights.
5. Short-long time fuel price prediction in Germany Project by Sergii Kurlov
Due to often (during day) changing of fuel price at all gas stations it is difficult to predict a real price in the near future. By short time prediction by ARIMA /SVM it is possible to find the best gas station for a lower price near you in the next minutes/hours.
6. AI-driven tools for doctors Project by Paul Jewell
The first is recording patient-doctor consultations: transcription using audio-to-text models, and then summarising and reformatting into professional clinical documentation using LLMs. The second is using NLP and vector databases to do efficient search of clinical guideline documents, and ability to interact with the guidelines using NLP.
7. Cervical Cancer Prediction Tool Project by Francesco Cocciro and Michele Lunelli
The project aims to provide a user-friendly web application that empowers users to assess the risk of cervical cancer and offers the ability to analyze images for potential tumor presence. By leveraging machine learning techniques and incorporating XAI and text generation, the application can contribute to early detection, promoting timely medical intervention.
More details to follow soon. Kindly RSVP confirming your participation as we have limited seats.
Sessions & talks
Showing 1–7 of 7 · Newest first
Leveraging Computer Vision for People Tracking and Object Detection. The application tracks and analyze people’s movements in various environments such as retail stores, shopping malls, warehouses, public spaces, airports, etc The Key Features: count people, create heatmaps, detect queues, track movement patterns, space occupancy analysis, zone-specific analytics, and customer movement patterns, providing valuable insights.
Berlin Computer Vision Bike Routing
2023-07-05
Love cycling, hate cobblestones? This project uses recent street view images of Berlin to help people plot the best bicycle route from A to B.
Cervical Cancer Prediction Tool
2023-07-05
The project aims to provide a user-friendly web application that empowers users to assess the risk of cervical cancer and offers the ability to analyze images for potential tumor presence. By leveraging machine learning techniques and incorporating XAI and text generation, the application can contribute to early detection, promoting timely medical intervention.
MAG (Medical Advice Generator)
2023-07-05
We are developing a LLM that uses medical question-answer pairs from PubMedQA: Jin et al., 2019, MedQA: Jin et al., 2020, and MMLU: Hendrycks et al., 2020. This model is mainly aimed as an instructional tool for non-EU doctors who want to become licensed doctors in Germany.
Natural Maps
2023-07-05
NaturalMaps is an attempt to explore maps with natural language, such as “Find all the quietest coffee shops in Berlin that open before 8 AM and are in close proximity to a library.” At the moment, this is readily accessible open data, but going beyond simple queries requires expert know-how. We are exploring ways to make this information and analysis more accessible to the user
Short-long time fuel price prediction in Germany
2023-07-05
Due to often (during day) changing of fuel price at all gas stations it is difficult to predict a real price in the near future. By short time prediction by ARIMA /SVM it is possible to find the best gas station for a lower price near you in the next minutes/hours.