Publications by authors named "K M Kucher"
Visualization for Trust in Machine Learning Revisited: The State of the Field in 2023.
IEEE Comput Graph Appl
June 2024
Article Synopsis
- Visualization for explainable and trustworthy machine learning is a critical area of research, especially in fields like medicine, finance, and bioinformatics.
- After compiling a comprehensive report in 2020, researchers have now updated their dataset to include 542 visualization techniques, which are organized into 119 categories.
- The latest findings indicate a significant growth in visualization methods aimed at enhancing trust in machine learning, showing that these techniques help improve model explainability and evaluate new deep learning frameworks.
Article Synopsis
- Activated phosphoinositide 3-kinase delta syndrome (APDS) is an immune disorder that leads to various health issues like infections and autoimmunity due to overactive PI3Kδ signaling.
- A phase 3 clinical trial tested leniolisib, a specific inhibitor of PI3Kδ, on 31 patients aged 12 and older, comparing its effects against a placebo over 12 weeks.
- Results showed that leniolisib significantly reduced lymph node size and increased naïve B cells, indicating improved immune function, while also being well-tolerated with fewer adverse events compared to placebo.
The machine learning (ML) life cycle involves a series of iterative steps, from the effective gathering and preparation of the data-including complex feature engineering processes-to the presentation and improvement of results, with various algorithms to choose from in every step. Feature engineering in particular can be very beneficial for ML, leading to numerous improvements such as boosting the predictive results, decreasing computational times, reducing excessive noise, and increasing the transparency behind the decisions taken during the training. Despite that, while several visual analytics tools exist to monitor and control the different stages of the ML life cycle (especially those related to data and algorithms), feature engineering support remains inadequate.
View Article and Find Full Text PDFArticle Synopsis
- The proposed autonomous monitoring system can measure temperature distribution in different layers (air, ice, and water) and records solar radiation, snow, and ice thickness simultaneously for months.
- The system, equipped with advanced sensors, is compact and efficient, specifically designed to capture fine-scale changes in ice thickness, and has been reliably tested in Lake Baikal.
To evaluate efficacy and safety of BGG492 (selurampanel; an orally active, competitive AMPA glutamate receptor antagonist) in patients with moderate-to-catastrophic chronic subjective tinnitus. Study (NCT01302873) enrolled patients with subjective tinnitus based on THI severity grade 3, 4 or 5 (moderate, severe or catastrophic), and those with chronic (>6 and <36 months) tinnitus. Primary endpoints were clinical status of tinnitus using TBF-12 and tinnitus loudness using VAS after multiple dose 2-week BGG492 treatment.
View Article and Find Full Text PDF