Conference paper Open Access

Multiple-Instance Learning for In-The-Wild Parkinsonian Tremor Detection

Alexandros Papadopoulos; Konstantinos Kyritsis; Sevasti Bostanjopoulou; Lisa Klingelhoefer; Ray K. Chaudhuri; Anastasios Delopoulos

Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="" xmlns:oai_dc="" xmlns:xsi="" xsi:schemaLocation="">
  <dc:creator>Alexandros Papadopoulos</dc:creator>
  <dc:creator>Konstantinos Kyritsis</dc:creator>
  <dc:creator>Sevasti Bostanjopoulou</dc:creator>
  <dc:creator>Lisa Klingelhoefer</dc:creator>
  <dc:creator>Ray K. Chaudhuri</dc:creator>
  <dc:creator>Anastasios Delopoulos</dc:creator>
  <dc:description>Parkinson’s Disease (PD) is a neurodegenerative disorder that manifests through slowly progressing symptoms, such as tremor, voice degradation and bradykinesia. Automated detection of such symptoms has recently received much attention by the research community, owing to the clinical benefits associated with the early diagnosis of the disease. Unfortunately, most of the approaches proposed so far, operate under a strictly laboratory setting, thus limiting their potential applicability in real world conditions. In this work, we present a method for automatically detecting tremorous episodes related to PD, based on acceleration signals. We propose to address the problem at hand, as a case of Multiple-Instance Learning, wherein a subject is represented as an unordered bag of signal segments and a single, expert-provided, ground-truth. We employ a deep learning approach that combines feature learning and a learnable pooling stage and is trainable end-to-end. Results on a newly introduced dataset of accelerometer signals collected in-the-wild confirm the validity of the proposed approach. </dc:description>
  <dc:title>Multiple-Instance Learning for In-The-Wild Parkinsonian Tremor Detection</dc:title>
All versions This version
Views 5656
Downloads 108108
Data volume 46.1 MB46.1 MB
Unique views 5151
Unique downloads 103103


Cite as