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


Citation Style Language JSON Export

{
  "publisher": "Zenodo", 
  "DOI": "10.5281/zenodo.3676525", 
  "author": [
    {
      "family": "Alexandros Papadopoulos"
    }, 
    {
      "family": "Konstantinos Kyritsis"
    }, 
    {
      "family": "Sevasti Bostanjopoulou"
    }, 
    {
      "family": "Lisa Klingelhoefer"
    }, 
    {
      "family": "Ray K. Chaudhuri"
    }, 
    {
      "family": "Anastasios Delopoulos"
    }
  ], 
  "issued": {
    "date-parts": [
      [
        2019, 
        7, 
        31
      ]
    ]
  }, 
  "abstract": "<p>Parkinson&rsquo;s Disease (PD) is a neurodegenerative&nbsp;disorder that manifests through slowly progressing symptoms,&nbsp;such as tremor, voice degradation and bradykinesia. Automated&nbsp;detection of such symptoms has recently received much attention&nbsp;by the research community, owing to the clinical benefits associated with the early diagnosis of the disease. Unfortunately,&nbsp;most of the approaches proposed so far, operate under a strictly&nbsp;laboratory setting, thus limiting their potential applicability in&nbsp;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&nbsp;at hand, as a case of Multiple-Instance Learning, wherein a&nbsp;subject is represented as an unordered bag of signal segments&nbsp;and a single, expert-provided, ground-truth. We employ a&nbsp;deep learning approach that combines feature learning and a&nbsp;learnable pooling stage and is trainable end-to-end. Results on&nbsp;a newly introduced dataset of accelerometer signals collected&nbsp;in-the-wild confirm the validity of the proposed approach.&nbsp;</p>", 
  "title": "Multiple-Instance Learning for In-The-Wild Parkinsonian Tremor Detection", 
  "type": "paper-conference", 
  "id": "3676525"
}
56
108
views
downloads
All versions This version
Views 5656
Downloads 108108
Data volume 46.1 MB46.1 MB
Unique views 5151
Unique downloads 103103

Share

Cite as