Sökning: "Multi-label classification"
Visar resultat 6 - 10 av 28 uppsatser innehållade orden Multi-label classification.
6. Effects of different characteristics of sound data on multi-label classification accuracy
Kandidat-uppsats, KTH/DatavetenskapSammanfattning : One of many areas to which machine learning can be applied is sound recognition. A multi-label classification problem is a problem where several sounds, which are played simultaneously, are to be identified. LÄS MER
7. FMCW mmWave Radar for Detection of Pulse, Breathing and Fall within Home Care
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Countless of elderly people fall and get hurt within their homes, worldwide, every year, and as they can not always reach out for help themselves, they end up helplessly waiting for someone to notice what has occurred. Throughout this work, it is investigated if remote sensing of the mmWave FMCW radar IWR6843AOPEVM can be adopted to detect the incident of falls, and also detect the vital signs of the human subject. LÄS MER
8. Multi-label Text Classification for Symptom Identification
Master-uppsats, Lunds universitet/Institutionen för datavetenskapSammanfattning : .... LÄS MER
9. Detecting Signal Corruptions in Voice Recordings for Speech Therapy
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : When recording voice samples from a patient in speech therapy the quality of the recording may be affected by different signal corruptions, for example background noise or clipping. The equipment and expertise required to identify small disturbances are not always present at smaller clinics. LÄS MER
10. Automatic Categorization of News Articles With Contextualized Language Models
Master-uppsats, Linköpings universitet/Artificiell intelligens och integrerade datorsystemSammanfattning : This thesis investigates how pre-trained contextualized language models can be adapted for multi-label text classification of Swedish news articles. Various classifiers are built on pre-trained BERT and ELECTRA models, exploring global and local classifier approaches. LÄS MER