Search

Your search keyword '"Erdem, Oğuzhan"' showing total 3 results
Start Over Author "Erdem, Oğuzhan" Topic parkinson's disease
3 results on '"Erdem, Oğuzhan"'

2. Detection of Parkinson's disease with keystroke data.

Author

Demir, Bahar, Ulukaya, Sezer, and Erdem, Oğuzhan

Subjects
PARKINSON'S disease, MAJORITIES, SUPPORT vector machines, K-nearest neighbor classification, NEUROLOGICAL disorders, MACHINE learning, FEATURE selection, KEYBOARDS (Electronics)
Abstract

Parkinson's disease (PD) is one of the most widespread neurological disorders associated with nerve damage without definitive treatment. Impairments, such as trembling and slowing down in hand movements are among the first symptoms. For this purpose, in this study, machine learning (ML)-based models were developed by using keyboard keystroke dynamics. According to patients' drug use status, disease severity, and gender, we created 14 different sub-datasets and extracted 378 features using raw keystroke data. We developed alternative models with Support Vector Machines (SVM), k-Nearest Neighbors (kNN), and Random Forest (RF) algorithms. We further used Minimum Redundancy Maximum Relevance (mRmR), RELIEF, sequential forward selection (SFS), and RF feature selection methods to investigate prominent features in distinguishing PD. We developed ML models that jointly use the most popular features of selection algorithms (feature ensemble [FE]) and an ensemble classifier by combining multiple ML algorithms utilizing majority vote (model ensemble [ME]). With 14 different sets, FE and ME models provided accuracy (Acc.) in the range of 91.73 − 100% and 81.08 − 100%, respectively. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

3. Detection of Parkinson's disease with musical features using machine learning methods

Author

Kurt, İlke, Erdem, Oğuzhan, Ulukaya, Sezer, and Hesaplamalı Bilimler Anabilim Dalı

Subjects
Öznitelik Çıkarımı ve Seçimi, Disfoni, Elektrik ve Elektronik Mühendisliği, Makine Öğrenimi, Dysphonia, Feature Extraction And Selection, Computer Engineering and Computer Science and Control, Parkinson hastalığı, disfoni, müzikal özellik, makine öğrenimi, ses analizi, öznitelik çıkarımı ve seçimi, sınıflandırma, Parkinson’s Disease, Machine Learning, Voice Analysis, Nöroloji, Neurology, Parkinson hastalığı, Musical Feature, Ses Analizi, Müzikal Özellik, Sınıflandırma, Classificatio, Electrical and Electronics Engineering, Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrol
Abstract

Parkinson hastalığı ülkemizde ve dünyada Alzheimer hastalığından sonra en yaygın görülen, sinir sistemini etkileyen motor becerileri (yazma, denge, yutkunma, vb.), konuşma zorluğu, ses kısıklığı, düşünme ve davranış fonksiyonların kısmen veya tamamen kaybolmasına neden olan ve gündelik yaşantıyı olumsuz yönde etkileyen nörodejeneratif (sinir sisteminde geri dönüşü olmayan) hastalıklardan biridir. Hastalığın kesin bir tedavisi olmamakla birlikte hastaların gündelik yaşantılarını etkileyen semptomları azaltmayı sağlayan ilaç tedavisi uygulanmaktadır. Konuşma ve ses bozuklukları, Parkinson hastalığı sürecinin erken teşhisinde başvurulan en belirleyici semptomlardır. Bu amaçla bu çalışmada sesin müzikal özelliklerinin Parkinson hastalığının teşhisindeki etkisi incelenmiştir. Bu doğrultuda, Parkinson hastası ve sağlıklı bireylerden alınan ham ses kayıtlarından sesin ritim, ton, tını, perde ve dinamiklik gibi özellikleri çıkartılarak yapay öğrenme algoritmaları ile hangi özelliklerin hastalığı teşhis etmede daha başarılı olduğu araştırılmıştır.Bu tez çalışması, sesin müzikal özelliklerinin, Parkinson hastalığının teşhisinde kullanıldığı literatürdeki ilk örnek çalışma olacaktır. Parkinson's disease becomes a prevalent neurodegenerative disorder comes after Alzheimer's diseases in our country as well as all around the world. It affects the nervous system motor skills (writing, balance, swallowing, etc.), speech and voice production difficulties, mental and behavioral functions partially or completely. While not being a definitive treatment of this disease, drug therapy is being applied to reduce the symptoms affecting the daily lives of patients.Speech and voice disorders are one of the most significative symptoms of early diagnosis of the Parkinson's disease process. For this purpose, in this study, the effect of musical features on the diagnosis of Parkinson's disease was investigated. The rhythm, tone, timbre, pitch and dynamics features of the voice were extracted from the raw voice recordings of patients with Parkinson's disease and healthy individuals and the machine learning algorithms were used to determine which feature is more successful in diagnosing the disease.This thesis study will be the first case study in the literature in which the musical properties of sound are used in the diagnosis of Parkinson's disease. 96

Published
2018

Catalog

Books, media, physical & digital resources
See catalog results