Mühendislik Fakültesi / Faculty of Engineering
Permanent URI for this collectionhttps://hdl.handle.net/11727/1401
Browse
4 results
Search Results
Item Detection of Visual Impairment From Retinal Fundus Images with Deep Learning(2022) Olcer, Didem; Erdas, Cagatay BerkeItem Prediction of Frailty Grade Using Machine Learning Models(2022) Erdas, Cagatay Berke; Olcer, DidemNowadays, frailty is becoming a major issue for the aging population. Frailty grading is important for patient quality of life because it is a geriatric syndrome of decreased physiological reserve that leads to increased susceptibility to physical stress factors and susceptibility to cardiovascular diseases. In this context, this study seeks a solution to the fragility rating regression problem with K Nearest Neighbor, Decision Tree, Random Forest, Extra Trees and CatBoost models using time domain features extracted from the triaxial accelerometer signals collected during the TUG test. Moreover, estimating the grade of frailty involved in addition to diagnosing people with the disease will provide physicians with more detailed information about the patient and allow accurate and effective treatment/supportive treatment.Item A Machine Learning Based Approach to Detect Survival of Heart Failure Patients(2020) Erdas, Cagatay Berke; Olcer, DidemOne of the diseases with high prevalence among the consequences of cardiovascular diseases is heart failure. Heart failure is a condition in which the muscles in the heart wall become faded and dilated, limiting the heart's ability to pump blood. As time passes, the heart cannot meet the proper blood requirement in the body, and as a result, the person has difficulty breathing. As the human age increases, the incidence of heart failure gradually increases, and the rate of mortality due to heart failure also increases. In this context, close monitoring of people suffering from this disease will significantly increase the survival rate. In this study, a machine learning-based system is proposed to predict the mortality-survival status of patients with heart failure. Thus, by identifying people with mortality risk, the survival probability of the patients may increase with more effective and close follow-up.Item A Deep Learning Based Approach to Detect Neurodegenerative Diseases(2020) Erdas, Cagatay Berke; Sumer, Emre; AGA-5711-2022Studies conducted by the World Health Organization (WHO) show that more than a billion people worldwide suffer from neurological disorders and the lack of effective diagnostic procedures affects treatment. Characterizing specific motor symptoms to facilitate their diagnosis can he useful in monitoring disease progression and effective treatment planning. Classification of highly prevalent neurodegenerative diseases (NDD) such as Parkinson's disease (PH), Amyotrophic Lateral Sclerosis (ALS), and Huntington's disease (HH) is of clinical importance, One of the methods used in the literature to detect these neurodegenerative diseases is gait analysis-based classification. in this study, 12 different features fed a unidimensional Convolutional Neural Network (CNN) deep learning algorithm-based model, and aims to detect PD, HD, and ALS diseases was studied. The unidimensional CNN deep learning model fed with 12 features achieved 78,92%, 84,39% and 92,09% classification accuracy for control against HH, control. against PH, and control detection problems against ALS. Again, the relevant classifier produced 84,75% accuracy with the approach developed to separate all neurodegenerative disease specimens (NDD) under a single label as a class, and to distinguish these diseases against the current control.