Person:
GÜNAYDIN, ÖZGE

Profile Picture

Email Address

Birth Date

Research Projects

Organizational Units

Job Title

Arş.Gör.

Last Name

GÜNAYDIN

First Name

ÖZGE

Name

Filters

20192
Reset filters

Settings

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    PublicationOpen Access
    Implementation of a simulated environment for data acquisition to monitor drivers' stress levels
    (2019-04) GÜNAYDIN, ÖZGE; Arslan, R.B.
    Most of the research on transportation safety aims to reduce the damage of accidents at the moment they occur or after they happen. Passive safety systems help to reduce the effects of the accidents, while active safety systems serve to minimize the risk of collision. The majority of accidents are related to the mental workload of the driver. In low levels of workload , fatigue and, in high levels of it, stress lead to driver errors which are the number one reason for accidents. In such cases the driver who can still perform routine driving tasks without problems is unable to cope with unattended or extraordinary driving conditions. In literature, there are several studies that propose monitoring of drivers physical and cognitive status and helping them by alerts or stimuli to avoid accidents in critical conditions. Nevertheless, the selection of objective parameters from these measurements is an ongoing problem. Another consideration should be the unobtrusiveness and ease of use for such systems. This study targets a simulated driving environment based on UNITY game engine, where a driver's status can be monitored multimodally. It is shown that a variety of physiological parameters such as changes in skin resistance and heart rate can be recorded under adjustable difficulty driving conditions. This provides a flexible toolkit which enables the analysis of the relation between the driver's stress level and his/her driving ability from different perspectives and without being physically on the road traffic.
  • No Thumbnail Available
    PublicationMetadata only
    Comparison of lung cancer detection algorithms
    (International Scientific Meeting on Electrical-Electronics and Biomedical Engineering and Computer Science (EBBT), 2019) GÜNAY, MELİKE; GÜNAYDIN, ÖZGE; ŞENGEL, ÖZNUR
    Lung cancer is a kind of difficult to diagnose and dangerous cancer. It commonly causes death both men and women so fast accurate analysis of nodules is more important for treatment. Various methods have been used for detecting cancer in early stages. In this paper, machine learning methods compared while detect lung cancer nodule. We applied Principal Component Analysis, K-Nearest Neighbors, Support Vector Machines, Naive Bayes, Decision Trees and Artificial Neural Networks machine learning methods to detect anomaly. We compared all methods both after preprocessing and without preprocessing. The experimental results show that Artificial Neural Networks gives the best result with 82,43% accuracy after image processing and Decision Tree gives the best result with 93,24% accuracy without image processing.