Department of Software Engineering

Permanent URI for this collection

http://hdl.handle.net/20.500.11905/1222

Browse

Browsing Department of Software Engineering by Author "Çağıltay, Nergiz Ercil"

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    A SYSTEMATIC MAPPING STUDY ON THE USE OF EYE-TRACKING IN PROGRAM UNDERSTANDABILITY
    (2022-01-10) ATIED, SHUKRULLAH; Çağıltay, Nergiz Ercil; Topalli, Damla
    Eye-tracking technology is used to get insight into a person’s vision and determine where they are looking and gather data on their visual behavior. Researchers have been collecting eye movement data to analyses and comprehend various tasks in Software Engineering (SE) by using eye-tracker technology. However, there are very limited studies analyzing the use of eye-tracking technology in the field of SE and providing a general picture from this perspective. Accordingly, in this thesis study, by undertaking a Systematic Mapping (SM) study, it is aimed to bring all evidence together and give an overview on the use of eye-tracking in SE, specifically for program comprehension. 121 related articles were selected after carefully reviewing and excluding unrelated studies. The result shows that the use of eye-tracking in SE is increased in recent years, and different SE activities were studied. Moreover, four different factors are influential in program comprehension: code elements and entities, tools, developer’s background, and eye movement and reading behaviors. These findings may help the developers to adopt the founded influential factors to help them in program understandability.
  • No Thumbnail Available
    Item
    MONITORING THROUGH EYE-MOVEMENT DATA IN CONTEXT AWARE ADAPTIVE SOFTWARE SYSTEMS: A CASE STUDY ON ENDO NEUROSURGERY TRAINING PROGRAM
    (2022-02-25) Menekşe Dalveren, Gonca Gökçe; Çağıltay, Nergiz Ercil
    Today, modern software is becoming very complex which needs to be compatible with constant changes in the environment. They required to support autonomic behaviors by monitoring the relevant phenomena of the environment and analyzing the collected data to better understand the possible consequences of the changes in the environment. In other words, by monitoring the relevant phenomena of the environment and analyzing the collected data to better understand the possible consequences of the changes in the environment, these type of software adapt themselves to the environment. Context defined as anything that can be observed by the software system including end-user, computing, and primary features of identity, location, time, and physical conditions at runtime. Hence, Context aware adaptive software (CAASS) architecture can be implemented at different levels for different purposes by monitoring a wide range of data. However, currently there is no conceptual framework showing the level and scope of the adaptation performed by these systems. Accordingly, in this study, first the related literature is examined to investigate the main dimensions of CAASS. Afterwards, a conceptual framework is proposed to address the level and scope of adaptation performed by a specific CAASS. The proposed framework has three dimensions namely the definition of the context of the adaptation, definition of the event that is planned to be adapted and finally the plan showing how the adaptation aimed to be performed. Additionally, a case study is also conducted for endo-neurosurgery education programs through the proposed conceptual framework. Results showed that by monitoring eye-movement events of the surgeons, their skill levels can be estimated with a high precision (91.3%). Accordingly, for this specific case, it is shown that, through the eye-movement events of surgeons, the content can be adapted according to the behaviors of the surgeons. The results of this study show evidences that, by regularly assessing their skill levels and evaluating the difficulty levels of each computer-based simulation scenario through eye movement events of the trainees, order of these scenarios in the curriculum can be adapted to the user skill levels and behaviors under different hand conditions. This will help to create a specific curriculum for each trainee that is adapted dynamically to their skill and knowledge. This study has two main contributions. First it proposes a conceptual model that can be used to evaluate the scope and the level of adaptation for CAASS. This information may help the researchers and the developers to better evaluate and compare the CAASS. The second contribution of this thesis study is the implementation of the proposed model on endo-neurosurgery domain. The field of endo-neurosurgery education programs have several problems. The main problem of these programs is the skill-based training opportunities. As the training and skill development had to be provided in the operating room, there are several drawbacks of these education programs such as the ethical considerations from the patients’ perspective, limited time and cases as well as the risk of patient safety. Currently, there are not many alternative training opportunities for the surgical training programs. As the skill improvement is very critical for these programs, the individual skill-based training opportunities are required. Even there are some examples of computer-based simulations for supporting surgical training programs, there are very limited examples of curriculum integrated models. Additionally, there is no instructional model of CAASS for the surgical education programs especially in the endo-neurosurgery education programs. We believe that, because of its very nature, CAASS approach may provide several benefits for the endo-neurosurgery education programs. However, as the process of creating CAASS for the field of endo-neurosurgery education programs is a very complex, in this thesis study a level of CAASS conceptual model is proposed. The findings of this thesis study is aimed to help future studies to better build CAASS for the field of endo-neurosurgery education programs and to better integrate these systems into the current educational programs.
  • No Thumbnail Available
    Item
    USE OF CLASSIFICATION ALGORITHMS IN DETERMINING SURGICAL SKILL LEVELS THROUGH SURGEONS’ HAND MOVEMENT BEHAVIORS
    (2022-02-21) Topallı, Damla; Çağıltay, Nergiz Ercil
    Today, endoscopic surgeries have become an alternative for open procedures whenever possible. In this technique, the surgeon performs the operation by using a camera and light source, called „endoscope‟, and special operational tools in order to operate through small entry points. For such types of operations, surgeons are required to gain several skills, whose development needs hands-on practice in them which is a challenge in surgical education programs. Several technology-enhanced training environments have been developed to improve current surgical education programs. However, in order to better integrate these technologies into the traditional methods, it is critical to understand the skill levels and prepare appropriate content according to the trainees‟ requirements. In other words, the trainees‟ skill levels need to be assessed regularly for better preparing the content and the sequence of the training program according to their individual requirements. The current skill level assessment techniques are mainly based on expert observations which are criticized as expensive and subjective. In this respect, the present study aims to evaluate the surgical skills objectively by using hand movement metrics through computer-based simulation software in Neurosurgery. This study is conducted with 28 surgical residents who were considered as intermediate or novice in their education. The evaluations are mainly concentrated on the hand movements of the trainees on computer simulated surgical training software. Accordingly, first an estimation of skill levels of intermediate and novice surgeons by using classification methods through performance metrics is performed. Secondly, velocity-based hand metrics are calculated using the hand movement data for classifying intermediate and novice surgeons. After that, by adapting BIT algorithm, which is an open source eye-event classification algorithm, to the hand movement data, new hand movement event metrics are proposed. Through these metrics, the participants‟ eye and hand movement events are analyzed. Finally, the results of the classification by using these newly introduced metrics are presented. As a conclusion, this thesis study attempts to better classify the intermediate and novice surgical residents‟ skill levels through their hand-movement events. The results are very promising showing that the proposed metrics potentially improve the accuracy of the classification. The researchers believe that, in the future by using the performance metrics together with hand- and eye- movement events metrics in a combined manner, the level of the accuracy may even be improved.