- Anomaly Detection Techniques and Applications
- Recommender Systems and Techniques
- Network Security and Intrusion Detection
- Time Series Analysis and Forecasting
- Data Mining Algorithms and Applications
- Internet Traffic Analysis and Secure E-voting
- Music Education and Analysis
- Advanced Database Systems and Queries
- Spam and Phishing Detection
- Visual Attention and Saliency Detection
- Cryptography and Data Security
- Virtual Reality Applications and Impacts
- COVID-19 diagnosis using AI
- Blockchain Technology Applications and Security
- Personality Traits and Psychology
- AI in cancer detection
- Attention Deficit Hyperactivity Disorder
- Expert finding and Q&A systems
- Video Analysis and Summarization
- Olfactory and Sensory Function Studies
- Privacy-Preserving Technologies in Data
- Advanced Authentication Protocols Security
- Multidisciplinary Science and Engineering Research
- Mental Health via Writing
- Ethics and Social Impacts of AI
Gazi University
2009-2024
Gazi Hastanesi
2013-2022
Middle East Technical University
2007-2010
In the field of unmanned systems, combination artificial intelligence with self-operating functionalities is becoming increasingly important. This study introduces a new method for autonomously detecting humans in indoor environments using aerial vehicles, utilizing advanced techniques deep learning framework commonly known as “You Only Look Once” (YOLO). The key contribution this research development model (YOLO-IHD), specifically designed human detection drones. created unique dataset...
There is a need to obtain more information about target audiences in many areas such as law enforcement agencies, institutions, human resources, and advertising agencies. In this context, addition the provided by individuals, their personal characteristics are also important. particular, predictability of personality traits individuals seen major parameter making decisions individuals. Textual media data social media, where people produce most data, can provide clues people's lives,...
Reviews and reputation scores of sellers play an important role in decision-making process potential buyers e-commerce system. A trustworthy reliable system is a crucial component the ecosystem, as rely on it to make informed decisions. In this work, we propose privacy-preserving decentralized designed include countermeasures against some known attacks. Our model built two permissioned blockchains, namely Hyperledger Indy Fabric. provides infrastructure for implementing verifiable...
Günümüz gelişen teknolojisiyle birlikte yapay zekâ kullanımı artmıştır. Bu durumun çoğunlukla faydaları üzerine konuşulsa da kişisel veri mahremiyetine ve güvenliğine olumsuz etkisi göz ardı edilmemelidir. Çünkü için ham madde olan veriler, kişilerin mahremiyet haklarına aykırı durumlara neden olabilmektedir. doğrultuda ilgili çalışmada; genel olarak zekânın mahremiyeti açısından oluşturduğu risklere, bu risklerin giderilmesi önerilen bazı yöntemlere yöntemlerden biri federe öğrenme metodu...
The development of Web 2.0 and the rapid growth available data have led to systems, such as recommendation systems (RSs), that can handle information overload. However, RS performance is severely limited by sparsity cold-start problems. Thus, this paper aims alleviate these To realize objective, a new model proposed integrating three sources information: user-item matrix, explicit implicit relationships. core strategy study use multi-step resource allocation (MSRA) method identify hidden...
Web applications are often exposed to attacks because of the critical information and valuable assets they host. In this study, Bi-LSTM based web application security models were developed in order detect classify them into binary or multiple classes using HTTP requests. A novel data augmentation technique on self-adapting noise adding method (DA-SANA) was developed. The DA-SANA solves low sensitivity problem caused by imbalanced complex structure multi-class classification attack detection....
Abstract In this study, we examined the mechanisms that control attention in natural scenes. We asked whether familiarity with environment makes subjects more sensitive to changes or novel events scene. Previous investigation of issue has been based on viewing 2-D images simple objects scenes, a situation does not accurately reflect challenges vision. found significantly increased time spent fixating regions scene where change had occurred. Together previous work (Brockmole & Henderson,...
Data mining is an important technique used in many fields with the purpose of acquiring valuable information from big data.This study aims to reveal relations between attributes independent criminal records.The NIBRS database, which includes records USA that are recorded 2013, this study.The association rules created by Apriori algorithm have been extract relationships features experimental results show useful for analysis.This reveals different and allows authorities establish new old incidents.
: Attention-Deficit Hyperactivity Disorder (ADHD) is a prevalent neurodevelopmental disorder characterized by inattention, hyperactivity, and impulsivity. Traditional diagnostic methods, which depend on subjective assessments, often lack precision. This study evaluates the validity reliability of newly developed tool, Distractor-Embedded Auditory Continuous Performance Test (da-CPT), integrates auditory stimuli with distractors to enhance clinical utility ADHD diagnosis.
Recommendation Systems (RSs) are used to provide users useful and effective suggestions. Effectiveness of RSs is depend on the quality In this study, a new RS based decision tree (DT) using implicit relevance feedback have been developed for movies. User behavior as implied modeled by clickstreams. The DT constructed Gini algorithm. experimental results show that method successful
Network Intrusion Detection Systems (IDSs) have been used to increase the level of network security for many years. The main purpose such systems is detect and block malicious activity in traffic. Researchers improving performance IDS technology decades by applying various machine-learning techniques. From perspective academia, obtaining a quality dataset (i.e. sufficient amount captured packets that contain both normal traffic) support machine learning approaches has always challenge. There...
Akan veri kümeleme, teknolojik gelişmelere paralel olarak miktarının inanılmaz boyutlara ulaştığı gümünüzün popüler konularından biridir. kümeleme yaklaşımlarında karşılaşılan en önemli problemler çoğu yaklaşımın çevrimiçi ve çevrimdışı evreden oluşması, küme sayısını tanımlama veya bu sayıya bir sınır koyma zorunluluğu, doğru yarıçap değerini belirlemede yaşanan önerilen modellerin kendisini gelen yeni verilere adapte etmesinde (concept evolution) problemlerdir. Bu problemlerin yanında,...
Recently, Recommender Systems (RSs) have attracted many researchers whose goal is to improve the performance of prediction accuracy recommendation systems by alleviating RSs drawbacks. The most common limitations are sparsity and cold-start problem. This article proposes two models mitigate effects these limitations. proposed exploit five sources information: rating information, which involves sources, namely explicit implicit, can be extracted via users’ ratings, types social relations:...
Recommendation systems (RSs) are tools for interacting with large and complex information spaces. They provide a personalized view of such spaces, prioritizing items likely to be interest the user. The main objective RSs is tool up users desired that meet their preferences. A major problem in called: “cold-start”; it potential called so computer-based which comprises degree automated data modeling. Particularly, concerns issue system cannot draw any inferences nor have yet gathered...
In this work, effects of stereoscopic view on object recognition and navigation performance the participants are examined in an indoor Desktop Virtual Reality Environment, which is a two-floor virtual museum having different floor plans 3D models inside. This environment used two experimental settings: 1) color-multiplex viewing provided by colored eye-wear, 2) regular 2D viewing. After experiment, filled questionnaire that inquires their feeling presence, tendency to be immersed...
Günümüz teknolojisinin gelişmesine paralel olarak bilgisayar ortamına aktarılmış olan veri miktarı inanılmaz boyutlara ulaşmış ve gün geçtikçe de artmaktadır. Bu nedenle veriyi işleme yöntemleri değişmektedir. Klasik kümeleme yaklaşımlarında statiktir. Oysa günümüz teknolojisinde, verinin çok hızlı olduğu dünyada artık akarken kümeleyecek, kullanıcıya istediği zaman sonuç verebilecek uygulamalara ihtiyaç vardır. anlamda ihtiyacı karşılayan akan yaklaşımlarına talep Çünkü yaklaşımları bir...
Solunum sistemine etki eden ve ileri vakalarda ölüme neden olan korona virüs salgını yaklaşık iki yıldır devam etmektedir. Her ülkenin salgın ile mücadele yöntemi farklı olmasına rağmen ortak izlenen metot ise hastalığın tespiti izolasyonudur. Tespit izolasyon için en kritik adım COVID-19 tanısının doğru hızlı konulmasıdır. Akciğer X-Ray görüntülerinde virüse özgü bulgulara rastlanılması, bu verilerin hastalık teşhisinde kullanılabileceğini göstermektedir. İlgili çalışmanın amacı, makine...
Universite web sitelerinin kullanilabilirligi kurum imaji ve kullanim kalitesi icin vazgecilmez bir unsurdur. Bu calismada Abant Izzet Baysal Universitesi (AIBU) sitesinin ogrencilerin kullanimi acisindan kullanilabilirliginin tespit edilmesi amaclanmistir. Arastirmada veri toplama araci olarak 20 sorudan olusan Website Analysis and Measurement Inventory anketi kullanilmis egitim fakultesinin degisik programlarinda okuyan 169 ogrenciye uygulanmistir. Veri analizinde betimlemeli istatistik...
Hamilelik döneminde kadınlar, oluşabilecek komplikasyonlar açısından yüksek risk altında bulunur. Bu riskler birçok zaman düşük ve ölümle sonuçlanmaktadır. yüzden de hamilelik boyunca hamilelikten önce kadın sağlığı hem anne çocuk için önemli rol oynamaktadır. Doğumdan sonra, bebeğin sağlık takibi, riskleri en aza indirmek önemlidir. kapsamda, derin öğrenmeye dayalı modeller, görüntüler, kayıtları verileri kullanılarak komplikasyonların tahminini kolaylaştırmak gibi çok çeşitli çalışmalar...