Hacer Karacan

Prof. Dr. Hacer Karacan

orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 January 2024 in Sensors
Verified
Journal Article
Open access
PDF file
Gokhan KucukayanGokhan Kucukayan
Gokhan Kucukayan
HKHacer Karacan
Hacer Karacan
In the field of unmanned systems, the combination of artificial intelligence with self-operating functionalities is becoming increasingly important. This study introduces a new method for autonomously detecting humans in indoor environments using unmanned aerial vehicles, utilizing the advanced techniques of a deep learning framework commonly known as “You Only Look Once” (YOLO). The key contribution of this research is the development of a new model (YOLO-IHD), specifically designed for human detection in indoor using drones. This model is created using a unique dataset gathered from aerial vehicle footage in various indoor environments. It significantly improves the accuracy of detecting people in these complex environments. The model achieves a notable advancement in autonomous monitoring and search-and-rescue operations, highlighting its importance for tasks that require precise human detection. The improved performance of the new model is due to its optimized convolutional layers and an attention mechanism that process complex visual data from indoor environments. This results in more dependable operation in critical situations like disaster response and indoor rescue missions. Moreover, when combined with an accelerating processing library, the model shows enhanced real-time detection capabilities and operates effectively in a real-world environment with a custom designed indoor drone. This research lays the groundwork for future enhancements designed to significantly increase the model’s accuracy and the reliability of indoor human detection in real-time drone applications.

10 May 2023 in IEEE Access
Verified
Journal Article
Open access
ÖDÖmer Doğan
Ömer Doğan
HKHacer Karacan
Hacer Karacan
Reviews and reputation scores of sellers play an important role in decision-making process of potential buyers in an e-commerce system. A trustworthy and reliable reputation system is a crucial component in the e-commerce ecosystem, as buyers rely on it to make informed decisions. In this work, we propose a privacy-preserving decentralized reputation system designed to include countermeasures against some known attacks. Our model is built on two permissioned blockchains, namely Hyperledger Indy and Hyperledger Fabric. Hyperledger Indy provides an infrastructure for implementing verifiable credentials with Zero Knowledge Proof support, which is essential for privacy preservation, while Hyperledger Fabric is a robust platform for implementing smart contracts. One of the key advantages of the proposed approach is the use of verifiable credentials for digital identities of sellers, feedback tokens issued to buyers after performing an e-commerce transaction and discount tokens issued to buyers after feedback submission. This helps to ensure that the feedback and identity information is authentic and tamper-proof, reducing the likelihood of identity-related attacks. Additionally, the collection of feedbacks and application of business rules are implemented as smart contracts on Hyperledger Fabric blockchain. This provides a secure and transparent mechanism for processing feedback, reducing the likelihood of unfair feedbacks. Overall, the proposed approach presents a robust reputation system that can help reduce identity-related attacks and unfair feedbacks. The privacy-preserving nature of the system ensures that sensitive information is protected while still enabling the verification of digital identities. The use of feedback and discount tokens incentivizes buyers to provide accurate and honest feedback, which can help reduce unfair feedbacks and identity-related attacks. Finally, the use of smart contracts ensures transparency and immutability, which enhances the overall reliability of the system.

8 November 2021 in IEEE Access
Verified
Journal Article
Open access
HKHacer Karacan
Hacer Karacan
MSMehmet Sevri
Mehmet Sevri
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 to detect web attacks and classify them into binary or multiple classes using HTTP requests. A novel data augmentation technique based on the self-adapting noise adding method (DA-SANA) was developed. The DA-SANA method solves the low sensitivity problem caused by imbalanced data and the complex structure of multi-class classification in web attack detection. Experimental evaluations are carried out in detail using two benchmark web security datasets and a newly created dataset within the scope of the study. The achieved worst case detection rates are 98.34% and 93.91% for binary-class and multi-class classifications, respectively. The proposed DA-SANA technique provides an average of 6.52% improvement in multi-class classification for two datasets. These results revealed that the best classification performance values were achieved when compared with previous studies.

31 October 2022 in Bilişim Teknolojileri Dergisi
Verified
Journal Article
Closed access
PDF file
FBFatma Başkaya
Fatma Başkaya
HKHacer Karacan
Hacer Karacan
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 yapay zekâ için ham madde olan veriler, kişilerin mahremiyet haklarına aykırı durumlara neden olabilmektedir. Bu doğrultuda ilgili çalışmada; genel olarak yapay zekânın kişisel veri mahremiyeti açısından oluşturduğu risklere, bu risklerin giderilmesi için önerilen bazı yöntemlere ve bu yöntemlerden biri olan federe öğrenme metodu ile ilgili detaylara yer verilmiştir. Ayrıca günümüzde çeşitli sektörlere ait uygulamalarda sıklıkla kullanılan yapay zekâ ürünü, sohbet robotları (chatbot) ile ilgili bir inceleme ve anket çalışması yapılmıştır. Bu anlamda; sohbet robotlarının kullanımı ve yapısının kişisel veri güvenliğine uygunluğu ile ilgili detaylara ve önerilere yer verilirken anket çalışmasında ise kişilere yöneltilen dört adet soru ile kişilerin, sohbet robotu kullanma boyutunu ve sohbet robotu kullanımının kişisel verilere etkisine yönelik farkındalığını ölçmek amaçlanmıştır. Anket sonuçları, sohbet robotlarının en fazla bankacılık işlemleri için kullanıldığını ve bireylerin %62,1’inin ise bu servislerin kişisel verileri kaydedip işleyebileceğini bilmediğini göstermiştir.

1 September 2016 in Konya Journal of Engineering Sciences
Verified
Journal Article
Open access
PDF file
CKCoşkun KARACA
Coşkun KARACA
HKHacer Karacan
Hacer Karacan
ÇOKLU REGRESYON METODUYLA ELEKTRİK TÜKETİM TALEBİNİ ETKİLEYEN FAKTÖRLERİN İNCELENMESİ

27 October 2024 in Journal of Clinical Medicine
Verified
Journal Article
Open access
PDF file
AÖAhmet Özaslan
Ahmet Özaslan
MSMehmet Sevri
Mehmet Sevri
EIElvan İşeri
Elvan İşeri
BKBarış Karacan
Barış Karacan
MCMehmet Cengiz
Mehmet Cengiz
EGEsra Güney
Esra Güney
Background/Objectives: 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 and reliability of a newly developed diagnostic tool, the Distractor-Embedded Auditory Continuous Performance Test (da-CPT), which integrates auditory stimuli with distractors to enhance the clinical utility of ADHD diagnosis. Methods: The study included 160 children aged 6–12 years, comprising 80 with a confirmed ADHD diagnosis and 80 controls. All participants completed the da-CPT, a web-based tool designed to assess inattention, hyperactivity, impulsivity, and timing via an auditory-based task. To validate the da-CPT, participants also completed the Conners’ Parent Rating Scale—Revised Short Form (CPRS-R) and either the MOXO or IVA-2 tests. Data were analyzed using ROC curves and statistical correlations to assess sensitivity, specificity, and overall diagnostic accuracy. Results: The da-CPT demonstrated high diagnostic accuracy, with a sensitivity of 91.25% and specificity of 83.75%. ROC analysis indicated that the inattention index had the highest discriminatory power (AUC = 0.881), followed by timing, impulsivity, and hyperactivity (all p < 0.01). Furthermore, the da-CPT scores were strongly correlated with ADHD severity (p < 0.01). Conclusions: This study confirms that the da-CPT is a valid and reliable tool for diagnosing ADHD in children aged 6–12. By incorporating auditory stimuli and distractors, the tool offers a more ecologically valid assessment of ADHD symptoms in clinical settings, improving diagnostic precision and utility.