Hasan Dağ

Dağ, Hasan

Name Variants

D., Hasan
Dağ, HASAN
DAĞ, HASAN
Hasan, Dag
HASAN DAĞ
Hasan DAĞ
DAĞ, Hasan
Daǧ H.
Hasan Dağ
Dağ, H.
Dağ,H.
D.,Hasan
Dağ, Hasan
Dag H.
Dag,H.
Dağ H.
Dag,Hasan
Dag, Hasan
H. Dağ

Job Title

Prof. Dr.

Email Address

hasan.dag@khas.edu.tr

ORCID ID

0000-0001-6252-1870

Scopus Author ID

6507328166

Full item page

Scholarly Output

66

Articles

16

Citation Count

238

Supervised Theses

15 Scholarly Output Search Results

Now showing 1 - 10 of 66

Audio detection using machine learning & transfer learning models
(Kadir Has Üniversitesi, 2021) Dağ, Hasan; Dağ, Hasan
In this paper, using datasets ESC-50 & ESC-10 of environmental sounds, machine learning algorithms, and feature extraction methods are used to develop recognition performance. K-NN, SVM, Random Forest are used for comparing the recognition results. The different feature extraction methods in the literature are used to get more meaningful attributes from these datasets and obtain a higher accuracy rate. This approach shows that SVM algorithm has a significantly good result with accuracy scores. The best accuracy scores obtained by classic machine learning algorithms are %42,15 for ESC-50 and %77,7 for ESC-10. In addition to this, the experiments have been done with a pre-trained ResNet neural network as a backbone, which achieves successful results despite the machine learning models. In this study, a higher accuracy rate is achieved from baseline machine learning algorithms in literature and using transfer learning with pre-trained Resnet backbones to reach some state of art results. The accuracy scores are %68,95 for ESC-50 and %87,25 for ESC-10.
Power consumption estimation using in-memory database computation
(Kadir Has Üniversitesi, 2016) Dağ, Hasan; Dağ, Hasan
Son elektrik tüketimini tahmin etmek amacıyla, hız ve güvenilirliği artırmak gerekir. hız ile ilgili olarak, birçok kat daha hızlı HDD den veri manipüle sağlar en iyi çözümdür IN-Bellek veritabanını kullanır. Bu amaçla, biz "en iyi" açık kaynak In-Memory veritabanı gibi YCSB gibi standart bir kriter kullanarak seçmeniz gerekir. güvenilirlik için, makine öğrenimi algoritmalarını kullanmaktadır. Model performans ve doğruluk verilerine her zaman bağlı olarak değişebilir bu yana, birçok algoritmalar test etmek ve en iyisini seçmek. Bu tezde, Python ve Aerospike bellek veritabanında öğrenme makinesi kullanılarak elektrik tüketimini tahmin etmek Londra Hanehalkı SmartMeter Enerji Tüketimi Verileri kullanın. Çalışma veri seti için en iyi algoritma Torbalama olduğunu göstermektedir. Biz de Ar-kare her zaman en iyi algoritma seçmek için iyi bir test olmadığını kanıtlamak. Son olarak, biz belirli bir zamanda tüketimini tahmin etmek deneyimli olmayan kullanıcılar tarafından kullanılabilir Python kullanarak makine öğrenimi, bir grafiksel kullanıcı arabirimi öneriyoruz
Öykü anlatıcısı olarak karakter : tek kişilik bir destan uyarlamasında anlatıcı
(Kadir Has Üniversitesi, 2017) Dağ, Hasan; Dağ, Hasan
in credit scoring statistical methods like logistic regression have been successfully used for years. in the last two decades several data mining algorithms have gained popularity and proved themselves to be useful in credit scoring. Most recent studies indicate that data mining methods are indeed good predictors of default. Additionally ensemble models which combine single models have even better predictive capability. However in most studies the rationale behind data transformation steps and selection criteria of single models while building ensemble models are unclear. in this study it is aimed to construct a fully automated comprehensive and dynamic system which gives the ability to a credit analyst to make credit decisions without any human interaction solely based on the data set. With this system it is hoped not to miss any valuable data transformation step and it is assumed that each built-in model in RapidMiner is a possible candidate to be the best predictor. To this end a model comparison engine has been designed in RapidMiner. This engine conducts almost every kind of data transformation on the data set and gives the opportunity to observe the effects of data transformations. The engine also trains every possible model on every possible transformed data. Therefore the analyst can easily compare the performances of models. As the final phase it is aimed to develop an objective method to select successful single models to build more successful ensemble models without any human interaction. However research in this direction has not been able to achieve an objective method. Hence to build ensemble models six of the most successful single models are chosen manually and every possible combination of these models are fed to another engine: ensemble model building engine. This engine tries every combination of single models in ensemble modelling and provides the credit analyst with the ability to find the best possible combination of single models and finally to reach the ultimate most successful model that can later be used in predicting thecreditworthiness of counterparties.
Citation Count: 1
Sparsity Preserving Computation for Spectral Projectors
(Amer Inst Physics, 2011) Dağ, Hasan; Dağ, Hasan
Several areas of applications such as model order reduction preconditioner design and eigenvalue problems for spectral projectors can be found in the literature. In this paper a fast and sparsity preserving approach for computing the spectral projectors is proposed. The suggested approach can be used in both Newton iteration and integral representation based methods. A comparison of the original and the suggested approaches in terms of computation time sparsity preservation and accuracy is presented in this paper.
Citation Count: 0
Konutların Günlük Elektrik Güç Tüketimi Tahmini İçin Uygun Model Seçimi
(Fırat Üniv. Fen Bilimleri Enst., 2018) Dağ, Hasan; Dağ, Hasan
Zamana bağlı değişim gösteren olayların modellenmesi zorlu bir veri analizi problemidir. Bu olaylardan biri olan elektrik güç tüketiminde ise veriden mevsimsel etki ve tatil günleri gibi örüntülerin öğrenilerek bir tüketim tahmin modelinin geliştirilebilmesi için klasik makine öğrenmesi ve derin öğrenme yöntemlerinden yararlanılmaktadır. Bu çalışmada, İngiltere’nin Londra şehrindeki belirli bir bölgede 30 farklı eve ait yaklaşık 3 yıllık elektrik güç tüketimi veri kümesi kullanılarak uygun bir kısa vadeli tüketim tahmin modelinin makine öğrenmesi algoritmaları ile bulunması amaçlanmıştır.
Citation Count: 0
Parallel Contingency Analysis Using Differential Evolution Based Solution For Branch Outage Problem
(IEEE, 2010) Dağ, Hasan; Ceylan, Oğuzhan; Özdemir, Aydoğan
Contingency analysis is one of the most fundamental work an electricity management center operator has to perform regularly. If both bus voltage magnitudes and reactive power flowing on the branches during any type of outages are within the acceptable limits the system is called secure. In this paper we solve the contingency problem using a recently developed local constrained optimization based branch outage problem. The optimization problem resulted from the formulation of branch outage is solved by differential evolution method. Using Matlab's parallel computing toolbox contingency analysis for IEEE 300 test system is performed and the results are presented. The study shows that it is straight forward to implement contingency analysis on the Matlab's parallel environment and obtain near linear speedups.
Federated anomaly detection for log-based defense systems
(Kadir Has Üniversitesi, 2022) ÜNAL, UĞUR; Dağ, Hasan; DAĞ, HASAN
The adaptation of Industry 4.0 and IoT creates a vast network which opens up various new vulnerabilities to systems. Increasing number of cyber attacks becomes more sophisticated which impedes functionality of enterprises and critical infrastructures. Malfunctioning of the services of these systems can cause catastrophic results considering wealth and well-being of a society. Organizations need an intelligent defense system which is adaptable to newer threats to create rapid solutions. Anomaly detection is widely adopted protection step and is significant for ensuring a system security. Logs, which are accepted sources universally, are utilized in debugging, system health monitoring, user authorization and access control systems and intrusion detection systems. Recent developments in Deep Learning (DL) and Natural Language Processing (NLP) show that contextual information decreases false-positives yield in detection of anomalous behaviors. Additionally, decentralization and exponentially increased number of data sources make traditional machine learning algorithms impractical. Federated Learning (FL) brings a solution to overcome decentralization and privacy issues. It aims to employ participating devices to learn from own data and sending local models for global convergence over secure communication. FL provides data security and decreases communication cost greatly, since local data is not transported to a central server. In a volatile cyber domain, it is a necessity to take a quick precautions for potential threats. The benefits of FL ensure building a defense system which provides realtime detection of cyber attacks. In this thesis, we propose a novel anomaly detection model and risk-adaptive feder ated approach. First, AnomalyAdapters (AAs) which is an extensible multi-anomaly task detection model. It uses pretrained transformers’ variant to encode log sequences and utilizes adapters to learn a log structure and anomaly types. Adapterbased approach collects contextual information, eliminates information loss in learn ing, and learns anomaly detection tasks from different log sources without overuse of parameters. Moreover, evaluation of this work elucidates the decision making process of the proposed model on different log datasets to emphasize extraction of threat data via explainability experiments. Lastly, Risk-adaptive anomaly detection with federated learning (FedRA) which is based on the idea of Spreading Phenomena. It decentralizes the aforementioned detection approach and adapts weighting of shared parameters to ensure capturing incoming cyber attacks in a timely manner.
Citation Count: 3
A Novel Blockchain-Based Deepfake Detection Method Using Federated and Deep Learning Models
(Springer, 2024) Dağ, Hasan; Navimipour, Nima Jafari; Dag, Hasan; Talebi, Samira; Unal, Mehmet
In recent years, the proliferation of deep learning (DL) techniques has given rise to a significant challenge in the form of deepfake videos, posing a grave threat to the authenticity of media content. With the rapid advancement of DL technology, the creation of convincingly realistic deepfake videos has become increasingly prevalent, raising serious concerns about the potential misuse of such content. Deepfakes have the potential to undermine trust in visual media, with implications for fields as diverse as journalism, entertainment, and security. This study presents an innovative solution by harnessing blockchain-based federated learning (FL) to address this issue, focusing on preserving data source anonymity. The approach combines the strengths of SegCaps and convolutional neural network (CNN) methods for improved image feature extraction, followed by capsule network (CN) training to enhance generalization. A novel data normalization technique is introduced to tackle data heterogeneity stemming from diverse global data sources. Moreover, transfer learning (TL) and preprocessing methods are deployed to elevate DL performance. These efforts culminate in collaborative global model training zfacilitated by blockchain and FL while maintaining the utmost confidentiality of data sources. The effectiveness of our methodology is rigorously tested and validated through extensive experiments. These experiments reveal a substantial improvement in accuracy, with an impressive average increase of 6.6% compared to six benchmark models. Furthermore, our approach demonstrates a 5.1% enhancement in the area under the curve (AUC) metric, underscoring its ability to outperform existing detection methods. These results substantiate the effectiveness of our proposed solution in countering the proliferation of deepfake content. In conclusion, our innovative approach represents a promising avenue for advancing deepfake detection. By leveraging existing data resources and the power of FL and blockchain technology, we address a critical need for media authenticity and security. As the threat of deepfake videos continues to grow, our comprehensive solution provides an effective means to protect the integrity and trustworthiness of visual media, with far-reaching implications for both industry and society. This work stands as a significant step toward countering the deepfake menace and preserving the authenticity of visual content in a rapidly evolving digital landscape.
Citation Count: 0
Network intrusion detection system by learning jointly from tabular and text-based features
(Wiley, 2024) Dağ, Hasan; Cayir, Aykut; Unal, Ugur; Dag, Hasan
Network intrusion detection systems (NIDS) play a critical role in maintaining the security and integrity of computer networks. These systems are designed to detect and respond to anomalous activities that may indicate malicious intent or unauthorized access. The need for robust NIDS solutions has never been more pressing in today's digital landscape, characterized by constantly evolving cyber threats. Deploying effective NIDS can be challenging, particularly in accurately identifying network anomalies amid the ever-increasing sophisticated and difficult-to-detect cyber threats. The motivation for our research stems from the recognition that while NIDS studies have made significant strides, there remains a crucial need for more effective and accurate methods to detect network anomalies. Commonly used features in NIDS studies include network logs, with some studies exploring text-based features such as payload. However, traditional machine and deep learning models may need to be improved in learning jointly from tabular and text-based features. Here, we present a new approach that integrates both tabular and text-based features to improve the performance of NIDS. Our research aims to address the existing limitations of NIDS and contribute to the development of more reliable and efficient network security solutions by introducing more effective and accurate methods for detecting network anomalies. Our internal experiments have revealed that the deep learning approach utilizing tabular features produces favourable results, whereas the pre-trained transformer approach needs to perform sufficiently. Hence, our proposed approach, which integrates both feature types using deep learning and pre-trained transformer approaches, achieves superior performance. These findings indicate that integrating both feature types using deep learning and pre-trained transformer approaches can significantly improve the accuracy of network anomaly detection. Moreover, our proposed approach outperforms the state-of-the-art methods in terms of accuracy, F1-score, and recall on commonly used NIDS datasets consisting of ISCX-IDS2012, UNSW-NB15, and CIC-IDS2017, with F1-scores of 99.80%, 92.37%, and 99.69%, respectively, indicating its effectiveness in detecting network anomalies.
Ağ sızma tespit sistemleri için tablosal ve metin temelli özniteliklerden birlikte öğrenmeye dayalı yeni bir mimari
(2023) Dağ, Hasan; Dağ, Hasan
Ağ Saldırı Tespit Sistemleri (ASTS) bilgisayar ağlarının güvenliğinin ve bütünlüğünün korunmasında kritik bir rol oynar. Bu sistemler, kötü niyetli veya yetkisiz erişime işaret edebilecek anormal faaliyetleri tespit etmek ve bunlara yanıt vermek üzere tasarlanmıştır. Sürekli gelişen siber tehditlerle karakterize edilen günümüzün dijital ortamında sağlam ASTS çözümlerine duyulan ihtiyaç hiç bu kadar acil olmamıştı. Etkili ASTS'lerin konuşlandırılması, özellikle de sürekli artan sofistike ve tespit edilmesi zor siber tehditlerin ortasında ağ anormalliklerinin doğru bir şekilde tanımlanması zor olabilir. Araştırmamızın motivasyonu, ASTS çalışmaları önemli adımlar atmış olsa da, ağ anormalliklerini tespit etmek için daha etkili ve doğru yöntemlere olan önemli ihtiyacın devam ettiğinin fark edilmesinden kaynaklanmaktadır. STS çalışmalarında yaygın olarak kullanılan özellikler ağ günlüklerini içermektedir ve bazı çalışmalar yük bilgisi gibi metin tabanlı özellikleri araştırmıştır. Ancak geleneksel makine ve derin öğrenme modelleri, tablosal ve metin tabanlı özelliklerden birlikte öğrenme konusunda yetersiz kalabilmektedir. Burada, ASTS'in performansını artırmak için hem tablo hem de metin tabanlı özellikleri entegre eden yeni bir yaklaşım sunuyoruz. Araştırmamız, ASTS'in mevcut sınırlamalarını ele almayı ve ağ anormalliklerini tespit etmek için daha etkili ve doğru yöntemler sunarak daha güvenilir ve verimli ağ güvenliği çözümlerinin geliştirilmesine katkıda bulunmayı amaçlamaktadır. Dahili deneylerimiz, tablosal özelliklerini kullanan derin öğrenme yaklaşımının olumlu sonuçlar verdiğini, metin tabanlı özelliklerini kullanan önceden eğitilmiş dönüştürücü yaklaşımının ise yeterli performans göstermediğini ortaya koymuştur. Bununla birlikte, derin öğrenme ve önceden eğitilmiş dönüştürücü yaklaşımlarını birlikte kullanarak her iki özellik türünü entegre eden önerilen yaklaşımımız üstün performans elde etmektedir. Bu bulgular, derin öğrenme ve önceden eğitilmiş dönüştürücü yaklaşımlarını birlikte kullanarak her iki özellik türünü entegre etmenin ağ aykırılığı tespitinin doğruluğunu önemli ölçüde artırabileceğini göstermektedir. Ayrıca, önerilen yaklaşımımız ISCX-IDS2012, UNSW-NB15 ve CIC-IDS2017 gibi yaygın olarak kullanılan ASTS veri kümelerinde doğruluk, F1-skoru ve duyarlılık açısından son teknoloji yöntemlerden daha iyi performans göstermekte ve sırasıyla %99,80, %92,37 ve %99,69 F1-skorları ile ağ aykırılık tespit etmedeki etkinliğini ortaya koymaktadır.