Bilgisayar ve Bilişim Fakültesi

Bu topluluk için Kalıcı Uri

http://hdl.handle.net/11527/25353

Gözat

Çıkarma tarihi ile Bilgisayar ve Bilişim Fakültesi'a göz atma

Dizinde bir noktaya atla:
  • Öge
    A drug prescription recommendation system based on novel DIAKID ontology and extensive semantic rules
    (Springer, 2024) Göğebakan, Kadime ; Ulu, Ramazan ; Abiyev, Rahib ; Şah, Melike ; 0000-0002-2584-9647 ; 0000-0003-1461-2764 ; 0000-0002-3085-6219 ; 0000-0003-3869-7205 ; Bilişim Sistemleri Mühendisliği
    According to the World Health Organization (WHO) data from 2000 to 2019, the number of people living with Diabetes Mellitus and Chronic Kidney Disease (CKD) is increasing rapidly. It is observed that Diabetes Mellitus increased by 70% and ranked in the top 10 among all causes of death, while the rate of those who died from CKD increased by 63% and rose from the 13th place to the 10th place. In this work, we combined the drug dose prediction model, drug-drug interaction warnings and drugs that potassium raising (K-raising) warnings to create a novel and effective ontology-based assistive prescription recommendation system for patients having both Type-2 Diabetes Mellitus (T2DM) and CKD. Although there are several computational solutions that use ontology-based systems for treatment plans for these type of diseases, none of them combine information analysis and treatment plans prediction for T2DM and CKD. The proposed method is novel: (1) We develop a new drug-drug interaction model and drug dose ontology called DIAKID (for drugs of T2DM and CKD). (2) Using comprehensive Semantic Web Rule Language (SWRL) rules, we automatically extract the correct drug dose, K-raising drugs, and drug-drug interaction warnings based on the Glomerular Filtration Rate (GFR) value of T2DM and CKD patients. The proposed work achieves very competitive results, and this is the first time such a study conducted on both diseases. The proposed system will guide clinicians in preparing prescriptions by giving necessary warnings about drug-drug interactions and doses.
  • Öge
    Accelerating molecular docking using machine learning methods
    (Wiley, 2024) Bande, Abdulsalam Y. ; Baday, Sefer ; Yapay Zeka ve Veri Mühendisliği
    Virtual screening (VS) is one of the well-established approaches in drug discovery which speeds up the search for a bioactive molecule and, reduces costs and efforts associated with experiments. VS helps to narrow down the search space of chemical space and allows selecting fewer and more probable candidate compounds for experimental testing. Docking calculations are one of the commonly used and highly appreciated structure-based drug discovery methods. Databases for chemical structures of small molecules have been growing rapidly. However, at the moment virtual screening of large libraries via docking is not very common. In this work, we aim to accelerate docking studies by predicting docking scores without explicitly performing docking calculations. We experimented with an attention based long short-term memory (LSTM) neural network for an efficient prediction of docking scores as well as other machine learning models such as XGBoost. By using docking scores of a small number of ligands we trained our models and predicted docking scores of a few million molecules. Specifically, we tested our approaches on 11 datasets that were produced from in-house drug discovery studies. On average, by training models using only 7000 molecules we predicted docking scores of approximately 3.8 million molecules with R2 (coefficient of determination) of 0.77 and Spearman rank correlation coefficient of 0.85. We designed the system with ease of use in mind. All the user needs to provide is a csv file containing SMILES and their respective docking scores, the system then outputs a model that the user can use for the prediction of docking score for a new molecule.
  • Öge
    Test case prioritization for embedded software
    (ACM, 2024) Özer, Elif Güşta ; Buzluca, Feza ; https://orcid.org/0009-0004-9943-6134 ; https://orcid.org/0000-0001-9589-8754 ; Bilgisayar Mühendisliği
    Electronic devices used daily contain software, which may have errors due to human factors during coding. Testing is essential before release, especially as software complexity increases with diverse user needs. Testing new features separately and then in combination multiplies test cases. Rerunning all tests after each change is costly. The aim of this study is to develop a test case prioritization method to decrease the time to find software errors in embedded software systems. For this purpose, we extracted the basic features that characterize embedded software systems and tests that run on them. The proposed method calculates prioritization scores for test cases utilizing these characteristics. The test cases will then be arranged in a systematic manner according to their respective scores. This prioritization strategy is designed to minimize error detection time by promptly finding and resolving errors throughout the initial stages of the testing process. The proposed prioritization strategy was tested on an embedded software system, and it was evaluated using the metrics APFD (average percentage of faults detected) and APFDc (APFD with cost). The results indicate that the proposed method based on the attributes of software systems and related tests reduces the time required to find the majority of the errors.
  • Öge
    Evaluating microservices maintainability: a classification system using code metrics and ISO/IEC 250xy standards
    (ACM, 2024) Özdemir, Oğuzcan ; Buzluca, Feza ; https://orcid.org/0009-0005-1820-1884 ; https://orcid.org/0000-0001-9589-8754 ; Bilgisayar Mühendisliği
    In the rapidly evolving landscape of software engineering, Microservice Architecture (MSA) has emerged as a pivotal approach, renowned for its modular structure, operational efficiency, scalability, and flexibility. Despite the extensive research on MSA development, and numerous studies dedicated to evaluating the maintainability of object-oriented programs, the focus on the quality of microservice-based systems remains notably limited. This study introduces an innovative model for evaluating the maintainability of microservices, a key element in MSA. Our approach, grounded in code metrics analysis, aligns with the ISO/IEC 250xy standards SQuaRE (System and Software Quality Requirements and Evaluation). It specifically targets testability and modifiability, integral components of maintainability. We carefully chose essential code metrics that precisely encapsulate the varied characteristics of MSA. The model employs clustering algorithms to categorize the quality characteristics of MSA into three distinct groups: low, medium and high. Our project’s primary goal is to identify microservices with low maintainability values. Our methodology was applied to a range of open-source MSA-designed applications, demonstrating its effectiveness and yielding promising outcomes. In our results, we achieved a recall of 83.33% and a precision of 71.43%. This research contributes a novel viewpoint in assessing microservice maintainability and offers a valuable resource for software architects and developers. It aims to improve the overall quality and longevity of software systems within the MSA.
  • Öge
    Enhancing cross-market recommendation system with graph isomorphism networks: a novel approach to personalized user experience
    (ACM, 2024) Öztürk, Sümeyye ; Ercan, Ahmed Burak ; Tugay, Resul ; Öğüdücü, Şule ; https://orcid.org/0009-0002-1308-7646 ; https://orcid.org/0009-0001-4051-8424 ; https://orcid.org/0000-0003-1621-9528 ; https://orcid.org/0000-0002-0288-4757 ; Yapay Zeka ve Veri Mühendisliği
    In today’s world of globalized commerce, cross-market recommendation systems (CMRs) are crucial for providing personalized user experiences across diverse market segments. However, traditional recommendation algorithms have difficulties dealing with market specificity and data sparsity, especially in new or emerging markets. In this paper, we propose the CrossGR model, which utilizes Graph Isomorphism Networks (GINs) to improve CMR systems. It outperforms existing benchmarks in NDCG@10 and HR@10 metrics, demonstrating its adaptability and accuracy in handling diverse market segments. The CrossGR model is adaptable and accurate, making it well-suited for handling the complexities of cross-market recommendation tasks. Its robustness is demonstrated by consistent performance across different evaluation timeframes, indicating its potential to cater to evolving market trends and user preferences. Our findings suggest that GINs represent a promising direction for CMRs, paving the way for more sophisticated, personalized, and context-aware recommendation systems in the dynamic landscape of global e-commerce.
  • Öge
    A GNN model with adaptive weights for session-based recommendation systems
    (ACM, 2024) Özbay, Begüm ; Tugay, Resul ; Gündüz Öğüdücü, Şule ; Bilgisayar Mühendisliği
    Session-based recommendation systems aim to model users’ interests based on their sequential interactions to predict the next item in an ongoing session. In this work, we present a novel approach that can be used in session-based recommendations (SBRs). Our goal is to enhance the prediction accuracy of an existing session-based recommendation model, the SR-GNN model, by introducing an adaptive weighting mechanism applied to the graph neural network (GNN) vectors. This mechanism is designed to incorporate various types of side information obtained through different methods during the study. Items are assigned varying degrees of importance within each session as a result of the weighting mechanism. We hypothesize that this adaptive weighting strategy will contribute to more accurate predictions and thus improve the overall performance of SBRs in different scenarios. The adaptive weighting strategy can be utilized to address the cold start problem in SBRs by dynamically adjusting the importance of items in each session, thus providing better recommendations in cold start situations, such as for new users or newly added items. Our experimental evaluations on the Dressipi dataset demonstrate the effectiveness of the proposed approach compared to traditional models in enhancing the user experience and highlighting its potential to optimize the recommendation results in real-world applications.