In the rapidly evolving landscape of natural language processing (NLP) and artificial intelligence, recent years have witnessed significant advancements, particularly in text-based question-answering (QA) systems. The Stanford Question Answering Dataset (SQuAD v2) has emerged as a prominent benchmark, offering diverse language understanding challenges. This study conducts a thorough examination of cutting-edge QA models—BERT, DistilBERT, RoBERTa, and ALBERT—each featuring distinct architectures, focusing on their training and performance on SQuAD v2. The analysis aims to uncover the unique strengths of each model, providing insights into their capabilities and exploring the impact of different training techniques on their performance. The primary objective is to enhance our understanding of text-based QA systems' evolution and their effectiveness in real-world scenarios. The results of this comparative study are poised to influence the utilization and development of these models in both industry and research. The investigation meticulously evaluates BERT, ALBERT, RoBERTa, and DistilBERT QA models using the SQuAD v2 dataset, emphasizing instances of accurate responses and identifying areas where completeness may be lacking. This nuanced exploration contributes to the ongoing discourse on the advancement of text-based question-answering systems, shedding light on the strengths and limitations of each QA model. Based on the results obtained, ALBERT achieved an exact match of 86.85% and an F1 score of 89.91% on the SQuAD v2 dataset, demonstrating superior performance in both answerable ('HasAns') and unanswerable ('NoAns') questions. BERT and RoBERTa also showed strong performance, while DistilBERT lagged slightly behind. This study provides a significant contribution to the advancement of text-based question-answering systems, offering insights that can shape the utilization of these models in both industry and research domains.
8 May 2024 in Journal of Mathematical Sciences and Modelling
The integration of artificial intelligence (AI) applications in the healthcare sector is ushering in a significant transformation, particularly in developing more effective strategies for early diagnosis and treatment of contagious diseases like tuberculosis. Tuberculosis, a global public health challenge, demands swift interventions to prevent its spread. While deep learning and image processing techniques show potential in extracting meaningful insights from complex radiological images, their accuracy is often scrutinized due to a lack of explainability. This research navigates the intersection of AI and tuberculosis diagnosis by focusing on explainable artificial intelligence (XAI). A meticulously designed deep learning model for tuberculosis detection is introduced alongside an exploration of XAI to unravel complex decisions. The core belief is that XAI, by elucidating diagnostic decision rationale, enhances the reliability of AI in clinical settings. Emphasizing the pivotal role of XAI in tuberculosis diagnosis, this study aims to impact future research and practical implementations, fostering the adoption of AI-driven disease diagnosis methodologies for global health improvement.
In this study, the generalizability and distributivity of three different chaotic systems within an industrial robotics time series dataset are explored using an annotated artificial intelligence algorithm. A time series dataset derived from industrial robotics processes was constructed and transformed into the Runge-Kutta system, comprising fourth-order differential equations for normalization. Among the processed data, variables related to x-y-z positions underwent chaotic transformations through Lorenz, Chen, and Rossler chaos systems. The x variable and angle variables from the transformed x-y-z data were inputted into the InterpretML model, an annotated artificial intelligence model, to elucidate the effects of angle variables on the x position variable. As a result of this analysis, InterpretML Local analysis revealed a sensitivity of 0.05 for the Rossler chaos system, 0.15 for Chen, and 0.25 for Lorenz. Furthermore, global analysis indicated precision rates of 0.17 for Rossler, 0.255 for Chen, and 0.35 for Lorenz chaos systems. These sensitivity results suggest that the Rossler chaos system consistently provides more accurate results in both InterpretML local and global analyses compared to other chaotic systems. This study contributes significantly to the literature by analyzing the distributive and generalization properties of chaos systems and enhancing understanding of these systems.
31 January 2025 in Information Technology in Economics and Business
In many industries, such as the telecommunications industry, identifying the causes of customer churn is a primary challenge. In the telecommunications industry, it is of great importance to predict which customers will abandon or continue their subscriptions. Machine learning and data science offer numerous solutions to this problem. These proposed solutions have an important place in decision making processes in various sectors. This study aims to predict lost customers using machine learning algorithms and explain the reasons behind them. The dataset used used Linear Regression, Logistic Regression, Naive Bayes, Decision Tree, Random Forest, K-Nearest Neighbors (KNN), Gradient Boosting, XGBoost (eXtreme Gradient Boosting), LightGBM, AdaBoost and CatBoost to find the classification with the best performance. Contains algorithms. model. Performance metrics such as R2 score, Mean Square Error, Mean Absolute Error, Root Mean Square Error and Accuracy are used in this process. Finally, the LightGBMmodel, which gives the highest accuracy value (73.085%), is explained using explainable artificial intelligence (XAI) algorithms.
A comparative analysis of two prominent Explainable Artificial Intelligence (XAI) techniques, SHAP (SHapley Additive exPlanations) and Interpreted ML Partial Dependence, was conducted on a Telecom Churn dataset. The objective of this study was to evaluate and compare the effectiveness of these techniques in enhancing the transparency and interpretability of machine learning models, specifically in telecom churn prediction. The study emphasizes the importance of XAI in ensuring trust and comprehension in predictive modeling. The methodology outlined the steps of data preprocessing and model training. Two separate analyses using SHAP and Interpreted ML Partial Dependence were conducted to evaluate their effectiveness in explaining model decisions and uncovering feature importance. The results of both techniques were discussed, highlighting their strengths and weaknesses, and providing valuable insights into interpretability and robustness. The SHAP analysis demonstrated that it is a powerful tool for identifying which features influence churn, thereby making it easier to understand why the model made certain predictions. The Interpreted ML Partial Dependence method showed the general effects of features, allowing for a broader perspective on model behavior. These results enhanced the transparency of model decisions, instilling trust in users and helping them understand how the model works. The comparative analysis contributed to understanding XAI methods and emphasized the importance of selecting appropriate techniques to enhance transparency in telecom churn prediction models.
21 July 2020 in Gazi Üniversitesi Mühendislik-Mimarlık Fakültesi Dergisi
Günümüzde teknoloji ve üretim ortamı sürekli gelişmektedir. İşletmeler bu rekabet ortamında ayakta kalabilmek için yenilikleri takip etmek zorundadır. Endüstri 4.0 ya da diğer bir adıyla dördüncü sanayi devriminin temel amacı bilişim teknolojileri ve endüstriyi bir araya getirmektir. Endüstri 4.0, birbirleri ile haberleşebilen, veri alışverişi yapabilen sistemler arası bütünleşmeyi içeren, ileri otomasyon seviyesi ile veri analizini yaparak, üretimdeki makine ve teçhizata ait tüm verilerin, üretimin eş zamanlı yapılabilmesi için bir bulut sisteminde depolanması olarak özetlenebilir. Endüstri 4.0, üretimde esnekliğin arttırılmasına ve daha yüksek verimliliğin sağlanmasına olanak sağlar. Bu çalışmada, işletmelerin Endüstri 4.0 seviyesini etkileyen kriterler belirlenmiş ve kriter etkilerinin Endüstri 4.0 seviyesine etkisinin analizi için yapısal eşitlik modeli (YEM) kullanılmıştır. Modelde teknoloji, strateji, müşteriler, liderlik, devlet politikası, kültür, süreçler ve çalışanlar olmak üzere 8 kriter kullanılmıştır. Gerçekleştirilen uygulama ile Endüstri 4.0 seviyesine etki eden en önemli üç kriterin sırasıyla 1,00 faktör yükü ile strateji, 0,97 faktör yükü ile kültür ve 0,90 faktör yükü ile süreçler olduğu görülmektedir. Çalışmada elde edilen bulguların işletmelerin Endüstri 4.0 hedefine ulaşmaları konusundaki eksik ve geliştirilebilir yönlerini görmeleri konusunda yardımcı olması hedeflenmektedir.