Normal 0 21 false false false TR X-NONE X-NONE /* Style Definitions */ table.MsoNormalTable {mso-style-name:"Normal Tablo"; mso-tstyle-rowband-size:0; mso-tstyle-colband-size:0; mso-style-noshow:yes; mso-style-priority:99; mso-style-parent:""; mso-padding-alt:0cm 5.4pt 0cm 5.4pt; mso-para-margin-top:0cm; mso-para-margin-right:0cm; mso-para-margin-bottom:10.0pt; mso-para-margin-left:0cm; line-height:115%; mso-pagination:widow-orphan; font-size:11.0pt; font-family:"Calibri",sans-serif; mso-ascii-font-family:Calibri; mso-ascii-theme-font:minor-latin; mso-hansi-font-family:Calibri; mso-hansi-theme-font:minor-latin; mso-bidi-font-family:"Times New Roman"; mso-bidi-theme-font:minor-bidi; mso-ansi-language:EN-US; mso-fareast-language:EN-US;} Müzik eserlerinin sayısal ortama aktarılmasıyla birlikte, bilgisayar bilimleri müzikoloji çalışmalarının içerisinde kendine yer bulmaya başlamıştır. Müzik eserleri bilimsel araştırmalarda veri olarak kullanılmakta ve hesaplamalı müzik alanı bu alanda yapılan çalışmalar ile hızla gelişmektedir. Her ne kadar yapılan çalışmaların büyük bir bölümü sembolik olarak ifade edilmesi daha kolay olan Batı Müziği eserleri üzerine olsa da, Türk Müziği eserleri de artık çeşitli çalışmaların konusu olmaktadır. Türk Müziğinin temeli olan makam sistemi, bilgisayar bilimleri ile uğraşan araştırmacıların dikkatini çekmiş ve Türk Müziği eserleri veri madenciliği, makine öğrenmesi, sınıflandırma gibi çalışmaların konusu olmuştur. Bu çalışmada, bir ses dosyasından nota tanıma ile elde edildiği varsayılan ve 1261 Türk Müziği eserine ait sadece nota dizilerini içeren veri dosyası üzerinde makine öğrenmesi metodu ile makam tahmini yapmaya yönelik deneysel bir çalışma gerçekleştirilmiştir. MusicXML biçimindeki eserlerin makine öğrenmesi uygulamasında kullanılabilmesi amacıyla bir yazılım geliştirilmiş, bu yazılımla makine öğrenmesinde başarımı arttırmak için özgün veri kümesine dört farklı türetilmiş veri sahası eklenmiştir. Sonuç olarak, ‘Rastgele Orman’ algoritması ile makam tanımada %89,7 oranında başarım gözlemlenmiştir.

Pile foundations are critical structural elements, and their integrity is essential for ensuring the stability and safety of construction projects. Low-strain pile integrity testing (LSPIT) is widely used for defect detection; however, conventional manual interpretation of reflectograms is both time-consuming and susceptible to human error. This study presents a deep learning-driven approach utilizing transfer learning with convolutional neural networks (CNNs) to automate pile defect detection. A dataset of 328 reflectograms collected from real construction sites, including 246 intact and 82 defective samples, was used to train and evaluate the model. To address class imbalance, oversampling techniques were applied. Several state-of-the-art pretrained CNN architectures were compared, with ConvNeXtLarge achieving the highest accuracy of 98.2%. The accuracy reported was achieved on a dedicated test set using real reflectogram data from actual construction sites, distinguishing this study from prior work relying primarily on synthetic data. The proposed novelty includes adapting pre-trained CNN architectures specifically for real-world pile integrity testing, addressing practical challenges such as data imbalance and limited dataset size through targeted oversampling techniques. The proposed approach demonstrates significant improvements in accuracy and efficiency compared to manual interpretation methods, making it a promising solution for practical applications in the construction industry. The proposed method demonstrates potential for generalization across varying pile lengths and geological conditions, though further validation with broader datasets is recommended.

In the current Semantic Web Community, as the size and complexity of ontologies increase, ontology summarisation is becoming more important. There are many studies in the literature that use different approaches and metrics. However, many of these studies are not effective in terms of performance or have integration issues with current technologies. In this study, the popular ontology summarisation metrics are examined focusing on their performance in terms of time, and a number of metrics have been selected accordingly. To increase the accuracy of selections made with chosen metrics, we propose a novel metric: ‘name inclusion’. This metric promotes a concept if its name is subsumed by the name of another concept. As the existing summarisation applications have integration issues, we have implemented our summarisation framework to integrate easily with the latest web technologies. Therefore, the algorithm is implemented using Rust language, which performs well and easily integrates with other languages.

This article presents a framework that detects potential ontology building errors to improve the ontology quality. These potential errors are called ontology pitfalls in the literature. This work extends the existing ontology pitfall set in the literature and suggests new solutions for ontology repair. We have also developed a Java implementation for detection of the proposed pitfalls. These pitfalls were evaluated with well-known ontologies using this implementation.

The Low-Strain Pile Integrity Test (LSPIT), standardized in ASTM D5882, is widely used as a rapid and economical non-destructive technique for assessing pile continuity in deep foundation systems. However, interpretation of LSPIT reflectograms remains strongly dependent on expert judgment and is influenced by soil–pile interaction effects such as damping and radiation losses, which can alter waveform morphology and confound automated defect screening. This study proposes a soil-aware deep learning framework that combines image-based reflectogram features with categorical geotechnical context describing the dominant soil regime at the measurement site. Reflectogram images are processed with a pretrained ConvNeXt-Large backbone, while soil information derived from Unified Soil Classification System (USCS) logs is represented as a categorical auxiliary input and mapped to a learnable embedding. The resulting multimodal design conditions waveform interpretation based on site context rather than relying on signal morphology alone. The framework is examined on an assembled benchmark of 510 expert-labeled reflectograms (404 intact and 106 defective), including a nine-site subset of 182 field records with explicit soil annotations. On the assembled benchmark, the model yields 99.41% accuracy and a weighted F1-score of 0.9941; on the nine-site subset, the observed accuracy is 99.45% with zero missed defective cases. Balanced accuracy, specificity, missed-detection rate, false-alarm rate, and confidence intervals are additionally reported to better align the evaluation with engineering screening practice. The study also states the current limits of the evidence base, including partial soil annotation, dominant-soil simplification, restricted soil coverage, and the absence of leave-site-out and interpretability-focused validation. Overall, the results support soil-aware multimodal learning as a promising proof-of-concept direction for more context-aware automated LSPIT interpretation, while also identifying the validation steps still required for broad field deployment.