{
    "exported_at": "2026-11-16 23:06:52",
    "count": 5,
    "records": [
        {
            "id": 45,
            "title": "IMPLEMENTASI MODEL CONVOLUTIONAL RECURRENT NEURAL NETWORK (CRNN) DENGAN BIDIRECTIONAL LONG SHORT-TERM MEMORY (BI-LSTM) UNTUK PENGENALAN EMOSI PADA SUARA",
            "title_ar": "",
            "title_en": "",
            "author": "ADHIRAJASA M. RADITYA",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "Lampung University",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Indonesia",
            "governorate": "",
            "publication_year": 2025,
            "language": "id",
            "research_domain": "nlp",
            "research_subdomain": "sentiment-analysis",
            "categories": "deep-learning; nlp; cnn; rnn; sentiment-analysis; speech-recognition",
            "keywords": "Speech Emotion Recognition, CRNN, BiLSTM, Log-Mel Spectrogram, Data Augmentation.",
            "abstract": "Pengenalan emosi pada suara merupakan tugas kompleks yang krusial untuk interaksi manusia-mesin. Penelitian ini mengimplementasikan dan mengevaluasi model Convolutional Recurrent Neural Network (CRNN) yang menggabungkan keunggulan Convolutional Neural Network (CNN) untuk ekstraksi fitur spasial dengan Bidirectional Long Short-Term Memory (BiLSTM) untuk analisis dependensi temporal. Model ini dilatih dan diuji menggunakan dataset CREMA-D, yang mencakup enam kelas emosi: marah, jijik, takut, bahagia, netral, dan sedih. Fitur diekstraksi dari sinyal audio menggunakan log-Mel spectrogram untuk merepresentasikan karakteristik suara yang relevan dengan persepsi manusia. Untuk meningkatkan variasi data dan generalisasi model, diterapkan teknik augmentasi data berupa pitch shifting dan time stretching. Hasil evaluasi menunjukkan bahwa model CRNN yang didukung dengan augmentasi data berhasil mencapai akurasi validasi sebesar 68.23%, sebuah peningkatan dari 66.08% yang dicapai oleh model tanpa augmentasi. Model ini menunjukkan performa yang menjanjikan, terutama dalam mengklasifikasikan emosi marah dan netral. Penelitian ini menyimpulkan bahwa arsitektur CRNN dengan BiLSTM efektif untuk tugas pengenalan emosi suara, dan augmentasi data berperan penting dalam meningkatkan kinerjanya. Kata Kunci: Pengenalan Emosi Suara, CRNN, BiLSTM, Log-Mel Spectrogram, Augmentasi Data. Speech emotion recognition is a complex task crucial for human-machine interaction. This study implements and evaluates a Convolutional Recurrent Neural Network (CRNN) model that combines the advantages of a Convolutional Neural Network (CNN) for spatial feature extraction with Bidirectional Long Short-Term Memory (BiLSTM) for temporal dependency analysis. The model is trained and tested using the CREMA-D dataset, which includes six emotion classes: anger, disgust, fear, happiness, neutral, and sadness. Features are extracted from the audio signals using log-Mel spectrograms to represent sound characteristics relevant to human perception. To enhance data variation and model generalization, data augmentation techniques such as pitch shifting and time stretching were implemented. The evaluation results show that the CRNN model with data augmentation achieved a validation accuracy of 68.23%, an increase from the 66.08% achieved by the model without augmentation. The model shows promising performance, especially in classifying the anger and neutral emotions. This study concludes that the CRNN architecture with BiLSTM is effective for the task of speech emotion recognition, and that data augmentation plays a crucial role in enhancing its performance. Keywords: Speech Emotion Recognition, CRNN, BiLSTM, Log-Mel Spectrogram, Data Augmentation.",
            "source_url": "https:\/\/openalex.org\/W7126365563",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "Digilib Repository Unila (Lampung University)",
            "source_record_id": "W7126365563",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:46",
            "updated_at": "2026-11-15 16:52:46"
        },
        {
            "id": 285,
            "title": "Automatic Detection and Verification System for Arabic Rumor News on Twitter",
            "title_ar": "",
            "title_en": "Automatic Detection and Verification System for Arabic Rumor News on Twitter",
            "author": "Sami Karali",
            "supervisor": "",
            "degree_type": "phd",
            "degree_evidence": "نص السجل: «doctoral research»",
            "university": "University of Technology Sydney",
            "university_source": "repository_host",
            "college": "",
            "department": "",
            "country": "Australia",
            "governorate": "",
            "publication_year": 2024,
            "language": "en",
            "research_domain": "nlp",
            "research_subdomain": "llm",
            "categories": "machine-learning; deep-learning; nlp; ai-applications; cnn; rnn; llm; arabic-nlp; ai-education",
            "keywords": "",
            "abstract": "anguage models have been extensively studied and applied in various fields in recent years.However, the majority of the language use models are designed for and perform significantly better in English compared to other languages, such as Arabic.The differences between English and Arabic in terms of grammar, writing, and word-forming structures pose significant challenges in applying English-based language models to Arabic content.Therefore, there is a critical need to develop and refine models and methodologies that can effectively process Arabic content.This research aims to address the gaps in Arabic language models by developing innovative machine learning (ML) and natural language processing (NLP) methodologies.We apply the developed model to Arabic rumor detection on Twitter to test its effectiveness.To achieve this, the research is divided into three fundamental phases: 1) Efficiently collecting and pre-processing a comprehensive dataset of Arabic news tweets; 2) The refinement of ML models through an enhanced Convolutional Neural Network (ECNN) equipped with N-gram feature maps for accurate rumor identification; 3) The augmentation of decision-making precision in rumor verification via sophisticated ensemble learning techniques.In the first phase, the research meticulously develops a methodology for the collection and pre-processing of Arabic news tweets, aiming to establish a dataset optimized for rumor detection analysis.Leveraging a blend of automated and manual processes, the research navigates the intricacies of the Arabic language, enhancing the dataset's quality for ML applications.This foundational phase ensures removing irrelevant data and normalizing text, setting a precedent for accuracy in subsequent detection tasks.The second phase is to develop an Enhanced Convolutional Neural Network (ECNN) model, which incorporates N-gram feature maps for a deeper linguistic analysis of tweets.This innovative ECNN model, designed specifically for the Arabic language, marks a significant departure from traditional rumor detection models by harnessing the power of spatial feature extraction alongside the contextual insights provided by N-gram analysis.Empirical results underscore the ECNN model's superior performance, demonstrating a marked improvement in detecting and classifying rumors with heightened accuracy and efficiency.The culmination of the study explores the efficacy of ensemble learning methods in enhancing the robustness and accuracy of rumor detection systems.By synergizing the ECNN model with Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), and Gated Recurrent Unit (GRU) networks within a stacked ensemble framework, the iii research pioneers a composite approach that significantly outstrips the capabilities of singular models.This innovation results in a state-of-the-art system for rumor verification that outperforms accuracy in identifying rumors, as demonstrated by empirical testing and analysis.This research contributes to bridging the gap between English-centric language models and Arabic language processing, demonstrating the importance of tailored approaches for different languages in the field of ML and NLP.These contributions signify a monumental step forward in the field of Arabic NLP and ML and offer practical solutions for the real-world challenge of rumor proliferation on social media platforms, ultimately fostering a more reliable digital environment for Arabic-speaking communities.n the journey that has been my doctoral research, I have been fortunate to be guided by individuals whose impact has been profound and far-reaching.At the forefront of these cherished relationships is Prof. CT Lin, whose guidance and support have been the beacon that navigated me through the complexities and challenges inherent in this rigorous academic endeavor.Prof. Lin's readiness to engage, discuss, and explore solutions with me, irrespective of the time or day, has been a testament to his dedication to academia and the growth of his students.His wisdom, coupled with an unwavering belief in my potential, provided me with the confidence to pursue this project with vigor and determination.To Prof.",
            "source_url": "https:\/\/openalex.org\/W7225354344",
            "pdf_url": "https:\/\/opus.lib.uts.edu.au\/bitstream\/10453\/187339\/1\/thesis.pdf",
            "doi": "",
            "handle": "",
            "repository_name": "OPUS - Open Publications of UTS Scholars (University of Technology Sydney)",
            "source_record_id": "W7225354344",
            "other_sources": "",
            "verification_status": "verified",
            "created_at": "2026-11-15 16:52:48",
            "updated_at": "2026-11-15 16:52:48"
        },
        {
            "id": 297,
            "title": "Prediction of Deep Learning Methods using Wavelet Transform",
            "title_ar": "",
            "title_en": "",
            "author": "Gökçe Nur Taşağıl Arslan",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "Turkey",
            "governorate": "",
            "publication_year": 2025,
            "language": "tr",
            "research_domain": "deep-learning",
            "research_subdomain": "cnn",
            "categories": "machine-learning; deep-learning; predictive-analytics; cnn; rnn",
            "keywords": "",
            "abstract": "Hava kirliliği, PM10 gibi partikül madde içeren yanma gazlarının salınması sonucu ortaya çıkmaktadır. Doğru ve güvenilir teknikler ile PM10 konsantrasyonlarının tahmini, sağlık risklerini düşürmek için göz önüne alınmalıdır. Ortam hava kalitesi ve halk sağlığı üzerindeki zararlı etkileri en aza indirmek için önleyici tedbirleri yürütmek üzere erken uyarı sistemlerinin potansiyelinin olması, PM10'u tahmin etme sayesinde mümkün hale gelmektedir. Bu çalışma, saatlik geçmiş hava kirletici konsantrasyonları ve meteorolojik verileri kullanarak, Ayrık Dalgacık Dönüşümü (DWT), Çok Katmanlı Algılayıcılar (MLP), Yinelemeli Sinir Ağları (RNN), Uzun Kısa Süreli Bellek (LSTM), Çift Yönlü LSTM (BiLSTM), Kapılı Yinelemeli Birim (GRU) ve Evrişimli Sinir Ağı (CNN) kullanarak 24 saat sonraki PM10 konsantrasyonunu tahmin etmek için bir yöntem önermektedir. İlk olarak, yüksek performanslı modelleri belirlemek için dalgacık tipleri kullanılır ve bu modeller arasında derin öğrenme tekniklerinde iyi performans gösterenler belirlenir. Modeller karşılaştırılırken RMSE, MAE ve R2 değerleri gibi performans parametreleri dikkate alınmıştır. En iyi model, en düşük RMSE (1,908), MAE (0,994), ve en yüksek R2 ()'ye sahip Dmey dalgacık dönüşümü kullanılan DWT-GRU-BiLSTM modeli olmuştur. Bu çalışmada kullanılan model, gelecekteki araştırmalarda bölgesel PM konsantrasyon seviyelerini doğru bir şekilde tahmin etmek için kullanılabilir. Sürdürülebilir akıllı çevre sistemleri kurmak ve önleyici eylemlerde bulunabilen kurum ve kuruluşların doğru zamanda harekete geçmesine yardımcı olmak için, uygulanan bu hibrit derin öğrenme algoritmalarının doğru tahminleme yeteneğinden yararlanılabilir. Hava kirliliğinin arttığı ve insan sağlığı için tehdit oluşturduğu mevcut ortamda, alınabilecek her türlü önleyici tedbir, tüm canlılar için yaşam kalitesini iyileştirecek, hava kirliliğinden kaynaklanan sağlık sorunlarını ve ölümleri azaltacak ve nihayetinde refah derecesini yükseltecektir. Ayrıca, bu bulgular İstanbul gibi yoğun nüfuslu, endüstriyel ve yoğun trafiğe sahip şehirlerin hava kalitesiyle ilgili ikna edici ampirik kanıtlar sunabilir.",
            "source_url": "https:\/\/openalex.org\/W7219471140",
            "pdf_url": "https:\/\/avesis.yildiz.edu.tr\/file?id=4447b2e1-fa87-4912-a948-b76c5deb0c71",
            "doi": "",
            "handle": "",
            "repository_name": "Yildiz Technical University - AVESIS",
            "source_record_id": "W7219471140",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:48",
            "updated_at": "2026-11-15 16:52:48"
        },
        {
            "id": 347,
            "title": "Deep learning-based damage detection on cherry leaves",
            "title_ar": "",
            "title_en": "",
            "author": "Hazel Bozcu",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "Turkey",
            "governorate": "",
            "publication_year": 2024,
            "language": "tr",
            "research_domain": "deep-learning",
            "research_subdomain": "cnn",
            "categories": "deep-learning; cnn; rnn",
            "keywords": "",
            "abstract": "Bu çalışmada tarımsal üretimde verim artışını sağlamak amacıyla kiraz yapraklarındaki hastalıkların tespiti için derin öğrenme yöntemlerinin kullanılması amaçlanmaktadır. Günümüzde yaprak hastalıkların tespiti uzman personel tarafından yapılabilmekte ancak uzun sürmektedir. Ayrıca, bu uzmanların sayısı yetersiz olabilir, bu da doğru tespitin zorluğuna işaret etmektedir. Bu nedenle, kiraz üretimini artırmak ve hastalıkları erken teşhis etmek için derin öğrenme temelli hastalık tespit uygulamalarının kullanımı bu çalışmanın ana amacıdır. Çalışmada iki farklı veri seti üzerinde kiraz yaprak hastalığı tespiti için farklı derin öğrenme modellerinin performansı incelenmiştir. Ortalama sonuçlara göre, MobileNet-V2 modeli .68 doğruluk ve .83 hassasiyet ile yüksek bir performans sergilemiş, Inception-V3 modeli .17 F1-Skor ile tatmin edici sonuçlar vermiştir. Önerilen CNN modeli .83 F1- Skor ile dikkat çekmiş, önerilen CNN + LSTM modeli .33 geri çağırma değeri ile tatmin edici sonuçlar sunmuş ve önerilen CNN + BiLSTM modeli .33 F1-Skor ile yüksek bir performans göstermiştir. En iyi sonuçlar kategorisinde, MobileNet-V2 modeli .03 doğruluk oranı ve .33 F1- Skor ile en iyi sonuçları vermiş, Inception-V3 modeli .00 doğruluk ve .33 hassasiyet ile tatmin edici bir performans sergilemiştir. Önerilen CNN modeli .66 F1-Skor ile iyi bir performans sergilemiş, önerilen CNN + LSTM modeli .67 doğruluk ve .67 F1-Skor ile en iyi sonuçları vermiş ve önerilen CNN + BiLSTM modeli .66 F1-Skor ile yüksek bir performans göstermiştir. Bu sonuçlar, kiraz yaprak hastalığı tespiti için derin öğrenme modellerinin umut veren sonuçlar elde ettiğini göstermektedir. Çalışma kapsamında en iyi sonuçlar MobileNet-V2 ve önerilen CNN + LSTM modelleri tarafından elde edilmiştir. Bu çalışmanın, çeşitli veri setleri kullanılarak güvenirliliği arttırılabilir, farklı derin öğrenme yöntemleri kullanılarak hastalık tespit başarım oranları yükseltilebilir ve hastalık tespit süreleri düşürülebilir.",
            "source_url": "https:\/\/openalex.org\/W7218050026",
            "pdf_url": "https:\/\/acikkaynak.bilecik.edu.tr\/bitstreams\/629b0f54-7406-4380-bfcc-442022f926d5\/download",
            "doi": "",
            "handle": "",
            "repository_name": "Bilecik Şeyh Edebali University Institutional Repository",
            "source_record_id": "W7218050026",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:48",
            "updated_at": "2026-11-15 16:52:48"
        },
        {
            "id": 1082,
            "title": "A Deep Neural Network Approach Integrating CNN and BiLSTM-Transformer Architectures for Emotion Recognition from Speech",
            "title_ar": "",
            "title_en": "A Deep Neural Network Approach Integrating CNN and BiLSTM-Transformer Architectures for Emotion Recognition from Speech",
            "author": "Divyansh Anand",
            "supervisor": "",
            "degree_type": "unspecified",
            "degree_evidence": "",
            "university": "",
            "university_source": "",
            "college": "",
            "department": "",
            "country": "",
            "governorate": "",
            "publication_year": 2024,
            "language": "en",
            "research_domain": "deep-learning",
            "research_subdomain": "transformers",
            "categories": "machine-learning; deep-learning; nlp; medical-ai; ai-applications; predictive-analytics; cnn; transformers; sentiment-analysis; speech-recognition; ai-education; ai-industry; ai-smart-cities",
            "keywords": "",
            "abstract": "The goal of speech emotion recognition is to make human-computer interaction more efficient in several areas such as customer service, entertainment industry, human-computer interaction, healthcare, and education. Previous work in speech emotion analysis presented some issues like limited choice of features, model complexity, noise variability, and insufficient data samples, which negatively affected the prediction of emotions. This paper provides an in-depth study of speech emotion recognition using a hybrid deep neural network architecture that combines 1-D Convolutional Neural Network (CNN) and BiLSTM-Transformer models to analyze data from the Ravdess and Crema-D datasets. To make the datasets appropriate for emotion detection, all were preprocessed by means of librosa library to get rid of non-speech segments. Important sound characteristics such as Mel-Frequency Cepstral Coefficients(MFCC), Root Mean Square Energy (RMSE), and Zero Crossing Rate (ZCR) were extracted to get the spectral characteristics, intensity of feelings, and dynamic features present in the emotions. In order to improve model’s generalization and robustness noise injection, time stretching, time shifting as well as pitch shifting have been applied during data augmentation. The proposed model leverages the strengths of both CNN and BiLSTM-Transformer components. The proposed model’s 1-D CNN captures local patterns in sound whereas the BiLSTM-Transformer handles sequence data and complex hierarchical structures of audio. Various datasets such as Ravdess and Crema-D were used to train and test the performance of the model in the emotion classification task. To evaluate model’s performance, training-validation accuracy graph, confusion matrix and overall metrics which include precision, recall, and F1-score are used. Ravdess dataset achieved a high accuracy of 83.3%, surprise, angry, disgust and sad were among those emotions which this model identified with great accuracy. Crema-D dataset achieved 82.7% accuracy, and showed solid performance in detecting neutral, fear, and happy emotions. Accuracy plots between training and validation demonstrated good generalization for the unseen data and confusion matrices highlighted the emotion categories where improvement could be made.",
            "source_url": "https:\/\/openalex.org\/W7127233843",
            "pdf_url": "",
            "doi": "",
            "handle": "",
            "repository_name": "NORMA",
            "source_record_id": "W7127233843",
            "other_sources": "",
            "verification_status": "needs_review",
            "created_at": "2026-11-15 16:52:58",
            "updated_at": "2026-11-15 16:52:58"
        }
    ]
}