1٬232 results

Export current results
CSV Excel JSON Up to 2٬000 records.
Not stated in source 2026 Needs review Available

Hybrid Machine Learning and Time-Series Modelling to Forecast Product Demand: A CRISP-DM Approach

Author
Niklas Virtanen
University
University of Vaasa
Country
Finland
Main specialisation
Natural Language Processing › Sentiment Analysis

Efficient demand forecasting can yield significant competitive advantage for companies in today’s market, making it a crucial process in supply chain management. By exploring and implementing modern demand forecasting models, encompassing time-series, machine…

Not stated in source 2026 Needs review Available

Automatisk särskiljning av fakta- och resoneringsfrågor i läsförståelsetest : En jämförande studie av BERT-baserade Transformer-modeller

Author
Elias Bergström Persson
University
Dalarna University Library
Country
Sweden
Main specialisation
Natural Language Processing › Large Language Models

Reading comprehension tests are a common way of assessing a language learner's ability. The difficulty of a reading comprehension test is often determined by the balance of factoid and inferential questions. While factoid questions test retrieval of explicitly…

Not stated in source 2026 Needs review Available

Federated Fine-Tuning of Mixture of Experts Vision Transformers

Author
Filippo Serafini
University
University of Bologna
Country
Italy
Main specialisation
Deep Learning & Neural Networks › Transformers

Mixture-of-Experts (MoE) architectures decouple representational capacity from per-token computational cost: each input activates only a few specialised experts, yielding far greater capacity than dense models at equal activation cost. Federated Learning (FL)…

Not stated in source 2026 Needs review

PERFORMANCE ANALYSIS OF TRANSFORMER-BASED LANGUAGE MODELS FOR DETECTION OF PHISHING EMAILS

Author
Chidozie Princewill Arannonu
University
Not available
Country
United States
Main specialisation
Natural Language Processing › Large Language Models

This thesis evaluates the performance and adversarial robustness of four transformer-based language models; BERT, RoBERTa, DistilBERT, and GPT-2 which were fine-tuned for binary phishing email classification. Two preprocessing configurations (Basic and Advance…

Not stated in source 2026 Needs review

Efficient fine-tuning of Transformer Models Under Hardware Constraints : An Empirical Study of LoRA and Knowledge Distillation

Author
Sai Mounika Karasu
University
Dalarna University Library
Country
Sweden
Main specialisation
Natural Language Processing › Large Language Models

Background Transformer-based language models dominate modern natural language processing but impose substantial computational costs during full fine-tuning, limiting accessibility on consumer-grade hardware. Knowledge Distillation and Low-Rank Adaptation (LoRA…

Not stated in source 2026 Needs review Available

Reinforcement Learning-Based Ordering

Author
Samuel Dahn ; Theodor Hallbeck
University
Lund University
Country
Sweden
Main specialisation
Reinforcement Learning › Predictive Analytics & Time Series

This thesis investigates the applicability and performance of reinforcement learn- ing (RL) for inventory management of spare parts in a single-echelon setting. Traditional inventory control methods, such as (R,Q)-policies, typically decou- ple forecasting and…

Not stated in source 2026 Needs review

Diversity in Reinforcement Learning

Author
Arno Feiden
University
University of Bonn
Country
Germany
Main specialisation
Computer Vision › Predictive Analytics & Time Series

Reinforcement learning is a machine learning paradigm that aims to develop optimal policies for discrete-time control problems based on quantitative feedback on the learner’s behaviour. Reinforcement learning is formulated as a gradient-based optimisation proc…

Not stated in source 2026 Needs review

سيميولوجيا السخرية الرقمية وإدارة الأزمات الإعلامية في المربع الدولي: دراسة تحليلية لنتائج مارس 2026 Semiology of Digital Satire and Media Crisis Management in the International Quadrant: An Analytical Study of March 2026 Outcomes

Author
Dalal AlDosari
University
Not available
Country
Not available
Main specialisation
Artificial Intelligence (general)

تستهدف هذه الدراسة تحليل دور السخرية الرقمية بوصفها أداة تواصلية في إدارة الأزمات الإعلامية وتشكيل مناخ الرأي العام خلال التوترات الجيوسياسية في ما يُعرف بـ “المربع الدولي” خلال مارس 2026. اعتمدت الدراسة على منهج النتنوغرافيا (Netnography) والتحليل السيميائي ل…

Not stated in source 2026 Needs review

أنا أشهدُ إذن أنا موجود ما بعد ديكارت: تأسيس الأنطولوجيا التوحيدية وفلسفة الشهود من الكوجيتو إلى الميثاق : قراءة في المعادلة الوجودية (B + F = NF)

Author
Fatiha Nesrine Bouzid
University
Not available
Country
Not available
Main specialisation
Artificial Intelligence (general)

يقدم هذا البحث نقضاً وجودياً لمقولة ديكارت أنا أفكر إذن أنا موجود، ويقدم بديلاً أنطولوجياً من النص القرآني تحت مسمى فلسفة الشهود التوحيدية . في عصر سيطر فيه الذكاء الاصطناعي على التفكير كعملية معالجة وظيفية، يثبت البحث أن التفكير لم يعد يميز الإنسان، بل الشهاد…

Not stated in source 2026 Needs review Available

أثرمنهج التعلم العميق القائم على الذكاء الاصطناعي على مهارة كتابة اللغة العربية لدى طلاب الصف الحادي عشر في المدرسة الثانوية الحكومية الثانية بيوجياكرتا ٢٠٢٦ = ATHR MANHAJ AL-TA'ALLUM AL-'AMIQ AL-QA'IM 'ALA AL-DHAKA' AL-ISTINA'I 'ALA MAHARAT KITABAT AL-LUGHAH AL-'ARABIYYAH LADA TULLAB AL-SAFF AL-HADI 'ASHAR FI AL-MADRASAH AL-THANAWIYYAH AL-HUKUMIYYAH AL-THANIYAH YOGYAKARTA 2026

Author
NIM.: 22104020014 Sri Fatimah
University
Sunan Kalijaga State Islamic University
Country
Indonesia
Main specialisation
Deep Learning & Neural Networks › Transformers

Penelitian ini dilatarbelakangi oleh masih rendahnya keterampilan menulis Bahasa Arab siswa kelas XI MAN 2 Yogyakarta, khususnya dalam menulis kalimat dan paragraf sederhana. Penelitian ini bertujuan untuk mengetahui pengaruh pendekatan deep learning berbasis…

Not stated in source 2026 Needs review Available

Predictive Maintenance in Modern Radar Systems using Machine Learning

Author
Klas Thorgren
University
Lund University
Country
Sweden
Main specialisation
AI in Healthcare › Recurrent Neural Networks / LSTM

This thesis investigated how machine learning-based anomaly detection can be applied to support predictive maintenance for a radar system using available monitoring data. An LSTM autoencoder was trained on selected healthy running operation and used to detect…

Not stated in source 2026 Needs review Available

Machine learning models for predictive maintenance in industrial systems

Author
Sandra Sanz Chamorro
University
Universidad Complutense de Madrid
Country
Spain
Main specialisation
Machine Learning › Predictive Analytics & Time Series

Este trabajo propone el diseño e implementación de un gemelo digital para la monitorización de la degradación de un filtro industrial además de la predicción de su vida útil restante (Remaining Useful Life, RUL). Para conseguirlo se usó un conjunto de datos fo…