Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 23 for “"Challenge Dataset"”.

  1. Using machine learning for stance detection

    … performance of various models on the fake news challenge dataset, including both traditional methods and neural networks. We find that the Enhanced Sequential Inference Model proposed for Natural Language Inference achieves great performance on the task of stance detection. To address the …

    texas Repository record for Using machine learning for stance detection (opens in a new tab)

  2. Robust Multiple Object Tracking Using ReID features and Graph Convolutional Networks

    … but the overall benefits outweigh the costs. The datasets used during this thesis are the UAVDT Benchmark and the MOT Challenge Dataset. These datasets cover aerial-based vehicle tracking and pedestrian tracking. The UAVDT Benchmark and MOT Challenge dataset feature crowded scenery as well as …

    rit Repository record for Robust Multiple Object Tracking Using ReID features and Graph Convolutional Networks (opens in a new tab)

  3. Remaining Useful Life Prediction of a Turbofan Engine Using Deep Layer Recurrent Neural Networks

    … and Health Management (PHM) conference Challenge dataset and C-MAPSS dataset provided by NASA results reveal a better predictive precision with respect to other ML algorithms.

    carleton Repository record for Remaining Useful Life Prediction of a Turbofan Engine Using Deep Layer Recurrent Neural Networks (opens in a new tab)

  4. Remaining Useful Life Prediction of Proton Exchange Membrane Fuel Cells Using Genetic Algorithm Based Nonlinear Autoregressive Exogenous Network

    … and validated with the 2014 IEEE PHM Data Challenge dataset, and compared with two common artificial neural network algorithms: genetic algorithm-based backpropagation neural network (GA-BPNN) and genetic algorithm-based time delay neural network (GA-TDNN). The results show that the …

    carleton Repository record for Remaining Useful Life Prediction of Proton Exchange Membrane Fuel Cells Using Genetic Algorithm Based Nonlinear Autoregressive Exogenous Network (opens in a new tab)

  5. Impacts of LLM-Based Text Normalization on Price Prediction

    … descriptions. Using the Mercari Price Suggestion Challenge dataset, we normalize 120,000 item descriptions with GPT-4o-mini and evaluate the impact across three modeling pipelines: a fine-tuned DistilBERT encoder with a linear regression head, a frozen DistilBERT encoder with a linear regression …

    reykjavik Repository record for Impacts of LLM-Based Text Normalization on Price Prediction (opens in a new tab)

  6. Ensemble video object cut in highly dynamic scenes

    … scenes, including the new Change Detection Challenge Dataset, demonstrate that the proposed ensemble video object cut method outperforms various state-of-the-art algorithms.

    missouri Repository record for Ensemble video object cut in highly dynamic scenes (opens in a new tab)

  7. Receptive Field Convolutional Neural Networks and Applications in Image Classification

    … of image classification using three challenging datasets: the UH 2013 hyperspectral dataset from the IEEE GRSS Data Fusion Contest, the Quick, Draw! Doodle Recognition Challenge dataset, and the Imagenet Large Scale Visual Recognition Challenge 2012 dataset. In addition, we propose a new deep …

    houston Repository record for Receptive Field Convolutional Neural Networks and Applications in Image Classification (opens in a new tab)

  8. Video Data Collection for Continuous Identity Assurance

    … effectively when trained with representative datasets. This thesis describes our effort at collecting a small dataset of multi-view videos of typical work session of several subjects to serve as a resource for other researchers of IA algorithms to evaluate and compare the performance of their …

    usf Repository record for Video Data Collection for Continuous Identity Assurance (opens in a new tab)

  9. Continuous Checkpointing System for Enhanced Model Recovery

    … computing environments and utilizes large datasets. Traditional checkpointing methods which periodically store the model's state on disk, are not only inefficient but can also cause potential disruptions to training. This research work focuses on increasing checkpointing frequency while …

    buffalo Repository record for Continuous Checkpointing System for Enhanced Model Recovery (opens in a new tab)

  10. Detección de melanoma cutáneo a través de la regla ABCD usando algoritmos de aprendizaje profundo

    … International Skin Imaging Collaboration (ISIC) Challenge Dataset}. For this, classic image processing techniques were used to calculate the ABCD characteristics of the entire database and then the training task was systematically assessed using: only the characteristics, only the images, and the …

    rosario Repository record for Detección de melanoma cutáneo a través de la regla ABCD usando algoritmos de aprendizaje profundo (opens in a new tab)

  11. Truck–Drone Collaborative Systems for Scalable Last-Mile Parcel Delivery

    … from the Amazon Last Mile Routing Research Challenge dataset (2021), ensuring practical relevance. Computational experiments and sensitivity analyses demonstrate that the proposed TDCD framework can significantly outperform conventional truck-only delivery systems, achieving substantial …

    ottawa-retro Repository record for Truck–Drone Collaborative Systems for Scalable Last-Mile Parcel Delivery (opens in a new tab)

  12. Real Time Fusion of Radioisotope Direction Estimation and Visual Object Tracking

    … 50 degrees when trained on a simple laboratory dataset. Under conditions similar to other state-of-the-art methods, the accuracy is comparable. YOLOv3 and SiamFC are chosen by evaluating advanced visual tracking methods in terms of speed and efficiency across multiple architectures, and in terms …

    ut-knoxville Repository record for Real Time Fusion of Radioisotope Direction Estimation and Visual Object Tracking (opens in a new tab)

  13. Towards robust conversational speech recognition and understanding

    … state-of-the-art performances on two benchmark datasets, the 2nd CHiME challenge (track 2) and Aurora-4, without front-end preprocessing, speaker adaptive training or multiple decoding passes. III. To study the specific case of conversational speech recognition in the presence of competing …

    gatech Repository record for Towards robust conversational speech recognition and understanding (opens in a new tab)

  14. Analysis of Cellular and Subcellular Morphology using Machine Learning in Microscopy Images

    … to identify minority and medium classes in the dataset and include them during training. Classification performance evaluated on the Human Protein Atlas Kaggle challenge dataset using F1-score shows that the proposed deep learning framework achieves better predictions than existing methods.

    unsw Repository record for Analysis of Cellular and Subcellular Morphology using Machine Learning in Microscopy Images (opens in a new tab)

  15. A study of different representation conventions during investigatory sensemaking

    … a small investigation using the IEEE 2011 VAST challenge dataset in which they structured information either as a timeline, an argumentation or as they wished (freeform). 30 participants took part in the study. The study used three levels of a between participants independent variable of …

    middlesex Download PDF for A study of different representation conventions during investigatory sensemaking (opens in a new tab)

  16. Nonlinear Classifier Stacking on Riemannian and Grassmann Manifolds with Application to Video Analysis

    … case of small and/or difficult classification datasets. The aforementioned two problems have been solved in two different ways: by splitting the entire datasets into functional groups depending on the classification difficulty using consensus of classifiers, and by embedding the data obtained …

    concordia Download PDF for Nonlinear Classifier Stacking on Riemannian and Grassmann Manifolds with Application to Video Analysis (opens in a new tab)

  17. Environment Modeling, Action Classification, and Control for Urban Automated Driving

    … outperform the baseline on the ICCV 2021 Road Challenge dataset. Furthermore, by integrating RAD-Net with the ADS' perception stack and the DRG, we demonstrate how a higher-order understanding of agent actions in the environment can improve decisions on a real AV system. The last ADS module …

    waterloo Repository record for Environment Modeling, Action Classification, and Control for Urban Automated Driving (opens in a new tab)

  18. Generalized Conditional Matching Algorithm for Ordered and Unordered Sets

    … building (clb). We present results on a large dataset of 8000 RGBD sequences spanning over 200 gesture classes, extracted from the ChaLearn Gesture Challenge dataset. The result is that there is significant improvement over the underlying distance used to compute conditional distance when …

    usf Repository record for Generalized Conditional Matching Algorithm for Ordered and Unordered Sets (opens in a new tab)

  19. Improving crop productivity through data-driven optimization and hybrid deep learning-based approaches

    … pressure on crop yields, exacerbating challenges already posed by increasing drought frequency, severe floods, heatwaves, and escalating pest and disease outbreaks. These environmental stressors underscore the urgency of adopting novel strategies to boost crop production and ensure food …

    iastate Repository record for Improving crop productivity through data-driven optimization and hybrid deep learning-based approaches (opens in a new tab)

Page 1 of 2