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 126 for “"Evaluation metrics"”.

  1. Safe shared autonomy and evaluation metrics

    Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2024-05-01

    uiuc Repository record for Safe shared autonomy and evaluation metrics (opens in a new tab)

  2. A Test Suite for Saliency Method Evaluation Metrics

    … processes by providing a comprehensive evaluation platform for saliency methods.

    mit Repository record for A Test Suite for Saliency Method Evaluation Metrics (opens in a new tab)

  3. Multi-Dimensional Evaluation Metrics for Chest X-Ray Reports

    … accuracy is the most important factor. Current evaluation metrics evaluate reports in one dimension. This work proposes the use of multiple dimensions (factual correctness, comprehensiveness, style, and overall quality) to better capture evaluation preferences of a clinical text generating model …

    mit Repository record for Multi-Dimensional Evaluation Metrics for Chest X-Ray Reports (opens in a new tab)

  4. Wingsail design methodology and performance evaluation metrics for autonomous sailing

    This dissertation explores an innovative approach to the design of aerodynamically-actuated wingsails, along with advancements in marine vehicle autonomy focused on vessel tracking and collision avoidance. The first segment of this research introduces a deterministic wingsail design optimization …

    woods-hole Repository record for Wingsail design methodology and performance evaluation metrics for autonomous sailing (opens in a new tab)

  5. Transformation Tolerance of Facial Recognition Technology and Informative Evaluation Metrics

    … methodological inspiration for more informative evaluation techniques, including the characterization of recognition performance as a function of a quantifiable input transformation. This work performs such an analysis. The performance scores of five state-of-the-art FR models are characterized …

    mit Repository record for Transformation Tolerance of Facial Recognition Technology and Informative Evaluation Metrics (opens in a new tab)

  6. Wingsail Design Methodology and Performance Evaluation Metrics for Autonomous Sailing

    This dissertation explores an innovative approach to the design of aerodynamically-actuated wingsails, along with advancements in marine vehicle autonomy focused on vessel tracking and collision avoidance. The first segment of this research introduces a deterministic wingsail design optimization …

    mit Repository record for Wingsail Design Methodology and Performance Evaluation Metrics for Autonomous Sailing (opens in a new tab)

  7. Fault Attacks on Cryptosystems: Novel Threat Models, Countermeasures and Evaluation Metrics

    … secure systems against fault attacks • Building evaluation metrics to measure the security of designs In this regard, my thesis has covered the first bullet, by proposing the Differential Fault Intensity Analysis (DFIA) based on the biased fault model. The biased fault model in this attack means …

    vt Repository record for Fault Attacks on Cryptosystems: Novel Threat Models, Countermeasures and Evaluation Metrics (opens in a new tab)

  8. Evaluation of Automatic Text Summarization Using Synthetic Facts

    … However, the unreliability of the existing evaluation metrics hinders its practical usage and slows down its progress. To address this issue, we propose an automatic reference-less text summarization evaluation system with dynamically generated synthetic facts. We hypothesize that if a …

    calpoly Repository record for Evaluation of Automatic Text Summarization Using Synthetic Facts (opens in a new tab)

  9. Evaluating websites using a practical quality model.

    Many of the existing website evaluation methods and criteria for evaluating website quality are not able to sufficiently assess the performance and quality of a website, and most of them focus on usability and accessibility. This thesis aims at proposing the website quality metrics and methods to …

    de-montfort Repository record for Evaluating websites using a practical quality model. (opens in a new tab)

  10. A novel dependency-based evaluation metric for machine translation

    Automatic evaluation measures such as BLEU (Papineni et al. (2002)) and NIST (Doddington (2002)) are indispensable in the development of Machine Translation (MT) systems, because they allow MT developers to conduct frequent, fast, and cost-effective evaluations of their evolving translation models. …

    dcu Repository record for A novel dependency-based evaluation metric for machine translation (opens in a new tab)

  11. A Systematic Evaluation of Climate Services and Decision Support Tools for Climate Change Adaptation

    … support tools based on previously proposed evaluation framework. This evaluation framework originally consists of four design elements which are divided into nine evaluation metrics for this study. These evaluation metrics are: identification of decision making context, discussion of the …

    vt Repository record for A Systematic Evaluation of Climate Services and Decision Support Tools for Climate Change Adaptation (opens in a new tab)

  12. Methodological and extrinsic challenges in offline evaluation of recommender systems

    … be attributed to the misapplication of offline evaluation protocols. These results highlight the potential for both methodological and extrinsic aspects of evaluation to impact results. Furthermore, specialised recommendation tasks, such as sequential and cross-domain recommendation, …

    helsinki Repository record for Methodological and extrinsic challenges in offline evaluation of recommender systems (opens in a new tab)

  13. Code Summarization and Program Synthesis with Large Language Models

    … against appropriate baselines using suitable evaluation metrics.

    mit Repository record for Code Summarization and Program Synthesis with Large Language Models (opens in a new tab)

  14. A comparison of approaches for processing the time dimension in automatic cover song identification

    … THAs in a testing environment using various evaluation metrics. While the exploratory phase yields promising results for some THAs, the baseline employed during the retrieval phase cannot be outperformed. The results qualitatively show that longer chunk lengths in THAs typically lead to …

    humboldt-diss Repository record for A comparison of approaches for processing the time dimension in automatic cover song identification (opens in a new tab)

  15. A comparative analysis of machine learning models for forecasting JSE Stock Returns

    … variables comprise nine firm-specific financial metrics, motivated by prior research. The sample is divided into a training period (2005–2016) and a testing period (2016–2021), further split into 1-year, 3-year, and 5-year testing intervals. The results show that the LSTM model performsbest …

    cape-town Repository record for A comparative analysis of machine learning models for forecasting JSE Stock Returns (opens in a new tab)

  16. Automated Self-Admitted Technical Debt Tracking, Classification, and Repayment for Sustainable Software Development

    … for Java) and introducing three new, effective evaluation metrics: BLEU-diff, CrystalBLEU-diff, and LEMOD. Using our new benchmarks and evaluation metrics, we evaluate two types of automated SATD repayment methods: fine-tuning smaller models, and prompt engineering with five large-scale models. …

    queens Repository record for Automated Self-Admitted Technical Debt Tracking, Classification, and Repayment for Sustainable Software Development (opens in a new tab)

  17. Multimodal machine translation

    … tested on multiple datasets using the automatic evaluation metrics like METEOR and BLEU. The experiments show that the proposed models outperform the text-only baseline model.

    uiuc Repository record for Multimodal machine translation (opens in a new tab)

  18. Measuring global progress towards a transition away from mercury use in artisanal and small-scale gold mining

    … interviews related to ASGM and other applicable evaluation approaches. The study concludes by proposing the development of a framework approach for measuring progress and by offering guiding principles and recommendations. Recommendations for the framework approach include: on-going and enhanced …

    royalroads Repository record for Measuring global progress towards a transition away from mercury use in artisanal and small-scale gold mining (opens in a new tab)

  19. Automated Discovery of Big Data Workload Types

    … techniques are compared in terms of different evaluation metrics, and the ones with the highest performance are introduced. The DBSCAN algorithm has shown the best performance and adequacy with 71% and 80% for the Purity, and Windows Type Accuracy (Awt), respectively. Ultimately, the …

    carleton Repository record for Automated Discovery of Big Data Workload Types (opens in a new tab)

  20. Query-Focused Abstractive Summarization using Neural Networks

    … and have reported our scores using various evaluation metrics.

    lethbridge Repository record for Query-Focused Abstractive Summarization using Neural Networks (opens in a new tab)

Page 1 of 7