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 42 for “"Bi-LSTM"”.

  1. Learning Peer Support Interactions via Bi-LSTM Graph Neural Networks for Suicide Risk Prediction

    … in online communities for individuals with bipolar disorder and leverage this information to predict suicide risk levels. We propose a model that uses contextualized posts and comments along with their sentiment features. By embedding these features into a peer support network, our model …

    usf Repository record for Learning Peer Support Interactions via Bi-LSTM Graph Neural Networks for Suicide Risk Prediction (opens in a new tab)

  2. Deciphering Emotional Responses to Music: A Fusion of Psychophysiological Data Analysis and Bi-LSTM Predictive Modeling

    This research explores the temporal patterns of psychophysiological responses to musical excerpts by analyzing the expansive Emotion in Motion dataset, the most comprehensive of its kind. Utilizing the Dynamic Time Warping and T-test analysis techniques, we examined data from participants across …

    vt Repository record for Deciphering Emotional Responses to Music: A Fusion of Psychophysiological Data Analysis and Bi-LSTM Predictive Modeling (opens in a new tab)

  3. Classification and Analysis of Osteoarthritis Using Unstructured Chart Notes and Structured Data from EMRs

    … including TF-IDF, Word2Vec, GloVe, FastText, and Bidirectional Encoder Representations from Transformers (BERT), in order to represent textual data as vectors. we presented a variety of statistical ML and DL models including Extreme Gradient Boosting (XGBoost), Random Forest (RF), Support Vector …

    queens Repository record for Classification and Analysis of Osteoarthritis Using Unstructured Chart Notes and Structured Data from EMRs (opens in a new tab)

  4. USING AI TOOLS TO UNMASK SARCASM

    … and has low inter- and intra-observer reliability. This research aims to improve sarcastic comment identification using a natural language processing approach, especially the BI-LSTM. The primary concern is to use fine-tuning methods to enhance the ways that strengthen the sarcasm …

    csusb Repository record for USING AI TOOLS TO UNMASK SARCASM (opens in a new tab)

  5. Named Entity Recognition With Deep Learning

    … In this thesis, we have mainly used the bidirectional LSTM model based on deep learning as an architecture, word embedding and Convolutional Neural Network (CNN) as a word-level and char-level feature extractor. The conditional random field (CRF) layer is used to output the predicted …

    auckland-tech Repository record for Named Entity Recognition With Deep Learning (opens in a new tab)

  6. Malware Detection and Next-Action Prediction using Learning-Based Methods

    … we introduce a comprehensive framework that combines natural language processing (NLP) techniques and machine learning (ML) algorithms for the early detection and prediction of malware activities. The core contribution of our research is the innovative application of text classification methods, …

    concordia Download PDF for Malware Detection and Next-Action Prediction using Learning-Based Methods (opens in a new tab)

  7. Rekurentiniai neuroniniai tinklai ir jų taikymas biomoksluose /

    … information technology, but also in the field of biosciences. Recurrent neural networks are successfully applied in genome research, proteomics, epidemiology and more. In this paper it was discussed that the monkeypox and SARS-CoV-2 viruses pose a threat to public health. Analysis of monkeypox …

    vilnius Repository record for Rekurentiniai neuroniniai tinklai ir jų taikymas biomoksluose / (opens in a new tab)

  8. A Study of Machine Learning based on Physical Load Classification

    … light-load and heavy-load. The traditional LSTM was able to achieve 71.1% accuracy for the multi-classification problem, and the Bi-LSTM was able to achieve a 74.5% correct classification rate. The excellent performance of multiple Bi-LSTMs for binary classification problems was exploited by …

    uwtsd Repository record for A Study of Machine Learning based on Physical Load Classification (opens in a new tab) Download PDF for A Study of Machine Learning based on Physical Load Classification (opens in a new tab)

  9. Automated Methods for Comparison and Generation of Privacy Policies

    … networks, including Long Short-Term Memory (LSTM) and bidirectional Long Short-Term Memory (bi-LSTM), to generate legal data practices and content in the three levels of paragraph, sentence, and data practice. Our findings have suggested that models trained on legal data practices using …

    guelph Repository record for Automated Methods for Comparison and Generation of Privacy Policies (opens in a new tab)

  10. Detection of Crypto-Ransomware Attack Using Deep Learning

    … models implemented in the proposed approach are Bi-directional Long Short-Term Memory (Bi-LSTM) and Convolutional Neural Networks (CNN). The deep learning models are compared against a classic machine learning model such as Logistic Regression (LR), Support Vector Machine (SVM), and Random Forest …

    kennesaw Repository record for Detection of Crypto-Ransomware Attack Using Deep Learning (opens in a new tab)

  11. A Novel Hybrid Model for Electricity Price Forecasting Based on the Integration of Bi-directional Long Short-Term Memory and Gated Recurrent Unit

    … electricity markets, influencing sale prices, bidding strategies, electricity dispatch, control, and the management of market. Notably, forecasting in a deregulated electricity market is challenging due to multiple factors such as high volatility, non-stationarity and multi-seasonality of …

    concordia Download PDF for A Novel Hybrid Model for Electricity Price Forecasting Based on the Integration of Bi-directional Long Short-Term Memory and Gated Recurrent Unit (opens in a new tab)

  12. Tuning and Optimising Concept Drift Detection

    … Second, we study a set of optimisers and tune a Bi-LSTM model parameters to maximize accuracy.

    mcmaster Repository record for Tuning and Optimising Concept Drift Detection (opens in a new tab)

  13. Gulf Cooperation Council Countries’ Electricity Sector Forecasting : Consumption Growth Issue and Renewable Energy Penetration Progress Challenges

    … The projects foreshadow the GCC countries’ ability to comply with future requirements and spearhead the renewable energy transition toward a more sustainable and equitable future. In addition, four forecasting models were developed to analyse the future performance of GCC power sectors, …

    lancaster Download PDF for Gulf Cooperation Council Countries’ Electricity Sector Forecasting : Consumption Growth Issue and Renewable Energy Penetration Progress Challenges (opens in a new tab)

  14. Insight Into Driver Behavior and Usage of ADAS Functions Using Machine Learning

    … were utilized to answer these questions: CNN, LSTM, a hybrid CNN-LSTM, and a Bi-LSTM autoencoder. The hybrid model achieved the highest performance. However, all models yielded poor predictive power, making it unclear whether the given dataset has a discernible pattern to predict and understand …

    chalmers Repository record for Insight Into Driver Behavior and Usage of ADAS Functions Using Machine Learning (opens in a new tab)

  15. Quantification of HVAC Energy Savings for Occupancy Sensing in Buildings: Hardware and Software

    … there are communication protocol incompatibility issues in the CPS interface between the sensors and the building HVAC server. Through either wired or wireless communication links, the server always needs to understand the communication schedule to receive occupant values from sensors. We …

    alabama Repository record for Quantification of HVAC Energy Savings for Occupancy Sensing in Buildings: Hardware and Software (opens in a new tab)

  16. Multi-label Classification and Sentiment Analysis on Textual Records

    … several classic deep learning models such as Bi-LSTM, RCNN, Attention mechanism and CNN to extract sentiment features. In the next step, a classification frame was designed to graded. At last, the start-of-art language model, BERT which use transfer learning method was employed. In conclusion, …

    mcmaster Repository record for Multi-label Classification and Sentiment Analysis on Textual Records (opens in a new tab)

  17. Disease Diagnosis Using Natural Language Processing and Deep Learning

    … models such as Logistic Regression and Bi-LSTM with transformer-based architectures built on BERT. Models are trained and evaluated with categorical cross-entropy loss and standard multi-class metrics, including accuracy, F1-score, and ROC-AUC, while hyperparameters such as learning …

    eiu Repository record for Disease Diagnosis Using Natural Language Processing and Deep Learning (opens in a new tab)

  18. A data-driven approach to evaluating the effectiveness and adverse outcomes of antidepressant exposure using longitudinal real-world EHR data

    … of life and well-being of millions. The variability in individual responses to antidepressant treatments necessitates a data-driven approach to improve predictive models and optimize therapeutic strategies. Leveraging a robust dataset from the PCORnet Common Data Model, which encompasses …

    missouri Repository record for A data-driven approach to evaluating the effectiveness and adverse outcomes of antidepressant exposure using longitudinal real-world EHR data (opens in a new tab)

  19. A Modular Multilevel Converter that Integrates Artificial Intelligence for Fault Locating and Protection

    … transmission has provided a variety of possibilities for renewable energy resources and regional substations to boost power supply reliability and operational flexibility. To accommodate this development and improve power system performance, the Modular Multilevel Converter (MMC) has been …

    auckland-tech Repository record for A Modular Multilevel Converter that Integrates Artificial Intelligence for Fault Locating and Protection (opens in a new tab)

  20. Sustainable Energy Management System for AIoT Solutions Using Multivariate and Multi-step Battery State of Charge Forecasting

    … it is important to prioritize the sustainability of AIoT solutions by a promising approach which is using renewable energy sources. While renewable energy offers numerous advantages, its intermittent nature necessitates effective power management systems. Developing a power management …

    concordia Download PDF for Sustainable Energy Management System for AIoT Solutions Using Multivariate and Multi-step Battery State of Charge Forecasting (opens in a new tab)

Page 1 of 3