Essays about: "Multimodal learning"

Showing result 21 - 25 of 65 essays containing the words Multimodal learning.

  1. 21. Digital Accessibility for Swedish Second Language Learners A development project for an online museum resource

    University essay from Göteborgs universitet/Institutionen för pedagogik, kommunikation och lärande

    Author : Vasiliki Ziourka; [2022-07-27]
    Keywords : Design Thinking; Universal Design for Learning; digital accessibility; second language acquisition; digital learning resources;

    Abstract : Purpose: The overall purpose of this development project is to explore the struggles that Swedish second language learners (SSLL) encounter while using digital learning resources and to suggest digital accessibility improvements on the Human Nature Skola, which is a museum digital learning resource. Theory: This thesis is a development project which is based on Design Thinking theory and the framework of Universal Design for Learning (UDL). READ MORE

  3. 22. Duplicate detection of multimodal and domain-specific trouble reports when having few samples : An evaluation of models using natural language processing, machine learning, and Siamese networks pre-trained on automatically labeled data

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Viktor Karlstrand; [2022]
    Keywords : Duplicate detection; Bug reports; Trouble reports; Natural language processing; Information retrieval; Machine learning; Siamese neural network; Transformers; Automated data labeling; Shapley values; Dubblettdetektering; Felrapporter; Buggrapporter; Naturlig språkbehandling; Informationssökning; Maskininlärning; Siamesiska neurala nätverk; Transformatorer; Automatiserad datamärkning; Shapley-värden;

    Abstract : Trouble and bug reports are essential in software maintenance and for identifying faults—a challenging and time-consuming task. In cases when the fault and reports are similar or identical to previous and already resolved ones, the effort can be reduced significantly making the prospect of automatically detecting duplicates very compelling. READ MORE

  4. 23. Hybrid Deep Learning Model for Cellular Network Traffic Prediction : Case Study using Telecom Time Series Data, Satellite Imagery, and Weather Data

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Ali Shibli; [2022]
    Keywords : Cellular network traffic; multi-modal; satellite imagery; weather data; LSTM; CNN; time series; Trafic sur les réseaux cellulaires; multimodal; imagerie satellite; données météo; LSTM; CNN; séries temporelles; Förutsägelse av mobilnätstrafik; multimodal modell; satellitbilder; väderdata; LSTM; CNN; tidsseriein;

    Abstract : Cellular network traffic prediction is a critical challenge for communication providers, which is important for use cases such as traffic steering and base station resources management. Traditional prediction methods mostly rely on historical time-series data to predict traffic load, which often fail to model the real world and capture surrounding environment conditions. READ MORE

  5. 24. Pediatric Brain Tumor Type Classification in MR Images Using Deep Learning

    University essay from Linköpings universitet/Institutionen för medicinsk teknik

    Author : Tamara Bianchessi; [2022]
    Keywords : pediatric brain tumors; MR image analysis; deep learning; classification; model explainability;

    Abstract : Brain tumors present the second highest cause of death among pediatric cancers. About 60% are located in the posterior fossa region of the brain; among the most frequent types the ones considered for this project were astrocytomas, medulloblastomas, and ependymomas. READ MORE

  6. 25. Multimodal Machine Learning in Human Motion Analysis

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Jia Fu; [2022]
    Keywords : Multimodal machine learning; Modal fusion; Human motion classification; Multimodal maskininlärning; Modal fusion; Mänsklig rörelseklassificering;

    Abstract : Currently, most long-term human motion classification and prediction tasks are driven by spatio-temporal data of the human trunk. In addition, data with multiple modalities can change idiosyncratically with human motion, such as electromyography (EMG) of specific muscles and respiratory rhythm. READ MORE