Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 5 of 5
Full-Text Articles in Entire DC Network
Forecasting Bitcoin Prices Using N-Beats Deep Learning Architecture, Alikhan Bulatov
Forecasting Bitcoin Prices Using N-Beats Deep Learning Architecture, Alikhan Bulatov
Student Theses
The use of computationally intensive systems that employ machine learning algorithms is increasingly common in the field of finance. New state of the art deep learning architectures for time series forecasting are being developed each year making them more accurate than ever. This study evaluates the predictive power of the N-BEATS deep learning architecture trained on Bitcoin daily, hourly, and up-to-the-minute data in comparison with other popular time series forecasting methods such as LSTM and ARIMA. Prediction errors are measured with Mean Average Percentage Error (MAPE), and Root Mean Squared Error (RMSE). The results suggest that the developed N-BEATS model …
An Investigation Of Grammar Gender-Bias Correction For Google Translate When Translating From English To French, Ahmed Samy Merah
An Investigation Of Grammar Gender-Bias Correction For Google Translate When Translating From English To French, Ahmed Samy Merah
Student Theses
This work investigated how to address the Google Translate's gender-bias when translating from English to French. The developed solution is called GT gender-bias corrector that was built based on combining natural language processing and machine learning methods. The natural language processing was used to analyze the original sentences and their translations grammatically identifying parts of speech. The parts of speech analysis facilitated the identification of three patterns that are associated with the gender bias of Google Translate when translating from English to French. The three patterns were labeled simple, intermediate and complex to reflect the structure complexity. Samples of texts …
Using Machine Learning To Regulate Intensity Of Immersion Therapy Treatment Of Phobias Through Vital Feedback, Mark Beauchamp
Using Machine Learning To Regulate Intensity Of Immersion Therapy Treatment Of Phobias Through Vital Feedback, Mark Beauchamp
Student Theses
The treatment of acrophobia has been trying to keep up with newer technology with the incorporation of virtual reality for exposure therapy, but that approach still lacks automation and still leaves a good portion for human error. The proposed method introduced in this paper is that a machine learning model could replace the need for continuous human intervention. With a few different models of bridges and buildings and the ability for a machine learning model to dynamically alter the height of these building we could theoretically put the patient in the exact situation that will maximize the efficiency of their …
Fire Code Violation Detection, Salim Elewa
Fire Code Violation Detection, Salim Elewa
Student Theses
his paper explores the creation of an object detection system for mobile using YOLO(You Only Look Once) algorithm., a real-time object detection model that is developed to run on a portable device such as a cellphone that does not have a Graphics Processing Unit (GPU). This algorithm is utilized to detect fire code violations, specifically the obstructed door in a fire separation: the areas surround- ing the door opening shall be kept clear of anything that would be likely to ob- struct. The machine learning algorithm utilized has been fine-tuned to fit the model based on accuracy levels. The author …
Fall Detection Using Neural Networks, Warren Zajac
Fall Detection Using Neural Networks, Warren Zajac
Student Theses
Falls inside of the home is a major concern facing the aging population. Monitoring the home environment to detect a fall can prevent profound consequences due to delayed emergency response. One option to monitor a home environment is to use a camera-based fall detection system. Conceptual designs vary from 3D positional monitoring (multi-camera monitoring) to body position and limb speed classification. Research shows varying degree of success with such concepts when designed with multi-camera setup. However, camera-based systems are inherently intrusive and costly to implement. In this research, we use a sound-based system to detect fall events. Acoustic sensors are …