Exploration of multisensory integration for adaptive activity recognition

In order for a machine to start performing a task, we need to first train it the way to solve the problem. When we encounter image classification problem, machine is not like humans, it is not difficult for us to recognize things but for computers, it has a series of steps to conduct in order to get...

Full description

Saved in:
Bibliographic Details
Main Author: Ke, Na
Other Authors: Mao Kezhi
Format: Final Year Project
Language:English
Published: 2017
Subjects:
Online Access:http://hdl.handle.net/10356/71706
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-71706
record_format dspace
spelling sg-ntu-dr.10356-717062023-07-07T15:42:15Z Exploration of multisensory integration for adaptive activity recognition Ke, Na Mao Kezhi School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering In order for a machine to start performing a task, we need to first train it the way to solve the problem. When we encounter image classification problem, machine is not like humans, it is not difficult for us to recognize things but for computers, it has a series of steps to conduct in order to get the classification result. The normal way to do image classification by a machine is by extracting the image features from a predefined data set first. Then use these features to train a classifier, and lastly use the classifier to make prediction for unseen images. However, when a human classifies the activities, except for the image features, we can also refer to the additional information to make decision. Especially for the activities that we never met before. This multisensory integration system of humans inspires me to search for other sources to make help improve the accuracy of activity classification. In this report, two classification method will be introduced, image-based classification and text-based classification. A process of how these two ways implement the classification function will explained in detail in the main content. In both classification process, two classifiers, SVM and Naïve Bayes classifiers will be used and the performance will be evaluated respectively. Lastly, a fusion of these two classification is developed, the decision score and the fusion-based classification accuracy is calculated. Followed by that is a conclusion of this project, the future work can be done for the further improvement of the project, and the program codes are included in the appendix. Bachelor of Engineering 2017-05-18T09:12:43Z 2017-05-18T09:12:43Z 2017 Final Year Project (FYP) http://hdl.handle.net/10356/71706 en Nanyang Technological University 63 p. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic DRNTU::Engineering::Electrical and electronic engineering
spellingShingle DRNTU::Engineering::Electrical and electronic engineering
Ke, Na
Exploration of multisensory integration for adaptive activity recognition
description In order for a machine to start performing a task, we need to first train it the way to solve the problem. When we encounter image classification problem, machine is not like humans, it is not difficult for us to recognize things but for computers, it has a series of steps to conduct in order to get the classification result. The normal way to do image classification by a machine is by extracting the image features from a predefined data set first. Then use these features to train a classifier, and lastly use the classifier to make prediction for unseen images. However, when a human classifies the activities, except for the image features, we can also refer to the additional information to make decision. Especially for the activities that we never met before. This multisensory integration system of humans inspires me to search for other sources to make help improve the accuracy of activity classification. In this report, two classification method will be introduced, image-based classification and text-based classification. A process of how these two ways implement the classification function will explained in detail in the main content. In both classification process, two classifiers, SVM and Naïve Bayes classifiers will be used and the performance will be evaluated respectively. Lastly, a fusion of these two classification is developed, the decision score and the fusion-based classification accuracy is calculated. Followed by that is a conclusion of this project, the future work can be done for the further improvement of the project, and the program codes are included in the appendix.
author2 Mao Kezhi
author_facet Mao Kezhi
Ke, Na
format Final Year Project
author Ke, Na
author_sort Ke, Na
title Exploration of multisensory integration for adaptive activity recognition
title_short Exploration of multisensory integration for adaptive activity recognition
title_full Exploration of multisensory integration for adaptive activity recognition
title_fullStr Exploration of multisensory integration for adaptive activity recognition
title_full_unstemmed Exploration of multisensory integration for adaptive activity recognition
title_sort exploration of multisensory integration for adaptive activity recognition
publishDate 2017
url http://hdl.handle.net/10356/71706
_version_ 1772825236207566848