Cover Image

Performance evaluation of recurrent neural networks applied to indoor camera localization

Researchers in robotics and computer vision are experimenting with the image-based localization of indoor cameras. Implementation of indoor camera localization problems using a Convolutional neural network (CNN) or Recurrent neural network (RNN) is more challenging from a large image dataset because...

Full description

Saved in:
Bibliographic Details
Main Authors: Alam, Muhammad S., Hossain, AKM B., Mohamed, Farhan B.
Format: Article
Language:English
Published: IJETAE Publication House 2022
Subjects:
QA Mathematics
Online Access:http://eprints.utm.my/id/eprint/98713/1/MuhammadSAlam2022_PerformanceEvaluationofRecurrentNeura.pdf
http://eprints.utm.my/id/eprint/98713/
http://dx.doi.org/10.46338/ijetae0822_15
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.98713
record_format eprints
spelling my.utm.987132023-02-02T06:16:49Z http://eprints.utm.my/id/eprint/98713/ Performance evaluation of recurrent neural networks applied to indoor camera localization Alam, Muhammad S. Hossain, AKM B. Mohamed, Farhan B. QA Mathematics Researchers in robotics and computer vision are experimenting with the image-based localization of indoor cameras. Implementation of indoor camera localization problems using a Convolutional neural network (CNN) or Recurrent neural network (RNN) is more challenging from a large image dataset because of the internal structure of CNN or RNN. We can choose a preferable CNN or RNN variant based on the problem type and size of the dataset. CNN is the most flexible method for implementing indoor localization problems. Despite CNN's suitability for hyper-parameter selection, it requires a lot of training images to achieve high accuracy. In addition, overfitting leads to a decrease in accuracy. Introduce RNN, which accurately keeps input images in internal memory to solve these problems. Long-short-term memory (LSTM), Bi-directional LSTM (BiLSTM), and Gated recurrent unit (GRU) are three variants of RNN. We may choose the most appropriate RNN variation based on the problem type and dataset. In this study, we can recommend which variant is effective for training more speedily and which variant produces more accurate results. Vanishing gradient issues also affect RNNs, making it difficult to learn more data. Overcome the gradient vanishing problem by utilizing LSTM. The BiLSTM is an advanced version of the LSTM and is capable of higher performance than the LSTM. A more advanced RNN variant is GRU which is computationally more efficient than an LSTM. In this study, we explore a variety of recurring units for localizing indoor cameras. Our focus is on more powerful recurrent units like LSTM, BiLSTM, and GRU. Using the Microsoft 7-Scenes and InteriorNet datasets, we evaluate the performance of LSTM, BiLSTM, and GRU. Our experiment has shown that the BiLSTM is more efficient in accuracy than the LSTM and GRU. We also observed that the GRU is faster than LSTM and BiLSTM. IJETAE Publication House 2022-08 Article PeerReviewed application/pdf en http://eprints.utm.my/id/eprint/98713/1/MuhammadSAlam2022_PerformanceEvaluationofRecurrentNeura.pdf Alam, Muhammad S. and Hossain, AKM B. and Mohamed, Farhan B. (2022) Performance evaluation of recurrent neural networks applied to indoor camera localization. International Journal of Emerging Technology and Advanced Engineering, 12 (8). pp. 116-124. ISSN 2250-2459 http://dx.doi.org/10.46338/ijetae0822_15 DOI: 10.46338/ijetae0822_15
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
language English
topic QA Mathematics
spellingShingle QA Mathematics
Alam, Muhammad S.
Hossain, AKM B.
Mohamed, Farhan B.
Performance evaluation of recurrent neural networks applied to indoor camera localization
description Researchers in robotics and computer vision are experimenting with the image-based localization of indoor cameras. Implementation of indoor camera localization problems using a Convolutional neural network (CNN) or Recurrent neural network (RNN) is more challenging from a large image dataset because of the internal structure of CNN or RNN. We can choose a preferable CNN or RNN variant based on the problem type and size of the dataset. CNN is the most flexible method for implementing indoor localization problems. Despite CNN's suitability for hyper-parameter selection, it requires a lot of training images to achieve high accuracy. In addition, overfitting leads to a decrease in accuracy. Introduce RNN, which accurately keeps input images in internal memory to solve these problems. Long-short-term memory (LSTM), Bi-directional LSTM (BiLSTM), and Gated recurrent unit (GRU) are three variants of RNN. We may choose the most appropriate RNN variation based on the problem type and dataset. In this study, we can recommend which variant is effective for training more speedily and which variant produces more accurate results. Vanishing gradient issues also affect RNNs, making it difficult to learn more data. Overcome the gradient vanishing problem by utilizing LSTM. The BiLSTM is an advanced version of the LSTM and is capable of higher performance than the LSTM. A more advanced RNN variant is GRU which is computationally more efficient than an LSTM. In this study, we explore a variety of recurring units for localizing indoor cameras. Our focus is on more powerful recurrent units like LSTM, BiLSTM, and GRU. Using the Microsoft 7-Scenes and InteriorNet datasets, we evaluate the performance of LSTM, BiLSTM, and GRU. Our experiment has shown that the BiLSTM is more efficient in accuracy than the LSTM and GRU. We also observed that the GRU is faster than LSTM and BiLSTM.
format Article
author Alam, Muhammad S.
Hossain, AKM B.
Mohamed, Farhan B.
author_facet Alam, Muhammad S.
Hossain, AKM B.
Mohamed, Farhan B.
author_sort Alam, Muhammad S.
title Performance evaluation of recurrent neural networks applied to indoor camera localization
title_short Performance evaluation of recurrent neural networks applied to indoor camera localization
title_full Performance evaluation of recurrent neural networks applied to indoor camera localization
title_fullStr Performance evaluation of recurrent neural networks applied to indoor camera localization
title_full_unstemmed Performance evaluation of recurrent neural networks applied to indoor camera localization
title_sort performance evaluation of recurrent neural networks applied to indoor camera localization
publisher IJETAE Publication House
publishDate 2022
url http://eprints.utm.my/id/eprint/98713/1/MuhammadSAlam2022_PerformanceEvaluationofRecurrentNeura.pdf
http://eprints.utm.my/id/eprint/98713/
http://dx.doi.org/10.46338/ijetae0822_15
_version_ 1758578009690865664
score 13.211869

Similar Items