• Home
  • Search
  • From time-series to 2D images for building occupancy prediction using deep transfer learning
  • Cite Icon65
  • https://doi.org/10.1016/j.engappai.2022.105786Copy DOI Icon

From time-series to 2D images for building occupancy prediction using deep transfer learning

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Building occupancy information could aid energy preservation while simultaneously maintaining the end-user comfort level. Energy conservation becomes essential since energy resources are scarce and human dependency on appliances is only exponentially increasing. While intrusive sensors (i.e., cameras and microphones) can raise privacy concerns, this paper presents an innovative non-intrusive occupancy detection approach using environmental sensor data (e.g., temperature, humidity, carbon dioxide (CO2), and light sensors). The proposed scheme transforms multivariate time-series data into images for better encoding and extracting relevant features. The utilized image transformation method is based on data normalization and matrix conversion. Precisely, by representing time-series in 2D space, an encoding kernel can move in two directions while it can move only in one direction when applied to a 1D signal. Moreover, machine learning (ML) and deep learning (DL) techniques are utilized to classify occupancy patterns. Several simulations are used to evaluate the approach; mainly, we investigated pre-trained and custom convolutional neural network (CNN) models. The latter attained an accuracy of 99.00%. Additionally, pixel data are extracted from the generated images and subjected to traditional ML methods. Throughout the numerous comparison settings, it was observed that the latter strategy provided the optimal balance of 99.42% accuracy performance and minimal training time across the occupancy datasets.

Loading PDF

Similar Papers
  • Research Article

Multi-task deep transfer learning for complicated seismic dynamic response prediction in slope systems

  • Mar 01, 2026
  • Geoscience Frontiers
  • Xu Han +4
  • PDF
  • Research Article
  • Citations1

Comparison of Deep Learning and Traditional Machine Learning Classification Performance in a SSVEP Based Brain Computer Interface

  • Jul 30, 2022
  • Balkan Journal of Electrical and Computer Engineering
  • Zafer İşcan
  • Research Article
  • Citations3

UAV-Multispectral Based Maize Lodging Stress Assessment with Machine and Deep Learning Methods

  • Dec 26, 2024
  • Agriculture
  • Minghu Zhao +4
  • Research Article
  • Citations4

Comparison of Deep Learning and Traditional Machine Learning Models for Predicting Mild Cognitive Impairment Using Plasma Proteomic Biomarkers.

  • Mar 08, 2025
  • International journal of molecular sciences
  • Kesheng Wang +6
  • PDF
  • Research Article
  • Citations21

Comparison of Deep and Traditional Learning Methods for Email Spam Filtering

  • Jan 01, 2021
  • International Journal of Advanced Computer Science and Applications
  • Abdullah Sheneamer
  • Research Article
  • Citations191

A systematic review of machine learning methods applied to fuel cells in performance evaluation, durability prediction, and application monitoring

  • Nov 28, 2022
  • International Journal of Hydrogen Energy
  • Wuyi Ming +10
  • Research Article
  • Citations9

Leveraging Attention-Based Deep Learning in Binary Classification for Early-Stage Breast Cancer Diagnosis.

  • Mar 13, 2025
  • Diagnostics (Basel, Switzerland)
  • Lama A Aldakhil +3
  • PDF
  • Research Article
  • Citations73

Exhaustive Study into Machine Learning and Deep Learning Methods for Multilingual Cyberbullying Detection in Bangla and Chittagonian Texts

  • Apr 26, 2024
  • Electronics
  • Tanjim Mahmud +2
  • PDF
  • Research Article
  • Citations3

A Review on Machine Learning and Deep Learning Methods on Medical Image Classification

  • Jun 15, 2024
  • International Journal of Scientific Research in Computer Science, Engineering and Information Technology
  • Dr Sheshang Degadwala Degadwala +1
  • Research Article

Multi-Omic Age Associations Identified With Artificial Intelligence (AI)

  • Dec 01, 2025
  • Innovation in Aging
  • Daniel Evans +4
  • PDF
  • Research Article
  • Citations23

Medical Image Segmentation Algorithm Based on Optimized Convolutional Neural Network-Adaptive Dropout Depth Calculation

  • May 15, 2020
  • Complexity
  • Feng-Ping An +1
  • Research Article
  • Citations18

Small data, big challenges: Machine- and deep-learning strategies for data-limited drug discovery.

  • Feb 01, 2026
  • Advanced drug delivery reviews
  • Nazreen Pallikkavaliyaveetil +1
  • Research Article
  • Citations6

Comparison review of image classification techniques for early diagnosis of diabetic retinopathy

  • Sep 05, 2024
  • Biomedical Physics & Engineering Express
  • Chayarat Wangweera +1
  • Research Article
  • Citations326

Development of Efficient CNN model for Tomato crop disease identification

  • Jul 04, 2020
  • Sustainable Computing: Informatics and Systems
  • Mohit Agarwal +2
  • Research Article
  • Citations7

Deep Learning Based Superconducting Radio-Frequency Cavity Fault Classification at Jefferson Laboratory.

  • Jan 03, 2022
  • Frontiers in Artificial Intelligence
  • Lasitha Vidyaratne +6
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.