Journal Articles

Permanent URI for this collectionhttps://mro.massey.ac.nz/handle/10179/7915

Browse

Subject: search.filters.subject.convolutional neural network

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Accurate Facial Temperature Measurement Using Low-Cost Thermal Camera for Indoor Thermal Comfort Applications
    (MDPI AG, Basel, 2025-11) Ahsan M; Shahzad W; Arif KM
    Non-contact measurement of human skin temperature is an important area of research. Infrared temperature devices have played a critical role in measuring skin temperature without physical contact. Thermal cameras have also been employed for non-contact skin temperature measurements. However, both infrared devices and thermal cameras have limitations that restrict their use in the building industry for assessing occupant thermal comfort. The building industry requires sophisticated equipment capable of measuring human temperature non-invasively and, through integration with building control systems, adjusting the environment to meet occupants’ thermal comfort needs. Unfortunately, standard thermal cameras and infrared temperature sensors are not designed with building applications in mind. This paper proposes an affordable and building-compatible thermal camera designed to measure occupant skin temperature via a non-contact method, enabling better integration with building control systems to support occupant comfort. Experimental results demonstrate that the proposed system can reliably capture facial skin temperature and establish a quantifiable relationship between facial and room temperatures. Moreover, this provides a foundation for future real-time thermal comfort and building-control applications.
  • Thumbnail Image
    Item
    Weed Identification by Single-Stage and Two-Stage Neural Networks: A Study on the Impact of Image Resizers and Weights Optimization Algorithms
    (Frontiers Media, 25/04/2022) Saleem MH; Velayudhan KK; Potgieter J; Arif K
    The accurate identification of weeds is an essential step for a site-specific weed management system. In recent years, deep learning (DL) has got rapid advancements to perform complex agricultural tasks. The previous studies emphasized the evaluation of advanced training techniques or modifying the well-known DL models to improve the overall accuracy. In contrast, this research attempted to improve the mean average precision (mAP) for the detection and classification of eight classes of weeds by proposing a novel DL-based methodology. First, a comprehensive analysis of single-stage and two-stage neural networks including Single-shot MultiBox Detector (SSD), You look only Once (YOLO-v4), EfficientDet, CenterNet, RetinaNet, Faster Region-based Convolutional Neural Network (RCNN), and Region-based Fully Convolutional Network (RFCN), has been performed. Next, the effects of image resizing techniques along with four image interpolation methods have been studied. It led to the final stage of the research through optimization of the weights of the best-acquired model by initialization techniques, batch normalization, and DL optimization algorithms. The effectiveness of the proposed work is proven due to a high mAP of 93.44% and validated by the stratified k-fold cross-validation technique. It was 5.8% improved as compared to the results obtained by the default settings of the best-suited DL architecture (Faster RCNN ResNet-101). The presented pipeline would be a baseline study for the research community to explore several tasks such as real-time detection and reducing the computation/training time. All the relevant data including the annotated dataset, configuration files, and inference graph of the final model are provided with this article. Furthermore, the selection of the DeepWeeds dataset shows the robustness/practicality of the study because it contains images collected in a real/complex agricultural environment. Therefore, this research would be a considerable step toward an efficient and automatic weed control system.