Browsing by Author "Potgieter J"

Now showing 1 - 7 of 7
  • Thumbnail Image
    Item
    A Performance-Optimized Deep Learning-based Plant Disease Detection Approach for Horticultural Crops of New Zealand
    (Institute of Electrical and Electronics Engineers, 23/08/2022) Saleem MH; Potgieter J; Arif K
    Deep learning-based plant disease detection has gained significant attention from the scientific community. However, various aspects of real horticultural conditions have not yet been explored. For example, the disease should be considered not only on leaves, but also on other parts of plants, including stems, canes, and fruits. Furthermore, the detection of multiple diseases in a single plant organ at a time has not been performed. Similarly, plant disease has not been identified in various crops in the complex horticultural environment with the same optimized/modified model. To address these research gaps, this research presents a dataset named NZDLPlantDisease-v1, consisting of diseases in five of the most important horticultural crops in New Zealand: kiwifruit, apple, pear, avocado, and grapevine. An optimized version of the best obtained deep learning (DL) model named region-based fully convolutional network (RFCN) has been proposed to detect plant disease using the newly generated dataset. After finding the most suitable DL model, the data augmentation techniques were successively evaluated. Subsequently, the effects of image resizers with interpolators, weight initializers, batch normalization, and DL optimizers were studied. Finally, performance was enhanced by empirical observation of position-sensitive score maps and anchor box specifications. Furthermore, the robustness/practicality of the proposed approach was demonstrated using a stratified k-fold cross-validation technique and testing on an external dataset. The final mean average precision of the RFCN model was found to be 93.80%, which was 19.33% better than the default settings. Therefore, this research could be a benchmark step for any follow-up research on automatic control of disease in several plant species.
  • Thumbnail Image
    Item
    A weight optimization-based transfer learning approach for plant disease detection of New Zealand vegetables
    (Frontiers Media, 25/10/2022) Saleem MH; Potgieter J; Arif K
    Deep learning (DL) is an effective approach to identifying plant diseases. Among several DL-based techniques, transfer learning (TL) produces significant results in terms of improved accuracy. However, the usefulness of TL has not yet been explored using weights optimized from agricultural datasets. Furthermore, the detection of plant diseases in different organs of various vegetables has not yet been performed using a trained/optimized DL model. Moreover, the presence/detection of multiple diseases in vegetable organs has not yet been investigated. To address these research gaps, a new dataset named NZDLPlantDisease-v2 has been collected for New Zealand vegetables. The dataset includes 28 healthy and defective organs of beans, broccoli, cabbage, cauliflower, kumara, peas, potato, and tomato. This paper presents a transfer learning method that optimizes weights obtained through agricultural datasets for better outcomes in plant disease identification. First, several DL architectures are compared to obtain the best-suited model, and then, data augmentation techniques are applied. The Faster Region-based Convolutional Neural Network (RCNN) Inception ResNet-v2 attained the highest mean average precision (mAP) compared to the other DL models including different versions of Faster RCNN, Single-Shot Multibox Detector (SSD), Region-based Fully Convolutional Networks (RFCN), RetinaNet, and EfficientDet. Next, weight optimization is performed on datasets including PlantVillage, NZDLPlantDisease-v1, and DeepWeeds using image resizers, interpolators, initializers, batch normalization, and DL optimizers. Updated/optimized weights are then used to retrain the Faster RCNN Inception ResNet-v2 model on the proposed dataset. Finally, the results are compared with the model trained/optimized using a large dataset, such as Common Objects in Context (COCO). The final mAP improves by 9.25% and is found to be 91.33%. Moreover, the robustness of the methodology is demonstrated by testing the final model on an external dataset and using the stratified k-fold cross-validation method.
  • Thumbnail Image
    Item
    Effects of In-Process Temperatures and Blending Polymers on Acrylonitrile Butadiene Styrene Blends
    (MDPI (Basel, Switzerland), 2021-12-01) Harris M; Potgieter J; Mohsin H; De Silva K; Guen M-JL
    Acrylonitrile butadiene styrene (ABS) is a renowned commodity polymer for additive manufacturing, particularly fused deposition modelling (FDM). The recent large-scale applications of 3D-printed ABS require stable mechanical properties than ever needed. However, thermochemical scission of butadiene bonds is one of the contemporary challenges affecting the overall ABS stability. In this regard, literature reports melt-blending of ABS with different polymers with high thermal resistance. However, the comparison for the effects of different polymers on tensile strength of 3D-printed ABS blends was not yet reported. Furthermore, the cumulative studies comprising both blended polymers and in-process thermal variables for FDM were not yet presented as well. This research, for the first time, presents the statistical comparison of tensile properties for the added polymers and in-process thermal variables (printing temperature and build surface temperature). The research presents Fourier transform infrared spectroscopy (FTIR) and thermogravimetric analysis (TGA) to explain the thermochemical reasons behind achieved mechanical properties. Overall, ABS blend with PP shows high tensile strength (≈31 MPa) at different combinations of in-process parameters. Furthermore, some commonalities among both blends are noted, i.e., the tensile strength improves with increase of surface (bed) and printing temperature.
  • Thumbnail Image
    Item
    Partial Biodegradable Blend with High Stability against Biodegradation for Fused Deposition Modeling
    (MDPI AG, 11/04/2022) Harris M; Mohsin H; Potgieter J; Ishfaq K; Archer R; Chen Q; De silva K; Guen M-JL; Wilson R; Arif K
    This research presents a partial biodegradable polymeric blend aimed for large-scale fused deposition modeling (FDM). The literature reports partial biodegradable blends with high contents of fossil fuel-based polymers (>20%) that make them unfriendly to the ecosystem. Furthermore, the reported polymer systems neither present good mechanical strength nor have been investigated in vulnerable environments that results in biodegradation. This research, as a continuity of previous work, presents the stability against biodegradability of a partial biodegradable blend prepared with polylactic acid (PLA) and polypropylene (PP). The blend is designed with intended excess physical interlocking and sufficient chemical grafting, which has only been investigated for thermal and hydrolytic degradation before by the same authors. The research presents, for the first time, ANOVA analysis for the statistical evaluation of endurance against biodegradability. The statistical results are complemented with thermochemical and visual analysis. Fourier transform infrared spectroscopy (FTIR) determines the signs of intermolecular interactions that are further confirmed by differential scanning calorimetry (DSC). The thermochemical interactions observed in FTIR and DSC are validated with thermogravimetric analysis (TGA). Scanning electron microscopy (SEM) is also used as a visual technique to affirm the physical interlocking. It is concluded that the blend exhibits high stability against soil biodegradation in terms of high mechanical strength and high mass retention percentage.
  • Thumbnail Image
    Item
    Partial Polymer Blend for Fused Filament Fabrication with High Thermal Stability
    (MDPI AG, 30/09/2021) Harris M; Potgieter J; Mohsin H; Ray S; Chen JQ; Arif K
    The materials for large scale fused filament fabrication (FFF) are not yet designed to resist thermal degradation. This research presents a novel polymer blend of polylactic acid with polypropylene for FFF, purposefully designed with minimum feasible chemical grafting and overwhelming physical interlocking to sustain thermal degradation. Multi-level general full factorial ANOVA is performed for the analysis of thermal effects. The statistical results are further investigated and validated using different thermo-chemical and visual techniques. For example, Fourier transform infrared spectroscopy (FTIR) analyzes the effects of blending and degradation on intermolecular interactions. Differential scanning calorimetry (DSC) investigates the nature of blending (grafting or interlocking) and effects of degradation on thermal properties. Thermogravimetric analysis (TGA) validates the extent of chemical grafting and physical interlocking detected in FTIR and DSC. Scanning electron microscopy (SEM) is used to analyze the morphology and phase separation. The novel approach of overwhelmed physical interlocking and minimum chemical grafting for manufacturing 3D printing blends results in high structural stability (mechanical and intermolecular) against thermal degradation as compared to neat PLA.
  • Thumbnail Image
    Item
    Weed Detection by Faster RCNN Model: An Enhanced Anchor Box Approach
    (MDPI AG, 29/06/2022) Saleem MH; Potgieter J; Arif KM
    To apply weed control treatments effectively, the weeds must be accurately detected. Deep learning (DL) has been quite successful in performing the weed identification task. However, various aspects of the DL have not been explored in previous studies. This research aimed to achieve a high average precision (AP) of eight classes of weeds and a negative (non-weed) class, using the DeepWeeds dataset. In this regard, a DL-based two-step methodology has been proposed. This article is the second stage of the research, while the first stage has already been published. The former phase presented a weed detection pipeline and consisted of the evaluation of various neural networks, image resizers, and weight optimization techniques. Although a significant improvement in the mean average precision (mAP) was attained. However, the Chinee apple weed did not reach a high average precision. This result provided a solid ground for the next stage of the study. Hence, this paper presents an in-depth analysis of the Faster Region-based Convolutional Neural Network (RCNN) with ResNet-101, the best-obtained model in the past step. The architectural details of the Faster RCNN model have been thoroughly studied to investigate each class of weeds. It was empirically found that the generation of anchor boxes affects the training and testing performance of the Faster RCNN model. An enhancement to the anchor box scales and aspect ratios has been attempted by various combinations. The final results, with the addition of 64 × 64 scale size, and aspect ratio of 1:3 and 3:1, produced the best classification and localization of all classes of weeds and a negative class. An enhancement of 24.95% AP was obtained in Chinee apple weed. Furthermore, the mAP was improved by 2.58%. The robustness of the approach has been shown by the stratified k-fold cross-validation technique and testing on an external dataset.
  • 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.