ORCID Profile
0000-0003-1904-3062
Current Organisations
Deakin University
,
University of New South Wales Canberra
,
Hajee Mohammad Danesh Science and Technology University
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: MDPI AG
Date: 13-07-2023
DOI: 10.3390/RS15143532
Abstract: Object classification in hyperspectral images involves accurately categorizing objects based on their spectral characteristics. However, the high dimensionality of hyperspectral data and class imbalance pose significant challenges to object classification performance. To address these challenges, we propose a framework that incorporates dimensionality reduction and re-s ling as preprocessing steps for a deep learning model. Our framework employs a novel subgroup-based dimensionality reduction technique to extract and select the most informative features with minimal redundancy. Additionally, the data are res led to achieve class balance across all categories. The reduced and balanced data are then processed through a hybrid CNN model, which combines a 3D learning block and a 2D learning block to extract spectral–spatial features and achieve satisfactory classification accuracy. By adopting this hybrid approach, we simplify the model while improving performance in the presence of noise and limited s le size. We evaluated our proposed model on the Salinas scene, Pavia University, and Kennedy Space Center benchmark hyperspectral datasets, comparing it to state-of-the-art methods. Our object classification technique achieves highly promising results, with overall accuracies of 99.98%, 99.94%, and 99.46% on the three datasets, respectively. This proposed approach offers a compelling solution to overcome the challenges of high dimensionality and class imbalance in hyperspectral object classification.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: MDPI AG
Date: 20-02-2023
DOI: 10.3390/RS15041147
Abstract: Hyperspectral images (HSIs) are one of the most successfully used tools for precisely and potentially detecting key ground surfaces, vegetation, and minerals. HSIs contain a large amount of information about the ground scene therefore, object classification becomes the most difficult task for such a high-dimensional HSI data cube. Additionally, the HSI’s spectral bands exhibit a high correlation, and a large amount of spectral data creates high dimensionality issues as well. Dimensionality reduction is, therefore, a crucial step in the HSI classification pipeline. In order to identify a pertinent subset of features for effective HSI classification, this study proposes a dimension reduction method that combines feature extraction and feature selection. In particular, we exploited the widely used denoising method minimum noise fraction (MNF) for feature extraction and an information theoretic-based strategy, cross-cumulative residual entropy (CCRE), for feature selection. Using the normalized CCRE, minimum redundancy maximum relevance (mRMR)-driven feature selection criteria were used to enhance the quality of the selected feature. To assess the effectiveness of the extracted features’ subsets, the kernel support vector machine (KSVM) classifier was applied to three publicly available HSIs. The experimental findings manifest a discernible improvement in classification accuracy and the qualities of the selected features. Specifically, the proposed method outperforms the traditional methods investigated, with overall classification accuracies on Indian Pines, Washington DC Mall, and Pavia University HSIs of 97.44%, 99.71%, and 98.35%, respectively.
Publisher: Trans Tech Publications, Ltd.
Date: 04-2014
DOI: 10.4028/WWW.SCIENTIFIC.NET/AMR.925.379
Abstract: Disposal of petroleum-based plastics has become a major concern due to its resistance to chemical, physical and biological degradation. As such, the production of an alternative biodegradable material from renewable sources is beneficial. This study aims to produce a polymer blend film, of enhanced formability and durability, from cellulose and chitin, the two most abundant naturally-occurring biodegradable polymers in the environment. Chitin was initially extracted from Portunus pelagicus shells through demineralization and deproteinization. The crude chitin is of comparable crystallinity with the commercially-available. However, other proteins were speculated to be present as indicated by the extra peaks in the XRD profile. This was then followed by the dissolution of the polymer powders in LiCl/DMAc, blending, casting, forming, cold-pressing and drying. The independent variables considered were cellulose-chitin ratio and the forming time. From the results, s les formed after 24 hours are relatively thinner, softer and more flexible. In addition, the best s le with UTS at 27.36 MPa was that of 80:20 cellulose-chitin, while the worst at 14.79 MPa was that of 20:80 cellulose-chitin both formed after 24 hours. ANOVA revealed that neither the main factors nor the interaction significantly affected the measured values. Lastly, thermal and biological degradation tests showed that the film started to degrade at 308°C and supported 4.9 x 10 3 and 3.8 x 10 4 CFU of mold and bacteria, respectively.
Publisher: Research Square Platform LLC
Date: 04-09-2023
Location: Bangladesh
Location: Bangladesh
No related grants have been discovered for Myra Ruth Poblete.