Assessment of machine learning classifiers in mapping the cocoa-forest mosaic landscape of Ghana

Ashiagbor, George; Asare-Ansah, Oparebea; Amoah, Emmanuel; Asante, Winston Adams; Asare, Yaw Mensah

doi:10.1016/j.sciaf.2023.e01718

Cited by 3 publications

(4 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thematic land use classes were classified based on the use of the multi-spectral bands from L8-OLI imagery. It is imperative to underscore the variations in area coverage for land cover classes amongst the MLAs (Figure 6); these results align with comparative research [17,18,73] that examined machine learning classifiers in mapping LULC classes. This reflects the variability in the inherent design of the machine learning models [73,74] and the dimensionality of the data to be processed [46].…”

Section: Discussionmentioning

confidence: 53%

“…It is imperative to underscore the variations in area coverage for land cover classes amongst the MLAs (Figure 6); these results align with comparative research [17,18,73] that examined machine learning classifiers in mapping LULC classes. This reflects the variability in the inherent design of the machine learning models [73,74] and the dimensionality of the data to be processed [46]. Thus, results from the RF model were used in the discussion of this work as it was the best-performing classifier.…”

Section: Discussionmentioning

confidence: 53%

“…The findings of this study indicate that RF outperformed all the MLAs with slightly higher OA and Kappa values than those recorded by the SVM model as the second-best classifier, yielding more accurate results than ANN and NB. Previous studies [9,16,17,73] have debated the comparison of RF and SVM and concluded that RF is resilient in classifying complex LULC classes. Its success is credited to its insensitivity to sample size and the advantage of the random multi-decision trees in generalization which are immune to outliers.…”

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Evaluating Machine-Learning Algorithms for Mapping LULC of the uMngeni Catchment Area, KwaZulu-Natal

Bhungeni,

Ramjatan,

Gebreslasie

2024

Remote Sensing

View full text Add to dashboard Cite

Analysis of land use/land cover (LULC) in catchment areas is the first action toward safeguarding freshwater resources. LULC information in the watershed has gained popularity in the natural science field as it helps water resource managers and environmental health specialists develop natural resource conservation strategies based on available quantitative information. Thus, remote sensing is the cornerstone in addressing environmental-related issues at the catchment level. In this study, the performance of four machine learning algorithms (MLAs), namely Random Forests (RFs), Support Vector Machines (SVMs), Artificial Neural Networks (ANNs), and Naïve Bayes (NB), were investigated to classify the catchment into nine relevant classes of the undulating watershed landscape using Landsat 8 Operational Land Imager (L8-OLI) imagery. The assessment of the MLAs was based on a visual inspection of the analyst and commonly used assessment metrics, such as user’s accuracy (UA), producers’ accuracy (PA), overall accuracy (OA), and the kappa coefficient. The MLAs produced good results, where RF (OA = 97.02%, Kappa = 0.96), SVM (OA = 89.74%, Kappa = 0.88), ANN (OA = 87%, Kappa = 0.86), and NB (OA = 68.64%, Kappa = 0.58). The results show the outstanding performance of the RF model over SVM and ANN with a significant margin. While NB yielded satisfactory results, its sensitivity to limited training samples could primarily influence these results. In contrast, the robust performance of RF could be due to an ability to classify high-dimensional data with limited training data.

show abstract

Section: Discussionmentioning

confidence: 53%

Section: Discussionmentioning

confidence: 53%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluating Machine-Learning Algorithms for Mapping LULC of the uMngeni Catchment Area, KwaZulu-Natal

Bhungeni,

Ramjatan,

Gebreslasie

2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The comparison of the RF and SVM has been debated in many previous studies. [18] found RF to be robust in assessing LULC using multiple MLAs, as did [64] in mapping the Cocco forest classes using various MLAs. They attributed the performance of the model to its less sensitivity to training data size and the advantage of the random multi-decision trees in generalization.…”

Section: Discussionmentioning

confidence: 89%

Machine-Learning Algorithms for Mapping LULC of the uMngeni Catchment Area, KwaZulu-Natal

Bhungeni,

Ramjatan,

Gebreslasie

2024

Preprint

View full text Add to dashboard Cite

Analysis of land use/land cover (LULC) in the catchment areas is the first action toward safeguarding the freshwater resources. The LULC information in the watershed has gained popularity in the natural science field as it helps water resource managers and environmental health specialists develop natural resource conservation strategies based on available quantitative information. Thus, remote sensing is the cornerstone in addressing environmental-related issues at the catchment level. In this study, the performance of four machine learning algorithms (MLAs), such as Random Forests (RF), Support Vector Machine (SVM), Artificial Neural Networks (ANN), and Naïve Bayes (NB) was investigated to classify the catchment into nine relevant classes of the undulating watershed landscape using Landsat 8 Operational Land Imager (L8-OLI) imagery. The assessment of the MLAs were based on the visual inspection of the analyst and the commonly used assessment metrics, such as user’s accuracy (UA), producers’ accuracy (PA), overall accuracy (OA), and kappa coefficient. The MLAs produced good results, where RF (OA= 97.02%, Kappa= 0.96), SVM (OA= 89.74 %, Kappa= 0.88), ANN (OA= 87%, Kappa= 0.86), and NB (OA= 68.64 Kappa= 0.58). The results show the outstanding performance of the RF model over SVM and ANN with a small margin. While NB yielded satisfactory results, which could be primarily influenced by its sensitivity to limited training samples. In contrast, the robust performance of RF could be due to an ability to classify high-dimensional data with limited training data.

show abstract

Integrating Artificial Intelligence in Disease Diagnosis, Treatment, and Formulation Development: A Review

Kumar,

Ahmed

et al. 2023

Asian J Pharm Clin Res

View full text Add to dashboard Cite

Artificial intelligence (AI) is rapidly advancing and significantly impacting clinical care and treatment. Machine learning and deep learning, as core digital AI technologies, are being extensively applied to support diagnosis and treatment. With the progress of digital health-care technologies such as AI, bioprinting, robotics, and nanotechnology, the health-care landscape is transforming. Digitization in health-care offers various opportunities, including reducing human error rates, improving clinical outcomes, and monitoring longitudinal data. AI techniques, ranging from learning algorithms to deep learning, play a critical role in several health-care domains, such as the development of new health-care systems, improvement of patient information and records, and treatment of various ailments. AI has emerged as a powerful scientific tool, capable of processing and analyzing vast amounts of data to support decision-making. Numerous studies have demonstrated that AI can perform on par with or outperform humans in crucial medical tasks, including disease detection. However, despite its potential to revolutionize health care, ethical considerations must be carefully addressed before implementing AI systems and making informed decisions about their usage. Researchers have utilized various AI-based approaches, including deep and machine learning models, to identify diseases that require early diagnosis, such as skin, liver, heart, and Alzheimer’s diseases. Consequently, related work presents different methods for disease diagnosis along with their respective levels of accuracy, including the Boltzmann machine, K nearest neighbor, support vector machine, decision tree, logistic regression, fuzzy logic, and artificial neural network. While AI holds immense promise, it is likely to take decades before it completely replaces humans in various medical operations.

show abstract

Assessment of machine learning classifiers in mapping the cocoa-forest mosaic landscape of Ghana

Cited by 3 publications

References 49 publications

Evaluating Machine-Learning Algorithms for Mapping LULC of the uMngeni Catchment Area, KwaZulu-Natal

Evaluating Machine-Learning Algorithms for Mapping LULC of the uMngeni Catchment Area, KwaZulu-Natal

Machine-Learning Algorithms for Mapping LULC of the uMngeni Catchment Area, KwaZulu-Natal

Integrating Artificial Intelligence in Disease Diagnosis, Treatment, and Formulation Development: A Review

Contact Info

Product

Resources

About