Search

Malaria fever is a potentially fatal disease caused by the Plasmodium parasite. Identifying Plasmodium parasites in blood smear images can help diagnose malaria fever rapidly and precisely. According to the World Health Organization (WHO), there were 241 million malaria cases and 627 000 deaths worldwide in 2020, while 95% of malaria cases and 96% of malaria deaths occurred in Africa. Also in Africa, children that are less than five years old accounted for an estimated 80% of all malaria deaths. To address the menace of malaria, this paper proposes a novel deep learning model, called a data augmentation convolutional neural network (DACNN), trained by reinforcement learning to tackle this problem. The performance of the proposed DACNN model is compared with CNN and directed acyclic graph convolutional neural network (DAGCNN) models. Results show that DACNN outperforms previous studies in processing and classification images. It achieved 94.79% classification accuracy in malaria blood sample images of balanced class dataset obtained from the Kaggle dataset. The proposed model can serve as an effective tool for the detection of malaria parasites in blood smear images. [ABSTRACT FROM AUTHOR]

Remote sensing technology is vital for precision agriculture, aiding in early issue detection, resource management, and environmentally friendly practices. Recent advances in remote sensing technology and data processing have propelled unmanned aerial vehicles (UAVs) into valuable tools for obtaining detailed data on plant diseases with high spatial, temporal, and spectral resolution. Given the growing body of scholarly research centered on UAV-based disease detection, a comprehensive review and analysis of current studies becomes imperative to provide a panoramic view of evolving methodologies in plant disease monitoring and to strategically evaluate the potential and limitations of such strategies. This study undertakes a systematic quantitative literature review to summarize existing literature and discern current research trends in UAV-based applications for plant disease detection and monitoring. Results reveal a global disparity in research on the topic, with Asian countries being the top contributing countries (43 out of 103 papers). World regions such as Oceania and Africa exhibit comparatively lesser representation. To date, research has largely focused on diseases affecting wheat, sugar beet, potato, maize, and grapevine. Multispectral, reg-green-blue, and hyperspectral sensors were most often used to detect and identify disease symptoms, with current trends pointing to approaches integrating multiple sensors and the use of machine learning and deep learning techniques. Future research should prioritize (i) development of cost-effective and user-friendly UAVs, (ii) integration with emerging agricultural technologies, (iii) improved data acquisition and processing efficiency (iv) diverse testing scenarios, and (v) ethical considerations through proper regulations. [ABSTRACT FROM AUTHOR]

Heart diseases are currently a major cause of death in the world. This problem is severe in developing countries in Africa and Asia. A heart disease predicted at earlier stages not only helps the patients prevent it, but I can also help the medical practitioners learn the major causes of a heart attack and avoid it before its actual occurrence in patient. In this paper, we propose a method named CardioHelp which predicts the probability of the presence of cardiovascular disease in a patient by incorporating a deep learning algorithm called convolutional neural networks (CNN). The proposed method is concerned with temporal data modeling by utilizing CNN for HF prediction at its earliest stage. We prepared the heart disease dataset and compared the results with state-of-the-art methods and achieved good results. Experimental results show that the proposed method outperforms the existing methods in terms of performance evaluation metrics. The achieved accuracy of the proposed method is 97%. [ABSTRACT FROM AUTHOR]

This review presents a comprehensive examination of recent advancements in utilizing multi-date satellite data to analyze spatial and temporal variations in seasonal and inter-annual surface water dynamics within arid environments of Africa. Remote sensing offers continuous, precise, and long-term datasets for surface water research. Various sensors with differing spatial resolutions are discussed, with high-resolution multispectral sensors providing superior spatial resolution but at higher costs. Conversely, dualsensor approaches, incuding optical sensors (Sentinel-2 and Landsat), radar satellites (Sentinel-1 and RADARSAT) and UAVs were investigated. The review further examines the efficiency and applicability of traditional algorithms such as the modified normalized difference water index (MNDWI), normalized difference water index (NDWI), and automated water extraction index (AWEI) in detecting and delineating surface water resources. Additionally, machine learning (ML) algorithms, including support vector machines (SVM), Random Forest (RF), deep learning and emerging methodologies like recurrent tranformer networks, have been explored. Therefore, we recommend that future research endeavours focus on leveraging high-resolution satellite imagery and integrating physical models with deep learning techniques, artificial intelligence, and online big data processing platforms to improve surface water mapping capabilities. [ABSTRACT FROM AUTHOR]

With the worldwide decline in COVID-19 viral infections, the monkeypox virus is slowly returning. People are scared of it because they believe that it will spread like COVID-19. As a result, it is essential to find them sooner than they spread widely within the community. The early discovery of them might be made possible by ML-based detection. Public health is endangered by the swift spread of the monkeypox outbreak to over 40 nations beyond Africa. Monkeypox is challenging to diagnose at an early stage since it shares similarities with both chickenpox and measles. To monitor and identify potential cases promptly, computer-assisted detection of monkeypox lesions could be helpful in situations where PCR tests for confirmation are not readily available. Provided that there are adequate training samples, deep learning methods have demonstrated effectiveness in automatically identifying skin lesions. [ABSTRACT FROM AUTHOR]

Cutaneous leishmaniasis (CL) is a common illness that causes skin lesions, principally ulcerations, on exposed regions of the body. Although neglected tropical diseases (NTDs) are typically found in tropical areas, they have recently become more common along Africa's northern coast, particularly in Libya. The devastation of healthcare infrastructure during the 2011 war and the following conflicts, as well as governmental apathy, may be causal factors associated with this catastrophic event. The main objective of this study is to evaluate alternative diagnostic strategies for recognizing amastigotes of cutaneous leishmaniasis parasites at various stages using Convolutional Neural Networks (CNNs). The research is additionally aimed at testing different classification models employing a dataset of ultra-thin skin smear images of Leishmania parasite-infected people with cutaneous leishmaniasis. The pre-trained deep learning models including EfficientNetB0, DenseNet201, ResNet101, MobileNetv2, and Xception are used for the cutaneous leishmania parasite diagnosis task. To assess the models' effectiveness, we employed a five-fold cross-validation approach to guarantee the consistency of the models' outputs when applied to different portions of the full dataset. Following a thorough assessment and contrast of the various models, DenseNet-201 proved to be the most suitable choice. It attained a mean accuracy of 0.9914 along with outstanding results for sensitivity, specificity, positive predictive value, negative predictive value, F1-score, Matthew's correlation coefficient, and Cohen's Kappa coefficient. The DenseNet-201 model surpassed the other models based on a comprehensive evaluation of these key classification performance metrics. [ABSTRACT FROM AUTHOR]

Climatic factors influence malaria transmission via the effect on the Anopheles vector and Plasmodium parasite. Modelling and understanding the complex effects that climate has on malaria incidence can enable important early warning capabilities. Deep learning applications across fields are proving valuable, however the field of epidemiological forecasting is still in its infancy with a lack of applied deep learning studies for malaria in southern Africa which leverage quality datasets. Using a novel high resolution malaria incidence dataset containing 23 years of daily data from 1998 to 2021, a statistical model and XGBOOST machine learning model were compared to a deep learning Transformer model by assessing the accuracy of their numerical predictions. A novel loss function, used to account for the variable nature of the data yielded performance around + 20% compared to the standard MSE loss. When numerical predictions were converted to alert thresholds to mimic use in a real-world setting, the Transformer's performance of 80% according to AUROC was 20–40% higher than the statistical and XGBOOST models and it had the highest overall accuracy of 98%. The Transformer performed consistently with increased accuracy as more climate variables were used, indicating further potential for this prediction framework to predict malaria incidence at a daily level using climate data for southern Africa. [ABSTRACT FROM AUTHOR]

The recent outbreak of monkeypox has raised significant concerns in the field of public health, primarily because it has quickly spread to over 40 countries outside of Africa. Detecting monkeypox in its early stages can be quite challenging because its symptoms can resemble those of chickenpox and measles. However, there is hope that potential use of computer-assisted tools may be used to identify monkeypox cases rapidly and efficiently. A promising approach involves the use of technology, specifically deep learning methods, which have proven effective in automatically detecting skin lesions when sufficient training examples are available. To improve monkeypox diagnosis through mobile applications, we have employed a particular neural network called MobileNetV2, which falls under the category of Fully Connected Convolutional Neural Networks (FCCNN). It enables us to identify suspected monkeypox cases accurately compared to classical machine learning approaches. The proposed approach was evaluated using the recall, precision, F score, and accuracy. The experimental results show that our architecture achieves an accuracy of 0.99%, a Recall of 1.0%, an F-score of 0.98%, and a Precision of 0.95%. We believe that such experimental evaluation will contribute to the medical domain and many use cases. [ABSTRACT FROM AUTHOR]

A novel Omicron subvariant named BQ.1 emerged in Nigeria in July 2022 and has since become a dominant strain, causing a significant number of repeated infections even in countries with high-vaccination rates. Due to the high flow of people between Western Africa and other non-African countries, there is a high risk of Omicron BQ.1 being introduced to other countries from Western Africa. In this context, we developed a model based on deep neural networks to estimate the probability that the Omicron BQ.1 introduced to other countries from Western Africa based on the incomplete population mobility data from Western Africa to other non-African countries. Our study found that the highest risk was in France and Spain during the study period, while the importation risk of other 13 non-African countries including Canada and the United States is also high. Our approach sheds light on how deep learning techniques can assist in the development of public health policies, and it has the potential to be extended to other types of viruses. [ABSTRACT FROM AUTHOR]

Morphometric analysis of wings has been suggested for identifying and controlling isolated populations of tsetse (Glossina spp), vectors of human and animal trypanosomiasis in Africa. Single-wing images were captured from an extensive data set of field-collected tsetse wings of species Glossina pallidipes and G. m. morsitans. Morphometric analysis required locating 11 anatomical landmarks on each wing. The manual location of landmarks is time-consuming, prone to error, and infeasible for large data sets. We developed a two-tier method using deep learning architectures to classify images and make accurate landmark predictions. The first tier used a classification convolutional neural network to remove most wings that were missing landmarks. The second tier provided landmark coordinates for the remaining wings. We compared direct coordinate regression using a convolutional neural network and segmentation using a fully convolutional network for the second tier. For the resulting landmark predictions, we evaluate shape bias using Procrustes analysis. We pay particular attention to consistent labelling to improve model performance. For an image size of 1024 × 1280, data augmentation reduced the mean pixel distance error from 8.3 (95% confidence interval [4.4,10.3]) to 5.34 (95% confidence interval [3.0,7.0]) for the regression model. For the segmentation model, data augmentation did not alter the mean pixel distance error of 3.43 (95% confidence interval [1.9,4.4]). Segmentation had a higher computational complexity and some large outliers. Both models showed minimal shape bias. We deployed the regression model on the complete unannotated data consisting of 14,354 pairs of wing images since this model had a lower computational cost and more stable predictions than the segmentation model. The resulting landmark data set was provided for future morphometric analysis. The methods we have developed could provide a starting point to studying the wings of other insect species. All the code used in this study has been written in Python and open sourced. Author summary: Tsetse flies, vectors of human and livestock disease, cost African countries billions of dollars annually. Wing shape can be used to identify isolated tsetse populations for suppression. The shape can be captured from digital images by locating anatomical points termed landmarks on the wings. Manual positioning of landmarks is prone to error and only feasible for small data sets. We analyse 14,354 wings and have developed a novel method for automatically positioning landmarks on insect wings. We use a two-step approach, first removing wings that are missing landmarks due to damage. We thereby provide accurate landmarks, unbiased for wing shape. We compared two modern deep-learning models to locate landmarks and showed how data manipulation techniques improve performance. We deployed the final system to generate the landmark data for the tsetse wing images and provide the trained models for transfer learning on similar tasks with smaller data sets. Our methods will allow researchers to study tsetse wing shape in relation to other biological data and to gauge how wing shape characterises tsetse populations. Our method could provide a starting point to the study of the wings of other insect species. [ABSTRACT FROM AUTHOR]

Monkeypox or Mpox is an infectious virus predominantly found in Africa. It has spread to many countries since its latest outbreak. Symptoms such as headaches, chills, and fever are observed in humans. Lumps and rashes also appear on the skin (similar to smallpox, measles, and chickenpox). Many artificial intelligence (AI) models have been developed for accurate and early diagnosis. In this work, we systematically reviewed recent studies that used AI for mpox-related research. After a literature search, 34 studies fulfilling prespecified criteria were selected with the following subject categories: diagnostic testing of mpox, epidemiological modeling of mpox infection spread, drug and vaccine discovery, and media risk management. In the beginning, mpox detection using AI and various modalities was described. Other applications of ML and DL in mitigating mpox were categorized later. The various machine and deep learning algorithms used in the studies and their performance were discussed. We believe that a state-of-the-art review will be a valuable resource for researchers and data scientists in developing measures to counter the mpox virus and its spread. [ABSTRACT FROM AUTHOR]

At the time the world is attempting to get over the damage caused by the COVID-19 spread, the monkeypox virus threatens to evolve into a global pandemic. Human monkeypox was first recognized in Africa and has recently emerged in 103 countries outside Africa. However, monkeypox diagnosis in an early stage is difficult because of the similarity between it, chickenpox, cowpox and measles. In some cases, computer-assisted detection of monkeypox lesions can be helpful for quick identification of suspected cases. Infected and uninfected cases have added to a growing dataset that is publicly accessible and may be utilized by machine and deep learning to predict the suspected cases at an early stage. Motivated by this, a diagnostic framework to categorize the cases of patients into four categories (i.e., normal, monkeypox, chicken pox and measles) is proposed. The diagnostic framework is a hybridization of pre-trained Convolution Neural Network (CNN) models, machine learning classifiers and a metaheuristic optimization algorithm. The hyperparameters of the five pre-trained models (i.e., VGG19, VGG16, Xception, MobileNet and MobileNetV2) are optimized using a Harris Hawks Optimizer (HHO) metaheuristic algorithm. After that, the features can be extracted from the feature extraction and reduction layers. These features are classified using seven machine learning models (i.e., Random Forest, AdaBoost, Histogram Gradient Boosting, Gradient Boosting, Support Vector Machine, Extra Trees and KNN). For each classifier, 10-fold cross-validation is used to train and test the classifiers on the features and the weighted average performance metrics are reported. The predictions from the pre-trained model and machine learning classifiers are then processed using majority voting. This study conducted the experiments on two datasets (i.e., Monkeypox Skin Images Dataset (MSID) and Monkeypox Images Dataset (MPID)). MSID dataset values 97.67%, 95.19%, 97.96%, 95.11%, 96.58%, 95.10%, 90.93% and 96.65% are achieved concerning accuracy, sensitivity, specificity, PPV, BAC, F1, IoU and ROC, respectively. While for the MPID dataset, values of 97.51%, 94.84%, 94.48%, 94.96%, 96.66%, 94.88%, 90.45% and 96.69% are achieved concerning accuracy, sensitivity, specificity, PPV, BAC, F1, IoU and ROC, respectively. [ABSTRACT FROM AUTHOR]

The improvement in computer vision, sensor quality, and remote sensing data availability makes satellite imagery increasingly useful for studying human settlements. Several challenges remain to be overcome for some types of settlements, particularly for internally displaced populations (IDPs) and refugee camps. Refugee-dwelling footprints and detailed information derived from satellite imagery are critical for a variety of applications, including humanitarian aid during disasters or conflicts. Nevertheless, extracting dwellings remains difficult due to their differing sizes, shapes, and location variations. In this study, we use U-Net and residual U-Net to deal with dwelling classification in a refugee camp in northern Cameroon, Africa. Specifically, two semantic segmentation networks are adapted and applied. A limited number of randomly divided sample patches is used to train and test the networks based on a single image of the WorldView-3 satellite. Our accuracy assessment was conducted using four different dwelling categories for classification purposes, using metrics such as Precision, Recall, F1, and Kappa coefficient. As a result, F1 ranges from 81% to over 99% and approximately 88.1% to 99.5% based on the U-Net and the residual U-Net, respectively. [ABSTRACT FROM AUTHOR]

Artisanal and small-scale mines (asm) are on the rise. They represent a crucial source of wealth for numerous communities but are rarely monitored or regulated. The main reason being the unavailability of reliable information on the precise location of the asm which are mostly operated informally or illegally. We address this issue by developing a strategy to map the asm locations using a convolutional neural network for image segmentation, aiming to detect surface mining with satellite data. Our novel dataset is the first comprehensive measure of asm activity over a vast area: we cover 1.75 million km2 across 13 countries in Sub-Tropical West Africa. The detected asm activities range from 0.1 ha to around 2, 000 ha and present a great diversity, yet we succeed in hitting acceptable compromises of performance, as achieving 70% precision while maintaining simultaneously 42% recall. Ultimately, the remarkable robustness of our procedure makes us confident that our method can be applied to other parts of Africa or the world, thus facilitating research and policy opportunities in this sector. [ABSTRACT FROM AUTHOR]

Assessing land-use following deforestation is vital for reducing emissions from deforestation and forest degradation. In this paper, for the first time, we assess the potential of spatial, temporal and spatio-temporal deep learning methods for large-scale classification of land-use following tropical deforestation using dense satellite time series over six years on the pan-tropical scale (incl. Latin America, Africa, and Asia). Based on an extensive reference database of six forest to land-use conversion types, we find that the spatio-temporal models achieved a substantially higher F1-score accuracies than models that account only for spatial or temporal patterns. Although all models performed better when the scope of the problem was limited to a single continent, the spatial models were more competitive than the temporal ones in this setting. These results suggest that the spatial patterns of land-use within a continent share more commonalities than the temporal patterns and the spatial patterns across continents. This work explores the feasibility of extending and complementing previous efforts for characterizing follow-up land-use after deforestation at a small-scale via human visual interpretation of high resolution RGB imagery. It supports the usage of fast and automated large-scale land-use classification and showcases the value of deep learning methods combined with spatio-temporal satellite data to effectively address the complex tasks of identifying land-use following deforestation in a scalable and cost effective manner. • We classify land-use following deforestation at continental and pan-tropical scales. • Using reference data we test six different spatio-temporal deep learning methods. • Continental models performed better compared to the pan-tropical model. • Pan-tropical spatio-temporal models performed better than spatial or temporal ones • Our results suggest higher spatial than temporal homogeneity at the continental level [ABSTRACT FROM AUTHOR]

Accurate and comprehensive measurements of economic well-being are fundamental inputs into both research and policy, but such measures are unavailable at a local level in many parts of the world. Here we train deep learning models to predict survey-based estimates of asset wealth across ~ 20,000 African villages from publicly-available multispectral satellite imagery. Models can explain 70% of the variation in ground-measured village wealth in countries where the model was not trained, outperforming previous benchmarks from high-resolution imagery, and comparison with independent wealth measurements from censuses suggests that errors in satellite estimates are comparable to errors in existing ground data. Satellite-based estimates can also explain up to 50% of the variation in district-aggregated changes in wealth over time, with daytime imagery particularly useful in this task. We demonstrate the utility of satellite-based estimates for research and policy, and demonstrate their scalability by creating a wealth map for Africa's most populous country. It is generally difficult to scale derived estimates and understand the accuracy across locations for passively-collected data sources, such as mobile phones and satellite imagery. Here the authors show that their trained deep learning models are able to explain 70% of the variation in ground-measured village wealth in held-out countries, outperforming previous benchmarks from high-resolution imagery with errors comparable to that of existing ground data. [ABSTRACT FROM AUTHOR]

Featured Application: Cut mark identification and analysis is a fundamental component for archaeological investigation. Cut mark analysis, however, has been the root of great debates, with some authors claiming to have the oldest cut marks in or outside of Africa. If these marks were to truly be anthropic in nature, then the repercussions of these findings would produce a paradigm shift for our understanding of human evolution. Unfortunately, the majority of methods available for cut mark classification are namely qualitative in nature. Here we provide a new, highly powerful artificially intelligent neural network classification model that can be used to quantitatively and more objectively overcome these issues, using 3D digital microscopy, Deep Learning and Geometric Morphometrics to obtain up to 100% accuracy in some cases. The concept of equifinality is currently one of the largest issues in taphonomy, frequently leading analysts to erroneously interpret the formation and functionality of archaeological and paleontological sites. An example of this equifinality can be found in the differentiation between anthropic cut marks and other traces on bone produced by natural agents, such as that of sedimentary abrasion and trampling. These issues are a key component in the understanding of early human evolution, yet frequently rely on qualitative features for their identification. Unfortunately, qualitative data is commonly susceptible to subjectivity, producing insecurity in research through analyst experience. The present study intends to confront these issues through a hybrid methodological approach. Here, we combine Geometric Morphometric data, 3D digital microscopy, and Deep Learning Neural Networks to provide a means of empirically classifying taphonomic traces on bone. Results obtained are able to reach over 95% classification, providing a possible means of overcoming taphonomic equifinality in the archaeological and paleontological register. [ABSTRACT FROM AUTHOR]

Featured Application: This work is applicable in computer science, software engineering and computational linguistic specifically in natural language processing. Deep learning has extensively been used in natural language processing with sub-word representation vectors playing a critical role. However, this cannot be said of Swahili, which is a low resource and widely spoken language in East and Central Africa. This study proposed novel word embeddings from syllable embeddings (WEFSE) for Swahili to address the concern of word representation for agglutinative and syllabic-based languages. Inspired by the learning methodology of Swahili in beginner classes, we encoded respective syllables instead of characters, character n-grams or morphemes of words and generated quality word embeddings using a convolutional neural network. The quality of WEFSE was demonstrated by the state-of-art results in the syllable-aware language model on both the small dataset (31.229 perplexity value) and the medium dataset (45.859 perplexity value), outperforming character-aware language models. We further evaluated the word embeddings using word analogy task. To the best of our knowledge, syllabic alphabets have not been used to compose the word representation vectors. Therefore, the main contributions of the study are a syllabic alphabet, WEFSE, a syllabic-aware language model and a word analogy dataset for Swahili. [ABSTRACT FROM AUTHOR]

Multitemporal environmental and urban studies are essential to guide policy making to ultimately improve human wellbeing in the Global South. Land-cover products derived from historical aerial orthomosaics acquired decades ago can provide important evidence to inform long-term studies. To reduce the manual labelling effort by human experts and to scale to large, meaningful regions, we investigate in this study how domain adaptation techniques and deep learning can help to efficiently map land cover in Central Africa. We propose and evaluate a methodology that is based on unsupervised adaptation to reduce the cost of generating reference data for several cities and across different dates. We present the first application of domain adaptation based on fully convolutional networks for semantic segmentation of a dataset of historical panchromatic orthomosaics for land-cover generation for two focus cities Goma-Gisenyi and Bukavu. Our experimental evaluation shows that the domain adaptation methods can reach an overall accuracy between 60% and 70% for different regions. If we add a small amount of labelled data from the target domain, too, further performance gains can be achieved. [ABSTRACT FROM AUTHOR]

The availability of free and open data from Earth observation programmes such as Copernicus, and from collaborative projects such as Open Street Map (OSM), enables low cost artificial intelligence (AI) based monitoring applications. This creates opportunities, particularly in developing countries with scarce economic resources, for large–scale monitoring in remote regions. A significant portion of Earth's surface comprises desert dune fields, where shifting sand affects infrastructure and hinders movement. A robust, cost–effective and scalable methodology is proposed for road detection and monitoring in regions covered by desert sand. The technique uses Copernicus Sentinel–1 synthetic aperture radar (SAR) satellite data as an input to a deep learning model based on the U–Net architecture for image segmentation. OSM data is used for model training. The method comprises two steps: The first involves processing time series of Sentinel–1 SAR interferometric wide swath (IW) acquisitions in the same geometry to produce multitemporal backscatter and coherence averages. These are divided into patches and matched with masks of OSM roads to form the training data, the quantity of which is increased through data augmentation. The second step includes the U–Net deep learning workflow. The methodology has been applied to three different dune fields in Africa and Asia. A performance evaluation through the calculation of the Jaccard similarity coefficient was carried out for each area, and ranges from 84% to 89% for the best available input. The rank distance, calculated from the completeness and correctness percentages, was also calculated and ranged from 75% to 80%. Over all areas there are more missed detections than false positives. In some cases, this was due to mixed infrastructure in the same resolution cell of the input SAR data. Drift sand and dune migration covering infrastructure is a concern in many desert regions, and broken segments in the resulting road detections are sometimes due to sand burial. The results also show that, in most cases, the Sentinel–1 vertical transmit–vertical receive (VV) backscatter averages alone constitute the best input to the U–Net model. The detection and monitoring of roads in desert areas are key concerns, particularly given a growing population increasingly on the move. [ABSTRACT FROM AUTHOR]

Background: Banana (Musa spp.) is the most popular marketable fruit crop grown all over the world, and a dominant staple food in many developing countries. Worldwide, banana production is affected by numerous diseases and pests. Novel and rapid methods for the timely detection of pests and diseases will allow to surveil and develop control measures with greater efficiency. As deep convolutional neural networks (DCNN) and transfer learning has been successfully applied in various fields, it has freshly moved in the domain of just-in-time crop disease detection. The aim of this research is to develop an AI-based banana disease and pest detection system using a DCNN to support banana farmers. Results: Large datasets of expert pre-screened banana disease and pest symptom/damage images were collected from various hotspots in Africa and Southern India. To build a detection model, we retrained three different convolutional neural network (CNN) architectures using a transfer learning approach. A total of six different models were developed from 18 different classes (disease by plant parts) using images collected from different parts of the banana plant. Our studies revealed ResNet50 and InceptionV2 based models performed better compared to MobileNetV1. These architectures represent the state-of-the-art results of banana diseases and pest detection with an accuracy of more than 90% in most of the models tested. These experimental results were comparable with other state-of-the-art models found in the literature. With a future view to run these detection capabilities on a mobile device, we evaluated the performance of SSD (single shot detector) MobileNetV1. Performance and validation metrics were also computed to measure the accuracy of different models in automated disease detection methods. Conclusion: Our results showed that the DCNN was a robust and easily deployable strategy for digital banana disease and pest detection. Using a pre-trained disease recognition model, we were able to perform deep transfer learning (DTL) to produce a network that can make accurate predictions. This significant high success rate makes the model a useful early disease and pest detection tool, and this research could be further extended to develop a fully automated mobile app to help millions of banana farmers in developing countries. [ABSTRACT FROM AUTHOR]