Andronicus A. Akinyelu

Crop diseases pose a significant threat to global food security, with both economic and environmental consequences. Early and accurate detection is essential for timely intervention and sustainable farming. This paper presents a review of machine learning (ML) and deep learning (DL) techniques for crop disease diagnosis, focusing on Support Vector Machines (SVMs), Random Forest (RF), k-Nearest Neighbors (KNNs), and deep models like VGG16, ResNet50, and DenseNet121. The review method includes an in-depth analysis of algorithm performance using key metrics such as accuracy, precision, recall, and F1 score across various datasets. We also highlight the data imbalances in commonly used datasets, particularly PlantVillage, and discuss the challenges posed by these imbalances. The research highlights critical insights regarding ML and DL models in crop disease detection. A primary challenge identified is the imbalance in the PlantVillage dataset, with a high number of healthy images and a strong bias toward certain disease categories like fungi, leaving other categories like mites and molds underrepresented. This imbalance complicates model generalization, indicating a need for preprocessing steps to enhance performance. This study also shows that combining Vision Transformers (ViTs) with Green Chromatic Coordinates and hybridizing these with SVM achieves high classification accuracy, emphasizing the value of advanced feature extraction techniques in improving model efficacy. In terms of comparative performance, DL architectures like ResNet50, VGG16, and convolutional neural network demonstrated robust accuracy (95–99%) across diverse datasets, underscoring their effectiveness in managing complex image data. Additionally, traditional ML models exhibited varied strengths; for instance, SVM performed better on balanced datasets, while RF excelled with imbalanced data. Preprocessing methods like K-means clustering, Fuzzy C-Means, and PCA, along with ensemble approaches, further improved model accuracy. Lastly, the study underscores that high-quality, well-labeled datasets, stakeholder involvement, and comprehensive evaluation metrics such as F1 score and precision are crucial for optimizing ML and DL models, making them more effective for real-world applications in sustainable agriculture.

This study proposes a deep-learning-based solution (named CapsNetCovid) for COVID-19 diagnosis using a capsule neural network (CapsNet). CapsNets are robust for image rotations and affine transformations, which is advantageous when processing medical imaging datasets. This study presents a performance analysis of CapsNets on standard images and their augmented variants for binary and multi-class classification. CapsNetCovid was trained and evaluated on two COVID-19 datasets of CT images and X-ray images. It was also evaluated on eight augmented datasets. The results show that the proposed model achieved classification accuracy, precision, sensitivity, and F1-score of 99.929%, 99.887%, 100%, and 99.319%, respectively, for the CT images. It also achieved a classification accuracy, precision, sensitivity, and F1-score of 94.721%, 93.864%, 92.947%, and 93.386%, respectively, for the X-ray images. This study presents a comparative analysis between CapsNetCovid, CNN, DenseNet121, and ResNet50 in terms of their ability to correctly identify randomly transformed and rotated CT and X-ray images without the use of data augmentation techniques. The analysis shows that CapsNetCovid outperforms CNN, DenseNet121, and ResNet50 when trained and evaluated on CT and X-ray images without data augmentation. We hope that this research will aid in improving decision making and diagnostic accuracy of medical professionals when diagnosing COVID-19.

COVID-19, a deadly and highly contagious virus, caused the deaths of millions of individuals around the world. Early detection of the virus can reduce the virus transmission and fatality rate. Many deep learning (DL) based COVID-19 detection methods have been proposed, but most are trained on either small, incomplete, noisy, or imbalanced datasets. Many are also trained on a small number of COVID-19 samples. This study tackles these concerns by introducing DL-based solutions for COVID-19 diagnosis using computerized tomography (CT) images and 12 cutting-edge DL pre-trained models with acceptable Top-1 accuracy. All the models are trained on 9,000 COVID-19 samples and 5,000 normal images, which is higher than the COVID-19 images used in most studies. In addition, while most of the research used X-ray images for training, this study used CT images. CT scans capture blood arteries, bones, and soft tissues more effectively than X-Ray. The proposed techniques were evaluated, and the results show that NASNetLarge produced the best classification accuracy, followed by InceptionResNetV2 and DenseNet169. The three models achieved an accuracy of 99.86, 99.79, and 99.71%, respectively. Moreover, DenseNet121 and VGG16 achieved the best sensitivity, while InceptionV3 and InceptionResNetV2 achieved the best specificity. DenseNet121 and VGG16 attained a sensitivity of 99.94%, while InceptionV3 and InceptionResNetV2 achieved a specificity of 100%. The models are compared to those designed in three existing studies, and they produce better results. The results show that deep neural networks have the potential for computer-assisted COVID-19 diagnosis. We hope this study will be valuable in improving the decisions and accuracy of medical practitioners when diagnosing COVID-19. This study will assist future researchers in minimizing the repetition of analysis and identifying the ideal network for their tasks.

Management of brain tumors is based on clinical and radiological information with presumed grade dictating treatment. Hence, a non-invasive assessment of tumor grade is of paramount importance to choose the best treatment plan. Convolutional Neural Networks (CNNs) represent one of the effective Deep Learning (DL)-based techniques that have been used for brain tumor diagnosis. However, they are unable to handle input modifications effectively. Capsule neural networks (CapsNets) are a novel type of machine learning (ML) architecture that was recently developed to address the drawbacks of CNNs. CapsNets are resistant to rotations and affine translations, which is beneficial when processing medical imaging datasets. Moreover, Vision Transformers (ViT)-based solutions have been very recently proposed to address the issue of long-range dependency in CNNs. This survey provides a comprehensive overview of brain tumor classification and segmentation techniques, with a focus on ML-based, CNN-based, CapsNet-based, and ViT-based techniques. The survey highlights the fundamental contributions of recent studies and the performance of state-of-the-art techniques. Moreover, we present an in-depth discussion of crucial issues and open challenges. We also identify some key limitations and promising future research directions. We envisage that this survey shall serve as a good springboard for further study.

Eye tracking is becoming a very popular, useful, and important technology. Many eye tracking technologies are currently expensive and only available to large corporations. Some of them necessitate explicit personal calibration, which makes them unsuitable for use in real-world or uncontrolled environments. Explicit personal calibration can also be cumbersome and degrades the user experience. To address these issues, this study proposes a Convolutional Neural Network (CNN) based calibration-free technique for improved gaze estimation in unconstrained environments. The proposed technique consists of two components, namely a face component and a 39-point facial landmark component. The face component is used to extract the gaze estimation features from the eyes, while the 39-point facial landmark component is used to encode the shape and location of the eyes (within the face) into the network. Adding this information can make the network learn free-head and eye movements. Another CNN model was designed in this study primarily for the sake of comparison. The CNN model accepts only the face images as input. Different experiments were performed, and the experimental result reveals that the proposed technique outperforms the second model. Fine-tuning was also performed using the VGG16 pre-trained model. Experimental results show that the fine-tuned results of the proposed technique perform better than the fine-tuned results of the second model. Overall, the results show that 39-point facial landmarks can be used to improve the performance of CNN-based gaze estimation models.

Today, digital data is exploding at a breakneck speed. Traditional data analytics techniques, unfortunately, are rapidly losing their capabilities and efficiencies when dealing with large datasets. This problem has prompted several researchers to develop more effective, efficient, and fast big data analytics tools. Machine Learning (ML)-based approaches are among the most dependable techniques used to extract usable insights from large datasets. However, some of them cannot efficiently handle large datasets, and their training time grows with dataset size. This paper presents two Nature-Inspired techniques for improving the training time of ML algorithms and the processing time of big datasets. The techniques are evaluated on four ML algorithms and large or medium-scale datasets. Results show that the training time of the four ML algorithms was reduced without a significant drop in classification accuracy. Moreover, the proposed methods are significantly faster than two well-known instance selection methods. Furthermore, statistical analysis reveals that the techniques reduced data size significantly, making them suitable for processing large datasets.

Eye tracking is becoming a very important tool across many domains, including human-computer-interaction, psychology, computer vision, and medical diagnosis. Different methods have been used to tackle eye tracking, however, some of them are inaccurate under real-world conditions, while some require explicit user calibration which can be burdensome. Some of these methods suffer from poor image quality and variable light conditions. The recent success and prevalence of deep learning have greatly improved the performance of eye-tracking. The availability of large-scale datasets has further improved the performance of deep learning-based methods. This paper presents a survey of the current state-of-the-art on deep learning-based gaze estimation techniques, with a focus on Convolutional Neural Networks (CNN). This paper also provides a survey on other machine learning-based gaze estimation techniques. This study aims to empower the research community with valuable and useful insights that can enhance the design and development of improved and efficient deep learning-based eye-tracking models. This study also provides information on various pre-trained models, network architectures, and open-source datasets that are useful for training deep learning models.

Phishing detection remains one of the most challenging problems currently faced by cyber users as sophisticated phishing schemes evolves rapidly. This paper presents a comprehensive survey of different phishing detection techniques with a focus of identifying gaps and proffering solutions to the current phishing detection problems. As shown in the survey, numerous techniques have been proposed to tackle phishing, including Machine Learning (ML) based, Nature Inspired (NI) based, heuristic-based, blacklist-based and whitelist-based techniques. However, ML-based techniques outperform other techniques in terms of classification accuracy due to their ability to analyze data contents, extract unknown or concealed patterns from the data and consequently turn the patterns into meaningful information for decision making. Unfortunately, ML algorithms cannot effectively handle big datasets, hence they can be combined with NI algorithms to build fast and improved models for phishing detection. Although, some surveys on phishing detection techniques exist, very few focused on ML-based and NI-based techniques. Therefore, this study presents a survey on ML-based and NI-based phishing detection techniques. The survey reveals the various shortcomings of phishing detection techniques, including limited dataset, use of third-party services (age of domain, search engine query, etc.), use of small feature set, use of classification rules, use of blacklist and whitelist, etc. There is an obvious need for efficient and reliable solutions for phishing detection. The recent success and prevalence of deep learning provides a rare opportunity for researchers seeking to design improved and effective phishing detection techniques. This study aims to empower the research community with suitable solutions and motivating insights that can be used to effectively tackle the phishing detection problem. It provides a good picture of the current state-of-the-art on phishing detection and serves as a reliable springboard for further studies.