Early Classification Research Articles

Adaptive Machine Learning Approach for Importance Evaluation of Multimodal Breast Cancer Radiomic Features

Breast cancer holds the highest diagnosis rate among female tumors and is the leading cause of death among women. Quantitative analysis of radiological images shows the potential to address several medical challenges, including the early detection and classification of breast tumors. In the P.I.N.K study, 66 women were enrolled. Their paired Automated Breast Volume Scanner (ABVS) and Digital Breast Tomosynthesis (DBT) images, annotated with cancerous lesions, populated the first ABVS+DBT dataset. This enabled not only a radiomic analysis for the malignant vs. benign breast cancer classification, but also the comparison of the two modalities. For this purpose, the models were trained using a leave-one-out nested cross-validation strategy combined with a proper threshold selection approach. This approach provides statistically significant results even with medium-sized data sets. Additionally it provides distributional variables of importance, thus identifying the most informative radiomic features. The analysis proved the predictive capacity of radiomic models even using a reduced number of features. Indeed, from tomography we achieved AUC-ROC 89.9%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$89.9\\%$$\\end{document} using 19 features and 92.1%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$92.1\\%$$\\end{document} using 7 of them; while from ABVS we attained an AUC-ROC of 72.3%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$72.3\\%$$\\end{document} using 22 features and 85.8%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$85.8\\%$$\\end{document} using only 3 features. Although the predictive power of DBT outperforms ABVS, when comparing the predictions at the patient level, only 8.7% of lesions are misclassified by both methods, suggesting a partial complementarity. Notably, promising results (AUC-ROC ABVS-DBT 71.8%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$71.8\\%$$\\end{document}-74.1%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$74.1\\%$$\\end{document}) were achieved using non-geometric features, thus opening the way to the integration of virtual biopsy in medical routine.

Machine learning insights into thrombo-ischemic risks and bleeding events through platelet lysophospholipids and acylcarnitine species

Coronary artery disease (CAD) often leads to adverse events resulting in significant disease burdens. Underlying risk factors often remain inapparent prior to disease incidence and the cardiovascular (CV) risk is not exclusively explained by traditional risk factors. Platelets inherently promote atheroprogression and enhanced platelet functions and distinct platelet lipid species are associated with disease severity in patients with CAD. Lipidomics data were acquired using mass spectrometry and processed alongside clinical data applying machine learning to model estimates of an increased CV risk in a consecutive CAD cohort (n = 595). By training machine learning models on CV risk measurements, stratification of CAD patients resulted in a phenotyping of risk groups. We found that distinct platelet lipids are associated with an increased CV or bleeding risk and independently predict adverse events. Notably, the addition of platelet lipids to conventional risk factors resulted in an increased diagnostic accuracy of patients with adverse CV events. Thus, patients with aberrant platelet lipid signatures and platelet functions are at elevated risk to develop adverse CV events. Machine learning combining platelet lipidome data and common clinical parameters demonstrated an increased diagnostic value in patients with CAD and might improve early risk discrimination and classification for CV events.

Integration of ultrasound and mammogram for multimodal classification of breast cancer using hybrid residual neural network and machine learning

Breast cancer (BC) is one of the topmost causes of mortality in women all over the world. Early detection and classification of the tumor allow proper treatment of patients and chances of survival. In this article, we propose a hybrid residual neural network (ResNet) and machine learning framework and integrate the features of both mammography (MG) and ultrasound (US) images to perform the multimodal classification of BC images as benign or malignant. The features are extracted automatically from the input images of each modality using the residual neural network from the average pooling layer. Next, the feature level fusion is carried out to obtain a feature vector by combining features of MG & US. Finally, the multimodal classification is performed using the support vector machine (SVM) as a classifier. Experiments are performed on a real-time dataset collected from patients who have undergone both MG and US examinations. The classification accuracy obtained for the multimodal approach with SVM is 99.22%, which is higher than unimodal systems. Results show that the proposed multimodal approach performs better in classifying breast tumors than unimodal mammogram and ultrasound systems.

Classification of brain strokes using divergence-based convolutional neural networks

Stroke is a cerebrovascular issue caused by reduced or interrupted blood flow to the brain, resulting in the rapid death of brain cells and potential permanent functional damage. Early detection, classification, and immediate intervention are essential to prevent severe consequences, including death or lifelong disabilities. In this study, a total of 6650 brain CT images were used, which included 1130 ischemic stroke, 1093 hemorrhagic stroke, and 4427 non-stroke cases provided by the Turkish Ministry of Health. The study first aimed to determine the presence of stroke in the brain. Secondly, in cases where stroke was detected, the type of stroke, whether ischemic or hemorrhagic, was determined. Lastly, the images were classified into three categories: non-stroke, hemorrhagic, and ischemic. A newly introduced divergence-based deep neural network (DNN) was modified and utilized for the method. Features were extracted from the convolutional neural network (CNN) using Walsh matrices, and classification was performed using the minimum distance network (MDN). Experimental results showed that when the images were binary classified as stroke vs. non-stroke and ischemic vs. hemorrhagic type, they achieved accuracies of 99.248% and 99.324%, respectively. For the three-class classification (non-stroke, ischemic, and hemorrhagic), a success rate of 99.097% was achieved. The proposed study has advantages in terms of no preprocessing stage, classification with real images without data augmentation, and the low number of parameters in the employed network. The results indicate that the proposed network successfully detects the presence and type of stroke with high accuracy and outperforms existing studies in the literature.

Nonlinearity analysis of sit-to-stand and its application

The examination of human biomechanics, particularly the sit-to-stand transition, has been a focal point of research for numerous years, utilizing mathematical models of the musculoskeletal structure and motion analysis. However, researchers and scientists have encountered substantial challenges attributable to the distributed, nonlinear, and time-varying nature of this phenomenon, characterized by numerous degrees of freedom and redundancy at various levels. Conventional biomechanical assessments of human movement typically rely on linear mathematical approaches, which, while advantageous in various scenarios, often inadequately capture the predominantly nonlinear characteristics inherent in human systems. As a consequence, there has been a growing recognition of the limitations of linear methods, leading to an increased adoption of nonlinear analytical techniques rooted in a dynamical systems approach in contemporary research. Notwithstanding this trend, there exists a conspicuous dearth of a comprehensive review paper that meticulously scrutinizes these nonlinear methods and their applications across the spectrum from modelling to rehabilitation. This mini-review aims to address this gap by highlighting recent advancements in nonlinear methodologies. These methodologies have demonstrated the potential to enhance the efficacy of interventions for individuals with sit-to-stand disorders, encompassing the design of intelligent rehabilitation devices, mitigating fall risks, and facilitating early patient classification.

Leaf Architecture and Genome Size Variation of Durio zibethinus L. from Jelebu, Negeri Sembilan, Malaysia.

Durio zibethinus L. is known as the "king of fruit" in Malaysia. Meanwhile, Jelebu, Negeri Sembilan has always become the top choice district to visit for durian lover for its Durian Kampung Jelebu, which possessed good quality on par with top D. zibethinus clones such as D197 Musang King and D24. However, there is still lacking in taxonomic data of D. zibethinus especially from Jelebu. This study aimed to analyse the leaf architecture and genome size variations of selected D. zibethinus accessions from Jelebu. Five D. zibethinus accessions from Jelebu were examined. Thirty-seven parameters of gross leaf morphological characteristics and leaf venation pattern were observed and recorded for identification and classification of D. zibethinus accessions from Jelebu. Seven parameters have been recorded which are petiole length, petiole features, leaf size, leaf shape, leaf base shape, lower leaf surface colour and areolation could be used in differentiating between accessions. Results of this study showed the intraspecific variations existed among D. zibethinus accessions from Jelebu with a genome size varying between 1.7433 pg and 1.800 pg. In conclusion, data on leaf architecture and genome size variations from D. zibethinus accessions are beneficial for early plant identification and classification.

Comparison of feature reduction and feature selection in early diabetes classification

Diabetes is one of the common health problems encountered today, and this problem is increasing day by day due to unbalanced and unconscious eating habits. Once a person is diagnosed with diabetes, the likelihood of recovery from this disease is often low. If a person is diagnosed with diabetes, the individual must usually take medication and/or follow a strict diet program for life. While this may be somewhat more manageable for patients living in developed countries, it is often difficult for citizens in developing countries to access these facilities. Because it is generally more difficult and costly to access medicine and healthy nutrition in these countries. Therefore, in this study, ways to diagnose diabetes at an early stage using machine learning techniques are examined. In the study, symptoms such as age, gender, polyuria, polydipsia, sudden weight loss, weakness, polyphagia, genital fungus, blurred vision, itching, irritability, delayed healing, partial paralysis, cramps, hair loss and obesity are examined and which parameters were more effective in diagnosing diabetes.

Using transfer learning-based plant disease classification and detection for sustainable agriculture

Subsistence farmers and global food security depend on sufficient food production, which aligns with the UN's “Zero Hunger,” “Climate Action,” and “Responsible Consumption and Production” sustainable development goals. In addition to already available methods for early disease detection and classification facing overfitting and fine feature extraction complexities during the training process, how early signs of green attacks can be identified or classified remains uncertain. Most pests and disease symptoms are seen in plant leaves and fruits, yet their diagnosis by experts in the laboratory is expensive, tedious, labor-intensive, and time-consuming. Notably, how plant pests and diseases can be appropriately detected and timely prevented is a hotspot paradigm in smart, sustainable agriculture remains unknown. In recent years, deep transfer learning has demonstrated tremendous advances in the recognition accuracy of object detection and image classification systems since these frameworks utilize previously acquired knowledge to solve similar problems more effectively and quickly. Therefore, in this research, we introduce two plant disease detection (PDDNet) models of early fusion (AE) and the lead voting ensemble (LVE) integrated with nine pre-trained convolutional neural networks (CNNs) and fine-tuned by deep feature extraction for efficient plant disease identification and classification. The experiments were carried out on 15 classes of the popular PlantVillage dataset, which has 54,305 image samples of different plant disease species in 38 categories. Hyperparameter fine-tuning was done with popular pre-trained models, including DenseNet201, ResNet101, ResNet50, GoogleNet, AlexNet, ResNet18, EfficientNetB7, NASNetMobile, and ConvNeXtSmall. We test these CNNs on the stated plant disease detection and classification problem, both independently and as part of an ensemble. In the final phase, a logistic regression (LR) classifier is utilized to determine the performance of various CNN model combinations. A comparative analysis was also performed on classifiers, deep learning, the proposed model, and similar state-of-the-art studies. The experiments demonstrated that PDDNet-AE and PDDNet-LVE achieved 96.74% and 97.79%, respectively, compared to current CNNs when tested on several plant diseases, depicting its exceptional robustness and generalization capabilities and mitigating current concerns in plant disease detection and classification.

GROUNDNUT CROP PEST DETECTION AND CLASSIFICATION USING COMPREHENSIVE DEEP-LEARNING MODELS

Pests pose a significant threat to crops, leading to substantial economic losses and decreased food production. Early detection and accurate classification of pests in crops are crucial for effective pest management strategies. In this study, we propose a method for pest detection and classification in groundnut crops using deep learning models. In this research, we compare the performance of three deep learning models, namely Custom CNN [proposed], LeNet-5, and VGG-16, for groundnut pest detection and classification. A comprehensive dataset containing images of diverse groundnut crop pests, including thrips, aphids, armyworms, and wireworms, from the IP102 dataset was utilized for model evaluation. The performance is evaluated using reliability metrics such as accuracy and loss. These findings demonstrate the utility of deep learning models for reliable pest classification of groundnut crops. The Custom CNN [proposed] model demonstrates high training accuracy but potential overfitting, while the VGG-16 model performs well on both training and test data, showcasing its ability to generalize. The models’ accuracy in predicting pest species underscores their capability to capture and utilize visual patterns for precise classification. These findings underscore the potential of deep learning models, particularly the VGG-16 model, for pest detection and classification in groundnut crops. The knowledge gained from this study can contribute to the development of practical pest management strategies and aid in maintaining crop health and productivity. Further analysis and comparisons with other models are recommended to comprehensively evaluate the competitiveness and suitability of deep learning models in real-world applications of pest detection and classification in agricultural settings.

Prostate cancer grading framework based on deep transfer learning and Aquila optimizer

Prostate cancer is the one of the most dominant cancer among males. It represents one of the leading cancer death causes worldwide. Due to the current evolution of artificial intelligence in medical imaging, deep learning has been successfully applied in diseases diagnosis. However, most of the recent studies in prostate cancer classification suffers from either low accuracy or lack of data. Therefore, the present work introduces a hybrid framework for early and accurate classification and segmentation of prostate cancer using deep learning. The proposed framework consists of two stages, namely classification stage and segmentation stage. In the classification stage, 8 pretrained convolutional neural networks were fine-tuned using Aquila optimizer and used to classify patients of prostate cancer from normal ones. If the patient is diagnosed with prostate cancer, segmenting the cancerous spot from the overall image using U-Net can help in accurate diagnosis, and here comes the importance of the segmentation stage. The proposed framework is trained on 3 different datasets in order to generalize the framework. The best reported classification accuracies of the proposed framework are 88.91% using MobileNet for the “ISUP Grade-wise Prostate Cancer” dataset and 100% using MobileNet and ResNet152 for the “Transverse Plane Prostate Dataset” dataset with precisions 89.22% and 100%, respectively. U-Net model gives an average segmentation accuracy and AUC of 98.46% and 0.9778, respectively, using the “PANDA: Resized Train Data (512 × 512)” dataset. The results give an indicator of the acceptable performance of the proposed framework.

Framework for early detection and classification of balance pathologies using posturography and anthropometric variables

BackgroundEarly detection of balance-related pathologies in adults using Posturography, anthropometric and personal data is limited. Our goal is to address this issue. It will enable us to identify adults in early stages of balance disorders using easily accessible and measurable data. MethodsOpen-source data of 163 subjects (47 males and 116 females) is used to train and test classification algorithms. Features include mean and standard deviation of the center of pressure displacement, obtained through posturography, the anthropometric and personal variables (age, sex, body mass index, foot length), and Trail Making Test scores. 75% of the data is employed for training and 25% of the data is used for testing. It is then validated using an indigenously collected dataset of healthy individuals. FindingsAccuracy and Sensitivity, both, increases when anthropometric and personal variables are included alongside center of pressure features for classification. Specificity decreases slightly with the addition of anthropometric and personal variables with center of pressure displacement feature, which also affects the classification algorithms' performance. Standard deviation of the center of pressure displacement is found to be more effective than the mean value. A similar trend of the increased performance is observed during validation, except when neural networks were used for the classification. InterpretationPosturography data, Anthropometric measurements, personal data and self-assessment scales can identify balance issues in adults, making it suitable for community health centers with limited resources. Early detection prompts timely medical care, improving the management of disorders and thus enhancing the quality of life through rehabilitation.

Computed tomography‐based artificial intelligence in lung disease—Chronic obstructive pulmonary disease

AbstractChronic obstructive pulmonary disease (COPD) stands as a global health crisis, responsible for substantial morbidity and mortality on a worldwide scale. Its insidious nature underscores the importance of early detection and accurate diagnosis. While spirometry has been the cornerstone for COPD diagnosis, the role of computed tomography (CT) imaging has evolved, offering a valuable avenue for early detection and subtype classification. Recently, the advent of artificial intelligence (AI) has brought forth the potential to revolutionize the accuracy and efficiency of COPD diagnosis, with a specific focus on CT images. This intersection of healthcare and technology signifies a paradigm shift in the way we approach COPD management. The transformative capacity of AI positions it as a vital instrument for early detection and precise subtype classification of COPD. Moreover, the synergistic relationship between medical imaging and AI paves the way for more precise and efficient disease management. Therefore, in this perspective, we tend to offer a comprehensive exploration of the latest breakthroughs in the field of CT‐based AI in COPD diagnosis, aiming to demonstrate the promise and potential of AI in refining the accuracy of COPD classification and to illuminate the evolving landscape of AI's impact on COPD management.

Advancing disease identification in fava bean crops: A novel deep learning solution integrating YOLO-NAS for precise rust

A significant concern is the economic impact of agricultural diseases on the world’s crop production. The disease significantly reduces agricultural production across the world. Loss of nutrients caused by parasite infection of leaves, pods, and roots–the pathogenic agent that causes fava bean rust disease–decreases crop health. This work addresses this requirement by offering an innovative deep-learning model approach for early identification and classification of fava bean rust disease. The suggested method uses the effectiveness of modern YOLO-based object detection architectures like You Only Look Once –Neural Architecture Search (YOLO-NAS) L, YOLO-NASM, and YOLO-NASS, Faster Region-based Convolutional Neural Network (Faster R-CNN), and RetinaNet. An inclusive dataset of 3296 images of various lighting and background situations was selected for extensive model training. Each model underwent thorough training and adjusted parameters through careful experimentation. The models’ comparative studies found significant performance differences. The precision for YOLO-NASL was 82.10%; for YOLO-NASM, it was 84.80%; for YOLO-NASS, it was 83.90%; for Faster R-CNN, it was 75.51%; and for RetinaNet, it was 73.74%. According to the evaluation, model complexity and detection accuracy are directly correlated. YOLO-NASL, YOLO-NASM, and YOLO-NASS showed remarkable mean average precision values of 90.90%, 94.10%, and 92.60%, respectively, and became highly functional models. The fastest model was YOLO-NASS. Its satisfying recognition speed made real-time detection possible in particular applications. The YOLO-NASM model, which shows an extraordinary state-of-the-art performance, represents the pinnacle of our work. Its mean average precision (mAP@0.5) was 94.10%, with notable values of 90.84%, 96.96%, and 84.80% for the F1-score, Recall, and precision, respectively. This investigation addresses a critical need in agricultural disease management, aligning with broader global efforts toward sustainable agriculture. Our studies add to the knowledge about precision agriculture and inspire practical, long-lasting disease management techniques in the agricultural industry. The real-time performance of the system will need to be improved, and satellite imagery integration may be considered in the future to provide more comprehensive coverage.

A novel CNN architecture for accurate early detection and classification of Alzheimer’s disease using MRI data

Alzheimer’s disease (AD) is a debilitating neurodegenerative disorder that requires accurate diagnosis for effective management and treatment. In this article, we propose an architecture for a convolutional neural network (CNN) that utilizes magnetic resonance imaging (MRI) data from the Alzheimer’s disease Neuroimaging Initiative (ADNI) dataset to categorize AD. The network employs two separate CNN models, each with distinct filter sizes and pooling layers, which are concatenated in a classification layer. The multi-class problem is addressed across three, four, and five categories. The proposed CNN architecture achieves exceptional accuracies of 99.43%, 99.57%, and 99.13%, respectively. These high accuracies demonstrate the efficacy of the network in capturing and discerning relevant features from MRI images, enabling precise classification of AD subtypes and stages. The network architecture leverages the hierarchical nature of convolutional layers, pooling layers, and fully connected layers to extract both local and global patterns from the data, facilitating accurate discrimination between different AD categories. Accurate classification of AD carries significant clinical implications, including early detection, personalized treatment planning, disease monitoring, and prognostic assessment. The reported accuracy underscores the potential of the proposed CNN architecture to assist medical professionals and researchers in making precise and informed judgments regarding AD patients.

A novel hybrid CNN methodology for automated leaf disease detection and classification

AbstractPlant leaf diseases are challenging to categorize due to the complexity of the pattern variations and the high degrees of inter‐class similarity. Plant ailments harm food quality and production. To ensure the quality and quantity of harvests, it is essential to protect plants from disease. Detection of diseases at an early stage is the main and the most complex task for farmers due to common morphological properties like colour, shape, texture, and edges. In this study, a Hybrid Deep Learning model named Hybrid‐Convolutional Support Machine (H‐CSM) based on ‘Support Vector Machine (SVM)’, ‘Convolutional Neural Network (CNN)’ and ‘Convolutional Block Attention Module (CBAM)’ is proposed for the early diagnosis and classification of leaf diseases in plants leaf. The suggested model can initially identify different plant leaf illnesses, although it is not constrained to these. A database of pictures of plant leaves is used to test the suggested method based on different evaluation parameters. The results were highly promising, with an accuracy of up to 98.72% which has been increased by applying better learning methods. Farmers can quickly identify 36 common diseases with a little instruction for 14 plant categories, enabling them to take prompt preventive measures using the proposed method.

Enhancing diabetic retinopathy detection through preprocessing and feature extraction with MGA-CSG algorithm

Anticipatory monitoring of diabetic retinal (DR) disease is crucial in preventing vision loss and blindness, making it a leading cause of worldwide vision impairment. In this study, we propose a novel technique, the Modified Generative Adversarial-based Crossover Salp Grasshopper (MGA-CSG) approach, for early prediction and accurate classification of diabetic retinal diseases using fundus image datasets. The proposed MGA-CSG approach combines deep learning with an optimization algorithm to achieve superior classification accuracy. We start with pre-processing of data to attenuate image variation, convert intensities, denoise, and enhance contrast in the fundus images. Next, a Convolutional Neural Network (CNN) is used for feature extraction, capturing essential information from the images. To address the limited amount of feature vectors generated by the CNN and improve learning uncertainty, we employ a Generative Adversarial Network (GAN) model to augment the feature vectors. It generates additional images, allowing the classifier to train with fewer input samples, leading to improved classification performance. One of the key novelties of our approach lies in the utilization of both labeled and unlabeled data samples, enhancing the GAN training performance. We replace the binary classifier in the GAN with a multiclass classifier, enabling separate discrimination of retinal disease classes. The MGA-CSG approach leverages the crossover Grasshopper Optimizer Algorithm (GOA) and Salp Swarm Algorithm (SSA) to optimize the model and avoid falling into local optimal solutions. This optimization process further enhances the accuracy of diabetic retinal disease classification. Experimental results demonstrate the superiority of the proposed MGA-CSG approach, achieving high accuracy, precision, recall, specificity, F1-measure, and Kappa coefficient in predicting glaucoma, diabetic retinopathy, cataract, macular edema, and myopia. The classification achieved impressive accuracy, precision, recall, specificity, F1-measure, and Kappa coefficient of 98.8%, 98.7%, 96.5%, 97.1%, 98.2%, and 95%, respectively. Overall, our novel MGA-CSG approach offers an efficient and accurate method for early screening and classification of diabetic retinal diseases. The combination of CNN-based feature extraction, GAN-based augmentation, and MGA-CSG optimization contributes to the model's high performance. This approach holds significant potential in improving healthcare management and providing timely interventions for patients with retinal diseases.

Damage Detection of Gantry Crane with a Moving Mass Using Artificial Neural Network

Gantry cranes play a pivotal role in various industrial applications, and their reliable operation is paramount. While routine inspections are standard practice, certain defects, particularly in less accessible components, remain challenging to detect early. In this study, first a finite element model is presented, and the damage is introduced using random changes in the stiffness of different parts of the structure. Contrary to the assumption of inherent reliability, undetected defects in crucial structural elements can lead to catastrophic failures. Then, the vibration equations of healthy and damaged models are analyzed to find the displacement, velocity, and acceleration of the different crane parts. The learning vector quantization neural network is used to train and detect the defects. The output is the location of the damage and the damage severity. Noisy data are then used to evaluate the network performance robustness. This research also addresses the limitations of traditional inspection methods, providing early detection and classification of defects in gantry cranes. The study’s relevance lies in the need for a comprehensive and efficient damage detection method, especially for components not easily accessible during routine inspections.

Snippet Policy Network V2: Knee-Guided Neuroevolution for Multi-Lead ECG Early Classification.

Early time series classification predicts the class label of a given time series before it is completely observed. In time-critical applications, such as arrhythmia monitoring in ICU, early treatment contributes to the patient's fast recovery, and early warning could even save lives. Hence, in these cases, it is worthy of trading, to some extent, classification accuracy in favor of earlier decisions when the time series data are collected over time. In this article, we propose a novel deep reinforcement learning-based framework, snippet policy network V2 (SPN-V2), for long and varied-length multi-lead electrocardiogram (ECG) early classification. The proposed SNP-V2 contains two main components: snippet representation learning (SRL) and early classification timing learning (ECTL). The SRL is proposed to encode inner-snippet spatial correlations and inter-snippet temporal correlations into the hidden representations of the subsegment (snippet) of the input ECG. ECTL aims to learn a decision agent to classify the time series early and accurately. To optimize the proposed framework, we design a novel knee-guided neuroevolution algorithm (KGNA) to solve cardiovascular diseases' early classification problem, automatically optimizing the proposed SPN-V2 regarding the tradeoff between accuracy and earliness. In addition, we conduct a series of experiments on two real-world ECG datasets. The experimental results show the superiority of the proposed algorithm over the state-of-the-art competing methods.

Crop Monitoring System Using MODIS Time-Series Data for Within-Season Prediction of Yield and Production of US Corn and Soybeans

In terms of contribution to global food security, this study aimed to build a crop monitoring system for within-season yield prediction of US corn and soybeans by using the Moderate Resolution Imaging Spectroradiometer (time-series data, which consists of three essential core algorithms (crop phenology detection, early crop classification, and crop yield prediction methods)). Within-season predictions for 2018–2022 were then made to evaluate the perfor- mance of the proposed system by comparing it with the United States Department of Agriculture's (USDA's) monthly forecasts and the fixed statistical data. The absolute percentage errors of the proposed system for predicting national-level yield and production were less than 5% for all simulation years as of day of year (DOY) 279. The prediction accuracy as of DOY 247 and DOY 279 were comparable to the USDA's forecasts. The proposed system would enable us to make a comprehensive understanding about overview of US corn and soybean crop condition by visualizing detail spatial pattern of good- or poor harvest regions on a within-season basis.

Cancer detection and classification using a simplified binary state vector machine.

Cancer is an invasive and malignant growth of cells and is known to be one of the most fatal diseases. Its early detection is essential for decreasing the mortality rate and increasing the probability of survival. This study presents an efficient machine learning approach based on the state vector machine (SVM) to diagnose and classify tumors into malignant or benign cancer using the online lymphographic data. Further, two types of neural network architectures are also implemented to evaluate the performance of the proposed SVM-based approach. The optimal structures of the classifiers are obtained by varying the architecture, topology, learning rate, and kernel function and recording the results' accuracy. The classifiers are trained with the preprocessed data examples after noise removal and tested on the unknown cases to diagnose each example as positive or negative. Further, the positive cases are classified into different stages including metastases, malign lymph, and fibrosis. The results are evaluated against the feed-forward and generalized regression neural networks. It is found that the proposed SVM-based approach significantly improves the early detection and classification accuracy in comparison to the experienced physicians and the other machine learning approaches. The proposed approach is robust and can perform sub-class divisions for multipurpose tasks. Experimental results demonstrate that the two-class SVM gives the best results and can effectively be used for the classification of cancer. It has outperformed all other classifiers with an average accuracy of 94.90%.