Adaptive generative AI is emerging as a significant method to improve brain disease detection by providing innovative methods for brain data augmentation using modality synthesis and handling incomplete and imbalanced datasets. In this paper, we present an adaptive conditional-aware Generative Adversarial Network (GAN) that generates brain modality at a specific stage of disease by creating realistic brain imaging modalities for both Alzheimer’s disease (AD) and brain tumor. Furthermore, it dynamically learns and captures the mapping between different modalities to generate missing brain modalities, such as generating PET from MRI for Alzheimer’s disease detection and CT from MRI for brain tumor detection. Additionally, we combined this adaptive GAN with a new multimodal spatio-temporal transformer model that integrates different brain modalities such as MRI and PET for AD detection and CT with MRI for brain tumor detection and other data types, including genetic and clinical data. This method is enhanced using CNN with an innovative Squeeze-and-Excitation (SE) block. The proposed multimodal transformer encoder incorporates multi-head linear self-attention and a memory-augmented self-attention module to deal with the quadratic complexity of traditional vision transformers. A multi-cross fusion block is designed to extract the brain modalities’ interactions with genetic and clinical data. We evaluate our models using stratified 5-fold cross-validation on three datasets such as the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset for Alzheimer’s disease detection, achieving an average accuracy of 99.05 ± 0.08, and two brain tumor datasets, such as the Cancer Genome Atlas Low Grade Glioma Collection (TCGA-LGG) dataset, where we obtain 98.9 ± 0.12% and 97.50 ± 0.15% accuracy on the brain tumor dataset from Kaggle, respectively. These obtained results demonstrate the effectiveness of our proposed models in both disease prediction and progression tracking, opening a new way for more advanced brain disease detection.

Accurate assessment of crop nutritional status is critical for effective farm management, affecting both environmental sustainability and economic viability. Nitrogen, an essential nutrient for plant growth, is critical in detecting crop health and making fertilization decisions. However, standard nitrogen level estimation methods frequently include labor-intensive and environmentally dangerous laboratory analyses. In response, this study investigates the possibilities of modern technologies, notably machine learning (ML) and remote sensing, for improving nitrogen estimate in crops. Remote sensing, which uses sensors mounted on satellites, drones, or other airborne platforms, provides a non-destructive and efficient alternative to traditional methods for obtaining extensive spectral data. Machine learning techniques improve upon this approach by processing massive amounts of data to uncover significant patterns and relationships. Although previous studies have primarily relied on vegetation indices generated from spectral observations, this study provides an alternate technique. By auto-encoding raw spectral data, machine-learned features are developed as an alternative to vegetation indices, providing a new perspective on leaf nitrogen content (LNC) estimation. To test performance, a number of machine learning algorithms are examined, including random forest, support vector machines, and extreme gradient boosting. Our findings suggest that the autoencoder-based methodology outperforms established methods, highlighting its potential for reshaping nitrogen estimate in agriculture.

Wasteful irrigation systems are significant contributors to water scarcity on the globe. Irrigation Scheduling based on Machine Learning (ML) algorithms is considered essential in helping reduce these wastes significantly. We conducted in this study a systematic mapping of ML-based Irrigation scheduling to identify how researchers approached Irrigation Scheduling and which ML models have been used in this area. It builds a comprehensive overview of what has been investigated on irrigation scheduling and discusses the open issues to be addressed in the future.

Mild cognitive impairment (MCI) is a condition marked by impairment in one or more cognitive areas, but not necessarily all of them. It is frequently referred to as the stage between typical age-related cognitive decline and dementia. Recent studies had focused on different modalities to assess disorders such as dementia and Alzheimer's disease (AD). Heart rate variability (HRV) stands out among them as having the potential to identify MCI. In this paper, we propose a new MCI detection method using HRV signals. MCI patients were compared to age-matched healthy controls (HC) for the effect of performing additional cognitive and postural tasks. Twenty-four participants were enrolled to complete three tasks: a postural balance master task, two cognitive tasks called CERAD+ and Neurotrack, and baseline. HRV data were recorded during these experiments. Six machine learning (ML) models were examined for task classification including k-Nearest Neighbors, Decision tree, Random Forest, Extra Trees, Gradient Boosting, and XGBoost. To avoid over-fitting, cross-validation (CV) was employed to assess how well the built models performed. To boost accuracy, a voting ensemble classifier model is developed that combines the top ML models with the highest accuracy rates. The findings of this study demonstrated that MCI might be diagnosed with ML classifiers utilizing HRV signals, particularly when postural and cognitive functions are taken into account.

Hypo-vigilance detection is becoming an important active research areas in the biomedical signal processing field. For this purpose, electroencephalogram (EEG) is one of the most common modalities in drowsiness and awakeness detection. In this context, we propose a new EEG classification method for detecting fatigue state. Our method makes use of a and awakeness detection. In this context, we propose a new EEG classification method for detecting fatigue state. Our method makes use of a Convolutional Neural Network (CNN) architecture. We define an experimental protocol using the Emotiv EPOC+ headset. After that, we evaluate our proposed method on a recorded and annotated dataset. The reported results demonstrate high detection accuracy (93%) and indicate that the proposed method is an efficient alternative for hypo-vigilance detection as compared with other methods.

Using Reflectance Confocal Microscopy (RCM) for lentigo diagnosis is today considered essential. Indeed, RCM allows fast data acquisition with a high spatial resolution of the skin. In this paper, we use a deep convolutional neural network (CNN) to perform RCM image classification in order to detect lentigo. The proposed method relies on an InceptionV3 architecture combined with data augmentation and transfer learning. The method is validated on RCM data and shows very efficient detection performance with more than 98% of accuracy.

Text within video frames carries important information for a visual content understanding, retrieval and browsing. In this paper, we propose a video-text region extraction and classification approach that proceeds in two main steps: text region extraction followed by text region classification. In the first step, we use an approach based on a split and merge process to detect at first the appearance of text regions then to localize and extract them. A filtering process that validates the effective regions is handled. For the classification, we propose a convolution neural network (CNN) to classify extracted text regions into semantic classes. Consequently, a visual table of content is generated based on extracted and classified text regions occurring within video sequence enriched by a semantic descriptors(ie. place name, player name, event, etc.). These text regions are then considered as visual indices that offer a nonlinear content video browsing. Experimentations conducted on a variety of video sequences show the efficiency of our approach.

Text in videos contains much semantic information that can be used for video indexing and browsing. In this paper, we propose a spatiotemporal video-text localization and identification approach which proceeds in two main steps: text region localization and text region identification. In the first step we detect the significant appearance of the new objects in a frame by a split and merge processes applied on binarized edge frame pair differences. Detected objects are, a priori, considered as text. They are then filtered according to both local contrast and texture criteria in order to get the effective ones. The resulted text regions are identified based on a visual grammar descriptor containing a set of semantic text class regions characterized by visual features. A visual table of content is generated based on extracted text regions occurring within video sequence enriched by a semantic identification. The experimentation performed on a variety of video sequences shows the efficiency of our.

In this paper we present a new texture feature extraction approach. Existing methods are generally time consuming and sensible to image complexity in terms of texture's regularity, directionality and coarseness. So that we propose a method which provide both rapidity and accuracy to extract and characterize texture features. It's based on Hough Transform technique combined with an extremity segment's neighbourhood analysis and a new computation algorithm to extract segments and detect regularity. Experimental results show that this approach is robust and can be applied not only to texture analysis but also to detect text within video images.