Abstract

Abstract

Abstract
In recent years, the use of remote sensing data obtained from satellite or unmanned aerial vehicle (UAV) imagery has grown in popularity for crop classification tasks such as yield prediction, soil classification or crop mapping. The ready availability of information, with improved temporal, radiometric, and spatial resolution, has resulted in the accumulation of vast amounts of data. Meeting the demands of analysing this data requires innovative solutions, and artificial intelligence techniques offer the necessary support. This systematic review aims to evaluate the effectiveness of deep learning techniques for crop classification using remote sensing data from aerial imagery. The reviewed papers focus on a variety of deep learning architectures, including convolutional neural networks (CNNs), long short-term memory networks, transformers, and hybrid CNN-recurrent neural network models, and incorporate techniques such as data augmentation, transfer learning, and multimodal fusion to improve model performance. The review analyses the use of these techniques to boost crop classification accuracy by developing new deep learning architectures or by combining various types of remote sensing data. Additionally, it assesses the impact of factors like spatial and spectral resolution, image annotation, and sample quality on crop classification. Ensembling models or integrating multiple data sources tends to enhance the classification accuracy of deep learning models. Satellite imagery is the most commonly used data source due to its accessibility and typically free availability. The study highlights the requirement for large amounts of training data and the incorporation of non-crop classes to enhance accuracy and provide valuable insights into the current state of deep learning models and datasets for crop classification tasks.

Abstract
Pathologies in concrete structures, such as cracks, splintering, efflorescence, corrosion spots, and exposed steel bars, can be visually evidenced on the concrete surface. This paper proposes a method for automatically detecting these pathologies from images of the concrete structure. The proposed method uses deep neural networks to detect pathologies in these images. This method results in time savings and error reduction. The paper presents results in detecting the pathologies from wide-angle images containing the overall structure and also for the specific pathology identification task for cropped images of the region of the pathology. Identifying pathologies in cropped images, the classification task could be performed with 99.4% accuracy using cross-validation and classifying cracks. Wide images containing no, one, or several pathologies in the same image, the case of pathology detection, could be analyzed with the YOLO network to identify five pathology classes. The results for detection with YOLO were measured with mAP, mean Average Precision, for five classes of concrete pathology, reaching 11.80% for fissure, 19.22% for fragmentation, 5.62% for efflorescence, 27.24% for exposed bar, and 24.44% for corrosion. Pathology identification in concrete photos can be optimized using deep learning.

Abstract
Precancerous conditions such as intestinal metaplasia (IM) have a key role in gastric cancer development and can be detected during endoscopy. During upper gastrointestinal endoscopy (UGIE), misdiagnosis can occur due to technical and human factors or by the nature of the lesions, leading to a wrong diagnosis which can result in no surveillance/treatment and impairing the prevention of gastric cancer. Deep learning systems show great potential in detecting precancerous gastric conditions and lesions by using endoscopic images and thus improving and aiding physicians in this task, resulting in higher detection rates and fewer operation errors. This study aims to develop deep learning algorithms capable of detecting IM in UGIE images with a focus on model explainability and interpretability. In this work, white light and narrow-band imaging UGIE images collected in the Portuguese Institute of Oncology of Porto were used to train deep learning models for IM classification. Standard models such as ResNet50, VGG16 and InceptionV3 were compared to more recent algorithms that rely on attention mechanisms, namely the Vision Transformer (ViT), trained in 818 UGIE images (409 normal and 409 IM). All the models were trained using a 5-fold cross-validation technique and for validation, an external dataset will be tested with 100 UGIE images (50 normal and 50 IM). In the end, explainability methods (Grad-CAM and attention rollout) were used for more clear and more interpretable results. The model which performed better was ResNet50 with a sensitivity of 0.75 (±0.05), an accuracy of 0.79 (±0.01), and a specificity of 0.82 (±0.04). This model obtained an AUC of 0.83 (±0.01), where the standard deviation was 0.01, which means that all iterations of the 5-fold cross-validation have a more significant agreement in classifying the samples than the other models. The ViT model showed promising performance, reaching similar results compared to the remaining models. © 2023, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

Abstract
Automatic Lip-Reading (ALR), also known as Visual Speech Recognition (VSR), is the technological process to extract and recognize speech content, based solely on the visual recognition of the speaker’s lip movements. Besides hearing-impaired people, regular hearing people also resort to visual cues for word disambiguation, every time one is in a noisy environment. Due to the increasingly interest in developing ALR systems, a considerable number of research articles are being published. This article selects, analyses, and summarizes the main papers from 2018 to early 2022, from traditional methods with handcrafted feature extraction algorithms to end-to-end deep learning based ALR which fully take advantage of learning the best features, and of the evergrowing publicly available databases. By providing a recent state-of-the-art overview, identifying trends, and presenting a conclusion on what is to be expected in future work, this article becomes an efficient way to update on the most relevant ALR techniques. © 2023, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.