A deep learning approach based on graphs to detect plantation lines.

Identifying plantation lines in aerial images of agricultural landscapes is re-quired for many automatic farming processes. Deep learning-based networks are among the most prominent methods to learn such patterns and extract this type of information from diverse imagery conditions. However, even state-of-the-art methods may stumble in complex plantation patterns. Here, we propose a deep learning approach based on graphs to detect plantation lines in UAV-based RGB imagery, presenting a challenging scenario containing spaced plants. The first module of our method extracts a feature map throughout the backbone, which consists of the initial layers of the VGG16. This feature map is used as an input to the Knowledge Estimation Module (KEM), organized in three concatenated branches for detecting 1) the plant positions, 2) the plantation lines, and 3) the displacement vectors between the plants. A graph modeling is applied considering each plant position on the image as vertices, and edges are formed between two vertices (i.e. plants). Finally, the edge is classified as pertaining to a certain plantation line based on three probabilities (higher than 0.5): i) in visual features obtained from the backbone; ii) a chance that the edge pixels belong to a line, from the KEM step; and iii) an alignment of the displacement vectors with the edge, also from the KEM step. Experiments were conducted initially in corn plantations with different growth stages and patterns with aerial RGB imagery to present the advantages of adopting each module. We assessed the generalization capability in the other two cultures (orange and eucalyptus) datasets. The proposed method was compared against state-of-the-art deep learning methods and achieved superior performance with a significant margin considering all three datasets. This approach is useful in extracting lines with spaced plantation patterns and could be implemented in scenarios where plantation gaps occur, generating lines with few-to-no interruptions.

Perfect prosthetic heart valve: generative design with machine learning, modeling, and optimization.

Majority of modern techniques for creating and optimizing the geometry of medical devices are based on a combination of computer-aided designs and the utility of the finite element method This approach, however, is limited by the number of geometries that can be investigated and by the time required for design optimization. To address this issue, we propose a generative design approach that combines machine learning (ML) methods and optimization algorithms. We evaluate eight different machine learning methods, including decision tree-based and boosting algorithms, neural networks, and ensembles. For optimal design, we investigate six state-of-the-art optimization algorithms, including Random Search, Tree-structured Parzen Estimator, CMA-ES-based algorithm, Nondominated Sorting Genetic Algorithm, Multiobjective Tree-structured Parzen Estimator, and Quasi-Monte Carlo Algorithm. In our study, we apply the proposed approach to study the generative design of a prosthetic heart valve (PHV). The design constraints of the prosthetic heart valve, including spatial requirements, materials, and manufacturing methods, are used as inputs, and the proposed approach produces a final design and a corresponding score to determine if the design is effective. Extensive testing leads to the conclusion that utilizing a combination of ensemble methods in conjunction with a Tree-structured Parzen Estimator or a Nondominated Sorting Genetic Algorithm is the most effective method in generating new designs with a relatively low error rate. Specifically, the Mean Absolute Percentage Error was found to be 11.8% and 10.2% for lumen and peak stress prediction respectively. Furthermore, it was observed that both optimization techniques result in design scores of approximately 95%. From both a scientific and applied perspective, this approach aims to select the most efficient geometry with given input parameters, which can then be prototyped and used for subsequent in vitro experiments. By proposing this approach, we believe it will replace or complement CAD-FEM-based modeling, thereby accelerating the design process and finding better designs within given constraints. The repository, which contains the essential components of the study, including curated source code, dataset, and trained models, is publicly available at https://github.com/ViacheslavDanilov/generative_design.

Machine learning methods for anomaly classification in wastewater treatment plants.

Modern wastewater treatment plants base their biological processes on advanced control systems which ensure compliance with discharge limits and minimize energy consumption responding to information from on-line probes. The correct readings of probes are particularly crucial for intermittent aeration controllers, which rely on real-time measurements of ammonia and oxygen in biological tanks. These data are also an important resource for developing artificial intelligence algorithms that can identify process or sensor anomalies, thus guiding the choices of plant operators and automatic process controllers. However, using anomaly detection and classification algorithms in real-time wastewater treatment is challenging because of the noisy nature of sensor measurements, the difficulty of obtaining labeled real-plant data, and the complex and interdependent mechanisms that govern biological processes. This work aims at thoroughly exploring the performance of machine learning methods in detecting and classifying the main anomalies in plants operating with intermittent aeration. Using oxygen, ammonia and aeration power measurements from a set of plants in Italy, we perform both binary and multiclass classification, and we compare them through a rigorous validation procedure that includes a test on an unknown dataset, proposing a new evaluation protocol. The classification methods explored are support vector machine, multilayer perceptron, random forest, and two gradient boosting methods (LightGBM and XGBoost). The best performance was achieved using the gradient boosting ensemble algorithms, with up to 96% of anomalies detected and up to 84% and 62% of anomalies classified correctly on the first and second datasets respectively.

Contrasting EfficientNet, ViT, and gMLP for COVID-19 Detection in Ultrasound Imagery.

A timely diagnosis of coronavirus is critical in order to control the spread of the virus. To aid in this, we propose in this paper a deep learning-based approach for detecting coronavirus patients using ultrasound imagery. We propose to exploit the transfer learning of a EfficientNet model pre-trained on the ImageNet dataset for the classification of ultrasound images of suspected patients. In particular, we contrast the results of EfficentNet-B2 with the results of ViT and gMLP. Then, we show the results of the three models by learning from scratch, i.e., without transfer learning. We view the detection problem from a multiclass classification perspective by classifying images as COVID-19, pneumonia, and normal. In the experiments, we evaluated the models on a publically available ultrasound dataset. This dataset consists of 261 recordings (202 videos + 59 images) belonging to 216 distinct patients. The best results were obtained using EfficientNet-B2 with transfer learning. In particular, we obtained precision, recall, and F1 scores of 95.84%, 99.88%, and 24 97.41%, respectively, for detecting the COVID-19 class. EfficientNet-B2 with transfer learning presented an overall accuracy of 96.79%, outperforming gMLP and ViT, which achieved accuracies of 93.03% and 92.82%, respectively.

COVID-19 Detection in CT/X-ray Imagery Using Vision Transformers.

The steady spread of the 2019 Coronavirus disease has brought about human and economic losses, imposing a new lifestyle across the world. On this point, medical imaging tests such as computed tomography (CT) and X-ray have demonstrated a sound screening potential. Deep learning methodologies have evidenced superior image analysis capabilities with respect to prior handcrafted counterparts. In this paper, we propose a novel deep learning framework for Coronavirus detection using CT and X-ray images. In particular, a Vision Transformer architecture is adopted as a backbone in the proposed network, in which a Siamese encoder is utilized. The latter is composed of two branches: one for processing the original image and another for processing an augmented view of the original image. The input images are divided into patches and fed through the encoder. The proposed framework is evaluated on public CT and X-ray datasets. The proposed system confirms its superiority over state-of-the-art methods on CT and X-ray data in terms of accuracy, precision, recall, specificity, and F1 score. Furthermore, the proposed system also exhibits good robustness when a small portion of training data is allocated.

Vision System for Automatic On-Tree Kiwifruit Counting and Yield Estimation.

Yield estimation is an essential preharvest practice among most large-scale farming companies, since it enables the predetermination of essential logistics to be allocated (i.e., transportation means, supplies, labor force, among others). An overestimation may thus incur further costs, whereas an underestimation entails potential crop waste. More interestingly, an accurate yield estimation enables stakeholders to better place themselves in the market. Yet, computer-aided precision farming is set to play a pivotal role in this respect. Kiwifruit represents a major produce in several countries (e.g., Italy, China, New and Zealand). However, up to date, the relevant literature remains short of a complete as well as automatic system for kiwifruit yield estimation. In this paper, we present a fully automatic and noninvasive computer vision system for kiwifruit yield estimation across a given orchard. It consists mainly of an optical sensor mounted on a minitractor that surveys the orchard of interest at a low pace. Afterwards, the acquired images are fed to a pipeline that incorporates image preprocessing, stitching, and fruit counting stages and outputs an estimated fruit count and yield estimation. Experimental results conducted on two large kiwifruit orchards confirm a high plausibility (i.e., errors of 6% and 15%) of the proposed system. The proposed yield estimation solution has been in commercial use for about 2 years. With respect to the traditional manual yield estimation carried out by kiwifruit companies, it was demonstrated to save a significant amount of time and cut down on estimation errors, especially when speaking of large-scale farming.

Computer vision-based phenotyping for improvement of plant productivity: a machine learning perspective.

Employing computer vision to extract useful information from images and videos is becoming a key technique for identifying phenotypic changes in plants. Here, we review the emerging aspects of computer vision for automated plant phenotyping. Recent advances in image analysis empowered by machine learning-based techniques, including convolutional neural network-based modeling, have expanded their application to assist high-throughput plant phenotyping. Combinatorial use of multiple sensors to acquire various spectra has allowed us to noninvasively obtain a series of datasets, including those related to the development and physiological responses of plants throughout their life. Automated phenotyping platforms accelerate the elucidation of gene functions associated with traits in model plants under controlled conditions. Remote sensing techniques with image collection platforms, such as unmanned vehicles and tractors, are also emerging for large-scale field phenotyping for crop breeding and precision agriculture. Computer vision-based phenotyping will play significant roles in both the nowcasting and forecasting of plant traits through modeling of genotype/phenotype relationships.

Real-Time Indoor Scene Description for the Visually Impaired Using Autoencoder Fusion Strategies with Visible Cameras.

This paper describes three coarse image description strategies, which are meant to promote a rough perception of surrounding objects for visually impaired individuals, with application to indoor spaces. The described algorithms operate on images (grabbed by the user, by means of a chest-mounted camera), and provide in output a list of objects that likely exist in his context across the indoor scene. In this regard, first, different colour, texture, and shape-based feature extractors are generated, followed by a feature learning step by means of AutoEncoder (AE) models. Second, the produced features are fused and fed into a multilabel classifier in order to list the potential objects. The conducted experiments point out that fusing a set of AE-learned features scores higher classification rates with respect to using the features individually. Furthermore, with respect to reference works, our method: (i) yields higher classification accuracies, and (ii) runs (at least four times) faster, which enables a potential full real-time application.

Active learning methods for electrocardiographic signal classification.

In this paper, we present three active learning strategies for the classification of electrocardiographic (ECG) signals. Starting from a small and suboptimal training set, these learning strategies select additional beat samples from a large set of unlabeled data. These samples are labeled manually, and then added to the training set. The entire procedure is iterated until the construction of a final training set representative of the considered classification problem. The proposed methods are based on support vector machine classification and on the: 1) margin sampling; 2) posterior probability; and 3) query by committee principles, respectively. To illustrate their performance, we conducted an experimental study based on both simulated data and real ECG signals from the MIT-BIH arrhythmia database. In general, the obtained results show that the proposed strategies exhibit a promising capability to select samples that are significant for the classification process, i.e., to boost the accuracy of the classification process while minimizing the number of involved labeled samples.

Classification of electrocardiogram signals with support vector machines and particle swarm optimization.

The aim of this paper is twofold. First, we present a thorough experimental study to show the superiority of the generalization capability of the support vector machine (SVM) approach in the automatic classification of electrocardiogram (ECG) beats. Second, we propose a novel classification system based on particle swarm optimization (PSO) to improve the generalization performance of the SVM classifier. For this purpose, we have optimized the SVM classifier design by searching for the best value of the parameters that tune its discriminant function, and upstream by looking for the best subset of features that feed the classifier. The experiments were conducted on the basis of ECG data from the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) arrhythmia database to classify five kinds of abnormal waveforms and normal beats. In particular, they were organized so as to test the sensitivity of the SVM classifier and that of two reference classifiers used for comparison, i.e., the k-nearest neighbor (kNN) classifier and the radial basis function (RBF) neural network classifier, with respect to the curse of dimensionality and the number of available training beats. The obtained results clearly confirm the superiority of the SVM approach as compared to traditional classifiers, and suggest that further substantial improvements in terms of classification accuracy can be achieved by the proposed PSO-SVM classification system. On an average, over three experiments making use of a different total number of training beats (250, 500, and 750, respectively), the PSO-SVM yielded an overall accuracy of 89.72% on 40438 test beats selected from 20 patient records against 85.98%, 83.70%, and 82.34% for the SVM, the kNN, and the RBF classifiers, respectively.