Application of image processing and transfer learning for the detection of rust disease.

Plant diseases introduce significant yield and quality losses to the food production industry, worldwide. Early identification of an epidemic could lead to more effective management of the disease and potentially reduce yield loss and limit excessive input costs. Image processing and deep learning techniques have shown promising results in distinguishing healthy and infected plants at early stages. In this paper, the potential of four convolutional neural network models, including Xception, Residual Networks (ResNet)50, EfficientNetB4, and MobileNet, in the detection of rust disease on three commercially important field crops was evaluated. A dataset of 857 positive and 907 negative samples captured in the field and greenhouse environments were used. Training and testing of the algorithms were conducted using 70% and 30% of the data, respectively where the performance of different optimizers and learning rates were tested. Results indicated that EfficientNetB4 model was the most accurate model (average accuracy = 94.29%) in the disease detection followed by ResNet50 (average accuracy = 93.52%). Adaptive moment estimation (Adam) optimizer and learning rate of 0.001 outperformed all other corresponding hyperparameters. The findings from this study provide insights into the development of tools and gadgets useful in the automated detection of rust disease required for precision spraying.

Using machine learning methods and EEG to discriminate aircraft pilot cognitive workload during flight.

Pilots of aircraft face varying degrees of cognitive workload even during normal flight operations. Periods of low cognitive workload may be followed by periods of high cognitive workload and vice versa. During such changing demands, there exists potential for increased error on behalf of the pilots due to periods of boredom or excessive cognitive task demand. To further understand cognitive workload in aviation, the present study involved collection of electroencephalogram (EEG) data from ten (10) collegiate aviation students in a live-flight environment in a single-engine aircraft. Each pilot possessed a Federal Aviation Administration (FAA) commercial pilot certificate and either FAA class I or class II medical certificate. Each pilot flew a standardized flight profile representing an average instrument flight training sequence. For data analysis, we used four main sub-bands of the recorded EEG signals: delta, theta, alpha, and beta. Power spectral density (PSD) and log energy entropy of each sub-band across 20 electrodes were computed and subjected to two feature selection algorithms (recursive feature elimination (RFE) and lasso cross-validation (LassoCV), and a stacking ensemble machine learning algorithm composed of support vector machine, random forest, and logistic regression. Also, hyperparameter optimization and tenfold cross-validation were used to improve the model performance, reliability, and generalization. The feature selection step resulted in 15 features that can be considered an indicator of pilots' cognitive workload states. Then these features were applied to the stacking ensemble algorithm, and the highest results were achieved using the selected features by the RFE algorithm with an accuracy of 91.67% (± 0.11), a precision of 93.89% (± 0.09), recall of 91.67% (± 0.11), F-score of 91.22% (± 0.12), and the mean ROC-AUC of 0.93 (± 0.06). The achieved results indicated that the combination of PSD and log energy entropy, along with well-designed machine learning algorithms, suggest the potential for the use of EEG to discriminate periods of the low, medium, and high workload to augment aircraft system design, including flight automation features to improve aviation safety.

The art gallery maze: a novel tool to assess human navigational abilities.

Humans differ widely in their ability to navigate effectively through the environment and in spatial memory skills. Navigation in the environment requires the analysis of many spatial cues, the construction of internal representations, and the use of various strategies. We present a novel tool to assess individual differences in human navigation, consisting of a virtual radial-arm maze presented as an art gallery to explore whether different sets of instructions (intentional or incidental) affect subjects' navigation performance. We furthermore tested the effect of the instructions on exploration strategies during both place learning and recall. We evaluated way-finding ability in 42 subjects, and individual differences in navigation were assessed through the analysis of navigational paths, which permitted the isolation and definition of a few strategies adopted by the incidental and intentional instructions groups. Our results showed that the intentional instruction group performed better than the other group: these subjects correctly paired each central statue and the two paintings in the adjacent arms, and they made less working and reference memory errors. Our analysis of path lengths showed that the intentional instruction group spent more time in the maze (thus being slower), specifically in the central hall, and covered more distance; the time spent in the main hall was, therefore, indicative of the quality of the following performance. Studying how environmental representations and the relative navigational strategies vary among "intentional" and "incidental" groups provides a new window into the acknowledgment of possible strategies to help subjects construct more efficient approaches in human navigation.