In recent years, a variety of deep learning techniques and methods have been adopted to provide AI solutions to issues within the medical field, with one specific area being audio-based classification of medical datasets. This research aims to create a novel deep learning architecture for this purpose, with a variety of different layer structures implemented for undertaking audio classification. Specifically, bidirectional Long Short-Term Memory (BiLSTM) and Gated Recurrent Units (GRU) networks in conjunction with an attention mechanism, are implemented in this research for chronic and non-chronic lung disease and COVID-19 diagnosis. We employ two audio datasets, i.e. the Respiratory Sound and the Coswara datasets, to evaluate the proposed model architectures pertaining to lung disease classification. The Respiratory Sound Database contains audio data with respect to lung conditions such as Chronic Obstructive Pulmonary Disease (COPD) and asthma, while the Coswara dataset contains coughing audio samples associated with COVID-19. After a comprehensive evaluation and experimentation process, as the most performant architecture, the proposed attention BiLSTM network (A-BiLSTM) achieves accuracy rates of 96.2% and 96.8% for the Respiratory Sound and the Coswara datasets, respectively. Our research indicates that the implementation of the BiLSTM and attention mechanism was effective in improving performance for undertaking audio classification with respect to various lung condition diagnoses.

Gait assessment is essential to understand injury prevention mechanisms during running, where high-impact forces can lead to a range of injuries in the lower extremities. Information regarding the running style to increase efficiency and/or selection of the correct running equipment, such as shoe type, can minimize the risk of injury, e.g., matching a runner's gait to a particular set of cushioning technologies found in modern shoes (neutral/support cushioning). Awareness of training or selection of the correct equipment requires an understanding of a runner's biomechanics, such as determining foot orientation when it strikes the ground. Previous work involved a low-cost approach with a foot-mounted inertial measurement unit (IMU) and an associated zero-crossing-based methodology to objectively understand a runner's biomechanics (in any setting) to learn about shoe selection. Here, an investigation of the previously presented ZC-based methodology is presented only to determine general validity for running gait assessment in a range of running abilities from novice (8 km/h) to experienced (16 km/h+). In comparison to Vicon 3D motion tracking data, the presented approach can extract pronation, foot strike location, and ground contact time with good [ICC(2,1) > 0.750] to excellent [ICC(2,1) > 0.900] agreement between 8–12 km/h runs. However, at higher speeds (14 km/h+), the ZC-based approach begins to deteriorate in performance, suggesting that other features and approaches may be more suitable for faster running and sprinting tasks.

Medical audio classification for lung abnormality diagnosis is a challenging problem owing to comparatively unstructured audio signals present in the respiratory sound clips. To tackle such challenges, we propose an ensemble model by incorporating diverse deep neural networks with attention mechanisms for undertaking lung abnormality and COVID-19 diagnosis using respiratory, speech, and coughing audio inputs. Specifically, four base deep networks are proposed, which include attention-based Convolutional Recurrent Neural Network (A-CRNN), attention-based bidirectional Long Short-Term Memory (A-BiLSTM), attention-based bidirectional Gated Recurrent Unit (A-BiGRU), as well as Convolutional Neural Network (CNN). A Particle Swarm Optimization (PSO) algorithm is used to optimize the training parameters of each network. An ensemble mechanism is used to integrate the outputs of these base networks by averaging the probability predictions of each class. Evaluated using respiratory ICBHI, Coswara breathing, speech, and cough datasets, as well as a combination of ICBHI and Coswara breathing databases, our ensemble model and base networks achieve ICBHI scores ranging from 0.920 to 0.9766. Most importantly, the empirical results indicate that a positive COVID-19 diagnosis can be distinguished to a high degree from other more common respiratory diseases using audio recordings, based on the combined ICBHI and Coswara breathing datasets.

The most common malignancies in the world are skin cancers, with melanomas being the most lethal. The emergence of Convolutional Neural Networks (CNNs) has provided a highly compelling method for medical diagnosis. This research therefore conducts transfer learning with grid search based hyper-parameter fine-tuning using six state-ofthe-art CNN models for the classification of benign nevus and malignant melanomas, with the models then being exported, implemented, and tested on a proof-of-concept Android application. Evaluated using Dermofit Image Library and PH2 skin lesion data sets, the empirical results indicate that the ResNeXt50 model achieves the highest accuracy rate with fast execution time, and a relatively small model size. It compares favourably with other related methods for melanoma diagnosis reported in the literature.

U.S. policy makers often justify agricultural subsidies by stressing that agriculture is the engine of the rural economy. We use the increase in crop prices in the late 2000s to estimate the marginal effect of increased agricultural revenues on local economies in the U.S. Heartland. We find that $1 more in crop revenue generated 64 cents in personal income, with most going to farm proprietors and workers (59 percent) or nonfarmers who own farm assets (36 percent). The evidence suggests a weak link between revenues and nonfarm income or employment, or on population.