Exploring classical machine learning for identification of pathological lung auscultations.

The use of machine learning in biomedical research has surged in recent years thanks to advances in devices and artificial intelligence. Our aim is to expand this body of knowledge by applying machine learning to pulmonary auscultation signals. Despite improvements in digital stethoscopes and attempts to find synergy between them and artificial intelligence, solutions for their use in clinical settings remain scarce. Physicians continue to infer initial diagnoses with less sophisticated means, resulting in low accuracy, leading to suboptimal patient care. To arrive at a correct preliminary diagnosis, the auscultation diagnostics need to be of high accuracy. Due to the large number of auscultations performed, data availability opens up opportunities for more effective sound analysis. In this study, digital 6-channel auscultations of 45 patients were used in various machine learning scenarios, with the aim of distinguishing between normal and abnormal pulmonary sounds. Audio features (such as fundamental frequencies F0-4, loudness, HNR, DFA, as well as descriptive statistics of log energy, RMS and MFCC) were extracted using the Python library Surfboard. Windowing, feature aggregation, and concatenation strategies were used to prepare data for machine learning algorithms in unsupervised (fair-cut forest, outlier forest) and supervised (random forest, regularized logistic regression) settings. The evaluation was carried out using 9-fold stratified cross-validation repeated 30 times. Decision fusion by averaging the outputs for a subject was also tested and found to be helpful. Supervised models showed a consistent advantage over unsupervised ones, with random forest achieving a mean AUC ROC of 0.691 (accuracy 71.11%, Kappa 0.416, F1-score 0.675) in side-based detection and a mean AUC ROC of 0.721 (accuracy 68.89%, Kappa 0.371, F1-score 0.650) in patient-based detection.

Automated Quantification of Brittle Stars in Seabed Imagery Using Computer Vision Techniques.

Underwater video surveys play a significant role in marine benthic research. Usually, surveys are filmed in transects, which are stitched into 2D mosaic maps for further analysis. Due to the massive amount of video data and time-consuming analysis, the need for automatic image segmentation and quantitative evaluation arises. This paper investigates such techniques on annotated mosaic maps containing hundreds of instances of brittle stars. By harnessing a deep convolutional neural network with pre-trained weights and post-processing results with a common blob detection technique, we investigate the effectiveness and potential of such segment-and-count approach by assessing the segmentation and counting success. Discs could be recommended instead of full shape masks for brittle stars due to faster annotation among marker variants tested. Underwater image enhancement techniques could not improve segmentation results noticeably, but some might be useful for augmentation purposes.

A fully-annotated imagery dataset of sublittoral benthic species in Svalbard, Arctic.

Underwater imagery is widely used for a variety of applications in marine biology and environmental sciences, such as classification and mapping of seabed habitats, marine environment monitoring and impact assessment, biogeographic reconstructions in the context of climate change, etc. This approach is relatively simple and cost-effective, allowing the rapid collection of large amounts of data. However, due to the laborious and time-consuming manual analysis procedure, only a small part of the information stored in the archives of underwater images is retrieved. Emerging novel deep learning methods open up the opportunity for more effective, accurate and rapid analysis of seabed images than ever before. We present annotated images of the bottom macrofauna obtained from underwater video recorded in Spitsbergen island's European Arctic waters, Svalbard Archipelago. Our videos were filmed in both the photic and aphotic zones of polar waters, often influenced by melting glaciers. We used artificial lighting and shot close to the seabed (<1 m) to preserve natural colours and avoid the distorting effect of muddy water. The underwater video footage was captured using a remotely operated vehicle (ROV) and a drop-down camera. The footage was converted to 2D mosaic images of the seabed. 2D mosaics were manually annotated by several experts using the Labelbox tool and co-annotations were refined using the SurveyJS platform. A set of carefully annotated underwater images associated with the original videos can be used by marine biologists as a biological atlas, as well as practitioners in the fields of machine vision, pattern recognition, and deep learning as training materials for the development of various tools for automatic analysis of underwater imagery.

Detecting Parkinson's disease from sustained phonation and speech signals.

This study investigates signals from sustained phonation and text-dependent speech modalities for Parkinson's disease screening. Phonation corresponds to the vowel /a/ voicing task and speech to the pronunciation of a short sentence in Lithuanian language. Signals were recorded through two channels simultaneously, namely, acoustic cardioid (AC) and smart phone (SP) microphones. Additional modalities were obtained by splitting speech recording into voiced and unvoiced parts. Information in each modality is summarized by 18 well-known audio feature sets. Random forest (RF) is used as a machine learning algorithm, both for individual feature sets and for decision-level fusion. Detection performance is measured by the out-of-bag equal error rate (EER) and the cost of log-likelihood-ratio. Essentia audio feature set was the best using the AC speech modality and YAAFE audio feature set was the best using the SP unvoiced modality, achieving EER of 20.30% and 25.57%, respectively. Fusion of all feature sets and modalities resulted in EER of 19.27% for the AC and 23.00% for the SP channel. Non-linear projection of a RF-based proximity matrix into the 2D space enriched medical decision support by visualization.

Electromyographic Patterns during Golf Swing: Activation Sequence Profiling and Prediction of Shot Effectiveness.

This study analyzes muscle activity, recorded in an eight-channel electromyographic (EMG) signal stream, during the golf swing using a 7-iron club and exploits information extracted from EMG dynamics to predict the success of the resulting shot. Muscles of the arm and shoulder on both the left and right sides, namely flexor carpi radialis, extensor digitorum communis, rhomboideus and trapezius, are considered for 15 golf players (∼5 shots each). The method using Gaussian filtering is outlined for EMG onset time estimation in each channel and activation sequence profiling. Shots of each player revealed a persistent pattern of muscle activation. Profiles were plotted and insights with respect to player effectiveness were provided. Inspection of EMG dynamics revealed a pair of highest peaks in each channel as the hallmark of golf swing, and a custom application of peak detection for automatic extraction of swing segment was introduced. Various EMG features, encompassing 22 feature sets, were constructed. Feature sets were used individually and also in decision-level fusion for the prediction of shot effectiveness. The prediction of the target attribute, such as club head speed or ball carry distance, was investigated using random forest as the learner in detection and regression tasks. Detection evaluates the personal effectiveness of a shot with respect to the player-specific average, whereas regression estimates the value of target attribute, using EMG features as predictors. Fusion after decision optimization provided the best results: the equal error rate in detection was 24.3% for the speed and 31.7% for the distance; the mean absolute percentage error in regression was 3.2% for the speed and 6.4% for the distance. Proposed EMG feature sets were found to be useful, especially when used in combination. Rankings of feature sets indicated statistics for muscle activity in both the left and right body sides, correlation-based analysis of EMG dynamics and features derived from the properties of two highest peaks as important predictors of personal shot effectiveness. Activation sequence profiles helped in analyzing muscle orchestration during golf shot, exposing a specific avalanche pattern, but data from more players are needed for stronger conclusions. Results demonstrate that information arising from an EMG signal stream is useful for predicting golf shot success, in terms of club head speed and ball carry distance, with acceptable accuracy. Surface EMG data, collected with a goal to automatically evaluate golf player's performance, enables wearable computing in the field of ambient intelligence and has potential to enhance exercising of a long carry distance drive.

Exploring the feasibility of smart phone microphone for measurement of acoustic voice parameters and voice pathology screening.

The objective of this study is to evaluate the reliability of acoustic voice parameters obtained using smart phone (SP) microphones and investigate the utility of use of SP voice recordings for voice screening. Voice samples of sustained vowel/a/obtained from 118 subjects (34 normal and 84 pathological voices) were recorded simultaneously through two microphones: oral AKG Perception 220 microphone and SP Samsung Galaxy Note3 microphone. Acoustic voice signal data were measured for fundamental frequency, jitter and shimmer, normalized noise energy (NNE), signal to noise ratio and harmonic to noise ratio using Dr. Speech software. Discriminant analysis-based Correct Classification Rate (CCR) and Random Forest Classifier (RFC) based Equal Error Rate (EER) were used to evaluate the feasibility of acoustic voice parameters classifying normal and pathological voice classes. Lithuanian version of Glottal Function Index (LT_GFI) questionnaire was utilized for self-assessment of the severity of voice disorder. The correlations of acoustic voice parameters obtained with two types of microphones were statistically significant and strong (r = 0.73-1.0) for the entire measurements. When classifying into normal/pathological voice classes, the Oral-NNE revealed the CCR of 73.7% and the pair of SP-NNE and SP-shimmer parameters revealed CCR of 79.5%. However, fusion of the results obtained from SP voice recordings and GFI data provided the CCR of 84.60% and RFC revealed the EER of 7.9%, respectively. In conclusion, measurements of acoustic voice parameters using SP microphone were shown to be reliable in clinical settings demonstrating high CCR and low EER when distinguishing normal and pathological voice classes, and validated the suitability of the SP microphone signal for the task of automatic voice analysis and screening.