Gait analysis based on inertial sensors has become an effective method of quantifying movement mechanics, such as joint kinematics and kinetics. Machine learning techniques are used to reliably ...predict joint mechanics directly from streams of IMU signals for various activities. These data-driven models require comprehensive and representative training datasets to be generalizable across the movement variability seen in the population at large. Bottlenecks in model development frequently occur due to the lack of sufficient training data and the significant time and resources necessary to acquire these datasets. Reliable methods to generate synthetic biomechanical training data could streamline model development and potentially improve model performance. In this study, we developed a methodology to generate synthetic kinematics and the associated predicted IMU signals using open source musculoskeletal modeling software. These synthetic data were used to train neural networks to predict three degree-of-freedom joint rotations at the hip and knee during gait either in lieu of or along with previously measured experimental gait data. The accuracy of the models’ kinematic predictions was assessed using experimentally measured IMU signals and gait kinematics. Models trained using the synthetic data out-performed models using only the experimental data in five of the six rotational degrees of freedom at the hip and knee. On average, root mean square errors in joint angle predictions were improved by 38% at the hip (synthetic data RMSE: 2.3°, measured data RMSE: 4.5°) and 11% at the knee (synthetic data RMSE: 2.9°, measured data RMSE: 3.3°), when models trained solely on synthetic data were compared to measured data. When models were trained on both measured and synthetic data, root mean square errors were reduced by 54% at the hip (measured + synthetic data RMSE: 1.9°) and 45% at the knee (measured + synthetic data RMSE: 1.7°), compared to measured data alone. These findings enable future model development for different activities of clinical significance without the burden of generating large quantities of gait lab data for model training, streamlining model development, and ultimately improving model performance.
The 2018 update of the Canadian Stroke Best Practice Recommendations for Acute Stroke Management, 6th edition, is a comprehensive summary of current evidence-based recommendations, appropriate for ...use by healthcare providers and system planners caring for persons with very recent symptoms of acute stroke or transient ischemic attack. The recommendations are intended for use by a interdisciplinary team of clinicians across a wide range of settings and highlight key elements involved in prehospital and Emergency Department care, acute treatments for ischemic stroke, and acute inpatient care. The most notable changes included in this 6th edition are the renaming of the module and its integration of the formerly separate modules on prehospital and emergency care and acute inpatient stroke care. The new module, Acute Stroke Management: Prehospital, Emergency Department, and Acute Inpatient Stroke Care is now a single, comprehensive module addressing the most important aspects of acute stroke care delivery. Other notable changes include the removal of two sections related to the emergency management of intracerebral hemorrhage and subarachnoid hemorrhage. These topics are covered in a new, dedicated module, to be released later this year. The most significant recommendation updates are for neuroimaging; the extension of the time window for endovascular thrombectomy treatment out to 24 h; considerations for treating a highly selected group of people with stroke of unknown time of onset; and recommendations for dual antiplatelet therapy for a limited duration after acute minor ischemic stroke and transient ischemic attack. This module also emphasizes the need for increased public and healthcare provider’s recognition of the signs of stroke and immediate actions to take; the important expanding role of paramedics and all emergency medical services personnel; arriving at a stroke-enabled Emergency Department without delay; and launching local healthcare institution code stroke protocols. Revisions have also been made to the recommendations for the triage and assessment of risk of recurrent stroke after transient ischemic attack/minor stroke and suggested urgency levels for investigations and initiation of management strategies. The goal of this updated guideline is to optimize stroke care across Canada, by reducing practice variations and reducing the gap between current knowledge and clinical practice.
Traditional machine learning (ML) techniques such as support vector machine, logistic regression, and artificial neural network have been applied most frequently in water quality anomaly detection ...tasks. This paper presents a review of progress and advances made in detecting anomalies in water quality data using ML techniques. The review encompasses both traditional ML and deep learning (DL) approaches. Our findings indicate that: 1) Generally, DL approaches outperform traditional ML techniques in terms of feature learning accuracy and fewer false positive rates. However, it is difficult to make a fair comparison between studies because of different datasets, models and parameters employed. 2) We notice that despite advances made and the advantages of the extreme learning machine (ELM), its application is sparsely exploited in this domain. This study also proposes a hybrid DL-ELM framework as a possible solution that could be investigated further and used to detect anomalies in water quality data.
The continued increase in computing resources is one key factor that is allowing deep learning researchers to scale, design and train new and complex convolutional neural network (CNN) architectures ...in terms of varying width, depth, or both width and depth to improve performance for a variety of problems. The contributions of this study include an uncovering of how different optimization algorithms impact CNN architectural setups with variations in width, depth, and both width/depth. Specifically in this study, three different CNN architectural setups in combination with nine different optimization algorithms—namely SGD vanilla, with momentum, and with Nesterov momentum, RMSProp, ADAM, ADAGrad, ADADelta, ADAMax, and NADAM—are trained and evaluated using three publicly available benchmark image classification datasets. Through extensive experimentation, we analyze the output predictions of the different optimizers with the CNN architectures using accuracy, convergence speed, and loss function as performance metrics. Findings based on the overall results obtained across the three image classification datasets show that ADAM and NADAM achieved superior performances with wider and deeper/wider setups, respectively, while ADADelta was the worst performer, especially with the deeper CNN architectural setup.
Automatic anomaly detection monitoring plays a vital role in water utilities’ distribution systems to reduce the risk posed by unclean water to consumers. One of the major problems with anomaly ...detection is imbalanced datasets. Dynamic selection techniques combined with ensemble models have proven to be effective for imbalanced datasets classification tasks. In this paper, water quality anomaly detection is formulated as a classification problem in the presences of class imbalance. To tackle this problem, considering the asymmetry dataset distribution between the majority and minority classes, the performance of sixteen previously proposed single and static ensemble classification methods embedded with resampling strategies are first optimised and compared. After that, six dynamic selection techniques, namely, Modified Class Rank (Rank), Local Class Accuracy (LCA), Overall-Local Accuracy (OLA), K-Nearest Oracles Eliminate (KNORA-E), K-Nearest Oracles Union (KNORA-U) and Meta-Learning for Dynamic Ensemble Selection (META-DES) in combination with homogeneous and heterogeneous ensemble models and three SMOTE-based resampling algorithms (SMOTE, SMOTE+ENN and SMOTE+Tomek Links), and one missing data method (missForest) are proposed and evaluated. A binary real-world drinking-water quality anomaly detection dataset is utilised to evaluate the models. The experimental results obtained reveal all the models benefitting from the combined optimisation of both the classifiers and resampling methods. Considering the three performance measures (balanced accuracy, F-score and G-mean), the result also shows that the dynamic classifier selection (DCS) techniques, in particular, the missForest+SMOTE+RANK and missForest+SMOTE+OLA models based on homogeneous ensemble-bagging with decision tree as the base classifier, exhibited better performances in terms of balanced accuracy and G-mean, while the Bg+mF+SMENN+LCA model based on homogeneous ensemble-bagging with random forest has a better overall F1-measure in comparison to the other models.
The globally ubiquitous lysianassoid amphipod, Eurythenes gryllus, has been shown to consist of multiple genetically distinct cryptic taxa, with depth considered a major driver of speciation and ...morphological divergence. Here we examine morphological variation of E. gryllus sensu lato through a continuous depth distribution that spans from abyssal (3000–6000m) into hadal depths (>6000m) in the Peru–Chile Trench (SE Pacific Ocean). Three distinct morphospecies were identified: one was confirmed as being E. magellanicus (4602–5329m) based on DNA sequence and morphological similarity. The other two morphologically distinct species were named based upon depth of occurrence; Abyssal (4602–6173m) and Hadal (6173–8074m). The three Eurythenes morphospecies showed vertical ontogenetic stratification across their bathymetric range, where juveniles were found shallower in their depth range and mature females deeper. Potential ecological and evolutionary drivers that explain the observed patterns of intra and inter-specific structure, such as hydrostatic pressure and topographical isolation, are discussed.
•Three Eurythenes morphotypes found from the Peru-Chile Trench (4600–8000 m).•Genetic divergence between morphotypes consistent with different species.•The abyssal species comprised E. magellanicus and a previously unknown species.•Vertical ontogenetic stratification was detected for each morphotype.•The hadal morphotype is thought to have undergone allopatric speciation.
Clostridioides difficile is an obligate anaerobe ubiquitous in the environment and is of particular interest in the healthcare setting as a cause of healthcare associated infection usually presenting ...with colitis. Extracolonic manifestations of C. difficile infection are less common with only rare reports of septic arthritis primarily in the setting of relative or overt immunocompromise. This report details the case of a 31-year-old immunocompetent male presenting with clinical features of septic arthritis, three weeks post right knee anterior cruciate ligament (ACL) reconstruction using a native hamstring tendon graft. C. difficile was isolated from two different samples of the synovial tissue from a subsequent arthroscopic washout and synovectomy. The ACL graft was retained. The isolate underwent whole genome sequencing and was found to be tcdA and tcdB gene deficient. Susceptibility testing showed susceptibility to benzylpenicillin and metronidazole. The patient received a two-week course of intravenous benzylpenicillin and four weeks of oral metronidazole. At one-year post cessation of antibiotics the patient has no clinical evidence of recurrence. This is the first known reported case of C. difficile septic arthritis in an immunocompetent patient. It demonstrates successful treatment of post-ACL septic arthritis with a graft retention strategy.
•C. difficile is an uncommon cause of septic arthritis.•C. difficile septic arthritis can occur in the absence of overt immunocompromise.•Septic arthritis post ACL reconstruction can be successfully treated with a graft retention strategy.
Imbalanced class distribution and missing data are two common problems and occurrences in water quality anomaly detection domain. Learning algorithms in an imbalanced dataset can yield an overrated ...classification accuracy driven by a bias towards the majority class at the expense of the minority class. On the other hand, missing values in data can induce complexity in the learning classifiers during data analysis. These two problems pose substantial challenges to the performance of learning algorithms in real-life water quality anomaly detection problems. Hence, the need for them to be carefully considered and addressed to achieve better performance. In this paper, the performance of a range of several combinations of techniques to deal with imbalanced classes in the context of binary-imbalanced water quality anomaly detection problem and the presence of missing values is extensively compare. The methods considered include seven missing data and eight resampling methods, on ten different learning state-of-the-art classifiers taking into account diversity in their learning philosophies. The different classifiers are evaluated using stratified 5-fold cross-validation, based on three performance evaluation metrics namely accuracy, ROC-AUC and F1-measure. Further experiments are carried out on nineteen variants of homogeneous and heterogeneous ensemble techniques embedded with resampling and missing value strategies during their training phase as well as an optimized deep neural network model. The experimental results show an improvement in the performance of the learning classifiers, especially when dealing with the class imbalance problem (on the one hand) and the incomplete data problem (on the other hand). Furthermore, the neural network model exhibit superior performance when dealing with both problems.
This paper presents the collected experimental data for water quality monitoring which was conducted in ten experiments by using five different common sources of water contaminants namely soil, salt, ...washing powder, chlorine and vinegar and their combination. The data were collected indoors at room temperature during the day for several days using sensors that measure pH, turbidity, flow rate, and conductivity in water. The water consumption risk (CR) was calculated as deviation based on the water quality parameters standards proposed by the World Health Organisation (WHO) and the South African Department of Water Affairs (DWA), with respect to the sensor measurement readings obtained. While the error measurements were calculated based on the expected parameter measurement per conducted experiment and repeated for 26 measurements. Pure tap water was the benchmark of water safe for human consumption. The first five experiments were performed by introducing each contaminant into the water and thereafter, two contaminants in the sixth experiment and their additions until all different contaminants were experimented at once in the last experiment.
The population structure of Hirondellea gigas (Birstein and Vinogradov, 1955), collected by baited trap from 8172 and 9316 m in the Izu-Bonin Trench (NW Pacific) was examined. Specimens were ...categorized according to sex and life stage. At 8172 m, juveniles comprised the overwhelming majority of the population, whilst at 9316 m the male: female: juvenile ratio was more evenly distributed, suggesting vertical ontogenetic structuring. Furthermore, juveniles from 8172 m were significantly smaller than those from 9316 m with an average body length of 11.1 mm (±4.6 S.D.) compared to 19.8 mm (±3.1 S.D.). Females and males showed the opposite trend to juveniles, with both the largest individuals and the greatest proportion of males and females occurring at 9316 m, no ♀6 nor brooding females were captured. Female reproductive strategies and the environmental drivers of ontogenetic structuring of H. gigas populations are discussed. We conclude that pressure per se does not drive the observed trends but rather an interaction between depth (pressure) and topography-influenced distribution of resources in terms of both quality and quantity.
PDF
