Open-source Algorithm Research Articles

In silico simulation of hepatic arteries: An open-source algorithm for efficient synthetic data generation.

In silico testing of novel image reconstruction and quantitative algorithms designed for interventional imaging requires realistic high-resolution modeling of arterial trees with contrast dynamics. Furthermore, data synthesis for training of deep learning algorithms requires that an arterial tree generation algorithm be computationally efficient and sufficiently random. The purpose of this paper is to provide a method for anatomically and physiologically motivated, computationally efficient, random hepatic arterial tree generation. The vessel generation algorithm uses a constrained constructive optimization approach with a volume minimization-based cost function. The optimization is constrained by the Couinaud liver classification system to assure a main feeding artery to each Couinaud segment. An intersection check is included to guarantee non-intersecting vasculature and cubic polynomial fits are used to optimize bifurcation angles and to generate smoothly curved segments. Furthermore, an approach to simulate contrast dynamics and respiratory and cardiac motion is also presented. The proposed algorithm can generate a synthetic hepatic arterial tree with 40 000 branches in 11 s. The high-resolution arterial trees have realistic morphological features such as branching angles (MAD with Murray's law ), radii (median Murray deviation ), and smoothly curved, non-intersecting vessels. Furthermore, the algorithm assures a main feeding artery to each Couinaud segment and is random (variability=0.98 ± 0.01). This method facilitates the generation of large datasets of high-resolution, unique hepatic angiograms for the training of deep learning algorithms and initial testing of novel 3D reconstruction and quantitative algorithms designed for interventional imaging.

Fine-scale mapping of urban malaria exposure under data scarcity: an approach centred on vector ecology

BackgroundAlthough malaria transmission has experienced an overall decline in sub-Saharan Africa, urban malaria is now considered an emerging health issue due to rapid and uncontrolled urbanization and the adaptation of vectors to urban environments. Fine-scale hazard and exposure maps are required to support evidence-based policies and targeted interventions, but data-driven predictive spatial modelling is hindered by gaps in epidemiological and entomological data. A knowledge-based geospatial framework is proposed for mapping the heterogeneity of urban malaria hazard and exposure under data scarcity. It builds on proven geospatial methods, implements open-source algorithms, and relies heavily on vector ecology knowledge and the involvement of local experts.MethodsA workflow for producing fine-scale maps was systematized, and most processing steps were automated. The method was evaluated through its application to the metropolitan area of Dakar, Senegal, where urban transmission has long been confirmed. Urban malaria exposure was defined as the contact risk between adult Anopheles vectors (the hazard) and urban population and accounted for socioeconomic vulnerability by including the dimension of urban deprivation that is reflected in the morphology of the built-up fabric. Larval habitat suitability was mapped through a deductive geospatial approach involving the participation of experts with a strong background in vector ecology and validated with existing geolocated entomological data. Adult vector habitat suitability was derived through a similar process, based on dispersal from suitable breeding site locations. The resulting hazard map was combined with a population density map to generate a gridded urban malaria exposure map at a spatial resolution of 100 m.ResultsThe identification of key criteria influencing vector habitat suitability, their translation into geospatial layers, and the assessment of their relative importance are major outcomes of the study that can serve as a basis for replication in other sub-Saharan African cities. Quantitative validation of the larval habitat suitability map demonstrates the reliable performance of the deductive approach, and the added value of including local vector ecology experts in the process. The patterns displayed in the hazard and exposure maps reflect the high degree of heterogeneity that exists throughout the city of Dakar and its suburbs, due not only to the influence of environmental factors, but also to urban deprivation.ConclusionsThis study is an effort to bring geospatial research output closer to effective support tools for local stakeholders and decision makers. Its major contributions are the identification of a broad set of criteria related to vector ecology and the systematization of the workflow for producing fine-scale maps. In a context of epidemiological and entomological data scarcity, vector ecology knowledge is key for mapping urban malaria exposure. An application of the framework to Dakar showed its potential in this regard. Fine-grained heterogeneity was revealed by the output maps, and besides the influence of environmental factors, the strong links between urban malaria and deprivation were also highlighted.

Coupled Tamm Phonon and Plasmon Polaritons for Designer Planar Multiresonance Absorbers.

Wavelength-selective absorbers (WS-absorbers) are of interest for various applications, including chemical sensing and light sources. Lithography-free fabrication of WS-absorbers can be realized via Tamm plasmon polaritons (TPPs) supported by distributed Bragg reflectors (DBRs) on plasmonic materials. While multifrequency and nearly arbitrary spectra can be realized with TPPs via inverse design algorithms, demanding and thick DBRs are required for high quality-factors (Q-factors) and/or multiband TPP-absorbers, increasing the cost and reducing fabrication error tolerance. Here, high Q-factor multiband absorption with limited DBR layers (3 layers) is experimentally demonstrated by Tamm hybrid polaritons (THPs) formed by coupling TPPs and Tamm phonon polaritons when modal frequencies are overlapped. Compared to the TPP component, the Q-factors of THPs are improved twofold, and the angular broadening is also reduced twofold, facilitating applications where narrow-band and nondispersive WS-absorbers are needed. Moreover, an open-source algorithm is developed to inversely design THP-absorbers consisting of anisotropic media and exemplify that the modal frequencies can be assigned to desirable positions. Furthermore, it is demonstrated that inversely designed THP-absorbers can realize same spectral resonances with fewer DBR layers than a TPP-absorber, thus reducing the fabrication complexity and enabling more cost-effective, lithography-free, wafer-scale WS-absorberss for applications such as free-space communications and gas sensing.

Comprehensive study of micro-seismicity by using an automatic monitoring platform

A modern digital seismic network, with many stations optimally distributed on the earthquake causative seismic zone, enables detection of very low magnitude earthquakes and determination of their source parameters. It is essential to associate to such kind of networks procedures to analyze the huge amount of continuously recorded data for monitoring the space-time-magnitude evolution of natural and/or induced seismicity. Hence, the demand for near-real-time, automated data collection and analysis procedures for assisting seismic network operators in carrying out microearthquake monitoring is growing. In response to this need, we designed a computational software platform, TREMOR, for fast and reliable detection and characterization of seismicity recorded by a dense local seismic network. TREMOR integrates different open-source seismological algorithms for earthquake signal detection, location, and source characterizations in a fully automatic workflow. We applied the platform in play-back mode to the continuous waveform data recorded during 1 month at the Japanese Hi-net seismic network in the Nagano region (Japan) and compared the resulting catalog with the Japan Meteorological Agency bulletin in terms of number of detections, location pattern and magnitudes. The results show that the completeness magnitude of the new seismic catalog decreased by 0.35 units of the local magnitude scale and consequently the number of events increased by about 60% with respect to the available catalog. Moreover, the fault plane solutions resulted coherent with the stress regime of the region, and the Vp/Vs ratio well delineated the main structural features of the area. According to our results, TREMOR has shown to be a valid tool for investigating and studying earthquakes, especially to identify and monitor natural or induced micro-seismicity.

AutoComet: A fully automated algorithm to quickly and accurately analyze comet assays

DNA damage is a common cellular feature seen in cancer and neurodegenerative disease, but fast and accurate methods for quantifying DNA damage are lacking. Comet assays are a biochemical tool to measure DNA damage based on the migration of broken DNA strands towards a positive electrode, which creates a quantifiable ‘tail’ behind the cell. However, a major limitation of this approach is the time needed for analysis of comets in the images with available open-source algorithms. The requirement for manual curation and the laborious pre- and post-processing steps can take hours to days. To overcome these limitations, we developed AutoComet, a new open-source algorithm for comet analysis that utilizes automated comet segmentation and quantification of tail parameters. AutoComet first segments and filters comets based on size and intensity and then filters out comets without a well-connected head and tail, which significantly increases segmentation accuracy. Because AutoComet is fully automated, it minimizes curator bias and is scalable, decreasing analysis time over ten-fold, to less than 3 s per comet. AutoComet successfully detected statistically significant differences in tail parameters between cells with and without induced DNA damage, and was more comparable to the results of manual curation than other open-source software analysis programs. We conclude that the AutoComet algorithm provides a fast, unbiased and accurate method to quantify DNA damage that avoids the inherent limitations of manual curation and will significantly improve the ability to detect DNA damage.

Integrated use of Sentinel-1 and Sentinel-2 data and open-source machine learning algorithms for burnt and unburnt scars

This research compares the use of the SAR (Sentinel-1) and Optical (Sentinel-2) sensors in identifying and mapping burnt and unburnt scars are rising during a bushfire in southeastern Australia and Margalla Hills, Islamabad, Pakistan, in 2019 and 2020. In order to evaluate the backscatter strength along with the Polarimetric decomposition portion, the C-band dual-polarized Sentinel-1 data was investigated to determine the magnitude of the burnt areas of forest cover in the study area. We could derive texture measurements from locally-based statistics using the Grey Level Co-occurrence Matrix (GLCM) and the backscatter coefficient. This was because of how well it picked up on differences in texture between burned and unburned scars. In contrast, Sentinel-2 optical remote sensing was employed to evaluate the extent of the burnt intensity levels for both regions utilizing the differential Normalized Burnt Ratio (dNBR). A Support Vector Machine (SVM) and Markov Random Field (MRF) classifier were utilized to investigate the study’s context. The ideal smoothing parameter is the result of incorporating the image’s spectral characteristics and spatial meaning. Sentinel-2 images were used as a foundation for both the test and training datasets, which were built from images of both unburned and burned areas broken down pixel by pixel. In both types, including spectral sensitivity and sensitivity of Polarimetric for the two groups identified after classification, the experimental findings showed a clear association between them. The algorithm’s efficiency was evaluated using the kappa coefficient and F-score calculation. Except for Sentinel-1 data in Pakistan, all fire areas have more than 0.80 accuracies. The highest precision of both Sentinel-1 and Sentinel-2 was also provided by the performance of users’ and producers’ accuracy. The entropy alpha decomposition helped define the target given by the H-a plane based on its physical properties. After the burn, the entropy and alpha values diminished and formed a pattern. However, the findings in this field validate the effectiveness of SAR sensors data and optical satellite in forest applications. The related sensitivity is highly dependent on the composition of the landscape, the geographical nature of the study area, and the severity of the burn.

The development and validation of an open-source accelerometery algorithm for measuring jump height and frequency in ballet

ABSTRACT The aim was to determine the validity of an open-source algorithm for measuring jump height and frequency in ballet using a wearable accelerometer. Nine professional ballet dancers completed a routine ballet class whilst wearing an accelerometer positioned at the waist. Two investigators independently conducted time-motion analysis to identify time-points at which jumps occurred. Accelerometer data were cross-referenced with time-motion data to determine classification accuracy. To determine the validity of the measurement of jump height, five participants completed nine jetés, nine sautés and three double tour en l’air from a force plate. The jump height predicted by the accelerometer algorithm was compared to the force plate jump height to determine agreement. Across 1440 jumps observed in time-motion analysis, 1371 true positives, 34 false positives and 69 false negatives were identified by the algorithm, resulting in a sensitivity of 0.98, a precision of 0.95 and a miss rate of 0.05. For all jump types, mean absolute error was 2.6 cm and the repeated measures correlation coefficient was 0.97. Bias was 1.2 cm and 95% limits of agreement were −4.9 to 7.2 cm. The algorithm may be used to manage jump load, implement periodization strategies, or plan return-to-jump pathways for rehabilitating athletes.

Inferior Alveolar Canal Automatic Detection with Deep Learning CNNs on CBCTs: Development of a Novel Model and Release of Open-Source Dataset and Algorithm

Introduction: The need of accurate three-dimensional data of anatomical structures is increasing in the surgical field. The development of convolutional neural networks (CNNs) has been helping to fill this gap by trying to provide efficient tools to clinicians. Nonetheless, the lack of a fully accessible datasets and open-source algorithms is slowing the improvements in this field. In this paper, we focus on the fully automatic segmentation of the Inferior Alveolar Canal (IAC), which is of immense interest in the dental and maxillo-facial surgeries. Conventionally, only a bidimensional annotation of the IAC is used in common clinical practice. A reliable convolutional neural network (CNNs) might be timesaving in daily practice and improve the quality of assistance. Materials and methods: Cone Beam Computed Tomography (CBCT) volumes obtained from a single radiological center using the same machine were gathered and annotated. The course of the IAC was annotated on the CBCT volumes. A secondary dataset with sparse annotations and a primary dataset with both dense and sparse annotations were generated. Three separate experiments were conducted in order to evaluate the CNN. The IoU and Dice scores of every experiment were recorded as the primary endpoint, while the time needed to achieve the annotation was assessed as the secondary end-point. Results: A total of 347 CBCT volumes were collected, then divided into primary and secondary datasets. Among the three experiments, an IoU score of 0.64 and a Dice score of 0.79 were obtained thanks to the pre-training of the CNN on the secondary dataset and the creation of a novel deep label propagation model, followed by proper training on the primary dataset. To the best of our knowledge, these results are the best ever published in the segmentation of the IAC. The datasets is publicly available and algorithm is published as open-source software. On average, the CNN could produce a 3D annotation of the IAC in 6.33 s, compared to 87.3 s needed by the radiology technician to produce a bidimensional annotation. Conclusions: To resume, the following achievements have been reached. A new state of the art in terms of Dice score was achieved, overcoming the threshold commonly considered of 0.75 for the use in clinical practice. The CNN could fully automatically produce accurate three-dimensional segmentation of the IAC in a rapid setting, compared to the bidimensional annotations commonly used in the clinical practice and generated in a time-consuming manner. We introduced our innovative deep label propagation method to optimize the performance of the CNN in the segmentation of the IAC. For the first time in this field, the datasets and the source codes used were publicly released, granting reproducibility of the experiments and helping in the improvement of IAC segmentation.

Estimating the impact of indirect action in neutron-induced DNA damage clusters and neutron RBE

Background: Neutron radiation protection factors indicate that the risk of neutron-induced stochastic biological effects is higher compared with other types of ionising radiation, and has strong energy dependence. Recent Monte Carlo studies simulated neutron radiation on a nuclear DNA model and demonstrated that the energy-dependent radiobiological risk of neutrons can be correlated with the induction of DNA damage clusters, particularly those that contain difficult-to-repair double-strand breaks. The main limitation of these studies is that only direct radiation action was investigated. Thus, for a more comprehensive understanding of pre-repair neutron-induced DNA damage, indirect action must be modelled and its impact must be quantified. Methods: An open-source algorithm for indirect action available in the TOPAS-nBio track structure Monte Carlo toolkit was adapted into our group’s existing TOPAS and TOPAS-nBio simulation pipeline for neutron and photon radiation. We performed 100 independent simulated irradiations of monoenergetic neutrons from 1 eV to 10 MeV on our existing custom-built nuclear DNA model, and scored various types of DNA damage due to direct and indirect action. The yields of DNA damage were stratified according to the damage-inducing action. For the resulting clusters of DNA damage, we determined the average cluster length and lesion count per cluster. This procedure was also performed for 250-keV x-ray photons that served as our reference radiation. We estimated neutron relative biological effectiveness (RBE) by dividing the neutron-inflicted yield of DNA damage clusters by photon-inflicted counterparts. Finally, we compared our RBE results with established radiation protection factors and previous studies that modelled direct action alone. Results: The inclusion of indirect action increased the yield of DNA damage significantly (the increase varies with damage type). We found that the majority of neutron-induced DNA damage events were isolated simple lesions due to indirect action, while most clustered lesions were hybrid in nature (i.e. contain lesions due to direct and indirect action). As for cluster properties, the inclusion of indirect action increased the average length of clusters by approximately 50% and the number of lesions per cluster by approximately 25%. Our estimated energy-dependent neutron RBE for inducing DNA damage clusters follows similar trends as the established radiation protection factors and the previous direct-action-only estimates, but is lower in magnitude. We found that this lower magnitude is due to the greater impact of indirect action in the yield of photon-induced clustered DNA damage compared with neutron-induced clustered lesions. Conclusion: Indirect action has significant effects on radiation-induced DNA damage clusters in terms of yield, length, and lesion count per cluster, and serves to amplify the effects of direct action. The energy-dependent risk of neutron-induced stochastic effects is likely related to, but not completely explained by, the induction of DNA damage clusters. For a more complete model of neutron RBE, the investigation of factors such as DNA damage repair and non-targeted radiation effects is recommended.

Comparative Analysis of SLAM Algorithms for Mechanical LiDAR and Solid-State LiDAR

With the advancement of light detection and ranging (LiDAR) technology in recent years, various new types of LiDAR have emerged, and the price of LiDAR equipment has gradually decreased. At present, low-cost solid-state LiDARs are gradually occupying the market. To evaluate the performance of two LIDARs for simultaneous localization and mapping. This study investigated the application of solid-state LiDAR and mechanical LiDAR in localization and mapping systems and comparatively analyzed their advantages and disadvantages. We selected some classic open-source algorithms [such as LiDAR odometry and mapping (A-LOAM)] to evaluate the performance of mechanical LiDAR and solid-state LiDAR in localization. The experimental data are adopted from some representative open-source data (such as KITTI data) and real data collected by Shenzhen University. The results showed that the localization accuracy of solid-state LiDAR was lower than that of mechanical LiDAR when the mobile robot moved to the corner and faced square to the wall at close range. Moreover, the localization accuracy of solid-state LiDAR was the same as or even higher than that of mechanical LiDAR when the mobile robots had small changes in the field of view (FOV) and the mobile robot moved along straight lines or other tracks.

A Review of Common Techniques for Visual Simultaneous Localization and Mapping

Mobile robots are widely used in medicine, agriculture, home furnishing, and industry. Simultaneous localization and mapping (SLAM) is the working basis of mobile robots, so it is extremely necessary and meaningful for making researches on SLAM technology. SLAM technology involves robot mechanism kinematics, logic, mathematics, perceptual detection, and other fields. However, it faces the problem of classifying the technical content, which leads to diverse technical frameworks of SLAM. Among all sorts of SLAM, visual SLAM (V-SLAM) has become the key academic research due to its advantages of low price, easy installation, and simple algorithm model. Firstly, we illustrate the superiority of V-SLAM by comparing it with other localization techniques. Secondly, we sort out some open-source V-SLAM algorithms and compare their real-time performance, robustness, and innovation. Then, we analyze the frameworks, mathematical models, and related basic theoretical knowledge of V-SLAM. Meanwhile, we review the related works from four aspects: visual odometry, back-end optimization, loop closure detection, and mapping. Finally, we prospect the future development trend and make a foundation for researchers to expand works in the future. All in all, this paper classifies each module of V-SLAM in detail and provides better readability to readers. This is undoubtedly the most comprehensive review of V-SLAM recently.

Improving Dynamic Placement of Virtual Machines in Cloud Data Centers Based on Open-Source Development Model Algorithm

Improving Dynamic Placement of Virtual Machines in Cloud Data Centers Based on Open-Source Development Model Algorithm

Exploratory Spatio-Temporal Data Analysis (ESTDA) of Dengue and its association with climatic, environmental, and sociodemographic factors in Punjab, India

Routine health data is rich in information but underutilised for research in Low and Middle-Income countries. The present study was carried out to understand spatiotemporal patterns of dengue and its association with risk factors using routine data from health and allied sectors. ESTDA included estimation of dengue incidence rates, time series features and correlation coefficients up to the sub-district level. Scatter plots and correlation coefficients were used to identify relationships between covariates. Dengue incidence in 2015–19 was 47.76, 33.64, 52.03, 49.71, and 33.36 per 100,000, respectively, with a mean (SD) age of 34.33 (16.78) years and the majority being males (63.94%). Dengue had significant cross-correlation, non-linear relationships, and spatio-temporal associations with climatic, environmental, and socio-demographic risk factors. Significant autocorrelation of dengue occurrence was present at a lag of one month with seasonal patterns. The reproducible open-source algorithms add value to existing Routine Health Information Systems, and the findings will enable the development of Spatio-temporal models in future research. The research was done using R version 4.1.0.

PyVisualFields: A Python Package for Visual Field Analysis.

Artificial intelligence (AI) methods are changing all areas of research and have a variety of capabilities of analysis in ophthalmology, specifically in visual fields (VFs) to detect or predict vision loss progression. Whereas most of the AI algorithms are implemented in Python language, which offers numerous open-source functions and algorithms, the majority of algorithms in VF analysis are offered in the R language. This paper introduces PyVisualFields, a developed package to address this gap and make available VF analysis in the Python language. For the first version, the R libraries for VF analysis provided by vfprogression and visualFields packages are analyzed to define the overlaps and distinct functions. Then, we defined and translated this functionality into Python with the help of the wrapper library rpy2. Besides maintaining, the subsequent versions' milestones are established, and the third version will be R-independent. The developed Python package is available as open-source software via the GitHub repository and is ready to be installed from PyPI. Several Jupyter notebooks are prepared to demonstrate and describe the capabilities of the PyVisualFields package in the categories of data presentation, normalization and deviation analysis, plotting, scoring, and progression analysis. We developed a Python package and demonstrated its functionality for VF analysis and facilitating ophthalmic research in VF statistical analysis, illustration, and progression prediction. Using this software package, researchers working on VF analysis can more quickly create algorithms for clinical applications using cutting-edge AI techniques.

Machine Learning Quantified Tumor-Stroma Ratio Is an Independent Prognosticator in Muscle-Invasive Bladder Cancer.

Although the tumor-stroma ratio (TSR) has prognostic value in many cancers, the traditional semi-quantitative visual assessment method has inter-observer variability, making it impossible for clinical practice. We aimed to develop a machine learning (ML) algorithm for accurately quantifying TSR in hematoxylin-and-eosin (H&E)-stained whole slide images (WSI) and further investigate its prognostic effect in patients with muscle-invasive bladder cancer (MIBC). We used an optimal cell classifier previously built based on QuPath open-source software and ML algorithm for quantitative calculation of TSR. We retrospectively analyzed data from two independent cohorts to verify the prognostic significance of ML-based TSR in MIBC patients. WSIs from 133 MIBC patients were used as the discovery set to identify the optimal association of TSR with patient survival outcomes. Furthermore, we performed validation in an independent external cohort consisting of 261 MIBC patients. We demonstrated a significant prognostic association of ML-based TSR with survival outcomes in MIBC patients (p < 0.001 for all comparisons), with higher TSR associated with better prognosis. Uni- and multivariate Cox regression analyses showed that TSR was independently associated with overall survival (p < 0.001 for all analyses) after adjusting for clinicopathological factors including age, gender, and pathologic stage. TSR was found to be a strong prognostic factor that was not redundant with the existing staging system in different subgroup analyses (p < 0.05 for all analyses). Finally, the expression of six genes (DACH1, DEEND2A, NOTCH4, DTWD1, TAF6L, and MARCHF5) were significantly associated with TSR, revealing possible potential biological relevance. In conclusion, we developed an ML algorithm based on WSIs of MIBC patients to accurately quantify TSR and demonstrated its prognostic validity for MIBC patients in two independent cohorts. This objective quantitative method allows application in clinical practice while reducing the workload of pathologists. Thus, it might be of significant aid in promoting precise pathology services in MIBC.

Automatic Choroidal Segmentation in Optical Coherence Tomography Images Based on Curvelet Transform and Graph Theory.

Automatic segmentation of the choroid on optical coherence tomography (OCT) images helps ophthalmologists in diagnosing eye pathologies. Compared to manual segmentations, it is faster and is not affected by human errors. The presence of the large speckle noise in the OCT images limits the automatic segmentation and interpretation of them. To solve this problem, a new curvelet transform-based K-SVD method is proposed in this study. Furthermore, the dataset was manually segmented by a retinal ophthalmologist to draw a comparison with the proposed automatic segmentation technique. In this study, curvelet transform-based K-SVD dictionary learning and Lucy-Richardson algorithm were used to remove the speckle noise from OCT images. The Outer/Inner Choroidal Boundaries (O/ICB) were determined utilizing graph theory. The area between ICB and outer choroidal boundary was considered as the choroidal region. The proposed method was evaluated on our dataset and the average dice similarity coefficient (DSC) was calculated to be 92.14% ± 3.30% between automatic and manual segmented regions. Moreover, by applying the latest presented open-source algorithm by Mazzaferri et al. on our dataset, the mean DSC was calculated to be 55.75% ± 14.54%. A significant similarity was observed between automatic and manual segmentations. Automatic segmentation of the choroidal layer could be also utilized in large-scale quantitative studies of the choroid.

TRACK—a new algorithm and open-source tool for the analysis of pursuit-tracking sensorimotor integration processes

In daily life, sensorimotor integration processes are fundamental for many cognitive operations. The pursuit-tracking paradigm is an ecological and valid paradigm to examine sensorimotor integration processes in a more complex environment than many established tasks that assess simple motor responses. However, the analysis of pursuit-tracking performance is complicated, and parameters quantified to examine performance are sometimes ambiguous regarding their interpretation. We introduce an open-source algorithm (TRACK) to calculate a new tracking error metric, the spatial error, based on the identification of the intended target position for the respective cursor position. The identification is based on assigning cursor and target direction changes to each other as key events, based on the assumptions of similarity and proximity. By applying our algorithm to pursuit-tracking data, beyond replication of known effects such as learning or practice effects, we show a higher precision of the spatial tracking error, i.e., it fits our behavioral data better than the temporal tracking error and thus provides new insights and parameters for the investigation of pursuit-tracking behavior. Our work provides an important step towards fully utilizing the potential of pursuit-tracking tasks for research on sensorimotor integration processes.

Nine-axis inertial measurement unit output discriminates activities of varying intensity in the dog

To explore relationships between 9-axis inertial measurement unit (IMU) output and activities of varying intensity in dogs of various sizes. 20 healthy, agility course-trained dogs of various ages and sizes. Height, weight, body condition score, age, length from IMU to the ischium, and height of IMU to the floor were recorded. Dogs performed a series of activities (rest, walk, trot, and agility course) while wearing the IMU device. IMU and video output were reviewed by independent investigators. Correlations and multiple regression models were used to explore relationships between independent variables and IMU output. Calibration demonstrated excellent correlation and concordance between IMUs (intraclass correlation > 0.9) and that the IMUs reliably measured a known acceleration (gravity at rest). Resultant vector magnitude {sqrt[(x^2) + (y^2) + (z^2)]} normalized to body size was calculated from the data. IMU output clearly discriminates between activities of varying intensity in the dog. The inability to accurately measure chronic pain is a barrier to the development of new, or critical evaluation of, therapeutics. Activity monitors (AM) may be the ideal diagnostic target since they are small and provide objective data that can be collected while the pet remains in its natural environment. These results demonstrate the concurrent and predictive validity of the IMU tested. Our long-range goal is to validate an open-source algorithm for the IMU so activity in a pet's natural environment can be used as an outcome measure in future studies.

PhenoBot: an automated system for leaf area analysis using deep learning.

A low-cost dynamic image capturing and analysis pipeline using color-based deep learning segmentation was developed for direct leaf area estimation of multiple crop types in a commercial environment. Crop yield is largely driven by intercepted radiation of the leaf canopy, making the leaf area index (LAI) a critical parameter for estimating yields. The growth rate of leaves at different growth stages determines the overall LAI, which is used by crop growth models (CGM) for simulating yield. Consequently, precise phenotyping of the leaves can help elucidate phenological processes relating to resource capturing. A stable system for acquiring images and a strong data processing backend play a vital role in reducing throughput time and increasing accuracy of calculations, compared to manual analysis. However, most available solutions are not dynamic, as they use color-based segmentation, which fails to capture leaves with varying shades and shapes. We have developed a system that uses a low-cost setup to acquire images and an automated pipeline to manage the data storage on the device and in the cloud. The system is powered by virtual machines that run multiple custom-trained deep learning models to segment out leaves, calculate leaf area (LA) for the whole set and at the individual leaf level, overlays important information on the images, and appends them on a compatible file used for CGMs with very high accuracy. The pipeline is dynamic and can be used for multiple crops. The use of open-source hardware, platforms, and algorithms makes this system affordable and reproducible.

Does Wearable-Measured Heart Rate Variability During Sleep Predict Perceived Morning Mental and Physical Fitness?

The emergence of wearable sensor technology may provide opportunities for automated measurement of psychophysiological markers of mental and physical fitness, which can be used for personalized feedback. This study explores to what extent within-subject changes in resting heart rate variability (HRV) during sleep predict the perceived mental and physical fitness of military personnel on the subsequent morning. Participants wore a Garmin wrist-worn wearable and filled in a short morning questionnaire on their perceived mental and physical fitness during a period of up to 46 days. A custom-built smartphone app was used to directly retrieve heart rate and accelerometer data from the wearable, on which open-source algorithms for sleep detection and artefact filtering were applied. A sample of 571 complete observations in 63 participants were analyzed using linear mixed models. Resting HRV during sleep was a small predictor of perceived physical fitness (marginal R2 = .031), but not of mental fitness. The items on perceived mental and physical fitness were strongly correlated (r = .77). Based on the current findings, resting HRV during sleep appears to be more related to the physical component of perceived fitness than its mental component. Recommendations for future studies include improvements in the measurement of sleep and resting HRV, as well as further investigation of the potential impact of resting HRV as a buffer on stress-related outcomes.