Min Of Data Research Articles

Clinical usefulness of a novel fluorescence technique for the intraoperative diagnosis of surgical margins in patients with breast cancer.

In both 5- and 15-min data, FI was significantly higher in malignant tissues than in benign tissues. The diagnostic accuracy was similar at 5 and 15 min. Therefore, the 5-min FI was enough applying in the further analyses.

The Effect of Data Length on the Assessment of Dynamic Cerebral Autoregulation with Transfer Function Analysis in Neurological ICU Patients.

BackgroundCerebral autoregulation plays an important role in safeguarding adequate cerebral perfusion and reducing the risk of secondary brain injury, which is highly important for patients in the neurological intensive care unit (neuro-ICU). Although the consensus white paper suggests that a minimum of 5 min of data are needed for assessing dynamic cerebral autoregulation with transfer function analysis (TFA), it remains unknown if the length of these data is valid for patients in the neuro-ICU, of whom are notably different than the general populations. We aimed to investigate the effect of data length using transcranial Doppler ultrasound combined with invasive blood pressure measurement for the assessment of dynamic cerebral autoregulation in patients in the neuro-ICU.MethodsTwenty patients with various clinical conditions (severe acute encephalitis, ischemic stroke, subarachnoid hemorrhage, brain injury, cerebrovascular intervention operation, cerebral hemorrhage, intracranial space-occupying lesion, and toxic encephalopathy) were recruited for this study. Continuous invasive blood pressure, with a pressure catheter placed at the radial artery, and bilateral continuous cerebral blood flow velocity with transcranial Doppler ultrasound were simultaneously recorded for a length of 10 min for each patient. TFA was applied to derive phase shift, gain, and coherence function at all frequency bands from the first 2, 3, 4, 5, 6, 7, 8, 9, and 10 min of the 10-min recordings in each patient on both hemispheres. The variability in the autoregulatory parameters in each hemisphere was investigated by repeated measures analysis of variance.ResultsForty-one recordings (82 hemispheres) were included in the study. According to the critical values of coherence provided by the Cerebral Autoregulation Research Network white paper, acceptable rates for the data were 100% with a length ≥ 7 min. The final analysis included 68 hemispheres. The effects of data length on trends in phase shift in the very low frequency (VLF) band (F1.801,120.669 = 6.321, P = 0.003), in the LF band (F1.274,85.343 = 4.290, P = 0.032), and in the HF band (F1.391,93.189 = 3.868, P = 0.039) were significant for 3–7 min, for 4–7 min, and for 5–8 min, respectively. Effects were also significant on the gain in the VLF band (F1.927,129.134 = 3.215, P = 0.045) for 2–8 min and on the coherence function in all frequency bands (VLF F2.846,190.671 = 90.247, P < 0.001, LF F2.515,168.492 = 55.770, P < 0.001, HF F2.411, 161.542 = 33.833, P < 0.001) for 2–10 min.ConclusionsConsidering the acceptable rates for the data and the variation in the TFA variables (phase shift and gain), we recommend recording data for a minimum length of 7 min for TFA in patients in the neuro-ICU.

Investigating event-based temporal patterns of design rainfall in a tropical region

ABSTRACT This study investigated the temporal rainfall pattern in order to facilitate rainfall design, which normally requires a good understanding of the temporal patterns of rainstorm events. The analysis employed a storm-event-based approach using the concept of inter-event time definition (IETD) and rainfall depth/duration/intensity thresholds. The 5-min rainfall data at three raingauge stations were analysed to determine representative quartiles of a design storm in a tropical city. The temporal characteristics of the design storm could be determined from the rainfall depth ratios of consecutive peak rainfalls for each interval of storm duration, and time to the first peak rainfall depending on each quartile’s rainstorm events. The determination of the quantile distribution of tropical rainfall could help improve the representativeness of design rainfall and facilitate rainfall–runoff modelling for urban flood control in a tropical region.

The effect of principal component analysis in the diagnosis of congestive heart failure via heart rate variability analysis.

In this study, we investigated the effect of principal component analysis (PCA) in congestive heart failure (CHF) diagnosis using various machine learning algorithms from 5-min HRV data. The extracted 59 heart rate variability (HRV) features consist of statistical time-domain measures, frequency-domain measures (power spectral density estimations from Fourier transform and Lomb-Scargle methods), time-frequency HRV measures (Wavelet transform), and nonlinear HRV measures (Poincare plot, symbolic dynamics, detrended fluctuation analysis, and sample entropy). All these HRV features are the classifiers' inputs. We repeated the study ten times using the first one to the first 10 principal components from PCA instead of all HRV features. Nine different classifiers, namely logistic regression, Naive Bayes, k-nearest neighbors, decision tree, AdaBoost, support vector machines, stochastic gradient descent, random forest, and artificial neuronal network (multilayer perceptron) are examined. The proposed study results in the 100% accuracy, 100% specificity, and 100% sensitivity after utilizing PCA (with the first eight principal components) using the Random Forest classifier where the maximum classifier performances are the 86% accuracy, 79% specificity, and 86% sensitivity before PCA. In conclusion, PCA is beneficial in the diagnosis of patients with CHF. In addition, we experienced the online Python-based visual machine learning tool, Orange, which can implement well-known machine learning algorithms.

An exploratory data quality analysis of time series physiologic signals using a large-scale intensive care unit database.

Physiological data, such as heart rate and blood pressure, are critical to clinical decision-making in the intensive care unit (ICU). Vital signs data, which are available from electronic health records, can be used to diagnose and predict important clinical outcomes; While there have been some reports on the data quality of nurse-verified vital sign data, little has been reported on the data quality of higher frequency time-series vital signs acquired in ICUs, that would enable such predictive modeling. In this study, we assessed the data quality issues, defined as the completeness, accuracy, and timeliness, of minute-by-minute time series vital signs data within the MIMIC-III data set, captured from 16009 patient-ICU stays and corresponding to 9410 unique adult patients. We measured data quality of four time-series vital signs data streams in the MIMIC-III data set: heart rate (HR), respiratory rate (RR), blood oxygen saturation (SpO2), and arterial blood pressure (ABP). Approximately, 30% of patient-ICU stays did not have at least 1 min of data during the time-frame of the ICU stay for HR, RR, and SpO2. The percentage of patient-ICU stays that did not have at least 1 min of ABP data was ∼56%. We observed ∼80% coverage of the total duration of the ICU stay for HR, RR, and SpO2. Finally, only 12.5%%, 9.9%, 7.5%, and 4.4% of ICU lengths of stay had ≥ 99% data available for HR, RR, SpO2, and ABP, respectively, that would meet the three data quality requirements we looked into in this study. Our findings on data completeness, accuracy, and timeliness have important implications for data scientists and informatics researchers who use time series vital signs data to develop predictive models of ICU outcomes.

Use of the Polar V800 and Actiheart 5 heart rate monitors for the assessment of heart rate variability (HRV) in horses

Heart rate variability (HRV) is a commonly used metric in animal science to quantify an aspect of the physiological response to stressors. HRV analysis relies upon accurate detection of the electrical activity of the heart to define inter-beat interval (IBI). In horses, this can be problematic due to specific features of the equine ECG waveform and a high incidence of 2nd-degree atrioventricular (AV) block in clinically normal horses at rest.The current study validates the collection and interpretation of IBI data from two heart rate monitors (HRMs) principally designed for human personal monitoring (Polar V800 and Actiheart 5). 30 min of synchronous IBI data was collected using the two HRMs and a 4-lead telemetric ECG that is widely used in equine veterinary clinical practice (Televet 100). The study was conducted using a mixed sample (n = 17) of general riding horses, with (n = 4) and without (n = 13) cardiac dysrhythmias. HRV data was derived from each IBI data set and compared following application of a series of correction factors.There was a very strong inter-class correlation of HRV parameters from both the Actiheart 5 and Polar V800 with the Televet 100 data. Both HRMs providing an acceptable level of agreement with both time and frequency domain HRV parameters. The data from the Actiheart 5 were found to be interchangeable with the Televet 100 in respect of beat detection whereas the Polar V800 data required a 0.4 s artefact correction to give best agreement. Both HRMs have utility in equine research for demonstrating the direction and magnitude of change in HRV parameters, although users must apply appropriate artefact correction to maximise data validity.

Validation of a nasal SedLine® sensor placement: Going beyond the forehead when depth of anesthesia is important

IntroductionSince the inception of general anesthesia, the assessment of anesthetic depth has been challenging and a goal that anesthesiologists constantly strive for. Nowadays, an increasing number of monitors allow us to have a more specific assessment of depth of anesthesia. However, the conventional sensor-lead positioning on the forehead recommended by manufacturers may sometimes coincide with the surgical field thereby posing a clinical challenge. This study compares the conventional frontal placement on the forehead with an experimental nasal placement for the standard Masimo SedLine® EEG sensor in surgical neuromonitoring, analyzing and comparing numeric values (Patient State Index-PSi) and EEG waveform traces. MethodsAuthors performed a single-center, observational, prospective study enrolling 40 patients under a standardized anesthesia protocol. Three contiguous time periods (induction, steady-state anesthesia and awakening) were used to stratify data analysis so that within-patient correlations between nasal and frontal readings could be examined by time period independently. ResultsA total of 106,209 matched numeric values and 3,543 min of EEG data from each sensor’s positions were collected from 40 patients. Total average alignment between two sensor positions, keeping in mind that 5 PSi units were used as acceptable limit of agreement, was 83.01% and p-values associated with R2 correlation coefficients were statistically significant at 0.001 level. Steady-state anesthesia phase alignment (with full muscle-relaxation), which present 73% of all collected data, show a concordance within 5 PSi unit alignment in 95.77%. One hundred and twenty tracings from 40 patients were presented to two epileptologists and inter-rater agreement or reliability was achieved in 88% of EEG-traces’ analysis. ConclusionsThe current results suggest that SedLine® Brain Function Monitoring sensor is acceptable for clinical use when standard sensor position in the forehead is not possible. This allows for the possibility of utilization of the sensor whenever the forehead placement cannot be utilized.

Market instability and technical trading at high frequency: Evidence from NASDAQ stocks

The promotion of financial stability is the mission of central banks and market authorities. This mission is more difficult to accomplish when trading activity is associated with financial instability in the form of intraday price jumps. While the literature has widely shown that exogenous news releases trigger these jumps, very little is known about the consequences of endogenous technical trading on market instability. Using high-frequency 5-min data on 460 NASDAQ stocks from February to September 2017, we provide new evidence that sharp price movements during the day are also triggered by technical trading around special market configurations. When technical trading activity dominates, intraday price jumps are detected more frequently, and their direction becomes significantly predictable, particularly in small caps and in the energy sector. Our results support the view that the explanations for intraday market instability are not limited to news releases.

An openly available wearable, a diaper cover, monitors infant's respiration and position during rest and sleep.

To describe and test the accuracy of respiratory rate assessment in long-term surveillance using an open-source infant wearable, NAPping PAnts (NAPPA). We recorded 24 infants aged 1-9months using our newly developed infant wearable that is a diaper cover with an integrated programmable electronics with accelerometer and gyroscope sensors. The sensor collects child's respiration rate (RR), activity and body posture in 30-s epochs, to be downloaded afterwards into a mobile phone application. An automated RR quality measure was also implemented using autocorrelation function, and the accuracy of RR estimate was compared with a reference obtained from the simultaneously recorded capnography signal that was part of polysomnography recordings. Altogether 88h 27min of data were recorded, and 4147 epochs (39% of all data) were accepted after quality detection. The median of patient wise mean absolute errors in RR estimates was 1.5 breaths per minute (interquartile range 1.1-2.6bpm), and the Blandt-Altman analysis indicated an RR bias of 0.0bpm with the 95% limits of agreement of -5.7-5.7bpm. Long-term monitoring of RR and posture can be done with reasonable accuracy in out-of-hospital settings using NAPPA, an openly available infant wearable.

A multi-analysis approach for estimating regional health impacts from the 2017 Northern California wildfires

ABSTRACT Smoke impacts from large wildfires are mounting, and the projection is for more such events in the future as the one experienced October 2017 in Northern California, and subsequently in 2018 and 2020. Further, the evidence is growing about the health impacts from these events which are also difficult to simulate. Therefore, we simulated air quality conditions using a suite of remotely-sensed data, surface observational data, chemical transport modeling with WRF-CMAQ, one data fusion, and three machine learning methods to arrive at datasets useful to air quality and health impact analyses. To demonstrate these analyses, we estimated the health impacts from smoke impacts during wildfires in October 8–20, 2017, in Northern California, when over 7 million people were exposed to Unhealthy to Very Unhealthy air quality conditions. We investigated using the 5-min available GOES-16 fire detection data to simulate timing of fire activity to allocate emissions hourly for the WRF-CMAQ system. Interestingly, this approach did not necessarily improve overall results, however it was key to simulating the initial 12-hr explosive fire activity and smoke impacts. To improve these results, we applied one data fusion and three machine learning algorithms. We also had a unique opportunity to evaluate results with temporary monitors deployed specifically for wildfires, and performance was markedly different. For example, at the permanent monitoring locations, the WRF-CMAQ simulations had a Pearson correlation of 0.65, and the data fusion approach improved this (Pearson correlation = 0.95), while at the temporary monitor locations across all cases, the best Pearson correlation was 0.5. Overall, WRF-CMAQ simulations were biased high and the geostatistical methods were biased low. Finally, we applied the optimized PM2.5 exposure estimate in an exposure-response function. Estimated mortality attributable to PM2.5 exposure during the smoke episode was 83 (95% CI: 0, 196) with 47% attributable to wildland fire smoke. Implications: Large wildfires in the United States and in particular California are becoming increasingly common. Associated with these large wildfires are air quality and health impact to millions of people from the smoke. We simulated air quality conditions using a suite of remotely-sensed data, surface observational data, chemical transport modeling, one data fusion, and three machine learning methods to arrive at datasets useful to air quality and health impact analyses from the October 2017 Northern California wildfires. Temporary monitors deployed for the wildfires provided an important model evaluation dataset. Total estimated regional mortality attributable to PM2.5 exposure during the smoke episode was 83 (95% confidence interval: 0, 196) with 47% of these deaths attributable to the wildland fire smoke. This illustrates the profound effect that even a 12-day exposure to wildland fire smoke can have on human health.

Feedback as a balancing act: Qualitative insights from an experienced multi-cultural sample of doctoral supervisors in nursing

AimTo better understand the views and experiences of experienced doctoral supervisors in nursing when providing feedback and critique to nursing doctoral students. Background: Feedback refers to information from a provider, intended to inform a receiver about the quality of their work in order for them to be able to see where improvements might occur and to signpost issues to be carried into future work. Feedback, particularly on student writing is central to successful doctoral supervision and is time consuming and labour-intensive for supervisors. Design: Qualitative. Methods: Following ethics approval and informed consent procedures, we gathered 962 min of interview data over a six-week period from 21 participants in four countries. During conversational-style interviews, participants shared their experiences of supervisionand elucidated on their experiences of providing feedback to doctoral students. Data were thematically analysed. Findings: Participants had more than 400 combined doctoral completions. As supervisors, participants aimed to strike a balance between helpful and empowering comments that motivated students to approach their work with renewed vigour and enthusiasm; and those that had the opposite effect of crushing and demoralising the student. ‘Feedback as a balancing act’ comprised four contributing themes with sub-themes. Findings reveal that feedback on student writing can remain a challenge for the duration of candidature. However, writing is an essential aspect of doctoral studies. It is through supervision that new nursing scholars are tutored and coached into the practices essential to creating disciplinary knowledge through writing. Our sample was drawn from multiple countries and included perspectives from various cultures. Despite the variation in countries and cultures, there was little variation in issues around feedback with all participants striving to provide clear, respectful feedback aimed at developing students and enhancing their skills. Conclusions: Supervision of doctoral student frequently involves working internationally and what while our sample was drawn from multiple countries and cultural perspectives, there was little variation in issues around provision of feedback to doctoral students. When considering feedback, our findings emphasise the importance of recognising feedback as a crucial educative process and one that is central to the production of a doctoral thesis. We argue that there is a need for nursing to move to developing and articulating meaningful and inclusive pedagogies of writing and doctoral supervision. We recommend universities support the development of such pedagogies and ensure that academic staff engaging in supervision are supported with the appropriate knowledge and skills to be optimally effective.

Head-to-head comparison of (R)-[11C]verapamil and [18F]MC225 in non-human primates, tracers for measuring P-glycoprotein function

PurposeP-glycoprotein (P-gp) function is altered in several brain disorders; thus, it is of interest to monitor the P-gp function in vivo using PET. (R)-[11C]verapamil is considered the gold standard tracer to measure the P-gp function; however, it presents some drawbacks that limit its use. New P-gp tracers have been developed with improved properties, such as [18F]MC225. This study compares the characteristics of (R)-[11C]verapamil and [18F]MC225 in the same subjects.MethodsThree non-human primates underwent 4 PET scans: 2 with (R)-[11C]verapamil and 2 with [18F]MC225, at baseline and after P-gp inhibition. The 30-min PET data were analyzed using 1-Tissue Compartment Model (1-TCM) and metabolite-corrected plasma as input function. Tracer kinetic parameters at baseline and after inhibition were compared. Regional differences and simplified methods to quantify the P-gp function were also assessed.ResultsAt baseline, [18F]MC225 VT values were higher, and k2 values were lower than those of (R)-[11C]verapamil, whereas K1 values were not significantly different. After inhibition, VT values of the 2 tracers were similar; however, (R)-[11C]verapamil K1 and k2 values were higher than those of [18F]MC225. Significant regional differences between tracers were found at baseline, which disappeared after inhibition. The positive slope of the SUV-TAC was positively correlated to the K1 and VT of both tracers.Conclusion[18F]MC225 and (R)-[11C]verapamil show comparable sensitivity to measure the P-gp function in non-human primates. Moreover, this study highlights the 30-min VT as the best parameter to measure decreases in the P-gp function with both tracers. [18F]MC225 may become the first radiofluorinated tracer able to measure decreases and increases in the P-gp function due to its higher baseline VT.

Scalable low-rank tensor learning for spatiotemporal traffic data imputation

Missing value problem in spatiotemporal traffic data has long been a challenging topic, in particular for large-scale and high-dimensional data with complex missing mechanisms and diverse degrees of missingness. Recent studies based on tensor nuclear norm have demonstrated the superiority of tensor learning in imputation tasks by effectively characterizing the complex correlations/dependencies in spatiotemporal data. However, despite the promising results, these approaches do not scale well to large data tensors. In this paper, we focus on addressing the missing data imputation problem for large-scale spatiotemporal traffic data. To achieve both high accuracy and efficiency, we develop a scalable tensor learning model—Low-Tubal-Rank Smoothing Tensor Completion (LSTC-Tubal)—based on the existing framework of Low-Rank Tensor Completion, which is well-suited for spatiotemporal traffic data that is characterized by multidimensional structure of location × time of day × day. In particular, the proposed LSTC-Tubal model involves a scalable tensor nuclear norm minimization scheme by integrating linear unitary transformation. Therefore, tensor nuclear norm minimization can be solved by singular value thresholding on the transformed matrix of each day while the day-to-day correlation can be effectively preserved by the unitary transform matrix. Before setting up the experiment, we consider some real-world data sets, including two large-scale 5-min traffic speed data sets collected by the California PeMS system with 11160 sensors: 1) PeMS-4W covers the data over 4 weeks (i.e., 288×28 time points), and 2) PeMS-8W covers the data over 8 weeks (i.e., 288×56 time points). We compare LSTC-Tubal with some state-of-the-art baseline models, and find that LSTC-Tubal can achieve competitively accuracy with a significantly lower computational cost. In addition, the LSTC-Tubal will also benefit other tasks in modeling large-scale spatiotemporal traffic data, such as network-level traffic forecasting.

Assessing one-minute diffuse fraction models based on worldwide climate features

Despite the variety of irradiance separation models available in the literature, there is not yet a model that performs equally well for every location worldwide. Nevertheless, separation models still represent an interesting approach when only global irradiance is measured. This work presents further developments of the recently proposed Boland-Ridley-Lauret minute model and proposes 1-min diffuse fraction models for each climate zone in the globe. To accomplish this, 1-min worldwide irradiance data from 51 the Baseline Surface Rresearch Network stations and one from Australian Bureau of Meteorology were used. The Köppen-Geiger classification was used to determine the climate zone of each station: both the simple climate classification (A, B, C, D, E) and the complete classification (Aw, Bsh, etc.). Furthermore, a robust nonlinear regression method was used to build the separation models without removing measurement outliers in advance. The climate-specific models proposed herein present better performance than other models from the literature, such as the BRL, Perez and Skartveit models (developed using hourly irradiance data) and the Engerer model (developed using minute data). Generally, the models proposed for climate zones in the complete Köppen classification presented better similitude with the measured data than the models for the simple classification, especially for stations within climate zones B and E.

Analysis of Rainfall Erosivity Trends 1980–2018 in a Complex Terrain Region (Abruzzo, Central Italy) from Rain Gauges and Gridded Datasets

The erosive capacity of precipitation depends on its intensity, volume, and duration. The rainfall erosivity factor (R) of the Universal Soil Loss Equation (USLE) requires high frequency (subhourly) data. When these are not available, R can be estimated from simplified indices such as the Modified Fournier Index (MFI), the Precipitation Concentration Index (PCI), and the Seasonality Index (SI), which are computed from monthly precipitation. We calculated these indices for 34 stations in the complex terrain Abruzzo region (central Italy) during 1980–2018, based on both gauge (point) and grid datasets. Using 30-min rainfall data of 14 stations, we verified that MFI and PCI are reliable predictors of R (R2 = 0.91, RMSE = 163.6 MJ mm ha−1 h−1 year−1). For MFI, grid data do not capture the peaks in high-altitude stations and the low values in some inland areas, detected by the point dataset. Grid data show significant MFI positive trends in 74% of the stations, while the point data display significant positive trends in only 26% of stations and significant negative trends in four stations in the inland areas. The grid data complex orography requires preliminary validation work.

Rain fade margin of terrestrial line-of-sight (LOS) links for 5G networks in Peninsular Malaysia

AbstractAdvanced telecommunication systems are moving toward a high data transfer rate and wider bandwidth. The 5G communication network has recently been implemented for such aims. However, 5G networks operating with high operating frequency (typically above 20 GHz) could lead to impairments because of the atmospheric phenomena mainly precipitation and especially heavy rain. To address this, an optimum rain fade margin for the 5G network in Peninsular Malaysia is proposed using 77 sites of the rain-gauge network, which convert 1-h rain data to 1-min rain data by means of the international telecommunication union recommendation (ITU-R) P.837-7 model. Long-term rain attenuation statistics are obtained from ITU-R P.530-17 and the synthetic storm technique. The predicted rain attenuation is also presented in monthly statistics and in rain attenuation contour maps. The analysis showed that at 99.99% of link availability, the optimum rain fade margin operating at 26 GHz link should be in the range of 6.50 to 10 dB and 7 to 11 dB at 28 GHz link for a 5G network. Such information is useful for network operators and system engineers for the operation of 5G terrestrial microwave links in heavy rain regions.

The 3D Neural Network for Improving Radar-Rainfall Estimation in Monsoon Climate

The reflectivity (Z)—rain rate (R) model has not been tested on single polarization radar for estimating monsoon rainfall in Southeast Asia, despite its widespread use for estimating heterogeneous rainfall. The artificial neural network (ANN) regression has been applied to the radar reflectivity data to estimate monsoon rainfall using parametric Z-R models. The 10-min reflectivity data recorded in Kota Bahru radar station (in Malaysia) and hourly rain record in nearby 58 gauge stations during 2013–2015 were used. The three-dimensional nearest neighbor interpolation with altitude correction was applied for pixel matching. The non-linear Levenberg Marquardt (LM) regression, integrated with ANN regression minimized the spatiotemporal variability of the proposed Z-R model. Results showed an improvement in the statistical indicator, when LM and ANN overestimated (6.6%) and underestimated (4.4%), respectively, the mean total rainfall. For all rainfall categories, the ANN model has a positive efficiency ratio of &gt;0.2.

Hybrid kinematic–visual sensing approach for activity recognition of construction equipment

Activity recognition of construction equipment is vital for operational productivity and safety analysis. For automated equipment monitoring, many researchers have developed kinematic or visual sensing approaches and found that the two approaches have their own technical advantages and disadvantages in classifying different types of equipment activities. However, since previous methods adopted only one of kinematic or visual sensing, there is a limitation to fully benefit from both approaches, causing difficulty in monitoring construction equipment precisely. Additionally, despite the great potential of data fusion, the hybrid effects of kinematic–visual sensing are still unclear. To fill such knowledge gaps, this study developed a hybrid kinematic–visual sensing approach and investigated its impacts on the recognition of equipment activities. Specifically, a smartphone was installed inside the equipment's cabin, and kinematic and visual data were collected from its built-in sensors, gyroscopes, accelerometers, and cameras. Total 60-min data were collected, and the data were further split into training (40-min) and testing data (20-min). The data were then used to experiment three different models: kinematic, visual, and hybrid models. In the experiments, the average F-score of the hybrid model was 77.4%, whereas those of kinematic and visual models were 61.7% and 72.4%, respectively. These results indicated that the hybrid sensing could improve the recognition performance and monitor construction equipment better than relying only on sole type of data sources. The findings can contribute to more reliable activity recognition and operation analysis of construction equipment, and provide meaningful insights for future research.

Individual-Specific Areal-Level Parcellations Improve Functional Connectivity Prediction of Behavior.

Resting-state functional magnetic resonance imaging (rs-fMRI) allows estimation of individual-specific cortical parcellations. We have previously developed a multi-session hierarchical Bayesian model (MS-HBM) for estimating high-quality individual-specific network-level parcellations. Here, we extend the model to estimate individual-specific areal-level parcellations. While network-level parcellations comprise spatially distributed networks spanning the cortex, the consensus is that areal-level parcels should be spatially localized, that is, should not span multiple lobes. There is disagreement about whether areal-level parcels should be strictly contiguous or comprise multiple noncontiguous components; therefore, we considered three areal-level MS-HBM variants spanning these range of possibilities. Individual-specific MS-HBM parcellations estimated using 10min of data generalized better than other approaches using 150min of data to out-of-sample rs-fMRI and task-fMRI from the same individuals. Resting-state functional connectivity derived from MS-HBM parcellations also achieved the best behavioral prediction performance. Among the three MS-HBM variants, the strictly contiguous MS-HBM exhibited the best resting-state homogeneity and most uniform within-parcel task activation. In terms of behavioral prediction, the gradient-infused MS-HBM was numerically the best, but differences among MS-HBM variants were not statistically significant. Overall, these results suggest that areal-level MS-HBMs can capture behaviorally meaningful individual-specific parcellation features beyond group-level parcellations. Multi-resolution trained models and parcellations are publicly available (https://github.com/ThomasYeoLab/CBIG/tree/master/stable_projects/brain_parcellation/Kong2022_ArealMSHBM).

Effects of skin-to-skin care on electrical activity of the diaphragm in preterm infants during neurally adjusted ventilatory assist

BackgroundSkin-to-skin care (SSC) reduces neonatal mortality and morbidity and is widely implemented in the neonatal intensive care unit. However, changes in respiratory effort during SSC in ventilated preterm infants remain unclear. AimsTo evaluate the effect of SSC on electrical activity of the diaphragm (Edi) and vital signs in premature infants who are intubated and under neurally adjusted ventilatory assist ventilation. Study designWe performed an observational cross-over study. Data were measured in three periods: before (pre-SSC period), during (SSC period), and after (post-SSC period) SSC. Stable 30-min data in each period were extracted. SubjectsThirty-four SSC procedures were performed in 14 preterm infants with a median gestational age of 25.3 weeks (interquartile range, 24, 26.4) and a birth weight of 659 g (566, 694). The median postnatal age was 41 days (31, 53) at the study with a median postmenstrual age of 31.3 weeks (30.4, 32.5). Outcome measuresMedian values of Edi peak, Edi minimum, respiratory rate, SpO2, and heart rate were measured in each condition. The Kruskal–Wallis test with Bonferroni multiple comparisons was used to compare each parameter in each period. ResultsMedian Edi peak and Edi minimum values were significantly lower during SSC compared with pre- and post-SSC, without any change in respiratory rate, SpO2, or heart rate. ConclusionsRespiratory efforts as evaluated by Edi are significantly reduced during SSC in ventilated preterm infants.