Search

Abstract Background Accurate segmentation of critical anatomical structures in fetal four-chamber view images is essential for the early detection of congenital heart defects. Current prenatal screening methods rely on manual measurements, which are time-consuming and prone to inter-observer variability. This study develops an AI-based model using the state-of-the-art nnU-NetV2 architecture for automatic segmentation and measurement of key anatomical structures in fetal four-chamber view images. Methods A dataset, consisting of 1,083 high-quality fetal four-chamber view images, was annotated with 15 critical anatomical labels and divided into training/validation (867 images) and test (216 images) sets. An AI-based model using the nnU-NetV2 architecture was trained on the annotated images and evaluated using the mean Dice coefficient (mDice) and mean intersection over union (mIoU) metrics. The model’s performance in automatically computing the cardiac axis (CAx) and cardiothoracic ratio (CTR) was compared with measurements from sonographers with varying levels of experience. Results The AI-based model achieved a mDice coefficient of 87.11% and an mIoU of 77.68% for the segmentation of critical anatomical structures. The model’s automated CAx and CTR measurements showed strong agreement with those of experienced sonographers, with respective intraclass correlation coefficients (ICCs) of 0.83 and 0.81. Bland–Altman analysis further confirmed the high agreement between the model and experienced sonographers. Conclusion We developed an AI-based model using the nnU-NetV2 architecture for accurate segmentation and automated measurement of critical anatomical structures in fetal four-chamber view images. Our model demonstrated high segmentation accuracy and strong agreement with experienced sonographers in computing clinically relevant parameters. This approach has the potential to improve the efficiency and reliability of prenatal cardiac screening, ultimately contributing to the early detection of congenital heart defects.

To investigate highway vehicle lane-changing behavior, we utilized the publicly available naturalistic driving dataset, HighD, to extract the movement data of vehicles involved in lane changes and their proximate counterparts. We employed univariate and multivariate Cox proportional hazards models alongside random survival forest models to analyze the influence of various factors on lane change duration, assess their statistical significance, and compare the performance of multiple random survival forest models. Our findings indicate that several variables significantly impact lane change duration, including the standard deviation of lane-changing vehicles, lane-changing vehicle speed, distance to the following vehicle in the target lane, lane-changing vehicle length, and distance to the following vehicle in the current lane. Notably, the standard deviation and vehicle length act as protective factors, with increases in these variables correlating with longer lane change durations. Conversely, higher lane-changing vehicle speeds and shorter distances to following vehicles in both the current and target lanes are associated with shorter lane change durations, indicating their role as risk factors. Feature variable selection did not substantially improve the training performance of the random survival forest model based on our findings. However, validation set evaluation showed that careful feature variable selection can enhance model accuracy, leading to improved AUC values. These insights lay the groundwork for advancing research in predicting lane-changing behaviors, understanding lane-changing intentions, and developing pre-emptive safety measures against hazardous lane changes.

Non-coding RNAs (ncRNAs) play essential regulatory functions in various physiological and pathological processes in the brain. To systematically characterize the ncRNA profile in cortical cells, we downloaded single-cell SMART-Seq v4 data of mouse cerebral cortex. Our results revealed that the ncRNAs alone are sufficient to define the identity of most cortical cell types. We identified 1,600 ncRNAs that exhibited cell type specificity, even yielding to distinguish microglia from perivascular macrophages with ncRNA. Moreover, we characterized cortical layer and region specific ncRNAs, in line with the results by spatial transcriptome (ST) data. By constructing a co-expression network of ncRNAs and protein-coding genes, we predicted the function of ncRNAs. By integrating with genome-wide association studies data, we established associations between cell type-specific ncRNAs and traits related to neurological disorders. Collectively, our study identified differentially expressed ncRNAs at multiple levels and provided the valuable resource to explore the functions and dysfunctions of ncRNAs in cortical cells.

Purpose To introduce the cranial-dorsal-hip angle (∠CDH) as a novel quantitative tool for assessing fetal position in the first trimester and to validate its feasibility for future AI applications.

The entrances of tunnels are generally considered to be accident-prone locations, and accidents related to this area mainly include rear-end and sideswipe crashes, which are also associated with lane-changing behaviours. Despite the extensive literature on the safety of lane-changing, little attention has been given to lane-changing behaviours in front of the tunnel entrance. To this end, this study investigates the contributing factors to the potential risk status of lane-changing, taking into account lane-changing scenarios and the distance to tunnel entrances. Vehicular trajectory data on adjacent sections of tunnel entrances was collected by naturalistic driving tests, and 615 lane-changing scenarios were extracted for analysis. Furthermore, lane-changing risk margin (LCRM) is proposed to estimate whether there is at potential risk during lane-changing. To verify the influence of risk factors on the safety of lane-changing on adjacent sections of tunnel entrances, a mixed logit model is established for different lane-changing scenarios and distance levels to tunnel entrances. The model estimation results indicate that the leading vehicles in the current lane and target lane (defined as CLV and TLV, respectively) significantly affect the risk of lane-changing, with the presence of CLV increasing the probability of performing risky lane-changing as approaching the tunnel entrance, while the presence of TLV instead reduces the probability of performing risky lane-changing behaviour. The distance to the tunnel entrance also has a significant impact on the risk of lane-changing, and the probability of the risk of lane-changing is higher at relatively close distances than at relatively long distances. Moreover, on adjacent sections of tunnel entrances, drivers mainly change lanes to the left, which is likely to be related to safer driving on the left. This implies that drivers approaching the tunnel may try to achieve better driving conditions before entering the tunnel by changing lanes in view of the complex driving conditions inside the tunnel.

Fetal heart rate (FHR) is an essential indicator of fetal well-being. The ultrasonic Doppler FHR detector is widely used to monitor the fetus’s health due to its advantages of non-invasion, high sensitivity, and good directivity. However, the existing commercial Doppler FHR detector primarily uses an analog multiplier for demodulation, which has limited functions and insufficient sensitivity. The analog demodulation is performed only on a single-sideband signal(in-phase or quadrature) (IQ), which is impossible to derive the fetal heart movement’s vector velocity. Moreover, repetitive recognition of the mitral valve’s positive and negative motion easily causes the measured FHR twice the actual one (FHR doubling). Although the traditional digital demodulation FHR detector can obtain in-phase and quadrature demodulation signals, it needs a high-level field-programmable gate array chip and therefore cannot meet low-power consumption requirements in battery-powered situations. Herein we proposed a novel digital demodulation FHR algorithm using time-domain windowing. Then, we applied the algorithm into a low-power complex programmable logic device to achieve low-cost acquisition of vector velocity and suppress FHR doubling and finally designed a hand-held, noninvasive digital Doppler FHR detection system for continuous perinatal detection. In this work, the comparison curve between the TREND curve generated by the simulator and the measured curve of our FHR detector was obtained. The comparative experiment between the commercial FM-3A FHR detector and our proposed FHR detector was performed, and the relative error and standard error of the obtained FHR data were used to evaluate the two FHR detectors’ detection accuracy. The results showed that our FHR detector showed excellent detection accuracy at an accuracy rate of 98%, which was much higher than the average accuracy of the FM-3A FHR detector and indicated our proposed digital FHR detector showed excellent detection performance. It means that the proposed digital windowed FHR demodulation algorithm is practical, the multi-FHR monitoring system is feasible, and our proposed FHR detector has high detection accuracy, effectively suppresses FHR doubling, and meets the requirements of Chinese national standards. It provides an alternative scheme towards the low-cost hand-held digital demodulation FHR detection application.

The assessment of liver fibrosis is usually required in the diagnostic and treatment procedures for chronic liver disease. In this paper, we propose a deep convolutional neural network (DCNN) with multi-feature fusion (DCNN-MFF) to extract and integrate features from ultrasound (US) B-mode image and Nakagami parametric map for significant liver fibrosis recognition. The DCNN-MFF model mainly consists of three branches, among which the first two branches are used for extracting deep features respectively from the US B-mode image and the Nakagami parametric map, while the remaining branch is designed for extracting quantitative US features from the Nakagami parametric map. At the backend of the DCNN model, the extracted deep and quantitative features are fused together for final decision making. The performance of the DCNN-MFF model was evaluated on an animal dataset collected from 84 rats with 168 liver lobes under various fibrosis stages. Across five-fold cross-validation, the accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) achieved by the proposed DCNN-MFF model for significant liver fibrosis recognition were respectively 0.827 (95% confidence interval [CI] 0.762–0.881), 0.821 (95% CI 0.729–0.892), 0.836 (95% CI 0.731–0.912), 0.869 (95% CI 0.809–0.916), which are significantly better than those provided by the comparative methods.

Vehicle rear-end collisions are primarily caused by tight car following in a continuous traffic flow, as well as a driver’s incorrect perception of the traffic environment ahead and delayed response. To facilitate an investigation pertaining to rear-end collision mechanisms and accurately measure the risk, the concept of a vehicle group is introduced herein. A risk measurement model for a vehicle group (RMVG) based on temporal and spatial similarities is proposed. First, vehicles are categorized based on their temporal and spatial similarities. Risk measurement metrics are defined based on the traffic composition, movement state, and conflict extent. Subsequently, vehicle group risk identification and risk measurement models based on an isolation forest are established. the rear-end collision risk of the vehicle groups is analyzed both qualitatively and quantitatively. Finally, the RMVG is tested using the vehicle trajectory data set of Longpan South Road, Nanjing City, Jiangsu Province, China, and the results are compared with those of a support vector machine and local outlier factor. The results show that the accuracy of the RMVG is higher than those of other models: its accuracy rate and specificity are 95.68% and 88.89%, respectively, whereas its false alarm rate is only 3.47%.

In this paper, we report a two-layer five-port diffraction grating by a polarization-independent design under normal incidence. To be different from conventional five-port gratings, initially, we design a novel two-layer grating with operation in transmission. Next, we firstly design a polarization-independent grating with five-port splitting output. On the one hand, the accurate grating vector parameters are optimized using rigorous coupled-wave analysis (RCWA) approach. On the other hand, the inherent coupling mechanism happened in the grating region can be well explained by employing simplified modal method (SMM). More importantly, all reported conventional five-port beam splitter gratings were designed based on polarization dependent. Although they could obtain high diffraction efficiency for TE or TM polarization, it requires more complicated and time-consuming fabrication processes in practical grating applications. Thus, this work can open up a possible thought for designing polarization-independent multi-port beam splitter diffraction gratings.

Emergency rescue plays a key role in accident remediation and prevention. It has been the most critical factor to control the negative impacts of accident deterioration, which can save more lives and reduce property loss in time. As an essential component, emergency rescue path planning can effectively shorten the travelling time and improve the robustness of the rescue path. However, there still exist various uncertainties that may make a great impact on selecting the rescue path, which is less successful and still requires further research. To address the problem of low rescue efficiency, a co-evolutionary optimization algorithm (CEOA) is proposed in this study. Meanwhile, this study presents how the sub-path weight function co-evolves with the future traffic environment dynamics using the evolution mechanism, considering the complex vehicle running characteristics in the urban roads. Three sets of simulation experiments are conducted to test the comprehensive performance of CEOA under various scenarios. Experimental results show that the proposed CEOA is superior to traditional and emerging path optimization methods in terms of the travelling time and its stability, such as on-line re-optimization (OLRO) and co-evolutionary path optimization (CEPO). The proposed CEOA integrates the advanced advantages of regular re-optimization and co-evolutionary optimization, and opens the door to develop new path optimization technology. The findings provide powerful technology support and a theoretical basis for emergency rescue management improvement.

The severe impact of traffic accidents, along with a large number of deaths and disabilities, necessitates further improvements in rescue path optimization. To make the emergency rescue more efficient and furthermore ensure health care in life-saving and mitigating traffic congestion as soon as possible, a methodology for rescue vehicle path optimization, timing co-evolutionary path optimization (TCEPO), is proposed to optimize the rescue path. Distinguishing from conventional online re-optimization (OLRO) and co-evolutionary path optimization (CEPO), in TCEPO, each optimization process co-evolves with future traffic environment that keeps changing over time, and the best path will be modified timely based on the predicted routing environmental dynamics (PRED) and recent traffic data. Besides, for better computation efficiency, this research reports an improved ripple spreading algorithm (RSA) as a realization of TCEPO to resolve the optimality problem. The modeling and solutions of TCEPO are discussed in detail to illustrate the applications in emergency rescue path optimization. In order to compare the performance of three methods (OLRO, CEPO and TCEPO), the same optimization tasks and scenarios are presented, and numerical simulation is carried out 100 times. Experimental results clearly prove that the proposed TCEPO possesses stronger robustness and is about 17.65% to 40.02% shorter than CEPO, as well as about 26.34% to 38.47% shorter than OLRO in terms of the travelling time under the PRED with various uncertainties. These advantages have a great impact on raising efficiency and reliability of emergency rescue, which can help rescue vehicles reach the destination as quickly as possible and save more lives.

The aim of this paper was to systematically obtain the poverty reduction effects and diversified poverty alleviation paths of road infrastructure, to assist in the planning of transport poverty alleviation and rural revitalization in the concentrated contiguous poverty-stricken areas. The measurement methods for impact effects and paths of transport poverty alleviation have been scientifically proposed based on methods of transportation economics and transportation geography. Firstly, an overview of the interactive mechanism and processes by which road infrastructure investment influences poverty reduction has been offered, and the characteristics of poverty space and spatial coupling result of road infrastructure have been systematically obtained. The results show that about 70% of the district counties’ road infrastructure and poverty rate are in a state of spatial coupling imbalance; the coordinated synchronous type is mainly distributed along the road network. Secondly, the structural equation model system has been formulated with variables that reflect transportation input in adjacent geographical units to consider spatial spillover effects. The results show that the direct poverty reduction effect of road infrastructure (0.105) is much lower than the indirect poverty reduction effect (0.830). Thirdly, empirical analysis at regional level of the concentrated contiguous poverty-stricken areas in China has been conducted. As a result, while addressing the limitations of previous studies, the poverty alleviation path that has been proposed also aims to catalyze actions to reduce the transport-related exclusion in poverty-stricken areas caused by the lack of access to basic facilities.

In road traffic crashes, although rollover crashes account for a relatively low proportion, those result in a high fatality rate. The present study performed random parameters ordered logit models to examine risk factors as well as their heterogeneous effects on driver injury severity in single-vehicle passenger car and SUV rollover crashes. Crash data for the empirical analysis were extracted from Texas Crash Record Information System (CRIS) database during the year 2016. Model estimation results show that six variables (male drivers, drivers’ age, airbag deployment, failure to drive in single lane, speed limit, and rural area) were found to produce normally distributed parameters in passenger car model, while nine parameters (male drivers, safety belt use, airbag deployment, drug or alcohol use, failure to drive in single lane, improper evasive action, vehicle model year, friday, and rural area) in SUV model were found to be normally distributed. Several other factors with fixed parameters were found to be associated with driver injury severity in single-vehicle passenger car or SUV rollover crashes, most notably: ejection or partial ejection, turning left, intersection, August, adverse weather conditions, and night with light. These variables were significant in both models; most variables have stronger effects on nonincapacitating injury and serious injury outcomes in SUV than in passenger car rollover crashes. These findings provide a deep insight into causality nature and factor involved in driver injury severity in single-vehicle passenger car and SUV rollover crashes and are also helpful for transport agencies to determine appropriate countermeasures aimed at mitigating injuries sustained by drivers in single-vehicle rollover crashes.

According to the accident analysis of vehicles in the curve, the skidding, rollover, and lateral drift of vehicles are determined as means to evaluate the lateral stability of vehicles. The utility truck of rear-wheel drive (RWD) is researched, which is high accident rate. Human-vehicle-road simulation models are established by CarSim. Through the orthogonal experiment method, the effects of different road geometries, speed, and interaction factors between road geometries on vehicle lateral stability are studied. In this paper, skidding risk of the vehicle is characterized by the Side-way Force Coefficient (SFC). Rollover risk of the vehicle is characterized by lateral acceleration and the load transfer ratio. Lateral drift risk of the vehicle is characterized by the sideslip angle of wheels. The results of orthogonal analysis reveal that the maximum tire-road friction coefficient and speed are highly significant in skidding of the vehicle. The effects of the combination of horizontal alignment and superelevation on vehicle skidding are important. The effects of horizontal alignment and speed on vehicle rollover risk are highly significant. The effects of superelevation on vehicle rollover risk are significant. The effects of the interaction of horizontal alignment and superelevation are also important on vehicles’ rollover risk. The speed and the maximum tire-road friction coefficient have highly significant effect on the vehicle’s lateral drift. The superelevation has a significant effect on the vehicle’s lateral drift. The effects of the interaction of horizontal alignment and superelevation and longitudinal slope are also important on the lateral drift of the vehicle.

In order to identify crash-prone sections of the highways in mountainous areas professionally and exclusively, the common phenomena of “sharp turns”, “continuous long downhill”, “multiple tunnels”, “dangerous roadside environment”, and complex and changeable meteorological environment, which all imply risk factors of the mountainous highways, are comprehensively considered. Utilizing the improved classical coupling model, the coupling mechanism of the risk factors is revealed, and the coupling model of the traffic risk factors is constructed, by which the coupling degrees of multi-risk factors couplings are calculated respectively. Based on the coupling degrees of the above factors, the concept of vehicle operation risk index (VORI) of the mountainous highway is introduced and its numerical value is quantified as the basis for identifying the crash-prone sections. The 21 km of Songming to Huize section of the Songdai Highway in the Yunnan Province of China is selected as an example, and the good applicability of the identification model is verified.

This study sets out to investigate the effects of traffic composition on freeway crash frequency by injury severity. A crash dataset collected from Kaiyang Freeway, China, is adopted for the empirical analysis, where vehicles are divided into five categories and crashes are classified into no injury and injury levels. In consideration of correlated spatial effects between adjacent segments, a Bayesian multivariate conditional autoregressive model is proposed to link no-injury and injury crash frequencies to the risk factors, including the percentages of different vehicle categories, daily vehicle kilometers traveled (DVKT), and roadway geometry. The model estimation results show that, compared to Category 5 vehicles (e.g., heavy truck), larger percentages of Categories 1 (e.g., passenger car) and 3 (e.g., medium truck) vehicles would lead to less no-injury crashes and more injury crashes. DVKT, horizontal curvature, and vertical grade are also found to be associated with no-injury and/or injury crash frequencies. The significant heterogeneous and spatial effects for no-injury and injury crashes justify the applicability of the proposed model. The findings are helpful to understand the relationship between traffic composition and freeway safety and to provide suggestions for designing strategies of vehicle safety improvement.

Road traffic congestion has become a normal state and caused many problems in large cities of China, and lane-changing model has attracted increased attention in recent years. This study is aimed to explore the changing trend and quantify the logical relationship between driver’s heart rate and lane-changing behavior under urban traffic congestion. First, the testing scheme of driver’s heart rate and lane-changing has been designed. Tested drivers and testing paths are chosen strictly to achieve the experiments as well. Then, with the drivers’ behavior-related data, the backpropagation neural network theory is introduced to build the driver’s “pressure–state–response” model under urban traffic congestion, which takes driver’s pressure and state as input variables, and driver’s response is selected as output variables. As the result of pressure–state–response model, it is significant that effect of urban traffic congestion on driver’s heart rate and lane-changing proportion. The validation results indicate that the pressure–state–response model works well to predict the proportion of risky lane-changing, and the pressure–state–response model can be used for warning the risky lane-changing directly under urban traffic congestion.

As the basis of traffic safety management, crash prediction models have long been a prominent focus in the field of freeway safety research. Studies usually take years or seasons as the observed time units, which may result in heterogeneity in crash frequency. To eliminate that heterogeneity, this study analyzes monthly crash counts and develops Bayesian hierarchical models with random effects, lag-1 autoregression (AR-1), and both (REAR-1) to accommodate the multilevel structure and temporal correlation in crash data. The candidate models are estimated and evaluated in the freeware WinBUGS using a crash dataset obtained from the Kaiyang Freeway in Guangdong Province, China. Significant temporal effects are found in the three models, and Deviance Information Criteria (DIC) results show that taking temporal correlation into account considerably improves the model fit compared with the Poisson model. The hierarchical models also avoid any misidentification of the factors with significant safety effects, because their variances are greater than in the Poisson model. The DIC value of the AR-1 model is substantially lower than that of the random effect model and equivalent to that of the REAR-1 model, which indicates the superiority of the lag-1 autoregressive structure in accounting for the temporal effects in crash frequency.

Although road traffic congestion is an objective state of traffic flow, drivers have different feelings about road traffic congestion. First of all, in order to reveal the law that driver’s mental state changes along with congested degree of road traffic, the targeted questionnaire was designed to analyze the driver’s psychological feeling under different state of traffic flow. Then, from the perspectives of the driver’s subjective feeling, the new definition of road traffic congestion was put forward, so the pressure coefficient of traffic congestion, which is written as χ press t 0 − t n , is defined to measure traffic congestion pressure. Furthermore, by adopting statistical methods to associate the driver’s subjective feeling toward traffic congestion with objective parameters of traffic flow, the grading thresholds of the unblocked state, mild congested state, moderate congested state, and severe congested state were calculated, which are χ press t 0 − t n = 0 . 37 , χ press t 0 − t n = 0 . 51 , and χ press t 0 − t n = 0 . 65 , respectively. And in the field of application for the grading thresholds, Fourier Transform theory was introduced to calculate domain frequency indexes of the driver’s heart rate variability in the four states of traffic flow, respectively. The results show that the domain frequency indexes of the driver’s heart rate variability present obvious differences in the four states, which illustrates the solving rationality and applied value of the new grading thresholds for traffic congestion based on driver’s feeling. On one hand, the new grading method for traffic congestion, which combines the subjectivity with objectivity, can reflect the driver’s actual feeling; on the other hand, it lays the foundation for the study about the influence of traffic congestion on the driver’s physiological and psychological characteristics.

In this paper, flame retardant composites were prepared by incorporating three flame retardants (FRs), including triphenyl phosphate (TPP), polysiloxane (PSQ) and phosphite functionalized polysiloxane (PPSQ), respectively into a polylactic acid (s/PLLA) matrix. The results indicated that the ultimate oxygen index increased from 20.6% (s/PLLA) to 22.5% (s/PLLA/TPP), 21.1% (s/PLLA/PSQ), and 23.3% (s/PLLA/PPSQ). The composites exhibited a decrease in peak heat release rate (pHRR) and prolonged peak time according to the cone calorimetry analysis. s/PLLA/PPSQ possessed the highest residual carbon content and the densest char residue with finest and smallest pores, indicating excellent flame-retardant performance. The crystallization behavior analysis revealed that the three FRs resulted in an increased crystallization rate and crystallinity. Notably, the crystallinity of s/PLLA/PPSQ increased from 25.8% in s/PLLA to 37.3%. Additionally, PSQ and PPSQ effectively enhanced the mechanical properties of composite materials. Compared to s/PLLA, the tensile strength of s/PLLA/PSQ and s/PLLA/PPSQ increased by 11.5% and 31.3% respectively, and storage modulus increased by 50.0% and 14.6%. This research demonstrated that among the three additives, PPSQ can effectively provide both flame retardancy and mechanical properties to the s/PLLA matrix, resulting in the composite with the best comprehensive performance. [ABSTRACT FROM AUTHOR]