Search

To expand previous understanding of age-related vascular changes, we examined the association between aging and characteristics of cerebral arteries among 1133 participants aged 35 to 75 years recruited from Shanghai, China. Characteristics of the cerebral vessels including arterial branch density, mean radius, and mean tortuosity were quantified using MR angiography. The radius, tortuosity, and length of the basilar artery (BA) and the M1 segment of middle cerebral artery (MCA) were also accessed. Linear regression model was used to examine the association between age and vasculature features. The sample was divided into four subgroups by age and the association was analyzed in each subgroup. Age was found to be a significant predictor for cerebrovascular modifications after adjusting for vascular risk factors. Further analysis in subgroup revealed that the associations were due to the predominate effect of the vascular modifications happened during the younger years (35–54 years). The radius of either BA or MCA was associated with aging only in subjects aged 45–54 years. In conclusion, rapid alterations in all three morphological features assessed have been noticed to be associated with aging in the 45–54 subgroup, suggesting the potential importance of the 5th decade for early preservation method for vascular aging.

The phase mismatch between odd and even echoes in EPI causes Nyquist ghost artifacts. Existing ghost correction methods often suffer from severe residual artifacts and are ineffective with k-space undersampling data. This study proposed a deep learning-based method (PEC-DL) to correct phase errors for DWI at 7 Tesla.The acquired k-space data were divided into 2 independent undersampled datasets according to their readout polarities. Then the proposed PEC-DL network reconstructed 2 ghost-free images using the undersampled data without calibration and navigator data. The network was trained with fully sampled images and applied to two- and fourfold accelerated data. Healthy volunteers and patients with Moyamoya disease were recruited to validate the efficacy of the PEC-DL method.The PEC-DL method was capable to mitigate the ghost artifacts in DWI in healthy volunteers as well as patients with Moyamoya disease. The fourfold accelerated results showed much less distortion in the lesions of the Moyamoya patient using high b-value DWI and the corresponding ADC maps. The ghost-to-signal ratios were significantly lower in PEC-DL images compared to conventional linear phase corrections, mini-entropy, and PEC-GRAPPA algorithms.The proposed method can effectively eliminate ghost artifacts for full sampled and up to fourfold accelerated EPI data without calibration and navigator data.

To solve the problems of the low target-positioning accuracy and weak algorithm robustness of target-dosing robots in greenhouse environments, an image segmentation method for cucumber seedlings based on a genetic algorithm was proposed. Firstly, images of cucumber seedlings in the greenhouse were collected under different light conditions, and grayscale histograms were used to evaluate the quality of target and background sample images. Secondly, the genetic algorithm was used to determine the optimal coefficient of the graying operator to further expand the difference between the grayscale of the target and background in the grayscale images. Then, the Otsu algorithm was used to perform the fast threshold segmentation of grayscale images to obtain a binary image after coarse segmentation. Finally, morphological processing and noise reduction methods based on area threshold were used to remove the holes and noise from the image, and a binary image with good segmentation was obtained. The proposed method was used to segment 60 sample images, and the experimental results show that under different lighting conditions, the average F1 score of the obtained binary images was over 94.4%, while the average false positive rate remained at about 1.1%, and the image segmentation showed strong robustness. This method can provide new approaches for the accurate identification and positioning of targets as performed by target-dosing robots in a greenhouse environment.

The purpose was to explore the value of high on-treatment platelet reactivity (HTPR) in predicting long-term clinical outcomes for stroke patients. The platelet reactivity was assayed after being treated with either 75 mg clopidogrel or 100 mg aspirin daily with VerifyNow System in stroke patients. HTPR for clopidogrel was defined as PRU ≥ 208, and that for aspirin was defined as ARU ≥ 550. CYP2C19 genotyping was performed using the Sequenom MassARRAY iPLEX platform. The primary endpoint was a composite of recurrent ischemic stroke, transient ischemic attack, myocardial infarction, or ischemic vascular death. The safety endpoint was bleeding. In the clopidogrel group, among 345 patients recruited, 174 of them were categorized as HTPR. A total of 270 patients were followed up for 54 months. There was a significant association between HTPR and the primary endpoint (HRadj 2.13 [95% CI, 1.43–3.15], p

Angelman syndrome (AS) is a genetic disorder that affects neurodevelopment. The investigation of changes in the brain white matter network, which would contribute to a better understanding of the pathogenesis of AS brain, was lacking.To investigate both local and global alterations of white matter in patients with AS.Prospective.A total of 29 AS patients (6.6 ± 1.4 years, 15 [52%] females) and 19 age-matched healthy controls (HC) (7.0 ± 1.5 years, 10 [53%] females).A 3-T, three-dimensional (3D) T1-weighted imaging by using gradient-echo-based sequence, single shell diffusion tensor imaging by using spin-echo-based echo-planar imaging.Network metrics including global efficiency (ELinear regression model, permutation test. P values estimated from the regression model for each brain region were adjusted by false discovery rate (FDR) correction.AS patients showed significantly lower EThe AS brain showed diminished connectivity, reflected by reduced network efficiency compared to HC. Compared to densely connected regions, less connected regions were more vulnerable in AS.2 TECHNICAL EFFICACY: Stage 3.

Background: Previous studies suggested blood pressure variability (BPV) might help reveal interactions between blood pressure fluctuation and white matter lesions, and the impact of elevated BPV on white matter hyperintensity (WMH) or cerebral arterial dilation is unclear. Methods: This retrospective observational study involved 2634 stroke-free individuals (68.6±11.1 years, 50.3% female), who underwent magnetic resonance imaging and magnetic resonance angiography scans, from a single center in Shanghai, China. Measurements for variability of blood pressure were made based on 7 days blood pressure recordings. WMHs were quantified from T2-FLAIR images and further classified as periventricular WMH or deep WMH. M1 segment of middle cerebral artery dilation was assessed from magnetic resonance angiography images. General linear model was used to examine the associations. Results: Both increased systolic and diastolic BPV were associated with increased WMH volume (systolic: β =0.02 [95% CI, 0.004–0.03], P =0.01; diastolic: β =0.05 [95% CI, 0.03–0.08], P β =0.02 [95% CI, 0.005–0.04], P =0.01; diastolic: β =0.06 [95% CI, 0.04–0.09], P β =0.11 [95% CI, 0.06–0.17], P β =0.17 [95% CI, 0.11–0.23], P Conclusions: Increased BPV might be one of the pathophysiological phenomena involving in the small vessel disease independent of hypertension. Increased BPV might independently contribute to intracranial arterial dilation. Management of BPV might be a target to preserve cerebrovascular wellness.

It is difficult to obtain high-protein contents from rice straw using direct fermentation due to its low nitrogen content. This study investigates the effects of ammonification–steam explosion pretreatment of rice straw on the protein content after solid-state fermentation (SSF). The pretreatment is carried out under multi-strain inoculation conditions. The samples of rice straw after ammonification (TA), steam explosion (TSE), and ammonification and steam explosion (TA-SE) were compared to the control group (TC). The results indicate that both ammonification and steam explosion could disintegrate rice straw’s lignocellulosic structure, releasing nutrients that can be used for microbial reproduction. In addition, amino compounds are formed along with depolymerization products, thus effectively promoting the true protein content. Post-fermentation, total crude protein contents of TA, TSE, and TA-SE samples were 2.56, 1.83, and 4.37 times higher than that of Tc samples, respectively, and true protein contents were 2.52, 1.83, and 5.03 times higher. This study shows that the true protein content by combined ammonification and steam explosion pretreatment of rice straw during 96 h of solid-state fermentation was 46.7% of its total matter, rendering it a suitable alternative to high-protein animal feed.

Background Monte Carlo (MC) has been widely used in fields such as biomedicine and computer graphics owing to its unique capabilities of flexibility, high-accuracy and simplicity for modeling light transport in tissues, but the applications in food and agricultural domain are limited or hindered due to the lack of knowledge on the optical properties of food products. Thanks to major breakthroughs in optical measuring and computing technologies since the year of 2000, significant advances have been made in sensing techniques for measuring tissue optical properties. Therefore, MC has witnessed great progress in food and agricultural domain over the past two decades. Scope and approach The development of MC for modeling light transport in food and agricultural products, including the principle, advanced MC methods, relevant applications, and future perspectives were reviewed. The paper is aimed at helping interested researchers to gain a better understanding of the MC technique, thus stimulating quality and safety assessment of food and agricultural products. Key findings and conclusions This paper provides an overview of the procedure of MC modeling for light transport in food and agricultural products and commonly used MC models. Advanced methods for accelerating MC simulations are then presented. Applications of MC simulations in food and agricultural products, since the year of 2000, for optimizing the design of sensing configuration and parameter, estimating tissue optical property, and assessing quality and safety are then reviewed. Finally, challenges and future perspectives for MC technique in modeling light transport are discussed.

Rice straw biogas residue contains high lignin content, so the decomposition of this material by natural compost is slow. This study investigated the effect of the combination of rice straw addition and microbial inoculation (Aspergillus niger CICIMF0410 and Phanerochaete chrysosporium AF96007) on the physiochemical properties of rice straw biogas residue in the composting process. Four composting treatment groups were designed: rice straw biogas residue (RR; T1), RR + rice straw (RS) (T2), RR + inoculants (T3), and RR + RS + inoculants (T4). The addition of rice straw significantly accelerated the initial temperature rise during composting, and microbial inoculation accelerated lignocellulose decomposition. After composting, the electrical conductivities of samples T1 to T4 were 1.22, 0.87, 0.99, and 0.82 DS ml−1, respectively. Compared with other treatment samples, T4 showed noticeably increased degradation rates of HC, CL, and ADL after decomposition. The total humic acid levels of samples T1 to T4 were 9.5, 12.7, 10.5, and 18.6%, with humification index values of 1.45, 1.80, 1.69, and 2.46, respectively, after maturation. After 12 weeks of composting, T4 showed the highest increase in total nitrogen (37.6%), phosphorus (33.6%), and potassium (29.8%) levels. Furthermore, compared with other treatment samples, T4 showed the best maturity indices, such as morphology, color, and odor. Rice straw addition and biological inoculation for biogas residue composting not only significantly decreases the time required for decomposition but also eliminates the toxicity risk for crops and improves the stability of the biogas residue fertilizer.

Highlights This study focused on the path tracking accuracy of a two-wheel steering, two-wheel drive autonomous vehicle. An improved fuzzy logic control method (IFM) was designed to control the steering angle of the front wheels. The IFM was better than traditional pure pursuit and fuzzy logic control methods for automatic path tracking. Abstract. This article presents a path-tracking algorithm based on an improved fuzzy logic control method (IFM) that generates optimal steering angles for an autonomous wheeled vehicle to track a sequence of waypoints. The path-tracking algorithm was designed to focus on the vehicle performance, including tracking accuracy, stability, and convergence speed. A prototype vehicle with two-wheel steering and two-wheel drive (2WS-2WD) was developed as a test platform and equipped with a series of sensors for evaluating the IFM. In this study, we considered two variables, i.e., lateral deviation (d) and heading deviation (θ), as inputs for the control system. The output (δ) was the steering angle of the front wheels as controlled by an electric linear actuator. A maximum steering angle strategy was adopted for rapid convergence when the vehicle was far from the desired path or when the heading deviation was large. An update-line distance algorithm was used for finding the best turning time as the vehicle moved closer to the next waypoint. To validate the proposed algorithm, testing was performed to compare traditional pure pursuit (TPP), traditional fuzzy logic control method (TFM), and the IFM in tracking two types of paths (straight and rectangular). Traveling at 0.5 m s-1 and with a signal sampling period of 0.5 s, the prototype converged to the desired straight path from different initial states. When the vehicle reached a stable state, the steady-state error was between 5.0 and 6.5 cm with a mean of ≤6.0 cm. The settling distance in the straight path test was between 125.0 and 422.3 cm, and the convergence time was in the range of 11.5 to 16.0 s; the greater the initial deviation of the vehicle was, the greater the settling distance and settling time were. In the 15 m x 14 m rectangular path test, the overall mean error of the IFM was 14.4 cm when the initial lateral and heading deviations were 0, and the maximum deviation was 67.4 cm, which occurred at the corners. The test results show that the proposed IFM had better accuracy, stability, and convergence speed for path tracking when compared to the TPP and TFM algorithms.

As an innovative mobility strategy, public bike-sharing has grown dramatically worldwide. Though it provides convenient, low-cost, and environmental-friendly transportation, the unique features of bike-sharing systems give rise to problems for both users and operators. The primary issue is the uneven distribution of bikes caused by ever-changing usage and (available) supply. This imbalance necessitates efficient bike rebalancing strategies, which depends highly on bike mobility modeling and prediction. In this paper, a trace-driven simulation-based prediction approach is proposed by simultaneously taking user mobility demand and real-time status of stations into consideration. We extensively evaluate the performance of our design with the dataset from one of the world’s largest public bike-sharing systems located in Hangzhou, China, which owns more than 2800 stations. The evaluation results show an 85 percentile relative error of 0.6 for checkout and 0.4 for checkin prediction. The preliminary results on how the predictions can be used for bike rebalancing are also provided. We believe that this new mobility modeling and prediction approach can improve the bike-sharing system operation algorithm design and pave the way for rapid deployment and adoption of bike-sharing systems across the globe.

BackgroundAmple evidence has suggested that vascular modifications are associated with aging. To expand previous understanding of age-related vascular changes, we examined the association between aging and cerebrovascular morphologies.Methods1176 participants aged 35 to 75 years recruited from Shanghai, China were included in this study. Cerebrovascular morphological features comprising arterial branch density, radius, and tortuosity were quantified using three-dimensional magnetic resonance angiography. Linear regression was used to examine the association between age and vasculature features.ResultsAge was found to be a significant predictor for cerebrovascular morphological alterations after adjusting for vascular risk factors. However, after dividing subjects into subgroups based on their age, aging was found to be significantly correlated with all three morphometric features only in the 45-54 subgroup after adjusting for the other vascular risk factors. Smoking gives rise to a more rapid age-related changes in vascular morphologies, while alcohol consumption could decelerate those age-related alterations.ConclusionsRapid alternations in all three morphological features assessed have been noticed to be associated with aging in the 45-54 subgroup, suggesting the potential importance of the 5th decade for early preservation method of vascular aging.FundingNational Natural Science Foundation of China.

Urban freeway traffic control is of great importance for traffic management and intelligent transportation systems. Various approaches have been proposed to relieve urban freeway traffic jam, among which, ALINEA, a ramp metering strategy, is commonly implemented with fixed triggering threshold and static controller parameter. However, such a strategy may not be able to effectively alleviate the traffic congestion while maintaining certain ramp throughput due to two reasons: i). the congestion threshold can be time-varying due to different factors, such as segment ID, weather condition, time, and etc. ii). The congestion evolution patterns are time-varying even for the same segment. In this paper, based on over 890 million records of vehicles collected on ramps in Hangzhou, China, we established dynamic congestion threshold for each road segment with external factors. Based on such dynamic congestion threshold, we further clustered the congestion evolution patterns, and designed adaptive ramp controller which could switch the controller parameter according to the predicted congestion evolution pattern. Finally, in order to show the performance among different strategies, we introduced three baseline groups, which are ‘without Controller’, ‘ALINEA controller’, and ‘Direct RBF(radial basis function)-neural network controller’, respectively.The evaluation of proposed controller design over real large-scale data indicated that our method achieves 8.4%(7.2%), 4.62%(9.48%) efficiency improvement in terms of average speed in km/h (average traffic flow in veh/h) than the performance with normal ALINEA controller and RBF-neural network controller respectively.

The rapid development of bike-sharing systems has brought people enormous convenience during the past decade. On the other hand, high transport flexibility gives rise to problems for both users and operators. For users, dynamic distribution of shared bikes caused by uneven user demand often leads to the check in or check out service unavailable at some stations. For operators, unbalanced bike usage comes with more bike broken and growing maintenance cost. In this paper, we consider enhancing user experiences and rebalance bicycle utilization by directing users to different stations with a higher success rate of rental and return. For the first time, we devise a trip advisor that recommends bike check-in and check-out stations with joint consideration of service quality and bicycle utilization. To ensure service quality, we firstly predict the user demand of each station to obtain the success rate of rental and return in the future. Experiments indicate that the precision of our method is as much as 0.826, which has raised by 25.9 percent as compared with that of the historical average method. To rebalance bike usage, from historical data, we identify that biased bike usage is rooted from circumscribed bicycle circulation among few active stations. Therefore, with defined station activeness, we optimize the bike circulation by leading users to shift bikes between highly active stations and inactive ones. We extensively evaluate the performance of our design through real-world datasets. Evaluation results show that the percentage of frequently used bikes decreases by 33.6 percent on usage number and 28.6 percent on usage time.

Spatial-frequency domain imaging (SFDI) is a wide-field, noncontact, and label-free imaging modality that is currently being explored as a new means for estimating optical absorption and scattering properties of two-layered turbid materials. The accuracy of SFDI for optical property estimation, however, depends on light transfer model and inverse algorithm. This study was therefore aimed at providing theoretical analyses of the diffusion model and inverse algorithm through numerical simulation, so as to evaluate the potential for estimating optical absorption and reduced scattering coefficients of two-layered horticultural products. The effect of varying optical properties on reflectance prediction was first simulated, which indicated that there is good separation in diffuse reflectance over a large range of spatial frequencies for different reduced scattering values in the top layer, whereas there is less separation in diffuse reflectance for different values of absorption in the top layer, and even less separation for optical properties in the bottom layer. To implement the nonlinear least-square method for extracting the optical properties of two-layered samples from Monte Carlo-generated reflectance, five curve fitting strategies with different constrained parameters were conducted and compared. The results confirmed that estimation accuracy improved as fewer variables were to be estimated each time. A stepwise method was thus suggested for estimating optical properties of two-layered samples. Four factors influencing optical property estimation of the top layer, which is the basis for accurately implementing the stepwise method, were investigated by generating absolute error contour maps. Finally, the relationship between light penetration depth and spatial frequency was studied. The results showed that penetration depth decreased with the increased spatial frequency and also optical properties, suggesting that appropriate selection of spatial frequencies for a stepwise method to estimate optical properties from two-layered samples provides potential for estimation accuracy improvement. This work lays a foundation for improving optical property estimation of two-layered horticultural products using SFDI.

Municipal solid waste (MSW) is an increasing waste resource and challenging task to solve environmental pollution and waste collection problems. The smart trash bin is sufficient equipment to reduce human intervention and improve living conditions, lacking multifunctional purposes. To solve the problem that traditional trash can lacks self-identification of recyclable garbage and nonrecyclable garbage, a smart trash bin based on WiFi environment and Arduino control is proposed. The smart trash bin takes Arduino as its master controller and interacts with Arduino in the WiFi environment to realize automatic garbage classification and communication between people and trash bin. This paper aims to describe the hardware and software design ideas of trash bins in the implementation process, and the mechanism of garbage classification and the application of the Internet of things in garbage recycling are emphatically studied. The results indicate that the system can run stably and achieve accurate classification within 2 seconds, which reduces the waste of resources, changes the traditional garbage management mode, improves management efficiency, and realizes recycling of garbage.

The purpose was to explore the value of high on-treatment platelet reactivity (HTPR) in predicting long-term clinical outcomes for stroke patients. The platelet reactivity was assayed after being treated with either 75 mg clopidogrel or 100 mg aspirin daily with VerifyNow System in stroke patients. HTPR for clopidogrel was defined as PRU ≥ 208, and that for aspirin was defined as ARU ≥ 550. CYP2C19 genotyping was performed using the Sequenom MassARRAY iPLEX platform. The primary endpoint was a composite of recurrent ischemic stroke, transient ischemic attack, myocardial infarction, or ischemic vascular death. The safety endpoint was bleeding. In the clopidogrel group, among 345 patients recruited, 174 of them were categorized as HTPR. A total of 270 patients were followed up for 54 months. There was a significant association between HTPR and the primary endpoint (HR

Purpose A phase correction method for high-resolution multi-shot (MSH) diffusion weighted imaging (DWI) is proposed. The efficacy and generalization capability of the method were validated on both healthy volunteers and patients. Theory and methods Conventionally, inter-shot phase variations for MSH echo-planar imaging (EPI) DWI are corrected by model-based algorithms. However, many acquisition imperfections are hard to measure accurately for conventional model-based methods, making the phase estimation and artifacts suppression unreliable. We propose a deep learning multiplexed sensitivity-encoding (DL-MUSE) framework to improve the phase estimations based on convolutional neural network (CNN) reconstruction. Aliasing-free single-shot (SSH) DW images, which have been used routinely in clinical settings, were used for training before the aliasing correction of MSH-DWI images. A dual-channel U-net comprising multiple convolutional layers was used for the phase estimation of MSH-EPI. The network was trained on a dataset containing 30 healthy volunteers and tested on another dataset of 52 healthy subjects and 15 patients with lesions or tumors with different shot numbers (4, 6 and 8). To further validate the generalization capability of our network, we acquired a dataset with different numbers of shots, TEs, partial Fourier factors, resolutions, ETLs, FOVs, coil numbers, and image orientations from two sites. We also compared the reconstruction performance of our proposed method with that of the conventional MUSE and SSH-EPI qualitatively and quantitatively. Results Our results show that DL-MUSE is capable of correcting inter-shot phase errors with high and robust performance. Compared to conventional model-based MUSE, our method, by applying deep learning-based phase corrections, showed reduced distortion, noise level, and signal loss in high b-value DWIs. The improvements of image quality become more evident as the shot number increases from 4 to 8, especially in those central regions of the images, where g-factor artifacts are severe. Furthermore, the proposed method could provide the information about the orientation of the white matter with better consistency and achieve finer fibers delineation compared to the SSH-EPI method. Besides, the experiments on volunteers and patients from two different sites demonstrated the generalizability of our proposed method preliminarily. Conclusion A deep learning-based reconstruction algorithm for MSH-EPI images, which helps improve image quality greatly, was proposed. Results from healthy volunteers and tumor patients demonstrated the feasibility and generalization performances of our method for high-resolution MSH-EPI DWI, which can be used for routine clinical applications as well as neuroimaging research.

The effects of solid loading on the fabrication of ceramic microparts by soft molding were studied. Alumina microchannel parts of different dimensions (60–160 µm) were fabricated from well-dispersed suspensions with different solid loadings (70, 75 and 80 wt%). The structural integrity of the green microchannel parts was examined to study the moldability of the suspensions. It was found that the minimum feature size and linear shrinkage of the microchannel parts decreased with increasing solid loading, while the green density and sintered density showed the opposite trend. The reasons for incomplete filling and demolding failures were also discussed.

In continuum mechanics, the concept of objectivity requires that the qualitative and quantitative description of physical phenomena remains unchanged under a change in reference frame. It means that the observations in different reference frames are coherent and thus the observed motions can be regarded as objectively equivalent. On the other hand, concerning the material constitution, the principle of material objectivity (also often referred as principle of material frame-indifference, or simply the principle of objectivity) requires that constitutive equations of a material body must be independent of the observer (reference frame). Both objectivity and principle of objectivity have been widely used in modern continuum mechanics studies. However, in molecular dynamics (MD) simulation, which is a prevalent numerical method in nanoscience, consideration is rarely given to the concept of objectivity or principle of objectivity since most of the MD simulations have been performed in inertial systems, where Galilean-invariance is assumed. This research aims to investigate the conditions for Euclidean objectivity in non-equilibrium molecular dynamics (NEMD), where reference frames are non-inertial and multi-physics effects are present in the atomistic material system. By supplementing fictitious acceleration to the governing equation and requiring the principle of objectivity on the constitutive equation, this research arrives at a special solution for NEMD that is Euclidean-invariant. Several sets of simulations demonstrate that equivalent motions can be achieved in NEMD. This study may provide new directions for future MD applications.

Rapid development of bike-sharing systems has brought people enormous convenience during the past decade. On the other hand, high transport flexibility comes with dynamic distribution of shared bikes, leading to an unbalanced bike usage and growing maintenance cost. In this paper, we consider to rebalance bicycle utilization by means of directing users to different stations. For the first time, we devise a trip advisor that recommends bike check-in and check-out stations with joint consideration of service quality and bicycle utilization. From historical data, we firstly identify that biased bike usage is rooted from circumscribed bicycle circulation among few active stations. Therefore, with defined station activeness, we optimize the bike circulation by leading users to shift bikes between highly active stations and inactive ones. We extensively evaluate the performance of our design through real-world datasets. Evaluation results show that the percentage of frequent used bikes decreases by 33.6% on usage number and 28.6% on usage time.

Dynamically localizing users in online social networks is challenging because people seldom post location-related microblogs due to privacy concern. To increase inference accuracy, a promising approach is to leverage microblogs from friends. However, it is difficult because microblogs from friends may not be synchronized or informative. To tackle these challenges, we propose a system consisting two steps. Firstly, "co-location" friends are detected and used to infer the statistical locations of users. Secondly, users' dynamic locations are determined by considering both statistical locations and POI(point of interest) names in microblogs. Experiments based on real world dataset demonstrates that our approach outperforms previous studies.

Public bike-sharing systems (BSS) are booming all around the world, providing a flexible trip mode for people in cities. However, the imbalance usage among stations is causing problems for both system operators and users. As a first step to address this challenge, a recent paper has proposed a spatio-temporal bicycle mobility model based on historical bike-sharing data, and devised a traffic prediction mechanism on a per-station basis with sub-hour granularity. To better demonstrate the mobility model and prediction, we develop this data analysis and visualization system, not only presenting massive real-time prediction results but also serving as a platform for human mobility analysis.

As an innovative mobility strategy, public bike-sharing has grown dramatically worldwide. Though providing convenient, low-cost and environmental-friendly transportation, the unique features of bike-sharing systems give rise to problems to both users and operators. The primary issue among these problems is the uneven distribution of bicycles caused by the ever-changing usage and (available) supply. This bicycle imbalance issue necessitates efficient bike re-balancing strategies, which depends highly on bicycle mobility modeling and prediction. In this paper, for the first time, we propose a spatio-temporal bicycle mobility model based on historical bike-sharing data, and devise a traffic prediction mechanism on a per-station basis with sub-hour granularity. We extensively evaluated the performance of our design through a one-year dataset from the world's largest public bike-sharing system (BSS) with more than 2800 stations and over 103 million check in/out records. Evaluation results show an 85 percentile relative error of 0.6 for both check in and check out prediction. We believe this new mobility modeling and prediction approach can advance the bike re-balancing algorithm design and pave the way for the rapid deployment and adoption of bike-sharing systems across the globe.