This study uses a large-scale click-stream dataset to model browsing and purchasing behavior of ecommerce website visitors. It is shown that direct visitors and indirect visitors act differently in terms of the number of viewed pages and purchasing decision. We subsequently use the ratio of direct visits to indirect visits as an indicator to add into website earning performance estimation and find that the ratio adds some explanatory power.
Target image detection based on a rapid serial visual presentation (RSVP) paradigm is a typical brain-computer interface system with various applications, such as image retrieval. In an RSVP paradigm, a P300 component is detected to determine target images. This strategy requires high-precision single-trial P300 detection methods. However, the performance of single-trial detection methods is relatively lower than that of multitrial P300 detection methods. Image retrieval based on multitrial P300 is a new research direction. In this paper, we propose a triple-RSVP paradigm with three images being presented simultaneously and a target image appearing three times. Thus, multitrial P300 classification methods can be used to improve detection accuracy. In this study, these mechanisms were extended and validated, and the characteristics of the multi-RSVP framework were further explored. Two different P300 detection algorithms were also utilized in multi-RSVP to demonstrate that the scheme is universally applicable. Results revealed that the detection accuracy of the multi-RSVP paradigm was higher than that of the standard RSVP paradigm. The results validate the effectiveness of the proposed method, and this method can provide a whole new idea in the field of EEG-based target detection.
A brain-computer interface (BCI) is an advanced human-machine interaction technology. The BCI speller is a typical application that detects the stimulated source-induced EEG signal to identify the expected characters of the subjects. The current mainstream matrix-based BCI speller involves two problems that remain unsolved, namely, gaze-dependent and space-dependent problems. Some scholars have designed gaze-independent and space-independent spelling systems. However, this system still cannot achieve a satisfactory information transfer rate (ITR). In this paper, we propose a novel triple RSVP speller with gaze-independent and space-independent characteristics and higher ITR. The triple RSVP speller uses rapid serial visual presentation (RSVP) paradigm, each time presents three different characters, and each character is presented three times to increase the ITR. The results of the experiments show the triple RSVP speller online average accuracy of 0.790 and average online ITR of 20.259 bit/min, where the system spelled at a speed of 10 s per character, and the stimulus presentation interface is a 90 × 195 pixel rectangle. Thus, the triple RSVP speller can be integrated into mobile smart devices (such as smartphones, smart watches, and others).
Aims Parameterization of reference temperature has always been the key and difficult part in calculating evapotranspiration and its evaporation and transpiration components by using three-temperature model.In this paper, the best value of reference temperature was determined by quantifying and comparing the influence of different reference temperature values on the accuracy of transpiration estimation by three-temperature model. MethodsBased on the Bowen ratio and thermal infrared observation data of a typical urban lawn, sensitivity analysis and error analysis were carried out on the input variables involved in the sub-model of the three-temperature model to determine the most critical variables for the accuracy of transpiration estimation.Then the influence of input variables parameterization on the calculation of transpiration was quantified and compared to determine the best value of reference temperature.Important findings When using the three-temperature model, the best estimation is to select the maximum temperature of the whole piece of paper as the reference leaf temperature (R 2 = 0.91, root mean square error (RMSE) = 0.078 mm•h -1 ).When the maximum value of the vegetation canopy temperature was used as the reference temperature, it is directly assumed that the transpiration at the maximum temperature of the vegetation is zero (there is a certain transpiration rate in fact).Therefore, it is easy to underestimate the actual transpiration, resulting in that the estimation accuracy of the three-temperature model was slightly lower than the accuracy of using the maximum value of the reference leaf temperature, but the estimation effect is still good (R 2 = 0.87, RMSE = 0.080 mm•h -1 ).Therefore, considering the limitations of the reference leaf settings, if the reference leaf temperature cannot be measured in practical applications, the maximum temperature of the vegetation canopy as
<p>This paper proposes a multi-scale attention fusion mechanism for automatic gland segmentation based on the colorectal adenocarcinoma cell dataset, aiming to address the issue of unclear cell adhesion and confusion with the background in colorectal adenocarcinoma cell instance segmentation. Deep learning methods are employed for top-down gland cell instance segmentation. The neural network features a novel spatial-pyramid dual-path attention module that not only integrates multi-dimensional feature map spatial information but also enriches feature space through cross-dimensional feature information interaction. With the assistance of the new fusion module, it can perceive higher resolution features effectively fuse multi-scale features, leading to higher segmentation accuracy, stronger robustness, and generalization. It demonstrates excellent performance on the GlaS and CRAG datasets.</p> <p> </p>
Purpose: 4D CT is useful clinically for detailed abdominal and thoracic imaging over the course of the respiratory cycle. However, it usually delivers 10∼15 times more radiation dose to the patient as compared to the standard 3D CT, since multiple scans at each couch position are required to obtain the temporal information. In this work we propose a method to obtain high quality 4D CT with low tube current, hence reducing the radiation exposure of patients. Method and Materials: The improvement of the signal‐to‐noise ratio (SNR) of the CT image at a given phase was achieved by superposing the imaging information from other phases with the use of a deformable image registration model. To further reduce the statistical noise caused by low tube current, we developed a novel 4D penalized weighted least square (4D‐PWLS) method to smooth the data spatially and temporally. The method was validated by motion‐phantom and patient studies using a GE Discovery‐ST PET/CT scanner. A Varian RPM respiratory gating system was used to track the motion and to facilitate the phase binning of the 4D CT data. Results: We calculated the SNRs for both studies. The average SNR of 10 mA phantom images increased by more than three‐fold from 0.051 to 0.165 after the proposed 4D‐PWLS processing, without noticeable resolution loss. The patient images acquired at 90mA showed an increase from 2.204 to 4.558 for the end‐inspiration phase, and from 1.741 to 3.862 for the end‐expiration phase, respectively. By examining the subtraction images before and after processing, good edge preservation was also observed in the patient study. Conclusion: By appropriately utilizing the temporal information in 4D‐CT, the proposed method effectively suppresses the noise while preserving the resolution. The technique provides a useful way to reduce the patient dose during 4D CT and is thus valuable for 4D‐radiotherapy.
The dynamic dual-target very long baseline interferometry (VLBI) processing technology applied to the CVNScorr software processor is introduced. Chang’e 5 (CE-5) has achieved China’s first sample return mission from an extraterrestrial body. The characteristics of VLBI are that there are several target probes and the telemetry tracking and command (TT&C) technical requirements are high in CE-5. In the rendezvous and docking process, a real-time in-beam VLBI technology is required to perform the high-precision orbit measurement of two dynamic targets, the orbiter and the ascender. In addition, the VLBI correlator (CVNScorr) should tackle two-phase centers from two probes simultaneously. In the special power flight phases such as rendezvous and docking, near-moon braking, powered descending, and lunar takeoff, the VLBI high-precision delay model cannot be derived owing to the low accuracy of the predicted orbit. If the conventional data processing method is adopted, the VLBI fringe cannot be obtained. Therefore, the VLBI correlator should have the function of real-time dual-target fringe search and delay model reconstruction. CVNscorr adopts the principle of FX-type software correlation and has the function of dual-target correlation module, multibeacon fringe search, and delay model reconstruction. By taking advantage of the characteristics of TT&C signals from different probes, multiple beacons fringes are automatically searched and the delay values of the two targets are obtained simultaneously to reconstruct the high-precision delay models. CVNScorr uses MPI, GPU, and other technologies to realize parallel computing, and it is run on a CPU+GPU parallel cluster platform. In the CE-5 mission, the real-time processing capability is up to four stations of the Chinese VLBI Network and the postprocessing capability is up to six stations. The real-time data rate reaches 128 Mbps per station, the VLBI delay accuracy reaches 0.4 ns, and the real-time performance is better than 25 s.
Purpose – The purpose of this paper is to examine recent developments pertaining to China’s shadow banking sector. Shadow banking has the potential not only to be a beneficial contributor to continued economic growth, but also to contribute to systematic instability if not properly monitored and regulated. An assessment is made in this paper as to whether shadow banking is beneficial or harmful to China’s economic growth. Design/methodology/approach – The authors start with providing an overview of shadow banking from a global perspective, with information on its recent growth and importance in selected countries. The authors then focus directly on China’s shadow banking sector, with information on the various entities and activities that comprise the sector. Specifically, the authors examine the interconnections between shadow banking and regular banking in China and the growth in shadow banking to overall economic growth, the growth in the money supply and the growth in commercial bank assets. Findings – Despite the wide range in the estimates, the trend in the size of shadow banking in China has been upward over the examined period. There are significant interconnections between the shadow banking sector and the commercial banking sector. Low deposit rate and high reserve requirement ratios have been the major factors driving its growth. Shadow banking has been a contributor, along with money growth, to economic growth. Practical implications – The authors argue that shadow banking may prove useful by diversifying China’s financial sector and providing greater investments and savings opportunities to consumers and businesses throughout the country, if the risks of shadow banking are adequately monitored and controlled. Originality/value – To the authors’ knowledge, this paper is among the few to systematically evaluate the influence of shadow banking on China’s economic growth.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
