Search

Your search keyword '"Zhu, Sulei"' showing total 17 results
Start Over Author "Zhu, Sulei"
17 results on '"Zhu, Sulei"'

2. SanMove: Next Location Recommendation via Self-Attention Network

Author

Li, Huifeng, Wang, Bin, Zhu, Sulei, and Xu, Yanyan

Subjects
Computer Science - Social and Information Networks, Computer Science - Artificial Intelligence, Computer Science - Machine Learning
Abstract

Currently, next location recommendation plays a vital role in location-based social network applications and services. Although many methods have been proposed to solve this problem, three important challenges have not been well addressed so far: (1) most existing methods are based on recurrent network, which is time-consuming to train long sequences due to not allowing for full parallelism; (2) personalized preferences generally are not considered reasonably; (3) existing methods rarely systematically studied how to efficiently utilize various auxiliary information (e.g., user ID and timestamp) in trajectory data and the spatio-temporal relations among non-consecutive locations. To address the above challenges, we propose a novel method named SanMove, a self-attention network based model, to predict the next location via capturing the long- and short-term mobility patterns of users. Specifically, SanMove introduces a long-term preference learning module, and it uses a self-attention module to capture the users long-term mobility pattern which can represent personalized location preferences of users. Meanwhile, SanMove uses a spatial-temporal guided non-invasive self-attention (STNOVA) to exploit auxiliary information to learn short-term preferences. We evaluate SanMove with two real-world datasets, and demonstrate SanMove is not only faster than the state-of-the-art RNN-based predict model but also outperforms the baselines for next location prediction.

Published
2021

3. PG$^2$Net: Personalized and Group Preferences Guided Network for Next Place Prediction

Author

Li, Huifeng, Wang, Bin, Xia, Fan, Zhai, Xi, Zhu, Sulei, and Xu, Yanyan

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Computers and Society
Abstract

Predicting the next place to visit is a key in human mobility behavior modeling, which plays a significant role in various fields, such as epidemic control, urban planning, traffic management, and travel recommendation. To achieve this, one typical solution is designing modules based on RNN to capture their preferences to various locations. Although these RNN-based methods can effectively learn individual's hidden personalized preferences to her visited places, the interactions among users can only be weakly learned through the representations of locations. Targeting this, we propose an end-to-end framework named personalized and group preference guided network (PG$^2$Net), considering the users' preferences to various places at both individual and collective levels. Specifically, PG$^2$Net concatenates Bi-LSTM and attention mechanism to capture each user's long-term mobility tendency. To learn population's group preferences, we utilize spatial and temporal information of the visitations to construct a spatio-temporal dependency module. We adopt a graph embedding method to map users' trajectory into a hidden space, capturing their sequential relation. In addition, we devise an auxiliary loss to learn the vectorial representation of her next location. Experiment results on two Foursquare check-in datasets and one mobile phone dataset indicate the advantages of our model compared to the state-of-the-art baselines. Source codes are available at https://github.com/urbanmobility/PG2Net.

Published
2021

5. Parking Lot Traffic Prediction Based on Fusion of Multifaceted Spatio-Temporal Features.

Author

Zhang, Lechuan, Wang, Bin, Zhang, Qian, Zhu, Sulei, and Ma, Yan

Subjects
TRAFFIC flow, CITY traffic, PARKING lots, TRAFFIC accidents, PREDICTION models, AUTOMOBILE parking, TRAFFIC congestion
Abstract

With the rapid growth of population and vehicles, issues such as traffic congestion are becoming increasingly apparent. Parking guidance and information (PGI) systems are becoming more critical, with one of the most important tasks being the prediction of traffic flow in parking lots. Predicting parking traffic can effectively improve parking efficiency and alleviate traffic congestion, traffic accidents, and other problems. However, due to the complex characteristics of parking spatio-temporal data, high levels of noise, and the intricate influence of external factors, there are three challenges to predicting parking traffic in a city effectively: (1) how to better model the nonlinear, asymmetric, and complex spatial relationships among parking lots; (2) how to model the temporal autocorrelation of parking flow more accurately for each parking lot, whether periodic or aperiodic; and (3) how to model the correlation between external influences, such as holiday weekends, POIs (points of interest), and weather factors. In this context, this paper proposes a parking lot traffic prediction model based on the fusion of multifaceted spatio-temporal features (MFF-STGCN). The model consists of a feature embedding module, a spatio-temporal attention mechanism module, and a spatio-temporal convolution module. The feature embedding module embeds external features such as weekend holidays, geographic POIs, and weather features into the time series, the spatio-temporal attention mechanism module captures the dynamic spatio-temporal correlation of parking traffic, and the spatio-temporal convolution module captures the spatio-temporal features by using graph convolution and gated recursion units. Finally, the outputs of adjacent time series, daily series, and weekly series are weighted and fused to obtain the final prediction results, thus predicting the parking lot traffic flow more accurately and effectively. Results on real datasets demonstrate that the proposed model enhances prediction performance. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

12. Design of dynamic braking control strategy based on EPBi

Author

ZHANG Zhiyang and ZHU Sulei

Subjects
integrated electronic parking break (epbi) system, real vehicle verification, Q1-390, Science (General), control strategy, dynamic braking, slip ratio
Abstract

In order to avoid the dangerous circumstances of the rear wheel anti-locking tail and rollover when the vehicle braked using the parking brake (EPBi) system after the active brake system failed,a dynamic braking control strategy based on EPBi system was proposed in this paper.By determining the related parameters of the EPBi system caliper,the control method of the caliper was defined.What's more,combining with the actual road conditions,the intelligent braking method was realized.At the same time,the experimental strategy under various road conditions was verified on the experimental vehicle equipped with EPBi system.The results of the experiments showed that the dynamic braking control strategy proposed can satisfy enterprise standards and national standards.

Published
2019

13. The design of fall detection algorithm based on multi-feature analysis

Author

Gao Miao and Zhu Sulei

Subjects
fall detection, centroid, Gaussian mixture model, motion coefficient, orientation angle, lcsh:Science (General), lcsh:Q1-390
Abstract

In view of the shortcomings of high detection error rate of the existing fall detection algorithm,an improved fall detection algorithm is proposed.First,the Gaussian mixture model is used to detect the foreground object,and then median filtering and morphological processing are used to extract the foreground object.Based on the use of human aspect ratio and effective area ratio,the change of centroid,orientation angle and motion coefficient are taken as features to judge whether the human has fallen.Compared with traditional algorithnal,experimental results show that the proposed algorithm has higher accuracy,higher sensitivity,low algorithm complexity,and can effectively prevent misjudgment.

Published
2017

14. Design of traffic accident scene alarm system based on radio frequency

Author

Zha Pinxian and Zhu Sulei

Subjects
ComputerSystemsOrganization_COMPUTER-COMMUNICATIONNETWORKS, STM32F429, RFX2401C, traffic accident alarm, lcsh:Science (General), wireless RF communication, lcsh:Q1-390
Abstract

In view of the increased seriousness of the accident caused by another collision on the scene of traffic accident,a traffic accident scene alarm system based on nRF24L01 is proposed.When a vehicle traffic accident occurs,the nRF24L01 module will keep sending wireless signals to the passing vehicles.After the passing vehicles receive the signals,audio codecs controlled by the STM32F429 master play the voice,and remind the drivers to slow down.Compared with the traditional nRF24L01 module,the transmission distance of the wireless signal amplified by RFX2401C can be farther.Compared with the signal of by light or broadcast,the wireless signal has strong penetration and strong anti-interference ability.Experiments show that the system can achieve long distance reminder to prevent another collision.

Published
2017

15. Design about position and display of GPS based on singlechip

Author

WU Dongdong and ZHU Sulei

Subjects
GPS module, singlechip, lcsh:Science (General), serial communications, lcsh:Q1-390
Abstract

GPS is used in ships,vehicles,aircraft and other moving objects.GPS also has the important application in vehicle monitoring system.However,with the expansion of the specialized functions of GPS,its high cost makes so many ordinary consumers unbearable.This paper proposes a simple design of GPS based on singlechip.The design Improves the basic utility functions of system and adds the speed and mileage measurement.GPS module uses the differential technology to improve the positioning accuracy.Therefore,the navigation device is compact,easy to carry and of high precision positioning.Through getting the data of 3D coordinates from the observation point and the factor of position accuracy,the average of which is less than five,indicating that the position accuracy can be improved by differential technology to achieve the desired range.At last,the feasibility of this design is verified through the current data tested in the outdoors.

Published
2016

16. The performances comparison of ROF systems based on intensity modulation and phase modulation

Author

XU Guan, WU Xiangnong, ZHANG Jing, Yin Ye, ZHU Sulei, and ZHANG Qian

Subjects
optical carrier suppression, ROF system, lcsh:Science (General), intensity modulation, phase modulation, lcsh:Q1-390
Abstract

According to the researches of transmitting downlink signal based on optical carrier suppression, we demonstrate two different ROF systems, one is based on intensity modulation to suppress the optical carrier, another is using phase modulation to generate sidebands to transmit the downlink signal. Simulation results prove the validity and reliability of the systems. A comparative study is carried out to the advantages and disadvantages of the transmission performance of both systems according to the spectra, the parameter of Q value, eye diagrams and BER curve, meanwhile the effectiveness and reliability of system are verified.

Published
2012

Catalog

Books, media, physical & digital resources
See catalog results