Jianhua Zou’s research while affiliated with Xi'an Jiaotong University and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (37)


Fig. 3: The architecture of DMM
Fig. 4: The architecture of location representer
Fig. 5: The architecture of map matcher
Fig. 6: The architecture of RL optimizer
Fig. 7: The workflow of DMM

+1

DMM: A Deep Reinforcement Learning based Map Matching Framework for Cellular Data
  • Article
  • Full-text available

October 2024

·

79 Reads

·

1 Citation

IEEE Transactions on Knowledge and Data Engineering

·

·

·

[...]

·

Junjie Wu

This paper presents a novel map matching framework that adopts deep learning techniques to map a sequence of cell tower locations to a trajectory on a road network. Map matching is an essential pre-processing step for many applications, such as traffic optimization and human mobility analysis. However, most recent approaches are based on hidden Markov models (HMMs) or neural networks that are hard to consider high-order location information or heuristics observed from real driving scenarios. In this paper, we develop a deep reinforcement learning based map matching framework for cellular data, named as DMM, which adopts a recurrent neural network (RNN) coupled with a reinforcement learning scheme to identify the most-likely trajectory of roads given a sequence of cell towers. To transform DMM into a practical system, several challenges are addressed by developing a set of techniques, including spatial-aware representation of input cell tower sequences, an encoder-decoder based RNN network for map matching model with variable-length input and output, and a global heuristics-driven reinforcement learning based scheme for optimizing the parameters of the encoder-decoder map matching model. Extensive experiments on a large-scale anonymized cellular dataset reveal that DMM provides high map matching accuracy and fast inference time.

Download

Retrieving Similar Trajectories from Cellular Data of Multiple Carriers at City Scale

August 2023

·

16 Reads

·

4 Citations

ACM Transactions on Sensor Networks

Retrieving similar trajectories aims to search for the trajectories that are close to a query trajectory in spatio-temporal domain from a large trajectory dataset. This is critical for a variety of applications, like transportation planning and mobility analysis. Unlike previous studies that perform similar trajectory retrieval on fine-grained GPS data or single cellular carrier, we investigate the feasibility of finding similar trajectories from cellular data of multiple carriers, which provide more comprehensive coverage of population and space. To handle the issues of spatial bias of cellular data from multiple carriers, coarse spatial granularity, and irregular sparse temporal sampling, we develop a holistic system cellSim . Specifically, to avoid the issue of spatial bias, we first propose a novel map matching approach, which transforms the cell tower sequences from multiple carriers to routes on a unified road map. Then, to address the issue of temporal sparse sampling, we generate multiple routes with different confidences to increases the probability of finding truly similar trajectories. Finally, a new trajectory similarity measure is developed for similar trajectory search by calculating the similarities between the irregularly-sampled trajectories. Extensive experiments on a large-scale cellular dataset from two carriers and real-world 1,701-km query trajectories reveal that cellSim provides state-of-the-art performance for similar trajectory retrieval.



ATPP: A Mobile App Prediction System Based on Deep Marked Temporal Point Processes

January 2023

·

145 Reads

·

6 Citations

ACM Transactions on Sensor Networks

Predicting the next application (app) a user will open is essential for improving user experience, e.g., app pre-loading and app recommendation. Unlike previous solutions that only predict which app the user will open, this paper predicts both the next app and the time to open it. Time prediction is essential to avoid loading the next app too early, and consuming unnecessary resources on smartphones. To predict the next app and open time jointly, we model the app usage sequence as a marked temporal point process (MTPP), whose conditional intensity function can capture the probability of a new app usage event. We develop a novel data-driven MTPP-based app prediction system, named ATPP (App Temporal Point Process), which adopts a recurrent neural network architecture to learn the MTPP conditional intensity function for app prediction. ATPP adopts a set of techniques to incorporate the unique features of app prediction in our RNN architecture, including learning the correlated usage behavior of different apps by representation learning, the temporal dependency of app usage by an attention mechanism, and the location-related app usage behavior by feature extraction and fusion layer. We conduct extensive experiments on a large-scale anonymized app usage dataset to verify ATPP's effectiveness.


IncreAuth: Incremental-Learning-Based Behavioral Biometric Authentication on Smartphones

January 2023

·

29 Reads

·

15 Citations

IEEE Internet of Things Journal

Touch behavior biometric has been widely studied for continuous authentication on mobile devices, which provides a more secure authentication in an implicit process. However, the existing touch behavior biometric based authentication systems suffer from two issues. First, the existing touch behavior representation methods are hard to characterize touch operations under complex usage context. Second, the authentication accuracy of existing authentication models is inclined to degrade over time in a long-term real-life usage scenario due to change in data distribution caused by varying touch behavior. Towards this end, in this paper, we develop IncreAuth, an incremental learning based continuous authentication framework, which allows to provide effective stable authentication performance in the long-term smartphone usage scenario. Specifically, we first propose a novel context-aware feature set to characterize touch behavior patterns in complex usage context. Then, we develop an authentication model GBDTNN, which integrates the advantages of gradient boosting decision tree model for processing our high-dimensional feature set and neural network model for efficient online updating. A behavior drift based online updating mechanism is also designed to learn both long-term and short-term touch behavior patterns. To evaluate our framework, we construct a large-scale smartphone usage dataset over 2 months collected from the unconstrained environment. Extensive experiments demonstrate that IncreAuth achieves the state-of-the-art and stable authentication accuracy over time and low system overheads.


CT-Auth: Capacitive Touchscreen-Based Continuous Authentication on Smartphones

January 2023

·

42 Reads

·

6 Citations

IEEE Transactions on Knowledge and Data Engineering

Continuous authentication, which provides identity verification using behavioral biometrics in an implicit and transparent manner, has shown potentials for protecting privacy. As the most common way of human-computer interaction, touch behavior pattern of each user has been proven distinctive and widely adopted for continuous authentication. However, most touch based solutions rely on the touchscreen signals obtained from high-level application programming interfaces, which are hard to characterize fine-grained appearance and contour profile of contact fingertips as well as dynamic sliding information in a touch gesture. In this paper, we propose a continuous authentication framework called CT-Auth, which leverages raw capacitive value collected from capacitive touchscreen on smartphone as a descriptor of touch behavior for authentication. Specifically, we first develop a three-dimensional convolution neural network model for capturing intra-gesture spatial-temporal feature and a structure extraction model for capturing structural information between moving fingertips of a touch gesture and touchscreen. A recurrent neural network based model is also applied for capturing temporal patterns among a sequence of touch gestures. To evaluate the effectiveness of our framework, we recruit 100 volunteers over 2 months and collect a large-scale dataset in the unconstrained conditions. Extensive experiments reveal that CT-Auth provides the state-of-the-art authentication accuracy.


MMAuth: A Continuous Authentication Framework on Smartphones Using Multiple Modalities

January 2022

·

98 Reads

·

29 Citations

IEEE Transactions on Information Forensics and Security

With the wide use of smartphones, more private data are collected and saved in the smartphones. This raises higher requirements for secure and effective user authentication scheme. Continuous authentication leverages behavioral biometrics as identity information and shows promising characteristics for user verification in a continuous and passive means. However, most studies require users to operate the smartphones in a specific mobile application or perform user-defined touch operations. This paper studies the continuous authentication on smartphones in the wild, where it is hard to characterize touching behavior accurately due to the complexity of usage context and cross-use of various types of touch gestures. Towards this end, in this paper, we propose a continuous authentication framework using multiple modalities, named as MMAuth, which integrates the heterogeneous information of user identity from multiple modalities (e.g., motion movement pattern, touch dynamics, usage context). A time-extended behavioral feature set (TEB) and a deep learning based one-class classifier (DeSVDD) are developed for performing more accurate authentication. Evaluations are conducted using a novel unconstrained smartphone usage dataset collected from 100 volunteers in real world as well as a public laboratory dataset. Extensive experimental results demonstrate that the state-of-the-art authentication performance of MMAuth in both unconstrained and laboratory environment, and the effectiveness of its two proposed modules (the TEB feature set and the DeSVDD classifier). Additional experiments on system robustness, in terms of usability to different touch gestures, sensitivity to various mobile applications, and scalability to user space, are also provided to examine the applicability of MMAuth.


Rotational motion estimation of non-cooperative target in space based on the 3D point cloud sequence

November 2021

·

19 Reads

·

7 Citations

Advances in Space Research

One of the key tasks for space debris removal is to estimate the rotation motion of non-cooperative targets. Many methods based on the Kalman filter have been proposed for motion estimation. However, they often need continuous tracking feature points, which conflicts with actual tracking conditions. Rodriguez formula can estimate rotation motion without continuous tracking feature points, while still facing the problem of poor estimation quality in the case of changing motion state. To overcome these problems, we propose a novel 3D point cloud sequence based algorithm to estimate the rotation motion parameters, which is composed of a phase of constructing double registration matrix and a phase of solving motion equation. With the point cloud sequence, the first phase proposes a double registration matrix to recover the local trajectory of the selected points, and the velocity information can be derived from the local trajectory. While in the second phase, the position information and velocity information of the local trajectory are substituted into the motion equation to solve the rotation axis direction and angular velocity of the non-cooperative target. Experimental results demonstrate the effectiveness and robustness of the proposed algorithm and its potential applicability for reality.


Decoupled self-supervised label augmentation for fully-supervised image classification

October 2021

·

25 Reads

·

13 Citations

Knowledge-Based Systems

Self-supervised label augmentation has emerged as an effective means to overcome the data scarcity problem for supervised vision tasks. Existing rotation-based self-supervised label augmentation methods either impose or relax the rotation invariance constraint on the primary classifier, which omit necessary supervisory information and may degrade the classification performance depending on the given working data. To overcome this problem, we propose a decoupled self-supervised label augmentation method to enhance the feature representation for fully-supervised image classification. Experimental results on diverse datasets demonstrate that the proposed method consistently outperforms state-of-the-art data augmentation methods. The proposed method is also complementary to conventional data augmentation methods, such as AutoAugment and Fast AutoAugment.



Citations (28)


... With the development of machine learning, data-driven methods have emerged as prominent options. A deep reinforcement learning framework for map-matching cellular data is proposed in [16]. In [17], data sparsity and noise are addressed through deep learning-based data augmentation. ...

Reference:

Map‐matching for cycling travel data in urban area
DMM: A Deep Reinforcement Learning based Map Matching Framework for Cellular Data

IEEE Transactions on Knowledge and Data Engineering

... As a result, such an assumption leads to the loss of contextual information, and thus reduces the map matching accuracy. Second, under the assumption of Markov property, they can only consider the heuristics observed from local information of current location samples (e.g., preferring major roads near the current sample [19], taking the shortest path between the last and current samples [8]). Third, they often assume to follow the shortest paths between the surrounding roads of two samples, which leads to extensive searches of the shortest paths during inference. ...

Retrieving Similar Trajectories from Cellular Data of Multiple Carriers at City Scale
  • Citing Article
  • August 2023

ACM Transactions on Sensor Networks

... Namun, meskipun dianggap aman, autentikasi biometrik tidak luput dari berbagai tantangan dan risiko keamanan [3]. Penelitian menunjukkan bahwa sistem ini rentan terhadap berbagai serangan, seperti spoofing, brute force, dan eksploitasi zero-day, yang memanfaatkan kelemahan dalam implementasi sistem biometric [4]. Celah seperti Cancel-After-Match-Fail (CAMF) dan Match-After-Lock (MAL) memungkinkan peretas untuk mencoba berbagai kombinasi biometrik tanpa terdeteksi, sementara ancaman dari malware seperti Chameleon menunjukkan bagaimana perangkat lunak berbahaya dapat melumpuhkan kunci biometrik [5]. ...

IncreAuth: Incremental-Learning-Based Behavioral Biometric Authentication on Smartphones
  • Citing Article
  • January 2023

IEEE Internet of Things Journal

... In contemporary consumer electronic devices, touch localization on a capacitive touchscreen displays rely on changes in the electrical properties of carefully arranged material layers when a finger touches the screen. In essence, the location is estimated by determining the 'touch cell' where there is maximum variation in the capacitance [13]. In contrast, contactless methods can also be used if accurate distance [14]- [16] and/or angle information [17] of the finger is known relative to sensors with known positions. ...

CT-Auth: Capacitive Touchscreen-Based Continuous Authentication on Smartphones
  • Citing Article
  • January 2023

IEEE Transactions on Knowledge and Data Engineering

... This restricts the use of this model on other mobile devices. MMAuth offers high reliability and minimal system overhead in the application context and achieves an EER of 14.9% and 8.8% respectively [22]. ...

MMAuth: A Continuous Authentication Framework on Smartphones Using Multiple Modalities
  • Citing Article
  • January 2022

IEEE Transactions on Information Forensics and Security

... DRL-based Control. DRL has been applied in many applications, such as network planning [17], cellular data analytics [18], sensor energy management [43], mobile app prediction [44,45] and building energy optimization [46,47]. In particular, DRL techniques have demonstrated the potential optimal irrigation controls. ...

ATPP: A Mobile App Prediction System Based on Deep Marked Temporal Point Processes

... 因此目标函数式 (10)改写为 Fig. 4 Comparative analysis of the estimation errors of motion parameters by DRM [15] , RPM [16] , TM [10] , and proposed method for Fig. 5 Analysis of the estimation errors of DRM [15] , RPM [16] , TM [10] , and proposed method for motion parameters under different Gaussian noise standard deviations for satellite A for 252 different motion states. (a) Mean error of spin angular velocity; ...

Rotational motion estimation of non-cooperative target in space based on the 3D point cloud sequence
  • Citing Article
  • November 2021

Advances in Space Research

... In addition, in the final measurement, the improved algorithm uses a fusion measurement method to connect the target appearance and motion information through linear weighting to perform correlation measurements, so as to improve the matching degree between detection and tracking trajectories. This process can be described in Eq. (12). ...

Decoupled self-supervised label augmentation for fully-supervised image classification
  • Citing Article
  • October 2021

Knowledge-Based Systems

... To further improve map matching performance, we exploit global heuristics observed from real driving scenarios, such as preferring the routes with more proportion of major roads, less frequency of turns and U-turns. To incorporate these heuristics, inspired by the recent advance of reinforcement learning (RL) approaches [24], [28]- [30], we customize the basic map matching model into a reinforcement learning framework. ...

DeepAPP: A Deep Reinforcement Learning Framework for Mobile Application Usage Prediction

IEEE Transactions on Mobile Computing