Xi Zhao

• Ph.D.
• Professor at Xi'an Jiaotong University

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 Mar...

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...

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...

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. Howeve...

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 t...

Physical activity applications (PA apps) offer low-cost, time-space-independent interventions that make it possible to promote public health. To increase users’ stickiness, the commercially available PA apps usually provide various services to adapt to different app usage patterns of users, thus helping them develop the habit of using apps. However...

Promoting mobility behavior can benefit individuals’ well-being and regional economic vitality. This study focuses on the role of a new ICT-related factor, smartphone usage feedback in promoting users’ mobility behavior. Though smartphone usage feedback is designed to help users to regulate their smartphone use, we find it also has the potential to...

In the emerging platform economy, blockchain technologies are reshaping the digital economy. Moreover, disintermediation and decentralization have broken new ground for platform organizations and management mechanisms and instigated the concept of a DAO (Decentralized Autonomous Organization). Recent literature on operations management has called f...

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 m...

This paper aims to predict a set of apps a user will open on her mobile device in the next time slot. Such an information is essential for many smartphone operations, e.g., app pre-loading and content pre-caching, to improve user experience. However, it is hard to build an explicit model that accurately captures the complex environment context and...

Face recognition under drastic pose drops rapidly due to the limited samples during the model training. In this paper, we propose a pose-autoaugment face recognition framework (PAFR) based on the training of a Convolutional Neural Network (CNN) with multi-view face augmentation. The proposed framework consists of three parts: face augmentation, CNN...

Emergency management (EM) has always been a concern of people from all walks of life due to the devastating impacts emergencies can have. The global outbreak of COVID-19 in 2020 has pushed EM to the top topic. As mobile phones have become ubiquitous, many scholars have shown interest in using mobile phone data for EM. This paper presents a systemat...

The low quality of data in information systems poses enormous risks to business operations and decision making. In this paper, a single-period resource allocation problem for controlling the information system's data quality problem is considered. We develop a Data-Quality-Petri net to capture the process through which data quality problem generate...

Different variants of the Vehicle Routing Problem (VRP) have been studied for decades. State-of-the-art methods based on local search have been developed for VRPs, while still facing problems of slow running time and poor solution quality in the case of large problem size. To overcome these problems, we first propose a novel deep reinforcement lear...

In light of individuals' increasing concern regarding their physical health, mobile health applications (mHealth Apps) have gained popularity in recent years as important tools for addressing health problems. However, users find it challenging to choose appropriate mHealth Apps, as these Apps incorporate diverse behavior change techniques (BCTs), a...

This paper aims at analyzing the growth rate of visits for 157 tourist attractions in response to the National Day and Mid-autumn Festival in Shandong, China, and investigating whether and to what extent it is possible to identify some influencing destination attributes. We find there exists a serious imbalance in the growth rate for various attrac...

Transactional Theory of Stress (TTS) suggests that appraisal and coping processes determine the impacts of stressors. Prior research applies TTS at the technology level, where the presence of information and communication technologies (ICTs) triggers the above-mentioned two processes and technostress creators are appraisals of ICTs. We apply TTS at...

Background: Although mobile app-delivered physical activity (PA) interventions have the potential to promote exercise, poor adherence to these apps is a common issue impeding their effectiveness. Gaining insights into the factors that influence PA app adherence is an important priority for app developers and intervention designers. Objective: Th...

This paper aims to predict the apps a user will open on her mobile device next. Such an information is essential for many smartphone operations, e.g., app pre-loading and content pre-caching, to save mobile energy. However, it is hard to build an explicit model that accurately depicts the affecting factors and their affecting mechanism of time-vary...

Wireless Sensor Network (WSN) is an emerging technology that has attractive intelligent sensor-based applications. In these intelligent sensor-based networks, control-overhead management and elimination of redundant inner-network transmissions are still challenging because the current WSN protocols are not data redundancy-aware. The clustering arch...

Testing phase augmentation is a fast way to further improve the performance of image classification when CNN (Convolutional Neural Network) is already trained for hours. Limited attempts have been made to find the best augmentation strategy for testing set. We propose a reinforcement learning based augmentation strategy searching method for testing...

Underwater Acoustic Network (UAN) is an emerging technology with attractive applications. In such type of networks, the control-overhead, redundant inner-network transmissions management, and data-similarity are still very challenging. The cluster-based frameworks manage the control-overhead and redundant inner-network transmissions persuasively. H...

The field of psychology is increasingly interested in daily spatial behavior, regarded as the diversity and regularity of people visiting various places. By combining survey data on the personality traits of 243 college students with their mobility patterns extracted from smartphone records, the current study examined the relationships between the...

Retrieving similar trajectories from a large trajectory dataset is important for a variety of applications, like transportation planning and mobility analysis. Unlike previous works based on fine-grained GPS trajectories, this paper investigates the feasibility of identifying similar trajectories from cellular data observed by mobile infrastructure...

As a common choice strategy for consumers, variety-seeking has a direct impact on the business performance of enterprises, and has been studied for decades in management science and marketing research. Existing research tends to find factors which influence variety-seeking by means of questionnaires and laboratory experiments. Based on the importan...

With the slowing growth of the telecommunication market and the intense competition for existing customers, Customer Churn Management has become a crucial task for all mobile network operators. Recommendation models based on customer behaviors are widely used by operators to provide diverse telecom tariff packages for suitable people and thus impro...

Location recommendation in a city district plays an essential role for people city experience. Most existing studies consider user mobility data as implicit feedback, and adopt collaborative filtering frameworks to make recommendations. However, most of them treat all unvisited locations as negative examples. This method fails to provide details ab...

The Internet of Underwater Things (IoUT) is an evolving class of Internet of Things and it is considered the basic unit for the development of smart cities. To support the idea of IoUT, an Underwater Sensor Network (USN) has emerged as a potential technology that has attractive and updated applications for underwater environment monitoring. In such...

As video blogs become favorable to the commonage, egocentric videos generate tremendous big video data, which capture a large number of interpersonal social events. There are significant challenges on retrieving rich social information, such as human identities, emotions and other interaction information from these massive video data. Limited metho...

Understanding why individuals behave unethically is an important topic for both theory and practice, especially nowadays when people experience many stressful events. The current research aims at examining the relationship between peoples’ experienced stress and their attitude towards unethical consumption behavior, and the underlying mechanism. Em...

Travel party size has been shown to affect tourists' behavior. However, due to a previous lack of big-data analytical techniques, there remains limited research on the effect of party size on tourist movements from a large-scale perspective. This paper presents an empirical case study on the understanding of tourist movement patterns from the persp...

It is important for an investor to determine the most suitable shop type (e.g., restaurant, cafe) given a location. Traditionally, investors determine shop types based on their subjective judgments and perceptions. However, insufficient information and cognitive limitation often lead to flawed decisions and increase investment risks. With advances...

Facial landmarking locates the key facial feature points on facial data, which provides not only information on semantic facial structures, but also prior knowledge for other kinds of facial analysis. However, most of the existing works still focus on the 2D facial image which may suffer from lighting condition variations. In order to address this...

P2P online lending platforms have become increasingly developed. However, these platforms may suffer a serious loss caused by default behaviors of borrowers. In this paper, we present an effective default behavior prediction model to reduce default risk in P2P lending. The proposed model uses mobile phone usage data, which are generated from widely...

P2P online lending platforms provide services where individuals lend money to others without the involvement of traditional financial institutions. Due to its convenience, the platforms have gained in popularity. However, these platforms may suffer a significant loss if they cannot make good loan decisions based on default prediction results. In th...

Modern supply chain is a complex system and plays an important role for different sectors under the globalization economic integration background. Supply chain management system is proposed to handle the increasing complexity and improve the efficiency of flows of goods. It is also useful to prevent potential frauds and guarantee trade compliance....

In this paper, we propose a novel approach for 3D face reconstruction from multi-facial images. Given original pose-variant images, coarse 3D face templates are initialized to reconstruct a refined 3D face mesh in an iteration manner. Then, we warp original facial images to the 2D meshes projected from 3D using Sparse Mesh Affine Warp (SMAW). Final...

Facial landmarking locates the key facial feature points on facial data, which provides not only information on semantic facial structures, but also prior knowledge for other types of facial analysis. However, most of the existing works still focus on the 2D facial image which is quite sensitive to the lighting condition changes. In order to addres...

The issue of scheduling interrelated activities is important and of particular concern to design managers. One tool that helps us to solve this issue is the design structure matrix (DSM) which can explicitly represent the information dependencies among interrelated activities. Based on the DSM method, this study presents effective approaches for se...

2D face analysis techniques, such as face landmarking, face recognition and face verification, are reasonably dependent on illumination conditions which are usually uncontrolled and unpredictable in the real world. An illumination robust preprocessing method thus remains a significant challenge in reliable face analysis. In this paper we propose a...

2D face analysis techniques, such as face landmarking, face recognition and face verification, are reasonably dependent on illumination conditions which are usually uncontrolled and unpredictable in the real world. An illumination robust preprocessing method thus remains a significant challenge in reliable face analysis. In this paper we propose a...

Iterative methods are typically utilized for blind image restoration (BIR); however, they are relatively slow, uncertain, and occasionally ill-behaved. This study presents a non-iterative algorithm to estimate the parameters of point spread functions (PSFs), particularly, Class G. We propose a curve model to approximate the normalized spectrum ampl...

Grading of essential hypertension according to blood pressure (BP) level may not adequately reflect clinical heterogeneity of hypertensive patients. This study was carried out to explore clinical phenotypes in essential hypertensive patients using cluster analysis. This study recruited 513 hypertensive patients and evaluated BP variations with ambu...

In this paper, we propose a 3D-2D framework for face recognition that is more practical than 3D-3D, yet more accurate than 2D-2D. For 3D-2D face recognition, the gallery data comprises of 3D shape and 2D texture data and the probes are arbitrary 2D images. A 3D-2D system (UR2D) is presented that is based on a 3D deformable face model that allows re...

People with low vision, Alzheimer's disease, and autism spectrum disorder experience difficulties in perceiving or interpreting facial expression of emotion in their social lives. Though automatic facial expression recognition (FER) methods on 2-D videos have been extensively investigated, their performance was constrained by challenges in head pos...

Egocentric videos are foreseen to be collected pervasively as smart glasses continue emerging in the market. Large amount of interpersonal social events will be recorded and stored online as big video data. However, limited method has been proposed to retrieve useful social information from them, such as other people's identity, emotion and head ge...

We present a fully automatic multimodal 2D + 3D feature-based facial expression recognition approach and demonstrate its performance on the BU-3DFE database. Our approach combines multi-order gradient-based local texture and shape descriptors in order to achieve efficiency and robustness. First, a large set of fiducial facial landmarks of 2D face i...

Face recognition (FR) across illumination variations endeavors to alleviate the effect of illumination changes on human face, which remains a great challenge in reliable FR. Most prior studies focus on normalization of holistic lighting intensity while neglecting or simplifying the mechanism of image color formation. In contrast, we propose in this...

With increasing privacy concerns and security demands present within mobile devices, behavioral biometric solutions, such as touch based user recognition, have been researched as of recent. However, several vital contextual behavior factors (i.e., screen size, physical and application context) and how those effect user identification performance, r...

Coinciding with the surge in popularity and adoption of mobile devices and the ever-expanding capabilities of these devices, the amount of sensitive information accessed and stored has increased exponentially. Inasmuch, these advancements have, and continue to demand great efforts from researchers and the industry alike in terms of improving securi...

We propose a new approach for improving user experience and privacy protection during human-mobile speech interaction by considering factors, such as user identity, application privacy level, usable app access control, and application function class. To integrate these factors into speech recognition on the mobile device, we design and implement a...

With the rise of Internet connected mobile devices, applications have migrated from PCs to mobile computing platforms. An important aspect, payment processing, faces new security challenges from these developments. Inasmuch, these advancements demand efforts from researchers and industry to meet increasing security needs. Threats can ensue from dat...

Those that suffer from macular or vision degenerative diseases report lower levels of ease and ability to participate in daily activities, even when using the most advanced corrective lens technologies. They desire to gain independence in daily tasks, including using everyday machines. Plenty of these machines, such as microwaves, vending machines,...

Behavioral biometrics have recently begun to gain attention for mobile user authentication. The feasibility of touch gestures as a novel modality for behavioral biometrics has been investigated. In this paper, we propose applying a statistical touch dynamics image (aka statistical feature model) trained from graphic touch gesture features to retain...

Motion sensors in smart wristbands/watches have been widely used to sense users' level of movement and animation. Some studies have further recognised activity contexts using these sensors, such as walking, sitting and running. However, in applications requiring understanding of more complex activities such as interactions with other people or obje...

Device scaling engineering is facing major challenges in producing reliable transistors for future electronic technologies. With shrinking device sizes, the total circuit sensitivity to both permanent and transient faults has increased significantly. Research for fault tolerant processors has primarily focused on the conventional processor architec...

Children afflicted with developmental disabilities, namely autism, suffer from a natural aversion to dyadic (i.e., eye-to-eye) contact. Research has shown this aversion to be an early indicator of slower development of linguistic skills, a narrow vocabulary, as well as social issues later in life. In addition, this aversion may also result in the l...

Due to the surge in the number of touch based smart devices, there is a growing need for touch based authentication. Historically, fingerprint has been one of the most effective ways for establishing the uniqueness of an individual's identity. Motivated by the fact that both touch sensing and fingerprint scan can be based on the same capacitive sen...

Employing mobile sensor data to recognize user behavioral activities has been well studied in recent years. However, to adopt the data as a biometric modality has rarely been explored. Existing methods either used the data to recognize gait, which is considered as a distinguished identity feature; or segmented a specific kind of motion for user rec...

As speech based operation becomes a main hand-free interaction solution between human and mobile devices (i.e., smartphones, Google Glass), privacy preserving speaker verification receives much attention nowadays. Privacy preserving speaker verification can be achieved through many different ways, such as fuzzy vault and encryption. Encryption base...

The need for touch based authentication is growing rapidly in smartphones and tablets. Historically, fingerprint has served at its fullest capacity in establishing the uniqueness of an individual’s identity. In this paper we present a novel design of capacitive in-cell TFT-LCDs that supports both fingerprint scan and touch sensing by extending the...

Asymmetric 3-D to 2-D face recognition has gained attention from the research community since the real-world application of 3-D to 3-D recognition is limited by the unavailability of inexpensive 3-D data acquisition equipment. A 3-D to 2-D face recognition system explicitly relies on 3-D facial data to account for uncontrolled image conditions rela...

Avoiding eye contact behavior has been characteristic of individuals with autism. Such behavior prevents intrinsic development of social and communication skills. In this paper we present a directional eye contact reminder system which reminds people with autism to generally focus their eyes in the direction of a human speaker. This device detects...

Data backup and archiving is an important aspect of business processes to avoid loss due to system failures and natural calamities. As the amount of data and applications grow in number, concerns regarding cost efficient data preservation force organizations to scout for inexpensive storage options. Addressing these concerns, we present Tape Cloud,...

Detecting Person-Of-Interest (POI), e.g., fugitives, criminals and terrorists in public spaces is a critical requirement of many law enforcers and police officers. In realty, most law enforcement personnel cannot effectively differentiate POIs from millions of faces and thus demand a portable assistant to recognize faces, in order to take the golde...

Employing mobile sensor data to recognize user behavioral activities has been well studied in recent years. However, exploiting mobile motion data as a novel biometric modality remains a new area. In this paper, we propose two novel methods, a Statistic Method to intuitively apply classifier on the statistic features of the data; and a Trajectory R...

Behavioral biometric on mobile devices has begun to gain attention in recent years and the feasibility of touch gestures as a novel biometric modality has been investigated lately. In this paper, we propose a novel Graphic Touch Gesture Feature (GTGF) to extract the identity traits from the touch traces. The traces' movement and pressure dynamics a...

Due to the increasing popularity of mobile technologies, sensitive user information is often stored on mobile devices. However, the essential task of mobile user authentication is rendered more challenging by the conflicting requirements of security and usability: usable solutions are often insecure, while secure solutions hinder device accessibili...

Asymmetric 3D-2D face recognition (FR) aims to recognize individuals from 2D face images using textured 3D face models in the gallery (or vice versa). This new FR scenario has the potential to be readily deployable in field applications while still keeping the advantages of 3D FR solutions of being more robust to pose and lighting variations. In th...

Illumination alignment is accomplished by relighting or unlighting methods that compensate the appearance differences due to variations in illumination conditions between a pair of face images or among a set of face images. In this paper, we propose a lighting ratio based method that avoids parameter tuning process by using an image-specific low-pa...

Textured 3D face models capture precise facial surfaces along with the associated textures, making it possible for an accurate description of facial activities. In this paper, we present a unified probabilistic framework based on a novel Bayesian Belief Network (BBN) for 3D facial expression and Action Unit (AU) recognition. The proposed BBN perfor...

Prosopagnosia (PA), or the inability to recognize faces, is widespread around the world, with no effective cure for the disease. We propose a wearable system to improve prosopagnosic's daily life. The system utilizes a real-time face recognition application that runs on a smartphone, and a portable eyewear that displays descriptive information when...

Due to hypersensitivity to sound, patients with autism spectrum disorders (ASD) can feel frustrated and even profoundly fearful when talking with multiple speakers. This exacerbates their impairments in social interaction and communication. We propose a fully interactive system that allows ASD patient to focus on a single auditory stream (a person'...

3D2D face recognition is beginning to gain attention from the research community. It takes advantage of 3D facial geometry to normalize the head pose and registers it into a canonical 2D space. In this paper, we present a novel illumination normalization approach for 3D2D face recognition which does not require any training or prior knowledge on th...

Facial expression analysis has interested many researchers in the past decade due to its potential applications in various fields such as human–computer interaction, psychological studies, and facial animation. Three-dimensional facial data has been proven to be insensitive to illumination condition and head pose, and has hence gathered attention i...