A5101782306- Mobile Crowdsensing and Crowdsourcing
- Human Mobility and Location-Based Analysis
- Indoor and Outdoor Localization Technologies
- Context-Aware Activity Recognition Systems
- Video Surveillance and Tracking Methods
- Visual Attention and Saliency Detection
- Direction-of-Arrival Estimation Techniques
- Human Pose and Action Recognition
- Transportation Planning and Optimization
- Air Quality Monitoring and Forecasting
- Evacuation and Crowd Dynamics
- Anomaly Detection Techniques and Applications
- Image and Video Quality Assessment
- Gaze Tracking and Assistive Technology
- Pharmacovigilance and Adverse Drug Reactions
- Complex Network Analysis Techniques
- Sparse and Compressive Sensing Techniques
- Neural Networks Stability and Synchronization
- stochastic dynamics and bifurcation
- Transportation and Mobility Innovations
- Non-Invasive Vital Sign Monitoring
- IoT and Edge/Fog Computing
- Vehicle emissions and performance
- Fire Detection and Safety Systems
- Video Analysis and Summarization
Foshan University
2018-2024
Shangqiu First People's Hospital
2024
China Three Gorges University
2023-2024
Ming Chuan University
2013-2023
Nanjing Drum Tower Hospital
2021-2022
Yanbian University
2021
Northwestern Polytechnical University
2014-2019
Chongqing University
2019
Science North
2016
Luoyang Institute of Science and Technology
2015-2016
Community bulletin boards serve an important function for public information sharing in modern society. Posted fliers advertise services, events, and other announcements. However, posted offline suffer from problems such as limited spatial-temporal coverage inefficient search support. In recent years, with the development of sensor-enhanced mobile devices, crowd sensing (MCS) has been used a variety application areas. This paper presents FlierMeet, crowd-powered system cross-space reposting,...
Visual crowdsensing (VCS), which leverages built-in cameras of smart devices to attain informative and comprehensive sensing interesting targets, has become a predominant paradigm mobile (MCS). Compared MCS tasks using other modalities, VCS faces numerous unique issues, such as multi-dimensional coverage needs, data redundancy identification elimination, low-cost transmission, well high processing cost. This paper characterizes the concepts, features, novel application areas VCS,...
Visual crowdsensing is successfully applied in numerous application areas, yet little work has been done on measuring and improving the quality of worker contributed visual data. Rather than evaluating based traditional metrics such as resolution, we focus data diversity, which crucial for a broad stream tasks. Two representative diversity-oriented task types are studied, namely static object imagery evolving event photography. The former aims to collect multi-facet/ aspect low redundant...
Abstract Lacosamide was the first approved third-generation antiepileptic drug. However, real-world data regarding its adverse cardiac reactions in large samples still need to be completed. We evaluated safety profile of lacosamide using Food and Drug Administration Adverse Event Reporting System (FAERS). performed disproportionality analysis computing reporting odds ratio (ROR) as a quantitative metric assess signal lacosamide-related events (AEs) from 2013 Q1 2022 Q4. The considered...
Mobile crowd photographing (MCP) is an emerging area of interest for researchers as the built-in cameras mobile devices are becoming one commonly used visual logging approaches in our daily lives. In order to meet diverse MCP application requirements and constraints sensing targets, a multifacet task model should be defined generic data collection framework. Furthermore, collects pictures distributed way which large number contributors upload whenever wherever it suitable. This inevitably...
Traditionally, vehicle tracking is accomplished using predeployed video camera networks, which relies on stationary cameras and searches for the target from videos. In this paper, we develop CrowdTracking, i.e., a crowd system that people can collaboratively keep track of moving by taking photographs, especially in areas where are deficient. other words, underlying support CrowdTracking mobile crowdsensing. Several novel ideas underpin CrowdTracking. First, be rapidly localized both...
With the surge of varied crowd sensing systems, active user participation becomes a crucial factor that determines whether system can provide good service quality. To encourage in mobile sensing, we propose novel incentive mechanism called CSII -- Cross-Space, multi-Interaction-based Incentive mechanism. estimate value task based on context and historical data. It then has multiple interactions with both requester candidate contributors to suggestion budget select suitable people form worker...
Mobile social media enables people to record ongoing physical events they witness and share them instantaneously online. However, since these event pictures are often individually provided, typically fragmented possess high redundancy. Though there have been studies about visual summarization, pay little attention collaborative sensing, subevent detection, summary. In this paper, we present several building blocks for a cooperative sensing sharing system. We create virtual opportunistic...
Achieving high-accuracy and non-contact heart rate monitoring via radar is a non-trivial task under the interference from respiration its harmonics. In order to eliminate interference, we propose weighted reconstruction method of second harmonic signal heartbeat for estimation. The proposed combines Variational Modal Decomposition (VMD) algorithm with prior information about heartbeat. Namely, after sophisticated endeavor preprocessing, chest wall displacement decomposed into several...
In order to achieve automatic behavioral monitoring of farming animals, this article proposes a convolutional neural network (CNN)-based recognition method for lactating sows. The data streams sows are collected by wearable sensors embedded with 3-D accelerometer and gyroscope used recognize six types behaviors, including movement, drinking, eating, nursing, sleeping, lying. Among these lying, sleeping can be classified as similar static behaviors. Based on the action images constructed...
Pedestrians distracted by smartphones are easy to meet with various dangers when crossing or walking on the street, such as obstacles sidewalk (e.g., temporary parking and road repairing). Existing works about pedestrian safety mostly based sensing capabilities from a single device. The surrounding information that can be learned, however, is quite limited incomplete. Therefore, in many cases cannot detected pedestrians alerted. In this paper, novel system called CrowdWatch proposed, which...
High-resolution and low-complexity direction of arrival (DOA) estimation deserves a warm welcome in real radar sensor. However, achieving this goal is nontrivial. For the DOA uniform linear array (ULA), we offer an efficient approach to reach good compromise between complexity, resolution accuracy. Under covariance fitting framework, construct sparse non-negative least squares (NNLS) that solved by alternating method multipliers (ADMM) at low-computational complexity. The regularization item...
Pervasive computing greatly advances the automatic recognition and understanding of human activities effectively bridges gap between low-level sensor signals high-level human-centric applications. The inherent complexity behavior, however, inevitably poses a huge challenge to design robust activity recognizer, especially in classifying similar activities. In this study, we present hierarchical framework, named HierHAR, that infers on-going multi-stage process for better distinguishing...
Tracking moving objects in a city, such as suspicious vehicles or persons, is important for public safety management. Traditionally, target tracking assisted by the pre-deployed stationary surveillance cameras, which are with insufficient coverage. In this work, we propose different approach called Co-Tracking, real-time system that leverages both citizens' mobile phones and cameras to track collaboratively. Two key techniques focused. Firstly, order accurately assign tasks, Middle Query...
The recognition of human activities plays a central role in bridging the gap between raw sensor signals and high-level pervasive applications. However, complex nature behavior presents great challenge to choice representative features discriminant classification model further makes it quite difficult develop an accurate robust activity recognizer. Random forest benefits from idea bootstrap random feature sampling, while only preliminary experimentation for simple has been previously reported...
Background and Aims NASH is an advanced stage of liver disease accompanied by lipid accumulation, inflammation, fibrosis. Guanine nucleotide-binding protein G(i) subunit alpha-2 (GNAI2) a member the "inhibitory" class α-subunits, recent studies showed that Gnai2 deficiency known to cause reduced weight in mice. However, role GNAI2 hepatocytes, particularly context inflammation metabolism, remains be elucidated. Herein, we aim ascertain function hepatocytes its impact on development NASH....
Bulletin boards serve an important function for public information sharing. Posted fliers advertise services, events and other announcements. However, posted offline suffer from problems such as limited spatial-temporal coverage inefficient search aid. In recent years, with the development of sensor-enhanced mobile devices, crowd sensing has been used in a variety application areas. this paper we present FlierMeet, crowd-powered system crossspace reposting, tagging The tags are auto-labeled...
This paper proposes a generic task-driven data collection framework, named as Crowd Pic, for Mobile Photographing (MCP) - widely used technique in crowd sensing. In order to meet diverse MCP application requirements (e.g. Spatio-temporal contexts, single or multiple shooting angles sensing target), multifaceted task model with constraints is provided Pic. Meanwhile, pre-selection process necessary prevent mobile clients from uploading redundant pictures so reduce the overhead traffic and...
Urban sensing and computing has become hot with the recent surge of Internet Things, smart phones, mobile social networks. Complementary to static infrastructure, crowd (MCS) an important way achieve large-scale urban sensing. However, few studies pay attention public improve city management. In this paper, we propose MCS-based framework facility We use a unique sourced data which collects complaint calls from citizens in Xi'an city, as case study for analyze call four different...