A5076835394- Advanced MIMO Systems Optimization
- Human Mobility and Location-Based Analysis
- Online Learning and Analytics
- Advanced Wireless Network Optimization
- Fuel Cells and Related Materials
- Wireless Communication Networks Research
- Electrocatalysts for Energy Conversion
- Advanced battery technologies research
- Cooperative Communication and Network Coding
- PAPR reduction in OFDM
- Anomaly Detection Techniques and Applications
- Catalytic Processes in Materials Science
- Time Series Analysis and Forecasting
- Topic Modeling
- Intelligent Tutoring Systems and Adaptive Learning
- Transportation Planning and Optimization
- Vehicle emissions and performance
- Data Management and Algorithms
- Traffic Prediction and Management Techniques
- Advanced Wireless Communication Techniques
- Advanced Combustion Engine Technologies
- Complex Network Analysis Techniques
- Advanced Graph Neural Networks
- Machine Fault Diagnosis Techniques
- Data Quality and Management
Beijing University of Posts and Telecommunications
2014-2023
Xiamen University
2021-2023
Xiamen University of Technology
2023
Xiangtan University
2018-2022
State Key Laboratory of Networking and Switching Technology
2022
Baotou Teachers College
2022
Ministry of Communications
2017-2018
University of Technology Sydney
2012-2013
Harbin University of Commerce
2013
In modern industrial engineered systems, variant working conditions disturb the distributions of machines' operational data, which results in different feature (DFD) problems for fault prognostics. Domain adaptation (DA) have been proved good at dealing DFD problems, and several deep DA-based methods also proposed prognostics filed. However, existing refer to DA tasks from one condition another, without considerations transferring between datasets under complex conditions. The prior...
With the increasing demands of personalized learning, knowledge tracing has become important which traces students' states based on their historical practices. Factor analysis methods mainly use two kinds factors are separately related to students and questions model states. These total number attempts learning progress hardly highlight impact most recent relevant Besides, current factor ignore rich information contained in questions. In this paper, we propose Multi-Factors Aware...
Deploying femtocell networks achieves great spatial reuse at the price of severe interference from concurrent transmissions. To mitigate downlink base stations (FBSs) to nearby macrocell users (MUEs), power control is employed enable FBSs dynamically reconfigure their allocation based on information obtained exchange between and femtocells. However, lack direct coordination makes cognitive radio (CR) a promising solution management two-tier networks. In this paper we address problem in...
Butanol is considered as the more promising alternative fuel candidate because of its favorable chemical and physical properties over ethanol methanol. In this study, performance emissions a port injected spark ignition engine fueled with butanol‐gasoline blends (0–60 vol % butanol blended gasoline referred G100‐B60), including brake thermal efficiency (BTE), specific consumption (BSFC) carbon monoxide (CO), unburned hydrocarbon (UHC), nitrogen oxide (NO x ), were investigated under various...
In order to improve the spectrum efficiency in femtocell network and mitigate co-tier/cross-tier interference, we propose a novel graph-theoretic scheme based on coloring algorithm for self-adaptive resource allocation femtocells. A dynamic orthogonal sharing between macrocell is utilized proposed reduce cross-tier interference. co-tier graph-based clustering (GCRA) presented. The interference graph of femto-tier built first measurement reports user equipments (FUEs). Then implemented...
Web of Things (WoT) facilitates the discovery and interoperability Internet (IoT) devices in a cyber-physical system (CPS). Moreover, uniform knowledge representation physical resources is quite necessary for further composition, collaboration, decision-making process CPS. Though several efforts have integrated semantics with WoT, such as engineering methods based on semantic sensor networks (SSN), it still could not represent complex relationships between when dynamic composition...
Trajectory User Linking (TUL), which links anonymous trajectories with users who generate them, plays a crucial role in modeling human mobility. Despite significant advancements this field, existing studies primarily neglect the high-order inter-trajectory relationships, represent complex associations among multiple trajectories, manifested through multi-location co-occurrence patterns emerging when intersect at various Points of Interest (POIs). Furthermore, they also overlook variable...
This paper presentsa new simple mobile tracking system based on IEEE802.11wireless signal detection, which can be used for analyzingthe movement of pedestrian traffic.Wi-Fi packets emitted by Wi-Fi enabled smartphones are received at a monitoring station and these contain date, time, MAC address, other information.The number stations, distributed throughout the zone, measure strength.Based location stations data collected traffic analyzed.This information to improve services, such as better...
Explosive increase of industrial data collected from sensors has brought increasing attractions to the data-driven predictive maintenance for machines in cyber-physical systems (CPSs). Since machinery faults are always caused by performance deterioration components, learning deteriorating mode observed sensor facilitates prognostics impeding and predicting remaining useful life (RUL). In modern CPSs, several key indicators (KPIs) monitored detect corresponding fine-grained modes machines....
Identifying group movement patterns of crowds and understanding behaviors are valuable for urban planners, especially when the groups special such as tourist groups. In this paper, we present a framework to discover investigate using mobile phone call detail records (CDRs). Unlike GPS data, CDRs relatively poor in spatial resolution with low sampling rates, which makes it big challenge identify members from thousands tourists. Moreover, since touristic trips not on regular basis, no...
Student Dropout Prediction (SDP) is pivotal in mitigating withdrawals Massive Open Online Courses. Previous studies generally modeled the SDP problem as a binary classification task, providing single prediction outcome. Accordingly, some attempts introduce survival analysis methods to achieve continuous and consistent predictions over time. However, volatility sparsity of data always weaken models' performance. Prevailing solutions rely heavily on pre-processing independent predictive...
In the age of industry 4.0 and smart manufacturing, a large volume sensor data is produced from cyber-physical systems (CPS) prediction remaining useful life (RUL) machine or system becomes crucial for prognostics health management (PHM). Several linear regression deep learning models have been studied to extract features segmented time windows learn degradation patterns. However, distributions are varying between source domain target test domains, due different working conditions...