A5031674501- Human Mobility and Location-Based Analysis
- Data Management and Algorithms
- Building Energy and Comfort Optimization
- Transportation Planning and Optimization
- Smart Parking Systems Research
- Transportation and Mobility Innovations
- Video Surveillance and Tracking Methods
- Facilities and Workplace Management
- Green IT and Sustainability
- Solar Radiation and Photovoltaics
- Energy Load and Power Forecasting
- Personal Information Management and User Behavior
- Impact of Light on Environment and Health
- Air Quality Monitoring and Forecasting
- Mental Health Research Topics
- Caching and Content Delivery
- Data Mining Algorithms and Applications
- Traffic Prediction and Management Techniques
- Multimedia Communication and Technology
- Robotic Path Planning Algorithms
- Urban Transport and Accessibility
- Flow Experience in Various Fields
- Stock Market Forecasting Methods
- Peer-to-Peer Network Technologies
- Online Learning and Analytics
Central Queensland University
2023-2024
RMIT University
2017-2023
MIT University
2018-2023
American International University-Bangladesh
2011-2015
Generative Adversarial Networks (GANs) have shown remarkable success in producing realistic-looking images the computer vision area. Recently, GAN-based techniques are to be promising for spatio-temporal-based applications such as trajectory prediction, events generation, and time-series data imputation. While several reviews GANs been presented, no one has considered addressing practical challenges relevant spatio-temporal data. In this article, we conducted a comprehensive review of recent...
In this paper, we introduce an integrated smart parking system. The proposed system brings multiple service providers together under a unified platform aiming to provide one-stop information services the commuters in city. However, adaptation of such is prone tempering while massive amount data shared among different parties which raise concerns related trust and performance. To address challenge, propose blockchain-based architecture specific systems. Finally, present set design principles...
The study of student engagement has attracted growing interests to address problems such as low academic performance, disaffection, and high dropout rates. Existing approaches measuring typically rely on survey-based instruments. While effective, those are time-consuming labour-intensive. Meanwhile, both the response rate quality survey usually poor. As an alternative, in this paper, we investigate whether can infer predict at multiple dimensions, just using sensors. We hypothesize that...
Accurate forecasting of regional solar photovoltaic power (SPVP) generation is essential for efficient energy management and planning. Existing approaches have shown the effectiveness decomposing time series to model stochastic variability in SPVP data. However, these limitations extracting exploiting both spatial temporal information from complex high-dimensional data multiple sources with intricate relationships, which can impact accuracy predictions. In this paper, we propose a novel...
The study of student engagement has attracted growing interests to address problems such as low academic performance, disaffection, and high dropout rates. Existing approaches measuring typically rely on survey-based instruments. While effective, those are time-consuming labour-intensive. Meanwhile, both the response rate quality survey usually poor. As an alternative, in this paper, we investigate whether can infer predict at multiple dimensions, just using sensors. We hypothesize that...
Seating location in the classroom can affect student engagement, attention and academic performance by providing better visibility, improved movement, participation discussions. Existing studies typically explore how traditional seating arrangements (e.g. grouped tables or rows) influence students' perceived without considering group behaviours under more flexible arrangements. Furthermore, survey-based measures of engagement are prone to subjectivity various response bias. Therefore, this...
Data Trusts are an important emerging approach to enabling the much wider sharing of data from many different sources and for purposes, backed by confidence clear unambiguous governance. combine technical infrastructure with governance framework a legal trust. The concept Trust applied specifically spatial offers significant opportunities new future applications, addressing some longstanding barriers sharing, such as location privacy sovereignty. This paper introduces explores 'spatial...
Existing research on parking availability sensing mainly relies extensive contextual and historical information. In practice, the of such information is a challenge as it requires continuous collection sensory signals. this study, we design an end-to-end transfer learning framework for to predict occupancy in areas which data insufficient feed into data-hungry models. This overcomes two main challenges: 1) many real-world cases cannot provide enough most existing data-driven models, 2)...
Stock market has become one of the major components economy not only in developed countries but also third world developing countries. Making decision stock is really easy because a lot factors are involved with every choice we make. Therefore, analysis required to make an optimal move on which may involve price trend, market's nature, company's stability, different news and rumors about stocks etc. The objective this study extract fundamental information from relevant sources use them...
In this paper, we address the neighborhood identification problem in presence of a large number heterogeneous contextual features. We formulate our research as queue wait time prediction for taxi drivers at airports and investigate factors related to time, weather, flight arrivals, trips. The neighborhood-based methods have been applied type previously. However, failure capture relevant their weights during calculation neighborhoods can make existing ineffective. Specifically, driver...
Workplace occupancy detection is becoming increasingly important in large Activity Based Work (ABW) environments as it helps building and office management understand the utilisation potential benefits of shared workplace. However, existing sensor-based technologies detect workstation indoor spaces require extensive installation hardware maintenance incurring ongoing costs. Moreover, accuracy can depend on specific seating styles workers since sensors are usually placed under table or...
One of the core challenges in open-plan workspaces is to ensure a good level concentration for workers while performing their tasks. Hence, being able infer levels will allow building designers, managers, and estimate what effect different layouts have find an optimal one. In this research, we present ambient-physical system investigate inference problem. Specifically, deploy series pervasive sensors capture various ambient physical signals related perceived at work. The practicality our has...
This paper addresses the problem of taxi-passenger queue context prediction using neighborhood based methods. We capture taxi drivers' knowledge on how they move in terms temporal driver-knowledge deviation (TDKD). Then a TDKD-aided feature importance scheme is introduced for prediction. apply our proposed to predict different contexts at busy international airport New York. argue that incorporation calculating significantly improves quality selected neighborhood, thus boosting accuracy. The...
Inferring human mental state (e.g., emotion, depression, engagement) with sensing technology is one of the most valuable challenges in affective computing area, which has a profound impact all industries interacting humans. Self-report common way to quantify how people think, but prone subjectivity and various responses bias. It usually used as ground truth for prediction. In recent years, many data-driven machine learning models are built based on self-report annotations target value. this...