A5085877806- Time Series Analysis and Forecasting
- Data Stream Mining Techniques
- Anomaly Detection Techniques and Applications
- Data Management and Algorithms
- Cancer survivorship and care
- Additive Manufacturing and 3D Printing Technologies
- 3D IC and TSV technologies
- Music and Audio Processing
- Context-Aware Activity Recognition Systems
- Electronic Packaging and Soldering Technologies
- Mental Health Research Topics
- Mental Health via Writing
- Advanced Text Analysis Techniques
- Traffic Prediction and Management Techniques
University of Surrey
2014-2018
Our world and our lives are changing in many ways. Communication, networking, computing technologies among the most influential enablers that shape today. Digital data connected worlds of physical objects, people, devices rapidly way we work, travel, socialize, interact with surroundings, they have a profound impact on different domains, such as healthcare, environmental monitoring, urban systems, control management applications, several other areas. Cities currently face an increasing...
The term Internet of Things (IoT) refers to the interaction and communication between billions devices that produce exchange data related real-world objects (i.e. things). Extracting higher level information from raw sensory captured by representing this as machine-interpretable or human-understandable has several interesting applications. Deriving into representations demands mechanisms find, extract, characterize meaningful abstractions data. This then have be presented in a human and/or...
The emergence of the Internet Things (IoT) has led to production huge volumes real-world streaming data. We need effective techniques process IoT data streams and gain insights actionable information from observations measurements. Most existing approaches are application or domain dependent. propose a method which determines how many different clusters can be found in stream based on distribution. After selecting number clusters, we use an online clustering mechanism cluster incoming...
Internet of Things is a generic term that refers to interconnection real-world services which are provided by smart objects and sensors enable interaction with the physical world. Cities also evolving into large interconnected ecosystems in an effort improve sustainability operational efficiency city infrastructure. However, it often difficult perform real-time analysis amount heterogeneous data sensory information various sources. This paper describes framework for semantic annotation...
With the growing popularity of information and communications technologies sharing integration, cities are evolving into large interconnected ecosystems by using smart objects sensors that enable interaction with physical world. However, it is often difficult to perform real-time analysis amount on heterogeneous data sensory provided various resources. This paper describes a framework for semantic annotation aggregation streams support dynamic integration Web advanced message queuing...
Effective symptom management is a critical component of cancer treatment. Computational tools that predict the course and severity these symptoms have potential to assist oncology clinicians personalize patient's treatment regimen more efficiently provide aggressive timely interventions. Three common inter-related in patients are depression, anxiety, sleep disturbance. In this paper, we elaborate on efficiency Support Vector Regression (SVR) Non-linear Canonical Correlation Analysis by...
Recent advancements in sensing, networking technologies and collecting real-world data on a large scale from various environments have created an opportunity for new forms of services applications.This is known under the umbrella term Internet Things (IoT).Physical sensor devices constantly produce very amounts data.Methods are needed which give raw measurements meaningful interpretation building automated decision support systems.To extract actionable information data, we propose method...
Analysis and processing of time-series data has been studied over the past decades resulted in several promising algorithms. Clustering continuous is an interesting subset unsupervised learning models to process categorise data. Over a long period with large number samples most conventional streams will converge Gaussian distributions. The existing clustering methods for are usually suitable this type However, growing volumes real world observation measurements, (i.e. Internet Things data),...