Outputs (462)

Multi-precision convolutional neural networks on heterogeneous hardware (2018)
Presentation / Conference Contribution

Fully binarised convolutional neural networks (CNNs) deliver very high inference performance using single-bit weights and activations, together with XNOR type operators for the kernel convolutions. Current research shows that full binarisation result... Read More about Multi-precision convolutional neural networks on heterogeneous hardware.

Simultaneous multiprocessing in a software-defined heterogeneous FPGA (2018)
Journal Article

Heterogeneous chips that combine CPUs and FPGAs can distribute processing so that the algorithm tasks are mapped onto the most suitable processing element. New software-defined high-level design environments for these chips use general purpose langua... Read More about Simultaneous multiprocessing in a software-defined heterogeneous FPGA.

Incommensurate Compositions (2018)
Digital Artefact

An output from a collaborative project with Architects and Crystallographers from Cardiff University to explore creative opportunities within crystallographic data-sets and modelling algorithms.

These compositions are made with a software tool, co... Read More about Incommensurate Compositions.

A trust-based intrusion detection system for mobile RPL based networks (2018)
Presentation / Conference Contribution

Successful deployment of Low power and Lossy Networks (LLNs) requires self-organising, self-configuring, security, and mobility support. However, these characteristics can be exploited to perform security attacks against the Routing Protocol for Low-... Read More about A trust-based intrusion detection system for mobile RPL based networks.

Composing with crystallography (2018)
Exhibition / Performance

Collaborative project with Architects and Crystallographers from Cardiff University to explore creative opportunities within crystallographic data-sets and modelling algorithms. This composition research developed and extended their Leverhulme funded... Read More about Composing with crystallography.

An open-air analysis of the air pollutants in malaysian atmosphere and experts engagement workshop on smart mobility (2018)
Presentation / Conference Contribution

Due to increase in population and modern urbanization, air pollution has become one of the primary culprits that has catastrophic effects on the health and environment. Cities are looking forward to undertaking smart and sustainable mobility initiati... Read More about An open-air analysis of the air pollutants in malaysian atmosphere and experts engagement workshop on smart mobility.

Log based method for faster IoT queries (2017)
Presentation / Conference Contribution

With increase in size of Internet of Things IoT device networks and applications, tremendous increase is witnessed in IoT data. Efficient storage and querying of this data is of major concern. This paper addresses the issue of faster query processing... Read More about Log based method for faster IoT queries.

DWAHP: workload aware hybrid partitioning and distribution of RDF data (2017)
Presentation / Conference Contribution

Proliferation of RDF data has reached to a peak where data is partitioned across multiple nodes. Significant contribution for developing solutions to manage RDF data in distributed environment is witnessed in recent years. We propose a workload aware... Read More about DWAHP: workload aware hybrid partitioning and distribution of RDF data.

Deformable paint palette: Actuated force controls for digital painting (2017)
Presentation / Conference Contribution

This work-in-progress presents early findings on using deformable interfaces with force input to enhance interactions with digital painting applications. Our prototype uses deformation to submerge controls to represent paint pots, and emerge controls... Read More about Deformable paint palette: Actuated force controls for digital painting.

Sentiment analysis of citations using word2vec (2017)
Preprint / Working Paper

Citation sentiment analysis is an important task in scientific paper analysis. Existing machine learning techniques for citation sentiment analysis are focusing on labor-intensive feature engineering, which requires large annotated corpus. As an auto... Read More about Sentiment analysis of citations using word2vec.