All Outputs (12)

Reproducibility in machine Learning-Based studies: An example of text mining (2017)
Presentation / Conference Contribution
Olorisade, B. K., Brereton, P., & Andras, P. (2017, August). Reproducibility in machine Learning-Based studies: An example of text mining. Presented at ICML 2017 RML Workshop: Reproducibility in Machine Learning, Sydney, Autralia

Reproducibility is an essential requirement for computational studies including those based on machine learning techniques. However, many machine learning studies are either not reproducible or are difficult to reproduce.
In this paper, we consider... Read More about Reproducibility in machine Learning-Based studies: An example of text mining.

A robust data-driven approach to the decoding of pyloric neuron activity (2017)
Presentation / Conference Contribution
dos Santos, F., Andras, P., Collins, D., & Lam, K. (2017, October). A robust data-driven approach to the decoding of pyloric neuron activity. Presented at 2017 IEEE International Workshop on Signal Processing Systems (SiPS), Lorient, France

The combination of intra and extra-cellular recording of small neuronal circuits such as stomatogastric nervous systems of the crab (Cancer borealis) is well documented and routinely practised. Voltage sensitive dye imaging (VSDi) is a promising tech... Read More about A robust data-driven approach to the decoding of pyloric neuron activity.

Towards an Accurate Identification of Pyloric Neuron Activity with VSDi (2017)
Presentation / Conference Contribution
dos Santos, F., Andras, P., & Lam, K. (2017, September). Towards an Accurate Identification of Pyloric Neuron Activity with VSDi. Presented at ICANN 2017: 26th International Conference on Artificial Neural Networks, Alghero, Italy

Voltage-sensitive dye imaging (VSDi) which enables simultaneous optical recording of many neurons in the pyloric circuit of the stomatogastric ganglion is an important technique to supplement electrophysiological recordings. However, utilising the te... Read More about Towards an Accurate Identification of Pyloric Neuron Activity with VSDi.

A multiresolution approach to the extraction of the pyloric rhythm (2017)
Presentation / Conference Contribution
dos Santos, F., Andras, P., & Lam, K. (2017, July). A multiresolution approach to the extraction of the pyloric rhythm. Presented at 2017 40th International Conference on Telecommunications and Signal Processing (TSP), Barcelona, Spain

This paper describes our work toward the development of a computationally robust methodology to identify the pyloric neurons in the stomatogastric ganglion of Cancer pagurus using voltage-sensitive dye imaging. The multi-resolution signal decompositi... Read More about A multiresolution approach to the extraction of the pyloric rhythm.

Locally Excited State–Charge Transfer State Coupled Dyes as Optically Responsive Neuron Firing Probes (2017)
Journal Article
Sirbu, D., Butcher, J. B., Waddell, P. G., Andras, P., & Benniston, A. C. (2017). Locally Excited State–Charge Transfer State Coupled Dyes as Optically Responsive Neuron Firing Probes. Chemistry - A European Journal, 23(58), 14639-14649. https://doi.org/10.1002/chem.201703366

A selection of NIR-optically responsive neuron probes was produced comprising of a donor julolidyl group connected to a BODIPY core and several different styryl and vinylpyridinyl derived acceptor moieties. The strength of the donor–acceptor interact... Read More about Locally Excited State–Charge Transfer State Coupled Dyes as Optically Responsive Neuron Firing Probes.

Open-ended evolution in cellular automata worlds (2017)
Presentation / Conference Contribution
Andras, P. (2017, September). Open-ended evolution in cellular automata worlds. Presented at ECAL 2017, the Fourteenth European Conference on Artificial Life, Lyon, France

Open-ended evolution is a fundamental issue in artificial life research. We consider biological and social systems as a flux of interacting components that transiently participate in interactions with other system components as part of these systems.... Read More about Open-ended evolution in cellular automata worlds.

A systematic mapping study of empirical studies on software cloud testing methods (2017)
Presentation / Conference Contribution
Ahmad, A. A.-S., Brereton, P., & Andras, P. (2017, July). A systematic mapping study of empirical studies on software cloud testing methods. Presented at 2017 IEEE International Conference on Software Quality, Reliability and Security Companion (QRS-C), Prague, Czech Republic

Context: Software has become more complicated, dynamic, and asynchronous than ever, making testing more challenging. With the increasing interest in the development of cloud computing, and increasing demand for cloud-based services, it has become ess... Read More about A systematic mapping study of empirical studies on software cloud testing methods.

Using supervised machine learning algorithms to detect suspicious URLs in online social networks (2017)
Presentation / Conference Contribution
Al-Janabi, M., Quincey, E. D., & Andras, P. (2017, July). Using supervised machine learning algorithms to detect suspicious URLs in online social networks. Presented at 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining 2017, Sydney, Australia

The increasing volume of malicious content in social networks requires automated methods to detect and eliminate such content. This paper describes a supervised machine learning classification model that has been built to detect the distribution of m... Read More about Using supervised machine learning algorithms to detect suspicious URLs in online social networks.

A systematic analysis of random forest based social media spam classification (2017)
Presentation / Conference Contribution
Al-Janabi, M., & Andras, P. (2017, August). A systematic analysis of random forest based social media spam classification. Presented at NSS: International Conference on Network and System Security, Helsinki, Finland

Recently random forest classification became a popular choice machine learning applications aimed to detect spam content in online social networks. In this paper, we report a systematic analysis of random forest classification for this purpose. We as... Read More about A systematic analysis of random forest based social media spam classification.

Reproducibility of studies on text mining for citation screening in systematic reviews: evaluation and checklist (2017)
Journal Article
Olorisade, B. K., Brereton, P., & Andras, P. (2017). Reproducibility of studies on text mining for citation screening in systematic reviews: evaluation and checklist. Journal of Biomedical Informatics, 73, 1-13. https://doi.org/10.1016/j.jbi.2017.07.010

Context
Independent validation of published scientific results through study replication is a pre-condition for accepting the validity of such results. In computation research, full replication is often unrealistic for independent results validation... Read More about Reproducibility of studies on text mining for citation screening in systematic reviews: evaluation and checklist.

Reporting Statistical Validity and Model Complexity in Machine Learning based Computational Studies (2017)
Presentation / Conference Contribution
Olorisade, B. K., Brereton, P., & Andras, P. (2017, June). Reporting Statistical Validity and Model Complexity in Machine Learning based Computational Studies. Presented at EASE'17: 21st International Conference on Evaluation and Assessment in Software Engineering, Karlskrona, Sweden

Background:: Statistical validity and model complexity are both important concepts to enhanced understanding and correctness assessment of computational models. However, information about these are often missing from publications applying machine lea... Read More about Reporting Statistical Validity and Model Complexity in Machine Learning based Computational Studies.

High-dimensional function approximation with neural networks for large volumes of data (2017)
Journal Article
Andras, P. (2018). High-dimensional function approximation with neural networks for large volumes of data. IEEE Transactions on Neural Networks and Learning Systems, 29(2), 500-508. https://doi.org/10.1109/TNNLS.2017.2651985

Approximation of high-dimensional functions is a challenge for neural networks due to the curse of dimensionality. Often the data for which the approximated function is defined resides on a low-dimensional manifold and in principle the approximation... Read More about High-dimensional function approximation with neural networks for large volumes of data.