PeerJ Computer Science – Tools, Packages and Databases Collection

PeerJ Computer Science publishes research across the whole range of computer science, from analysis of algorithms to web science. When the journal launched we wanted to ensure it recognised the importance and scientific value of pure software contributions, rewarding the sometimes overlooked contributions from developers and maintainers of code and databases. It’s great to see a number of such software papers in our most cited papers, including our most cited paper from Thomas Wiecki and colleagues describing PyMC3. 

We have recently launched a new collection of notable software tools, packages and databases that have been published in PeerJ Computer Science over the past couple of years. Whilst all of these papers describe software tools, packages or databases they have a wide and varied application, showing the vital importance of computer science research and software development to solving myriad problems across numerous research fields.

Articles in the collection include:

R-DECO: an open-source Matlab based graphical user interface for the detection and correction of R-peaks

The electrocardiogram (ECG) is one of the primary screening and diagnostic tools of the cardiologist. It records the electrical activity of the heart, which generates the myocardial contractions. A crucial step in the study of the ECG is the location of the QRS-complexes which involves detecting the R-Peak. In this paper, Jonathan Moeyersons and colleagues present R-DECO, a MATLAB-based GUI for the detection and correction of R-Peaks.

NIPS4Bplus: a richly annotated birdsong audio dataset

NIPS4Bplus is the first richly annotated birdsong audio dataset, comprised of recordings containing bird vocalisations along with their active species tags and temporal annotations. By including statistical information about the recordings, their species specific tags and their temporal annotations, Morfi and colleagues explain how NIPS4Bplus could be used in various ecoacoustic tasks, such as training models for bird population monitoring, species classification, birdsong vocalisation detection and classification.

DeepMoney: counterfeit money detection using generative adversarial networks

Currency counterfeiters have become more sophisticated, meaning identification of fake currency becomes increasingly difficult. Ali and colleagues describe the open source machine assisted system – DeepMoney – which was developed to discriminate fake notes from genuine ones using Generative Adversarial Networks (GANs). 

Efficient facial representations for age, gender and identity recognition in organizing photo albums using multi-output ConvNet

The rise of digital cameras and mobile phones means the number of multimedia resources is rapidly increasing; it’s estimated that in 2020 over 1.4 trillion photos will be taken. As a result the task of automatic structuring of photo and video albums is attracting increasing attention. In this article Savchenko et al use a convolutional neural network approach for the automatic extraction of persons and their attributes (gender, year of born) from photos. 

Tools4MSP: an open source software package to support Maritime Spatial Planning

Stefano Menegon and colleagues present the Tools4MSP software package, a Python-based Free and Open Source Software (FOSS) for geospatial analysis in support of Maritime Spatial Planning (MSP) and marine environmental management. Tools4MSP supports a wide user community that facilitates the implementation of collaborative analyses improving the reusability and sharing of the result outputs.The usage of the plugin is particularly suitable as it provides a user-friendly interface appropriate to decision-makers, regional authorities, academics and MSP stakeholders (e.g., fishers, eNGOs, industry).

The Modern Research Data Portal: a design pattern for networked, data-intensive science

Kyle Chard and colleagues describe best practices for providing convenient, high-speed, secure access to large data via research data portals. They capture these best practices in a new design pattern, the Modern Research Data Portal, that disaggregates the traditional monolithic web-based data portal to achieve orders-of-magnitude increases in data transfer performance, support new deployment architectures that decouple control logic from data storage, and reduce development and operations costs. 

Read these and other software papers in the Tools, Packages and Databases Collection

PeerJ Computer Science welcomes submissions in this area.