International Journal of Networking and Virtual Organisations

Sharma, Moolchand; Deswal, Suman

doi: 10.1504/ijnvo.2022.130941pmid: N/A

The drug design process is lengthy, complex, and dependent on several factors. Developing a medicine can take 10 to 15 years, from discovery to commercialisation. Machine learning (ML) refers to a set of tools that can assist you in learning more and making better decisions for well-defined questions with a large amount of data. The opportunities to use ML occur throughout the drug development process. Examples include target identification and validation, identification of alternative targets, and biomarker identification. Some approaches have produced accurate predictions and insights, while others have not. But to deal with high-dimensional data, we need soft-computing methods to find the best solution, which could be a new drug. This article provides a detailed overview of various ML, evolutionary algorithms, and soft computing techniques surveyed and analysed for de novo drug design, emphasising the computational aspects.

Dallagnol, Mathäus M. Freitag; Zuliani, André Luís Baumhardt; Girardi, Gabriele; Wegner, Douglas

doi: 10.1504/ijnvo.2022.130946pmid: N/A

This study investigates how governance occurs in collaborative networks based on practices of collaborative arrangements aiming to reduce gaps of how networks are governed, analysing the influence of contextual factors, functions, and practices to obtain certain results. A qualitative case study of a Brazilian agribusiness network that has worked collaboratively for over 20 years was done based on in-depth interviews and complementary data. To analyse the data, we used the content analysis technique. Results indicate that micro-governance functions and practices produce outcomes that influence the network's development, coordination activities, and performance. This implies that members believe that joining the network provides strategic, financial, relational, and social benefits that would be difficult to achieve on their own. Moreover, contextual factors regarding the relationships after the network formation, environmental factors and previous relations influence the organisation of micro-governance. Thus, the observed high commitment and incentive to engage in this network, certain functions are not used.

Pyae, Aung

doi: 10.1504/ijnvo.2022.130945pmid: N/A

Recently, 'mindfulness' has been of interest to researchers in psychology as an intervention to promote psychological well-being. Due to recent technological advances, mindfulness-based interventions can now be delivered through digital platforms including mobile phones. Whilst the literature shows the promise of mindfulness-based applications for users, there is limited research into location-based games (LBGs) for mindfulness. To address this gap, in this study, a questionnaire was administered to Pokémon GO game players to gauge mindfulness and better understand which aspects of their play contributed to their mindfulness. The findings suggest that the Pokémon GO game is promising to promote players' mindfulness through gameplay. Further, the findings shed light on the level of mindfulness as measured by player's attention, focus, awareness, and acceptance in the gameplay. Lastly, the application of LBGs deserves a wider interest and attention from researchers due to their demonstrated potential to promote people's psychological well-being by improving mindfulness.

Prashanthi, M.; Miryala, Chandra Mohan

doi: 10.1504/ijnvo.2022.130947pmid: N/A

In this research, the defects in the software are predicted using the deep CNN classifier by effectively optimising the classifier using spiderhunt optimisation. The effective communication and hunting characteristics of the spiderhunt are employed for tuning the classifier that boosts the classifier performance. The proposed spiderhunt optimisation not only optimises the classifier but also plays a significant role in the feature selection for the extraction of necessary features that helps in defect prediction. The proposed spiderhunt optimisation achieved an improvement rate of 1.009%, 1.083%, 0.578%, and 1.01% in terms of accuracy, precision, recall, and F-measure and is proved to be quite efficient compared to state of art methods.