Predicting the footfall in a new brick-and-mortar shop (and thus, its prosperity), is a problem of strategic importance in business. Few previous attempts have been made to address this problem in the context of big data analytics in smart cities, proposing the use of social network check-ins as a proxy for business popularity, concentrating however only on singular business types. Adding to the existing literature, we mine a large dataset of high temporal granularity check-in data for two medium-sized cities in Southern and Northern Europe, with the aim to predict the evolution of check-ins of new businesses of any type, from the moment that they appear in a social network. We propose and analyze the performance of three algorithms for the dynamic identification of suitable neighbouring businesses, whose data can be used to predict the evolution of a new business. Our SmartGrid algorithm reaches a performance of being able to accurately predict the evolution of 86% of new businesses.

Papadimitriou, G., Komninos A., & Garofalakis J. (In Press).  Supporting Retail Business in Smart Cities using Urban Social Data Mining. 15th International Conference on Intelligent Environments (IntEnv'19). Rabat, Morocco, IEEE.

In smart spaces with connected smart lighting, there is an opportunity to deliver smartphone notifications using peripheral light, along with using standard smartphone modalities such as sound, vibration and LEDs, in order to help a user perceive them without constantly monitoring their mobile device. In this paper, we examine the effectiveness of on-device and extra-device modalities through smart lighting. We address a gap in literature by establishing a foundation that explains the role of modalities with which a notification is delivered on a mobile device. For this purpose, we conducted two ecologically valid and carefully designed experiments in a controlled environment that simulates multitasking in a smart home environment, and demonstrate that modality preferences are dependent on the environment context, by analysing subjective user data through a machine learning approach. We derive a set of guidelines for choosing notification modalities and set future research directions.

Komninos, A., Besharat J., Stefanis V., Gogoulou G., & Garofalakis J. (In Press).  Assessing the Perceptibility of Smartphone Notifications in Smart Lighting Spaces. Journal of Ambient Intelligence and Smart Environments. ..

To address the problem of improving text entry accuracy in mobile devices, we present a new tablet keyboard that offers both immediate and delayed feedback on language quality through auto-correction, prediction, and grammar checking. We combine different visual representations for grammar and spelling errors, accepted predictions, auto-corrections, as well as support interactive swiping/tapping features and improved interaction with previous errors, predictions, and auto-corrections. We also added smart error correction features to the system to decrease the overhead of correcting errors and decrease the number of operations. We designed the new input method with an iterative user-centered approach through multiple pilot studies. To determine the effect of our approach, we conducted a lab-based study used a refined methodology and found that WiseType outperforms a standard keyboard in terms of text entry speed and error rate. The study shows that color-coded text background highlighting and underlining of potential mistakes in combination with fast correction methods can improve writing speed and accuracy.

Alharbi, O., Arif A. Sabbir, Stuerzlinger W., Dunlop M. D., & Komninos A. (In Press).  WiseType: A Tablet Keyboard with Color-Coded Visualization and Various Editing Options for Error Correction. Graphics Interface - 45th Annual Conference on Computer Graphics, Visualization and Human-Computer Interaction (GI2019). Kingston, Canada, Canadian Human-Computer Communications Society.