Search

The rapid growth of mobile applications and the associated increased dependency on digital identity raises the growing risk of identity theft and related fraud. Hence, protecting identity in a mobile environment is a problem. This study develops a model that examines the role of identity protection self-efficacy in increasing users’ motivation intentions to achieve actual mobile identity protection. Our research found that self-efficacy significantly affects the relationship between users’ perceived threat appraisal and their motivational intentions for identity protection. The relation between mobile users’ protection, motivational intentions, and actual mobile identity protection actions was also found to be significant. Additionally, the findings revealed the considerable impact of awareness in fully mediating between self-efficacy and actual identity protection. The model and its hypotheses are empirically tested through a survey of 383 mobile users, and the findings are validated through a panel of experts, thus confirming the impact of self-efficacy on an individual’s identity protection in the mobile context.

Recent years have witnessed the rapid prevalence of big data and it is necessary for mobile application to filter out information for users. As a significant means of information retrieval, recommendation system that recommends a ranked list of items to users according to their preferences has become a key functionality in Location-Based Social Networks (LBSNs). Point of interest (POI) recommendation that aims to recommend satisfactory locations that users may be interested in plays an important role in LBSNs. However, the traditional POI recommendation uses the original user-POI matrix, which faces a huge challenge of data sparsity because most users just check in a few POIs in their phones. Moreover, it is hard for POI recommendation to give reasonable explanations on why user will visit these locations that we recommend. Therefore, in terms of the challenges mentioned above, we propose a new POI recommendation model called PR-RCUC that uses region-based collaborative filtering and user-based mobile context. Firstly, we cluster locations into different regions and enhance the traditional collaborative filtering with region factor. Secondly, we capture the preferences of users on mobile context such as geographical distance and location category. Thirdly, by combing the two parts we present, we finish the final computation of prediction score and recommend Top-K locations to users. The results of experiments on two real-world datasets collected from Foursquare demonstrate the PR-RCUC model outperforms some popular recommendation algorithms and achieves our expected goal. [ABSTRACT FROM AUTHOR]

After the introduction of mobile computing devices, the way people listen to music has changed considerably. Although there is a broad scientific consensus on the fact that people show music preferences and make music choices based on their feelings and emotions, the sources of such preferences and choices are still debated. The main aim of this study is to understand whether listening in ecological (mobile) contexts differs from listening in non-mobile contexts in terms of the elicited emotive response. A total of 328 participants listen to 100 classical music tracks, available through an ad-hoc mobile application for mobile devices. The participants were asked to report their self-evaluation of each of the tracks, according to the Pleasure-Arousal-Dominance model and filled out a questionnaire about their listening behaviour. Our findings show that the same factors that affect music listening in non-mobile contexts also affect it in a mobile context.

The popularity of watching video clips on mobile devices is rapidly increasing. The providers of such video services have developed mobile capabilities and have worked to increase their video selections. This study investigates the effect of the factors of preview content (the thumbnail and the title) and context (the popularity cue and the serial position) on video selection in a mobile context by adopting dual process theory and the model of attention capture and transfer. We performed a logit transformation on the dependent variable, and then applied generalized least squares (GLS) regression to analyze 206,221 logs and 323 thumbnails and titles of a video service. Image and text- mining techniques were used to ascertain the level of valence and response to content. This study has four main findings: (1) low valence but high arousal of a thumbnail has a positive effect on video selection; (2) high valence and arousal by a title has a positive effect on video selection; (3) the upper serial position of a video clip and a high popularity cue have a positive effect on the video selection; and (4) the length and recency of a video have a positive effect on the video selection. The results of this study suggest practical implications to help the programming and marketing strategy of the video service as well. [ABSTRACT FROM AUTHOR]

After the introduction of mobile computing devices, the way people listen to music has changed considerably. Although there is a broad scientific consensus on the fact that people show music preferences and make music choices based on their feelings and emotions, the sources of such preferences and choices are still debated. The main aim of this study is to understand whether listening in ecological (mobile) contexts differs from listening in non-mobile contexts in terms of the elicited emotive response. A total of 328 participants listen to 100 classical music tracks, available through an ad-hoc mobile application for mobile devices. The participants were asked to report their self-evaluation of each of the tracks, according to the Pleasure-Arousal-Dominance model and filled out a questionnaire about their listening behaviour. Our findings show that the same factors that affect music listening in non-mobile contexts also affect it in a mobile context. [ABSTRACT FROM AUTHOR]

Traffic optimization is a subject that has become vital for the world we live in. People these days need to get from a starting point to a destination point as fast and as safe as possible. Traffic congestion plays a key role in the frustration of people and it results in lost time, reduced productivity and wasted resources. In our study we seek to address these issues by proposing a real-time road traffic planning system based on mobile context and crowd sourcing efforts. The first step toward this goal is real-time traffic characterization using data collected from mobile sensors of drivers, pedestrians, cyclists, passengers, etc.. We started developing a data collection and analysis system composed of a mobile application in order to collect user context data and a Web application to view and analyze the data. This new system will eventually give the users an automatically optimized route to the destination and predict the users' traveling route based on live traffic conditions and historical data. [ABSTRACT FROM AUTHOR]

Mobile user data are collected by service providers around the clock and through intelligent data analysis in which it can offer great services for health cares, business activities, and other personal or social services, etc. However, data could be misused and privacy could potentially be breached which might lead to harmful consequences. Many privacy-preserving techniques have been proposed in the past decade for anonymizing relational and social data. But only a handful of privacy-preserving techniques have been proposed to anonymize sensitive mobile context before releasing data to service providers. Unfortunately, these techniques also reduce the utility of data that are supposed to provide helpful services. As such, the effectiveness of these anonymization techniques cannot be easily justified and compared. In this work, we propose a unified approach to define privacy gain and utility loss due to anonymizing sensitive context on mobile user data. We further perform extensive numerical evaluation on various well-known anonymization techniques, compare their performances and trade-offs between privacy and utility, and also provide a framework of analysis which serves a reference for adopting suitable anonymization technique for different user requirements. [ABSTRACT FROM AUTHOR]

The accurate detection of the mobile context information of public transportation vehicles and their passengers is a key feature to realize intelligent transportation systems. A topical example is in-vehicle presence detection that can, e.g. , be used to ticket passengers automatically. Unfortunately, most existing solutions in this field suffer from low spatiotemporal accuracy which impedes their use in practice. In previous work, we addressed this challenge through a deep learning-based framework, called DeepMatch , that allows us to detect in-vehicle presence with a high degree of accuracy. DeepMatch utilizes the smartphone of a passenger to analyse and match the event streams of its own sensors with the event streams of counterpart sensors provided by a reference unit that is installed inside the vehicle. This is achieved through a new learning model architecture using Stacked Convolutional Autoencoders to compress sensor input streams by feature extraction and dimensionality reduction as well as a deep convolutional neural network to match the streams of the user phone and the reference device. The sensor stream compression is offloaded to the smartphone, while the matching is performed in a server. In this paper, we introduce DeepMatch2. It is an amended version of DeepMatch that reduces the amount of data to be transferred from the user and reference devices to the server by the factor of four. Further, DeepMatch2 improves the already good accuracy of DeepMatch from 97.81% to 98.51%. Moreover, we propose a travel inference algorithm, based on DeepMatch2 , to detect the duration of whole passenger trips in public transport vehicles with a high degree of precision. This is needed to create intelligent and highly reliable auto-ticketing systems. Thanks to the high accuracy of 98.51% by DeepMatch2 , the inferences can be carried out with a negligible error rate. [ABSTRACT FROM AUTHOR]