Real-world Mobile Data Research Articles

특징적 단어 및 이모티콘 집합을 활용한 모바일 기기 내 성별 예측 프레임워크

User demographic information is necessary in order to improve the quality of personalized services such as recommendation systems. Mobile data, especially text data, is known to be effective for prediction of user demographic information. However, mobile text data has privacy issues so that its utilization is limited. In this regard, we introduce an on-device gender prediction framework utilizing mobile text data while minimizing the privacy issue. Discriminative word and emoticon sets of each gender are constructed from web documents written by authors of each gender. After gender prediction is performed by comparing discriminative word and emoticon sets with a user's mobile text data, an ensemble method that combines two prediction results draws a final result. From experiments conducted on real-world mobile text data, the proposed on-device framework shows promising results for gender prediction.

A risk model for privacy in trajectory data

Time sequence data relating to users, such as medical histories and mobility data, are good candidates for data mining, but often contain highly sensitive information. Different methods in privacy-preserving data publishing are utilised to release such private data so that individual records in the released data cannot be re-linked to specific users with a high degree of certainty. These methods provide theoretical worst-case privacy risks as measures of the privacy protection that they offer. However, often with many real-world data the worst-case scenario is too pessimistic and does not provide a realistic view of the privacy risks: the real probability of re-identification is often much lower than the theoretical worst-case risk. In this paper, we propose a novel empirical risk model for privacy which, in relation to the cost of privacy attacks, demonstrates better the practical risks associated with a privacy preserving data release. We show detailed evaluation of the proposed risk model by using k-anonymised real-world mobility data and then, we show how the empirical evaluation of the privacy risk has a different trend in synthetic data describing random movements.

Traffic sign detection via interest region extraction

Mobile mapping systems acquire massive amount of data under uncontrolled conditions and pose new challenges to the development of robust computer vision algorithms. In this work, we show how a combination of solid image analysis and pattern recognition techniques can be used to tackle the problem of traffic sign detection in mobile mapping data. Different from the majority of existing systems, our pipeline is based on interest regions extraction rather than sliding window detection. Thanks to the robustness of local features, the proposed pipeline can withstand great appearance variations, which typically occur in outdoor data, especially dramatic illumination and scale changes. The proposed approach has been specialized and tested in three variants, each aimed at detecting one of the three categories of mandatory, prohibitory and danger traffic signs, according to the experimental setup of the recent German Traffic Sign Detection Benchmark competition. Besides achieving very good performance in the on-line competition, our proposal has been successfully evaluated on a novel, more challenging dataset of Italian signs, thereby proving its robustness and suitability to automatic analysis of real-world mobile mapping data.

Campaign Optimization Through Behavioral Modeling and Mobile Network Analysis

Optimizing the use of available resources is one of the key challenges in activities that consist of interactions with a large number of “target individuals,” with the ultimate goal of “winning” as many of them as possible, such as in marketing, service provision, political campaigns, or homeland security. Typically, the cost of interactions is monotonically increasing such that a method for maximizing the performance of these campaigns is required. In this paper, we propose a mathematical model to compute an optimized campaign by automatically determining the number of interacting units and their type, and how they should be allocated to different geographical regions in order to maximize the campaign’s performance. We validate our proposed model using real world mobility data.

European type-approval test procedure for evaporative emissions from passenger cars against real-world mobility data from two Italian provinces

This paper presents an evaluation of the European type-approval test procedure for evaporative emissions from passenger cars based on real-world mobility data. The study relies on two large databases of driving patterns from conventional fuel vehicles collected by means of on-board GPS systems in the Italian provinces of Modena and Firenze. Approximately 28,000 vehicles were monitored, corresponding to approximately 36millionkilometres over a period of one month. The driving pattern of each vehicle was processed to derive the relation between trip length and parking duration, and the rate of occurrence of parking events against multiple evaporative cycles, defined on the basis of the type-approval test procedure as 12-hour diurnal time windows. These results are used as input for an emission simulation model, which calculates the total evaporative emissions given the characteristics of the evaporative emission control system of the vehicle and the ambient temperature conditions. The results suggest that the evaporative emission control system, fitted to the vehicles from Euro 3 step and optimised for the current type-approval test procedure, could not efficiently work under real-world conditions, resulting in evaporative emissions well above the type-approval limit, especially for small size vehicles and warm climate conditions. This calls for a revision of the type-approval test procedure in order to address real-world evaporative emissions.