A habit mining approach for discovering similar mobile users

Ma, Haiping; Cao, Huanhuan; Yang, Qiang; Chen, Enhong; Tian, Jilei

doi:10.1145/2187836.2187868

Cited by 50 publications

(42 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The more we zoom into device usage scenarios, the more attributes need to be considered. Rather than reducing the complexity of the n-ary usage logs analysis into a frequent binary pattern and association rule mining problem by converting n-ary to binary logs (e.g., Context × Activity, Context × Device) [2], [4], [5], [12]- [14], we rely on recent advances in data mining over n-ary relations (e.g., Device × Context × Activity) [6], [7]. Our choice is motivated by the need to employ the same general purpose mining algorithms for serving different analytical use cases.…”

Section: Analysis Of Device Co-usagementioning

confidence: 99%

“…Traditional market basket analysis has been recently revised for extracting associations between users' interactions (e.g., communication and entertainment services) and context (e.g., time periods) captured by mobile devices [2], [3], frequent co-occurring mobile context events (e.g., a user listens to music during workdays, while driving) [4] or frequent co-usage patterns of different appliances under various contexts [5]. Unlike these works, we extract n-ary (vs. binary) patterns from device logs involving attributes of at least three distinct entities: Device, Context, and Activity.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Extracting usage patterns of home IoT devices

Poghosyan

Pefkianakis

Guyadec

et al. 2017

2017 IEEE Symposium on Computers and Communications (ISCC)

View full text Add to dashboard Cite

Abstract-Ubiquitous connectivity and smart technologies gradually transform homes into Intranet of Things, where a multitude of connected, intelligent devices allow for novel home automation services. Providing new services for home users (e.g., energy saving automations) and Internet Service Providers (e.g., network management and troubleshooting) requires an in-depth analysis of various kinds of data (connectivity, performance, usage) collected from home networks. In this paper, we explore new Machine-to-Machine data analysis techniques that go beyond binary association rule mining for traditional market basket analysis considered by previous studies, to analyze individual device logs of home gateways. We introduce a multidimensional patterns mining framework, to extract complex device co-usage patterns of 201 residential broadband users of an ISP, subscribed to a triple-play service. Our results show that our analytics engine provides valuable insights for emerging use cases such as monitoring for energy efficiency, and "things" recommendation.

show abstract

Section: Analysis Of Device Co-usagementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Extracting usage patterns of home IoT devices

Poghosyan

Pefkianakis

Guyadec

et al. 2017

2017 IEEE Symposium on Computers and Communications (ISCC)

View full text Add to dashboard Cite

show abstract

“…Lv et al [20] develops a website using the Google Maps API, where users can manually record their trajectory and also name the category of location for the referred places. Ma et al [26] in their approach for finding user similarity utilize the Nokia Ovi Store for mapping the raw trajectories to semantic locations. However, geographical position of the retrieved category and the point from which the query is made, is not always the same geographical location.…”

Section: Motivation and Problem Statementmentioning

confidence: 99%

An approach to compute user similarity for GPS applications

Mazumdar

Patra

Lock

et al. 2016

Knowledge-Based Systems

View full text Add to dashboard Cite

The proliferation of GPS enabled devices has led people to share locations both consciously and unconsciously. Large spatio-temporal data comprising of shared locations and whereabouts are now being routinely collected for analysis. As user movements are generally driven by their interests, so mining these mobility patterns can reveal commonalities between a pair of users. In this paper, we present a framework for mining the published trajectories to identify patterns in user mobility. In this framework, we extract the locations where a user stays for a period of time popularly known as the stay points. These stay points help to identify the interests of a user. The statistics of pattern and check-in distributions over the GPS data are used to formulate similarity measures for finding K -nearest neighbors of an active user. In this work, we categorize the neighbors into three groups namely strongly similar, closely similar and weakly similar. We introduce three similarity measures to determine them, one for each of the categories. We perform experiments on a real-world GPS log data to find the similarity scores between a pair of users and subsequently find the effective K -neighbors. Experimental results show that our proposed metric outperforms existing metrics in literature.

show abstract

“…Contextual categories are often predefined by taxonomies [24,100,251]. Alternatively, an unsupervised technique is used to discover contextual information [144,174]. Moreover, context discovery can be formulated as an optimization problem [143] or a feature selection problem [233,235].…”

Section: Context-aware Recommendationsmentioning

confidence: 99%

Using Contextual Information to Understand Searching and Browsing Behavior

Kiseleva

2015

Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

A habit mining approach for discovering similar mobile users

Cited by 50 publications

References 27 publications

Extracting usage patterns of home IoT devices

Extracting usage patterns of home IoT devices

An approach to compute user similarity for GPS applications

Using Contextual Information to Understand Searching and Browsing Behavior

Contact Info

Product

Resources

About