Probabilistic Event Extraction from RFID Data

Khoussainova, Nodira; Balazinska, Magdalena; Suciu, Dan

doi:10.1109/icde.2008.4497596

Cited by 50 publications

(26 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this step, the different data gathered from each customer including services used, customer tracking, facial and voice analysis results, and social media activity are prepared for data mining as depicted in Figure 4(a). Data cleaning and disambiguating methods (Khoussainova et al, 2008) should be applied to handle inconsistent data and missing values. 2.…”

Section: Multi-domain Data Miningmentioning

confidence: 99%

Pervasive information gathering and data mining for efficient business administration

Garrigós‐Simón¹,

Llorente²,

Morant

et al. 2016

Journal of Vacation Marketing

View full text Add to dashboard Cite

Following a multidisciplinary perspective (that combines the literature from management, information systems, marketing and engineering telecommunications perspectives), the purpose of this article is to create and analyze a conceptual framework and to propose a new methodology that encompasses different techniques for pervasive information gathering in hotels and for identifying clients' habits. Focusing on the future of hotels, this work presents new technologies for hotels suitable for correlating the customers' on-site activities with online activities including passive location tracking using Wi-Fi devices' connectivity, customer satisfaction evaluated via facial or voice recognition using inbuilt cameras/microphones altogether with data mining analysis. Moreover, this article explains how multidisciplinary consumer behavior can be analyzed by data mining to include this information in the vacation marketing approach for efficient business administration.

show abstract

Section: Multi-domain Data Miningmentioning

confidence: 99%

Pervasive information gathering and data mining for efficient business administration

Garrigós‐Simón¹,

Llorente²,

Morant

et al. 2016

Journal of Vacation Marketing

View full text Add to dashboard Cite

show abstract

“…PEEX [6] is Cascadiaś event detection subsystem. PEEX supports probabilistic events represented as tuples and stored in relations named for each event type.…”

Section: Peexmentioning

confidence: 99%

“…Scenic translates these graphical event definitions into PeexL, a SQL-like language for defining high-level events. The Probabilistic Event EXtraction system (PEEX) [6] is an RFID data management system that enables applications to declaratively specify events in PeexL. It then continuously and automatically extracts these events from RFID data streams and stores them persistently to simplify their subsequent management.…”

Section: Introductionmentioning

confidence: 99%

A demonstration of Cascadia through a digital diary application

Khoussainova

Welbourne

Balazinska

et al. 2008

Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data

Self Cite

View full text Add to dashboard Cite

The Cascadia system provides RFID-based pervasive computing applications with an infrastructure for specifying, extracting and managing meaningful high-level events from raw RFID data. Cascadia allows users to specify events of interest using a graphical interface with an intuitive visual language. Cascadia also effectively extracts these events from data in spite of the unreliability of RFID technology and the inherent ambiguity in event extraction.We demonstrate Cascadia's technique through a digital diary application in the form of a calendar. Cascadia automatically populates the calendar with meaningful events for the user. We use data collected in a building-wide RFID deployment.

show abstract

“…The stream of tags read by various sensors is stored in a relation SIGHTING(t, tID, aID), which denotes that the RFID tag tID was detected by antenna aID at time t. Since an RFID antenna has only a certain probability of reading a tag within its range, the PEEX system [13] processes the On Probabilistic Models for Uncertain Sequential Pattern Mining 3 SIGHTING relation to output an uncertain higher-level event relation such as MEETING(time, person1, person2, room, prob). An example tuple in MEETING could be (103, 'Alice', 'Bob', 435, 0.4), which means that at time 103, PEEX believes that Alice and Bob are having a meeting (event) with probability 0.4 in room 435 (source) [13]; since antennae are at xed locations, the source is certain but the event is uncertain.…”

Section: Introductionmentioning

confidence: 99%

“…(a) Employees movements are tracked in a building using RFID sensors [13]. The stream of tags read by various sensors is stored in a relation SIGHTING(t, tID, aID), which denotes that the RFID tag tID was detected by antenna aID at time t. Since an RFID antenna has only a certain probability of reading a tag within its range, the PEEX system [13] processes the On Probabilistic Models for Uncertain Sequential Pattern Mining 3 SIGHTING relation to output an uncertain higher-level event relation such as MEETING(time, person1, person2, room, prob).…”

Section: Introductionmentioning

confidence: 99%

On Probabilistic Models for Uncertain Sequential Pattern Mining

Muzammal

Raman

2010

Advanced Data Mining and Applications

View full text Add to dashboard Cite

Abstract. We study uncertainty models in sequential pattern mining. We consider situations where there is uncertainty either about a source or an event. We show that both these types of uncertainties could be modelled using probabilistic databases, and give possible-worlds semantics for both. We then describe "interestingness" criteria based on two notions of frequentness (previously studied for frequent itemset mining) namely expected support and probabilistic frequentness. We study the interestingness criteria from a complexity-theoretic perspective, and show that in case of source-level uncertainty, evaluating probabilistic frequentness is #P-complete, and thus no polynomial time algorithms are likely to exist, but evaluate the interestingness predicate in polynomial time in the remaining cases.

show abstract

Probabilistic Event Extraction from RFID Data

Cited by 50 publications

References 7 publications

Pervasive information gathering and data mining for efficient business administration

Pervasive information gathering and data mining for efficient business administration

A demonstration of Cascadia through a digital diary application

On Probabilistic Models for Uncertain Sequential Pattern Mining

Contact Info

Product

Resources

About