Exploitation of Physical Constraints for Reliable Social Sensing

Wang, Dong; Abdelzaher, Tarek; Kaplan, Lance; Ganti, Raghu; Hu, Shaohan; Liu, Hengchang

doi:10.1109/rtss.2013.29

Cited by 53 publications

(48 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, we extend the previous work by addressing the challenge of uncertain provenance as well, which is a main distinguishing factor between networked physical sensors and networked humans. In prior sensing literature on sources of unknown reliability, uncertain provenance was either ignored altogether [47], [48], [52], or addressed via admission control that selects only independent sources [45]. We show, in our evaluation, that such limitations lead to an inferior assessment of observation correctness in the case of humans as sensors.…”

Section: Related Workmentioning

confidence: 98%

Using humans as sensors: An estimation-theoretic perspective

Wang

Amin

Shen

et al. 2014

IPSN-14 Proceedings of the 13th International Symposium on Information Processing in Sensor Networks

Self Cite

163

108

View full text Add to dashboard Cite

Abstract-The explosive growth in social network content suggests that the largest "sensor network" yet might be human.Extending the participatory sensing model, this paper explores the prospect of utilizing social networks as sensor networks, which gives rise to an interesting reliable sensing problem. In this problem, individuals are represented by sensors (data sources) who occasionally make observations about the physical world. These observations may be true or false, and hence are viewed as binary claims. The reliable sensing problem is to determine the correctness of reported observations. From a networked sensing standpoint, what makes this sensing problem formulation different is that, in the case of human participants, not only is the reliability of sources usually unknown but also the original data provenance may be uncertain. Individuals may report observations made by others as their own. The contribution of this paper lies in developing a model that considers the impact of such information sharing on the analytical foundations of reliable sensing, and embed it into a tool called Apollo that uses Twitter as a "sensor network" for observing events in the physical world. Evaluation, using Twitter-based case-studies, shows good correspondence between observations deemed correct by Apollo and ground truth.

show abstract

Section: Related Workmentioning

confidence: 98%

Using humans as sensors: An estimation-theoretic perspective

Wang

Amin

Shen

et al. 2014

IPSN-14 Proceedings of the 13th International Symposium on Information Processing in Sensor Networks

Self Cite

163

108

View full text Add to dashboard Cite

show abstract

“…A similar approach with more than 200,000 traces from a vehicle fleet is used by Ruhhammer et al (2014) to extract multiple intersection parameters like the number of lanes or the probability of turning maneuvers. In contrast, Wang et al (2013) use the term "social sensing" for applications, where observations are collected by a group of sources, e.g. individuals and their mobile phones.…”

Section: State Of the Artmentioning

confidence: 99%

Image Based Recognition of Dynamic Traffic Situations by Evaluating the Exterior Surrounding and Interior Space of Vehicles

Hanel¹,

Kloden

Hoegner³

et al. 2015

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Today, cameras mounted in vehicles are used to observe the driver as well as the objects around a vehicle. In this article, an outline of a concept for image based recognition of dynamic traffic situations is shown. A dynamic traffic situation will be described by road users and their intentions. Images will be taken by a vehicle fleet and aggregated on a server. On these images, new strategies for machine learning will be applied iteratively when new data has arrived on the server. The results of the learning process will be models describing the traffic situation and will be transmitted back to the recording vehicles. The recognition will be performed as a standalone function in the vehicles and will use the received models. It can be expected, that this method can make the detection and classification of objects around the vehicles more reliable. In addition, the prediction of their actions for the next seconds should be possible. As one example how this concept is used, a method to recognize the illumination situation of a traffic scene is described. This allows to handle different appearances of objects depending on the illumination of the scene. Different illumination classes will be defined to distinguish different illumination situations. Intensity based features are extracted from the images and used by a classifier to assign an image to an illumination class. This method is being tested for a real data set of daytime and nighttime images. It can be shown, that the illumination class can be classified correctly for more than 80% of the images.

show abstract

“…Next, we construct a probabilistic model combining the error rate of participants and the context effect. Compared with the OtOEM algorithm [2], if the correct estimation rate of real status of all public facilities achieves 90%, under the premise of the same number of participants, our method can reduce 64% of the observations reported by each participant; under the premise of each participant reporting the same number of facilities, our method can reduce the number of participants by 53%.…”

Section: Introductionmentioning

confidence: 98%

“…Hence, in the scenarios of the majority of participants with high error rate, the status of a facility may be wrongly decided. The OtOEM algorithm [2] involves the error rate of participant, but in order to get the real status of public facilities, participants need to make multiple observations, and each participant should make the same observations for all facilities. Actually, the facilities are different, and the judgement for a facility may be different along with the changes of times, locations of participants and environments.…”

Section: Introductionmentioning

confidence: 99%

Context-Aware Estimation Approach Based on Participatory Sensing

Guo¹,

Sun²,

Wu³

et al. 2014

2015 IEEE Global Communications Conference (GLOBECOM)

View full text Add to dashboard Cite

In participatory sensing applications, the inaccuracy and conflict of the reported data, commonly caused by the error rate of participants or the differences of observation context, have received more and more attention. Estimating the real status of facilities according to observations becomes a big challenge for participatory sensing. Towards this end, we propose a contextaware estimation approach based on participatory sensing in this paper. We first model the effects of observation context, and then propose an iterative method to infer the error rate of participants and estimate the real status with high precision. Our method is verified using a public facilities monitoring application in our campus, and tested via extensive simulations. The results demonstrate that the proposed method outperforms recent popular three-estimates algorithm and OtO EM algorithm.

show abstract

Exploitation of Physical Constraints for Reliable Social Sensing

Cited by 53 publications

References 35 publications

Using humans as sensors: An estimation-theoretic perspective

Using humans as sensors: An estimation-theoretic perspective

Image Based Recognition of Dynamic Traffic Situations by Evaluating the Exterior Surrounding and Interior Space of Vehicles

Context-Aware Estimation Approach Based on Participatory Sensing

Contact Info

Product

Resources

About