Integrating Sensors in Social Networks   Leave a comment

A number of sensor applications in recent years collect data which can be directly associated with human interactions. Some examples of such applications include GPS applications on mobile devices, accelerometers, or location sensors designed to track human and vehicular traffic. Such data lends itself to a variety of rich applications in which one can use the sensor data in order to model the underlying relationships and interactions. It also leads to a number of challenges, since such data may often be private, and it is important to be able to perform the mining process without violating the privacy of the users.

Social networks have become extremely popular in recent years, because of numerous online social networks such as Facebook, LinkedIn and MySpace. In addition, many chat applications can also be modeled as social networks.  Social networks provide a rich and flexible platform for performing the mining process with different kinds of data such as text, images, audio and video. Therefore, a tremendous amount of research has been performed in recent years on mining such data in the context of social networks. In particular, it has been observed that the use of a combination of linkage structure and different kinds of data can be a very powerful tool for mining purposes. How one can combine the text in social networks with the linkage structure in order to implement more effective classification models. Other recent work uses the linkage structure in image data in order to perform more effective mining and search in information networks. Therefore, it is natural to explore whether sensor data processing can be tightly integrated with social network construction and analysis. Most of the afore-mentioned data types on a social network are static and change slowly over time. On the other hand, sensors collect vast amounts of data which need to be stored and processed in real time. There are a couple of important drivers for integrating sensor and social networks:

-One driver for integrating sensors and social networks is to allow the actors in the social network to both publish their data and subscribe to each other’s data either directly, or indirectly after discovery of useful information from such data. The idea is that such collaborative sharing on a social network can increase real-time awareness of different users about each other, and provide unprecedented information and understanding about global behavior of different actors in the social network. The vision of integrating sensor processing with the real world.

-A second driver for integrating sensors and social networks is to better understand or measure the aggregate behavior of self-selected communities or the external environment in which these communities function. Examples may include understanding traffic conditions in a city, understanding
environmental pollution levels, or measuring obesity trends. Sensors in the possession of large numbers  of individuals enable exploiting the crowd for massively distributed data collection and processing.
Recent literature reports on several efforts that exploit individuals for data collection and processing purposes such as collection of vehicular GPS trajectories as a way for developing street maps, collectively locating items of interest using cell-phone reports, such as mapping speed traps using the Trapster application, use of massive human input to translate documents, and the development of protein folding games that use competition among players to implement the equivalent of global optimization algorithms.

The above trends are enabled by the emergence of large-scale data collection opportunities, brought about by the proliferation of sensing devices of every-day use such as cell-phones, piedometers, smart energy meters, fuel consumption sensors (standardized in modern vehicles), and GPS navigators.
The proliferation of many sensors in the possession of the common individual creates an unprecedented potential for building services that leverage massive amounts data collected from willing participants, or involving such participants as elements of distributed computing applications. Social networks, in a sensor-rich world, have become inherently multi-modal data sources, because if the richness of the data collection process in the context of the network structure.  In recent years, sensor data collection techniques and services have been integrated into many kinds of social networks. These services have caused a computational paradigm shift, known as crowd-sourcing, referring to the involvement of the general population in data collection and processing. Crowd-sourcing, arguably pioneered by programs such as SETI, has become remarkably successful recently due to increased networking, mobile connectivity and geo-tagging. Some examples of integration of social and sensor networks are as follows:

-The Google Latitude application collects mobile position data of uses, and shares this data among different users. The sharing of such data among users can lead to signi􀂿cant events of interest. For example, proximity alerts may be triggered when two linked users are within geographical proximity of one another. This may itself trigger changes in the user-behavior patterns, and therefore the underlying sensor values. This is generally true of many applications, the data on one sensor can influence data in the other sensors.

-The City Sense application  collects sensor data extracted from fixed sensors, GPS-enabled cell phones and cabs in order to determine where the people are, and then carries this information to clients who subscribe to this information. The information can also be delivered to clients with mobile devices. This kind of social networking application provides a “sense” as to where the people in the city are, and can be used in order to effectively plan activities. A similar project, referred to as WikiCity,  developed at MIT, uses the mobile data collected from cell phones in order to determine the spatial trends in a city, and which the social streets might be.

-This general approach of collecting individual location data from mobile phones can also be used in order to generate interesting business decisions. For example, the project MacroSense analyzes customers location behaviors, in order to determine individuals which behave in a similar way to a given target. The application is able to perform real time recommendations, personalization and discovery from real time location data.

Automotive Tracking Application: A number of real-time automotive tracking applications determine the important points of congestion in the city by pooling GPS data from the vehicles in the city. This can be used by other drivers in order to avoid points of congestion in the city. In many applications, such objects may have implicit links among them. For example, in a military application, the different vehicles may have links depending upon their unit membership or other related data. Another related application is that of sharing of bike track paths by different users. The problem of fnding bike routes is naturally a trialand- error process in terms of finding paths which are safe and enjoyable.
The designs Biketastic, which uses GPS-based sensing on a mobile phone application in order to create a platform which enables rich sharing of biker experiences with one another. The microphone and the accelerometer embedded on the phone are sampled to infer route noise level and roughness. The speed can also be inferred directly from the GPS sensing abilities of the mobile phone. The platform combines
this rich sensor data with mapping and visualization in order to provide an intuitive and visual interface for sharing information about the bike routes.

Animal Tracking: In its most general interpretation, an actor in a social network need not necessary be a person, but can be any living entity such as an animal. Recently, animal tracking data is collected with the use of radio-frequency identifiers. A number of social links may exist between the different animals such as group membership, or family membership. It is extremely useful to utilize the sensor information in order to predict linkage information and vice-versa. A recent project called MoveBank has made tremendous advances in collecting such data sets. A similar approach may be used for commercial product-tracking applications, though social networking applications are generally relevant to living entities, which are most typically people.

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: