Jiang Zhu

Integrating Web Usage and Content Mining for More Effective Personalization

Recent proposals have suggested Web usage mining as an enabling mechanism to overcome the problems associated with more traditional Web personalization techniques such as collaborative or content-based filtering. These problems include lack of scalability, reliance on subjective user ratings or static profiles, and the inability to capture a richer set of semantic relationships among objects (in content-based systems). Yet, usage-based personalization can be problematic when little usage data is available pertaining to some objects or when the site content changes regularly. For more effective personalization, both usage and content attributes of a site must be integrated into a Web mining framework and used by the recommendation engine in a uniform manner. In this paper we present such a framework, distinguishing between the offine tasks of data preparation and mining, and the online process of customizing Web pages based on a users active session. We describe effective techniques based on clustering to obtain a uniform representation for both site usage and site content profiles, and we show how these profiles can be used to perform real-time personalization.

Fog Computing: A Platform for Internet of Things and Analytics

Internet of Things (IoT) brings more than an explosive proliferation of endpoints. It is disruptive in several ways. In this chapter we examine those disruptions, and propose a hierarchical distributed architecture that extends from the edge of the network to the core nicknamed Fog Computing. In particular, we pay attention to a new dimension that IoT adds to Big Data and Analytics: a massively distributed number of sources at the edge.

Retweet Modeling Using Conditional Random Fields

Among the most popular micro-blogging service, Twitter recently introduced their reblogging service called retweet to allow a user to repopulate another users content for his followers. It quickly becomes one of the most prominent features on Twitter and an important mean for secondary content promotion. However, it remains unclear what motivates users to retweet and whether the retweeting decisions are predictable based on a users tweeting history and social relationships. In this paper, we propose modeling the retweet patterns using conditional random fields with a three types of user-tweet features: content influence, network influence and temporal decay factor. We also investigate approaches to partition the social graphs and construct the network relations for retweet prediction. Our experiments demonstrate that CRF can improve prediction effectiveness by incorporating social relationships compared to the baselines that do not.

SenSec: Mobile security through passive sensing

We introduce a new mobile system framework, SenSec, which uses passive sensory data to ensure the security of applications and data on mobile devices. SenSec constantly collects sensory data from accelerometers, gyroscopes and magnetometers and constructs the gesture model of how a user uses the device. SenSec calculates the sureness that the mobile device is being used by its owner. Based on the sureness score, mobile devices can dynamically request the user to provide active authentication (such as a strong password), or disable certain features of the mobile devices to protect users privacy and information security. In this paper, we model such gesture patterns through a continuous n-gram language model using a set of features constructed from these sensors. We built mobile application prototype based on this model and use it to perform both user classification and user authentication experiments. User studies show that SenSec can achieve 75% accuracy in identifying the users and 71.3% accuracy in detecting the non-owners with only 13.1% false alarms.

KeySens: Passive User Authentication through Micro-behavior Modeling of Soft Keyboard Interaction

Mobile devices have become almost ever-present in our daily lives and increasingly so in the professional workplace. Applications put company data, personal information and sensitive documents in the hands of busy nurses at hospitals, company employees on business trips and government workers at large conferences. Smartphones and tablets also not only store data on-device, but users are frequently authorized to access sensitive information in the cloud. Protecting the sensitivity of mobile devices yet not burdening users with complicated and cumbersome active authentication methods is of great importance to the security and convenience of mobile computing. In this paper, we propose a novel passive authentication method; we model the micro-behavior of mobile users’ interaction with their devices’ soft keyboard. We show that the way a user types—the specific location touched on each key, the drift from finger down to finger up, the force of touch, the area of press—reflects their unique physical and behavioral characteristics. We demonstrate that using these micro-behavior features without any contextual information, we can passively identify that a mobile device is being used by a non-authorized user within 5 keypresses 67.7% of the time. This comes with a False Acceptance Rate (FAR) of 32.3% and a False Rejection Rate (FRR) of only 4.6%. Our detection rate after 15 keypresses is 86% with a FAR of 14% and a FRR of only 2.2%.

MobiSens: A Versatile Mobile Sensing Platform for Real-World Applications

We present the design, implementation and evaluation of MobiSens, a versatile mobile sensing platform for a variety of real-life mobile sensing applications. MobiSens addresses common requirements of mobile sensing applications on power optimization, activity segmentation, recognition and annotation, interaction between mobile client and server, motivating users to provide activity labels with convenience and privacy concerns. After releasing three versions of MobiSens to the Android Market with evolving UI and increased functionalities, we have collected 13,993 h of data from 310 users over five months. We evaluate and compare the user experience and the sensing efficiency in each release. We show that the average number of activities annotated by a user increases from 0.6 to 6. This result indicates the activity auto-segmentation/recognition feature and certain UI design changes significantly improve the user experience and motivate users to use MobiSens more actively. Based on the MobiSens platform, we have developed a range of mobile sensing applications including Mobile Lifelogger, SensCare for assisted living, Ground Reporting for soldiers to share their positions and actions horizontally and vertically, and CMU SenSec, a behavior-driven mobile Security system.

Building a RCP (Rate Control Protocol) Test Network

We recently proposed the Rate Control Protocol (RCP) as way to minimize download times (or flow-completion times). Simulations suggest that if RCP were widely deployed, downloads would frequently finish ten times faster than with TCP. This is because RCP involves explicit feedback from the routers along the path, allowing a sender to pick a fast starting rate, and adapt quickly to network conditions. RCP is particularly appealing because it can be shown to be stable under broad operating conditions, and its performance is independent of the flow-size distribution and the RTT. Although it requires changes to the routers, the changes are small: The routers keep no per-flow state or per-flow queues, and the per-packet processing is minimal. However, the bar is high for a new congestion control mechanism - introducing a new scheme requires enormous change, and the argument needs to be compelling. And so, to enable some scientific and repeatable experiments with RCP, we have built and tested an open and public implementation of RCP; we have made available both the end- host software, and the router hardware. In this paper we describe our end-host implementation of RCP in Linux, and our router implementation in Verilog (on the NetFPGA platform). We hope that others will be able to use these implementations to experiment with RCP and further our understanding of congestion control.A mesh of trees (MoT) on-chip interconnection network has been proposed recently to provide high throughput between memory units and processors for single-chip parallel processing (Balkan et al., 2006). In this paper, we report our findings in bringing this concept to silicon. Specifically, we conduct cycle-accurate Verilog simulations to verify the analytical results claimed in (Balkan et al., 2006). We synthesize and obtain the layout of the MoT interconnection networks of various sizes. To further improve throughput, we investigate different arbitration primitives to handle load and store, the two most common memory operations. We also study the use of pipeline registers in large networks when there are long wires. Simulation based on full network layout demonstrates that significant throughput improvement can be achieved over the original proposed MoT interconnection network. The importance of this work lies in its validation of performance features of the MoT interconnection network, as they were previously shown to be competitive with traditional network solutions. The MoT network is currently used in an eXplicit multi-threading (XMT) on-chip parallel processor, which is engineered to support parallel programming. In that context, a 32-terminal MoT network could support up to 512 on-chip XMT processors. Our 8-terminal network that could serve 8 processor clusters (or 128 total processors), was also accepted recently for fabrication.

SensCare: Semi-automatic Activity Summarization System for Elderly Care

The fast growing mobile sensor technology makes sensor-based lifelogging system attractive to the remote elderly care. However, existing lifelogging systems are weak at generating meaningful activity summaries from heterogeneous sensor data which significantly limits the usability of lifelogging systems in practice. In this paper, we introduce SensCare, a semi-automatic lifelog summarization system for elderly care. From various sensor information collected from mobile phones carried by elderlies, SensCare fuses the heterogeneous sensor information and automatically segments/recognizes user’s daily activities in a hierarchical way. With a few human annotations, SensCare generates summaries of data collected from activties performed by the elderly. SensCare addresses three challenges in sensor-based elderly care systems: the rarity of activity labels, the uncertainty of activity granularities, and the difficulty of multi-dimensional sensor fusion. We conduct a set of experiments with users carrying a smart phone for multiple days and evaluate the effectiveness of the automatic summary. With proper sensor configuration, the phone can continue to monitor user’s activities for more than 24 hours without charging. SensCare also demonstrates that unsupervised hierarchical activity segmentation and semi-automatic summarization can be achieved with reasonably good accuracy (average F1 score 0.65) and the system is very useful for users to recall what has happened in their daily lives.

Mobile Lifelogger – Recording, Indexing, and Understanding a Mobile User’s Life

Lifelog system involves capturing personal experiences in the form of digital multimedia during an entire lifespan. Recent advancements in mobile sensor technologies have helped to develop these systems using commercial smart phones. These systems have the potential to act as a secondary memory and also aid people who struggle with episodic memory impairment (EMI). Despite their huge potential, there are major challenges that need to be addressed to make them useful. One of them is how to index the inherently large lifelog data so that the person can efficiently retrieve the log segments that interest him / her most. In this paper, we present an ongoing research of using mobile phones to record and index lifelogs using activity language. By converting sensory data such as accelerometer and GPS readings into activity language, we are able to apply statistical natural language processing techniques to index, recognize, segment, cluster, retrieve, and infer high-level semantic meanings of the collected lifelogs. Based on this indexing approach, our lifelog system supports easy retrieval of log segments representing past similar activities and automatic lifelog segmentation for efficient browsing and activity summarization.

Helix: Unsupervised Grammar Induction for Structured Activity Recognition

The omnipresence of mobile sensors has brought tremendous opportunities to ubiquitous computing systems. In many natural settings, however, their broader applications are hindered by three main challenges: rarity of labels, uncertainty of activity granularities, and the difficulty of multi-dimensional sensor fusion. In this paper, we propose building a grammar to address all these challenges using a language-based approach. The proposed algorithm, called Helix, first generates an initial vocabulary using unlabeled sensor readings, followed by iteratively combining statistically collocated sub-activities across sensor dimensions and grouping similar activities together to discover higher level activities. The experiments using a 20-minute ping-pong game demonstrate favorable results compared to a Hierarchical Hidden Markov Model (HHMM) baseline. Closer investigations to the learned grammar also shows that the learned grammar captures the natural structure of the underlying activities.