John Kolb

LensKit: a modular recommender framework

LensKit is a new recommender systems toolkit aiming to be a platform for recommender research and education. It provides a common API for recommender systems, modular implementations of several collaborative filtering algorithms, and an evaluation framework for consistent, reproducible offline evaluation of recommender algorithms. In this demo, we will showcase the ease with which LensKit allows recommenders to be configured and evaluated.

Toward a Global Data Infrastructure

The Internet of Things (IoT) represents a new class of applications that can benefit from cloud infrastructure. However, directly connecting smart devices to the cloud has multiple disadvantages and is unlikely to keep up with the growing speed of the IoT or the diverse needs of IoT applications. Here, the authors argue that fundamental IoT properties prevent the current approach from scaling. Whats missing is a well-architected system extending cloud functionality and providing seamless interplay among heterogeneous components closer to the edge in the IoT space. Raising the level of abstraction to a data-centric design -- focused around the distribution, preservation, and protection of information -- better matches the IoT. To address such problems with the cloud-centric architecture, the authors present their early work on a distributed platform, the Global Data Plane.

Exploiting User Interest in Data-Driven Cloud-Based Mobile Optimization

In this paper, we present our vision for data-driven cloud-based mobile computing. We identify the concept of Region of interest (RoI) that reflects the profile of the user in how they access information or interact with applications. Such information enables a series of data-driven optimizations: filtering, aggregation, and speculation, that go beyond the well-researched benefit of mobile outsourcing. These optimizations can improve performance, reliability, and energy usage. A novel aspect of our approach is to exploit the unique ability of the cloud to collect and analyze large amounts of user profile data, cache shared data, and even enable sharing of computations, across different mobile users. We implement two exemplar mobile-cloud applications on an Android/Amazon Elastic Cloud Compute (EC2)-based mobile outsourcing platform, that utilize the RoI abstraction for data-driven optimizations. We presentresults driven by workload traces derived from Twitter feeds and Wikipedia document editing to illustrate the opportunities of using such optimizations.

SnapLink: Fast and Accurate Vision-Based Appliance Control in Large Commercial Buildings

As the number and heterogeneity of appliances in smart buildings increases, identifying and controlling them becomes challenging. Existing methods face various challenges when deployed in large commercial buildings. For example, voice command assistants require users to memorize many control commands. Attaching Bluetooth dongles or QR codes to appliances introduces considerable deployment overhead. In comparison, identifying an appliance by simply pointing a smartphone camera at it and controlling the appliance using a graphical overlay interface is more intuitive. We introduce SnapLink, a responsive and accurate vision-based system for mobile appliance identification and interaction using image localization. Compared to the image retrieval approaches used in previous vision-based appliance control systems, SnapLink exploits 3D models to improve identification accuracy and reduce deployment overhead via quick video captures and a simplified labeling process. We also introduce a feature sub-sampling mechanism to achieve low latency at the scale of a commercial building. To evaluate SnapLink, we collected training videos from 39 rooms to represent the scale of a modern commercial building. It achieves a 94% successful appliance identification rate among 1526 test images of 179 appliances within 120 ms average server processing time. Furthermore, we show that SnapLink is robust to viewing angle and distance differences, illumination changes, as well as daily changes in the environment. We believe the SnapLink use case is not limited to appliance control: it has the potential to enable various new smart building applications.

Cloud-Based, User-Centric Mobile Application Optimization

The abundance of compute and storage resources available in the cloud makes it well-suited to addressing the limitations of mobile devices. We explore the use of cloud infrastructure to optimize content-centric mobile applications, which can have high communication and storage requirements, based on the analysis of user activity. We present two specific optimizations, precaching and prefetching, as well as the design and implementation of a middleware framework that allows mobile application developers to easily utilize these techniques. Our framework is fully generalizable to any content-centric mobile application, a large and growing class of Internet applications. A news aggregation application is used as a case study to evaluate our implementation. We make use of a cosine similarity scheme to identify users with similar interests, which in turn is used to determine what content to prefetch. Various cache algorithms, implemented for our framework, are also considered. A workload trace and simulation are used to measure the performance of the application and framework. We observe a dramatic improvement in application performance due to use of our framework with a reasonable amount of overhead. Our system also significantly outperforms a baseline implementation that performs the same optimizations without taking user activity into account.

Democratizing authority in the built environment

Operating systems and applications in the built environment have relied upon central authorization and management mechanisms which restrict their scalability, especially with respect to administrative overhead. We propose a new set of primitives encompassing syndication, security, and service execution that unifies the management of applications and services across the built environment, while enabling participants to individually delegate privilege across multiple administrative domains with no loss of security or manageability. We show how to leverage a decentralized authorization syndication platform to extend the design of building operating systems beyond the single administrative domain of a building. The authorization system leveraged is based on blockchain smart contracts to permit decentralized and democratized delegation of authorization without central trust. Upon this, a publish/subscribe syndication tier and a containerized service execution environment are constructed. Combined, these mechanisms solve problems of delegation, federation, device protection and service execution that arise throughout the built environment. We leverage a high-fidelity city-scale emulation to verify the scalability of the authorization tier, and briefly describe a prototypical democratized operating system for the built environment using this foundation.

BearLoc: A Composable Distributed Framework for Indoor Localization Systems

Many indoor localization algorithms have been proposed to enable location-based applications in indoor environments. However, these systems are monolithic and not component-based. We present BearLoc, a distributed modular framework for indoor localization systems that provides (1) natural development abstractions for sensor, algorithm, and application components, and (2) easy and flexible component composition. We demonstrate the merits of BearLoc with an example use case. Our evaluation shows we can reduce developer lines of code by 60% while introducing acceptable network delay overhead.