A Content Delivery Network (CDN) refers to a geographically distributed network of caching servers at the network edge that provides fast and efficient delivery of popular content. Video makes up at least 80% of the current Internet traffic. Consumer trends, such as high-definition video streaming across devices, growing IoT traffic, and data-intensive use cases requiring ultra-low latency transit are expected to make high-throughput content delivery increasingly important. As this content continues to get richer, more localized, personalized, interactive, and immersive, the volume of data required grows substantially. Therefore, the pressure is on CDN providers to deliver more content at a lower cost. CDN providers are increasingly looking for ways to optimize platform cost and performance to deliver to customer expectations for an exceptional experience without exorbitant capital and operational expenditures. Fortunately, advances in processor, memory and storage architectures are available to make the cost over efficiency equation easier to solve. In this paper, we show how AT&T* and Intel® have collaborated to demonstrate a foundational architecture for the next generation of open standards-based high performance CDNs; this includes benchmarks on 2nd and 3rd Generation Intel® Xeon® Scalable Processors with Intel® Optane™ Persistent Memory (PMem) technology as the elements to increase video stream density per CDN node, while lowering Total Cost of Ownership (TCO).

OBJECTIVE: While non-invasive, cuffless blood pressure (BP) measurement has demonstrated relevancy in controlled environments, ambulatory measurement is important for hypertension diagnosis and control. We present both in-lab and ambulatory BP estimation results from a diverse cohort of participants. METHODS: Participants (N=1125, aged 21-85, 49.2% female, multiple hypertensive categories) had BP measured in-lab over a 24-hour period with a subset also receiving ambulatory measurements. Radial tonometry, photoplethysmography (PPG), electrocardiography (ECG), and accelerometry signals were collected simultaneously with auscultatory or oscillometric references for systolic (SBP) and diastolic blood pressure (DBP). Predictive models to estimate BP using a variety of sensor-based feature groups were evaluated against challenging baselines. RESULTS: Despite limited availability, tonometry-derived features showed superior performance compared to other feature groups and baselines, yieldingprediction errors of 0.32 ±9.8 mmHg SBP and 0.54 ±7.7 mmHg DBP in-lab, and 0.86 ±8.7 mmHg SBP and 0.75 ±5.9 mmHg DBP for 24-hour averages. SBP error standard deviation (SD) was reduced in normotensive (in-lab: 8.1 mmHg, 24-hr: 7.2 mmHg) and younger (in-lab: 7.8 mmHg, 24-hr: 6.7 mmHg) subpopulations. SBP SD was further reduced 15-20% when constrained to the calibration posture alone. CONCLUSION: Performance for normotensive and younger participants was superior to the general population across all feature groups. Reference type, posture relative to calibration, and controlled vs. ambulatory setting all impacted BP errors. SIGNIFICANCE: Results highlight the need for demographically diverse populations and challenging evaluation settings for BP estimation studies. We present the first public dataset of ambulatory tonometry and cuffless BP over a 24-hour period to aid in future cardiovascular research.

In this work, we advance research efforts in combining the casual sketching approach of whiteboards with the machine's computing power. We present SketchInsight, a system that applies the familiar and collaborative features of a whiteboard interface to the accurate data exploration capabilities of interactive visualizations. SketchInsight enables data analysis with more fluid interaction, allowing people to visually explore their data by drawing simple charts and directly manipulating them. In addition, we report results from a qualitative study conducted to evaluate user experience in exploring data with SketchInsight, expanding our understanding on how people use a pen- and touch-enabled digital whiteboard for data exploration. We also discuss the challenges in building a working system that supports data analytic capabilities with pen and touch interaction and freeform annotation.

New sensor streams are being generated at a rapidly increasing rate. The sources of these streams are a diverse set of networked sensors, diverse both in sensing hardware and sensing modality. Machine learning algorithms are ideally placed to develop generalized methods for stream analysis. One exemplar problem is the detection and analysis of periodic structure within these streams. Our contribution is the proposal of a new machine learning framework that (i) classifies a signal as periodic or aperiodic, (ii) further analyses the signal to find periodic structure using a neural network, and (iii) groups the motifs in the periodic signals using a modified Self Organising Map algorithm. We also demonstrate the framework using data generated by an Oyster heart rate sensor. We find that the generalized approach our classifier improves the detection of signal periods by reducing the number of functions classified as periodic from 11% to 9%; however, most benefit occurs for period calculation with the number of erroneously calculated periods reducing from 14% to 4%.

Presenting and communicating insights to an audience-telling a story-is one of the main goals of data exploration. Even though visualization as a storytelling medium has recently begun to gain attention, storytelling is still underexplored in information visualization and little research has been done to help people tell their stories with data. To create a new, more engaging form of storytelling with data, we leverage and extend the narrative storytelling attributes of whiteboard animation with pen and touch interactions. We present SketchStory, a data-enabled digital whiteboard that facilitates the creation of personalized and expressive data charts quickly and easily. SketchStory recognizes a small set of sketch gestures for chart invocation, and automatically completes charts by synthesizing the visuals from the presenter-provided example icon and binding them to the underlying data. Furthermore, SketchStory allows the presenter to move and resize the completed data charts with touch, and filter the underlying data to facilitate interactive exploration. We conducted a controlled experiment for both audiences and presenters to compare SketchStory with a traditional presentation system, Microsoft PowerPoint. Results show that the audience is more engaged by presentations done with SketchStory than PowerPoint. Eighteen out of 24 audience participants preferred SketchStory to PowerPoint. Four out of five presenter participants also favored SketchStory despite the extra effort required for presentation.

The awareness that hospital patients have of the people and events surrounding their care has a dramatic impact on satisfaction and clinical outcomes. However, patients are often under-informed about even basic aspects of their care. In this work, we hypothesize that mobile devices - which are increasingly available to patients - can be used as real-time information conduits to improve patient awareness and consequently improve patient care. To better understand the unique affordances that mobile devices offer in the hospital setting, we provided twenty-five patients with mobile phones that presented a dynamic, interactive report on their progress, care plan, and care team throughout their emergency department stay. Through interviews with these patients, their visitors, and hospital staff, we explore the benefits and challenges of using the mobile phone as an information display, finding overall that this is a promising approach to improving patient awareness. Furthermore, we demonstrate that only a small number of technology challenges remain before such a system could be deployed without researcher intervention.

Computers today make it easy for people to scatter copies and versions of digital items across their file systems, but do little to help people manage the resulting mess. In this paper, we introduce the concept of a copy-aware computing ecosystem, inspired by a vision of computing when systems track and surface copy relationships between files. Based on two deployments of a copy-aware software prototype and in-depth interviews with individuals in collaborative relationships, we present our findings on the origins of copies and the barriers to eliminating them, but offer a promising solution based on the set of files that together represent a user's conceptual view of a document - the versionset. We show that the versionset is viable to infer, and we draw upon user activity logs and feedback on personalized views of versionsets to distill guidelines for the factors that define a versionset. We conclude by enumerating the many PIM user experiences that could be transformed as a result.

When information is known only to friends in a social network, traditional crowdsourcing mechanisms struggle to motivate a large enough user population and to ensure accuracy of the collected information. We thus introduce friendsourcing, a form of crowdsourcing aimed at collecting accurate information available only to a small, socially-connected group of individuals. Our approach to friendsourcing is to design socially enjoyable interactions that produce the desired information as a side effect. We focus our analysis around Collabio, a novel social tagging game that we developed to encourage friends to tag one another within an online social network. Collabio encourages friends, family, and colleagues to generate useful information about each other. We describe the design space of incentives in social tagging games and evaluate our choices by a combination of usage log analysis and survey data. Data acquired via Collabio is typically accurate and augments tags that could have been found on Facebook or the Web. To complete the arc from data collection to application, we produce a trio of prototype applications to demonstrate how Collabio tags could be utilized: an aggregate tag cloud visualization, a personalized RSS feed, and a question and answer system. The social data powering these applications enables them to address needs previously difficult to support, such as question answering for topics comprehensible only to a few of a user's friends.

Previous research has shown that faceted browsing is effective and enjoyable in searching and browsing large collections of data. In this work, we explore the efficacy of interactive visualization systems in supporting exploration and sensemaking within faceted datasets. To do this, we developed an interactive visualization system called FacetLens, which exposes trends and relationships within faceted datasets. FacetLens implements linear facets to enable users not only to identify trends but also to easily compare several trends simultaneously. Furthermore, it offers pivot operations to allow users to navigate the faceted dataset using relationships between items. We evaluate the utility of the system through a description of insights gained while experts used the system to explore the CHI publication repository as well as a database of funding grant data, and report a formative user study that identified usability issues.

We present Collabio, a social tagging game within an online social network that encourages friends to tag one another. Collabio's approach of incentivizing members of the social network to generate information about each other produces personalizing information about its users. We report usage log analysis, survey data, and a rating exercise demonstrating that Collabio tags are accurate and augment information that could have been scraped online.

Uncertainty in data occurs in domains ranging from natural science to medicine to computer science. By developing ways to include uncertainty in our information visualizations we can provide more accurate visual depictions of critical datasets. One hindrance to visualizing uncertainty is that we must first understand what uncertainty is and how it is expressed by users. We reviewed existing work from several domains on uncertainty and conducted qualitative interviews with 18 people from diverse domains who self-identified as working with uncertainty. We created a classification of uncertainty representing commonalities in uncertainty across domains and that will be useful for developing appropriate visualizations of uncertainty.

We present RelAltTab, an enhanced ALT+TAB prototype that assists users in switching windows. Our approach uses semantic and temporal information to create a list of related windows to the window that the user is currently engaged in. The main assumption is that the user is more likely to switch to a related window than to any other window in the system. We propose two different user interfaces that present the related window list to the user. We describe in detail the techniques and user interfaces of the RelAltTab system, and present the results of one user study comparing our approach to the standard Windows ALT+TAB program.

Software developers spend significant time gaining and maintaining awareness of fellow developers' activities. FASTDash is a new interactive visualization that seeks to improve team activity awareness using a spatial representation of the shared code base that highlights team members' current activities. With FASTDash, a developer can quickly determine which team members have source files checked out, which files are being viewed, and what methods and classes are currently being changed. The visualization can be annotated, allowing programmers to supplement activity information with additional status details. It provides immediate awareness of potential conflict situations, such as two programmers editing the same source file. FASTDash was developed through user-centered design, including surveys, team interviews, and in situ observation. Results from a field study show that FASTDash improved team awareness, reduced reliance on shared artifacts, and increased project-related communication. Additionally, the team that participated in our field study continues to use FASTDash.

Online pick'em games, such as the recent NCAA college basketball March Madness tournament, form a large and rapidly growing industry. In these games, players make predictions on a tournament bracket that defines which competitors play each other and how they proceed toward a single champion. Throughout the course of the tournament, players monitor the brackets to track progress and to compare predictions made by multiple players. This is often a complex sensemaking task. The classic bracket visualization was designed for use on paper and utilizes an incrementally additive system in which the winner of each match-up is rewritten in the next round as the tournament progresses. Unfortunately, this representation requires a significant amount of space and makes it relatively difficult to get a quick overview of the tournament state since competitors take arbitrary paths through the static bracket. In this paper, we present AdaptiviTree, a novel visualization that adaptively deforms the representation of the tree and uses its shape to convey outcome information. AdaptiviTree not only provides a more compact and understandable representation, but also allows overlays that display predictions as well as other statistics. We describe results from a lab study we conducted to explore the efficacy of AdaptiviTree, as well as from a deployment of the system in a recent real-world sports tournament.

In this paper we describe a novel approach for searching large data sets from a mobile phone. Existing interfaces for mobile search require keyword text entry and are not suited for browsing. Our alternative uses a hybrid model to de-emphasize tedious keyword entry in favor of iterative data filtering. We propose navigation and selection of hierarchical metadata (facet navigation), with incremental text entry to further narrow the results. We conducted a formative evaluation to understand the relative advantages of keyword entry versus facet navigation for both browse and search tasks on the phone. We found keyword entry to be more powerful when the name of the search target is known, while facet navigation is otherwise more effective and strongly preferred.

Information workers are often involved in multiple tasks and activities that they must perform in parallel or in rapid succession. In consequence, task management itself becomes yet another task that information workers need to perform in order to get the rest of their work done. Recognition of this problem has led to research on task management systems, which can help by allowing fast task switching, fast task resumption, and automatic task identification. In this paper we focus on the latter: we tackle the problem of automatically detecting the tasks that the user is involved in, by identifying which of the windows on the user's desktop are related to each other. The underlying assumption is that windows that belong to the same task share some common properties with one another that we can detect from data. We will refer to this problem as the task assignment problem.To address this problem, we have built a prototype named Swish that: (1) constantly monitors users' desktop activities using a stream of windows events; (2) logs and processes this raw event stream, and (3) implements two criteria of window "relatedness", namely the semantic similarity of their titles, and the temporal closeness in their access patterns.In addition to describing the Swish prototype in detail, we validate it with 4 hours of user data, obtaining task classification accuracies of about 70%. We also discuss our plans on including Swish in a number of intelligent user interfaces and future lines of research.

The dominant paradigm for searching and browsing large data stores is text-based: presenting a scrollable list of search results in response to textual search term input. While this works well for the Web, there is opportunity for improvement in the domain of personal information stores, which tend to have more heterogeneous data and richer metadata. In this paper, we introduce FacetMap, an interactive, query-driven visualization, generalizable to a wide range of metadata-rich data stores. FacetMap uses a visual metaphor for both input (selection of metadata facets as filters) and output. Results of a user study provide insight into tradeoffs between FacetMap's graphical approach and the traditional text-oriented approach.

The continuing trend toward greater processing power, larger storage, and in particular increased display surface by using multiple monitor supports increased multi-tasking by the computer user. The concomitant increase in desktop complexity has the potential to push the overhead of window management to frustrating and counterproductive new levels. It is difficult to adequately design for multiple monitor systems without understanding how multiple monitor users differ from, or are similar to, single monitor users. Therefore, we deployed a tool to a group of single monitor and multiple monitor users to log window management activity. Analysis of the data collected from this tool revealed that usage of interaction components may change with an increase in number of monitors, and window visibility can be a useful measure of user display space management activity, especially for multiple monitor users. The results from this analysis begin to fill a gap in research about real-world window management practices.

Our studies have shown that as displays become larger, users leave more windows open for easy multitasking. A larger number of windows, however, may increase the time that users spend arranging and switching between tasks. We present Scalable Fabric, a task management system designed to address problems with the proliferation of open windows on the PC desktop. Scalable Fabric couples window management with a flexible visual representation to provide a focus-plus-context solution to desktop complexity. Users interact with windows in a central focus region of the display in a normal manner, but when a user moves a window into the periphery, it shrinks in size, getting smaller as it nears the edge of the display. The window "minimize" action is redefined to return the window to its preferred location in the periphery, allowing windows to remain visible when not in use. Windows in the periphery may be grouped together into named tasks, and task switching is accomplished with a single mouse click. The spatial arrangement of tasks leverages human spatial memory to make task switching easier. We review the evolution of Scalable Fabric over three design iterations, including discussion of results from two user studies that were performed to compare the experience with Scalable Fabric to that of the Microsoft Windows XP TaskBar.