A5040526518- Interactive and Immersive Displays
- Personal Information Management and User Behavior
- Tactile and Sensory Interactions
- Augmented Reality Applications
- Spatial Cognition and Navigation
- EEG and Brain-Computer Interfaces
- Virtual Reality Applications and Impacts
- Usability and User Interface Design
- Gaze Tracking and Assistive Technology
- Innovative Human-Technology Interaction
- Hand Gesture Recognition Systems
- Data Visualization and Analytics
- Advanced Image and Video Retrieval Techniques
- Mobile Health and mHealth Applications
- Context-Aware Activity Recognition Systems
- Machine Learning and Data Classification
- User Authentication and Security Systems
- Neural dynamics and brain function
- Image Retrieval and Classification Techniques
- Video Analysis and Summarization
- Non-Invasive Vital Sign Monitoring
- Consumer Market Behavior and Pricing
- Indoor and Outdoor Localization Technologies
- Advanced Sensor and Energy Harvesting Materials
- Neural and Behavioral Psychology Studies
Microsoft (United States)
2010-2022
UC Davis Health System
2020
Georgetown University
2020
Microsoft Research Asia (China)
2012
Microsoft Research (United Kingdom)
2006-2010
Carnegie Mellon University
2001-2004
We present Skinput, a technology that appropriates the human body for acoustic transmission, allowing skin to be used as an input surface. In particular, we resolve location of finger taps on arm and hand by analyzing mechanical vibrations propagate through body. collect these signals using novel array sensors worn armband. This approach provides always available, naturally portable, on-body system. assess capabilities, accuracy limitations our technique two-part, twenty-participant user...
We present fingerIO, a novel fine-grained finger tracking solution for around-device interaction. FingerIO does not require instrumenting the with sensors and works even in presence of occlusions between device. achieve this by transforming device into an active sonar system that transmits inaudible sound signals tracks echoes at its microphones. To sub-centimeter level accuracies, we innovative approach use modulation technique commonly used wireless communication called Orthogonal...
Gesture is becoming an increasingly popular means of interacting with computers. However, it still relatively costly to deploy robust gesture recognition sensors in existing mobile platforms. We present SoundWave, a technique that leverages the speaker and microphone already embedded most commodity devices sense in-air gestures around device. To do this, we generate inaudible tone, which gets frequency-shifted when reflects off moving objects like hand. measure this shift infer various...
We exploit the falloff of acuity in visual periphery to accelerate graphics computation by a factor 5-6 on desktop HD display (1920x1080). Our method tracks user's gaze point and renders three image layers around it at progressively higher angular size but lower sampling rate. The are then magnified resolution smoothly composited. develop general efficient antialiasing algorithm easily retrofitted into existing code minimize "twinkling" artifacts lower-resolution layers. A standard...
Previous work has demonstrated the viability of applying offline analysis to interpret forearm electromyography (EMG) and classify finger gestures on a physical surface. We extend those results bring us closer using muscle-computer interfaces for always-available input in real-world applications. leverage existing taxonomies natural human grips develop gesture set covering interaction free space even when hands are busy with other objects. present system that classifies these real-time we...
Advances in cognitive neuroscience and brain-imaging technologies give us the unprecedented ability to interface directly with brain activity. These let monitor physical processes that correspond certain forms of thought. Researchers have begun using these build brain-computer interfaces (BCIs)—communication systems don't depend on brain's normal output pathways peripheral nerves muscles. Four short articles provide a quick overview past, present, future BCIs.
We explore the feasibility of muscle-computer interfaces (muCIs): an interaction methodology that directly senses and decodes human muscular activity rather than relying on physical device actuation or user actions are externally visible audible. As a first step towards realizing mu-CI concept, we conducted experiment to potential exploiting sensing processing technologies for muCIs. present results demonstrating accurate gesture classification with off-the-shelf electromyography (EMG)...
Machine learning is an increasingly used computational tool within human-computer interaction research. While most researchers currently utilize iterative approach to refining classifier models and performance, we propose that ensemble classification techniques may be a viable even preferable alternative. In learning, algorithms combine multiple classifiers build one superior its components. this paper, present EnsembleMatrix, interactive visualization system presents graphical view of...
The PC's increasing graphical-processing power is fueling a demand for larger and more capable display devices. Several operating systems have supported work with multiple displays some time. This fact, coupled graphic-card advancements has led to an increase in monitor (multimon) use. Large offer users significant benefits usability challenges. In this article the authors discuss those challenges along novel techniques address these issues.
We present a task-based taxonomy of navigation techniques for 3D virtual environments, used to categorize existing techniques, drive exploration the design space, and inspire new techniques. briefly discuss several describe in detail one Speed-coupled Flying with Orbiting. This technique couples control movement speed camera height tilt, allowing users seamlessly transition between local environment-views global overviews. Users can also orbit specific objects inspection. Results from two...
Large wall-sized displays are becoming prevalent. Although researchers have articulated qualitative benefits of group work on large displays, little has been done to quantify the for individual users. In this article we present four experiments comparing performance users working a projected wall display that standard desktop monitor. these experiments, held visual angle constant by adjusting viewing distance each displays. Results from first two suggest physically even when viewed at...
A reliable and unobtrusive measurement of working memory load could be used to evaluate the efficacy interfaces provide real-time user-state information adaptive systems. In this paper, we describe an experiment con-ducted explore some issues around using elec-troencephalograph (EEG) for classifying load. Within experiment, present our classification methodology, including a novel feature selection scheme that seems alleviate need complex drift modeling artifact rejection. We demonstrate...
For decades, researchers have presented different adaptive user interfaces and discussed the pros cons of adaptation on task performance satisfaction. Little research, however, has been directed at isolating understanding those aspects which make some them successful others not. We designed implemented three graphical evaluated in two experiments along with a non-adaptive baseline. In this paper we synthesize our results previous work discuss how design choices interactions affect success interfaces.
Web image search is difficult in part because a handful of keywords are generally insufficient for characterizing the visual properties an image. Popular engines have begun to provide tags based on simple characteristics images (such as black and white or that contain face), but such approaches limited by fact it unclear what end users want be able use examining results. This paper presents CueFlik, application allows quickly create their own rules re ranking characteristics. End can then...
Modern brain sensing technologies provide a variety of methods for detecting specific forms activity. In this paper, we present an initial step in exploring how these may be used to perform task classification and applied relevant manner HCI research. We describe two experiments showing successful between tasks using low-cost off-the-shelf electroencephalograph (EEG) system. the first study, achieved mean accuracy 84.0% subjects performing one three cognitive - rest, mental arithmetic,...
Computer vision and inertial measurement have made it possible for people to interact with computers using whole-body gestures. Although there has been rapid growth in the uses applications of these systems, their ubiquity limited by high cost heavily instrumenting either environment or user. In this paper, we use human body as an antenna sensing Such approach requires no instrumentation environment, only minimal user, thus enables truly mobile applications. We show robust gesture...
Recent work in muscle sensing has demonstrated the poten-tial of human-computer interfaces based on finger gestures sensed from electrodes upper forearm. While this approach holds much potential, previous given little attention to context three important real-world requirements: hardware suitable for mobile and off-desktop environments, elec-trodes that can be put quickly without adhesives or gel, gesture recognition techniques require no new training calibration after re-donning a...
Interest has been growing within HCI on the use of machine learning and reasoning in applications to classify such hidden states as user intentions, based observations. researchers with these interests typically have little expertise often employ toolkits relatively fixed "black boxes" for generating statistical classifiers. However, attempts tailor performance classifiers specific application requirements may require a more sophisticated understanding custom-tailoring methods. We present...
While non-invasive, cuffless blood pressure (BP) measurement has demonstrated relevancy in controlled environments, ambulatory is important for hypertension diagnosis and control. We present both in-lab BP estimation results from a diverse cohort of participants.Participants (N=1125, aged 21-85, 49.2% female, multiple hypertensive categories) had measured over 24-hour period with subset also receiving measurements. Radial tonometry, photoplethysmography (PPG), electrocardiography (ECG),...
Published reports suggest that males significantly outperform females in navigating virtual environments. A novel navigation technique reported CHI 2001, when combined with a large display and wide field of view, appeared to reduce gender bias. That work has been extended two studies order understand the finding under carefully controlled conditions. The first study replicated view coupled benefits both male female users reduces second suggested fields on were useful despite more densely...
Each window on our computer desktop provides a view into some information. Although users can currently manipulate multiple windows, we assert that being able to spatially arrange smaller regions of these windows could help perform certain tasks more efficiently. In this paper, describe novel interaction technique allows replicate arbitrary existing independent called WinCuts. WinCut is live region the source with which interact. We also present an extension share WinCuts across devices....
Large wall-sized displays are becoming prevalent. Although researchers have articulated qualitative benefits of group work on large displays, little has been done to quantify the for individual users. We ran two studies comparing performance users working a projected wall display that standard desktop monitor. In these studies, we held visual angle constant by adjusting viewing distance each displays. Results from first study indicate although there was no significant difference in reading...
While proponents of adaptive user interfaces tout potential performance gains, critics argue that adaptation's unpredictability may disorient users, causing more harm than good. We present a study examines the relative effects predictability and accuracy on usability UIs. Our results show increasing led to strongly improved satisfaction. Increasing also resulted in higher utilization interface. Contrary our expectations, improvement had stronger effect performance, some satisfaction ratings...