Joe Paradiso’s research while affiliated with Massachusetts Institute of Technology and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (12)


Evaluating Head-Mounted Visual-Haptic Displays for Recovery from Unusual Flight Attitudes under Normal and Visually-Degraded Conditions
  • Article

August 2024

·

6 Reads

Proceedings of the Human Factors and Ergonomics Society Annual Meeting

Sam Chin

·

Noam Eisen

·

Brittany Bishop

·

[...]

·

Joe Paradiso

Haptics are a promising approach for improving situation awareness when visual and auditory channels are saturated. This study explores using head-mounted haptic feedback to improve pilot recovery from unusual attitudes. Seven participants were tested in Digital Combat Simulator (DCS) under two test conditions (haptic-visual, visual-only) in two environmental conditions (daytime, nighttime).


Figure 5: Experimental protocol. The top lines represent the control condition and the bottom lines represent the experimental condition. The dashed lines represent when haptic feedback is absent and a solid line represents the presence of haptic feedback. The numbers in brackets represent the number of trials.
Figure 6: Box plots of the perceived distance between two vibrotactile motors on the back. The cross mark indicates the mean value. Red dots and the red dashed line indicate the ground truth.
Figure 7: Total percent of correct response per condition during training based on mixed-effects logistic regression. The adjusted marginal prediction of a correct response is 34% (95% C.I.=[0.270, 0.410]) for the audio-only group and 54.3% (95% C.I.=[0.463, 0.624]) for the audio-haptic group. *** p<0.001 we are interested in the relative distance within a distance range determined by our hardware rather than the absolute scale. Similar to the setup of a free magnitude estimation task, we asked participants to rate the felt distance on a scale of their choice. To account for the variations in individuals' range of distance values, we first normalize each participant's score by fitting their ratings to a 0-1 scale, where 0 is the minimum rated distance, and 1 is the maximum rated distance. Concretely, within a participant, for each score, we divide the difference between the score and the minimum value over the difference between the maximum and minimum values. We first want to know if the perceptual distances of each pair of motors are distinct from each other, especially the neighboring pairs. Figure 6 shows the participants' distance estimation of the 8 pairs of vibrations. As expected, the perceived distance increases as the actual distance between the two haptic motors increases. Then we look at whether the neighboring distances can be differentiated from each other. The differences between the neighboring distances are mostly clear, except for between distances 3 and 4 and between distances 6 and 7. We then look at the direction in which the estimated distances deviate from the ground truth. The red dots and the red dashed line indicate the ground truth distance responses. Specifically, distance 3 is estimated to be bigger and distance 7 is estimated to be smaller. The top motor's position for distance 7 is near the neck, farthest away from the bottom motor. It is also worth noting the significant variance of distance 4. This shows that distances where the top motor is around the middle of the spine are notably perceptually ambiguous.
Figure 8: Percent correct response per trial over the number of trials during training. The dots represent the raw data. The lines and confidence intervals are average marginal predictions of the mixed-effect logistic regression.
Figure 9: Guess time per trial over the number of trials during training. The dots represent the raw data. The lines and confidence intervals are average marginal predictions of the mixed-effect linear regression.

+2

Purrfect Pitch: Exploring Musical Interval Learning through Multisensory Interfaces
  • Preprint
  • File available

July 2024

·

52 Reads

We introduce Purrfect Pitch, a system consisting of a wearable haptic device and a custom-designed learning interface for musical ear training. We focus on the ability to identify musical intervals (sequences of two musical notes), which is a perceptually ambiguous task that usually requires strenuous rote training. With our system, the user would hear a sequence of two tones while simultaneously receiving two corresponding vibrotactile stimuli on the back. Providing haptic feedback along the back makes the auditory distance between the two tones more salient, and the back-worn design is comfortable and unobtrusive. During training, the user receives multi-sensory feedback from our system and inputs their guessed interval value on our web-based learning interface. They see a green (otherwise red) screen for a correct guess with the correct interval value. Our study with 18 participants shows that our system enables novice learners to identify intervals more accurately and consistently than those who only received audio feedback, even after the haptic feedback is removed. We also share further insights on how to design a multisensory learning system.

Download


Figure 1: Areas of Human-Computer Interaction for Space Exploration
Proposed Workshop Schedule
SpaceCHI 2.0: Advancing Human-Computer Interaction Systems for Space Exploration

April 2022

·

348 Reads

·

8 Citations

We are now entering the new space age! In 2021, for the first time in history that there is civilian crew in space, demonstrating the next frontier of human space exploration that will not be restricted to highly trained astronauts but will be open to a more general public. However, keeping a human healthy, happy and productive in space is one of the most challenging aspects of current space programs [11]. Thus, there is an emerging opportunity for researchers in HCI to design and research new types of interactive systems and computer interfaces that can support humans living and working in space and elsewhere in the solar system. Last year, SpaceCHI workshop (https://spacechi.media.mit.edu/) at CHI 2021 welcomed over 130 participants from 20 countries around the world to present new ideas and discuss future possibilities for human-computer interaction for space exploration. The SpaceCHI 1.0, for the first time, brought together crossdisciplinary researchers from HCI, aerospace engineering, robotics, biological science, design, art, architecture to envision the future of human space exploration leading the workshop participants and organizers to form a new global community focused on HCI research for space applications. With success from the previous SpaceCHI, we are exploring the exciting opportunity for researchers in HCI to contribute to the great endeavor of space exploration by participating in our workshop.


A Scalable Solution for Signaling Face Touches to Reduce the Spread of Surface-based Pathogens

March 2021

·

30 Reads

·

15 Citations

Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies

Hand-to-Face transmission has been estimated to be a minority, yet non-negligible, vector of COVID-19 transmission and a major vector for multiple other pathogens. At the same time, as it cannot be effectively addressed with mainstream protection measures, such as wearing masks or tracing contacts, it remains largely untackled. To help address this issue, we have developed Saving Face - an app that alerts users when they are about to touch their faces, by analyzing the distortion patterns in the ultrasound signal emitted by their earphones. The system only relies on pre-existing hardware (a smartphone with generic earphones), which allows it to be rapidly scalable to billions of smartphone users worldwide. This paper describes the design, implementation and evaluation of the system, as well as the results of a user study testing the solution's accuracy, robustness, and user experience during various day-to-day activities (93.7% Sensitivity and 91.5% Precision, N=10). While this paper focuses on the system's application to detecting hand-to-face gestures, the technique can also be applicable to other types of gestures and gesture-based applications.




The Dermal Abyss: Color-Changing Tattoos for Medical Diagnostics

September 2018

·

1,154 Reads

·

5 Citations

GetMobile Mobile Computing and Communications

Can tattoos reveal changes in human physiology? The Dermal Abyss (d-abyss) presents an approach to biointerfaces in which the body surface is rendered an interactive display. Traditional tattoo inks are replaced with biosensors whose colours or intensity change in response to variations of biomarkers in the interstitial fluid. The Dermal Abyss is designed to use the aesthetics, permanence, and visible nature of tattoos to encode diagnostic information. Here, tattoo biosensors were designed to report on the concentration of sodium ions, glucose, and pH in the skin. We report the preliminary quantitative evaluation of these biosensors in an ex vivo skin model by assessing their visibility of color changes from the dermis. This work provides a proof of concept of a platform in which the skin reveals information inside the body, tattoos form wearable displays within the skin, and the body's metabolism works as an input for the d-abyss biosensors.


The dermal abyss: interfacing with the skin by tattooing biosensors

September 2017

·

799 Reads

·

53 Citations

The Dermal Abyss (d-abyss) presents an approach to biointerfaces in which the body surface is rendered as an interactive display by patterning biosensors into the skin to produce color changes in response to biomarker variations in the interstitial fluid. It combines advances in biotechnology with traditional methods in tattoo artistry. d-abyss is designed to use the aesthetics, permanence, and visible nature of tattoos to encode information. In the present work, we replace traditional inks with colorimetric and fluorescent biosensors that can report on the concentration of sodium, glucose, and pH in the interstitial fluid of the skin. We report the preliminary evaluation of these biosensors in an ex vivo skin model, assessing their visibility from the dermis. We describe different applications of d-abyss in the medical, lifestyle, and security domains. This work is a proof of concept of a platform in which the skin reveals information inside the body, tattoos form wearable displays within the skin, and the body's metabolism works as an input for the d-abyss biosensors.



Citations (6)


... Moreover, private space companies have emerged as integral players in space exploration, enhancing the democratization and accessibility of space travel. Advancements in human-computer interaction (HCI) systems are being designed to support a diverse range of missions, enabling better human integration in space environments [57]. Additionally, innovative research in areas such as space life sciences is expanding our understanding of how biological systems adapt to space conditions, furthering efforts to cultivate food in space through fermentation processes [58]. ...

Reference:

Materials Used in Space Shuttle: Evolution, Challenges, and Future Prospects – an Overview
SpaceCHI 2.0: Advancing Human-Computer Interaction Systems for Space Exploration

... Recent advances in mobile sensing technologies and artificial intelligence (AI) have led to the emergence of research on intelligent, just-in-time interventions (JITIs) using mobile or wearable devices [3,57,58,86,91,95,128]. A typical research paradigm usually starts by identifying a target undesirable behavior, followed by data collection from mobile and/or wearable devices, machine learning (ML) model development, and finally, real-time system evaluation (e.g., [3,26,46,53,79]). ...

A Scalable Solution for Signaling Face Touches to Reduce the Spread of Surface-based Pathogens
  • Citing Article
  • March 2021

Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies

... While microbes live everywhere around, on, and within us, there is often a stigma around them, especially due to the increasing number of recent epidemics (H1NI, ebola) and pandemics (COVID-19). As such, HCI researchers have begun designing products that limit direct human-microbe interactions for health and safety, resulting in self-cleaning textiles [9], touch-less interfaces [52], and wearable sanitizers [85]. This work is consequently limited by the social acceptability of microbes. ...

Wearable Sanitizer: Design and Implementation of an Open-source, On-body Sanitizer

... While biosensors for such fluids have traditionally been confined to medical devices and laboratory settings, recent HCI advancements have explored more accessible and diverse applications of these sensors. For instance, researchers have developed biofluid sensors in various forms, including epidermal devices [13,31], textiles [50], jewelry [42,49], cosmetics [41], othodontics [46] and tattoo inks [47]. These developments highlight the multidisciplinary nature of biofluid sensor research in HCI. ...

The dermal abyss: interfacing with the skin by tattooing biosensors
  • Citing Conference Paper
  • September 2017

... Especially, the use of biomaterials for close-to-body applications brings critical requirements for biocompatibility to ensure safety and user acceptance. Prior work has addressed some of these challenges by exploring wearability factors in skin interfaces [22] and body-worn colorimetric biosensors [43]. However, balancing the wearability and sustainability of such wearables can be challenging. ...

Wearability Factors for Skin Interfaces
  • Citing Conference Paper
  • February 2016

... Statistical methods are foundational in anomaly detection due to their efficiency and simplicity. Thresholding is a widely used approach where predefined limits indicate anomalies, as demonstrated by Amores et al. [55], who used an intelligent trash bin with gas sensors to monitor food quality. Another standard method, Analysis of Variance, determines significant differences between groups and is valuable for identifying unusual patterns [56]. ...

Bin-ary
  • Citing Conference Paper
  • September 2015