David Heise

Heartbeat detection from a hydraulic bed sensor using a clustering approach

Encouraged by previous performance of a hydraulic bed sensor, this work presents a new hydraulic transducer configuration which improves the systems ability to capture a heartbeat signal from four subjects with different body weight and height, gender, age and cardiac history. It also proposes a new approach for detecting the occurrence of heartbeats from ballistocardiogram (BCG) signals through the use of the k-means clustering algorithm, based on finding the location of the J-peaks. Preliminary testing showed that the new transducer arrangement was able to capture the occurrence of heartbeats for all the participants, and the clustering approach achieved correct heartbeat detection ranging from 98.6 to 100% for three of them. Some considerations are discussed regarding adjustments that can be done in order to increase the correct detection of heartbeats for the participant whose percentage of correct detection ranged from 71.0 to 92.5%.

Monitoring pulse and respiration with a non-invasive hydraulic bed sensor

A hydraulic bed sensor has been developed to non-invasively monitor pulse and respiration during sleep. This sensor is designed for in-home use, to be part of an integrated sensor network for the early detection of illness and functional decline in elderly adults. Experience with another bed sensor has motivated a desire to acquire enhanced, quantitative data related to pulse and respiration. This paper describes a working prototype, the signal processing methods used to extract data from the constructed transducer, and results from preliminary testing.

Non-invasive measurement of heartbeat with a hydraulic bed sensor Progress, challenges, and opportunities

A hydraulic bed sensor has been developed to non-invasively measure heartbeat during sleep. The motivation for this work is to enable early detection of physiological and behavioral change, thereby allowing effective interventions prior to an acute event. The transducer configuration and signal processing strategies have progressed to provide a low-cost, effective solution to eldercare monitoring needs. This sensor is now being deployed into the homes of elders in two locations, integrating into existing ambient sensor networks to generate clinician alerts and provide an improved quality of care. Challenges and opportunities remain, and this paper reports on the current progress and development of the system.

Refinement and evaluation of a hydraulic bed sensor

Research indicates that long-term monitoring of vital signs and activity in elderly adults may provide opportunities for maintaining quality-of-life and extending independence into later years. Such a strategy requires development of a system to collect this data while imposing minimal intrusion into the lives of those being monitored. To further this goal, we have developed a hydraulic bed sensor to non-invasively monitor heartbeat and respiration during sleep. This paper describes the refinement of our developed prototype and signal processing methods, along with an evaluation of the robustness of our algorithms and results from testing. An evaluation of our sensor on a group of five diverse subjects (ranging in age from 24 to 67, two with cardiac history), in three different positions, demonstrates accuracy within 8 beats per minute up to 97.5% of the time.

Acoustic detection of bees in the field using CASA with focal templates

This paper describes a method of detecting buzzes of bees in field audio. Detecting the buzzing of bees from environmental recordings is an instance of sound scene analysis. In this work, we build upon prior work in computational auditory scene analysis (CASA), employing spectral clustering techniques to mitigate the weakness of the target signal, coupled with a newly-introduced concept of “focal templates”. This system yields promising results on a previously acquired collection of environmental recordings, yielding results consistent with human performance, and, in some cases, improving upon human performance. Our success in this task suggests that the combination of focal templates and spectral clustering may prove valuable in other sound scene analysis tasks, especially when the target may be well-defined but may suffer from low signal-to-noise ratio (SNR). Survey recordings with manual (visual and acoustic) annotations were processed, and the algorithm yielded very favorable results. The potential for deploying this approach into a low-cost pollinator monitoring system is discussed.

Computing in the Arts: Curricular Innovations and Results

Computing in the Arts (CITA) is an innovative, interdisciplinary curriculum model which integrates computer science and information technology with traditional art theory and practice. At the College of Charleston, implementation of an undergraduate CITA degree program resulted in an increase in the number of female and minority students pursuing computing-related degrees. [14] With the support of the National Science Foundation (DUE 1323605) and two partner institutions, we are building a community of educators who are creating innovative instructional materials that synthesize computing and the arts. Three faculty summer workshops (Wake Forest University in 2014, College of Charleston in 2015, and University of North Carolina at Asheville in 2016) involved over 70 computer science and arts faculty from across the U.S. What has emerged are various ways of synthesizing computer science and arts, including creation of new synthesis courses, modifications to traditional computing courses, development of new CITA-like curricula, design of CITA-like project experiences for undergrads, and other creative endeavors combining computer science techniques and traditional art practices and theory. During the session, we will discuss steps involved in moving forward and keeping this community growing. The session will involve audience participation, including exchanges between the session presenters and other audience members. The goal is to share our results, hear about results from other non-presenting colleagues, and to continue to grow the teaching of computer science and computational thinking to the arts and humanities masses, as well as to further enrich traditional computer science courses with creative applications, assignments, and projects.

Flight of the bumble bee: Buzzes predict pollination services

Multiple interacting factors drive recent declines in wild and managed bees, threatening their pollination services. Widespread and intensive monitoring could lead to more effective management of wild and managed bees. However, tracking their dynamic populations is costly. We tested the effectiveness of an inexpensive, noninvasive and passive acoustic survey technique for monitoring bumble bee behavior and pollination services. First, we assessed the relationship between the first harmonic of the flight buzz (characteristic frequency) and pollinator functional traits that influence pollination success using flight cage experiments and a literature search. We analyzed passive acoustic survey data from three locations on Pennsylvania Mountain, Colorado to estimate bumble bee activity. We developed an algorithm based on Computational Auditory Scene Analysis that identified and quantified the number of buzzes recorded in each location. We then compared visual and acoustic estimates of bumble bee activity. Using pollinator exclusion experiments, we tested the power of buzz density to predict pollination services at the landscape scale for two bumble bee pollinated alpine forbs (Trifolium dasyphyllum and T. parryi). We found that the characteristic frequency was correlated with traits known to affect pollination efficacy, explaining 30–52% of variation in body size and tongue length. Buzz density was highly correlated with visual estimates of bumble bee density (r = 0.97), indicating that acoustic signals are predictive of bumble bee activity. Buzz density predicted seed set in two alpine forbs when bumble bees were permitted access to the flowers, but not when they were excluded from visiting. Our results indicate that acoustic signatures of flight can be deciphered to monitor bee activity and pollination services to bumble bee pollinated plants. We propose that applications of this technique could assist scientists and farmers in rapidly detecting and responding to bee population declines.

Launching CROMA: Computational Research On Music & Audio

This lightning talk describes the current effort to create a research group at Lincoln University to conduct Computational Research On Music & Audio (CROMA). A CROMA Team of Interdisciplinary Collaborators (CROMA-TIC) will be assembled to participate in different aspects and applications of computational audio signal processing, drawing from disciplines such as computer science, mathematics, music, psychology, and nursing. This effort is modelled upon the Centre for Interdisciplinary Research in Music Media and Technology (CIRMMT) housed at McGill University, but it will be distinct in its focus on undergraduate research. Further, this research group will be unique among Historically Black Colleges and Universities (HBCUs). A goal of assembling CROMA-TIC and establishing the CROMA-Lab is to inspire participants, especially including minority students, to seek graduate degrees while enriching their undergraduate learning experiences. The initial research aims will focus on sound event separation within musical audio, with the idea that the research conducted by CROMA-TIC will be applicable to a wide array of applications (such as improving the performance of hearing aids in noisy environments or automatic transcription of music recordings, among innumerable possibilities). This effort is just underway; interested faculty and students are invited to attend the presentation and consider participation in CROMA so that it may develop into a truly interdisciplinary, multi-institutional endeavour.

Pollination on the Dark Side: Acoustic Monitoring Reveals Impacts of a Total Solar Eclipse on Flight Behavior and Activity Schedule of Foraging Bees

Abstract The total solar eclipse of 21 August 2017 traversed ~5000 km from coast to coast of North America. In its 90-min span, sunlight dropped by three orders of magnitude and temperature by 10–15°C. To investigate impacts of these changes on bee (Hymenoptera: Apoidea) pollinators, we monitored their flights acoustically in natural habitats of Pacific Coast, Rocky Mountain, and Midwest regions. Temperature changes during the eclipse had little impact on bee activity. Most of the explained variation (R 2) in buzzing rate was attributable to changes in light intensity. Bees ceased flying during complete darkness at totality, but flight activity was unaffected by dim light in partial phases before and after totality. Flights of bees during partial phases of the eclipse lasted longer than flights made under full sun, showing that behavioral plasticity matched bee flight properties to changes in light intensity during the eclipse. Efforts of citizen scientists, including hundreds of school children, contributed to the scope and educational impact of this study.

Development of an Offset Detection Task for MIREX 2015 (Abstract Only)

Analysis of musical audio is of interest for a variety of tasks within the field of music information retrieval (MIR). One component of MIR is audio event detection, of which onset detection is one component. Audio offset detection is a complementary task to audio onset detection, but this task has received scant attention in the literature. This research will develop an offset detection task that can be included in the Music Information Retrieval Evaluation Exchange (MIREX) 2015 suite of evaluation tasks. The development of this task will provide a tool for researchers to evaluate performance of offset detection algorithms while establishing a baseline of performance for the current state-of-the-art. An existing offset detection algorithm will be utilized for testing prior to public release of the task in Summer 2015. Results of the public evaluation will be presented during the MIREX session at the 2015 International Society for Music Information Retrieval (ISMIR) conference, to be held 26-30 October 2015 in Malaga, Spain.