[ad_1]
WASHINGTON, D.C., NOVEMBER 5, 2018 – With thousands of fans cheering, singing, shouting and mocking, college basketball games can be of almost deafening intensity. Some arenas have decibels, which, accurately or otherwise, give an idea of the volume of noise generated by viewers and sound systems. However, the noise of the crowd is rarely the subject of a scientific inquiry.
"Whenever this is mentioned in the literature, it's mainly a problem that investigators are trying to get around," said Brooks Butler, undergraduate physics student at Brigham Young University and a member of the board. BYU team presenting its research at the 176th Meeting, held in conjunction with the Canadian Acoustic Association 2018 Acoustics Week in Canada, November 5-9, at the Victoria Conference Center in Ottawa. Victoria, Canada.
"The noise of the crowd is usually treated as a background interference – an element to be filtered." But BYU researchers felt that the noise of the crowd was worthy of its own investigation. In particular, they wanted to know if the machine learning algorithms could identify patterns in the raw acoustic data indicating what the crowd was doing at a given time, thus providing clues as to what was going on in the game itself . One of the possible applications of this could be the early detection of unruly or violent behavior of the crowd – although this idea has not been tested.
The BYU team performed high fidelity acoustic measurements at both men's and women's basketball games at university, before doing the same for football and volleyball games. They divided the games into half-seconds of interval by measuring the frequency content (as indicated on the spectrograms), the sound levels, the ratio between the maximum and minimum sound levels in a defined block of time, and 39, other variables. Then, they applied signal processing tools that identified 512 distinct acoustic characteristics composed of different frequency bands, amplitudes, and so on.
The group used these variables to construct a 512-dimensional space, using machine-learning techniques to perform computerized classification analysis of this complex and multidimensional domain.
Kent Gee, professor of physics at BYU University, was the principal investigator of the project alongside Professors Mark Transtrum and Sean Warnick. Together, they led a team of several students focusing on different aspects of the problem, including data collection, analysis, and machine learning.
Gee explained the process with a simple analogy. "Suppose you have a dot plot on a two-dimensional graph, x-y and you measure the distance between these points," he said. "You may notice that the points are grouped into three groups – we did something similar with our 512-dimensional space, although you obviously need a computer to track all that."
The so-called "K-means clustering" analysis they carried out revealed six distinct groups corresponding to what was going on in the arena, as people cheered, sang, booed, keep quiet or let the speakers dominate the soundscape.
In this way, Gee and his colleagues were able to measure the emotional state of the audience, simply from an automated analysis of sound data. "One of the important potential applications of our research," he said, "could be the early detection of unruly or violent behavior by the crowd."
###
Presentation # 1pSP11, "Crowd Noise Analysis from University Basketball Matches" by Brooks A. Butler, Mylan R. Cook, Kent L. Gee, Mark K. Transtrum, Sean Warnick, Eric Todd and Harald Larsen Monday, November 17: 16: 25 in the Shaughnessy (Fe) Room of the Victoria Conference Center in Victoria, British Columbia, Canada.
———————– MORE INFORMATION ON THE MEETING —————— —–
USEFUL LINKS
Main Website of the meeting: https: /
Technical Program Meeting: https: /
Hotel information: https: /
WORLD PRESS ROOM
Over the next few weeks, the ASA's global press room will be updated with additional tips on dozens of newsworthy features and popular language articles, summarized in 300 to 800 words & # 39; Presentations written by scientists for a general audience and accompanied by photos, audio, and video. You can visit the site from the end of October at http: // acoustics.
PRESS REGISTRATION
We will grant free registration to accredited journalists and professional freelance journalists. If you are a journalist and would like to attend, contact Rhys Leahy or the AIP Media Line ([email protected], 301-209-3090). We can also help you arrange interviews and obtain images, sound clips or basic information.
LIVE WEB MEDIA BROADCAST
A press conference featuring a selection of topical research will be webcast live from the conference on Tuesday, November 6, 2018. Times and topics to be clarified. Members of the media must register in advance at http: // aipwebcasting.
ABOUT ASA
The Acoustical Society of America (ASA) is the leading international scientific society in acoustics devoted to sound science and technology. Its 7,000 members worldwide represent a wide range of studies on acoustics. ASA publications include The journal of the acoustic society of America (the world's largest newspaper on acoustics), Acoustics today magazine, books and standards on acoustics. The company also organizes two major scientific meetings each year. For more information about ASA, visit https: /
About CAA
The Canadian Acoustic Association (CAA) is an interdisciplinary professional organization that promotes communication among people working in all areas of acoustics in Canada. promotes the growth and practical application of acoustical knowledge; promotes education, research, environmental protection and employment in acoustics; and is an umbrella organization through which general education, employment and research issues can be addressed at the national and multidisciplinary level. For more information on CAA, visit http: // caa-aca.
Warning: AAAS and EurekAlert! are not responsible for the accuracy of the news releases published on EurekAlert! contributing institutions or for the use of any information via the EurekAlert system.
Source link
