Peter Gloor | Massachusetts Institute of Technology (MIT) (original) (raw)

Papers by Peter Gloor

arXiv (Cornell University), May 10, 2020

Studies on entrepreneurship, structural change and industrial dynamics, 2018

This paper describes preliminary results of measuring the impact of human body movements on plant... more This paper describes preliminary results of measuring the impact of human body movements on plants. In particular, we analyze the influence of eurythmic gestures of human actors on lettuce and beans. In an eight week experiment, we exposed rows of lettuce and beans to weekly eurythmic movements (similar to Qi Gong) of a eurythmist, while at the same time measuring changes in voltage between the roots and leaves of lettuce and beans using the plant spikerbox (https://backyardbrains.com/products/plantspikerbox). We compared this experimental group of vegetables with a control group of vegetables whose voltage differential was also measured while never being exposed to eurythmy. Using t-tests, we found a clear difference between the experimental and the control group which was also verified with a machine learning model. In other words, the vegetables showed a noticeably different pattern in electric potentials in response to eurythmic gestures.

As the novel coronavirus disease 2019 (COVID-19) continues to rage worldwide, the United States h... more As the novel coronavirus disease 2019 (COVID-19) continues to rage worldwide, the United States has become the most affected country with more than 2.5 million total confirmed cases up to now (June 2, 2020). In this work, we investigate the predictive power of online social media and Internet search for the COVID-19 pandemic among 50 U.S. states. By collecting the state-level daily trends through both Twitter and Google Trends, we observe a high but state-different lag correlation with the number of daily confirmed cases. We further find that the predictive accuracy measured by the correlation coefficient is positively correlated to a state’s demographic, air traffic volume and GDP development. Most importantly, we show that a state’s early infection rate is negatively correlated with the lag to the previous peak in Internet search and tweeting about COVID-19, indicating that the earlier the collective awareness on Twitter/Google in a state, the lower is the infection rate.

arXiv (Cornell University), Nov 13, 2017

arXiv (Cornell University), Apr 26, 2021

Future Internet, Apr 27, 2022

Future Internet

As the coronavirus disease 2019 (COVID-19) continues to rage worldwide, the United States has bec... more As the coronavirus disease 2019 (COVID-19) continues to rage worldwide, the United States has become the most affected country, with more than 34.1 million total confirmed cases up to 1 June 2021. In this work, we investigate correlations between online social media and Internet search for the COVID-19 pandemic among 50 U.S. states. By collecting the state-level daily trends through both Twitter and Google Trends, we observe a high but state-different lag correlation with the number of daily confirmed cases. We further find that the accuracy measured by the correlation coefficient is positively correlated to a state’s demographic, air traffic volume and GDP development. Most importantly, we show that a state’s early infection rate is negatively correlated with the lag to the previous peak in Internet searches and tweeting about COVID-19, indicating that earlier collective awareness on Twitter/Google correlates with a lower infection rate. Lastly, we demonstrate that correlations bet...

arXiv (Cornell University), May 10, 2020

Studies on Entrepreneurship, Structural Change and Industrial Dynamics, 2018

Digital Transformation of Collaboration, 2020

Cognitive Computation, 2021

Speech is one of the most natural communication channels for expressing human emotions. Therefore... more Speech is one of the most natural communication channels for expressing human emotions. Therefore, speech emotion recognition (SER) has been an active area of research with an extensive range of applications that can be found in several domains, such as biomedical diagnostics in healthcare and human–machine interactions. Recent works in SER have been focused on end-to-end deep neural networks (DNNs). However, the scarcity of emotion-labeled speech datasets inhibits the full potential of training a deep network from scratch. In this paper, we propose new approaches for classifying emotions from speech by combining conventional mel-frequency cepstral coefficients (MFCCs) with image features extracted from spectrograms by a pretrained convolutional neural network (CNN). Unlike prior studies that employ end-to-end DNNs, our methods eliminate the resource-intensive network training process. By using the best prediction model obtained, we also build an SER application that predicts emotio...

More and more, user-generated content is complementing conventional journalism. While we don’t th... more More and more, user-generated content is complementing conventional journalism. While we don’t think that CNN or New York Times and its professional journalists will disappear anytime soon, formidable competition is emerging through humble Wikipedia editors. In earlier work (Becker 2012), we found that entertainment and sports news appeared on average about two hours earlier on Wikipedia than on CNN and Reuters online. In this project we build a news-reader that automatically identifies late-breaking news among the most recent Wikipedia articles and then displays it on a dedicated Web site.

In this research project we predict the moral values of individuals through their body movements ... more In this research project we predict the moral values of individuals through their body movements measured with the sensors of a smartwatch. The personal moral values are assessed using the Schwartz value theory, which proposes two dimensions of universal values (open to change versus conservative, self-enhancement versus self-transcendence). Data for all variables are gathered through the Happimeter, a smartwatch-based body-sensing system. Through multilevel mixed-effects generalized linear models, our results show that sensor and mood factors predict a person’s values. We utilized three methods to investigate the relationship between the Big Five personality traits (OCEAN: openness, conscientiousness, extraversion, agreeableness, and neuroticism) of a person and their Schwartz values. This research highlights the use of recent technological advances for studying a person’s values from an integrated perspective, combining body sensors and mood states to investigate individual behavi...

Studies on Entrepreneurship, Structural Change and Industrial Dynamics, 2018

Body signals appear to be surprisingly informative in reflecting long-term personal traits (Gloor... more Body signals appear to be surprisingly informative in reflecting long-term personal traits (Gloor et al. 2010). In this project we use the Happimeter, a smartwatch based system to correlate body-signals with mood states (Budner et al. 2017) Based on the data collected by Pebble smartwatches from over 200 individuals during a year, we are able to develop statistical learning models that have substantial predictive power over the users’ personal traits. In this short paper we describe two studies, (1) predicting FFI personality characteristics (McCrae & Costa 2003), and (2) individual creativity measured with the Torrance test (Torrance 1980).

Advances in Minimally Invasive Surgery [Working Title], 2021

Wearable technology is an emerging field that has the potential to revolutionize healthcare. Adva... more Wearable technology is an emerging field that has the potential to revolutionize healthcare. Advances in sensors, augmented reality devices, the internet of things, and artificial intelligence offer clinically relevant and promising functionalities in the field of surgery. Apart from its well-known benefits for the patient, minimally invasive surgery (MIS) is a technically demanding surgical discipline for the surgeon. In this regard, wearable technology has been used in various fields of application in MIS such as the assessment of the surgeon’s ergonomic conditions, interaction with the patient or the quality of surgical performance, as well as in providing tools for surgical planning and assistance during surgery. The aim of this chapter is to provide an overview based on the scientific literature and our experience regarding the use of wearable technology in MIS, both in experimental and clinical settings.

Studies on Entrepreneurship, Structural Change and Industrial Dynamics, 2019

Designing Networks for Innovation and Improvisation, 2016

The purpose of this study is to elaborate theory-driven models of collaborative engagement in Kno... more The purpose of this study is to elaborate theory-driven models of collaborative engagement in Knowledge Building/knowledge creation. Assessment methods from Collaborative Innovation Network theory and Knowledge Building theory were integrated to investigate the phenomenon of collective responsibility for knowledge advancement as grade 1 students engaged in creative work with ideas in Knowledge Forum. At the group level, temporal network analyses were conducted, followed by discourse analysis of student notes in Knowledge Forum. At the individual level, social network analyses were conducted, followed by content analysis of student portfolios. Results indicate that overall, the student network was relatively decentralized, with many students rotating leadership at different points in time. Student notes and portfolios suggest that community knowledge (i.e., shared ideas, theories, and explanations) became increasingly complex and sophisticated over time. Educational implications are discussed within the context of redesigning schools to increase the knowledge-creating capacity of students.

arXiv (Cornell University), May 10, 2020

Studies on entrepreneurship, structural change and industrial dynamics, 2018

This paper describes preliminary results of measuring the impact of human body movements on plant... more This paper describes preliminary results of measuring the impact of human body movements on plants. In particular, we analyze the influence of eurythmic gestures of human actors on lettuce and beans. In an eight week experiment, we exposed rows of lettuce and beans to weekly eurythmic movements (similar to Qi Gong) of a eurythmist, while at the same time measuring changes in voltage between the roots and leaves of lettuce and beans using the plant spikerbox (https://backyardbrains.com/products/plantspikerbox). We compared this experimental group of vegetables with a control group of vegetables whose voltage differential was also measured while never being exposed to eurythmy. Using t-tests, we found a clear difference between the experimental and the control group which was also verified with a machine learning model. In other words, the vegetables showed a noticeably different pattern in electric potentials in response to eurythmic gestures.

As the novel coronavirus disease 2019 (COVID-19) continues to rage worldwide, the United States h... more As the novel coronavirus disease 2019 (COVID-19) continues to rage worldwide, the United States has become the most affected country with more than 2.5 million total confirmed cases up to now (June 2, 2020). In this work, we investigate the predictive power of online social media and Internet search for the COVID-19 pandemic among 50 U.S. states. By collecting the state-level daily trends through both Twitter and Google Trends, we observe a high but state-different lag correlation with the number of daily confirmed cases. We further find that the predictive accuracy measured by the correlation coefficient is positively correlated to a state’s demographic, air traffic volume and GDP development. Most importantly, we show that a state’s early infection rate is negatively correlated with the lag to the previous peak in Internet search and tweeting about COVID-19, indicating that the earlier the collective awareness on Twitter/Google in a state, the lower is the infection rate.

arXiv (Cornell University), Nov 13, 2017

arXiv (Cornell University), Apr 26, 2021

Future Internet, Apr 27, 2022

Future Internet

As the coronavirus disease 2019 (COVID-19) continues to rage worldwide, the United States has bec... more As the coronavirus disease 2019 (COVID-19) continues to rage worldwide, the United States has become the most affected country, with more than 34.1 million total confirmed cases up to 1 June 2021. In this work, we investigate correlations between online social media and Internet search for the COVID-19 pandemic among 50 U.S. states. By collecting the state-level daily trends through both Twitter and Google Trends, we observe a high but state-different lag correlation with the number of daily confirmed cases. We further find that the accuracy measured by the correlation coefficient is positively correlated to a state’s demographic, air traffic volume and GDP development. Most importantly, we show that a state’s early infection rate is negatively correlated with the lag to the previous peak in Internet searches and tweeting about COVID-19, indicating that earlier collective awareness on Twitter/Google correlates with a lower infection rate. Lastly, we demonstrate that correlations bet...

arXiv (Cornell University), May 10, 2020

Studies on Entrepreneurship, Structural Change and Industrial Dynamics, 2018

Digital Transformation of Collaboration, 2020

Cognitive Computation, 2021

Speech is one of the most natural communication channels for expressing human emotions. Therefore... more Speech is one of the most natural communication channels for expressing human emotions. Therefore, speech emotion recognition (SER) has been an active area of research with an extensive range of applications that can be found in several domains, such as biomedical diagnostics in healthcare and human–machine interactions. Recent works in SER have been focused on end-to-end deep neural networks (DNNs). However, the scarcity of emotion-labeled speech datasets inhibits the full potential of training a deep network from scratch. In this paper, we propose new approaches for classifying emotions from speech by combining conventional mel-frequency cepstral coefficients (MFCCs) with image features extracted from spectrograms by a pretrained convolutional neural network (CNN). Unlike prior studies that employ end-to-end DNNs, our methods eliminate the resource-intensive network training process. By using the best prediction model obtained, we also build an SER application that predicts emotio...

More and more, user-generated content is complementing conventional journalism. While we don’t th... more More and more, user-generated content is complementing conventional journalism. While we don’t think that CNN or New York Times and its professional journalists will disappear anytime soon, formidable competition is emerging through humble Wikipedia editors. In earlier work (Becker 2012), we found that entertainment and sports news appeared on average about two hours earlier on Wikipedia than on CNN and Reuters online. In this project we build a news-reader that automatically identifies late-breaking news among the most recent Wikipedia articles and then displays it on a dedicated Web site.

In this research project we predict the moral values of individuals through their body movements ... more In this research project we predict the moral values of individuals through their body movements measured with the sensors of a smartwatch. The personal moral values are assessed using the Schwartz value theory, which proposes two dimensions of universal values (open to change versus conservative, self-enhancement versus self-transcendence). Data for all variables are gathered through the Happimeter, a smartwatch-based body-sensing system. Through multilevel mixed-effects generalized linear models, our results show that sensor and mood factors predict a person’s values. We utilized three methods to investigate the relationship between the Big Five personality traits (OCEAN: openness, conscientiousness, extraversion, agreeableness, and neuroticism) of a person and their Schwartz values. This research highlights the use of recent technological advances for studying a person’s values from an integrated perspective, combining body sensors and mood states to investigate individual behavi...

Studies on Entrepreneurship, Structural Change and Industrial Dynamics, 2018

Body signals appear to be surprisingly informative in reflecting long-term personal traits (Gloor... more Body signals appear to be surprisingly informative in reflecting long-term personal traits (Gloor et al. 2010). In this project we use the Happimeter, a smartwatch based system to correlate body-signals with mood states (Budner et al. 2017) Based on the data collected by Pebble smartwatches from over 200 individuals during a year, we are able to develop statistical learning models that have substantial predictive power over the users’ personal traits. In this short paper we describe two studies, (1) predicting FFI personality characteristics (McCrae & Costa 2003), and (2) individual creativity measured with the Torrance test (Torrance 1980).

Advances in Minimally Invasive Surgery [Working Title], 2021

Wearable technology is an emerging field that has the potential to revolutionize healthcare. Adva... more Wearable technology is an emerging field that has the potential to revolutionize healthcare. Advances in sensors, augmented reality devices, the internet of things, and artificial intelligence offer clinically relevant and promising functionalities in the field of surgery. Apart from its well-known benefits for the patient, minimally invasive surgery (MIS) is a technically demanding surgical discipline for the surgeon. In this regard, wearable technology has been used in various fields of application in MIS such as the assessment of the surgeon’s ergonomic conditions, interaction with the patient or the quality of surgical performance, as well as in providing tools for surgical planning and assistance during surgery. The aim of this chapter is to provide an overview based on the scientific literature and our experience regarding the use of wearable technology in MIS, both in experimental and clinical settings.

Studies on Entrepreneurship, Structural Change and Industrial Dynamics, 2019

Designing Networks for Innovation and Improvisation, 2016

The purpose of this study is to elaborate theory-driven models of collaborative engagement in Kno... more The purpose of this study is to elaborate theory-driven models of collaborative engagement in Knowledge Building/knowledge creation. Assessment methods from Collaborative Innovation Network theory and Knowledge Building theory were integrated to investigate the phenomenon of collective responsibility for knowledge advancement as grade 1 students engaged in creative work with ideas in Knowledge Forum. At the group level, temporal network analyses were conducted, followed by discourse analysis of student notes in Knowledge Forum. At the individual level, social network analyses were conducted, followed by content analysis of student portfolios. Results indicate that overall, the student network was relatively decentralized, with many students rotating leadership at different points in time. Student notes and portfolios suggest that community knowledge (i.e., shared ideas, theories, and explanations) became increasingly complex and sophisticated over time. Educational implications are discussed within the context of redesigning schools to increase the knowledge-creating capacity of students.