Flipping the Frame: How Rudy Gobert Went From an Episodic Bad Actor to a Thematic Hero

Rudy Gobert's positive COVID-19 diagnosis in March of 2020 started the process that led to American sports shutting down in the early days of the pandemic. After the diagnosis, video of him touching reporters' voice recorders at a press availability went viral. This framing analysis in five mainstream newspapers finds that over the course of 72 hours, Gobert went from a bad actor to a hero in news copy as an episodic frame focusing on his actions gave way to a thematic frame about the virus and its effects on the country.

MEMs Based Low-Cost Urban Noise Monitoring: Tests and Case Study

Noise pollution has been one of the main causes of citizens' discomfort in the urban centers in Brazil, an issue enhanced by the Covid pandemic that resulted in an increase of noise complaints, especially those related to noise from construction sites. This context triggered the construction industry to pursue solutions to understand the acoustic reality and minimize the impacts through regulations that require long-term noise measurements. Due to the necessity of a comprehensive evaluation in several locations, class 1 Sound Level Meters measurement systems can hardly be considered because of their high costs. This paper discusses the practical implementation of MEMs in a low-cost monitoring system for urban noise, focusing on construction sites. The prototype, based on a Raspberry Pi (a single-board computer model widely used in IoT projects) and a MEMs microphone with I2S interface for high-fidelity digital audio communication, was compared in a controlled environment to a Sound Level Meter of Class 1 through validation tests, such as calibration, frequency response, and dynamic range. Field measurements were also carried out in typical urban noise-generating sound environments. © 2022 Internoise 2022 - 51st International Congress and Exposition on Noise Control Engineering. All rights reserved.

Domestic Violence Detection Using Smart Microphones

Domestic violence between partners and family members is a worldwide problem increasing every day. As per academic studies and media articles, it escalated during the COVID-19 outbreak. Domestic violence can portray verbally and physically in several ways (for instance, between partners or against children and older people). Deep Learning (DL) combined with the Internet of Things (IoT) technology could support the detection of domestic violence, which is one of many societal issues. This paper describes a system that uses a Deep Learning model and smart microphones to identify domestic violence. The datasets used are from the Google AudioSet (GA) and from the Toronto Emotional Speech Set (TESS). For the training of the dataset, the system used spectrograms and MFCCs (Mel-Frequency Cepstral Coefficients). The system employs two approaches: (i) an ANN (Artificial Neural Network) model, and (ii) a ResNet model. The Resnet model obtained an accuracy of 71%. The ANN model, which brought an accuracy of 83%, was tested and loaded to a Raspberry Pi, i.e., connected to the microphone for audio recording. The recorded audio was fed to the trained model, classifying the audio, and alerting the domestic violence to relatives, friends, or volunteers registered with the system via e-mail. The designed system is compact and can be placed inside the home. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Early Detection of Covid-19 Through Cough Sound Recognition using LPC and K-NN algorithm

COVID-19 (Coronavirus Disease 2019) is an infectious disease caused by the SARS-CoV-2 virus. This disease has spread worldwide since the beginning of 2020. Patients with this highly contagious disease generally experience only mild to moderate respiratory problems such as sore throat, cough, runny nose, fever, shortness of breath, and fatigue. However, some will become seriously ill and may cause severe respiratory distress or in severe cases multiple organ failure. Therefore, early identification of COVID-19 patients is very important. In this study, a disease detection system was created using an open dataset from COUGHVID which were contained the coughing sound of the Covid-19 disease. The implementation of the cough voice recognition system uses the K-Nearest Neighbor (K-NN) machine learning method and the Linear Predictive Coding (LPC) as method of extracting features from voice. The system was built using the Raspberry Pi 3 b+ microcontroller with microphone voice input and connected to a 3.5-inch LCD touchscreen display as the interface of the system device. The test uses a coughing sound as input through a microphone and processed by LPC feature extraction. At each running process, about 399 MB of memory is used from a total of 1 GB of memory. Meanwhile, the prediction of coughing sounds with the K-NN classification algorithm using 5 neighbors produces accuracy of 62% to predict disease. © 2022 ACM.

Domestic Violence Detection Using Smart Microphones

Domestic violence between partners and family members is a worldwide problem increasing every day. As per academic studies and media articles, it escalated during the COVID-19 outbreak. Domestic violence can portray verbally and physically in several ways (for instance, between partners or against children and older people). Deep Learning (DL) combined with the Internet of Things (IoT) technology could support the detection of domestic violence, which is one of many societal issues. This paper describes a system that uses a Deep Learning model and smart microphones to identify domestic violence. The datasets used are from the Google AudioSet (GA) and from the Toronto Emotional Speech Set (TESS). For the training of the dataset, the system used spectrograms and MFCCs (Mel-Frequency Cepstral Coefficients). The system employs two approaches: (i) an ANN (Artificial Neural Network) model, and (ii) a ResNet model. The Resnet model obtained an accuracy of 71%. The ANN model, which brought an accuracy of 83%, was tested and loaded to a Raspberry Pi, i.e., connected to the microphone for audio recording. The recorded audio was fed to the trained model, classifying the audio, and alerting the domestic violence to relatives, friends, or volunteers registered with the system via e-mail. The designed system is compact and can be placed inside the home. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Telemedicine System Based on Mixed Reality and Cognitive Speech Service Technologies

Because of the prevalence of COVID-19, medical capacity reduction, and inconvenience due to epidemic prevention policies, the development of telemedicine has been emphasized. An AI sensing device (i.e., Azure Kinect DK) with a mixed reality device (i.e., HoloLens 2) and window application are combined to design a system that completes the consultation process from a distance. This registering system uses an SQL server database, which reads the data of registered patients, selects the registration time and department on its own, and converts the data by PC/SC with an ISO7816 database. For the window application, the patient side screen and audio content for the window screen are captured through the lens and microphone array of Azure Kinect DK. HoloLens 2 is used as the main device on the doctor's side to design the window application for dictating case conversion and transmission, whereas the Unity engine is used to create mixed-reality scenes for viewing medical records and photos of patients. In the consultation part, doctor and patient devices use Dynamic 365 Assist to conduct video consultations via Microsoft Teams, transforming the traditional consultation form into a remote consultation service via the Internet. The consultation process records the consultation data by voice and then the prescription by Speech to Text and Azure cognitive voice service. It is expected to develop a hybrid-reality telemedicine system and combine metaverse-related technologies for more online interactive service functions. The future development goal is to integrate the virtual reality rehabilitation training system further to make the application of telemedicine more complete. © 2022 IEEE.

Toward an intellectual capital cyber security theory: insights from Lebanon

Purpose>Intellectual capital (IC) cyber security is a priority in all organizations. Because of the dearth in IC cyber security (ICCS) research theories and the constant call to theory building, this study proposes a theory of ICCS drawing upon tested empirical data of information systems security (ISS) theory in Lebanon.Design/methodology/approach>After a pilot test, the authors tested the newly developed ISS theory using a field study consisting of 187 respondents, representing many industries, thus contributing to generalizability. ISS theory is used as a proxy for the development of ICCS theory.Findings>Based on a review of the literature from the past three decades in the information systems (IS) discipline and a discovery of the partial yet significant relevance of ISS literature to ICCS, this study succinctly summarized the antecedents and independent variables impacting security compliance behavior, putting the variables into one comprehensive yet parsimonious theoretical model. This study shows the theoretical and practical relevancy of ISS theory to ICCS theory building.Practical implications>This paper highlights the importance of ISS compliance in the context of ICCS, especially in the area of spoken knowledge in environments containing Internet-based security devices.Originality/value>This research article is original, as it presents the theory of ICCS, which was developed by drawing upon a comprehensive literature review of the IS discipline and finding the bridges between the security of both IS and IC.

Do You Have the Energy for This Meeting?: An Empirical Study on the Energy Consumption of the Google Meet and Zoom Android apps

Context. With 'work from home' policies becoming the norm during the COVID-19 pandemic, videoconferencing apps have soared in popularity, especially on mobile devices. However, mobile devices only have limited energy capacities, and their batteries degrade slightly with each charge/discharge cycle. Goal. With this research we aim at comparing the energy consumption of two Android videoconferencing apps, and studying the impact that different features and settings of these apps have on energy consumption. Method. We conduct an empirical experiment by utilizing as subjects Google Meet and Zoom. We test the impact of multiple factors on the energy consumption: number of call participants, microphone and camera use, and virtual backgrounds. Results. Zoom results to be more energy efficient than Google Meet, albeit only to a small extent. Camera use is the most energy greedy feature, while the use of virtual background only marginally impacts energy consumption. Number of participants affect differently the energy consumption of the apps. As exception, microphone use does not significantly affect energy consumption. Conclusions. Most features of Android videoconferencing apps significantly impact their energy consumption. As implication for users, selecting which features to use can significantly prolong their mobile battery charge. For developers, our results provide empirical evidence on which features are more energy-greedy, and how features can impact differently energy consumption across apps. © 2022 ACM.

Efficient and Explainable Deep Neural Networks for Airway Symptom Detection in Support of Wearable Health Technology

Mobile health wearables are often embedded with small processors for signal acquisition and analysis. These embedded wearable systems are, however, limited with low available memory and computational power. Advances in machine learning, especially deep neural networks (DNNs), have been adopted for efficient and intelligent applications to overcome constrained computational environments. Herein, evolutionary algorithms are used to find novel DNNs that are accurate in classifying airway symptoms while allowing wearable deployment. As opposed to typical microphone‐acoustic signals, mechano‐acoustic data signals, which did not contain identifiable speech information for better privacy protection, are acquired from laboratory‐generated and publicly available datasets. The optimized DNNs had a low model file size of less than 150 kB and predicted airway symptoms of interest with 81.49% accuracy on unseen data. By performing explainable AI techniques, namely occlusion experiments and class activation maps, mel‐frequency bands up to 8,000 Hz are found as the most important feature for the classification. It is further found that DNN decisions are consistently relying on these specific features, fostering trust and transparency of the proposed DNNs. The proposed efficient and explainable DNN is expected to support edge computing on mechano‐acoustic sensing wearables for remote, long‐term monitoring of airway symptoms.

A Data-Driven Approach to Quantify and Measure Students’ Engagement in Synchronous Virtual Learning Environments

In face-to-face learning environments, instructors (sub)consciously measure student engagement to obtain immediate feedback regarding the training they are leading. This constant monitoring process enables instructors to dynamically adapt the training activities according to the perceived student reactions, which aims to keep them engaged in the learning process. However, when shifting from face-to-face to synchronous virtual learning environments (VLEs), assessing to what extent students are engaged to the training process during the lecture has become a challenging and arduous task. Typical indicators such as students’ faces, gestural poses, or even hearing their voice can be easily masked by the intrinsic nature of the virtual domain (e.g., cameras and microphones can be turned off). The purpose of this paper is to propose a methodology and its associated model to measure student engagement in VLEs that can be obtained from the systematic analysis of more than 30 types of digital interactions and events during a synchronous lesson. To validate the feasibility of this approach, a software prototype has been implemented to measure student engagement in two different learning activities in a synchronous learning session: a masterclass and a hands-on session. The obtained results aim to help those instructors who feel that the connection with their students has weakened due to the virtuality of the learning environment.

An Assessment of an Online Flipped-style Classroom Instruction for Mechanical and Aerospace Engineering Students

During the Spring 2020 semester at Old Dominion University (ODU), a completely online mode of instruction was adopted to arrest the Coronavirus Disease 2019 (COVID-19) outbreak. As a consequence, each unit within the university was practically required to make its own arrangement to ensure the students and faculty were well equipped to smoothly transition to the new mode of instruction and at the same time, ensure student success in the program. The Department of Mechanical and Aerospace Engineering (MAE) at ODU responded with an effective strategy to equip its faculty with a cost-effective, timely solution to transition to the new mode of instruction. As part of MAE department's strategy to equip its faculty with low-cost, simple-to-use equipment, a minimalistic hardware setup was identified, which would consist of - (i) a camera/webcam, (ii) a microphone, and (iii) an adjustable webcam stand. The MAE department bought several Logitech webcams, which came with a built-in microphone, and flexible gooseneck camera stands with C-clamp desk mounts. A simple assembly of this setup connected to a computer was used to - (i) pre-record lectures and (ii) conduct live sessions. For seamless recording, it was recommended that the Zoom application - a video conferencing, web conferencing, webinar hosting, screen sharing computer software - be installed on the computer used for online instruction. An elaborate user manual was prepared for using the hardware setup along with the Zoom application for online instruction. This article discusses elements of the cost-effective, timely solution adopted by the MAE department at ODU. It describes the implementation of a completely online flipped-style classroom instruction using a low-cost, simple-to-use equipment. To assess the effectiveness of the online flipped-style classroom instruction, the article presents the results of a survey conducted among the students of a MAE course. © American Society for Engineering Education, 2021

Identification of Soft Tissue-Mimicking Materials and Application in the Characterization of Sensors for Lung Sounds

Early diagnosis of pulmonary implications is fundamental for the treatment of several diseases, such as idiopathic pulmonary fibrosis, rheumatoid arthritis, connective tissue diseases and interstitial pneumonia secondary to COVID-19 among the many. Recent studies prove that a wide class of pulmonary diseases can be early detected by auscultation and suitably developed algorithms for the analysis of lung sounds. Indeed, the technical characteristics of sensors have an impact on the quality of the acquired lung sounds. The availability of a fair and quantitative approach to sensors’comparison is a prerequisite for the development of new diagnostic tools. In this work the problem of a fair comparison between sensors for lung sounds is decoupled into two steps. The first part of this study is devoted to the identification of a synthetic material capable of mimicking the acoustic behavior of human soft tissues;this material is then adopted as a reference. In the second part, the standard skin is exploited to quantitatively compare several types of sensors in terms of noise floor and sensitivity. The proposed methodology leads to reproducible results and allows to consider sensors of different nature, e.g. laryngophone, electret microphone, digital MEMS microphone, mechanical phonendoscope and electronic phonendoscope. Finally, the experimental results are interpreted under the new perspective of equivalent sensitivity and some important guidelines for the design of new sensors are provided. These guidelines could represent the starting point for improving the devices for acquisition of lung sounds. IEEE