Wearable Temperature Sensor and Artificial Intelligence to Reduce Hospital Workload

Patient sensing and data analytics provide information that plays an important role in the patient care process. Patterns identified from data and Machine Learning (ML) algorithms can identify risk/abnormal patients' data. Due to automatization this process can reduce workload of medical staff, as the algorithms alert for possible problems. We developed an integrated approach to monitor patients' temperature applied to COVID-19 elderly patients and an ML process to identify abnormal behavior with alerts to physicians. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

When Evil Calls: Targeted Adversarial Voice over IP Network

As the COVID-19 pandemic fundamentally reshaped the remote life and working styles, Voice over IP (VoIP) telephony and video conferencing have become a primary method of connecting communities together. However, little has been done to understand the feasibility and limitations of delivering adversarial voice samples via such communication channels. In this paper, we propose TAINT-Targeted Adversarial Voice over IP Network, the first targeted, query-efficient, hard label black-box, adversarial attack on commercial speech recognition platforms over VoIP. The unique channel characteristics of VoIP pose significant new challenges, such as signal degradation, random channel noise, frequency selectivity, etc. To address these challenges, we systematically analyze the structure and channel characteristics of VoIP through reverse engineering. A noise-resilient efficient gradient estimation method is then developed to ensure a steady and fast convergence of the adversarial sample generation process. We demonstrate our attack in both over-the-air and over-the-line settings on four commercial automatic speech recognition (ASR) systems over the five most popular VoIP Conferencing Software (VCS). We show that TAINT can achieve performance that is comparable to the existing methods even with the addition of VoIP channel. Even in the most challenging scenario where there is an active speaker in Zoom, TAINT can still succeed within 10 attempts while staying out of the speaker focus of the video conference. © 2022 Owner/Author.

Forensic Analysis of Microsoft Teams: Investigating Memory, Disk and Network

Videoconferencing applications have seen a jump in their userbase owing to the COVID-19 pandemic. The security of these applications has certainly been a hot topic since millions of VoIP users’ data is involved. However, research pertaining to VoIP forensics is still limited to Skype and Zoom. This paper presents a detailed forensic analysis of Microsoft Teams, one of the top 3 videoconferencing applications, in the areas of memory, disk-space and network forensics. Extracted artifacts include critical user data, such as emails, user account information, profile photos, exchanged (including deleted) messages, exchanged text/media files, timestamps and Advanced Encryption Standard encryption keys. The encrypted network traffic is investigated to reconstruct client-server connections involved in a Microsoft Teams meeting with IP addresses, timestamps and digital certificates. The conducted analysis demonstrates that, with strong security mechanisms in place, user data can still be extracted from a client’s desktop. The artifacts also serve as digital evidence in the court of Law, in addition to providing forensic analysts a reference for cases involving Microsoft Teams. © 2022, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

Design of Campus Health Information System using Face Recognition and Body Temperature Detection

Currently under the epidemic crisis of COVID-19, campus epidemic prevention has become a hot topic, and temperature detecting equipment has become a necessity in public spaces. However, temperature detection systems that are widely sold on the market are relatively simple and cannot recognize personal identity. Besides, they cannot record individual temperature changes, and they are still inadequate in terms of managing personal health information. In this study, we proposed a system that can meet the needs of campus epidemic prevention called CHIS (Campus Health Information System). In CHIS, an infrared sensor is used for temperature detection and combined with face recognition. The body temperature is recorded while face recognition is performed, and the face ID and the collected real-time body temperature are transmitted to the cloud for viewing and managing by the school. The data will be managed centrally in the cloud and will be cleaned during daily processing. In the end, the student's health data history will be stored only in their personal Pod (Personal online datastore), a decentralized personal cloud data model that prevents the risk of large-scale data leakage due to centralized management. The combination of body temperature detection and face recognition avoids substituting the presence of a real person with photos or pictures, which further enhances security. It also reduces the risk of infection prompted by human detection, which increases safety. © 2021 IEEE.

Visualization of the Epidemic Situation of COVID-19

The COVID-19 epidemic has extremely attracted our attentions and lots of maps and visualization charts were created to represent and disseminate the information about COVID-19 in time, which exactly became a key role for the public to acquire and understand the quantitative information and spatial-temporal information of COVID-19. The paper analyzed the dimension of data for COVID-19 and processing levels about them, then divided the COVID-19 visualization into three types, that is 1-order visualization, 2-order visualization and multi-order visualization for COVID-19, based on direct data or indirect data of COVID-19 with the corresponding visualization methods, characteristics and information transmission Shortcomings and weakness of visualization methods for COVID-19 were analyzed in details, from the aspects of multiple scale unit in spatial data statistics, max value dealing in data classification, also many key design points were described including color connotation in disease visualization, the influences of area / unit size in visualization, symbol overlapping, multiple-scale heat maps and labels in statistical tables. The paper indicated the visualization traps of COVID-19, such as misuse of visual effects and excessive visualization, and reasonable abilities of COVID-19 visualization including map-story narrative methods and visualization pertinence for specific problems should be considered sufficiently to provide the references for cartographers to design the maps and for readers to understand the maps. 2021, Science Press. All right reserved.