ABSTRACT
The World Health Organization (WHO) has declared the novel coronavirus as global pandemic on 11 March 2020. It was known to originate from Wuhan, China and its spread is unstoppable due to no proper medication and vaccine. The developed forecasting models predict the number of cases and its fatality rate for coronavirus disease 2019 (COVID-19), which is highly impulsive. This paper provides intrinsic algorithms namely - linear regression and long short-term memory (LSTM) using deep learning for time series-based prediction. It also uses the ReLU activation function and Adam optimiser. This paper also reports a comparative study on existing models for COVID-19 cases from different continents in the world. It also provides an extensive model that shows a brief prediction about the number of cases and time for recovered, active and deaths rate till January 2021.Copyright © 2023 Inderscience Enterprises Ltd.
ABSTRACT
The purpose of this paper is to enhance the performance of the virtual assistant. So, what exactly is a virtual assistant. Application software, often called virtual assistants, also known as AI assistants or digital assistants, is software that understands natural language voice commands and can perform tasks on your behalf. What does a virtual assistant do. Virtual assistants can complete practically any specific smartphone or PC activity that you can complete on your own, and the list is continually expanding. Virtual assistants typically do an impressive variety of tasks, including scheduling meetings, delivering messages, and monitoring the weather. Previous virtual assistants, like Google Assistant and Cortana, had limits in that they could only perform searches and were not entirely automated. For instance, these engines do not have the ability to forward and rewind the song in order to maintain the control function of the song;they can only have the module to search for songs and play them. Currently, we are working on a project where we are automating Google, YouTube, and many other new things to improve the functionality of this project. Now, in order to simplify the process, we've added a virtual mouse that can only be used for cursor control and clicking. It receives input from the camera, and our index finger acts as the mouse tip, our middle finger as the right click, and so forth.Copyright © 2022 Wolters Kluwer Medknow Publications. All rights reserved.
ABSTRACT
AIM: N95 masks are recommended for the healthcare providers (HCPs) taking care of patients with coronavirus disease 2019. However, the use of these masks hampers communication. We aimed to evaluate the effect of N95 masks on speech comprehension among listeners and vocal efforts (VEs) of the HCPs. MATERIALS AND METHODS: This prospective study involved 50 HCPs. We used a single observer with normal hearing to assess the difficulty in comprehension, while VE was estimated in HCPs. The speech reception threshold (SRT), speech discrimination score (SDS), and VEs were evaluated initially without using N95 mask and then repeated with HCPs wearing N95 mask. RESULTS: The use of masks resulted in a statistically significant increase in mean SRT [4.25 (1.65) dB] and VE [2.6 (0.69)], with simultaneous decrease in mean SDS [19.2 (8.77)] (all p-values < 0.0001). Moreover, demographic parameters including age, sex, and profession were not associated with change in SRT, SDS, and VE (all p-values > 0.05). CONCLUSION: Though use of N95 masks protects the HCPs against the viral infection, it results in decreased speech comprehension and increased VEs. Moreover, these issues are universal among the HCPs and are applicable to the general public as well.
ABSTRACT
The Sunshine Coast Hospital and Health Service commenced a six-month proof-of-concept to trial speech recognition and self-type software in 2020. This action was taken in response to an ageing medical transcription workforce;an increase in outpatient letters due to population growth and the novel coronavirus pandemic;and more timely transfer of care communication to GPs. The proof-of-concept presented the health service with a unique opportunity as no other public hospital in Queensland had leveraged speech recognition or self-type software for the production and distribution of outpatient letters. The proof-of-concept trial provided 18 clinicians with the choice to type or dictate outpatient letters, electronically sign, and distribute to referring general practitioners (GPs) in one transaction. The results of the proof-of-concept demonstrated a 39% uptake of speech recognition and self-type software, demonstrating an opportunity to supplement the medical transcription workforce to address the rising outpatient activity. The proof-of-concept also demonstrated an average reduction in transaction time of 25% from the baseline measure over the six-month trial period. This finding supports the timely transfer of communication to GPs. However, it will need to be carefully analysed against the participant frustrations of voice to text accuracy to minimisethe risk of poo r adoption. © Australasian College of Health Service Management. All rights reserved.
ABSTRACT
Objective: Communication difficulties are considered the most significant consequence of hearing loss. This study aimed to determine whether surgical face masks, which have been mandatory throughout the COVID-19 pandemic, have an effect on speech comprehension scores in geriatric lip-reading patients with hearing loss and to raise awareness of the need for solutions to this problem. Materials and Method: Patients with moderate and higher sensorineural or mixed bilateral symmetrical hearing loss who stated that they lip-read to better understand during communication were included in the study. The patients’ speech comprehension scores were gathered while the audiologist wore a surgical mask and then a transparent mask, respectively. Results: Twelve (33,3%) of the patients were female, and 24 (66.7%) were male. The mean age of the patients was 66.64±1.53 years. The mean speech comprehension scores of the patients when the audiologist was wearing a surgical mask (38.25±14.33) and a transparent mask (67.81 ± 14.30), respectively, were compared. The surgical mask significantly affected speech comprehension scores, and the Cohen d value of the effect size was 2.06. As such, the surgical face mask had a great effect on these patients’ speech comprehension scores. Conclusions: In elderly lip-reading patients who suffer from hearing loss, seeing the lip movements of the speaker, especially in hospital applications, promotes more effective communication. Transparent face masks can be considered a solution.
ABSTRACT
Glomus tumors are benign neoplasms that can be observed in the head and neck region. Because of their critical anatomical location, the management of patients may require consultation from multiple departments. Glomus tumors affecting the middle ear may cause various symptoms including hearing loss and tinnitus. Our aim in presenting this case report is to share our treatment method for tinnitus caused by jugular glomus tumor and to emphasize the benefit of applying an individual therapy approach, especially in patients with reduced options for getting help during the pandemic period.
ABSTRACT
Objective: This analysis describes strategies to overcome challenges posed by the COVID-19 pandemic in a clinical study involving Mild Cognitive Impairment (MCI) patients. Background: COVID-19 presents safety risks and technical difficulties for research involving in-person visits. Design/Methods: A prospective study investigating digital cognitive assessments in MCI patients was conducted in an outpatient memory clinic starting January 2020. In-person assessments were completed via tablet and paper. Recruitment paused during stay-at-home mandates for nonessential employees starting March 2020 and lasted six months. To optimize paused recruitment, study activities shifted to chart screening which also maintained grant supported study personnel. After resuming recruitment, precautions were applied, mitigating infection risk: protective glass, disinfection, temperature checks, six-foot distancing, surgical masks for patients, and respirators for staff. Participants were informed of precautions prior to scheduling a visit. Patient portal direct messaging, SMS appointment reminders, and increased compensation were implemented. Effects of masks on verbal response analysis by a speech recognition algorithm were assessed during a second, three-month pause starting January 2021. Results: 4569 medical charts were screened. 332 patients were eligible of which 190 patients declined participation with three citing COVID-19 as the reason. Four participants were enrolled prior to shutdown, 22 were analyzed for masking effects, and 62 were enrolled after the second pause (n=88, 74.9±6.8 years old, 46 female). Enrollment rates before and after portal messaging alongside increased compensation were 23.6% and 31.5%, respectively. Data suggested that masks had no effect on speech analysis. No COVID-19 cases were reported among research personnel or participants. Conclusions: The applied strategies allowed proper COVID-19 risk management without negatively affecting data quality. Rearranging study tasks mitigated the effect of recruitment pauses and transparent communication with patients regarding precautions helped instill confidence in their decision to participate, allowing for successful execution of the study. This work offers guidance for investigators faced with similar challenges.
ABSTRACT
OBJECTIVE: Analysis of the otorhinolaryngological problems caused by mask-wearing in the coronavirus disease 2019 era. METHODS: A survey with 26 questions was sent by e-mail to 576 individuals. RESULTS: The most frequently worn masks were three-layer surgical ear loop masks (n = 434, 80.1 per cent), followed by N95 or filtering facepiece code 2 masks (n = 58, 10.7 per cent), and cloth masks (n = 50, 9.2 per cent). The most bothersome symptoms caused by mask-wearing were difficulty in nasal breathing (n = 227, 41.8 per cent), nasal itching and pain (n = 93, 17.2 per cent), earache (n = 88, 16.2 per cent), difficulty in expressing oneself (n = 73, 13.5 per cent), difficulty in understanding speech (n = 56, 10.3 per cent), and ear itching (n = 5, 0.9 per cent). CONCLUSION: The problems associated with mask-wearing may result in avoidance of wearing them. Thus, there is a need for new methods that will reduce the problems related to mask-wearing, to increase their use in the community.