Search

The Covid-19 pandemic has highlighted an era in hearing health care that necessitates a comprehensive rethinking of audiology service delivery. There has been a significant increase in the number of individuals with hearing loss who seek information online. An estimated 430 million individuals worldwide suffer from hearing loss, including 11 million in the United Kingdom. The objective of this study was to identify National Health Service (NHS) audiology service social media posts and understand how they were used to communicate service changes within audiology departments at the onset of the Covid-19 pandemic. Facebook and Twitter posts relating to audiology were extracted over a six week period (March 23 to April 30 2020) from the United Kingdom. We manually filtered the posts to remove those not directly linked to NHS audiology service communication. The extracted data was then geospatially mapped, and themes of interest were identified via a manual review. We also calculated interactions (likes, shares, comments) per post to determine the posts' efficacy. A total of 981 Facebook and 291 Twitter posts were initially mined using our keywords, and following filtration, 174 posts related to NHS audiology change of service were included for analysis. The results were then analysed geographically, along with an assessment of the interactions and sentiment analysis within the included posts. NHS Trusts and Boards should consider incorporating and promoting social media to communicate service changes. Users would be notified of service modifications in real-time, and different modalities could be used (e.g. videos), resulting in a more efficient service.

Considering the ongoing climate transformations, the appropriate and reliable phenotyping information of plant leaves is quite significant for early detection of disease, yield improvement. In real-life digital agricultural environment, the real-time prediction and identification of living plants leaves has immensely grown in recent years. Hence, cost-effective and automated and timely detection of plans species is vital for sustainable agriculture. This paper presents a novel, non-invasive method aiming to establish a feasible, and viable technique for the precise identification and observation of altering behaviour of plants species at cellular level for four consecutive days by integrating machine learning (ML) and THz with a swissto12 materials characterization kit (MCK) in the frequency range of 0.75 to 1.1 THz. For this purpose, measurements observations data of seven various living plants leaves were determined and incorporate three different ML algorithms such as random forest (RF), support vector machine, (SVM), and K-nearest neighbour (KNN). The results demonstrated that RF exhibited higher accuracy of 98.87% followed by KNN and SVM with an accuracy of 94.64% and 89.67%, respectively, for precise detection of different leaves by observing their morphological features. In addition, RF outperformed other classifiers for determination of water-stressed leaves and having an accuracy of 99.42%. It is envisioned that proposed study can be proven beneficial and vital in digital agriculture technology for the timely detection of plants species to significantly help in mitigate yield and economic losses and improve crops quality.

Abstract Personalized hydration level monitoring play vital role in sports, health, wellbeing and safety of a person while performing particular set of activities. Clinical staff must be mindful of numerous physiological symptoms that identify the optimum hydration specific to the person, event and environment. Hence, it becomes extremely critical to monitor the hydration levels in a human body to avoid potential complications and fatalities. Hydration tracking solutions available in the literature are either inefficient and invasive or require clinical trials. An efficient hydration monitoring system is very required, which can regularly track the hydration level, non-invasively. To this aim, this paper proposes a machine learning (ML) and deep learning (DL) enabled hydration tracking system, which can accurately estimate the hydration level in human skin using galvanic skin response (GSR) of human body. For this study, data is collected, in three different hydration states, namely hydrated, mild dehydration (8 hours of dehydration) and extreme mild dehydration (16 hours of dehydration), and three different body postures, such as sitting, standing and walking. Eight different ML algorithms and four different DL algorithms are trained on the collected GSR data. Their accuracies are compared and a hybrid (ML+DL) model is proposed to increase the estimation accuracy. It can be reported that hybrid Bi-LSTM algorithm can achieve an accuracy of 97.83%.

Social media networks have grown exponentially over the last two decades, providing the opportunity for users of the internet to communicate and exchange ideas on a variety of topics. The outcome is that opinion mining plays a crucial role in analyzing user opinions and applying these to guide choices, making it one of the most popular areas of research in the field of natural language processing. Despite the fact that several languages, including English, have been the subjects of several studies, not much has been conducted in the area of the Arabic language. The morphological complexities and various dialects of the language make semantic analysis particularly challenging. Moreover, the lack of accurate pre-processing tools and limited resources are constraining factors. This novel study was motivated by the accomplishments of deep learning algorithms and word embeddings in the field of English sentiment analysis. Extensive experiments were conducted based on supervised machine learning in which word embeddings were exploited to determine the sentiment of Arabic reviews. Three deep learning algorithms, convolutional neural networks (CNNs), long short-term memory (LSTM), and a hybrid CNN-LSTM, were introduced. The models used features learned by word embeddings such as Word2Vec and fastText rather than hand-crafted features. The models were tested using two benchmark Arabic datasets: Hotel Arabic Reviews Dataset (HARD) for hotel reviews and Large-Scale Arabic Book Reviews (LARB) for book reviews, with different setups. Comparative experiments utilized the three models with two-word embeddings and different setups of the datasets. The main novelty of this study is to explore the effectiveness of using various word embeddings and different setups of benchmark datasets relating to balance, imbalance, and binary and multi-classification aspects. Findings showed that the best results were obtained in most cases when applying the fastText word embedding using the HARD 2-imbalance dataset for all three proposed models: CNN, LSTM, and CNN-LSTM. Further, the proposed CNN model outperformed the LSTM and CNN-LSTM models for the benchmark HARD dataset by achieving 94.69%, 94.63%, and 94.54% accuracy with fastText, respectively. Although the worst results were obtained for the LABR 3-imbalance dataset using both Word2Vec and FastText, they still outperformed other researchers’ state-of-the-art outcomes applying the same dataset.

Background The rollout of vaccines for COVID-19 in the United Kingdom started in December 2020. Uptake has been high, and there has been a subsequent reduction in infections, hospitalizations, and deaths among vaccinated individuals. However, vaccine hesitancy remains a concern, in particular relating to adverse effects following immunization (AEFIs). Social media analysis has the potential to inform policy makers about AEFIs being discussed by the public as well as public attitudes toward the national immunization campaign. Objective We sought to assess the frequency and nature of AEFI-related mentions on social media in the United Kingdom and to provide insights on public sentiments toward COVID-19 vaccines. Methods We extracted and analyzed over 121,406 relevant Twitter and Facebook posts, from December 8, 2020, to April 30, 2021. These were thematically filtered using a 2-step approach, initially using COVID-19–related keywords and then using vaccine- and manufacturer-related keywords. We identified AEFI-related keywords and modeled their word frequency to monitor their trends over 2-week periods. We also adapted and utilized our recently developed hybrid ensemble model, which combines state-of-the-art lexicon rule–based and deep learning–based approaches, to analyze sentiment trends relating to the main vaccines available in the United Kingdom. Results Our COVID-19 AEFI search strategy identified 46,762 unique Facebook posts by 14,346 users and 74,644 tweets (excluding retweets) by 36,446 users over the 4-month period. We identified an increasing trend in the number of mentions for each AEFI on social media over the study period. The most frequent AEFI mentions were found to be symptoms related to appetite (n=79,132, 14%), allergy (n=53,924, 9%), injection site (n=56,152, 10%), and clots (n=43,907, 8%). We also found some rarely reported AEFIs such as Bell palsy (n=11,909, 2%) and Guillain-Barre syndrome (n=9576, 2%) being discussed as frequently as more well-known side effects like headache (n=10,641, 2%), fever (n=12,707, 2%), and diarrhea (n=16,559, 3%). Overall, we found public sentiment toward vaccines and their manufacturers to be largely positive (58%), with a near equal split between negative (22%) and neutral (19%) sentiments. The sentiment trend was relatively steady over time and had minor variations, likely based on political and regulatory announcements and debates. Conclusions The most frequently discussed COVID-19 AEFIs on social media were found to be broadly consistent with those reported in the literature and by government pharmacovigilance. We also detected potential safety signals from our analysis that have been detected elsewhere and are currently being investigated. As such, we believe our findings support the use of social media analysis to provide a complementary data source to conventional knowledge sources being used for pharmacovigilance purposes.

High-tech services in smart cities, ubiquity of smart phones, and proliferation of social media platforms have enabled social sensing, either through direct human observers or through humans as sensor carriers and operators, such as through the use of smart phones, cameras, etc. We performed a sentiment analysis (SA) and mined public opinion on the civil services and policing authority in a smart city. The establishment of high-tech policing in Lahore, Pakistan, known as the Punjab Safe Cities Authority (PSCA), Lahore, along with integrated command and control centers and various equipments, such as 8,000 cameras, monitoring sensors, etc., has resulted in a requirement for its performance evaluation and social media–enabled opinion mining to determine the broader impact on communities. Social sensing of civil services has been enabled through the presence of the PSCA on Facebook, Twitter, YouTube, and Web TV. The SA of the local civil services is not possible without taking into account the local language. In this article, we utilize machine learning techniques to perform multi-class SA of public opinion on policing authority and the provided civil services in both the local languages Urdu and English. The support vector machine provides the highest performance multi-classification accuracy of 86.87% for positive, negative, and neutral sentiments. The temporal sentiments are determined over time from January 2020 to July 2021, with an overall positive sentiment of 62.40% and a negative sentiment of 13.51%, which shows high satisfaction of policing authority and the provided civil services.

The development of reinforced polymer composite materials has had a significant influence on the challenging problem of shielding against high-energy photons, particularly X-rays and γ-rays in industrial and healthcare facilities. Heavy materials’ shielding characteristics hold a lot of potential for bolstering concrete chunks. The mass attenuation coefficient is the main physical factor that is utilized to measure the narrow beam γ-ray attenuation of various combinations of magnetite and mineral powders with concrete. Data-driven machine learning approaches can be investigated to assess the gamma-ray shielding behavior of composites as an alternative to theoretical calculations, which are often time- and resource-intensive during workbench testing. We developed a dataset using magnetite and seventeen mineral powder combinations at different densities and water/cement ratios, exposed to photon energy ranging from 1 to 1006 kiloelectronvolt (KeV). The National Institute of Standards and Technology (NIST) photon cross-section database and software methodology (XCOM) was used to compute the concrete’s γ-ray shielding characteristics (LAC). The XCOM-calculated LACs and seventeen mineral powders were exploited using a range of machine learning (ML) regressors. The goal was to investigate whether the available dataset and XCOM-simulated LAC can be replicated using ML techniques in a data-driven approach. The minimum absolute error (MAE), root mean square error (RMSE), and R2score were employed to assess the performance of our proposed ML models, specifically a support vector machine (SVM), 1d-convolutional neural network (CNN), multi-Layer perceptrons (MLP), linear regressor, decision tree, hierarchical extreme machine learning (HELM), extreme learning machine (ELM), and random forest networks. Comparative results showed that our proposed HELM architecture outperformed state-of-the-art SVM, decision tree, polynomial regressor, random forest, MLP, CNN, and conventional ELM models. Stepwise regression and correlation analysis were further used to evaluate the forecasting capability of ML techniques compared to the benchmark XCOM approach. According to the statistical analysis, the HELM model showed strong consistency between XCOM and predicted LAC values. Additionally, the HELM model performed better in terms of accuracy than the other models used in this study, yielding the highest R2score and the lowest MAE and RMSE.

The increasing popularity of Unmanned Aerial Vehicles (UAV) has resulted in exponential growth of the market owing to numerous applications that have been facilitated by advances in battery technology and wireless communications. Given the successes of UAVs thus far, researchers are already gearing towards aerial transport systems that consist of dense deployment of both UAVs and Personal Aerial Vehicles (PAVs) with human passengers. Although the fifth-generation mobile network (5G) key performance indicators have been optimised to support drone use cases for both high data rates and low latency applications, future aerial transport systems will require stricter network key performance indicators to support the expected massive deployment of aerial vehicles taking into account network capacity and distance between the base station and the aerial vehicles, among others. In this article, we present our perspective, vision, architecture, requirements and key performance indicators for future aerial wireless networks supported by 6G for Urban Air Mobility (UAM). Furthermore, we review key enabling technologies and discuss future challenges for incorporating aerial wireless networks in 6G.

Atrial fibrillation (AF) is one of the most common types of cardiac arrhythmia, with a prevalence of 1–2% in the community, increasing the risk of stroke and myocardial infarction. Early detection of AF, typically causing an irregular and abnormally fast heart rate, can help reduce the risk of strokes that are more common among older people. Intelligent models capable of automatic detection of AF in its earliest possible stages can improve the early diagnosis and treatment. Luckily, this can be made possible with the information about the heart's rhythm and electrical activity provided through electrocardiogram (ECG) and the decision-making machine learning-based autonomous models. In addition, AF has a direct impact on the skin hydration level and, hence, can be used as a measure for detection. In this paper, we present an independent review along with a comparative analysis of the state-of-the-art techniques proposed for AF detection using ECG and skin hydration levels. This paper also highlights the effects of AF on skin hydration level that is missing in most of the previous studies.

With the advancement of social media networks, there are lots of unlabeled reviews available online, therefore it is necessarily to develop automatic tools to classify these types of reviews. To utilize these reviews for user perception, there is a need for automated tools that can process online user data. In this paper, a sentiment analysis framework has been proposed to identify people’s perception towards mobile networks. The proposed framework consists of three basic steps: preprocessing, feature selection, and applying different machine learning algorithms. The performance of the framework has taken into account different feature combinations. The simulation results show that the best performance is by integrating unigram, bigram, and trigram features.

The COVID-19 pandemic has affected more than 100 million people worldwide, with around 500,000 cases reported daily. This has led to the overwhelming of healthcare systems even in developed countries such as the US, UK, etc. Remote monitoring of COVID-19 patients with non-serious symptoms can help reduce the burden on healthcare facilities and make them available for high risk groups and the seriously affected. The pandemic has accelerated the demand for the remote patient monitoring (RPM) technologies, and the market is expected to reach 2.14 billion in 2027 from the value of 786.4 million in 2019. In RPM programs, there are two types of sensors that can be used: wearable and contactless. The former, which is currently more widely used, is not only more obtrusive and uncomfortable, but can also lead to cross-infection through patient contact. These two types of technologies are discussed and compared for each vital sign. In the respiratory system, the vital signs are the respiratory rate (RR) and oxygen saturation (SpO2), while for the latter, they are the heart rate/rhythm and the blood pressure (BP). Then, the discussion is broadened to policy level changes needed to expedite the use of such technologies for remote patient monitoring (RPM) in the world. Around 80% of countries' RPM programs are either informal or in a pilot phase, and thus lack policies and an established regulatory framework to implement their programs. The various policies needed to initiate, deliver, and reimburse RPM programs during emergency situations and outbreaks are discussed. Finally, technologies such as contactless systems, robotics, and Internet-of-things (IoT) that will revolutionize healthcare in the future by reducing the interaction between physicians and patients and cross-infection are discussed.

There is no doubt that chaotic systems are still attractive issues in various radar applications and communication systems. In this paper, we present a new 0.3 GHz mono-static microwave chaotic radar. It includes a chaotic system based on a time-delay to generate and process frequency modulated (FM) waveforms. Such a radar is designed to extract high-resolution information from the targets. To generate a continuous FM signal, the chaotic signal is first modulated using the voltage control oscillator (VCO). Next, the correct value for the loop gain (G) is carefully set when utilizing the Phase-Locked Loop (PLL) at the receiver, so that the instantaneous frequency that reflects a chaotic state variable can be reliably recovered. In this system, the PLL synchronization and radar correlation are enough to recover the echo signal and detect the target. The finding indicates that the system can be implemented with no need to use the complete self-synchronization or complex projective synchronization schemes as compared to the existing chaotic radar systems. The simulation results show that the short-time cross-correlation of the transmitted and reconstructed waveforms is good and satisfactory to detect the target under various signal-to-noise ratio (SNR) levels and with less complexity in the design.

Until now, clinicians are not able to evaluate the Psychogenic Non-Epileptic Seizures (PNES) from the rest-electroencephalography (EEG) readout. No EEG marker can help differentiate PNES cases from healthy subjects. In this paper, we have investigated the power spectrum density (PSD), in resting-state EEGs, to evaluate the abnormalities in PNES affected brains. Additionally, we have used functional connectivity tools, such as phase lag index (PLI), and graph-derived metrics to better observe the integration of distributed information of regular and synchronized multi-scale communication within and across inter-regional brain areas. We proved the utility of our method after enrolling a cohort study of 20 age- and gender-matched PNES and 19 healthy control (HC) subjects. In this work, three classification models, namely support vector machine (SVM), linear discriminant analysis (LDA), and Multilayer perceptron (MLP), have been employed to model the relationship between the functional connectivity features (rest-HC versus rest-PNES). The best performance for the discrimination of participants was obtained using the MLP classifier, reporting a precision of 85.73%, a recall of 86.57%, an F1-score of 78.98%, and, finally, an accuracy of 91.02%. In conclusion, our results hypothesized two main aspects. The first is an intrinsic organization of functional brain networks that reflects a dysfunctional level of integration across brain regions, which can provide new insights into the pathophysiological mechanisms of PNES. The second is that functional connectivity features and MLP could be a promising method to classify rest-EEG data of PNES form healthy controls subjects.

Global navigation satellite systems have been used for reliable location-based services in outdoor environments. However, satellite-based systems are not suitable for indoor positioning due to low signal power inside buildings and low accuracy of 5 m. Future smart homes demand low-cost, high-accuracy and low-power indoor positioning systems that can provide accuracy of less than 5 m and enable battery operation for mobility and long-term use. We propose and implement an intelligent, highly accurate and low-power indoor positioning system for smart homes leveraging Gaussian Process Regression (GPR) model using information-theoretic gain based on reduction in differential entropy. The system is based on Time Difference of Arrival (TDOA) and uses ultra-low-power radio transceivers working at 434 MHz. The system has been deployed and tested using indoor measurements for two-dimensional (2D) positioning. In addition, the proposed system provides dual functionality with the same wireless links used for receiving telemetry data, with configurable data rates of up to 600 Kbauds. The implemented system integrates the time difference pulses obtained from the differential circuitry to determine the radio frequency (RF) transmitter node positions. The implemented system provides a high positioning accuracy of 0.68 m and 1.08 m for outdoor and indoor localization, respectively, when using GPR machine learning models, and provides telemetry data reception of 250 Kbauds. The system enables low-power battery operation with consumption of

The health status of an elderly person can be identified by examining the additive effects of aging along with disease linked to it and can lead to ‘unstable incapacity’. This health status is determined by the apparent decline of independence in activities of daily living (ADLs). Detecting ADLs provides possibilities of improving the home life of elderly people as it can be applied to fall detection systems. This paper presents fall detection in elderly people based on radar image classification by examining their daily routine activities, using radar data that were previously collected for 99 volunteers. Machine learning techniques are used classify six human activities, namely walking, sitting, standing, picking up objects, drinking water and fall events. Different machine learning algorithms, such as random forest, K-nearest neighbours, support vector machine, long short-term memory, bi-directional long short-term memory and convolutional neural networks, were used for data classification. To obtain optimum results, we applied data processing techniques, such as principal component analysis and data augmentation, to the available radar images. The aim of this paper is to improve upon the results achieved using a publicly available dataset to further improve upon research of fall detection systems. It was found out that the best results were obtained using the CNN algorithm with principal component analysis and data augmentation together to obtain a result of 95.30% accuracy. The results also demonstrated that principal component analysis was most beneficial when the training data were expanded by augmentation of the available data. The results of our proposed approach, in comparison to the state of the art, have shown the highest accuracy.

Sentiment analysis aims to automatically classify the subject’s sentiment (e.g., positive, negative, or neutral) towards a particular aspect such as a topic, product, movie, news, etc. Deep learning has recently emerged as a powerful machine learning technique to tackle the growing demand for accurate sentiment analysis. However, the majority of research efforts are devoted to English-language only, while information of great importance is also available in other languages. This paper presents a novel, context-aware, deep-learning-driven, Persian sentiment analysis approach. Specifically, the proposed deep-learning-driven automated feature-engineering approach classifies Persian movie reviews as having positive or negative sentiments. Two deep learning algorithms, convolutional neural networks (CNN) and long-short-term memory (LSTM), are applied and compared with our previously proposed manual-feature-engineering-driven, SVM-based approach. Simulation results demonstrate that LSTM obtained a better performance as compared to multilayer perceptron (MLP), autoencoder, support vector machine (SVM), logistic regression and CNN algorithms.

Offline Arabic Handwriting Recognition (OAHR) has recently become instrumental in the areas of pattern recognition and image processing due to its application in several fields, such as office automation and document processing. However, OAHR continues to face several challenges, including high variability of the Arabic script and its intrinsic characteristics such as cursiveness, ligatures, and diacritics, the unlimited variation in human handwriting, and the lack of large public databases. In this paper, we introduce a novel context-aware model based on deep neural networks to address the challenges of recognizing offline handwritten Arabic text, including isolated digits, characters, and words. Specifically, we propose a supervised Convolutional Neural Network (CNN) model that contextually extracts optimal features and employs batch normalization and dropout regularization parameters. This aims to prevent overfitting and further enhance generalization performance when compared to conventional deep learning models. We employ a number of deep stacked-convolutional layers to design the proposed Deep CNN (DCNN) architecture. The model is extensively evaluated and shown to demonstrate excellent classification accuracy when compared to conventional OAHR approaches on a diverse set of six benchmark databases, including MADBase (Digits), CMATERDB (Digits), HACDB (Characters), SUST-ALT (Digits), SUST-ALT (Characters), and SUST-ALT (Names). A further experimental study is conducted on the benchmark Arabic databases by exploiting transfer learning (TL)-based feature extraction which demonstrates the superiority of our proposed model in relation to state-of-the-art VGGNet-19 and MobileNet pre-trained models. Finally, experiments are conducted to assess comparative generalization capabilities of the models using another language database , specifically the benchmark MNIST English isolated Digits database, which further confirm the superiority of our proposed DCNN model.

The atrial fibrillation (AF) is one of the most well-known cardiac arrhythmias in clinical practice, with a prevalence of 1–2% in the community, which can increase the risk of stroke and myocardial infarction. The detection of AF electrocardiogram (ECG) can improve the early detection of diagnosis. In this paper, we have further developed a framework for processing the ECG signal in order to determine the AF episodes. We have implemented machine learning and deep learning algorithms to detect AF. Moreover, the experimental results show that better performance can be achieved with long short-term memory (LSTM) as compared to other algorithms. The initial experimental results illustrate that the deep learning algorithms, such as LSTM and convolutional neural network (CNN), achieved better performance (10%) as compared to machine learning classifiers, such as support vectors, logistic regression, etc. This preliminary work can help clinicians in AF detection with high accuracy and less probability of errors, which can ultimately result in reduction in fatality rate.

COVID-19, caused by SARS-CoV-2, has resulted in a global pandemic recently. With no approved vaccination or treatment, governments around the world have issued guidance to their citizens to remain at home in efforts to control the spread of the disease. The goal of controlling the spread of the virus is to prevent strain on hospitals. In this paper, we focus on how non-invasive methods are being used to detect COVID-19 and assist healthcare workers in caring for COVID-19 patients. Early detection of COVID-19 can allow for early isolation to prevent further spread. This study outlines the advantages and disadvantages and a breakdown of the methods applied in the current state-of-the-art approaches. In addition, the paper highlights some future research directions, which need to be explored further to produce innovative technologies to control this pandemic.

Human motion detection is getting considerable attention in the field of Artificial Intelligence (AI) driven healthcare systems. Human motion can be used to provide remote healthcare solutions for vulnerable people by identifying particular movements such as falls, gait and breathing disorders. This can allow people to live more independent lifestyles and still have the safety of being monitored if more direct care is needed. At present wearable devices can provide real-time monitoring by deploying equipment on a person’s body. However, putting devices on a person’s body all the time makes it uncomfortable and the elderly tend to forget to wear them, in addition to the insecurity of being tracked all the time. This paper demonstrates how human motions can be detected in a quasi-real-time scenario using a non-invasive method. Patterns in the wireless signals present particular human body motions as each movement induces a unique change in the wireless medium. These changes can be used to identify particular body motions. This work produces a dataset that contains patterns of radio wave signals obtained using software-defined radios (SDRs) to establish if a subject is standing up or sitting down as a test case. The dataset was used to create a machine learning model, which was used in a developed application to provide a quasi-real-time classification of standing or sitting state. The machine-learning model was able to achieve 96.70% accuracy using the Random Forest algorithm using 10 fold cross-validation. A benchmark dataset of wearable devices was compared to the proposed dataset and results showed the proposed dataset to have similar accuracy of nearly 90%. The machine-learning models developed in this paper are tested for two activities but the developed system is designed and applicable for detecting and differentiating x number of activities.