RESUMO
Contactless or non-invasive technology has a significant impact on healthcare applications such as the prediction of COVID-19 symptoms. Non-invasive methods are essential especially during the COVID-19 pandemic as they minimise the burden on healthcare personnel. One notable symptom of COVID-19 infection is a rapid respiratory rate, which requires constant real-time monitoring of respiratory patterns. In this paper, Software Defined Radio (SDR) based Radio-Frequency sensing technique and supervised machine learning algorithm is employed to provide a platform for detecting and monitoring various respiratory: eupnea, biot, bradypnea, sighing, tachypnea, and kussmaul. The variations in Channel State Information produced by human respiratory were utilised to identify distinct respiratory patterns using fine-grained Orthogonal Frequency-Division Multiplexing signals. The proposed platform based on the SDR and the Deep Multilayer Perceptron classifier exhibits the ability to effectively detect and classify the afore-mentioned distinct respiratory with an accuracy of up to 99%. Moreover, the effectiveness of the proposed scheme in terms of diagnosis accuracy, precision, recall, F1-score, and confusion matrix is demonstrated by comparison with a state-of-the-art machine learning classifier: Random Forest.
RESUMO
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.
Assuntos
Inteligência Artificial , Atividades Humanas , Dispositivos Eletrônicos Vestíveis , Idoso , Sistemas Computacionais , Atenção à Saúde , HumanosRESUMO
With the popularity of smart wearable systems, sensor signal processing poses more challenges to machine learning in embedded scenarios. For example, traditional machine-learning methods for data classification, especially in real time, are computationally intensive. The deployment of Artificial Intelligence algorithms on embedded hardware for fast data classification and accurate fall detection poses a huge challenge in achieving power-efficient embedded systems. Therefore, by exploiting the associative memory feature of Hopfield Neural Network, a hardware module has been designed to simulate the Neural Network algorithm which uses sensor data integration and data classification for recognizing the fall. By adopting the Hebbian learning method for training neural networks, weights of human activity features are obtained and implemented/embedded into the hardware design. Here, the neural network weight of fall activity is achieved through data preprocessing, and then the weight is mapped to the amplification factor setting in the hardware. The designs are checked with validation scenarios, and the experiment is completed with a Hopfield neural network in the analog module. Through simulations, the classification accuracy of the fall data reached 88.9% which compares well with some other results achieved by the software-based machine-learning algorithms, which verify the feasibility of our hardware design. The designed system performs the complex signal calculations of the hardware's feedback signal, replacing the software-based method. A straightforward circuit design is used to meet the weight setting from the Hopfield neural network, which is maximizing the reusability and flexibility of the circuit design.
Assuntos
Acidentes por Quedas , Inteligência Artificial , Redes Neurais de Computação , Algoritmos , Computadores , HumanosRESUMO
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.
RESUMO
BACKGROUND: Bethesda category III and IV thyroid nodules fall in the indeterminate risk of malignancy category. These nodules have been a relatively elusive entity to manage as previous studies have shown a wide variation in malignancy rates in different regions and institutions across the world. However, data from the subcontinent with regards to this is scarce. AIM AND OBJECTIVE: This study aimed to determine the characteristics and malignancy rates of cytology proven Bethesda Category III and IV thyroid nodules and its association with clinical, histopathological and laboratory variables, in the regional population. METHOD: A retrospective search was performed on all patients with thyroid nodules who presented to this hospital, from January 2011 to September 2018. Patients who had cytology proven Bethesda category III and IV thyroid nodules that underwent surgery were included in the study. RESULTS: Malignancy in Bethesda Category III and Bethesda Category IV thyroid nodules was 29.6% and 47.1%, respectively. There was no significant association determined between malignancy rate and various clinical, histopathological, and radiological characteristics. CONCLUSION: The malignancy rates in Bethesda category III and IV thyroid nodules in this study are significantly higher than that initially suggested by the Bethesda consensus publication but is comparable to international data present.
RESUMO
Objective The aim of this study was to evaluate the demographic and clinical characteristics of patients with pheochromocytoma and determine the treatment outcome with overall survival rates of patients with pheochromocytoma. Methods A retrospective, cross-sectional study was performed on all the patients with histologically proven pheochromocytoma presenting to Shaukat Khanum Memorial Cancer Hospital and Research Center (SKMCH & RC) Lahore, between August 2006 and July 2018. Clinical, biochemical and radiological data were collected at presentation, post-surgery, at discharge and till the last follow-up; data was retrieved from hospital records. Cure was defined as no evidence of disease biochemically, clinically, and structurally. Results This study included 29 patients, 69% were female. The three most common symptoms were abdominal pain (51.7%), hypertension (44.8%) and headache (41.4%). Most pheochromocytomas were sporadic (82.8%), all were adrenal gland tumors, and 89.7% were unilateral. All patients underwent adrenalectomy. Open adrenalectomy was performed in 25 patients whereas four underwent laparoscopic adrenalectomy. Fifteen patients experienced postoperative complications. The most frequently documented intraoperative complication was hypotension. Death occurred in two patients, one patient died of metastatic disease secondary to malignant pheochromocytoma and the other patient died from perioperative complications. Cure was documented biochemically and/or radiologically in 96.5% patients. Conclusions Abdominal pain was predominant presenting feature most likely due to large tumor size. Most patients presenting to SKMCH & RC, had large intra-abdominal tumors with high cure rate. Mortality was low despite high rate of perioperative complications.
RESUMO
BACKGROUND: The demand for effective use of water resources has increased because of ongoing global climate transformations in the agriculture science sector. Cost-effective and timely distributions of the appropriate amount of water are vital not only to maintain a healthy status of plants leaves but to drive the productivity of the crops and achieve economic benefits. In this regard, employing a terahertz (THz) technology can be more reliable and progressive technique due to its distinctive features. This paper presents a novel, and non-invasive machine learning (ML) driven approach using terahertz waves with a swissto12 material characterization kit (MCK) in the frequency range of 0.75 to 1.1 THz in real-life digital agriculture interventions, aiming to develop a feasible and viable technique for the precise estimation of water content (WC) in plants leaves for 4 days. For this purpose, using measurements observations data, multi-domain features are extracted from frequency, time, time-frequency domains to incorporate three different machine learning algorithms such as support vector machine (SVM), K-nearest neighbour (KNN) and decision-tree (D-Tree). RESULTS: The results demonstrated SVM outperformed other classifiers using tenfold and leave-one-observations-out cross-validation for different days classification with an overall accuracy of 98.8%, 97.15%, and 96.82% for Coffee, pea shoot, and baby spinach leaves respectively. In addition, using SFS technique, coffee leaf showed a significant improvement of 15%, 11.9%, 6.5% in computational time for SVM, KNN and D-tree. For pea-shoot, 21.28%, 10.01%, and 8.53% of improvement was noticed in operating time for SVM, KNN and D-Tree classifiers, respectively. Lastly, baby spinach leaf exhibited a further improvement of 21.28% in SVM, 10.01% in KNN, and 8.53% in D-tree in overall operating time for classifiers. These improvements in classifiers produced significant advancements in classification accuracy, indicating a more precise quantification of WC in leaves. CONCLUSION: Thus, the proposed method incorporating ML using terahertz waves can be beneficial for precise estimation of WC in leaves and can provide prolific recommendations and insights for growers to take proactive actions in relations to plants health monitoring.
RESUMO
BACKGROUND: Street children are a global phenomenon, with an estimated population of around 150 million across the world. These children include those who work on the streets but retain their family contacts, and also those who practically live on the streets and have no or limited family contacts. In Pakistan, many children are forced to work on the streets due to health-related events occurring at home which require children to play a financially productive role from an early stage. An explanatory framework adapted from the poverty-disease cycle has been used to elaborate these findings. METHODS: This study is a qualitative study, and involved 19 in-depth interviews and two key informant interviews, conducted in Rawalpindi, Pakistan, from February to May 2013. The data was audio taped and transcribed. Key themes were identified and built upon. The respondents were contacted through a gatekeeper ex-street child who was a member of the street children community. RESULTS: We asked the children to describe their life stories. These stories led us to the finding that street children are always forced to attain altered social roles because health-related problems, poverty, and large family sizes leave them no choice but to enter the workforce and earn their way. We also gathered information regarding high-risk practices and increased risks of sexual and substance abuse, based on the street children's increased exposure. These children face the issue of social exclusion because diseases and poverty push them into a life full of risks and hazards; a life which also confines their social role in the future. CONCLUSION: The street child community in Pakistan is on the rise. These children are excluded from mainstream society, and the absence of access to education and vocational skills reduces their future opportunities. Keeping in mind the implications of health-related events on these children, robust inter-sectoral interventions are required.