Mohammad Helal Uddin

The Deep Neural Networks (DNN) are computationally intensive in terms of processing, energy and memory which becomes a bottleneck to run these models on edge devices. This research study provides a technique for pruning the neural networks to enhance the performance of deep learning models in IoT devices. The proposed method combines magnitude-based pruning, which merges insignificant weights based on their magnitude, with node pruning, which eliminates insignificant nodes based on their contribution to the network. The hybrid pruning technique is designed to be energy-efficient, reducing the computational overhead of deep learning models while maintaining their accuracy. The experimental results demonstrate that the proposed method can achieve significant reductions in model size and energy consumption with minimal loss in accuracy. The technique has the potential to enable the deployment of deep learning models on resource constrained IoT devices.

COVID-19 is a life-threatening infectious disease that has become a pandemic. The virus grows within the lower respiratory tract, where early-stage symptoms (such as cough, fever, and sore throat) develop, and then it causes a lung infection (pneumonia). This paper proposes a new artificial testing methodology to determine whether a patient has been infected by COVID-19. We have presented a prediction model based on a convolutional neural network (CNN) and our own developed mathematical equation-based algorithm named SymptomNet. The CNN algorithm classifies lung infections (pneumonia) using frontal chest X-ray images, and the symptom analysis algorithm (SymptomNet) predicts the possibility of COVID-19 infection from the developed symptoms in a patient. By combining the CNN image classifier method and SymptomNet algorithm, we have developed a model that predicts COVID-19 patients with an approximate accuracy of 96%. Ten out of the 13 symptoms were significantly correlated to the COVID-19 disease. Specially, fever, cough, body chills, shortness of breath, muscle pain, and sore throat were shown to be significantly related (r = 0.20; p = 0.001, r = 0.20; p < 0.001, r = 0.22; p < 0.001, r = 0.16; p < 0.001, r = −0.45; p < 0.001, r = −0.35; p < 0.001, respectively). In this model, the CNN classifier has an accuracy of approximately 96% (training loss = 0.1311, training accuracy = 0.9596, validation loss: 0.2754, and validation accuracy of 0.9273, F1-score: 94.16, precision: 91.33), and the SymptomNet algorithm has an accuracy of 97% (485 successful predictions out of 500 samples). This research work obtained promising accuracy while predicting COVID-19-infected patients. The proposed model can be ubiquitously used at a low cost and achieve high accuracy.

Cognitive impairment has a significantly negative impact on global healthcare and the community. Holding a person’s cognition and mental retention among older adults is improbable with aging. Early detection of cognitive impairment will decline the most significant impact of extended disease to permanent mental damage. This paper aims to develop a machine learning model to detect and differentiate cognitive impairment categories like severe, moderate, mild, and normal by analyzing neurophysical and physical data. Keystroke and smartwatch have been used to extract individuals’ neurophysical and physical data, respectively. An advanced ensemble learning algorithm named Gradient Boosting Machine (GBM) is proposed to classify the cognitive severity level (absence, mild, moderate, and severe) based on the Standardised Mini-Mental State Examination (SMMSE) questionnaire scores. The statistical method “Pearson’s correlation” and the wrapper feature selection technique have been used to analyze and select the best features. Then, we have conducted our proposed algorithm GBM on those features. And the result has shown an accuracy of more than 94%. This paper has added a new dimension to the state-of-the-art to predict cognitive impairment by implementing neurophysical data and physical data together.

Recognition of activities by the use of the sensor is one of the context-conscious studies fascinated by many research teams. This paper explains how different types of physical activities are recognized using cell phone’s motion sensors data. Three types of motion sensors (accelerometer, gravity, linear acceleration) data were used for this work. An effective and efficient deep neural network model was proposed for this work that is able to recognize human physical activities from tri-axial motion sensor data in real-time which was later implemented on android-based smartphones using android studio. The sequential model was implemented for this work where LSTM, flatten and the dense layer was added. The model is able to classify seven types of human activities in the real-time data feed. The model achieves 98.8% of classification accuracy while training and testing. Later on, the model has been converted to a smartphone-compatible model using Tensorflow, as the initial deep learning model isn’t compatible to insert into smartphones. The model was successfully converted and implemented to an android based smartphone.

Neural network pruning methods can decrease the parameter counts of trained neural networks along with improving the computational performance of inference without compromising the accuracy. This work has demonstrated the effectiveness of the neural network pruning methodology, which was applied to deep learning-based human activity recognition. A long short-term memory (LSTM) architecture was used to recognize daily human activities from smartphone-based accelerometer data. An android-based application has been developed to collect the accelerometer data from smartphones. Data has been preprocessed before training the LSTM network. The accuracy of the proposed LSTM model was 97.2% while recognizing the human activities. Neural network pruning was applied to the model once the model was trained. After 70% of weight pruning on the trained/initial network, the Pruned network accuracy was similar (97.2%) as the original one. However, the accuracy of the pruned network was better than the initial model, while the network has been pruned by 25% (accuracy 97.26%), 50% (accuracy 97.29%), and 60% (accuracy 97.22%). The initial model started to slightly decline the accuracy (from 97.2% to 96.72%), while the model was pruned by 80%. In terms of neural/unit pruning, slightly declination in the accuracy (97.2% to 97.09%) occurred after 50% of pruning.

BACKGROUND COVID-19 is a life-threatening infectious disease that has become a pandemic for the time being. The virus grows within the lower respiratory tract where early-stage symptoms(like- cough, fever, sore throat, etc.) develop and then it causes lung infection(pneumonia) OBJECTIVE This paper proposed a new methodology of artificial testing whether a patient has been infected by COVID-19 or not METHODS We have presented a prediction model based on, Convolutional Neural Networks(CNN) and our own developed mathematical equation based algorithm named SymptomNet. The CNN algorithm classifies the lung infection(pneumonia) from frontal chest X-ray images, while the symptoms analyzing algorithm(SymptomNet) predicts the possibility of COVID-19 infection from developed symptoms in a patient RESULTS The model has the accuracy of 96% while predicting COVID-19 patients. In this Model, the CNN classifier has the accuracy of around 96% and the SymptomNet algorithm has the accuracy of 97%. CONCLUSIONS This research work obtained a promising accuracy while predicting COVID-19 infected patients. The proposed model can be ubiquitously used at a low cost with high accuracy.

How to cite this article: Al Mahtab M, Huq AKMF, Rahman MF, et al. Therapeutic Endoscopy during COVID-19 Pandemic: An Observational Study from Bangladesh. Euroasian J Hepato-Gastroenterol 2020;10(1): 47–49.