Multi-branch sustainable convolutional neural network for disease classification

Pandemic and natural disasters are growing more often, imposing even more pressure on life care services and users. There are knowledge gaps regarding how to prevent disasters and pandemics. In recent years, after heart disease, corona virus disease-19 (COVID-19), brain stroke, and cancer are at their peak. Different machine learning and deep learning-based techniques are presented to detect these diseases. Existing technique uses two branches that have been used for detection and prediction of disease accurately such as brain hemorrhage. However, existing techniques have been focused on the detection of specific diseases with double-branches convolutional neural networks (CNNs). There is a need to develop a model to detect multiple diseases at the same time using computerized tomography (CT) scan images. We proposed a model that consists of 12 branches of CNN to detect the different types of diseases with their subtypes using CT scan images and classify them more accurately. We proposed multi-branch sustainable CNN model with deep learning architecture trained on the brain CT hemorrhage, COVID-19 lung CT scans and chest CT scans with subtypes of lung cancers. Feature extracted automatically from preprocessed input data and passed to classifiers for classification in the form of concatenated feature vectors. Six classifiers support vector machine (SVM), decision tree (DT), K-nearest neighbor (K-NN), artificial neural network (ANN), naïve Bayes (NB), linear regression (LR) classifiers, and three ensembles the random forest (RF), AdaBoost, gradient boosting ensembles were tested on our model for classification and prediction. Our model achieved the best results on RF on each dataset. Respectively, on brain CT hemorrhage achieved (99.79%) accuracy, on COVID-19 lung CT scans achieved (97.61%), and on chest CT scans dataset achieved (98.77%). © 2023 Wiley Periodicals LLC.

Tocilizumab in severe COVID-19 – A randomized, double-blind, placebo-controlled trial

Background: The therapeutic effectiveness of interleukin-6 receptor inhibitor in critically ill hospitalized patients with coronavirus disease 2019 (COVID-19) is uncertain. Methods: To evaluate the efficacy and safety of the outcome as recovery or death of tocilizumab for severe acute respiratory syndrome-coronavirus-2 (SARS-CoV-2) infection, we conducted a randomized, double-blinded, placebo-controlled phase 2 trial in critically ill COVID-19 adult patients. The patients were randomly assigned in a 4:1 ratio to receive standard medical treatment plus the recommended dose of either tocilizumab or the placebo drug. Randomization was stratified. The primary outcome was the recovery or death after administration of tocilizumab or a placebo drug. The secondary outcomes were clinical recovery or worsening of the patients' symptoms and inflammatory markers and discharge from the hospital. Results: Of 190 patients included in this study, 152 received tocilizumab, and 38 received a placebo. The duration of hospital stay of the interventional group was 12.9 ± 9.2, while the placebo group had a more extended hospital stay (15.6 ± 8.8). The mortality ratio for the primary outcome, ie, mortality or recovery in the tocilizumab group was 17.8%;p = 0.58 by log-rank test). The mortality ratio in the placebo group was 76.3%;p = 0.32 by log-rank test). The inflammatory markers in the tocilizumab group significantly declined by day 16 compared to the placebo group. Conclusions: The use of tocilizumab was associated with decreased mortality, earlier improvement of inflammatory markers, and reduced hospital stay in patients with severe COVID-19. © 2022 The Author(s)

Adoption of social media-based knowledge-sharing behaviour and authentic leadership development: evidence from the educational sector of Pakistan during COVID-19

Purpose: This research paper aims to explore the influence of social media–based knowledge-sharing intentions (SMKI) on prospective authentic leadership development (ALD) to deal with the future crisis. In the existing literature, to the best of the authors' knowledge, there is no significant empirical evidence to test the relationship between SMKI and ALD. Thus, this study contributes to the growing literature regarding the role of SMKIs, ALD, social media–based knowledge-sharing behavior (SMKB) and facilitating conditions (FCs). However, in this study, the authors developed a conceptual framework based on technology adoption and leadership theory. It was used to identify preservice educational leaders' SMKIs and their effect on ALD to deal with an educational crisis during the COVID-19 pandemic. Furthermore, SMKIs are strengthening ALD, directly and indirectly, using SMKB and FCs. Design/methodology/approach: In this study, the higher education students are considered preservice leaders who were enrolled in educational leadership and management programs. However, this study's target population and sample are students enrolled in educational leadership and management programs. Therefore, higher education students are considered preservice educational leaders. Therefore, a multilevel questionnaire survey approach was adopted to collect data from preservice educational leaders (n = 451 at Time 1 and n = 398 at Time 2) enrolled in education departments in the selected universities in Pakistan. A total of 398 survey questionnaires were finalized with a return ratio of 89%. The partial least square structural equation modeling with SmartPLS 3.2.8 was used for the data analysis. Findings: This research found that SMKIs are positively and significantly connected with ALD. This study also confirms that SMKB significantly and positively mediates the relationship between SMKIs and ALD. Therefore, this study concludes that preservice educational leaders were ready to adopt SMKB. Practical implications: Social media–based knowledge sharing can be helpful to develop authentic leadership among preservice educational leaders during a crisis. Preservice educational leaders as authentic leaders can prove to be an asset in dealing with the COVID-19 pandemic crisis. Originality/value: This research integrated the technology adoption model and leadership theory to provide empirical evidence of SMKIs' direct and indirect influence on ALD through social media–based knowledge-sharing actual use behavior by preservice educational leaders during the COVID-19 pandemic. Moreover, the moderated mediating effect of the FCs was also studied in the relationship between SMKIs and actual user behavior as well as ALD. © 2022, Emerald Publishing Limited.

Covid-19 Vaccine Acceptance, Intention to Participate and its Associated Adverse Events Happening among the Vaccinated Population of Lahore, Pakistan

Background: This cross-sectional study being instrumented by a close ended questionnaire was conducted to evaluate society's affirmation for being jabbed with COVID-19 vaccine, their acquisition towards immunization and associated anomalies in vaccinated people. According to the recent update from WHO, the glob is facing 5th wave of pandemic "Omicron". However, the problem is that vaccines were in trials. Majority of people were demonstrating reluctance for being immunization against COVID-19 due prevailing oddities after vaccination. Aim(s): To measure the possible adverse effects caused by the vaccination and society's participation towards immunization. Methodology: In this study we adapted cross sectional study design by means of convenience sampling. Study instrument was a close ended questionnaire. Data was collected from only vaccinated participants by visiting universities, medical personnel, colleges and other society sectors under the supervision of team members. Data transferred to software SPSS to extract the results. Cross tabulation was used for demographic analysis such as age, gender and vaccine type jabbed. Result(s): The most common adverse effects include inflammation at site of injection, fever, nausea and vomiting, diarrhea, abdominal pain, joint pain and numbness of limbs were highlighted. Mostly jabbed vaccine types include Sinopharm and Sinovac. Majority of respondents showed willingness for immunization however, only a small proportion was afraid for being vaccinated. The significance in our study that we have conducted study for acceptance of vaccine, intention of participants towards immunization and adverse events associated with different types of COVID-19 vaccines in vaccinated population residing in different towns of Lahore, Pakistan. Conclusion(s): In our local population, majority accepted the vaccine and didn't deny to administer the vaccine. Pain, redness, lethargy, nausea, vomiting, diarrhea, abdominal pain, numbness and arthritis were noted to be the most common side effects of COVID-19 vaccine. Copyright © 2022 Lahore Medical And Dental College. All rights reserved.

Comparison of the Covid-19 Infection Severity in Known Diabetic Patients vs. Known Hypertensive Patients Admitted in A Tertiary Care Hospital in Peshawar

Objectives: To compare the severity of COVID-19 infection among known diabetic and known hypertensive patients who were admitted in a tertiary care hospital in Peshawar, Pakistan. Methodology: A cross-sectional clinical study was conducted for comparison in diabetic vs hypertensive patients in the department of medicine of Lady Reading Hospital, Peshawar during the period from April-June 2021. All the patients were admitted in COVID ward and COVID ICU, showed their full consent and active participation in this study. Along with patient's ECG and Echo report, a questionnaire based on Canadian categorization employed for angina grading and NYHA categorization to classify shortness of breath was used. Result(s): The mean age group taken for the sample was (n=140) with maximum age of 84 years. Majority were 102(72.9%) males and females were 38(27.1%). According to laboratory tests performed on patients of COVID-19 about 48(34.4%) of patients showed positive diabetes mellitus findings. Also, patients with positive hypertension found were 67(47.9%). The average stays of patients, at the hospital, was 15-40 days. About 58.3% of mortality was noted in patients with diabetes mellitus, a bulk of patients expired were from ICU-COVID-UNIT and 55.2% was the mortality rate in patients with positive hypertension according to our clinical findings and assessment. About 7.9% of COVID inpatients had cardiac infraction with severe condition and such patients who faced congestive heart failure expired. Almost 56(40%) of the patients were found with severe condition and 63(45%) were diagnosed with moderate condition during their stay at hospital. Conclusion(s): Regardless of age, gender and disease the death rate evaluated was 50%. Moreover, in diabetics and hypertensive patients there should be raised awareness for preventing the severity of disease. Copyright © 2022 Lahore Medical And Dental College. All rights reserved.

Emergency Remote Learning: Developing an Understanding about Online Learning Features and Students' Feelings

In mid spring 2020, an unprecedented Covid-19 induced switch of learning mode, from face-to-face instruction to online learning, disrupted not only teachers, but also students, both cognitively and emotionally. This study seeks to understand how students felt about their capabilities to succeed in the online learning environment (OLE) and which online learning features (OLF), offered to them by their instructors, positively, negatively, or neutrally impacted their learning. Three research questions guided this study: (1) What online learning features did students perceive as contributing positively, negatively, or neutrally to their learning and how were these perceived contributions related to students' demographics?;(2) How did students feel about their capabilities to succeed in the OLE?;and (3) How did students' feelings change during their online learning experiences and how did these changes relate to students' gender, academic performance, and prior online experience? An online survey was designed and face-validated to solicit information about students' perceptions about online learning features and feelings about their capabilities to succeed in the OLE. The 13-item survey consisted of 10 multiple-choice/multiple-answer and 3 open-ended questions. One thousand two hundred and thirty-seven (N = 1237) students taking 27 different courses, from 6 different institutions participated in the study. Presentation of the qualitative analyses of open-ended survey responses is outside the scope of this paper. Findings suggest that the three most frequent OLFs provided to students were electronic homework submission, recorded video lectures, and electronic exams. While video lectures, homework electronics submission, and downloadable documents or files were reported to be the top three OLFs that contributed positively to students' learning, poor internet performance, online exams, and projects were the top three OLFs that were reported to have contributed negatively to student learning. Changes in students' feelings during the online learning experience were also reported.

Social Media Networking Sites Usage and Depression Among University Students During the COVID-19 Pandemic: The Mediating Roles of Social Anxiety and Loneliness

The current COVID-19 pandemic has resulted in increased psychological issues such as excessive social media networking sites usage (SMNSU), loneliness, social anxiety, and depression. In this quantitative study, we examined how SMNSU can directly and indirectly influence depression, with loneliness and social anxiety examined as mediator variables. A 39-item questionnaire was used to collect survey data on SMNSU, loneliness, social anxiety, and depression from 244 blended learning undergraduate students from universities in the Hunan province in China. Partial least squares structural equation modeling was conducted using SmartPLS 3.3.3 to measure the relationships between the stated variables of interest. Results indicated that SMNSU has a direct, significant, and positive relationship with depression. In terms of mediating effects, both loneliness and social anxiety have an intervening role in the association between SMNSU and depression. This study focused on the higher education sector of China by recruiting students who were enrolled in blended learning courses during the COVID-19 pandemic and experiencing psychological problems. We found that excessive SMNSU is associated with depression. Loneliness and social anxiety also increase depression along with excessive SMNSU among blended learning students during unprecedented situations, in this case, the COVID-19 pandemic. The valuable implications of these findings for teachers, counselors, and university managers are discussed, along with a consideration of future research directions.

Analyzing the impact of COVID-19 on flight cancellation using machine learning and deep learning algorithms for a highly unbalanced dataset

Flight cancellations can be caused by many factors, including adverse weather conditions, and can result in lost money and time, etc. The COVID-19 pandemic has significantly exacerbated this situation, leading to a significant decrease in air travel. In 2020, the number of cancelled flights increased by 200% over 2019 and the number of flights decreased by 38%. This research focused on analyzing the impact of COVID-19 on flight cancellation using publicly available datasets from different locations. We looked further into the impact of class imbalance and techniques to reduce its effects on classification errors. The research was performed using four data sets, six re-sampling techniques, and 12 modeling algorithms. Random oversampling combined with random subsampling outperformed all other resampling techniques and multi-layer perceptron (MLP) was the best among all other machine learning models. For validation, we used the same resampling technique to two additional datasets namely income and diabetes datasets. The results showed that combining random oversampling with subsampling improved the accuracy of machine learning models.

Deep Learning based Customer Count/Flow Monitoring System for Social Distancing

Despite the COVID-19 vaccination drives, use of preventative measures such as masks and social distancing are still deemed essential. This paper presents an application that will allow businesses/enterprises to monitor the flow of customers by detecting people as objects, counting the number of people, tracking the safe distance between them to maintain the two-meter distance norm. The proposed solution is set up to generate an alarm when the customers reach the allowed limit as per shop dimensions or overcrowding is detected. For the implementation, YOLOv4 and YOLOv3-Tiny were used for the task of object detection and transfer learning is used to set up weights. The models were evaluated using MSCOCO API with 100 image instances per class. The results of the YOLOv4 model are also compared with YOLOv3-Tiny in terms of calculating mean, average precision (AP), frames per second (FPS), and identification of groups (crowd). Experimental results (on several video clips from a shopping center CCTV) show that the YOLOv3-Tiny maintains real-time performance even on modest hardware. It is further demonstrated that if a high-end GPU is available, the overall detection of objects and cluster identification is much more accurate and clearer using YOLOv4. © 2021 IEEE.

Joint Crypto-Blockchain Scheme for Trust-Enabled CCTV Videos Sharing

The declaration of COVID-19 as pandemic affected almost all public and private functionaries by enforcing them to operate remotely, and the judiciary is no exception. The trend seems to continue for the foreseeable future. The judicial proceedings where a piece of evidence, particularly the digital one, holds undisputed importance. Its preservation and intact transmission to the jury have gained an enhanced significance in this era which is highly susceptible to manipulation. This research proposes joint encryption and blockchain-based solution for immutable decentralised evidence management for CCTV footage. The permissioned chain of evidence system is implemented using Hyperledger Fabric to ensure the validity of the video metadata. The hash values are calculated on videos (recorded per session) and stored in the blockchain, while Region of Interest (ROI) based selective encryption of videos adds optimized security to individuals' privacy and protects from illegal access of stored videos. The experimental results provide a proof of concept that the proposed scheme facilitates the remote court services by maintaining a legal chain of evidence for CCTV videos. © 2021 IEEE.

Optimizing Energy in WiFi Direct Based Multi-hop D2D Networks

The recent pandemic of COVID-19 has changed the way people socially interact with each other. A huge increase in the usage of social media applications has been observed due to quarantine strategies enforced by many governments across the globe. This has put a great burden on already overloaded cellular networks. It is believed that direct Device-to-Device (D2D) communication can offload a significant amount of traffic from cellular networks, especially during scenarios when residents in a locality aim to share information among them. WiFi Direct is one of the enabling technologies of D2D communications, having a great potential to facilitate various proximity-based applications. In this work, we propose power saving schemes that aim at minimizing energy consumption of user devices across D2D based multi-hop networks. Further, we provide an analytical model to formulate energy consumption of such a network. The simulation results demonstrate that a small modification in the network configuration, such as group size and transmit power can provide considerable energy gains. The observed energy consumption is reduced by 5 times for a throughput loss of 12 %. Additionally, we measure the energy per transmitted bit for different configurations of the network. Furthermore, we analyze the behavior of the network, in terms of its energy consumption and throughput, for different file sizes.

Covid-19: From Pandemic to Epidemic an Ostrich Syndrome Causing Desensitization among Urban and Suburban Masses

Background: After declaration of the Covid-19 as pandemic by WHO, like every country of the world Pakistan also took exceptional precautionary measure to control the spread and transmission of this virus. These measures included strict lockdowns, shutting down educational institutions, markets, shopping malls, airports and masjids. The study primarily aimed to assess the individuals' knowledge, attitude, behavioral practices to prevent coronavirus and its psychological impacts on their mental health but later researcher also conducted another post study. Factually, the economic crisis, holy month of Ramadan and Eid-ul-Fitar forced the authorities soften the lockdown. Consequently, after this relaxation, the patients of Covid-19 as well as the death rates increased exponentially in Punjab. Methods: A non-equivalent quasi-experimental research designed was used to conduct pre and post study. An online survey having standardized questions about the peoples' knowledge regarding Covid-19, attitudes, their behavioral practices to prevent it and in what manner covid effected their mental health was conducted. Moreover, it also includes the information for demographics of sample. The link was sent to the participants through email, WhatsApp, Social media, Twitter, Facebook and LinkedIn. Similarly, same procedure was followed in post-study, with the same participants, but after a gap of three weeks. Results: Data was analyzed by SPSS and t-test was applied to draw comparisons among the responses of pre and post study. Results revealed that peoples' knowledge and attitude towards Covid-19 remained same in both studies, however, their behavioral practices to prevent Covid-19 and psychological impacts on their mental health (i.e., stress, depression, fear) greatly reduced in post study as compared to the prestudy. Conclusion: The authorities should initiate the health education programs to improve the knowledge, attitude and behavioral practices regarding Covid-19 and to combat its psychological impact on mental health. Besides, it is highly recommended that authorities should take bold steps to enforce formal, or smart lockdown to take control over the situation or else get ready to filled up the graveyards. The situation can also be controlled by enforcing precautionary measures and re-inviting awareness.