Transformer-based Deep Learning for COVID-19 Prediction Based on Climate Variables in Indonesia

Recent research on the effect of climate variables on coronavirus (COVID-19) transmission has emerged. Climate change can potentially cause new viral outbreaks, illness, and death. This study contributes to COVID-19 disease prevention efforts. This study makes two contributions: (1) we investigated the impact of climate variables on the number of COVID-19 cases in 34 Indonesian provinces, and (2) we developed a transformer-based deep learning model for time series forecasting for the number of positive COVID-19 cases the following day based on climate variables in 34 Indonesian provinces. We obtained data from March 15, 2020, to July 22, 2021, on the number of positive COVID-19 cases and climate change variables (wind, temperature, humidity) in Indonesia. To examine the effect of climate change on the number of positive COVID-19 cases, we employed 15 scenarios for training. The experiment results of the proposed model show that the combination of wind speed and humidity has a weakly positive correlation with positive COVID-19 incidence;however, the temperature has a considerably negative association with positive COVID-19 incidences. Compared to the other testing scenarios, the transformer-based deep learning model produced the lowest MAE of 175.96 and the lowest RMSE of 375.81. This study demonstrates that the transformer model works well in several provinces, such as Sumatra, Java, Papua, Bali, West Nusa Tenggara, East Nusa Tenggara, East Kalimantan, and Sulawesi, but not in Central Kalimantan, West Sulawesi, South Sulawesi, and North Sulawesi. © IJASEIT is licensed under a Creative Commons Attribution-Share Alike 4.0 International License.

Accuration of Classification of Covid with Convolutional Neural Network-Based Image Chest X-ray with Variations in Image Size and Batch Size

The use of convolutional neural networks in Covid classification has a positive impact on the speed of justification and can provide high accuracy. But on the one hand, the many parameters on CNN will also have an impact on the resulting accuracy. CNN requires time and a heavy level of computation. Setting the right parameters will provide high accuracy. This study examines the performance of CNN with variations in image size and minibatch. Parameter settings used are max epoch values of 100, minibatch variations of 32, 64, and 128, and learning rate of 0.1 with image size inputs of 50,100, and 150 variations on the level of accuracy. The dataset consists of training data and test data, 200 images, which are divided into two categories of normal and abnormal images (Covid). The results showed an accuracy with the use of minibatch 128 with the highest level of accuracy at image size 150 × 150 on test data of 99,08%. The size of the input matrix does not always have an impact on increasing the level of accuracy, especially on the minibatch 32. The parameter setting on CNN was dependent on the CNN architecture, the dataset used, and the size of the dataset. One can imply that optimization parameter in CNN can approve good accuration. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

ANALYSIS OF THE EFFECT OF USING COVID-19 MEDICAL MASK WASTE WITH POLYPROPYLENE ON THE COMPRESSIVE STRENGTH AND SPLIT TENSILE STRENGTH OF HIGH-PERFORMANCE CONCRETE

The coronavirus causing the Covid-19 pandemic has been experienced by us since 2020, which has led to an increase in the use of disposable medical masks in Indonesia and even worldwide. Polypropylene is a thermoplastic polymer used as the main ingredient in medical masks that takes more than 25 years to decompose in landfills. This research offers an innovative way to use medical mask waste in high-performance concrete. The resulting medical mask waste is subjected to a sterilization process and cut into fibers to analyze the effect of its addition on the compressive strength and splitting tensile strength of high-performance concrete. The research began with testing the physical and mechanical properties of the materials, designing a concrete mix using the absolute volume method, and taking samples for compression and splitting tests. The variation in the ratio of water-cement and pozzolanic materials w (c+p) is 0.32. As a result, the compressive strength of concrete increased with a fiber size of 5×0.5 cm and 2×0.5 cm. An increase is up to 7 % with an optimum value of 72.37 MPa with a fiber size of 2×0.5 cm and a content of 0.15 %. However, there was a decrease in the compressive strength with a 5×1 cm mask fiber size. The overall split tensile strength value of all variations in waste fiber size and content increased with an optimum value of 7.29 MPa at 0.20 % fiber content with a fiber size of 5×0.5 cm. This indicates that polypropylene fibers from medical mask waste have a positive effect on high-performance concrete, namely improve the properties of concrete with a low tensile strength, which is expected to inhibit the propagation and reduce the size of cracks in reinforced concrete structures © 2023

Physical condition and heart rate rest of yogyakarta rugby pon team players during the COVID-19 pandemic

Aim: To identify the correlation between different fitness indicators of rugby players in training conditions during quarantine related to Covid-19. Material and methods. The study involved athletes from PON Rugby DIY (n = 28, including 15 male athletes and 13 female athletes). To assess the level of physical fitness, the following tests were used: to assess the level of strength, push ups for 1 minute (number) and squats for one minute (number) were used;the yo-yo test was used to assess the level of endurance;speed was assessed using a 40 meter running test (s);agility by performing an Illinois agility test;power (speed-strength abilities) was assessed by the value of the vertical jump (cm);and for the heart rate was determined by the athlete independently within 60 seconds after waking up. The data collection method in this study is test and questionnaire. Data analysis was performed using Pearson correlation analysis using SPSS V 25 software. Results. It was shown that endurance has a strong correlation with power with r value (0.651) and significant p = 0.000. Speed ?also has a strong correlation with strength, as evidenced by the r (0.538) value with a significant p = 0.003. Strength has a strong correlation with power, as evidenced by the value of r (0.561) with a significant value of p = 0.002. Speed ?has a very strong correlation with agility, as evidenced by the value (0.935) with a significant p = 0.000. Conclusions. It was found that endurance does not correlate with resting heart rate, and endurance does not correlate with strength, because the load of the training program was not optimally implemented by athletes in the Covid-19 quarantine. © Antonius Tri Wibowo, 2020.

The Role of Labacs in Long COVID-19 Patients in Pringsewu,Indonesia

Background: Severe covid-19 disease has led to many death. Some post mortem study has investigated the cause. The autopsy revealed occurrence of DVT and postmortem lung CT showed reticular infiltration, dense consolidation, while histologically showed diffuse alveolar damage. Through FOB conducted In mechanically ventilated COVID-19 patient, airway obstruction was seen due to hypersecretion and mucus plug in the bronchi. Inhaled budesonide in COVID-19 patient has showed faster recovery and the research focus in the administration of ICS is limited. Objective(s): This study aims to investigate the benefit of LABACS treatment in LONG COVID-19 patients in Pringsewu Indonesia. Method(s): The method of this research was cross sectional. Total subjects included in this study were 276 patients. 168 subjects were treated with Beclomethasone-Formoterol (61%), 49 subjects were treated with FluticasoneSalmeterol (17%), 59 subjects were treated with Budesonide-Formoterol (22%) during 3 months period. We assessed symptoms improvement, mMRC score and chest X-ray imaging. Spirometry of 34 subjects were measured. Result(s): There was a significant correlation between the incidence of lung obstruction and persistent symptom of long covid patients according to spirometry measurement (P value = 0.000). There was a significant correlation between symptoms improvement, mMRC score and chest X-ray imaging after treatment with Beclomethasoneformoterol (p-value = <0.05) Fluticasone-Salmeterol (P value = <0.05) Budesonide-Formoterol (P value = 0.002, P value = 0.007, P value = 0.049). Conclusion(s): LABACS treatment improved lung function and clinically benefit in managing obstruction due to COVID-19.

Serious Game Development of COVID-19 Social Distancing Simulator using Agent-based Modelling

A social distancing protocol has been acknowledged and encouraged practically everywhere, since the global COVID-19 epidemic in 2020. This research resulted in the Serious game to simulate social distance using agent-based modeling so that it can be used as a medium of entertainment and educate the public during the Pandemic COVID-19 conditions by developing simulation games using UNITY 3D to educate in the middle of the COVID-19 pandemic and reduce transmission rates on an individual scale. © 2022,Telfor Journal..All Rights Reserved.

Tourism CSR Model during the COVID-19 Pandemic: Literature Review

This research aims to study the potential development of tourism Corporate Social Responsibility (CSR) model during COVID-19 pandemic, through creating framework of tourism CSR model compatible to increase the tourist visit rate. Research method employed was literature review with qualitative approach. The result of research showed COVID-19 pandemic condition conceived through risk society theory. Theoreticians raised reflexivity concept to see abilities of responding to and anticipating risk. CSR is a business policy guiding company to integrate social and environmental problem into their business vision, mission, and strategy, and their interaction with stakeholders. Strategy development and CSR implementation are intended to identify and to manage stakeholders' expectation. Tourism CSR model during COVID-19 pandemic can be developed based on stakeholder reflexivity, offering 5 stages: identify learning goals, focus on specific problem at work, reflect on personal predispositions, learn about learning, and develop reflexivity. Stakeholder analysis generates basic dimensions of advantage and perceived threat, perceived social impact, guidance value and principle, guideline of ethical decision making, and stakeholders' information need. Stakeholder reflexivity can result in decision to revise more health protocol-oriented program. Image as a safe destination will increase the tourist visit. © The Authors, published by EDP Sciences.

Identifying factors affecting entrepreneurship education and entrepreneurial intention among Indonesian university students

Objective: The shift from conventional to online learning activities may impact students’ performance and entrepreneurial involvement. This research investigates the role of e-learning in determining entrepreneur-ship education and entrepreneurial self-efficacy, and students’ intention on entrepreneurship. Research Design & Methods: A quantitative method with structural equation modelling using the partial least squared was implemented to understand the phenomenon. The study involved students who enrolled in online entrepreneurship education in several universities in Malang of Indonesia. Findings: The findings indicate that students’ entrepreneurship education and self-efficacy can be performed using e-learning, and it is closely linked with lecturer competence, performance expectancy, and facilitating condition. The results also show a linkage between entrepreneurship education and entrepreneurial intention. This research confirms a crucial role of self-efficacy and entrepreneurship education in mediating teachers’ competence and intention for entrepreneurship. This is the first step for further investigation regarding the effect of online learning on college students’ entrepreneurial intentions. Implications & Recommendations: This study implies that lecturers need to improve their competency on how to teach entrepreneurship more meaningful and involve all of students’ psychological aspects. Further-more, in cooperation with the government, the campus can provide adequate facilities and infrastructure to support online learning. Additionally, the government can consider improving the quality of the internet network so that geographical conditions do not constrain it. Contribution & Value Added: This research provides an appropriate strategy to promote entrepreneurship education with e-learning that can be adopted during the global Covid-19 pandemic. Moreover, in a regular situation, the strategy may still enhance entrepreneurship promotion as it fosters familiarity with the use of educational technology. © 2022, Cracow University of Economics. All rights reserved.

STUDENTS IDEAL CAREER IN THE 4.0 INDUSTRIAL

This study aims to analyze quantitatively the factors that affect the career planning of students in the Industrial 4.0 era. A sample of 381 students was taken using a proportional random sampling technique. The data were analyzed using the SEM technique with the help of the SEM AMOS 24.0 program. The results show that career center management, entrepreneurship personality, family environment, entrepreneurship education, and entrepreneurship intention contributed both directly and indirectly to student career planning in the Industry 4.0 era, both partially and simultaneously. The results also indicate that entrepreneurship personality is the variable that has the most significant contribution to encouraging students' intention to have a career as an entrepreneur. The research contribution shows that providing appropriate entrepreneurship education, supporting the performance of career center management, strengthening the entrepreneurship personality, and strengthening the role of the family environment, increases student intention in planning careers as entrepreneurs in the 4.0 industrial era. © 2022, Institute of Eastern Europe and Central Asia. All rights reserved.

Systematic literature review on physical distancing policy for mass gathering events

The explosive spread of Corona Virus Disease-19 (COVID-19) in late December 2019, requires the health authorities worldwide to enforced stricter standard operating procedures (SOP) for mass gathering events, which eventually caused postponement and cancellation. This has led to a great loss and bankruptcy for most event organizers. As an effort to offer solution to this matter, a professional touch producing "soft landing"such as "Mathematical Modelling of Physical Distancing Policy for Mass Gathering Event Organizer"was proposed. Therefore, a holistic understanding about the issues related to physical distancing in mass gathering event is required. This systematic review paper summarizes current practice of physical distancing among mass gathering event organizers. This study reviewed thirteen articles using two leading databases namely Scopus and Google Scholar. Based on thematic analysis, this review finalized four themes: 1) physical distancing method;2) the importance of physical distancing;3) challenges in physical distancing enforcement and 4) approach to monitor the compliance of physical distancing. © 2022 Author(s).

Physical distancing evaluation for classroom layout management during COVID-19 pandemic era

Mass gathering has been identified as one of the causes of fast-spreading of COVID-19. Physical distancing practices and large gathering control in Malaysia and all over the world are likely to be continued until the end of the year, even after Movement Control Order (MCO) has been lifted. This has imposed event organizers to redesign their events into virtual events where attendees are to stay at their houses and meet with the host and other attendees virtually. However, certain types of educational events or activities such as practical and hands-on classes are not to be virtually conducted as it by nature carries a competency for the students. This paper evaluates the standard classroom layout by comparing with optimal layout based on circle packing problem (CPP) solution. CPP solution is used to optimize the physical distancing-constrained for the student seat layout as in it happens in real life. The findings can provide an effective exit strategy for Malaysia to deal with this COVID-19 pandemic or other pandemics in the future. © 2022 Author(s).

Optimization and simulation methods in addressing COVID-19 physical distancing policy: A bibliometric analysis

COVID-19 has received tremendous attention from scholars worldwide and even being labelled as a black swan event that has disrupted every aspect of human life. Within a short time span of the pandemic, a large volume of research pertaining to COVID-19 has been published in diverse research fields. This paper adopts a bibliometric analysis to systematically evaluate the research development in the application of optimization and simulation methods to address COVID-19 physical distancing policy (OSPhyD) using Bibliometrix R package. A textual query on Scopus database using the combination of four classes of keywords;covid-19, optimization, simulation, and physical distance has returned a total of 299 original research articles and reviews published in English. Appropriate visualizations were generated to describe the collaborations between different authors, countries, and institutions, whilst co-word analysis that uses text mining technique has produced a conceptual cluster via co-occurrence network map to underscore the emerging themes in the current research interest. The main findings pinpoint that: 1) OSPhyD as a scientific research field is an emerging multidisciplinary research topic that is growing progressively and steadily in the fields of medicine, engineering, social sciences, mathematics and decision science, 2) The field has attracted the attention of scholars from all over the world particularly from United States of America, United Kingdom, European countries including authors from Asia, and 3) Three dominant themes or research front emerged from the publications including COVID-19 mainstream, medical education and undergraduate. © 2022 Author(s).

Urban Heat Island Mitigation Strategy based on Local Climate Zone Classification using Landsat 8 satellite imagery

Appropriate strategies on urban climate mitigation should be formulated by considering the physical morphology of the urban landscape. This study aimed to investigate, analyze, and promote possible strategies to mitigate Jakarta’s urban heat island (UHI) phenomena. Jakarta’s local climate zone (LCZ) was classified into 17 classes using Landsat 8 data and the random forest method. Land surface temperature (LST) characteristic in each LCZ class was analyzed from 2018, 2019 and 2020. The result revealed that most of the local climate zone in Jakarta is dominated by LCZ 6 (open low-rise) and LCZ 3 (compact low-rise), which is the typical residential area in Jakarta. However, the mean LST in 2018, 2019 and 2020 showed that LCZ 3 (compact low-rise) and LCZ 7 (lightweight low-rise) are the areas that were most likely causing high surface temperature with the highest UHI intensity. During the COVID-19 pandemic in 2020, LST in Jakarta decreased drastically in some parts of the area, especially in public facility such as airport. However, the LST value in low-rise areas (LCZ 3 and LCZ 7) remains higher than the other LCZ classes. Materials of the building and land cover play a significant role in raising the land surface temperature. Therefore, mitigation strategies for urban heat islands in Jakarta should be focused on such particular areas mentioned.

Comparison of Models Architecture on Chest X-Ray Image Classification With Transfer Learning Algorithms

Coronavirus disease is an infectious disease caused by the newly discovered coronavirus. Most people infected with the Coronavirus disease have difficulty breathing. Some patients who underwent radiographic tests had changes in their lungs. There are many methods to detect people who have contracted the COVID-19. One alternative method proposed is to perform automatic diagnostics through x-ray images. To perform automation, a model is needed to classify patients with COVID-19 and normal. One of the training methods for creating classifiers is deep learning, but deep learning method needs a huge amount of annotated data. Therefore, the transfer learning method is used by using an existing model, then back again with the desired data. The model used is Xception, InceptionV3 and MobileNetv3. This study produces accuracy of 91% on model trained with Xception, 89% accuracy on model trained with InceptionV3, and 86% accuracy on model trained with MobileNetV3.

The use of salivary specimen for COVID-19 detection using RT-PCR assay: a systematic review

As coronavirus disease 2019 (COVID-19) cases arose globally, active case finding by performing throat swab test proposed high risk for the healthcare workers. Saliva had recently been reported to show positive detection means for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and proposed advantages of self-collection, less requirement of transport media, and reduced nosocomial transmission risk. However, support evidence regarding its diagnostic value was still lacking and varied widely in specimen collection method. This systematic review aimed to assess the diagnostic value of salivary specimens (SS) for COVID-19 detection using reverse transcription polymerase chain reaction (RT-PCR) assay compared with throat swab specimens (TSS), while putting into consideration confounders such as patients’ initial condition, specimen collection method, and transport media used. Six databases were used for identifying relevant studies. Final search yielded 19 eligible studies which was reviewed based on the major outcome: diagnostic agreement, sensitivity & specificity, and viral load comparison. The use of SS as an alternative to TSS showed to be promising although specimen collection method needed to be standardized. SS was comparable to TSS in detecting COVID-19 using RT-PCR assay, especially in symptomatic or confirmed cases. More Randomized controlled trials (RCTs) were still needed to clearly demonstrate the ability of SS to capture asymptomatic cases in the setting of mass surveillance, where patients would self-collect the specimen at ease. © 2022, Intelektual Pustaka Media Utama. All rights reserved.

Sentiment Analysis of Indonesian Government Policies in Handling Covid 19 Through Twitter Data

This paper presented a sentiment analysis of the Indonesian government's policies in overcoming Covid 19 through twitter data using several classification methods, namely SVM, Naive Bayes, and LSTM. Based on the analysis of the twitter data, it was found that the twitter community in Indonesia gave negative sentiments to government policies in handling Covid 19. From the experimental results, it was found that SVM gave the best sentiment results compared to Naïve Bayes and LSTM by providing an accuracy of 88.5%. © 2021 IEEE.

EMPATHETIC LEADERSHIP, JOB SATISFACTION AND INTENTION TO LEAVE AMONG MILLENNIALS IN A START-UP INDUSTRY: NEEDS' SATISFACTION AS A MEDIATING VARIABLE

Introduction/Main Objectives: The purpose of this research is to examine the relationship between empathetic leadership and employees' job satisfaction and the intention to leave with needs' satisfaction as a mediating variable among millennials in a start-up business. The number of millennials will only continue to grow, and by 2025 it is expected that 75% of the global workforce will be millennials. In particular, empathetic leadership will be required to manage and control this generation if the organizations they choose to work for are to be successful, as this generation's members have different characteristics compared to those of the older generations. Design/methodology/approach: Following a cross-sectional research design, this research collected data from 137 millennial employees of start-up companies in Indonesia. A structural equation modeling technique was used for the data's analysis. Findings: The results reveal that empathetic leadership has a direct and positive relationship with employees' job satisfaction and has a direct and negative relationship with the intention to leave. Needs' satisfaction partially mediates these relationships. Originality: This study makes a novel contribution to the existing literature by first providing empirical evidence that among the three dimensions of needs' satisfaction only the relatedness dimension passed the measurement test in the structural equation modeling. Second, empathetic leadership is proven to increase job satisfaction and reduce the intention to leave among millennials, considering their unique characteristics. Research limitations/implications: The research was conducted during COVID-19 pandemic. Circumstances related to that pandemic might influence the result of this study. It is, therefore suggested to conduct the study again under normal circumstances. Policy and Practical implications: The findings of this study suggest managers should develop an empathetic leadership style in order to better manage the millennials. Leaders can be nurtured, but disciplined efforts have to be invested in their creation. © 2021 Departamento de Literatura Española-Universidad de Sevilla. All rights reserved.

Disconnectedness and Quality: Understanding the Ineffectiveness of Online Learning Emergency during Covid-19

Aims The increasing development of information communication technology is increasingly positively ‎impacting individuals in various fields, including education. This research aimed to understand the causes of ineffective online learning from the point of view of activists. ‎ Participants & Methods This qualitative research was conducted in 2019 in the context of Instructors in the Department of Accounting, Padang State Polytechnic. This study used a phenomenological design with semi-structured interviews that focuses on activists’ ‎experiences (egos) who are central to the entire environment. Based on these assumptions, phenomenology seeks to find the intentionality behind the activist’s behavior for his understanding. Findings In the view point of participants, the causes of ineffective online learning were cultural and emotional. The cultural aspects are categorized under awkwardness with technology and content and characteristics of online learning and the emotional aspects are categorized under ‎instructors’ pressures and workload and students’ dishonesty. Conclusion The effectiveness of online learning systems is about connectedness and quality. Meaning is a subjective truth that arises from the consciousness of a person who experiences and performs an ‎action. ‎. © 2021, the Authors.

The Post-Covid-19 Pandemic Education Model Is Effective, Let's Compare: Online Versus Offline Learning

Many variations of learning methods, ranging from discussions, dialogues, to simulations. When the COVID-19 pandemic began to emerge, learning models using information technology began to become a trend. Many media can be used as learning media such as the internet, mobile phones, and other platforms. The problem is that not all teachers and students understand the use of information technology. The solution offered is to create a model with the 3M concept (Methods, Media, and Materials) which will be the basis for educators and students to create balance and ease in the learning process. Method: To process the existing data, the identification concept will be used which is then made a hierarchical arrangement to facilitate the analysis of the results. The results were obtained in the form of several parameters that can be used as the basic for designing the 3M model (Method, Media, and Material).. © 2021 IEEE.