A Comparison of LSTM and BiLSTM for Forecasting the Air Pollution Index and Meteorological Conditions in Jakarta

Jakarta is the capital city of Indonesia where air pollution becomes one of the problems that must be properly handled. The historical data of the air pollution index is beneficial for developing models for forecasting future values. One of the advantages of forecasting air pollution is to help people to arrange future plans to reduce the dangerous effect on health. Analyzing a record of meteorological conditions can be used to understand climate change. This paper reports the comparison of Long Short Term Memory (LSTM) and Bidirectional LSTM (BiLSTM) models for multivariate forecasting of the air pollution index and meteorological conditions in Jakarta. It also informs the performance of those algorithms for forecasting the observed variables before and during the Coronavirus disease (Covid-19) outbreak to analyze the effect of the pandemic on the environment. The experiments use a historical time series dataset from 2010-2021. The experimental results show that LSTM and BiLSTM work well to forecast PM10, temperature, humidity, and wind speed. In this case study, there are no significant differences in the performance of LSTM and BiLSTM. © 2022 IEEE.

The Graph Convolutional Networks Framework for Predicting Pandemic Impact on Stock Prices

Covid-19 has dealt an unprecedented hit to the global economy and all industries, with varying degrees of decline from retail to real estate. This volatility is most evident in stock prices. Previous stock price forecasting methods typically used historical data for each stock as a separate input into the system. This paper proposes an attention-based parallel graph convolutional network framework, which consists of two parallel GCNs. The first GCN takes stock features as input, and the second GCN takes other industry features as input, and sets an attention model to reflect the pairwise interactions between networks. Experimental results on selected stock data show that the model outperforms both the LSTM model and the GCN model in accuracy and F1 score. © 2022 IEEE.

Impact Analysis of Covid-19 Pandemic on Construction Employment in the United States

Construction industry is one of the major contributing sectors of the U.S. economy. Due to COVID-19 pandemic construction industry has witnessed halt and cancellation of ongoing and planned projects. As projects got halted and cancelled many construction companies furloughed or terminated employment contracts of their workers. This sudden termination has been reflected in the monthly employment numbers. This paper presents the employment change in three constituting subsectors of construction industry: building, heavy and civil, and specialty trade due to COVID-19 pandemic. The paper has utilized historical data from the U.S. Bureau of Labor Statistics to forecast the expected employment numbers in absence of the pandemic. It has been found that due to pandemic the construction employment went down by 5.5 million between March 2020 and December 2020. Additionally, it has been found that the variation of the extent of impact of the COVID-19 pandemic in terms of employment on the three subsectors is insignificant. This means that the three subsectors suffered the consequences equally. The outcomes of the paper can be utilized by the policy makers in exploring the broader implications of the construction employment change. It can also be used in subsector specific policy planning purpose. © 2023, Canadian Society for Civil Engineering.

Prediction of the Epidemic Trend of Novel Coronavirus Pneumonia Based on SIR Model

This paper collects real-time epidemic data released by the World Health Organization and various Internet authorities, predict the development of the epidemic through the classical model (SIR model) in the field of communication disease, bring historical data into the model, verify the parameters of the model and establish a new model, compare multiple sets of data, obtain the system that is closest to the real data, and speculate on the development direction and turning point of the subsequent NEW CROWN epidemic. The use of scientific and technical means to reason and analyze the overall situation of the new crown epidemic situation provides a solid backing for the prevention and control of the epidemic. © 2022 IEEE.

COVID-19 Pandemic vis-à-vis Zamboanga Peninsula Aviation: A Predictive Analysis

The use of time-series analysis to examine aviation data trends through time comes crucial in planning its future. The prophet is an additive model that fits non-linear patterns. It functions best with historical data from various seasons and time series with significant seasonal impacts. This research looked closely into the aviation data in Zamboanga Peninsula, Jolo, and Tawi-Tawi to give a clearer picture of its impact on the sector and forecast passenger and aircraft movement in the coming months to see whether the impact of the opening in the aviation industry can be sustained. The final data comprise 51 data points for flight arrivals and departures and 51 data points for passenger arrivals and departures. Data show the decline in passengers and aircrafts arriving and departing in major airports in Zamboanga Peninsula, Jolo, and Tawi-Tawi during the pandemic. However, an increasing trend was observed years after the pandemic hit the region. Findings during the training and testing phase revealed that different models attained varied results;however, there are models which attained a higher degree of accuracy as depicted in the RMSE and R2. This indicates that predicting passenger and aircraft movement using models with higher accuracy is similar to real data thus, it is viable in predicting future values. Forecasting results further show a gradually increasing trend of aircraft and passenger arrivals in the major airports in Zamboanga Peninsula, Jolo, and Tawi-Tawi despite some observed smaller forecasted values. © 2022 IEEE.

Predictive Analytics Comparison of Indonesia Government Budget With or Without Covid-19 Pandemic

An accurate budget forecast of Indonesia before starting a financial year is very important, the budget can be used to direct socio-economic development, ensure sustainability, and improve the quality of life of the people. Since the pandemic covid occurred in 2020 many countries carry out social restrictions to regional or national lockdown that impact the national budget. To estimate the Indonesian government's budget and accurately at the planning stage with the assumption the pandemic will continue or end. The solution can be figured out by using predictive analytics. Predictive analytics seeks to predict the future by examining historical data, detecting patterns or relationships in these data, and connecting all historical data patterns in the future. This solution can be used to predict how much the Indonesia Budget will be with the assumption previously mention. © 2022 IEEE.

Forecasting Covid-19 Time Series Data using the Long Short-Term Memory (LSTM)

Confirmed statistical data of Covid-19 cases that have accumulated sourced from (https://corona.riau.go.id/data-statistik/) in Riau Province on June 7, 2021, there were 63441 cases, on June 14, 2021, it increased to 65883 cases, on June 21, 2021, it increased to 67910, and on June 28, 2021, it increased to 69830 cases. Since the beginning of this pandemic outbreak, it has been observed that the case data continues to increase every week until this July. This study predicts cases of Covid-19 time series data in Riau Province using the LSTM algorithm, with a dataset of 64 lines. Long-Short Term Memory has the ability to store memory information for patterns in the data for a long time at the same time. Tests predicting historical data for Covid-19 cases in Riau Province resulted in the lowest RMSE value in the training data, which was 8.87, and the test data, which was 13.00, in the death column. The evaluation of the best MAPE value in the training data, which is 0.23%, is in the recovered column, and the evaluation of the best MAPE value in the test data, which is 0.27%, in the positive_number column. In the test to predict the next 30 days using the LSTM model that has been trained, it was found that the performance evaluation of the prediction results for the positive_number column and the death column was very good, the recovery column was categorized as good, the independent_isolation column and the care_rs column were categorized as poor. © 2022, International Journal of Advanced Computer Science and Applications. All Rights Reserved.

A Recommender System for Communication Apps by Analyzing Reviews

Due to the impact of Covid-19, various means of virtual communication such as online education and online teamwork have become increasingly popular under different circumstances. However, it is difficult to select the one that suits your needs fast from a large number of online communication apps. Therefore, this study is aimed to build a system that is capable to recommend online communication apps and meet the needs of users through analysis of app reviews. Despite attempts made in some of the existing studies to recommend apps using the negative/positive information carried by reviews and the historical data of users, it cannot be said that the use of textual information included in reviews is directly linked to user needs. This study built a system that is capable to recommend online communication apps and meet the needs of users through analysis of app reviews. In this research, by employing the user requests (hereinafter referred to as "request sentences") and app review data extracted in advance, the online communication apps that match the user needs are output in a ranking list. © 2022 ACM.

Forecast of Aviation Traffic in Indonesia Based on Google Trend and Macroeconomic Data using Long Short-Term Memory

The COVID-19 pandemic has impacted many sectors. For example, in the aviation sector, flight traffic went down drastically with no certainty of being recovered. This calls for a methodology to predict the flight traffic to provide strategic planning on flight schedules operational, route structuring, and flight navigation service cost determination. However, current developments mainly focus on flight traffic forecasting based on historical data without considering external factors. In this study, we propose the Long Short-Term Memory (LSTM) technique to forecast flight traffic in Indonesia involving external variables such as macroeconomic variables and Google Trends. LSTM is proposed because of its flexibility to model non-linear time series data and has a good reputation for predictive accuracy. We first select a few among Google Trends and macroeconomic variables using nonlinearity analysis and cross-correlation function (CCF). We then employ the selected variables to forecast the flight traffic and compare it to the one using only historical flight traffic data. Our results concluded, based on the Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE), that the model involving google trend outperforms the other three models, i.e., the model with only historical data, the model with macroeconomics, and the model with both macroeconomic and Google Trends. It is because, in this digital era, Google Trends can reflect population psychology in an up-to-date manner. © 2022 IEEE.

Decrease of Taxi Ridership due to the Impact of COVID-19: A Case Study of New York City

The outbreak of COVID-19 has greatly impacted all industries of many countries in the world. As an important part of people's daily life, transportation is one of the most severely impacted industries. Taking New York City as an example, this paper explores the decline of taxi ridership due to the COVID-19. The decreased ratio of the actual taxi ridership to the taxi ridership predicted for the no COVID-19 scenario based on historical data is calculated as the dependent variable. The fractional response model is used to study the effect of built environment factors including demographic and socioeconomic, land use, and road-related on the decline of ridership. One model is constructed for each of the four periods, to explore the influence of influencing factors on the dependent variables in different periods. The model results show that the percentage of taxi trips decline is associated with the proportion of high-income people living in the area. The reason could be that these people have more flexible working hours and working places. They can choose to telecommute or travel by private cars to avoid contacting other people during transportation. The analysis of the other factors shows that industrial jobs are related to the low percentage of decline. The model results reveal to us the problem of equity exposed in New York City during the pandemic: limited by jobs(race/income), a portion of citizens are not fully free to choose their travel mode during the pandemic. According to the findings, this paper gives traffic management some policy suggestions. As a result, this study could provide an important reference for policymakers to develop appropriate measures to control the epidemic. © 2021 IEEE.

Cost-Effective Data Mining Application Covid-19 Analyzer

The idea of data mining has been around for longer than a century, yet come into a more prominent public core interest in the 1930s. As time passed, the measure of information in numerous frameworks developed to bigger than terabyte size, which can no longer be maintained manually. Additionally, for the effective presence of any business, finding hidden examples in information is viewed as fundamental. Accordingly, several software tools were created to find covered up information and make assumptions. Salesforce Einstein is an Artificial Intelligence-based tool, provided by Salesforce.com. Salesforce Einstein tool is designed to enable companies to become smarter and predictive about their customers. It analyzes your historical data against set boundaries or parameters and generates recommended actions for the companies accordingly. In this project, we are using the Salesforce Einstein tool to create insights into Covid data. © 2021 IEEE.

Improving Prediction Accuracy of Covid-19 Data Analysis

Since early 2020 Covid-19 has casted great shadow to everyone worldwide. Due to large number of infected and death cases, accurate predictions can help the government and medical divisions in pandemic preparedness and prevention. In this paper, we used the Prophet machine learning model to analyze the historical data of the past year to predict the future trend of confirmed, death, recovered total cases. To improve the prediction accuracy, we optimized the data by detecting "turning points"of confirmed cases and then redo predictions. From the result comparison of predictions using original data vs. optimized data it is shown that our optimization improves the prediction accuracy significantly. © 2021 ACM.

Analysis of Top-Ranked HEI Publications' Strategy on Twitter

In recent years we have seen a large adherence to social media by various Higher Education Institutions (HEI) with the intent of reaching their target audiences and strengthen their brand recognition. It is important for organizations to discover the true audience-aggregating themes resulting from their communication strategies, as it provides institutions with the ability to monitor their organizational positioning and identify opportunities and threats. In this work we create an automatic system capable of identifying HEI Twitter communication strategies. We gathered and analyzed more than 18k Twitter publications from 12 of the top-HEI according to the 2019 Center for World University Rankings (CWUR). Results show that there are different strategies, and most of HEI had to adapt them to the covid situation. The analysis also shows the prediction of topics and retweets for a HEI cannot just be based on recent historical data. © 2021 IEEE.

Predict ATFCM weather regulations using a time-distributed Recurrent Neural Network

In recent years, prior to COVID-19, capacity shortfalls in airspace and airports inevitably caused an increase in aircraft delays. Therefore, when it returns to normal conditions, the airspace will exhibit the same capacity limits, even under normal weather conditions. To ensure that air traffic remains safe, reliable, and efficient in adverse weather conditions, planning and coordination activities through a Collaborative Decision Making process are required to deliver the most effective Air Traffic Flow and Capacity Management services to Air Traffic Control and Aircraft Operators. Nowadays, this task is based on air traffic controllers' experience and historical data. That means that the Flow Manager Positions and the Network Manager operators have to process a huge amount of information, and the detection of future overloads is based on past experiences. Moreover, due to the inherent uncertainty of weather information, a reliable decision support framework is required to handle these situations as efficiently as possible. We propose a Deep Learning model able to extract the relationship between both the historical data and the implemented actions, accurately identifying the intervals of time that must be regulated. The proposed model achieves an accuracy between 80% and 90% across six traffic volumes belonging to both the MUAC and REIMS regions, a recall higher than 85%, and an F1-score higher than 0.8 in all the cases. Furthermore, the confidence-level analysis shows a really high activation when making a prediction. Finally, the SHapley Additive exPlanations method is applied to identify the most relevant input features. © 2021 IEEE.

Does historical data still count? Exploring the applicability of smart building applications in the post-pandemic period.

The emergence of COVID-19 pandemic is causing tremendous impact on our daily lives, including the way people interact with buildings. Leveraging the advances in machine learning and other supporting digital technologies, recent attempts have been sought to establish exciting smart building applications that facilitates better facility management and higher energy efficiency. However, relying on the historical data collected prior to the pandemic, the resulting smart building applications are not necessarily effective under the current ever-changing situation due to the drifts of data distribution. This paper investigates the bidirectional interaction between human and buildings that leads to dramatic change of building performance data distributions post-pandemic, and evaluates the applicability of typical facility management and energy management applications against these changes. According to the evaluation, this paper recommends three mitigation measures to rescue the applications and embedded machine learning algorithms from the data inconsistency issue in the post-pandemic era. Among these measures, incorporating occupancy and behavioural parameters as independent variables in machine learning algorithms is highlighted. Taking a Bayesian perspective, the value of data is exploited, historical or recent, pre- and post-pandemic, under a people-focused view.