An Improved Granulated Convolutional Neural Network Data Analysis Model for COVID-19 Prediction

As COVID-19 poses a major threat to people's health and economy, there is an urgent need for forecasting methodologies that can anticipate its trajectory efficiently. In non-stationary time series forecasting jobs, there is frequently a hysteresis in the anticipated values relative to the real values. The multilayer deep-time convolutional network and a feature fusion network are combined in this paper's proposal of an enhanced Multilayer Deep Time Convolutional Neural Network (MDTCNet) for COVID-19 prediction to address this problem. In particular, it is possible to record the deep features and temporal dependencies in uncertain time series, and the features may then be combined using a feature fusion network and a multilayer perceptron. Last but not least, the experimental verification is conducted on the prediction task of COVID-19 real daily confirmed cases in the world and the United States with uncertainty, realizing the short-term and long-term prediction of COVID-19 daily confirmed cases, and verifying the effectiveness and accuracy of the suggested prediction method, as well as reducing the hysteresis of the prediction results.

Visualising the Optimistic, Realistic, and Pessimistic Financial Distress Outlooks for Airport Operations in Malaysia

This paper aims to visualise three financial distress outlooks using computer simulations. The financial distress exposure for airport operations in Malaysia between 1991 and 2021 is given by Altman Z”-score and modelled by the multivariate generalized linear model (MGLM). Seven determinants contributing to the financial distress from literature are examined. The determinant series are fitted individually by using linear model with time series components and autoregressive integrated moving average models to forecast values for the next 10 financial years. Future short- to long-term memory effects following COVID-19 are apparent in time series plots. In the simulations, the MGLM procedure utilised Gaussian, gamma, and Cauchy probability distributions associated with expectations and challenges of doing business as well as uncertainties in the economy. The underlying trends of realistic, optimistic, and pessimistic financial distress outlooks insinuate that the increasing risk of financial distress of airport operations in Malaysia is expected to continue for the next decade.

Forecasting Residential Energy Consumption: A Case Study for Greece

Residential energy consumption forecasting has immense value in energy efficiency and sustainability. In the current work we tried to forecast energy consumption on residences in Athens, Greece. As a proof of concept, smart sensors were installed into two residences that recorded energy consumption, as well as indoors environmental variables (humidity and temperature). It should be noted that the data set was collected during the COVID-19 pandemic. Moreover, we integrated weather data from a public weather site. A dashboard was designed to facilitate monitoring of the sensors' data. We addressed various issues related to data quality and then we tried different models to forecast daily energy consumption. In particular, LSTM neural networks, ARIMA, SARIMA, SARIMAX and Facebook (FB) Prophet were tested. Overall SARIMA and FB Prophet had the best performance. Copyright © 2023 by SCITEPRESS - Science and Technology Publications, Lda. Under CC license (CC BY-NC-ND 4.0)

Extracting Rules via Markov Chains for Cryptocurrencies Returns Forecasting.

With the growing popularity of digital currencies known as cryptocurrencies, there is a need to develop models capable of robustly analyzing and predicting the value of future returns in these markets. In this article, we extract behavior rules to predict the values of future returns in the Bitcoin, Ethereum, Litecoin, and Ripple closing series. We used categorical data in the analyses and Markov chain models from the first to the tenth order to propose a new way of establishing possible future scenarios, in which we analyze the dependence of memory on the dynamics of the process. We used the measurements of accuracy Mean Quadratic Error, Absolute Error Mean Percentage, and Absolute Standard Deviation for the choice of the best models. Our findings reveal that cryptocurrencies have long-range memory. Bitcoin, Ethereum, and Ripple exposed seven steps of memory, while Litecoin displayed nine memory steps. From the transitions between states that happened the most, we defined decision rules that assisted in the definition of future returns in the series. Our results can support the decisions of traders, investors, crypto-traders, and policy-makers.

Outbreak trends of fatality rate into coronavirus disease-2019 using deep learning

The World Health Organization (WHO) has declared the novel coronavirus as global pandemic on 11 March 2020. It was known to originate from Wuhan, China and its spread is unstoppable due to no proper medication and vaccine. The developed forecasting models predict the number of cases and its fatality rate for coronavirus disease 2019 (COVID-19), which is highly impulsive. This paper provides intrinsic algorithms namely - linear regression and long short-term memory (LSTM) using deep learning for time series-based prediction. It also uses the ReLU activation function and Adam optimiser. This paper also reports a comparative study on existing models for COVID-19 cases from different continents in the world. It also provides an extensive model that shows a brief prediction about the number of cases and time for recovered, active and deaths rate till January 2021.Copyright © 2023 Inderscience Enterprises Ltd.

Stock Price Forecasting of IBEX35 Companies in the Petroleum, Electricity, and Gas Industries

In recent years, time series forecasting has become an essential tool for stock market analysts to make informed decisions regarding stock prices. The present research makes use of various exponential smoothing forecasting methods. These include exponential smoothing with multiplicative errors and additive trend (MAN), exponential smoothing with multiplicative errors (MNN), and simple exponential smoothing with additive errors (ANN) for the forecasting of the stock prices of six different companies in the petroleum, electricity, and gas industries that are listed in the IBEX35 index. The database employed for this research contained the IBEX35 index values and stock closing prices from 3 January 2000 to 30 December 2022. The models trained with this data were employed in order to forecast the index value and the closing prices of the stocks under study from 2 January 2023 to 24 March 2023. The results obtained confirmed that although none of the proposed models outperformed the rest for all the companies, it is possible to calculate forecasting models able to predict a 95% confidence interval about real stock closing values and where the index will be in the following three months.

ARIMA Model based Time Series Modelling and Prediction of Foreign Exchange Rate against US Dollar

Exchange rate forecasting has proven challenging for players like traders and professionals in this current financial industry. Econometric and statistical models are often utilized in the analysis and forecasting of foreign exchange rate. Governments, financial organizations, and investors prioritize analyzing the future behaviour of currency pairs because this analyzing technique is being utilized to understand a country's economic status and to make a decision on whether to do any transactions of goods from that country. Several models are used to predict this kind of time-series with adequate accuracy. However, because of the random nature of these time series, strong predicting performance is difficult to achieve. During the Covid-19 situation, there is a drastic change in the exchange rate worldwide. This paper examines the behaviour of Australia's (AUD) daily foreign exchange rates against the US Dollar from January 2016 to December 2020 and forecasts the 2021 exchange rate using the ARIMA model. For better accuracy, technical indicators such as Interest Rate Differential, GDP Growth Rate and Unemployment Rate are also taken into account. In exchange rate forecasting, there are various types of performance measures based on which the accuracy of the forecasted result is computed. This paper examines seven performance measures and found that the accuracy of the forecasted results is adequate with the actual data. © 2022 IEEE.

PAN-cODE: COVID-19 forecasting using conditional latent ODEs.

The coronavirus disease 2019 (COVID-19) pandemic has caused millions of deaths around the world and revealed the need for data-driven models of pandemic spread. Accurate pandemic caseload forecasting allows informed policy decisions on the adoption of non-pharmaceutical interventions (NPIs) to reduce disease transmission. Using COVID-19 as an example, we present Pandemic conditional Ordinary Differential Equation (PAN-cODE), a deep learning method to forecast daily increases in pandemic infections and deaths. By using a deep conditional latent variable model, PAN-cODE can generate alternative caseload trajectories based on alternate adoptions of NPIs, allowing stakeholders to make policy decisions in an informed manner. PAN-cODE also allows caseload estimation for regions that are unseen during model training. We demonstrate that, despite using less detailed data and having fully automated training, PAN-cODE's performance is comparable to state-of-the-art methods on 4-week-ahead and 6-week-ahead forecasting. Finally, we highlight the ability of PAN-cODE to generate realistic alternative outcome trajectories on select US regions.

Using Time Series Forecasting for Analysis of GDP Growth in India

Gross Domestic Product is one of the most important economic indicators of the country and its positive or negative growth indicates the economic development of the country. It is calculated quarterly and yearly at the end of the financial year. The GDP growth of India has seen fluctuations from last few decades after independence and reached as high as 10.25 in 2010 and declined to low of -5.23 in 1979. The GDP growth has witnessed a continuous decline in the past five years, taking it from 8.15 in 2015 to 1.87 in 2020.The lockdown imposed in the country to curb the spread of COVID-19 has caused massive slowdown in the economy of the country by affecting all major contributing sectors of the GDP except agricultural sector. To keep on track on the GDP growth is one of the parameters for deciding the economic policies of the country. In this study, we are analyzing and forecasting the GDP growth using the time series forecasting techniques Prophet and Arima model. This model can assist policy makers in framing policies or making decisions.

Omicron Case Prediction using Machine Learning

It's been over two years that the world has been dealing with the novel Coronavirus Disease 2019 (COVID-19). It has rocked the world in the face of another major outbreak. Countries have undergone various lockdowns curfews in their own ways, which certainly has impacted our daily lives. COVID-19 has undergone various mutations till now. It is responsible for the spikes in COVID-19 cases across the world. The latest variant 'Omicron'., labeled as B.1.1.529, has been marked as a Variant of Concern by the World Health Organization (WHO). It has been proven to be the most infectious, but less deadly as of now. This paper attempts to propose an analysis and prediction of Omicron daily cases in India using SARIMA Exponential Smoothing Machine Learning models. Both of these machine learning models are based on the time series forecasting concept and rely on previous data to predict future outcomes. © 2022 IEEE.

Data-driven predictive control for smart HVAC system in IoT-integrated buildings with time-series forecasting and reinforcement learning

Optimising HVAC operations towards human wellness and energy efficiency is a major challenge for smart facilities management, especially amid COVID situations. Although IoT sensors and deep learning were applied to support HVAC operations, the loss of forecasting accuracy in recursive prediction largely hinders their applications. This study presents a data-driven predictive control method with time-series forecasting (TSF) and reinforcement learning (RL), to examine various sensor metadata for HVAC system optimisation. This involves the development and validation of 16 Long Short-Term Memory (LSTM) based architectures with bi-directional processing, convolution, and attention mechanisms. The TSF models are comprehensively evaluated under independent, short-term recursive, and long-term recursive prediction scenarios. The optimal TSF models are integrated with a Soft Actor-Critic RL agent to analyse sensor metadata and optimise HVAC operations, achieving 17.4% energy savings and 16.9% thermal comfort improvement in the surrogate environment. The results show that recursive prediction leads to a significant reduction in model accuracy, and the effect is more pronounced in the temperature-humidity prediction model. The attention mechanism significantly improves prediction performance in both recursive and independent prediction scenarios. This study contributes new data-driven methods for smart HVAC operations in IoT-enabled intelligent buildings towards a human-centric built environment. © 2023 The Authors

Integrated smart analytics of nucleic acid amplification tests via paper microfluidics and deep learning in cloud computing

Pandemics such as COVID-19 have exposed global inequalities in essential health care. Here, we proposed a novel analytics of nucleic acid amplification tests (NAATs) by combining paper microfluidics with deep learning and cloud computing. Real-time amplifications of synthesized SARS-CoV-2 RNA templates were performed in paper devices. Information pertained to on-chip reactions in time-series format were transmitted to cloud server on which deep learning (DL) models were preloaded for data analysis. DL models enable prediction of NAAT results using partly gathered real-time fluorescence data. Using information provided by the G-channel, accurate prediction can be made as early as 9 min, a 78% reduction from the conventional 40 min mark. Reaction dynamics hidden in amplification curves were effectively leveraged. Positive and negative samples can be unbiasedly and automatically distinguished. Practical utility of the approach was validated by cross-platform study using clinical datasets. Predicted clinical accuracy, sensitivity and specificity were 98.6%, 97.6% and 99.1%. Not only the approach reduced the need for the use of bulky apparatus, but also provided intelligent, distributable and robotic insights for NAAT analysis. It set a novel paradigm for analyzing NAATs, and can be combined with the most cutting-edge technologies in fields of biosensor, artificial intelligence and cloud computing to facilitate fundamental and clinical research.Copyright © 2023 Elsevier Ltd

Aggregating Prophet and Seasonal Trend Decomposition for Time Series Forecasting of Italian Electricity Spot Prices

The cost of electricity and gas has a direct influence on the everyday routines of people who rely on these resources to keep their businesses running. However, the value of electricity is strongly related to spot market prices, and the arrival of winter and increased energy use owing to the demand for heating can lead to an increase in energy prices. Approaches to forecasting energy costs have been used in recent years;however, existing models are not yet robust enough due to competition, seasonal changes, and other variables. More effective modeling and forecasting approaches are required to assist investors in planning their bidding strategies and regulators in ensuring the security and stability of energy markets. In the literature, there is considerable interest in building better pricing modeling and forecasting frameworks to meet these difficulties. In this context, this work proposes combining seasonal and trend decomposition utilizing LOESS (locally estimated scatterplot smoothing) and Facebook Prophet methodologies to perform a more accurate and resilient time series analysis of Italian electricity spot prices. This can assist in enhancing projections and better understanding the variables driving the data, while also including additional information such as holidays and special events. The combination of approaches improves forecast accuracy while lowering the mean absolute percentage error (MAPE) performance metric by 18% compared to the baseline model.

Shape-based Evaluation of Epidemic Forecasts

Infectious disease forecasting for ongoing epidemics has been traditionally performed, communicated, and evaluated as numerical targets - 1, 2, 3, and 4 week ahead cases, deaths, and hospitalizations. While there is great value in predicting these numerical targets to assess the burden of the disease, we argue that there is also value in communicating the future trend (description of the shape) of the epidemic - for instance, if the cases will remain flat o r a s urge i s expected. To ensure what is being communicated is useful we need to be able to evaluate how well the predicted shape matches with the ground truth shape. Instead of treating this as a classification problem ( one out of n shapes), we define a transformation of the numerical forecasts into a "shapelet"-space representation. In this representation, each dimension corresponds to the similarity of the shape with one of the shapes of interest (a shapelet). We prove that this representation satisfies the property that two shapes that one would consider similar are mapped close to each other, and vice versa. We demonstrate that our representation is able to reasonably capture the trends in COVID-19 cases and deaths time-series. With this representation, we define an evaluation measure and a measure of agreement among multiple models. We also define the shapelet-space ensemble of multiple models as the mean of their shapelet-space representations. We show that this ensemble is able to accurately predict the shape of the future trend for COVID-19 cases and trends. We also show that the agreement between models can provide a good indicator of the reliability of the forecast. © 2022 IEEE.

Improving performance of deep learning predictive models for COVID-19 by incorporating environmental parameters.

The Coronavirus disease 2019 (COVID-19) pandemic has severely crippled the economy on a global scale. Effective and accurate forecasting models are essential for proper management and preparedness of the healthcare system and resources, eventually aiding in preventing the rapid spread of the disease. With the intention to provide better forecasting tools for the management of the pandemic, the current research work analyzes the effect of the inclusion of environmental parameters in the forecasting of daily COVID-19 cases. Three univariate variants of the long short-term memory (LSTM) model (basic/vanilla, stacked, and bi-directional) were employed for the prediction of daily cases in 9 cities across 3 countries with varying climatic zones (tropical, sub-tropical, and frigid), namely India (New Delhi and Nagpur), USA (Yuma and Los Angeles) and Sweden (Stockholm, Skane, Uppsala and Vastra Gotaland). The results were compared to a basic multivariate LSTM model with environmental parameters (temperature (T) and relative humidity (RH)) as additional inputs. Periods with no or minimal lockdown were chosen specifically in these cities to observe the uninhibited spread of COVID-19 and explore its dependence on daily environmental parameters. The multivariate LSTM model showed the best overall performance; the mean absolute percentage error (MAPE) showed an average of 64% improvement from other univariate models upon the inclusion of the above environmental parameters. Correlation with temperature was generally positive for the cold regions and negative for the warm regions. RH showed mixed correlations, most likely driven by its temperature dependence and effect of allied local factors. The results suggest that the inclusion of environmental parameters could significantly improve the performance of LSTMs for predicting daily cases of COVID-19, although other positive and negative confounding factors can affect the forecasting power.

COVID-19 Outbreak Estimation Approach Using Hybrid Time Series Modelling

In the beginning of March 2020, coronavirus was claimed to be a worldwide pandemic by the World Health Organization (WHO). In Wuhan, a region in China, around December 2019, the Corona virus, also known as the novel COVID-19 was first to arise and spread throughout the world within weeks. Depending upon publicly available data-sets, for the COVID-19 outbreak, we have developed a forecasting model with the use of hybridization of sequential and time series modelling. In our work, we assessed the main elements to forecasting the potential of COVID-19 outbreak throughout the globe. Inside the work, we have analyzed several relevant algorithms like Long short-term memory (LSTM) model (which is a sequential deep learning model), used to predict the tendency of the pandemic, Auto-Regressive Integrated Moving Average (ARIMA) method, used for analyzing and forecasting time series data, Prophet model an algorithm to construct forecasting/predictive models for time series data. Based on our analysis outcome proposed hybrid LSTM and ARIMA model outperformed other models in forecasting the trend of the Corona Virus Outbreak. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

District Level Covid Case Prediction using LSTM Models

Covid-19 has had an adverse effect on the world, with more than 440 million cases recorded so far. The outbreak has hampered the country's healthcare and economy. This calls for an accurate prediction model for the prediction of Covid Cases, so that it gives some time to the hospitals and administration, to make the necessary arrangement. For population-dense countries like India, the covid case dynamics of every district is different, hence this requires a district-wise case prediction of Covid Cases. In this paper, we perform prediction of covid cases across all districts of India using different architectures of Long short-term memory (LSTM) and performed a comparative analysis between them. To the best of our knowledge, this is the first such attempt at the district level. Bidirectional LSTM encoder-decoder outperformed other LSTM-based models and, gave a test set MAPE of 15.44, followed by LSTM Encoder Decoder, giving a MAPE of 19.72. © 2022 IEEE.

Solving resource forecasting in WiFi Network by NeuralProphet

Time series forecasting needs several approaches such as data pretreatment, model construction, etc. During the covid 19 outbreak, the data is very dynamic, therefore data processing and appropriate modeling are worried. Identifying patterns, recognizing abnormal data points, is one of the first stages to enhancing forecast outcomes. A point is considered an anomalous point when it is far distant from the mean of the data series. In this research, we deploy an automated anomaly detection approach that incorporates data preparation of neuralprophet library. After that, we design a model via neuralprophet to predict data after preprocessing data. The strategy is evaluated on a dataset of the times that public wifi was used every day with the purpose of forecasting the value of the following 30 days. The anticipated outcome is compared with that of Prophet, hybrid AR-LSTM, consequently indicating that the suggested technique in the study offers the best outcomes. © 2022 ACM.

Application of Machine Learning and Deep Learning in Forecasting Covid Daily Death Counts

Time series modeling and forecasting has fundamental importance to a wide range of applications. While classical time series models dominated the forecasting field for years, their applications have been limited to single time series data at low frequency such as monthly, quarterly or annually. The goal of this paper is to build multi-series time series models to forecast future daily death counts for each county in the state of Pennsylvania. The data used in this paper include JHU daily death counts and confirmed cases and CDC vaccination rates from 1/22/2020 to 1/7/2022 at the county level for Pennsylvania. Both machine learning (Extreme Gradient Boosted Tree XGBoost) and deep learning (Keras Slim Residual Neural Network Regressor, Keras) algorithms were explored and time series modeling related steps such as feature engineering, data partition and project setup are discussed in detail. In addition, four metrics were calculated to evaluate the algorithms' performance. The comparison with a baseline time series model indicated that machine learning and deep learning algorithms did improve forecasting accuracy significantly and Keras has slightly better performance than XGBoost. Finally, the Keras model was utilized to forecast daily death counts for 60 days after 1/7/2022, i.e., 1/8/2022 to 3/8/2022. Based on the model forecasts, daily death counts should gradually ease off by mid-February which has been validated by the subsequent observations. () © 2022 IEEE.

Outbreak trends of fatality rate into coronavirus disease-2019 using deep learning

The World Health Organization (WHO) has declared the novel coronavirus as global pandemic on 11 March 2020. It was known to originate from Wuhan, China and its spread is unstoppable due to no proper medication and vaccine. The developed forecasting models predict the number of cases and its fatality rate for coronavirus disease 2019 (COVID-19), which is highly impulsive. This paper provides intrinsic algorithms namely - linear regression and long short-term memory (LSTM) using deep learning for time series-based prediction. It also uses the ReLU activation function and Adam optimiser. This paper also reports a comparative study on existing models for COVID-19 cases from different continents in the world. It also provides an extensive model that shows a brief prediction about the number of cases and time for recovered, active and deaths rate till January 2021.