Deep Learning Based Customer Preferences Analysis in Industry 4.0 Environment

Customer preferences analysis and modelling using deep learning in edge computing environment are critical to enhance customer relationship management that focus on a dynamically changing market place. Existing forecasting methods work well with often seen and linear demand patterns but become less accurate with intermittent demands in the catering industry. In this paper, we introduce a throughput deep learning model for both short-term and long-term demands forecasting aimed at allowing catering businesses to be highly efficient and avoid wastage. Moreover, detailed data collected from a business online booking system in the past three years have been used to train and verify the proposed model. Meanwhile, we carefully analyzed the seasonal conditions as well as past local or national events (event analysis) that could have had critical impact on the sales. The results are compared with the best performing forecast methods Xgboost and autoregressive moving average model (ARMA), and they suggest that the proposed method significantly improves demand forecasting accuracy (up to 80%) for dishes demand along with reduction in associated costs and labor allocation.

Determining the Pension Benefit Obligation of a Defined Benefit Plan: Applying a Multivariate ARIMA Stochastic Model

<p>In this study we examine the robustness of fit for a multivariate and an autoregressive integrated moving average model to a data sample time series type. The sample is a recurrent actuarial data set for a 10-year horizon. We utilize this methodology to contrast with stochastic models to make projections beyond the data horizon. Our key results suggest that both types of models are useful for making predictions of actuarial liability levels given by PBO Projected Benefit Obligations on and off the horizon of the sample time series. As we have seen in prior research, the use of multivariate models for control and auditing purposes is widely recommended. Fast and reliable statistical estimates are desirable in all cases, whether for audit purposes or to verify and validate miscellaneous actuarial results.</p>

Analysis of Statistical Trends of Future Air Pollutants for Accurate Prediction

The climate change may be mitigated, and intra air quality assessment and local human well-being can benefit from a decrease in emission of pollutant content in the air. Monitoring the quality of the air around us is one way to do this. However, a location with various emission sources and short-term fluctuations in emissions in both time and space, and changes in winds, temperature, and precipitation creates a complex and variable pollution concentration field in the atmosphere. Therefore, based on the time and location where the sample is obtained, the measurement conducted are reflected in the monitoring results. This study aims to investigate one of India's most polluted cities' air quality measurements by greenhouse gas emissions. Using the Mann-Kendall and Sen's slope estimators, the research piece gives a statistical trend analysis of several air contaminants based on previous pollution data from Mumbai, India's air quality index station. In addition, future levels of air pollution may be correctly forecasted using an autoregressive integrated moving average model. This is followed by comparing different air quality standards and forecasts for future air pollution levels.

Provision of social-norms feedback to general practices whose antibiotic prescribing is increasing: a national randomized controlled trial

Aim The Chief Medical Officer of England writes an annual social-norms-feedback letter to the highest antibiotic-prescribing GP practices. We investigated whether sending a social-norms-feedback letter to practices whose prescribing was increasing would reduce prescribing. Subject and methods We conducted a two-armed randomised controlled trial amongst practices whose STAR-PU-adjusted prescribing was in the 20th–95th percentiles and had increased by > 4% year-on-year in the 2 previous financial years. Intervention practices received a letter on 1st March 2018 stating ‘The great majority (80%) of practices in England reduced or stabilised their antibiotic prescribing rates in 2016/17. However, your practice is in the minority that have increased their prescribing by more than 4%.’. Control practices received no letter. The primary outcome was the STAR-PU-adjusted rate of antibiotic prescribing in the months from March to September 2018. Results We randomly assigned 930 practices; ten closed or merged pre-trial, leaving 920 practices — 448 in the intervention and 472 in the control. An autoregressive and moving average model of first order ARMA(1,1) correlation structure showed no effect of the intervention (β < −0.01, z = −0.50, p = 0.565). Prescribing reduced over time in both arms (β < −0.01, z = −36.36, p < 0.001). Conclusions A social-norms-feedback letter to practices whose prescribing was increasing did not decrease prescribing compared to no letter. Trial registration NCT03582072.

Applying Deep Learning in the Training of Communication Design Talents Under University-Industrial Research Collaboration

The purpose of the study was to solve the problem of the mismatching between the supply and demand of the talents that universities provide for society, whose major is communication design. The correlations between social post demand and university cultivation, as well as between social post demand and the demand indexes of enterprises for posts, are explored under the guidance of University-Industrial Research Collaboration. The backpropagation neural network (BPNN) is used, and the advantages of the Seasonal Autoregressive Integrated Moving Average model (SARIMA) model are combined to design the SARIMA-BPNN (SARIMA-BP) model after the relevant parameters are adjusted. Through the experimental analysis, it is found that the error of the root mean square of the designed SARIMA-BP model in post prediction is 7.523 and that of the BPNN model is 16.122. The effect of the prediction model that was designed based on deep learning is smaller than that of the previous model based on the neural network, and it can predict future posts more accurately for colleges and universities. Guided by the “University-Industrial Research Collaboration,” students will have more practice in the teaching process in response to social needs. “University-Industrial Research Collaboration” guides the teaching direction for communication design majors and can help to cultivate communication design talents who are competent for the post provided.

Epidemiological Trends of Malaria in Five Years and under Children of Nsanje District in Malawi, 2015–2019

Background: Malaria continues to be a major public health problem in Malawi and the greatest load of mortality and morbidity occurs in children five years and under. However, there is no information yet regarding trends and predictions of malaria incidence in children five years and under at district hospital level, particularly at Nsanje district hospital. Aim: Therefore, this study aimed at investigating the trends of malaria morbidity and mortality in order to design appropriate interventions on the best approach to contain the disease in the near future. Methodology: Trend analysis of malaria morbidity and mortality together with time series analysis using the SARIMA (Seasonal Autoregressive Integrated Moving Average) model was used to predict malaria incidence in Nsanje district. Results: The SARIMA model used malaria cases from 2015 to 2019 and created the best model to forecast the malaria cases in Nsanje from 2020 to 2022. An SARIMA (0, 1, 2) (0,1,1)12 was suitable for forecasting the incidence of malaria for Nsanje. Conclusion: The mortality and morbidity trend showed that malaria cases were growing at a fluctuating rate at Nsanje district hospital. The relative errors between the actual values and predicted values indicated that the predicted values matched the actual values well. Therefore, the model proved that it was adequate to forecast monthly malaria cases and it had a good fit, hence, was appropriate for this study

Price Analysis and Forecasting for Bitcoin Using Auto Regressive Integrated Moving Average Model

This paper investigated Bitcoin daily closing price using time series approach to predict future values for financial managers and investors. Daily data were sourced from CoinDesk, with Bitcoin Price Index (BPI) for 5 years (January 1, 2016 to May 31, 2021) extracted. Data analysis and modelling of price trend using Autoregressive Integrated Moving Average (ARIMA) model was carried out, and a suitable model for forecasting was proposed. Results showed that ARIMA(6,1,12) model was the most suitable based on a combination of number of significant coefficients and values of volatility, Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC). A two-month test window was used for forecasting and prediction. Results showed a decline in prediction accuracy as number of days of the test period increased; from 99.94% for the first 7 days, to 99.59 % for 14 days and 95.84% for 30 days. For the two-month test period, percentage accuracy was 84.75%. The study confirms that the ARIMA model is a veritable planning tool for financial managers, investors and other stakeholders; especially for short-term forecasting. It is however imperative that the influence of external factors, such as investors’/influencers’ comments and government intervention, that may affect forecasting be taken into consideration.

Studying monthly rainfall over Dibrugarh, Assam: Use of SARIMA approach

Perceptive the rainfall pattern is tough for the solution of several regional environmental issues of water resources management, with implications for agriculture, climate change, and natural calamity such as floods and droughts. Statistical computing, modeling and forecasting data are key instruments for studying these patterns. The study of time series analysis and forecasting has become a major tool in different applications in hydrology and environmental fields. Among the most effective approaches for analyzing time series data is the ARIMA (Autoregressive Integrated Moving Average) model introduced by Box and Jenkins. In this study, an attempt has been made to use Box-Jenkins methodology to build ARIMA model for monthly rainfall data taken from Dibrugarh for the period of 1980- 2014 with a total of 420 points. We investigated and found that ARIMA (0, 0, 0) (0, 1, 1)12 model is suitable for the given data set. As such this model can be used to forecast the pattern of monthly rainfall for the upcoming years, which can help the decision makers to establish priorities in terms of agricultural, flood, water demand management etc.