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.

Socially Responsible Investing and Sustainable Indices: A Sustainability Agenda

COVID-19 pandemic has brought climate change and socially responsible investing back to the forefront. Sustainable investing, though well-entrenched in developed countries, is slowly gaining traction in emerging markets. Sustainability indices operate as quality indicators and bridge information gap. This study explores the usefulness of three such indices and offers an autoregressive moving average model on Carbonex series for sustainable investments on Bombay Stock Exchange. However, the model fails to align with the long-term goals of socially responsible investing and the investor community needs to engage with regulators, corporations and rating agencies so that these sustainability indices can better serve their information needs and offer a valid measure of sustainable practices. COVID-19 brings with it the opportunity to ideate and envision innovative approaches to support a carbon-free economic agenda and to design eco-friendly infrastructure, planned urban development and transition to clean energy. Take–make–consume–waste attitude is out and the philosophy of preserve–endure–nurture–bequeath will be the new normal.

Gaze Focalization System for Driving Applications Using OpenFace 2.0 Toolkit with NARMAX Algorithm in Accidental Scenarios

Monitoring driver attention using the gaze estimation is a typical approach used on road scenes. This indicator is of great importance for safe driving, specially on Level 3 and Level 4 automation systems, where the take over request control strategy could be based on the driver’s gaze estimation. Nowadays, gaze estimation techniques used in the state-of-the-art are intrusive and costly, and these two aspects are limiting the usage of these techniques on real vehicles. To test this kind of application, there are some databases focused on critical situations in simulation, but they do not show real accidents because of the complexity and the danger to record them. Within this context, this paper presents a low-cost and non-intrusive camera-based gaze mapping system integrating the open-source state-of-the-art OpenFace 2.0 Toolkit to visualize the driver focalization on a database composed of recorded real traffic scenes through a heat map using NARMAX (Nonlinear AutoRegressive Moving Average model with eXogenous inputs) to establish the correspondence between the OpenFace 2.0 parameters and the screen region the user is looking at. This proposal is an improvement of our previous work, which was based on a linear approximation using a projection matrix. The proposal has been validated using the recent and challenging public database DADA2000, which has 2000 video sequences with annotated driving scenarios based on real accidents. We compare our proposal with our previous one and with an expensive desktop-mounted eye-tracker, obtaining on par results. We proved that this method can be used to record driver attention databases.

Analysis of public opinion evolution of COVID-19 based on LDA-ARMA hybrid model

The aim of this study was to explore a method for developing an emotional evolution classification model for large-scale online public opinion of events such as Coronavirus Disease 2019 (COVID-19), in order to guide government departments to adopt differentiated forms of emergency management and to correctly guide online public opinion for severely afflicted areas such as Wuhan and those afflicted elsewhere in China. We propose the LDA-ARMA deep neural network for dynamic presentation and fine-grained categorization of a public opinion events. This was applied to a huge quantity of online public opinion texts in a complicated setting and integrated the proposed sentiment measurement algorithm. To begin, the Latent Dirichlet Allocation (LDA) was employed to extract information about the topic of comments. The autoregressive moving average model (ARMA) was then utilized to perform multidimensional sentiment analysis and evolution prediction on large-scale textual data related to COVID-19 published by netizens from Wuhan and other countries on Sina Weibo. The results show that Wuhan netizens paid more attention to the development of the situation, treatment measures, and policies related to COVID-19 than other issues, and were under greater emotional pressure, whereas netizens in the rest of the country paid more attention to the overall COVID-19 prevention and control, and were more positive and optimistic with the assistance of the government and NGOs. The average error in predicting public opinion sentiment was less than 5.64%, demonstrating that this approach may be effectively applied to the analysis of large-scale online public sentiment evolution.

Co-integration with score-driven models: an application to US real GDP growth, US inflation rate, and effective federal funds rate

Nonlinear co-integration is studied for score-driven models, using a new multivariate dynamic conditional score/generalized autoregressive score model. The model is named t-QVARMA (quasi-vector autoregressive moving average model), which is a location model for the multivariate t-distribution. In t-QVARMA, I(0) and co-integrated I(1) components of the dependent variables are included. For t-QVARMA, the conditions of the maximum likelihood estimator and impulse response functions (IRFs) are presented. A limiting special case of t-QVARMA, named Gaussian-QVARMA, is a Gaussian-VARMA specification with I(0) and I(1) components. As an empirical application, the US real gross domestic product growth, US inflation rate, and effective federal funds rate are studied for the period of 1954 Q3 to 2020 Q2. Statistical performance and predictive accuracy of t-QVARMA are superior to those of Gaussian-VAR. Estimates of the short-run IRF, long-run IRF, and total IRF impacts for the US data are reported.

Analysis and prediction of polar motion using MSSA method

Polar motion is the movement of the Earth's rotational axis relative to its crust, reflecting the influence of the material exchange and mass redistribution of each layer of the Earth on the Earth's rotation axis. To better analyze the temporally varying characteristics of polar motion, multi-channel singular spectrum analysis (MSSA) was used to analyze the EOP 14 C04 series released by the International Earth Rotation and Reference System Service (IERS) from 1962 to 2020, and the amplitude of the Chandler wobbles were found to fluctuate between 20 and 200 mas and decrease significantly over the last 20 years. The amplitude of annual oscillation fluctuated between 60 and 120 mas, and the long-term trend was 3.72 mas/year, moving towards N56.79 °W. To improve prediction of polar motion, the MSSA method combining linear model and autoregressive moving average model was used to predict polar motion with ahead 1 year, repeatedly. Comparing to predictions of IERS Bulletin A, the results show that the proposed method can effectively predict polar motion, and the improvement rates of polar motion prediction for 365 days into the future were approximately 50% on average.