Multi-Regional Modeling of Cumulative COVID-19 Cases Integrated with Environmental Forest Knowledge Estimation: A Deep Learning Ensemble Approach

Reliable modeling of novel commutative cases of COVID-19 (CCC) is essential for determining hospitalization needs and providing the benchmark for health-related policies. The current study proposes multi-regional modeling of CCC cases for the first scenario using autoregressive integrated moving average (ARIMA) based on automatic routines (AUTOARIMA), ARIMA with maximum likelihood (ARIMAML), and ARIMA with generalized least squares method (ARIMAGLS) and ensembled (ARIMAML-ARIMAGLS). Subsequently, different deep learning (DL) models viz: long short-term memory (LSTM), random forest (RF), and ensemble learning (EML) were applied to the second scenario to predict the effect of forest knowledge (FK) during the COVID-19 pandemic. For this purpose, augmented Dickey–Fuller (ADF) and Phillips–Perron (PP) unit root tests, autocorrelation function (ACF), partial autocorrelation function (PACF), Schwarz information criterion (SIC), and residual diagnostics were considered in determining the best ARIMA model for cumulative COVID-19 cases (CCC) across multi-region countries. Seven different performance criteria were used to evaluate the accuracy of the models. The obtained results justified both types of ARIMA model, with ARIMAGLS and ensemble ARIMA demonstrating superiority to the other models. Among the DL models analyzed, LSTM-M1 emerged as the best and most reliable estimation model, with both RF and LSTM attaining more than 80% prediction accuracy. While the EML of the DL proved merit with 96% accuracy. The outcomes of the two scenarios indicate the superiority of ARIMA time series and DL models in further decision making for FK.

A Hybrid Classification Technique for Enhancing the Effectiveness of Intrusion Detection Systems Using Machine Learning

The objective of this paper is to propose and develop a hybrid intrusion detection system to handle series and non-series data by applying the two different concepts that are named clustering and autocorrelation function in a single architecture. There is a need to propose and build a system that can handle both types of data whether it is series or non-series. Therefore, the authors used two concepts to generate a robust approach to craft a hybrid intrusion detection system. The authors utilize an unsupervised clustering approach that is used to categorize the data based on domain similarity to handle non-series data and another approach is based on autocorrelation function to handle series data. The approach is consumed in single architecture where it carries data as input from both host-based intrusion detection systems and network-based intrusion detection systems. The result shows that the hybrid intrusion detection system is categorizing data based on the optimal number of clusters obtained through the elbow method in clustering.

Stride segmentation of inertial sensor data using statistical methods for different walking activities

Human gait data can be collected using inertial measurement units (IMUs). An IMU is an electronic device that uses an accelerometer and gyroscope to capture three-axial linear acceleration and three-axial angular velocity. The data so collected are time series in nature. The major challenge associated with these data is the segmentation of signal samples into stride-specific information, that is, individual gait cycles. One empirical approach for stride segmentation is based on timestamps. However, timestamping is a manual technique, and it requires a timing device and a fixed laboratory set-up which usually restricts its applicability outside of the laboratory. In this study, we have proposed an automatic technique for stride segmentation of accelerometry data for three different walking activities. The autocorrelation function (ACF) is utilized for the identification of stride boundaries. Identification and extraction of stride-specific data are done by devising a concept of tuning parameter ( $t_{p}$ ) which is based on minimum standard deviation ( $\sigma$ ). Rigorous experimentation is done on human activities and postural transition and Osaka University – Institute of Scientific and Industrial Research gait inertial sensor datasets. Obtained mean stride duration for level walking, walking upstairs, and walking downstairs is 1.1, 1.19, and 1.02 s with 95% confidence interval [1.08, 1.12], [1.15, 1.22], and [0.97, 1.07], respectively, which is on par with standard findings reported in the literature. Limitations of accelerometry and ACF are also discussed. stride segmentation; human activity recognition; accelerometry; gait parameter estimation; gait cycle; inertial measurement unit; autocorrelation function; wearable sensors; IoT; edge computing; tinyML.

Delirium, Caffeine, and Perioperative Cortical Dynamics

Delirium is a major public health issue associated with considerable morbidity and mortality, particularly after surgery. While the neurobiology of delirium remains incompletely understood, emerging evidence suggests that cognition requires close proximity to a system state called criticality, which reflects a point of dynamic instability that allows for flexible access to a wide range of brain states. Deviations from criticality are associated with neurocognitive disorders, though the relationship between criticality and delirium has not been formally tested. This study tested the primary hypothesis that delirium in the postanesthesia care unit would be associated with deviations from criticality, based on surrogate electroencephalographic measures. As a secondary objective, the impact of caffeine was also tested on delirium incidence and criticality. To address these aims, we conducted a secondary analysis of a randomized clinical trial that tested the effects of intraoperative caffeine on postoperative recovery in adults undergoing major surgery. In this substudy, whole-scalp (16-channel) electroencephalographic data were analyzed from a subset of trial participants (n = 55) to determine whether surrogate measures of neural criticality – (1) autocorrelation function of global alpha oscillations and (2) topography of phase relationships via phase lag entropy – were associated with delirium. These measures were analyzed in participants experiencing delirium in the postanesthesia care unit (compared to those without delirium) and in participants randomized to caffeine compared to placebo. Results demonstrated that autocorrelation function in the alpha band was significantly reduced in delirious participants, which is important given that alpha rhythms are postulated to play a vital role in consciousness. Moreover, participants randomized to caffeine demonstrated increased alpha autocorrelation function concurrent with reduced delirium incidence. Lastly, the anterior-posterior topography of phase relationships appeared most preserved in non-delirious participants and in those receiving caffeine. These data suggest that early postoperative delirium may reflect deviations from neural criticality, and caffeine may reduce delirium risk by shifting cortical dynamics toward criticality.

ARIMA model for forecasting of evaporation of Solapur station of Maharashtra, India

This paper deals with the stochastic modeling of weekly evaporation by using Seasonal ARIMA model for weekly evaporation data for the period of 1987-2008 with a total of 1144 readings for semi-arid Solapur station in Maharashtra. ARIMA models of 1st order were selected based on observing autocorrelation function (ACF) and partial autocorrelation function (PACF) of the weekly evaporation series. The model parameters were obtained by using maximum likelihood method with the help of three tests (i.e., standard error, ACF and PACF of residuals and Akaike Information Criteria). Adequacy of the selected models was determined. The ARIMA model that passed the adequacy test was selected for forecasting. The Seasonal ARIMA (1, 0, 1) (1, 0, 1)52 with lower RMSE is finally selected for forecasting of weekly evaporation values, at Solapur.

SARIMA modeling of the monthly average maximum and minimum temperatures in the eastern plateau region of India

The SARIMA time series model is fitted to the monthly average maximum and minimum temperature data sets collected at Giridih, India for the years 1990-2011. From the time-series plots, we observe that the patterns of both the series are quite different; maximum temperature series contain sharp peaks in almost all the years while it is not true for the minimum temperature series and hence both the series are modeled separately (also for the sake of simplicity). SARIMA models are selected based on observing autocorrelation function (ACF) and partial autocorrelation function (PACF) of the monthly temperature series. The model parameters are obtained by using maximum likelihood method with the help of three tests [i.e., standard error, ACF and PACF of residuals and Akaike Information Criteria (AIC), Bayesian Information Criteria (BIC) and corrected Akaike Information Criteria (AICc)]. Adequacy of the selected models is determined using diagnostic checking with the standardized residuals, ACF of residuals, normal Q-Q plot of the standardized residuals and p-values of the Ljung-Box statistic. The models ARIMA (1; 0; 2) × (0; 1; 1)12 and ARIMA (0; 1; 1) × (1; 1; 1)12 are finally selected for forecasting of monthly average maximum and minimum temperature values respectively for the eastern plateau region of India.

Fried’s coherence length measurement of dynamic Kolmogorov type turbulence using autocorrelation function

A new method to find Fried’s coherence length of a dynamic Kolmogorov type turbulence in laboratory environment is reported in this paper. This method utilises autocorrelation function obtained from the quantitative characteristics of a rotating pseudo random phase plate in one of the arms of Mach-Zehnder interferometer. Theoretical formalism and experimental verification are presented.

On longitudinal and transversal diffusion of carbon nanotubes

In this work, the anisotropy of diffusion of carbon nanotubes in water was studied by the molecular dynamics method. Two models of nanotubes were used, their lengths varied from 4 to 31 nanometers. The first model is a nanotube with armchair chirality, the second is connected solid nanoscale rods. The behavior of various components of the velocity autocorrelation function of the nanotubes center of mass has been studied. It was established that the transverse component of this function has a negative region and a minimum point, in contrast to the average autocorrelation function, which decays monotonically. It is shown that the diffusion coefficients in the longitudinal and transverse directions can differ several times; the method proposed in this work was used to determine them. The effect of anisotropy increases with an increase in the ratio of the characteristic sizes of the nanotube. Using the Stokes - Einstein formula, the effective hydrodynamic radii of nanotubes have been determined. In all cases, the effective radius is significantly less than the tube length.