Ensemble averaging deep neural network for botnet detection in heterogeneous Internet of Things devices

The botnet attack is one of the coordinated attack types that can infect Internet of Things (IoT) devices and cause them to malfunction. Botnets can steal sensitive information from IoT devices and control them to launch another attack, such as a Distributed Denial-of-Service (DDoS) attack or email spam. This attack is commonly detected using a network-based Intrusion Detection System (NIDS) that monitors the network device's activity. However, IoT network is dynamic and IoT devices have many types with different configurations and vendors in IoT environments. Therefore, this research proposes an Intrusion Detection System (IDS) by ensemble-ing traffic from heterogeneous IoT devices. This research proposes Deep Neural Network (DNN) to create a training model from each heterogeneous IoT device. After that, each training model from each heterogeneous IoT device is used to predict the traffic. The prediction results from each training model are averaged using the ensemble averaging method to determine the final result. This research used the N-BaIoT dataset to validate the proposed IDS model. Based on experimental results, ensemble averaging DNN can detect botnet attacks in heterogeneous IoT devices with an average accuracy of 97.21, precision of 91.41, recall of 87.31, and F1-score 88.48.

Ensemble averaging using remote sensing data to model spatiotemporal PM10 concentrations in sparsely monitored South Africa

There is a paucity of air quality data in sub-Saharan African countries to inform science driven air quality management and epidemiological studies. We investigated the use of available remote-sensing aerosol optical depth (AOD) data to develop spatially and temporally resolved models to predict daily particulate matter (PM₁₀) concentrations across four provinces of South Africa (Gauteng, Mpumalanga, KwaZulu-Natal and Western Cape) for the year 2016 in a two-staged approach. In stage 1, a Random Forest (RF) model was used to impute Multiangle Implementation of Atmospheric Correction AOD data for days where it was missing. In stage 2, the machine learner algorithms RF, Gradient Boosting and Support Vector Regression were used to model the relationship between ground-monitored PM₁₀ data, AOD and other spatial and temporal predictors. These were subsequently combined in an ensemble model to predict daily PM₁₀ concentrations at 1 km × 1 km spatial resolution across the four provinces. An out-of-bag R² of 0.96 was achieved for the first stage model. The stage 2 cross-validated (CV) ensemble model captured 0.84 variability in ground-monitored PM₁₀ with a spatial CV R² of 0.48 and temporal CV R² of 0.80. The stage 2 model indicated an optimal performance of the daily predictions when aggregated to monthly and annual means. Our results suggest that a combination of remote sensing data, chemical transport model estimates and other spatiotemporal predictors has the potential to improve air quality exposure data in South Africa's major industrial provinces. In particular, the use of a combined ensemble approach was found to be useful for this area with limited availability of air pollution ground monitoring data.

MFC: An open-source high-order multi-component, multi-phase, and multi-scale compressible flow solver

MFC is an open-source tool for solving multi-component, multi-phase, and bubbly compressible flows. It is capable of efficiently solving a wide range of flows, including droplet atomization, shock-bubble interaction, and bubble dynamics. We present the 5- and 6-equation thermodynamically-consistent diffuse-interface models we use to handle such flows, which are coupled to high-order interface-capturing methods, HLL-type Riemann solvers, and TVD time-integration schemes that are capable of simulating unsteady flows with strong shocks. The numerical methods are implemented in a flexible, modular framework that is amenable to future development. The methods we employ are validated via comparisons to experimental results for shock-bubble, shock-droplet, and shock-water-cylinder interaction problems and verified to be free of spurious oscillations for material-interface advection and gas-liquid Riemann problems. For smooth solutions, such as the advection of an isentropic vortex, the methods are verified to be high-order accurate. Illustrative examples involving shock-bubble-vessel-wall and acoustic-bubble-net interactions are used to demonstrate the full capabilities of MFC.

Transient protein-protein interactions visualized by solution NMR

Proteins interact with each other to establish their identities in cell. The affinities for the interactions span more than ten orders of magnitude, and KD values in μM-mM regimen are considered transient and are important in cell signaling. Solution NMR including diamagnetic and paramagnetic techniques has enabled atomic-resolution depictions of transient protein-protein interactions. Diamagnetic NMR allows characterization of protein complexes with KD values up to several mM, whereas ultraweak and fleeting complexes can be modeled with the use of paramagnetic NMR especially paramagnetic relaxation enhancement (PRE). When tackling ever-larger protein complexes, PRE can be particularly useful in providing long-range intermolecular distance restraints. As NMR measurements are averaged over the ensemble of complex structures, structural information for dynamic protein-protein interactions besides the stereospecific one can often be extracted. Herein the protein interaction dynamics are exemplified by encounter complexes, alternative binding modes, and coupled binding/folding of intrinsically disordered proteins. Further integration of NMR with other biophysical techniques should allow better visualization of transient protein-protein interactions. In particular, single-molecule data may facilitate the interpretation of ensemble-averaged NMR data. Though same structures of proteins and protein complexes were found in cell as in diluted solution, we anticipate that the dynamics of transient protein protein-protein interactions be different, which awaits awaits exploration by NMR. This article is part of a Special Issue entitled: Physiological Enzymology and Protein Functions. This article is part of a Special Issue entitled: Physiological Enzymology and Protein Functions.

Computational method for high resolution spectral analysis of fractionated atrial electrograms

BACKGROUND

The discrete Fourier transform (DFT) is often used as a spectral estimator for analysis of complex fractionated atrial electrograms (CFAE) acquired during atrial fibrillation (AF). However, time resolution can be unsatisfactory, as the frequency resolution is proportional to rate/time interval. In this study we compared the DFT to a new spectral estimator with improved time-frequency resolution.

METHOD

Recently, a novel spectral estimator (NSE) based upon signal averaging was derived and implemented computationally. The NSE is similar to the DFT in that both estimators model the autocorrelation function to form the power spectrum. However, as derived in this study, NSE frequency resolution is proportional to rate/period(2) and thus unlike the DFT, is not directly dependent on the window length. We hypothesized that the NSE would provide improved time resolution while maintaining satisfactory frequency resolution for computation of CFAE spectral parameters. Window lengths of 8s, 4s, 2s, 1s, and 0.5s were used for analysis. Two criteria gauged estimator performance. Firstly, a periodic electrogram pattern with phase jitter was embedded in interference. The error in detecting the frequency of the periodic pattern was determined. Secondly, significant differences in spectral parameters for paroxysmal versus persistent AF data, which have known dissimilarities, were determined using the DFT versus NSE methods. The parameters measured were the dominant amplitude, dominant frequency, and mean spectral profile.

RESULTS

At all time resolutions, the error in detecting the frequency of the repeating electrogram pattern was less for NSE than for DFT (p<0.001). The DFT was accurate to 2s time resolution/0.5 Hz frequency resolution, while the NSE was accurate to 0.5s time resolution/0.05 Hz frequency resolution. At all time resolutions, significant differences in the dominant amplitude spectral parameter for paroxysmal versus persistent CFAE were greater using NSE than DFT (p<0.0001). For three of five time resolutions, the NSE had greater significant differences than DFT for discriminating the dominant frequency and mean spectral profile parameters between AF types.

CONCLUSIONS

The results suggest that the NSE has improved performance versus DFT for measurement of CFAE spectral properties.