Javascript is required
Search
Volume 14, Issue 3, 2026

Abstract

Full Text|PDF|XML
This study suggests a hybrid model of prediction and anomaly detection of dynamic network based on graph density time series. The main issue that is being tackled is that traditional linear models cannot explain non-linear structural shocks and volatility clustering that are facts in cyber network data. The methodology proposed implies turning network flows of the UNSW-NB15 dataset into dynamic graph snapshots, deriving graph density as a scalar measure, and stabilizing the series by converting it to log-returns. The existence of the “fat tails” and non-Gaussian shocks which cannot be detected using traditional statistical tools was verified by the use of advanced diagnostic tests, like Kurtosis and Jarque-Bera test. As a result, a hybrid model that was a combination of the autoregressive moving average (ARMA) and exponential generalized autoregressive conditional heteroscedasticity (EGARCH) was applied. This research used the selection of the ARMA ($p$, $q$)-EGARCH ($u$, $v$) model as the best specification in terms of the Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC). The result of the hybrid model had an accuracy with running time spent in predictive and anomaly detection. Compared with two different methods, the methodology of ARMA ($p$, $q$)-EGARCH ($u$, $v$) has demonstrated the highest level of anomaly detection with a decrease in time processing in prediction and detection processes. This paper shows that structural graph analysis with modeling can be used to increase the resilience and sensitivity of intrusion detection systems.

Abstract

Full Text|PDF|XML

Zero-day attacks–exploiting unknown vulnerabilities before patches exist–pose a critical threat to modern network infrastructure that signature-based intrusion detection systems cannot address. This paper proposes a hybrid computational framework combining a Convolutional Neural Network (CNN)-Gated Recurrent Unit (GRU)-Attention classifier with a skip-connection convolutional autoencoder (AE) for simultaneous known-attack classification and zero-day anomaly detection. The framework introduces three key computational contributions: (1) deterministic reshaping of 64 Random Forest-selected network flow features into 8 $\times$ 8 spatial images, enabling end-to-end CNN processing without feature engineering; (2) a strict Score-based Label Separation and Ordering (SLSO) data partition enforcing complete information isolation between training, validation, and zero-day evaluation sets; and (3) an OR-fusion hybrid decision rule combining anomaly score and reconstruction error signals. Experimental evaluation on Canadian Institute for Cybersecurity Intrusion Detection System (CICIDS)2017 demonstrates 97.48% zero-day detection rate (Z-DR) (95% confidence interval (CI) [97.1%, 97.9%]) at 4.2% false positive rate (FPR) and Area Under the Receiver Operating Characteristic curve (AUROC) of 0.956 across three held-out zero-day attack families–substantially outperforming all classical baselines (best: Stochastic Gradient Descent-optimized One-Class Support Vector Machine (SGD-OCSVM) at 85.45%). SHapley Additive exPlanations (SHAP) explainability analysis reveals mechanistic complementarity: the CNN captures temporal flow signatures while the AE contributes 1,012 exclusive detections via backward inter-arrival time anomalies. The system operates at 14,201 samples/second on Graphics Processing Unit (GPU), satisfying real-time deployment requirements. These results demonstrate that hybrid supervised-unsupervised fusion with rigorous experimental methodology substantially advances zero-day detection capability for computational network security systems.

Abstract

Full Text|PDF|XML

Solid-particle erosion at pipeline elbows threatens the integrity of oil-and-gas transport systems. This numerical study used the Euler–Lagrange discrete phase model and the Finnie erosion model in ANSYS Fluent to compare a single 90° elbow, two 45° elbows, and three 30° elbows for water–sand flow at inlet velocities of 10–40 m/s and particle diameters of 0.0002–0.0005 m. Two output measures are reported: contour plots show the local cellwise maximum wall erosion rate, whereas line graphs show the area-weighted mean wall erosion rate. At the reference condition of 40 m/s and a particle diameter of 0.0005 m, the area-weighted mean rates were 5.18 $\times$ 10$^{-5}$, 2.89 $\times$ 10$^{-5}$, and 3.59 $\times$ 10$^{-5}$ kg m$^{-2}$ s$^{-1}$ for the single 90° elbow, two 45° elbows, and three 30° elbows, respectively. Relative to the single elbow under the same simulation conditions, the mean erosion rate decreased by 44.2% with two 45° elbows and by 30.7% with three 30° elbows. The corresponding local contour maxima were 3.17 $\times$ 10$^{-3}$, 2.82 $\times$ 10$^{-3}$, and 2.59 $\times$ 10$^{-3}$ kg m$^{-2}$ s$^{-1}$. These results show that distributing the change in flow direction across multiple elbows reduces severe particle–wall impacts, with two 45° elbows providing the lowest area-weighted mean erosion rate.

Abstract

Full Text|PDF|XML

This study presents detailed modelling and comparative analysis of pouch lithium-ion cells (PLCs) configured in combined single and dual battery packs for electric vehicles (EVs), appraising their performance with and without active cooling systems. Pouch cells were selected due to their high volumetric energy density (VED), lightweight design, and suitability for high-power EV applications. Using SolidWorks for computer aided design (CAD) modelling, Analysis System (ANSYS) Fluent software with the multi-scale multi-domain (MSMD) approach, and equivalent circuit model (ECM), simulation based thermal and electrochemical behaviour during 1-hour charging process at specified currents was achieved. Four configurations were examined: single-pack and dual-pack, each with and without liquid active cooling. Main parameters included state of charge (SoC), temperature distribution, and thermal gradients. Results confirmed that dual-pack configuration significantly outperformed single-pack, achieving over 69.3% higher SoC (55.07% against 32.53%) under the same conditions. Without active cooling, maximum temperatures reached 541.11 K (single) and 462.77 K (dual), indicating notable hotspots in the single pack. Active cooling dramatically reduced temperatures to 295 K across both setups, with the dual pack displaying superior uniformity and a 0.45% lower average temperature, adequately averting thermal gradients and enhancing safety. Mathematical validation of SoC dynamics confirmed the dual configuration’s theoretical advantage in charging efficiency, tempered by heat losses. Findings reveal that dual battery packs integrated with active cooling render optimal equilibrium of faster charging, improved thermal management, and extended battery life, addressing limitations associated with conventional single-pack designs.

Abstract

Full Text|PDF|XML

Flood early-warning systems increasingly use machine learning, but predictive studies rarely assess whether candidate models meet deployment constraints at warning locations. This study evaluated a six-layer, digital-twin-inspired edge artificial intelligence (AI) framework using five years of daily hydro-meteorological observations ($n$ = 1,826) from one river gauge in Indonesia. The framework integrated causal preprocessing, 93 engineered predictors, paired extreme gradient boosting (XGBoost) classification and regression models, a synchronised state-update surrogate for stage–inundation scenarios, and a rule-based alert engine. The alert engine used class-specific probability gates and dispatch de-duplication. Evaluation followed chronological partitions. Imputation statistics and risk thresholds were derived from training data, uncertainty was assessed using a moving-block bootstrap, and paired model comparisons used McNemar and Diebold–Mariano tests (DMs). On the held-out year, the deployed model achieved a macro F1-score of 0.788 (95% confidence interval: 0.721–0.830) and a next-day stage root mean squared error (RMSE) of 0.353 m. Nash–Sutcliffe efficiency was 0.872. Warning-state verification yielded a probability of detection (POD) of 0.945 and a false-alarm ratio (FAR) of 0.101 under the configured policy. XGBoost, random forest, and gradient boosting showed no statistically detectable performance differences in the reported tests, including an eightfold rolling-origin evaluation of 728 pooled test days. Sequence models trained on raw 30-day windows did not improve performance under the evaluated pipelines. However, the tree models used engineered predictors, so the comparison does not isolate architectural effects. The XGBoost classifier was approximately 41 times smaller and 175 times faster at the 99th percentile inference latency (P99) than the random forest. The complete deployed bundle occupied 134 kB and achieved a 99th-percentile latency of 1.39 ms on the benchmark host. These findings support deployment cost as a practical selection consideration when available tests cannot distinguish predictive performance. Generalisation requires multi-station replication, formal equivalence testing where equivalence is claimed, and hardware-in-the-loop validation.

- no more data -