Saudi Electronic University

Deep learning (DL) has significantly advanced automated epilepsy seizure detection and prediction, enabling improved feature learning and temporal modeling from EEG signals. However, progress remains constrained by heterogeneous datasets, inconsistent evaluation protocols, and limited cross-study comparability, often leading to optimistic performance estimates that do not translate to real-world settings. This review provides a protocol-aware synthesis of 129 studies across major public and clinical EEG datasets, systematically examining how dataset characteristics, temporal definitions, and preprocessing strategies influence model performance and generalization. We introduce a unified evaluation framework that standardizes task definitions, validation protocols (Intra-P, Inter-P/LOPO, cross-dataset), and clinically relevant time-aware metrics, including prediction horizon, seizure occurrence period (SOP), false positives per hour (FP/h), and time in warning (TIW). A taxonomy of DL architectures spanning CNNs, RNNs, hybrid CNN RNN models, transfer learning approaches, and graph-based networks is analyzed through protocol-aware comparisons. Cross-study synthesis reveals that spectrogram-based CNNs are highly effective for seizure detection, while hybrid CNN RNN and LSTM/GRU models better capture long-range temporal dependencies required for prediction. Transfer learning improves performance in data-scarce settings, whereas connectivity-aware and graph-based models enhance interpretability by modeling inter-channel relationships. Despite these advances, consistent limitations emerge, including weak cross-dataset generalization, sensitivity to noise and annotation variability, imbalance in datasets, inconsistent temporal framing, and limited interpretability. Furthermore, ethical and deployment challenges such as privacy, bias, regulatory compliance, and computational constraints remain critical barriers to clinical adoption. This review highlights key research directions, including multimodal and context-aware modeling, personalized and continual learning, privacy-preserving frameworks, and lightweight architectures for real-time wearable systems. By aligning datasets, architectures, evaluation protocols, and clinical requirements, this work provides a structured roadmap toward robust, interpretable, and clinically deployable DL-based seizure monitoring systems.

This study investigates the complex dynamics and codimension-two bifurcations in a delayed mutually coupled optoelectronic system. The objective is to analyze the effects of feedback delay and coupling strength on the system dynamics and to provide insights that enhance the reliability and performance of optoelectronic and photonic technologies used in optical communication and signal processing. DDE-BIFTOOL is employed to construct bifurcation diagrams with respect to the feedback delay parameter (τ) and coupling strength parameter (β), enabling the identification of double-Hopf bifurcation points. The method of multiple scales (MMS) is then applied to derive complex amplitude equations near the bifurcation points. Furthermore, the method of normal form is used to classify and unfold the bifurcation behavior and determine the stability characteristics of the resulting solutions. The analysis reveals the existence of several double-Hopf bifurcation points and demonstrates a variety of complex dynamical behaviors. Stable equilibrium states, stable periodic oscillations, and bistability of periodic solutions are identified in specific parameter regions. Additionally, more intricate dynamics, including stable almost-periodic solutions and phase-locked solutions, are observed. The system is shown to transition to chaos through different routes depending on the varying parameter: chaos emerges through a period-5 window when β varies, whereas a period-doubling bifurcation route to chaos is observed when τ varies. This work provides a comprehensive bifurcation analysis of a delayed, mutually coupled optoelectronic system, with an emphasis on codimension-two dynamics and the unfolding of a double-Hopf bifurcation. The results contribute to a deeper understanding of nonlinear behaviors in optoelectronic systems and offer valuable theoretical guidance for the design and optimization of advanced photonic devices and communication systems.

This study examines how policy-related indicators are associated with circular economy performance in Australia over 2007–2021. Circular economy performance is measured across four dimensions: material productivity and consumption; waste generation and treatment; wastewater treatment; and recycling. The analysis is based on newly constructed composite indices of OECD data and an asymmetric NARDL model to explore whether positive and negative shifts in environment-related taxation and trust in government are correlated with the outcomes of the circular economy in both the short and long run. The results indicate significant long-run relationships between environment-related taxation, trust in government, science and technology conditions, and circular economy indicators. In particular, the findings show asymmetric tax effects, a generally positive association of institutional trust and science and technology with several circular-economy outcomes, and a negative association between environmental pressure and material, waste, and wastewater performance. The research adds a multidimensional measurement model to the evaluation of the circular economy in Australia and emphasizes that the estimated relations should be viewed as dynamic in the long run, rather than as absolute causal influences.

This work presents an Adaptive Multimodal Engagement Framework (AMEF) for metaverse ecosystems supported by 6G-enabled IoT. AMEF comprises four coordinated modules: a Multimodal Data Fusion Engine (MDFE) with hierarchical attention for context-aware weighting of heterogeneous sensor streams; a Predictive Engagement Module (PEM) that applies a contextual predictive algorithm to combine temporal embeddings with user-specific factors for real-time engagement forecasting; a 6G-Optimized Communication Layer (6G-OCL) implementing a dynamic bandwidth allocation protocol to reduce latency under variable load; and a Behavioral Adaptation Engine (BAE) that translates predicted states into environment modifications. A hybrid simulation evaluated AMEF across nine scenarios (varying bandwidth, user/device density, packet loss, and interaction rates) for 600 minutes. AMEF achieved 95.4

The Bay of Bengal Initiative for Multi-Sectoral Technical and Economic Cooperation (BIMSTEC) economies have yet to meaningfully contribute to accomplishing Sustainable Development Goals (SDG 7) affordable and clean energy, (SDG 8) decent work and economic growth, and (SDG 13) climate action. Dealing with this issue might require a shift or alteration of policy framework that is the major theme of this study. Consequently, this present research inspects the influence of economic growth, transportation, tourism sector development, and renewable energy on ecological footprint using panel time series from 1990 and 2019 for the BIMSTEC region. To evaluate this dynamic nexus between the mentioned environmental pollution drivers of ecological footprint, this study employed the augumented mean group (AMG) and common correlated effect mean group (CCEMG) regression estimators after detection of cross-sectional dependency. The empirical outcomes denote that economic growth and transportation sector of BIMSTEC countries increase the levels of ecological footprint. Conversely, tourism sector development, globalization, and renewable energy protect the ecological excellence in the region. Moreover, it is observed that a unidirectional causality exists from economic growth to ecological footprint, ecological footprint to transportation, tourism to ecological footprint, and globalization to ecological footprint, while bidirectional causality exists between renewable energy and ecological footprint. By observing the positive function of tourism, green energy, and globalization on sustainable environment progress, central authorities are capable to redesign policies concerning supportable efficient technologies and regulate globalization towards green programs and agenda to reduce global warming.