Search Results (815)

This study proposes a novel Deep Reinforcement Learning (DRL) policy network structure for portfolio management called PortRSMs. PortRSMs employs stacked State-Space Models (SSMs) for the modeling of multi-scale continuous regime shifts in financial time series, striking a balance between exploring consistent distribution properties over short periods and maintaining sensitivity to sudden shocks in price sequences. PortRSMs also performs cross-asset regime fusion through hypergraph attention mechanisms, providing a more comprehensive state space for describing changes in asset correlations and co-integration. Experiments conducted on two different trading frequencies in the stock markets of the United States and Hong Kong show the superiority of PortRSMs compared to other approaches in terms of profitability, risk–return balancing, robustness, and the ability to handle sudden market shocks. Specifically, PortRSMs achieves up to a 0.03 improvement in the annual Sharpe ratio in the U.S. market, and up to a 0.12 improvement for the Hong Kong market compared to baseline methods. Full article

Highway accessibility plays a vital role in supporting local economic development, particularly in regions lacking access to sea or river ports. Recognizing the functional transformation of road infrastructure, the Chinese government has made substantial investments in its expansion. Nevertheless, a theoretical gap remains in justifying whether such investments yield significant economic returns. Drawing on the theory of economic externalities, this study investigates the causal relationship between highway development and regional economic growth, and assesses whether highway construction leads to an acceleration in growth rates. Utilizing panel data from 14 Chinese cities spanning 2000 to 2014, the synthetic control method (SCM) is employed to evaluate the economic externalities of highway investment. The results indicate a positive impact on surrounding industries. Furthermore, a growth rate forecasting analysis based on Back-Propagation Neural Networks (BPNNs) is conducted using industrial enterprise data from 2005 to 2014. The growth rate in the treated city is 1.144%, which is close to the real number 1.117%, higher than the number for the weighted control group, which is 1.000%. The findings suggest that the growth rate of total industrial output improved significantly, confirming the existence of positive spillover effects. This not only enriches the empirical literature on transport infrastructure but also provides targeted enlightenment for the sustainable development of urban economy in terms of policy guidance. Full article

Reconfigurable intelligent surfaces (RISs), recognized as one of the most promising key technologies for sixth-generation (6G) mobile communications, are characterized by their minimal energy expenditure, cost-effectiveness, and straightforward implementation. In this study, we develop a novel communication channel model that integrates RIS-enabled base stations with unmanned ground vehicles. To enhance the system’s adaptability, we implement a fluid antenna system (FAS) at the unmanned ground vehicle (UGV) terminal. This innovative model demonstrates exceptional versatility across various wireless communication scenarios through the strategic adjustment of active ports. The inherent dynamic reconfigurability of the FAS provides superior flexibility and adaptability in air-to-ground communication environments. In the paper, we derive and study key performance characteristics like the autocorrelation function (ACF), validating the model’s effectiveness. The results demonstrate that the RIS-FAS collaborative scheme significantly enhances channel reliability while effectively addressing critical challenges in 6G networks, including signal blockage and spatial constraints in mobile terminals. Full article

The optimal design of electromagnetic interference (EMI) filters relies on accurate characterization of noise source impedance. The conventional insertion loss method involves integrating two distinct passive two-port networks between the linear impedance stabilization network (LISN) and the equipment under test (EUT). The utilization of the insertion loss to formulate a system of binary quadratic equations concerning the real and imaginary components of the impedance of the noise source enables the precise extraction of the magnitude and phase of the noise source impedance in theory. However, inherent inaccuracies in the insertion loss method during extraction can compromise impedance accuracy or even cause extraction failure. This work employs a series inductance method to overcome these limitations. Exact analytical expressions are derived for the magnitude and phase of the noise source impedance. Subsequently, the application scope of the series insertion loss method is analyzed, and the impact of insertion loss measurement error on noise source impedance extraction accuracy is quantified. Requirements for improving extraction accuracy are discussed, and method optimization strategies are proposed. The permissible range of insertion loss error ensuring a solution exists is deduced. Finally, simulation and experimental results validate the proposed approach in a buck converter. Full article

High-speed switching chips are key components of network core devices in the high-performance computing paradigm, and their scheduling algorithm performance directly influences the throughput, latency, and fairness within the system. However, traditional scheduling algorithms often encounter issues such as high implementation complexity and high communication overhead when dealing with bursty traffic. To addressing the issue of bottlenecks in high-speed switching chip scheduling, we propose a low-complexity and high-performance scheduling algorithm called m-RGA, where m represents a priority mechanism. First, by monitoring the historical service time and load level of the VOQs at the port, the priority of the VOQs is dynamically adjusted to enhance the efficient matching and fair allocation of port resources. Additionally, we prove that an algorithm achieving a 2× speedup under a constant traffic model can simultaneously guarantee throughput and latency, making this algorithm theoretically as excellent as any maximum matching algorithm. Through simulation, we demonstrate that m-RGA outperforms Highest Rank First (HRF) arbitration in terms of latency under non-uniform and bursty traffic patterns. Full article

With increasing network security threats, Internet-wide scanning has become a key technique for identifying network vulnerabilities. However, traditional scanning methods tend to ignore the impact of geographic factors on scanning efficiency. In this study, we experimentally find that the geographic location of the scanner has a significant impact on scanning efficiency. Based on this finding, we propose a large-scale network scanning method based on geographic location awareness. The method divides scanners into multiple scanner clusters based on their geographic locations and designs a similarity matrix based on the average scanning time to quantify the scanning efficiency between two geographic locations. To avoid wasting scanning resources, we implement a load-balancing mechanism between scanner clusters and between nodes within each cluster. Experimental validation in a real network environment shows that the proposed method can effectively improve the scanning efficiency while ensuring the coverage. Full article

Accurate ship berthing behavior prediction (BBP) is essential for enabling collision warnings and support decision-making. Existing methods based on Automatic Identification System (AIS) data perform well in the task of ship trajectory prediction over long time-series and large scales, but struggle with addressing the fine-grained and highly dynamic changes in berthing scenarios. Therefore, the accuracy of BBP remains a crucial challenge. In this paper, a novel BBP method based on Light Detection and Ranging (LiDAR) data is proposed. To test its feasibility, a comprehensive dataset is established by conducting on-site collection of berthing data at Dalian Port (China) using a shore-based LiDAR system. This dataset comprises equal-interval data from 77 berthing activities involving three large ships. In order to find a straightforward architecture to provide good performance on our dataset, a cascading network model combining convolutional neural network (CNN), a bi-directional gated recurrent unit (BiGRU) and bi-directional long short-term memory (BiLSTM) are developed to serve as the baseline. Experimental results demonstrate that the baseline outperformed other commonly used prediction models and their combinations in terms of prediction accuracy. In summary, our research findings help overcome the limitations of AIS data in berthing scenarios and provide a foundation for predicting complete berthing status, therefore offering practical insights for safer, more efficient, and automated management in smart port systems. Full article

The rising frequency of network intrusions has significantly impacted critical infrastructures, leading to an increased focus on the detection of malicious network traffic in recent years. However, traditional port-based and classical machine learning-based malicious network traffic detection methods suffer from a dependence on expert experience and limited generalizability. In this paper, we propose a malicious traffic detection method based on an efficient federated learning framework of Bidirectional Encoder Representations from Transformers (BERT), called MT-FBERT. It offers two major advantages over most existing approaches. First, MT-FBERT pretrains BERT using two pre-training tasks along with an overall pre-training loss on large-scale unlabeled network traffic, allowing the model to automatically learn generalized traffic representations, which do not require human experience to extract the behavior features or label the malicious samples. Second, MT-FBERT finetunes BERT for malicious network traffic detection through an efficient federated learning framework, which both protects the data privacy of critical infrastructures and reduces resource consumption by dynamically identifying and updating only the most significant neurons in the global model. Evaluation experiments on public datasets demonstrated that MT-FBERT outperforms state-of-the-art baselines in malicious network traffic detection. Full article

Advanced Persistent Threat (APT) attacks pose a serious challenge to traditional detection methods. These methods often suffer from high false-alarm rates and limited accuracy due to the multi-stage and covert nature of APT attacks. In this paper, we propose TSE-APT, a time-series ensemble model that addresses these two limitations. It combines multiple machine-learning models, such as Random Forest (RF), Multi-Layer Perceptron (MLP), and Bidirectional Long Short-Term Memory Network (BiLSTM) models, to dynamically capture correlations between multiple stages of the attack process based on time-series features. It discovers hidden features through the integration of multiple machine-learning models to significantly improve the accuracy and robustness of APT detection. First, we extract a collection of dynamic time-series features such as traffic mean, flow duration, and flag frequency. We fuse them with static contextual features, including the port service matrix and protocol type distribution, to effectively capture the multi-stage behaviors of APT attacks. Then, we utilize an ensemble-learning model with a dynamic weight-allocation mechanism using a self-attention network to adaptively adjust the sub-model contribution. The experiments showed that using time-series feature fusion significantly enhanced the detection performance. The RF, MLP, and BiLSTM models achieved 96.7% accuracy, considerably enhancing recall and the false positive rate. The adaptive mechanism optimizes the model’s performance and reduces false-alarm rates. This study provides an analytical method for APT attack detection, considering both temporal dynamics and context static characteristics, and provides new ideas for security protection in complex networks. Full article

With the large-scale integration of renewable energy sources, traditional distribution networks are gradually evolving into a new form of flexible interconnection distribution networks. To enhance the rapidity and accuracy of power flow control through flexible interconnection devices, there is an increasing demand for precise grid equivalent models. Existing grid equivalent models predominantly adopt single-port configurations for radial networks, while there is limited research on two-port network equivalent models tailored for flexible interconnection distribution networks. Focusing on the scenario of flexible interconnection distribution networks integrated with Rotary Power Flow Controllers (RPFCs), this paper proposes an equivalent modeling method of two-port networks based on the superposition theorem under small disturbance conditions. A flexible interconnection distribution network model incorporating RPFCs and its corresponding two-port equivalent model are developed. The parameters of the two-port equivalent model are derived through superposition theorem calculations, enabling the realization of power decoupling control functionality for RPFCs. The simulation results show that the deviations between the set value of active power and the actual value remains at about 3%, and the deviations between the set value of reactive power and the actual value is between 4% and 7%, thereby verifying the effectiveness of the constructed two-port model in power flow control and further supporting the accuracy of the proposed method. Full article

Maritime transportation is the backbone of global trade, with ports acting as pivotal nodes for the efficient and resilient movement of goods in international supply chains. However, most existing studies lack a systematic and integrated framework for assessing port connectivity. To address this gap, this study develops an integrated Bayesian Network (BN) modeling approach that, for the first time, simultaneously incorporates international connectivity, port competitiveness, and hinterland connectivity within a unified probabilistic framework. Drawing on empirical data from 26 major coastal countries in Asia, the model quantifies the multi-layered and interdependent determinants of port connectivity. The results demonstrate that port competitiveness and hinterland connectivity are the dominant drivers, while the impact of international shipping links is comparatively limited in the current Asian context. Sensitivity analysis further highlights the critical roles of rail transport development and trade facilitation in enhancing port connectivity. The proposed BN framework supports comprehensive scenario analysis under uncertainty and offers targeted, practical policy recommendations for port authorities and regional planners. By systematically capturing the interactions among maritime, port, and inland factors, this study advances both the theoretical understanding and practical management of port connectivity. Full article

Clos networks and their folded versions, fat trees, are widely adopted in interconnection network designs for data centers and supercomputers. There are two main types of Clos networks: strictly nonblocking Clos networks and rearrangeably nonblocking Clos networks. Strictly nonblocking Clos networks can connect an idle input to an idle output without interfering with existing connections. Rearrangeably nonblocking Clos networks can connect an idle input to an idle output with rearrangements of existing connections. Traditional strictly nonblocking Clos networks have two drawbacks. One drawback is the use of crossbars with different numbers of input and output ports, whereas the currently available switches are square crossbars with the same number of input and output ports. Another drawback is that every connection goes through a fixed number of stages, increasing the length of the communication path. A drawback of traditional fat trees is that the root stage uses differently sized crossbar switches than the other stages. To solve these problems, this paper proposes an Identical Strictly NonBlocking folded Clos (ISNBC) network that uses equally sized square crossbars for all switches. Correspondingly, this paper also proposes an Identical Rearrangeably NonBlocking folded Clos (IRNBC) network. Both ISNBC and IRNBC networks can have any number of stages, can use equally sized square crossbars with no unused switch ports, and can utilize shortcut connections to reduce communication path lengths. Moreover, both ISNBC and IRNBC networks have a lower switch crosspoint cost ratio relative to a single crossbar than their corresponding traditional Clos networks. Specifically, ISNBC networks use 46.43% to 87.71% crosspoints of traditional strictly nonblocking folded Clos networks, and IRNBC networks use 53.85% to 60.00% crosspoints of traditional rearrangeably nonblocking folded Clos networks. Full article

This paper presents a method to model and optimize the supply chain processes for floating offshore wind turbines using a network model based on Generalized Multi-Commodity Network Flows (GMCNF). The proposed method represents production bases, base ports, installation sites, component transfer areas, and transportation routes as nodes and arcs within the network. The installation process is modeled using three transport concepts: assembling components at the base port, direct assembly and installation at the installation site, and transferring components to the installation vessel at a nearby port. These processes are expressed as a linear network model, with the objective function set to minimize total transportation and assembly costs. The optimal transportation network is derived by solving the network problem while incorporating constraints such as supply, demand, and transportation capacity. Case studies demonstrate the method’s effectiveness in optimizing the supply chain and evaluating potential new production site locations for floating foundations, considering overall supply chain optimization. Full article

High-speed railway (HSR) is a key transport mode for achieving carbon reduction targets and promoting sustainable regional economic development due to its fast, efficient, and low-carbon nature. Accurate wind speed forecasting (WSF) is vital for HSR systems, as it provides future wind conditions that are critical for ensuring safe train operations. Numerous WSF schemes based on deep learning have been proposed. However, accurately forecasting strong wind events remains challenging due to the complex and dynamic nature of wind. In this study, we propose a novel hybrid network architecture, MHSETCN-LSTM, for forecasting strong wind. The MHSETCN-LSTM integrates temporal convolutional networks (TCNs) and long short-term memory networks (LSTMs) to capture both short-term fluctuations and long-term trends in wind behavior. The multi-head squeeze-and-excitation (MHSE) attention mechanism dynamically recalibrates the importance of different aspects of the input sequence, allowing the model to focus on critical time steps, particularly when abrupt wind events occur. In addition to wind speed, we introduce wind direction (WD) to characterize wind behavior due to its impact on the aerodynamic forces acting on trains. To maintain the periodicity of WD, we employ a triangular transform to predict the sine and cosine values of WD, improving the reliability of predictions. Massive experiments are conducted to evaluate the effectiveness of the proposed method based on real-world wind data collected from sensors along the Beijing–Baotou railway. Experimental results demonstrated that our model outperforms state-of-the-art solutions for WSF, achieving a mean-squared error (MSE) of 0.0393, a root-mean-squared error (RMSE) of 0.1982, and a coefficient of determination ($R^2$) of 99.59%. These experimental results validate the efficacy of our proposed model in enhancing the resilience and sustainability of railway infrastructure.Furthermore, the model can be utilized in other wind-sensitive sectors, such as highways, ports, and offshore wind operations. This will further promote the achievement of Sustainable Development Goal 9. Full article

This article reports on the interrogation of fiber Bragg grating (FBG)-based sensors that are multiplexed in an asymmetric tree topology. At each stage in the topology, FBGs are connected at one output port of a 50:50 coupler with fibers of different lengths. This asymmetric structure allows the simultaneous interrogation of long-distance and parallel sensor networks to be realized. Time- and wavelength-division multiplexing techniques are used to multiplex the FBGs. Using the heterodyne detection technique, high-sensitivity detection of reflection signals that have been weakened by losses induced by a round-trip transmission through the couplers and long-distance propagation is performed. Quasi-distributed FBGs are interrogated simultaneously, over distances ranging from 15 m to 80 km. Full article