Search Results (23,026)

Accurate load forecasting is crucial to the stable operation of integrated energy systems (IES), which plays a significant role in advancing sustainable development. Addressing the challenge of insufficient prediction accuracy caused by the inherent uncertainty and volatility of load data, this study proposes a multi-energy load forecasting method for IES using an improved VMD-TCN-BiLSTM model. The proposed model consists of optimizing the Variational Mode Decomposition (VMD) parameters through a mathematical model based on minimizing the average permutation entropy (PE). Moreover, load sequences are decomposed into different Intrinsic Mode Functions (IMFs) using VMD, with the optimal number of models determined by the average PE to reduce the non-stationarity of the original sequences. Considering the coupling relationship among electrical, thermal, and cooling loads, the input features of the forecasting model are constructed by combining the IMF set of multi-energy loads with meteorological data and related load information. As a result, a hybrid neural network structure, integrating a Temporal Convolutional Network (TCN) with a Bidirectional Long Short-Term Memory (BiLSTM) network for load prediction is developed. The Sand Cat Swarm Optimization (SCSO) algorithm is employed to obtain the optimal hyper-parameters of the TCN-BiLSTM model. A case analysis is performed using the Arizona State University Tempe campus dataset. The findings demonstrate that the proposed method can outperform six other existing models in terms of Mean Absolute Percentage Error (MAPE) and Coefficient of Determination (R²), verifying its effectiveness and superiority in load forecasting. Full article

With the continuous development of network security situations, the types of attacks increase sharply, but can be divided into symmetric attacks and asymmetric attacks. Symmetric attacks such as phishing and DDoS attacks exploit fixed patterns, resulting in system crashes and data breaches that cause losses to businesses. Asymmetric attacks such as Advanced Persistent Threat (APT), a highly sophisticated and organized form of cyber attack, because of its concealment and complexity, realize data theft through long-term latency and pose a greater threat to organization security. In addition, there are challenges in the processing of missing data, especially in the application of symmetric and asymmetric data filling, the former is simple but not flexible, and the latter is complex and more suitable for highly complex attack scenarios. Since asymmetric attack research is particularly important, this paper proposes a method that combines causal discovery with graph autoencoder to solve missing data, classify potentially malicious nodes, and reveal causal relationships. The core is to use graphic autoencoders to learn the underlying causal structure of APT attacks, with a special focus on the complex causal relationships in asymmetric attacks. This causal knowledge is then applied to enhance the robustness of the model by compensating for data gaps. In the final phase, it also reveals causality, predicts and classifies potential APT attack nodes, and provides a comprehensive framework that not only predicts potential threats, but also provides insight into the logical sequence of the attacker’s actions. Full article

Since the 1990s, Petri nets have been used in systems biology for quantitative modeling. Despite the increasing number of models developed during this period, doubts remain about their biological relevance. Although biological systems predominantly exhibit intracellular or cellular structures, the models rely largely on deterministic predictions, failing to capture the inherent randomness and uncertainties of such systems. The question arises whether these models accurately describe the dynamic behavior of biological systems. This paper introduces a methodology for selecting the appropriate modeling paradigms in systems biology. Initially, we construct a Petri net model and perform deterministic, stochastic, and fuzzy stochastic simulations. Then we perform various statistical tests to measure the discrepancies between the simulation results. Based on scale-density analysis, we determine the modeling approach that best approximates the biological system. Finally, we compare the results of the statistical tests and the scale-density analysis to identify the optimal modeling approach. We applied the proposed methodology to the synthesis of spinal motor neuron protein from the spinal motor neuron-2 gene. Analysis revealed significant discrepancies between the simulation results of different modeling paradigms. Due to the sparse nature of the underlying drug-disease network, we conclude that the fuzzy stochastic paradigm provides the most biologically relevant results. We predict drug combinations that could lead to an up to 149-fold increase in spinal motor neuron protein levels, indicating a promising treatment for the disease. This methodology has the potential for application to other gene-drug-disease networks and broader biological systems. Full article

An accurate understanding of the structure of spatial correlation networks of land use carbon emissions (LUCEs) and carbon balance zoning plays a guiding role in promoting regional emission reductions and achieving high-quality coordinated development. In this study, 42 counties in the Tarim River Basin from 2002 to 2022 were chosen as samples (Corps cities were excluded due to missing statistics). The LUCE spatial correlation network characteristics and carbon balance zoning were analyzed by using the Ecological Support Coefficient (ESC), Social Network Analysis (SNA), and Spatial Clustering Data Analysis (SCDA), and a targeted optimization strategy was proposed for each zone. The results of the study indicate the following: (1) The LUCEs showed an overall upward trend, but the increase in LUCEs gradually slowed down, presenting a spatial characteristic of “high in the mid-north and low at the edges”. In addition, the ESC showed an overall decreasing trend, with a spatial characteristic opposite to that of the LUCEs. (2) With an increasingly close spatial LUCE correlation network in the Tarim River Basin, the network structure presented better accessibility and stability, but the individual network characteristics differed significantly. Aksu City, Korla City, Bachu County, Shache County, Hotan City, and Kuqa City, which were at the center of the network, displayed a remarkable ability to control and master the network correlation. (3) Based on the carbon balance analysis, the counties were subdivided into six carbon balance functional zones and targeted synergistic emission reduction strategies were proposed for each zone to promote fair and efficient low-carbon transformational development among the regions. Full article

The probiotic bacterium Bifidobacterium animalis subsp. lactis BB-12 (BB-12) was encapsulated in two composites, alginate/agar and alginate/agar/casein. The network structure and physicochemical properties of these composites are influenced by complex interactions, including hydrogen bonding, electrostatic forces between biopolymers, calcium ions, and the encapsulated bacteria. The composites demonstrated a granular surface, with the granules being spatially oriented on the alginate/agar/BB-12 surface and linearly oriented on the alginate/agar/casein/BB-12 surface. They possess a highly organized microparticle structure and exhibit viscoelastic solid-like behavior. The alginate/agar/BB-12 composite showed higher storage modulus, shear stress, and shear strain values, indicating enhanced stability in various physical environments. Both composites displayed good thermal stability, aligning with their rheological properties, confirming their well-ordered structures. Despite differences in composite structures, the release mechanism of bacteria is governed by Fickian diffusion through the composite matrix. Based on physicochemical properties, the alginate/agar/casein composite is recommended for dairy product fermentation, while the alginate/agar composite seems more suitable for oral use. These findings provide new insights into the interactions between bacterial cultures and alginate composite ingredients. Full article

Surfactants are among the most versatile molecules in the chemical industry because they can self-assemble in bulk solutions and at interfaces. Predicting the properties of surfactant solutions, such as their critical micelle concentration (CMC), limiting surface tension (${\gamma }_{cmc}$), and maximal packing density (${\Gamma }_{max}$) at water–air interfaces, is essential to their rational design. However, the relationship between surfactant structure and these properties is complex and difficult to predict theoretically. Here, we develop a graph neural network (GNN)-based quantitative structure–property relationship (QSPR) model to predict the CMC, ${\gamma }_{cmc}$, and ${\Gamma }_{max}$. Ninety-two surfactant data points, encompassing all types of surfactants—anionic, cationic, zwitterionic, and nonionic—are fed into the model, covering a temperature range of [20–30 °C], which contributes to its generalization across all surfactant types. We show that our models have high accuracy (R² = 0.87 on average in tests) in predicting the three parameters across all types of surfactants. The effectiveness of the QSPR model in capturing the variation of CMC, ${\gamma }_{cmc}$, and ${\Gamma }_{max}$ with molecular design parameters are carefully assessed. The curated dataset, developed model, and critical assessment of the developed model will contribute to the development of improved surfactants QSPR models and facilitate their rational design for diverse applications. Full article

Aiming at the problems of insufficient navigation area recognition accuracy, fuzzy boundary of obstacle segmentation, and high consumption of computational resources in the autonomous navigation of water navigation sensors, such as USVs, this paper proposes a DMTN-Net network architecture based on DeeplabV3+ to improve the accuracy and efficiency of environment sensing. Firstly, DMTN-Net adopts the lightweight MobileNetV2 as the backbone, which reduces the amount of computation. Secondly, the innovative N-Decoder structure integrates cSE and Triplet Attention, which enhances the feature representation and improves the segmentation performance. Finally, various experiments were conducted on the MassMind dataset, Pascal VOC2007 dataset, and related sea areas. The experimental results show that DMTN-Net performs well on MassMind and Pascal VOC2007 datasets, and compared with other mainstream networks, the indexes of mIoU, mPA, and mPrecision are significantly improved, and the computational cost is greatly reduced. In addition, the offshore navigation experiments further validate its performance advantages and provide solid support for the practicalization of USV waterborne sensors. Full article

Vessel traffic flow forecasting in port waterways is critical to improving safety and efficiency of port navigation. Aiming at the stage characteristics of vessel traffic in port waterways in time sequence, which leads to complexity of data in the prediction process and difficulty in adjusting the model parameters, a convolutional neural network (CNN) based on the optimization of the pelican algorithm (POA) and the combination of bi-directional gated recurrent units (BiGRUs) is proposed as a prediction model, and the POA algorithm is used to search for optimized hyper-parameters, and then the iterative optimization of the optimal parameter combinations is input into the best combination of iteratively found parameters, which is input into the CNN-BiGRU model structure for training and prediction. The results indicate that the POA algorithm has better global search capability and faster convergence than other optimization algorithms in the experiment. Meanwhile, the BiGRU model is introduced and compared with the CNN-BiGRU model prediction; the POA-CNN-BiGRU combined model has higher prediction accuracy and stability; the prediction effect is significantly improved; and it can provide more accurate prediction information and cycle characteristics, which can serve as a reference for the planning of ships’ routes in and out of ports and optimizing the management of ships’ organizations. Full article

Depression in adolescents has been linked to poor life outcomes, including suicidal ideation, peer victimization, and fewer friendships. Less is known about how depressed adolescents perceive their peer interactions. Based on the depression-distortion model, we expected that adolescents with depressive symptoms misperceive their social ties by being less likely to like some peers, and more likely to dislike other peers. An Italian dataset about adolescent relationships was used, including 275 first-year secondary school students (M age = 11.80, 46% female) in 12 classrooms across nine schools. Adolescents were asked to nominate classmates they liked and disliked. Longitudinal social network analyses (stochastic actor-oriented models) were conducted, including structural network effects (reciprocity, transitivity, indegree-popularity) and covariates such as gender, immigrant origin, and highest parents’ education level. The results indicated that adolescents with depressive symptoms were less likely to send liking nominations, and conversely, they were more likely to send disliking nominations than non-depressed classmates. Interestingly, adolescents with depressive symptoms were not more disliked or less liked by their peers. These findings seem to support the depression-distortion model by suggesting that, compared to non-depressed peers, adolescents with depressive symptoms misperceive their relationships by overstating negative relationships and underestimating positive ones. Full article

This paper presents a deep learning algorithm for channel estimation in 5G New Radio (NR). The classical approach that uses neural networks for channel estimation requires more than one stage to obtain the full channel matrix. First, the channel has to be constructed by the received reference signal, and then, the precision is improved. In contrast, to reduce the computational cost, the proposed neural network method generates the channel matrix from the information captured from a few subcarriers along the slot. This information is extrapolated by applying the Least Square technique only on the Demodulation Reference Signal (DMRS). The received DMRS placed in the grid can be seen as a 2D low-resolution image and it is processed to generate the full channel matrix. To reduce complexity in the hardware implementation, the convolutional neural network (CNN) structure is selected. This solution is analyzed comparing the Mean Square Error (MSE) and the computational cost with other deep learning-based channel estimation, as well as the traditional channel estimation methods. It is demonstrated that the proposed neural network delivers substantial complexity savings and favorable error performance. It reduces the computational cost by an order of magnitude, and it has a maximum error discrepancy of 0.018 at 5 dB compared to Minimum Mean Square Error (MMSE) channel estimation. Full article

Hydrogels are hydrophilic 3-dimensional networks characterized by the retention of a large amount of water. Because of their water component, hydrogels are a promising method for targeted drug delivery. The water component, or “free volume”, is a potential vehicle for protein drugs. A particularly intriguing hydrogel is pectin. In addition to a generous free volume, pectin has structural characteristics that facilitate hydrogel binding to the glycocalyceal surface of visceral organs. To test drug function and pectin integrity after loading, we compared pectin films from four distinct plant sources: lemon, potato, soybean, and sugar beet. The pectin films were tested for their micromechanical properties and intrinsic antibacterial activity. Lemon pectin films demonstrated the greatest cohesion at 30% water content. Moreover, modest growth inhibition was observed with lemon pectin (p < 0.05). No effective inhibition was observed with soybean, potato, or sugar beet films (p > 0.05). In contrast, lemon pectin films embedded with carbenicillin, chloramphenicol, or kanamycin demonstrated significant bacterial growth inhibition (p < 0.05). The antibacterial activity was similar when the antibiotics were embedded in inert filter disks or pectin disks (p > 0.05). We conclude that lemon pectin films represent a promising structural platform for antibacterial drug delivery. Full article

As the economic environment becomes more complex, improving supply chain resilience is critical for the effective operation and long-term sustainability of businesses. Real-world supply chains, which consist of various components such as goods, warehouses, and plants, often feature intricate network structures that pose challenges for resilience analysis. This paper addresses these challenges by proposing a framework for studying supply chains using multi-layer network community detection. The complex multi-mode supply chain network is transformed into single-mode, multi-layer weighted networks. A multi-layer weighted community detection method is proposed for identifying local clusters within these networks, revealing interconnected groups that highlight flexibility and redundancy in production capabilities across different plants and goods. An empirical study utilizing real data demonstrates that this clustering method effectively detects indirect capacity links between plants and goods. The insights derived from this method are useful for strategic capacity management, allowing businesses to respond more effectively to supply shortages and unexpected increases in demand. Full article

One undescribed fatty glyceride (1), two unreported N-acetyldopamine dimers (2 and 3), and four known structurally diverse N-acetyldopamine dimers were isolated from adult Vespa velutina auraria Smith. Their structures were elucidated based on a comprehensive analysis of spectroscopic data, HRESIMS, and NMR calculations with ML_J_DP4, and the absolute configurations of 2 and 3 were determined via ECD calculations. Regarding their bioactivities, compounds 5 and 6 can inhibit the production of NO. Moreover, compounds 3, 5 and 7 showed stronger antioxidant activity than the positive control (VC) at 14 μg/mL. A network pharmacology study was used to explore the potential bioactive mechanisms. In addition, a docking study of anti-inflammatory and antioxidative compounds was also performed. Full article

This study investigates the molecular mechanisms underlying fruit cracking in Akebia trifoliata, a phenomenon that significantly impacts fruit quality and marketability. Through comprehensive physiological, biochemical, and transcriptomic analyses, we identified key changes in cell wall components and enzymatic activities during fruit ripening. Our results revealed that ventral suture tissues exhibit significantly elevated activities of polygalacturonase (PG) and β-galactosidase compared to dorsoventral line tissues, indicating their crucial roles in cell wall degradation and structural weakening. The cellulose content in VS tissues peaked early and declined during ripening, while DL tissues maintained relatively stable cellulose levels, highlighting the importance of cellulose dynamics in fruit cracking susceptibility. Transcriptomic analysis revealed differentially expressed genes (DEGs) associated with pectin biosynthesis and catabolism, cell wall organization, and oxidoreductase activities, indicating significant transcriptional regulation. Key genes like AKT032945 (pectinesterase) and AKT045678 (polygalacturonase) were identified as crucial for cell wall loosening and pericarp dehiscence. Additionally, expansin-related genes AKT017642, AKT017643, and AKT021517 were expressed during critical stages, promoting cell wall loosening. Genes involved in auxin-activated signaling and oxidoreductase activities, such as AKT022903 (auxin response factor) and AKT054321 (peroxidase), were also differentially expressed, suggesting roles in regulating cell wall rigidity. Moreover, weighted gene co-expression network analysis (WGCNA) identified key gene modules correlated with traits like pectin lyase activity and soluble pectin content, pinpointing potential targets for genetic manipulation. Our findings offer valuable insights into the molecular basis of fruit cracking in A. trifoliata, laying a foundation for breeding programs aimed at developing crack-resistant varieties to enhance fruit quality and commercial viability. Full article

Neuroimaging is revolutionizing our ability to investigate the brain’s structural and functional properties, enabling us to visualize brain activity during diverse mental processes and actions. One of the most widely used neuroimaging techniques is electroencephalography (EEG), which records electrical activity from the brain using electrodes positioned on the scalp. EEG signals capture both spatial (brain region) and temporal (time-based) data. While a high temporal resolution is achievable with EEG, spatial resolution is comparatively limited. Consequently, capturing both spatial and temporal information from EEG data to recognize mental activities remains challenging. In this paper, we represent spatial and temporal information obtained from EEG signals by transforming EEG data into sequential topographic brain maps. We then apply hybrid deep learning models to capture the spatiotemporal features of the EEG topographic images and classify imagined English words. The hybrid framework utilizes a sequential combination of three-dimensional convolutional neural networks (3DCNNs) and recurrent neural networks (RNNs). The experimental results reveal the effectiveness of the proposed approach, achieving an average accuracy of 77.8% in identifying imagined English speech. Full article