Search Results (2,832)

Financial time-series prediction remains a significant challenge, driven by market volatility, nonlinear dynamic characteristics, and the complex interplay between quantitative indicators and investor sentiment. Traditional time-series models (e.g., ARIMA and GARCH) struggle to capture the nuanced sentiment in textual data, while static deep learning integration methods fail to adapt to market regime transitions (bull markets, bear markets, and consolidation). This study proposes a hybrid framework that integrates investor forum sentiment analysis with adaptive deep reinforcement learning (DRL) for dynamic model integration. By constructing a domain-specific financial sentiment dictionary (containing 16,673 entries) based on the sentiment analysis approach and word-embedding technique, we achieved up to 97.35% accuracy in forum title classification tasks. Historical price data and investor forum sentiment information were then fed into a Support Vector Regressor (SVR) and three Transformer variants (single-layer, multi-layer, and bidirectional variants) for predictions, with a Deep Q-Network (DQN) agent dynamically fusing the prediction results. Comprehensive experiments were conducted on diverse financial datasets, including China Unicom, the CSI 100 index, corn, and Amazon (AMZN). The experimental results demonstrate that our proposed approach, combining textual sentiment with adaptive DRL integration, significantly enhances prediction robustness in volatile markets, achieving the lowest RMSEs across diverse assets. It overcomes the limitations of static methods and multi-market generalization, outperforming both benchmark and state-of-the-art models. Full article

The increasing use of UAVs has reshaped urban logistics, enabling sustainable alternatives to traditional deliveries. To address critical issues inherent in the system, the proposed study presents the design and evaluation of an innovative unmanned aerial vehicle (UAV) prototype that integrates advanced electronic components and artificial intelligence (AI), with the aim of reducing environmental impact and enabling autonomous navigation in complex urban environments. The UAV platform incorporates brushless DC motors, high-density LiPo batteries and perovskite solar cells to improve energy efficiency and increase flight range. The Deep Q-Network (DQN) allocates energy and selects reference points in the presence of wind and payload disturbances, while an integrated sensor system monitors motor vibration/temperature and charge status to prevent failures. In urban canyon and field scenarios (wind from 0 to 8 m/s; payload from 0.35 to 0.55 kg), the system reduces energy consumption by up to 18%, increases area coverage by 12% for the same charge, and maintains structural safety factors > 1.5 under gust loading. The approach combines sustainable materials, efficient propulsion, and real-time AI-based navigation for energy-conscious flight planning. A hybrid methodology, combining experimental design principles with finite-element-based structural modelling and AI-enhanced monitoring, has been applied to ensure structural health awareness. The study implements proven edge-AI sensor fusion architectures, balancing portability and telemonitoring with an integrated low-power design. The results confirm a reduction in energy consumption and CO₂ emissions compared to traditional delivery vehicles, confirming that the proposed system represents a scalable and intelligent solution for last-mile delivery, contributing to climate resilience and urban sustainability. The findings position the proposed UAV as a scalable reference model for integrating AI-driven navigation and renewable energy systems in sustainable logistics. Full article

In this article, we present a novel reinforcement learning-based framework in the discrete cosine transform to achieve better image steganography. First, the input image is divided into several blocks to extract semantic and structural features, evaluating their suitability for data embedding. Second, the Proximal Policy Optimization algorithm (PPO) is introduced in the block selection process to learn adaptive embedding policies, which effectively balances image fidelity and steganographic security. Moreover, the Deep Q-network (DQN) is used for adaptively adjusting the weights of the peak signal-to-noise ratio, structural similarity index, and detection accuracy in the reward formulation. Experimental results on the BOSSBase dataset confirm the superiority of our framework, achieving both lower detection rates and higher visual quality across a range of embedding payloads, particularly under low-bpp conditions. Full article

Early and accurate diagnosis of dementia is essential to improving patient outcomes and reducing societal burden. The Mini-Mental State Examination (MMSE) is widely used to assess cognitive function, yet traditional statistical and machine learning approaches often face limitations in capturing nonlinear interactions and subtle decline patterns. This study developed a novel deep learning-based dementia prediction model using MMSE data collected from domestic clinical settings and compared its performance with traditional machine learning models. A notable strength of this work lies in its use of item-level MMSE features combined with explainable AI (SHAP analysis), enabling both high predictive accuracy and clinical interpretability—an advancement over prior approaches that primarily relied on total scores or linear modeling. Data from 164 participants, classified into cognitively normal, mild cognitive impairment (MCI), and dementia groups, were analyzed. Individual MMSE items and total scores were used as input features, and the dataset was divided into training and validation sets (8:2 split). A fully connected neural network with regularization techniques was constructed and evaluated alongside Random Forest and support vector machine (SVM) classifiers. Model performance was assessed using accuracy, F1-score, confusion matrices, and receiver operating characteristic (ROC) curves. The deep learning model achieved the highest performance (accuracy 0.90, F1-score 0.90), surpassing Random Forest (0.86) and SVM (0.82). SHAP analysis identified Q11 (immediate memory), Q12 (calculation), and Q17 (drawing shapes) as the most influential variables, aligning with clinical diagnostic practices. These findings suggest that deep learning not only enhances predictive accuracy but also offers interpretable insights aligned with clinical reasoning, underscoring its potential utility as a reliable tool for early dementia diagnosis. However, the study is limited by the use of data from a single clinical site with a relatively small sample size, which may restrict generalizability. Future research should validate the model using larger, multi-institutional, and multimodal datasets to strengthen clinical applicability and robustness. Full article

The cereal cyst nematode, Heterodera avena, is responsible for substantial economic losses in the global production of wheat, barley, and other cereal crops. Extracellular enzymes, particularly those from the glycoside hydrolase 18 (GH18) family, such as chitinases secreted by Trichoderma spp., play a crucial role in nematode control. However, the genome-wide analysis of Trichoderma longibrachiatum T6 (T6) GH18 family genes in controlling of H. avenae remains unexplored. Through phylogenetic analysis and bioinformatics tools, we identified and conducted a detailed analysis of 18 GH18 genes distributed across 13 chromosomes. The analysis encompassed gene structure, evolutionary development, protein characteristics, and gene expression profiles following T6 parasitism on H. avenae, as determined by RT-qPCR. Our results indicate that 18 GH18 members in T6 were clustered into three major groups (A, B, and C), which comprise seven subgroups. Each subgroup exhibits highly conserved catalytic domains, motifs, and gene structures, while the cis-acting elements demonstrate extensive responsiveness to hormones, stress-related signals, and light. These members are significantly enriched in the chitin catabolic process, extracellular region, and chitinase activity (GO functional enrichment), and they are involved in amino sugar and nucleotide sugar metabolism (KEGG pathway enrichment). Additionally, 13 members formed an interaction network, enhancing chitin degradation efficiency through synergistic effects. Interestingly, 18 members of the GH18 family genes were expressed after T6 parasitism on H. avenae cysts. Notably, GH18-3 (Group B) and GH18-16 (Group A) were significantly upregulated, with average increases of 3.21-fold and 3.10-fold, respectively, from 12 to 96 h after parasitism while compared to the control group. Meanwhile, we found that the GH18-3 and GH18-16 proteins exhibit the highest homology with key enzymes responsible for antifungal activity in T. harzianum, demonstrating dual biocontrol potential in both antifungal activity and nematode control. Overall, these results indicate that the GH18 family has undergone functional diversification during evolution, with each member assuming specific biological roles in T6 effect on nematodes. This study provides a theoretical foundation for identifying novel nematicidal genes from T6 and cultivating highly efficient biocontrol strains through transgenic engineering, which holds significant practical implications for advancing the biocontrol of plant-parasitic nematodes (PPNs). Full article

This paper presents an innovative end-to-end framework for conformal antenna array design and beam steering in Low Earth Orbit (LEO) satellite-based IoT communication systems. We propose a multi-stage learning architecture that integrates machine learning (ML) for antenna parameter prediction with reinforcement learning (RL) for adaptive beam steering. The ML module predicts optimal geometric and material parameters for conformal antenna arrays based on mission-specific performance requirements such as frequency, gain, coverage angle, and satellite constraints with an accuracy of 99%. These predictions are then passed to a Deep Q-Network (DQN)-based offline RL model, which learns beamforming strategies to maximize gain toward dynamic ground terminals, without requiring real-time interaction. To enable this, a synthetic dataset grounded in statistical principles and a static dataset is generated using CST Studio Suite and COMSOL Multiphysics simulations, capturing the electromagnetic behavior of various conformal geometries. The results from both the machine learning and reinforcement learning models show that the predicted antenna designs and beam steering angles closely align with simulation benchmarks. Our approach demonstrates the potential of combining data-driven ensemble models with offline reinforcement learning for scalable, efficient, and autonomous antenna synthesis in resource-constrained space environments. Full article

This study investigated the mechanism of hydroxysafflor yellow A (HSYA) on senescent human umbilical cord mesenchymal stem cells (hUC-MSCs) through transcriptome sequencing. HSYA treatment identified 2377 differentially expressed genes (DEGs). Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses revealed that these DEGs were primarily enriched in cell adhesion regulation and the extracellular matrix (ECM)–receptor interaction pathway. Gene Set Enrichment Analysis (GSEA) and protein–protein interaction (PPI) network analysis corroborated the central role of ECM–receptor interaction signaling, and Key Driver Analysis (KDA) revealed 10 core regulatory genes (e.g., ID1, SMAD3, TGFB3). SA-β-gal staining showed that HSYA significantly reduced senescence-associated β-galactosidase activity. Flow cytometry showed no significant changes in cell cycle distribution. Western blot analysis indicated that HSYA treatment reduced the protein expression level of p16 without significantly altering p53 levels. Furthermore, HSYA significantly attenuated intracellular reactive oxygen species (ROS) accumulation. qPCR validation demonstrated that HSYA significantly upregulated ID1, GDF5, SMAD3, and TGFB3 while downregulating BMP4, TGFB2, and CCN2. These findings indicate that HSYA modulates genes associated with the ECM–receptor interaction pathway, potentially contributing to improved ECM homeostasis in senescent hUC-MSCs. Full article

The Cognitive Satellite–Terrestrial Network (CSTN) is an important infrastructure for the future development of 6G communication networks. This paper focuses on a potential communication scenario, where satellite users (SUs) dominate and are selected as the primary users, and terrestrial base station users (TUs) are the secondary users. Additionally, each terrestrial base station owns multiple antennae, and the interference of TUs to SUs in the CSTN is limited to a low level or below. In this paper, based on the observation of diversity and the time-varying characteristics of a variety of user requirements, a multi-agent deep Q-network algorithm under interference limitation (MADQN-IL) was proposed, where the power of each antenna in the base station is allocated to maximize the total system throughput while meeting the interference constraints in the CSTN. In our proposed MADQN-IL, the base stations play the role of intelligent agents, and each agent selects the antenna power allocation and cooperates with other agents through sharing system states and the total rewards. Through a simulation comparison, it was discovered that the MADQN-IL algorithm can achieve a higher system throughput than the adaptive resource adjustment (ARA) algorithm and the fixed power allocation methods. Full article

China’s dual carbon goals necessitate green transformation across industries, with STAR Market enterprises serving as crucial drivers of technological innovation. Existing studies predominantly focus on traditional sectors, overlooking dynamic policy interactions and structural heterogeneity in these technology-intensive firms. This study examines how coordinated environmental tax reforms, green finance initiatives, and equity network synergies collectively shape enterprise green transition, using multi-period difference-in-differences and triple-difference models across 2019 Q3–2023 Q4. By integrating financial records, patent filings, and carbon emission data from 487 STAR Market firms, the analysis identifies environmental cost pressures as the dominant policy driver, complemented by delayed financing incentives and accelerated resource integration through corporate networks. Regional institutional environments further modulate these effects, with areas implementing stricter tax reforms exhibiting stronger outcomes. The findings advocate for adaptive policy designs that align fiscal instruments with regional innovation capacities, optimize financial tools for technology commercialization cycles, and leverage inter-firm networks to amplify sustainability efforts. These insights contribute to refining China’s climate governance framework for emerging technology sectors. Full article

Sensor-rich Automated Guided Vehicles (AGVs) are increasingly deployed in logistics, yet large fleets relying on fixed tracks face high maintenance costs and frequent route conflicts. This study targets rail-based material handling and proposes an end-to-end multi-AGV navigation pipeline under realistic operational constraints. A conflict-aware global planner, extended from the A* algorithm, generates feasible routes, while a multi-sensor perception stack integrates LiDAR and camera data to distinguish moving AGVs, static obstacles, and task targets. Based on this perception, a Deep Q-Network (DQN) policy with a tailored reward function enables real-time dynamic obstacle avoidance in complex traffic. Simulation results demonstrate that, compared with the Artificial Potential Field (APF) baseline, the proposed GG-DRL approach reduces collisions by ~70%, lowers planning time by 25–30%, shortens paths by 10–15%, and improves smoothness by 20–25%. On the Maze Benchmark Map, GG-DRL surpasses classical planners (e.g., RRT) and deep RL baselines (e.g., DDPG) in path quality, computation, and avoidance behavior, achieving an average path length of 81.12, computation time of 11.94 s, 5.2 avoidance maneuvers, and smoothness of 0.86. Robustness is maintained as a dynamic obstacles scale up to 30. These findings confirm that combining multi-sensor fusion with deep reinforcement learning enhances AGV safety, efficiency, and reliability, with broad potential for intelligent railway logistics. Full article

Aiming at the problems of traditional calibrated visual servo systems relying on precise model calibration and the high training cost and low efficiency of online reinforcement learning, this paper proposes a Multi-Network Mean Delayed Deep Deterministic Policy Gradient Algorithm with Behavior Cloning (MN-MD3+BC) for uncalibrated visual adaptive control of robotic arms. The algorithm improves upon the Twin Delayed Deep Deterministic Policy Gradient (TD3) network framework by adopting an architecture with one actor network and three critic networks, along with corresponding target networks. By constructing a multi-critic network integration mechanism, the mean output of the networks is used as the final Q-value estimate, effectively reducing the estimation bias of a single critic network. Meanwhile, a behavior cloning regularization term is introduced to address the common distribution shift problem in offline reinforcement learning. Furthermore, to obtain a high-quality dataset, an innovative data recombination-driven dataset creation method is proposed, which reduces training costs and avoids the risks of real-world exploration. The trained policy network is embedded into the actual system as an adaptive controller, driving the robotic arm to gradually approach the target position through closed-loop control. The algorithm is applied to uncalibrated multi-degree-of-freedom robotic arm visual servo tasks, providing an adaptive and low-dependency solution for dynamic and complex scenarios. MATLAB simulations and experiments on the WPR1 platform demonstrate that, compared to traditional Jacobian matrix-based model-free methods, the proposed approach exhibits advantages in tracking accuracy, error convergence speed, and system stability. Full article

Efficient and scalable quantum key scheduling remains a critical challenge in trusted-relay Quantum Key Distribution (QKD) networks due to imbalanced key resource utilization, dynamic key consumption, and topology-induced congestion. This paper presents a Q-learning-based adaptive routing framework designed to optimize quantum key delivery in dynamic QKD networks. The model formulates routing as a Markov Decision Process, with a compact state representation that combines the current node, destination node, and discretized key occupancy levels. The reward function is designed to jointly penalize resource imbalance and rapid key depletion while promoting traversal through links with sustainable key generation, guiding the agent toward balanced and congestion-aware decisions. Simulation results demonstrate that the Q-learning scheduler outperforms non-adaptive baseline algorithms, achieving an average distribution time of approximately 100 s compared with 170–590 s for the baseline algorithms, a throughput of 61 keys/s compared with 32–55 keys/s, and a failure ratio limited to 0–0.1, demonstrating superior scalability, congestion resilience, and resource-efficient decision-making in dynamic QKD networks. Full article

The role of mesenchymal-to-endothelial transition in the angiogenic response remains controversial. In this study, we investigated whether human fetal lung fibroblasts (MRC-5 cells) exhibit morphological plasticity in a biomimetic extracellular matrix environment. To this end, MRC-5 cells were first cultured on and within Matrigel hydrogel and then studied with tube formation assays, confocal/fluorescence microscopy, invasion assays, and transcriptomic profiling. In addition, quantitative assessment for cord formation and gene expression was conducted via qPCR and RNA sequencing. In this study, MRC-5 cells quickly self-organized into cord-like networks, resembling early stages of vascular patterning, and at higher densities, invaded the hydrogel and formed spheroid-like aggregates. Transcriptomic analysis revealed upregulation of genes related to nervous system development and synaptic signaling in Matrigel-grown MRC-5 cultures. Collectively, these findings suggest that MRC-5 fibroblasts display structural and transcriptional plasticity in 3D Matrigel cultures, forming vascular-like cords that are more likely to resemble early developmental morphologies or neuroectodermal-like transcriptional signatures than definitive endothelial structures. This work underscores the potential of fibroblasts as an alternative cell source for vascular tissue engineering and highlights a strategy to overcome current limitations in autologous endothelial cell availability for regenerative applications. Full article

Under the background of energy transition, the Integrated Energy System (IES) of the park has become a key carrier for enhancing the consumption capacity of renewable energy due to its multi-energy complementary characteristics. However, the high proportion of wind and solar resource access and the fluctuation of diverse loads have led to the system facing dual uncertainty challenges, and traditional optimization methods are difficult to adapt to the dynamic and complex dispatching requirements. To this end, this paper proposes a new dynamic energy management method based on Deep Reinforcement Learning (DRL) and constructs an IES hybrid integer nonlinear programming model including wind power, photovoltaic, combined heat and power generation, and storage of electric heat energy, with the goal of minimizing the operating cost of the system. By expressing the dispatching process as a Markov decision process, a state space covering wind and solar output, multiple loads and energy storage states is defined, a continuous action space for unit output and energy storage control is constructed, and a reward function integrating economic cost and the penalty for renewable energy consumption is designed. The Deep Deterministic Policy Gradient (DDPG) and Deep Q-Network (DQN) algorithms were adopted to achieve policy optimization. This study is based on simulation rather than experimental validation, which aligns with the exploratory scope of this research. The simulation results show that the DDPG algorithm achieves an average weekly operating cost of 532,424 yuan in the continuous action space scheduling, which is 8.6% lower than that of the DQN algorithm, and the standard deviation of the cost is reduced by 19.5%, indicating better robustness. Under the fluctuation of 10% to 30% on the source-load side, the DQN algorithm still maintains a cost fluctuation of less than 4.5%, highlighting the strong adaptability of DRL to uncertain environments. Therefore, this method has significant theoretical and practical value for promoting the intelligent transformation of the energy system. Full article

The MADS-box gene family is a large family of transcription factors, and its members are widely distributed in the plant kingdom. Members of this family are well known to be crucial regulators of many biological processes and environmental responses. In this study, bioinformatics methods were employed to analyze the MADS-box gene family members in the common oat, focusing on their phylogenetic relationships, gene structures, conserved motifs, evolutionary relationships, promoter analysis and responses to photoperiod and abiotic stress. A total of 175 MADS-box genes were detected in Avena sativa, which were categorized into Type I and Type II. Type II members exhibited more complex gene structures, while each subfamily showed similar gene structures and motifs. Evolutionary analysis identified 138 segmental duplication events and revealed strong syntenic conservation with Triticum aestivum (337 collinear gene pairs). Four categories of cis-elements were detected in the promoter regions of the AsMADS-box genes. qRT-PCR analysis revealed that the expression of six Type II AsMADS-box genes varied in response to ABA, GA, drought and salt. Furthermore, 23 AsMADS-box members were potentially associated with heading date when the common oat plants were exposed to different photoperiod conditions. The overexpression of chr4D_AsMADS95 in Arabidopsis thaliana led to early flowering under long-day and short-day photoperiod conditions, likely associated with a significant increase in the expression levels of flowering-related genes in transgenic plants. These findings will provide useful information for future studies on stress responses and increase our understanding of the network that regulates flowering in the common oat. Full article