Dependency Relations Research Articles

Vessel Type Recognition Using a Multi-Graph Fusion Method Integrating Vessel Trajectory Sequence and Dependency Relations

In the field of research into vessel type recognition utilizing trajectory data, researchers have primarily concentrated on developing models based on trajectory sequences to extract the relevant information. However, this approach often overlooks the crucial significance of the spatial dependency relationships among trajectory points, posing challenges for comprehensively capturing the intricate features of vessel travel patterns. To address this limitation, our study introduces a novel multi-graph fusion representation method that integrates both trajectory sequences and dependency relationships to optimize the task of vessel type recognition. The proposed method initially extracts the spatiotemporal features and behavioral semantic features from vessel trajectories. By utilizing these behavioral semantic features, the key nodes within the trajectory that exhibit dependencies are identified. Subsequently, graph structures are constructed to represent the intricate dependencies between these nodes and the sequences of trajectory points. These graph structures are then processed through graph convolutional networks (GCNs), which integrate various sources of information within the graphs to obtain behavioral representations of vessel trajectories. Finally, these representations are applied to the task of vessel type recognition for experimental validation. The experimental results indicate that this method significantly enhances vessel type recognition performance when compared to other baseline methods. Additionally, ablation experiments have been conducted to validate the effectiveness of each component of the method. This innovative approach not only delves deeply into the behavioral representations of vessel trajectories but also contributes to advancements in intelligent water traffic control.

Machine learning aided prediction of martensite transformation temperature of NiTi-based shape memory alloy

The martensitic transformation temperature (Ms) of shape memory alloys plays a crucial role in their performance. To achieve rapid prediction of Ms in shape memory alloys, this study employs machine learning techniques, using NiTi-based SMAs, the most widely used type, as an example. The results show that the gradient boosting machine algorithm provides the best prediction accuracy, with an R² of 0.92 and a mean absolute error (MAE) of 23.42 °C on the test set. Through correlation analysis, recursive feature elimination, and exhaustive search methods, six key features were identified. Subsequently, SHapley Additive exPlanations (SHAP) values were introduced to analyze the model interpretability, revealing the feature importance ranking and the dependence relationship between features and SHAP values. To address the issue of low Ms in NiTi-based shape memory alloys, the concept of high-entropy alloys was introduced. The study designed a TiZrHfNiCu high-entropy shape memory alloy and efficiently screened alloy compositions using the predictive model. This approach successfully increased the Ms, with the Ti19Zr19Hf19Ni37Cu6 alloy exhibiting an Ms exceeding 400 °C, significantly enhancing high-temperature application performance.

An Intelligent Maneuver Decision-Making Approach for Air Combat Based on Deep Reinforcement Learning and Transformer Networks

The traditional maneuver decision-making approaches are highly dependent on accurate and complete situation information, and their decision-making quality becomes poor when opponent information is occasionally missing in complex electromagnetic environments. In order to solve this problem, an autonomous maneuver decision-making approach is developed based on deep reinforcement learning (DRL) architecture. Meanwhile, a Transformer network is integrated into the actor and critic networks, which can find the potential dependency relationships among the time series trajectory data. By using these relationships, the information loss is partially compensated, which leads to maneuvering decisions being more accurate. The issues of limited experience samples, low sampling efficiency, and poor stability in the agent training state appear when the Transformer network is introduced into DRL. To address these issues, the measures of designing an effective decision-making reward, a prioritized sampling method, and a dynamic learning rate adjustment mechanism are proposed. Numerous simulation results show that the proposed approach outperforms the traditional DRL algorithms, with a higher win rate in the case of opponent information loss.

MTLPM: a long-term fine-grained PM2.5 prediction method based on spatio-temporal graph neural network.

The concentration of PM2.5 is one of the air quality indicators that the public pays the most attention to. Existing methods for PM2.5 prediction primarily analyze and forecast data from individual monitoring stations, without considering the mutual influence among multiple stations caused by natural environmental factors, e.g., air circulation. Moreover, the existing methods are mostly short-term predictions and perform poorly in long-term forecasting. In this paper, we propose MTLPM, i.e., a spatio-temporal graph neural network model based on an encoder-decoder architecture, which fully exploits the spatial dynamic patterns and long-term dependencies. Firstly, we adopt a message passing mechanism combined with spatial features and complex environmental factors (e.g., temperature, humidity, and wind direction) to update station data, capturing real-time spatial dynamic information. Secondly, we adopt the Multi-head ProbSparse Self-attention to extract temporal features, learning the long-term dependency relationships among the data. Finally, we adopt a generative one-step decoder structure to simultaneously forecast the data for multiple stations over a long period. We conducted experiments on both the project dataset and the publicly available dataset. Compared to existing state-of-the-art methods, MTLPM achieved an average reduction of approximately 1.6 in mean absolute error (MAE) and approximately 0.02 in symmetric mean absolute percentage error (SMAPE) in predicting results. The relevant source code is publicly available on GitHub1.

Local charge radius relations based on neutron shell effects

In this paper, we obtained the mean mass density parameter (MMDP) [Formula: see text] based on the nuclear mass AME2020 and nuclear charge radius CR2013 databases. On this basis, we study the dependence relationship between neutron number N and the two neighboring isotopes MMDP difference [Formula: see text], and then obtained the empirical formula for [Formula: see text]. By combining this empirical formula with the AME2020 and CR2013 databases, the root-mean-square deviation (RMSD) for 606 nuclear charge radii with [Formula: see text] 21 between the calculated and experimental values is 0.0046[Formula: see text]fm. Considering the odd–even staggering and isospin term correction, the study found that the RMSD is reduced to 0.0040[Formula: see text]fm. This work also uses Levenberg–Marquart (L-M) neural network approach to study the nuclear charge radius. The RMSD of nuclear charge radius is only 0.0030 fm, where the accuracy is increased by about 25%. Furthermore, the predicted values of nuclear charge radius obtained using this modified empirical formula and Neural Network model are competitive with the results of other models. These results indicate that nuclear charge radius relation and Neural Network model based on [Formula: see text] proposed in this work have a certain accuracy, simplicity and reliability.

Coordinate-Corrected and Graph-Convolution-Based Hand Pose Estimation Method.

To address the problem of low accuracy in joint point estimation in hand pose estimation methods due to the self-similarity of fingers and easy self-obscuration of hand joints, a hand pose estimation method based on coordinate correction and graph convolution is proposed. First, the standard coordinate encoding is improved by generating an unbiased heat map, and the distribution-aware method is used for decoding coordinates to reduce the error in decoding the coordinate encoding of joints. Then, the complex dependency relationship between the joints and the relationship between pixels and joints of the hand are modeled by using graph convolution, and the feature information of the hand joints is enhanced by determining the relationship between the hand joints. Finally, the skeletal constraint loss function is used to impose constraints on the joints, and a natural and undistorted hand skeleton structure is generated. Training tests are conducted on the public gesture interaction dataset STB, and the experimental results show that the method in this paper can reduce errors in hand joint point detection and improve the estimation accuracy.

Frequency of physical activity during leisure time and variables related to pain and pain medication use in Spanish adults: A cross-sectional study.

Physical inactivity has been identified as a risk factor for pain. The main objective was to analyze the relationships between leisure time physical activity frequency (PAF) and pain prevalence, pain level, pain impairment, daily life pain impairment, and analgesic use in Spanish adults. In addition, risk factors such as sex, body mass index, marital status and social class were assessed for these pain variables in addition to PAF. Cross-sectional study based on data from the 2014 and 2020 European Health Surveys in Spain residents. The Chi-square test was used to analyze the relationship of dependence between the variables of interest. A correlation study calculating Spearman's rho and a multiple logistic regression were performed to assess risk factors for pain variables. 20,113 and 19,196 subjects with a median age of 49 and 52 years old in 2014 and 2020 European Health Surveys, respectively, were analyzed. Dependence relationships were found between PAF and pain variables (p<0.001). The prevalence of: pain, high levels of pain, pain impairment, high level of pain impairment and use analgesic were higher in the inactive population than in the rest of the PAF levels (36.7-53%) vs (18.6-44.3%), p<0.05. Weak correlations were found between PAF and pain variables (-0.177 ≤ Rho ≤ -0.107) (p<0.001). Logistics regression show that being active or very active reduces the odds of pain, the intensity of pain and being affected in daily activities due to pain by 0.524 to 0.776 times. Likewise, being active or very active reduces the odds of taking pain medication by 0.661 to 0.755 times. Also age, low social class, being a woman, and being obese increase of odds of pain, pain affectation and use of analgesics in both surveys by 1.008 to 2.202 times. Physical inactivity was related to a higher prevalence of: pain, higher levels of pain, higher pain involvement and higher analgesic use. In addition, lower social class, being female, older age, and obesity were factors for higher odds of pain, pain involvement, and analgesic use in both surveys.

Batch process soft sensing based on data-stacking multiscale adaptive graph neural network

Abstract Soft sensing technology has found extensive application in predicting key quality variables in batch processes. However, its application in batch process is limited by the uneven batch length, the correlation of data and the difficulty in extracting the dependencies between variables and within variables. To address these issues, we propose a data-stacking multiscale adaptive graph neural network (DSMAGNN) soft sensor model. Firstly, Mutual information (MI) is used to selected quality-related variables, the 3D batch data is converted into a time-delay sequence suitable for input to the soft sensor model through the data stacking strategy, and the underlying time correlation at different time scales is preserved by incorporating the multi-scale pyramid network. Secondly, the dependencies between variables are inferred by the adaptive graph learning module, while the dependencies both within and between variables are modeled by the multi-scale temporal graph neural network. Thirdly, collaborative work across different time scales is further facilitated by the scale fusion module. Finally, the feasibility and effectiveness of the model are verified through experiments in the industrial-scale penicillin fermentation process and hot rolling process.

The Relationship of Grade Expectation and Academic Achievement of College Students

Students’ motivation is an important factor in academic performance. The purpose of this study is to examine the relationship and interaction effects among college students' grade expectations, academic performance and perceptions of course difficulty. The sample of the study consists of 2,946 students enrolled at an university in Ankara. 11,294 responses of the students to the Teaching Quality Assesment Questionnaire and grades of students form the study’s data. The dependency relationship between students' expected grade and received grades was examined with the Chi-square test of independence. In addition, multilevel frequency analysis and log linear analysis were applied to determine the interactions between the levels of expected grade, received grade and perceived difficulty level of the course variables. The study found that students who received high grades had expectations that closely aligned with their actual grades, while students who received low grades had expectations that were less aligned. In other words, as students' academic achievement increases, their expectations of their grades and the grades they receive align more closely. Another finding is a negative relationship between an increase in the perceived difficulty of the course and the likelihood of expecting and receiving high grades. The findings are discussed in terms of Expectancy Theory, Goal Setting Theory and the Dunning-Kruger effect.

Explainable artificial intelligence for machine learning prediction of bandgap energies

The bandgap is an inherent property of semiconductors and insulators, significantly influencing their electrical and optical characteristics. However, theoretical calculations using the density functional theory (DFT) are time-consuming and underestimate bandgaps. Machine learning offers a promising approach for predicting bandgaps with high precision and high throughput, but its models face the difficulty of being hard to interpret. Hence, an application of explainable artificial intelligence techniques to the bandgap prediction models is necessary to enhance the model's explainability. In our study, we analyzed the support vector regression, gradient boosting regression, and random forest regression models for reproducing the experimental and DFT bandgaps using the permutation feature importance (PFI), the partial dependence plot (PDP), the individual conditional expectation plot, and the accumulated local effects plot. Through PFI, we identified that the average number of electrons forming covalent bonds and the average mass density of the elements within compounds are particularly important features for bandgap prediction models. Furthermore, PDP visualized the dependency relationship between the characteristics of the constituent elements of compounds and the bandgap. Particularly, we revealed that there is a dependency where the bandgap decreases as the average mass density of the elements of compounds increases. This result was then theoretically interpreted based on the atomic structure. These findings provide crucial guidance for selecting promising descriptors in developing high-precision and explainable bandgap prediction models. Furthermore, this research demonstrates the utility of explainable artificial intelligence methods in the efficient exploration of potential inorganic semiconductor materials.

Efficient inference of Vision Transformer with structural pruning and operator fusion on GPU

Abstract Currently, Vision Transformer (ViT) has been widely applied in computer vision tasks and has achieved remarkable results. However, its storage, memory, and computational requirements hinder its deployment on general and common GPUs. We propose a framework for accelerating the inference of ViT models, which takes into account both model compression and hardware-friendly operator fusion. This framework facilitates the efficient execution of the model on a single GPU while minimizing any substantial reduction in model accuracy. Our approach consists of two stages. The first stage entails structured pruning, whereby an automated approach is employed to determine the dependency relationships among layers within ViT models. By leveraging these relationships, group pruning is implemented on the interdependent parameters, resulting in a pruned model. In the second stage, hardware-specific acceleration algorithms, tailored to the unique characteristics of the pruned model, are introduced. These algorithms aim to further enhance the performance of the pruned ViT models, enabling them to achieve inference speedup on GPUs. We conducted experiments on various ViT models, and the results indicate that our designed acceleration framework achieves a significant improvement in inference speed, ranging from 1.05 times to 3.08 times, while maintaining accuracy loss within a tolerable range of 3%.

Ramachandran-like Conformational Space for DNA.

DNA's ability to exist in a wide variety of structural forms, subforms, and secondary motifs is fundamental to numerous biological processes and has driven the development of biotechnological applications. Major determinants of DNA flexibility are the multiple torsional degrees of freedom around the phosphodiester backbone. This high complexity can be rationalized by using two pseudotorsional angles linking atoms P and C4', from which Ramachandran-like plots can be built. In this contribution, we explore the distribution of η (eta: C4'i-1-Pi-C4'i-Pi+1) and θ (theta: Pi-C4'i-Pi+1-C4'i+1) angles in known experimental structures retrieved from the Protein Data Bank (PDB), subdividing the conformational space into different datasets. After the removal of the canonical/helical conformations typical of the B-form, we find the existence of a conformational map with clearly permitted and forbidden regions. Some of these regions are populated with specific DNA forms, like Z- or A-DNA, or by specific secondary motifs, like G-quadruplexes and junctions. We evaluated the sequence dependency and energy relationship among the high-density regions identified in the η-θ space. Furthermore, we analyzed the effect produced by proteins and cations when bound to DNA, finding that specific proteins produce some nonhelical conformations, while other regions appear to be stabilized by divalent cations.

Predicting Dependent Edges in Nonequilibrium Complex Systems Based on Overlapping Module Characteristics

Problem: Predicting dependency relationships in nonequilibrium systems is a critical challenge in complex systems research. Solution proposed: In this paper, we propose a novel method for predicting dependent edges in network models of nonequilibrium complex systems, based on overlapping module features. This approach addresses the many-to-many dependency prediction problem between nonequilibrium complex networks. By transforming node-based network models into edge-based models, we identify overlapping modular structures, enabling the prediction of many-to-many dependent edges. Experimental evaluation: This method is applied to dependency edge prediction in power and gas networks, curriculum and competency networks, and text and question networks. Results: The results indicate that the proposed dependency edge prediction method enhances the robustness of the network in power–gas networks, accurately identifies supporting relationships in curriculum–competency networks, and achieves better information gain in text–question networks. Conclusion: These findings confirm that the overlapping module-based approach effectively predicts dependencies across various nonequilibrium complex systems in diverse fields.

Using Political Connections to Raise Rivals’ Costs: Evidence from an Emerging Market

AbstractIn this paper, we leverage resource dependency theory to examine the impact of political connections on rivals’ costs and how this impact is affected by rival‐side and politician‐side contingencies. Using a panel dataset of Pakistani firms, our system generalized method of moments estimates show that politically connected firms can increase their rivals’ costs by influencing their rivals’ dependency relationship with the government. This impact is attenuated by the rivals’ strategic flexibility and social legitimacy, which provide some protection or insulation from political attacks in resource markets. Together, our findings extend the contingent dynamics of resource dependency in political markets from focal firms to competitors and offer significant contributions to the corporate political activity literature and resource dependency theory.

Rotor dynamic response prediction using physics-informed multi-LSTM networks

The deep learning method provides an effective alternative to numerical simulations for establishing the nonlinear input-output relationship and calculating dynamic responses of rotor systems. To overcome the low generalization capability of pure data-driven long short-term memory (LSTM) networks when predicting dynamic responses to out-of-distribution inputs, a dynamic response prediction method using physics-informed multi-LSTM networks is proposed. This approach incorporates required physical constraints into the deep LSTM network, allowing the model training process to optimize the network parameters within the feasible solution space that adheres to physical laws. Consequently, this enhances the physical interpretability of the deep learning model. Specifically, two physics-informed multi-LSTM network architectures are introduced, and physical laws of equation of motion, state dependency and hysteretic constitutive relationship are considered to construct the physics loss. The feasibility of the proposed method is verified by a Bouc-Wen hysteresis model and a simulated gas generator rotor. The response prediction performance of the two networks is validated on a constructed fault rotor dataset with significant sample differences, along with cross-speed and cross-node prediction validation for the rotor system. The results demonstrate that the trained networks exhibit strong robustness and generalization capabilities, making them suitable as surrogate models for rotor systems.

Information fusion in order-2 fuzzy environments: A matrix transformation perspective

Order-2 information granules, as a representation of multi-layer structured information, have recently rekindled discussions. It is usually generated by abstracting order-1 information granules. When the dependence relationship and corresponding membership function of the order-1 information granules (reference information granules) are known, Pedrycz et al. used a method based on gradient optimization to complete the aggregation of the order-2 information granules. In this paper, we discuss a more specific scenario: not only the dependencies between reference information granules are captured, but also the order-1 information granules can be expressed as specific fuzzy information distributions. For this, we propose a fusion scheme of order-2 fuzzy sets based on matrix transformation called CQRP. To our knowledge, it is the first method that completely integrates the structural information of the order-2 environment into the fusion of order-2 fuzzy sets. In the process, we also creatively proposed the attraction and exclusion of structural information, deepening the understanding of structural information. Through sufficient comparison and analysis, we prove that it makes fuller use of information in the order-2 environment and is more reasonable and effective in tasks such as classification and identification.

Great lakes basin model based on physical flow and Data-Driven

Abstract As a group of freshwater lakes, the Great Lakes span the United States and Canada and have a great impact on the economies and environments of the regions. To meet the needs of various stakeholders, it is significant to regulate the flow through the control mechanism to achieve the optimal water level balance. Combined Physical Process and Data-Driven, this paper established a dynamic model of the Great Lakes based on the lake dependence relationship and complex climate factors. After judging the optimal water level by combining the needs of all stakeholders, the hydrodynamic model is run to verify and predict the water level, and the flow control algorithm is obtained. The results show that the prediction of optimal water level has a high accuracy rate. After the flow control, the error between the predicted and optimal water levels is greatly reduced.

Recycled aggregate concrete using seawater: Optimizing concrete's sustainability

Concrete is the most widely used building material worldwide and causes huge carbon emissions, high water consumption and negative impacts on the environment. In this context, in order to reduce natural resources consumption and obtaining a “greener” concrete, the use of seawater and recycled aggregates becomes a promising option.In this study, the effect of the use of seawater in the composition and curing of concrete with natural aggregates (NA) and recycled aggregates (RA) applied at different ratios (0 %, 50 % and 100 %) on its mechanical and durability properties was evaluated. By applying structural equation modelling (SEM) with the R version 4.2.2, the dependence relationships between the variables were empirically evaluated.The analysis of the results has made it possible to establish the advantages and disadvantages of the manufacture of concrete with seawater and RA. It was found there is a need to increase the water/cement ratio in concrete made with seawater, the effective water/cement ratio was increased by 0.03 with respect to the control (in order to maintain workability constant) and that the use of seawater did not influence the mechanical properties of concrete made with NA. However, in concrete made with RA, the mechanical properties improved with the presence of seawater in the mixing, 39 MPa compressive strength at 28 days was obtained for concrete made with 50 % of RA. Durability properties were negatively affected by the presence of seawater and RA, with an increase in water absorption, shrinkage and carbonation depth. The seawater curing process did not influence the mechanical and durability properties of concrete.These results indicate that seawater alone does not influence the mechanical and durability properties of concrete. However, there the combined effect of seawater and RA improves the final characteristics of concrete.

Study on the spatial distribution characteristics of traditional villages and their response to the water network system in the lower yangtze river basin

Traditional villages hold significant historical and cultural value as the precious heritage of China’s agricultural civilization. Currently, against the backdrop of increasing urbanization and rapid expansion of urban construction land, the spatial patterns of traditional villages across various regions in China are being encroached upon and damaged, with protection pressures growing daily. As one of the important cradles of Chinese civilization, the Lower Yangtze River Basin (LYRB) has traditional villages closely linked with its water systems, forming a unique human-land relationship and spatial distribution pattern. However, influenced by the rapid urbanization process, the spatial patterns of traditional villages in this region also face a crisis, and the contradiction between protection and development is becoming increasingly prominent. How to balance this contradiction and ensure the reasonable protection and sustainable development of traditional villages has become an urgent issue to address. Therefore, this study focuses on the LYRB. Using ArcGIS tools and combined with mathematical analysis methods, the spatial distribution characteristics and essential influencing factors of traditional villages in this area were screened and analyzed. The objective was to examine the spatial structural relationship between traditional villages, four water system types, and nine sub-basin units, intending to reveal the unique interdependence between the water system and traditional villages in this area. This would provide scientific support for the formulation of scientific conservation strategies. The research results show that: (1) Traditional villages in The LYRB form two core clusters spatially and exhibit substantial spatial accumulation; (2) Water system characteristics are the main factors affecting the distribution of traditional villages; (3) In the LYRB, the spatial distribution of the nine sub-basins is closely related to the spatial distribution of traditional villages, resulting in typical regional spatial differentiation of traditional villages in this area. This study is based on a watershed perspective, and the results highlight the importance of the water system network in the development of traditional villages, revealing a unique spatial dependency relationship between traditional villages and the water network in the LYRB. In order to ensure the comprehensive protection of the traditional village system in this region, it is essential to adhere to the fundamental principles that govern its spatial configuration. A tripartite collaborative protection system based on the watershed should be formulated from the perspective of the overall distribution relationship between the water network and the traditional villages. This system would serve to protect the overall landscape, the water network pattern, and the traditional villages. Establishing an overall pattern view of integrating the water system network and the traditional villages is essential.

Attribute Value Weighted Averaged One-Dependence Estimators with Kullback–Leibler Divergence

The Averaged One-Dependence Estimators (AODE) algorithm is an improvement of the naive Bayes algorithm, which allows all the attributes dependent on one common attribute, called parent attribute, thus forming One-Dependence Estimators (ODE). The classification probability is estimated by averaging the conditional probability of the ODE. When there is a dependency relationship between attributes, the AODE algorithm can better capture these relationships, thus improving classification performance. The AODE algorithm treats the parent and child attribute values equally in different ODEs. However, the parent attribute value and the child attribute value in different ODEs have different importance for classification. In this paper, two attribute value weighted AODE based on Kullback–Leibler divergence are proposed, one is parent attribute value weighted AODE, and the other is child attribute value weighted AODE. Comparative experiments were carried out with 30 datasets in the UCI database, and the experiments indicate that the performance of the parent attribute value weighted AODE algorithm with Kullback–Leibler divergence is significantly better than the original AODE algorithm, and its performance is also better than the mutual information weighted AODE algorithm.