Dependency Graph Research Articles

Micro-Doppler based Human Activity Recognition using ABOA based Dual Spatial Convolution with Gated Recurrent Unit

The through-wall capability, device-free detection of radar-based human activity recognition are drawing a lot of interest from both academics and industry. The majority of radar-based systems do not yet combine signal analysis and feature extraction in the frequency domain and the time domain. Applications like smart homes, assisted living, and monitoring rely on human identification and activity recognition (HIAR). Radar has a number of advantages over other sensing modalities, such as the ability to shield users' privacy and conduct contactless sensing. The article introduces a new human tracking system that uses radar and a classifier called Dual Spatial Convolution Gated Recurrent Unit (DSC-GRU) to identify the subject and their behavior. The system follows the person and identifies the type of motion whenever it detects movement. One important feature is the integration of the GRU with the DSC unit, which allows the model to simultaneously capture the spatiotemporal dependence. Present prediction models just take into account spatial features that are immediately adjacent to each other, disregarding or just superimposing global spatial features when taking spatial correlation into account. A new dependency graph is created by calculating the correlation among nodes using the correlation coefficient; this graph represents the global spatial dependence, while the classic static graph represents the neighboring spatial dependence in the DSC unit. The DSC unit goes a step further by using a modified gated mechanism to quantify the various contributions of both local and global spatial correlation. While previous models performed worse, the suggested model outperformed them with an accuracy of 99.45 percent and a precision of 97.15 percent.

Exploring the drivers of local government budget coordination: A random forest regression analysis

Budget coordination is a critical issue of local government coordinative governance. Existing literature emphasizes its importance but does not give in-depth empirical research. The random forest regression model was used to probe into the drivers of budget coordination for 2815 local government projects in China. Based on the purity of the split nodes of the decision tree, the three most important factors for achieving the goal of local government budget coordination are identified: discretion, decision-making level and fund scale. The partial dependence graphs visually illustrate the differentiated and nonlinear marginal effects of various explanatory variables on the response variable.

SAGL: A self-attention-based graph learning framework for predicting survival of colorectal cancer patients

Background and Objective: Colorectal cancer (CRC) is one of the most commonly diagnosed cancers worldwide. The accurate survival prediction for CRC patients plays a significant role in the formulation of treatment strategies. Recently, machine learning and deep learning approaches have been increasingly applied in cancer survival prediction. However, most existing methods inadequately represent and leverage the dependencies among features and fail to sufficiently mine and utilize the comorbidity patterns of CRC. To address these issues, we propose a self-attention-based graph learning (SAGL) framework to improve the postoperative cancer-specific survival prediction for CRC patients.Methods: We present a novel method for constructing dependency graph (DG) to reflect two types of dependencies including comorbidity-comorbidity dependencies and the dependencies between features related to patient characteristics and cancer treatments. This graph is subsequently refined by a disease comorbidity network, which offers a holistic view of comorbidity patterns of CRC. A DG-guided self-attention mechanism is proposed to unearth novel dependencies beyond what DG offers, thus augmenting CRC survival prediction. Finally, each patient will be represented, and these representations will be used for survival prediction.Results: The experimental results show that SAGL outperforms state-of-the-art methods on a real-world dataset, with the receiver operating characteristic curve for 3- and 5-year survival prediction achieving 0.849±0.002 and 0.895±0.005, respectively. In addition, the comparison results with different graph neural network-based variants demonstrate the advantages of our DG-guided self-attention graph learning framework.Conclusions: Our study reveals that the potential of the DG-guided self-attention in optimizing feature graph learning which can improve the performance of CRC survival prediction.

Research of numerical indicators for the development of the Asselskaya area of Orenburg oil and gas condensate field using the material balance method

The purpose of this work is to analyze and forecast the development indicators of the Assel deposit of Orenburg oil and gas condensate field. To complete this task, a large amount of data is required, which was obtained from the technological development project. The calculation is performed using a program written in the Python programming language. The variables for the material balance equation are given, some of them are calculated using intermediate formulas. The average values of the parameters over the last 15 years of development were chosen as the optimized parameters, since small amounts of cumulative production in the first years of development can lead to a significant error in the calculation of the material balance equation. Also, a comparison was made of the estimated forecast for the development of the Assel deposit with the forecast, according to the state plan, presented in the field development project. The comparison was made on the main parameters: cumulative oil production, annual oil production, oil recovery factor and water cut. For a visual comparison of the calculated parameters, dependency graphs are presented that reflect the forecast made by the material balance method, as well as the forecast based on the data of the state plan. The difference in the behavior of the curves shown on the graphs can be explained by the inaccuracy of the parameters describing the reservoir, as well as the inaccuracy of determining the initial recoverable reserves. This is also affected by the difference in reservoir drawdowns for injection and production wells, proposed in the state plan and in the forecast. Of course, the inaccuracy of the injectivity and productivity coefficients of wells, which were selected based on the estimated volumes of water injection and oil production, also affects. Based on the calculation performed, it can be concluded that it is expedient to further exploit the Asselskaya area of Orenburg oil and gas condensate field with the introduction of a reservoir pressure maintenance system until 2079. According to the forecasts, the water cut equal to 96% will be achieved in 2079, while the oil recovery factor will be 0.427.

Intelligent code search aids edge software development

The growth of multimedia applications poses new challenges to software facilities in edge computing. Developers must effectively develop edge computing software to accommodate the rapid expansion of multimedia applications. Code search has become a prevalent practice to enhance the efficiency of the construction of edge software infrastructure. Researchers have proposed lots of approaches for code search, and employed deep learning technology to extract features from program representations, such as token, AST, graphs, method name, and API. Nevertheless, two prominent issues remain: 1) there are only a few studies on the effective use of graph representation for code search (especially in Java language), and 2) there is a lack of empirical study on the contributions of different program representations. To address these issues, we conduct an empirical study to explore program representations, especially program graphs. To the best of our knowledge, this is the first attempt to conduct code search with mixed graphs representation for Java language, containing the control flow graph and the program dependence graph. We also present a hybrid approach to capture and fuse the features of a program with representations of Token, AST, and Mixed Graphs (TAMG). The results of our experiment show that our approach possesses the best ability (R@1 with 37% and R@10 with 67.1%). Our graph representation exhibits a positive effect, and the token and AST also have a significant contribution to the code search. Our findings can aid developers in efficiently searching for the desired code while constructing the software infrastructure for edge computing, which is crucial for the rapid expansion of multimedia applications.

Exploring user satisfaction and improvement opportunities in public charging pile resources

The existing market of public charging pile services for electric vehicle (EV) users has occupied a particular market share. However, instead of solely focusing on pre-planning the construction of charging piles, it is crucial to address the shortcomings of the existing charging pile service and develop effective marketing strategies. This approach can help optimize the utilization of charging pile resources and minimize wastage. In this study, we explore EV users’ comments on the public charging pile service and adopt a natural language pre-training model to classify comments for extracting positive and negative comments. For these two types of comments respectively, we construct the text-to-knowledge to mine the keywords from multiple dimensions. We further excavate the words correlated with the keywords by utilizing dependency parsing to create relational dependency graphs. Taken together, we identify key factors influencing EV user satisfaction or dissatisfaction and uncover the relationships among these factors. These insights provide valuable information for charging pile operators to develop targeted marketing strategies and improvement plans for the existing public charging pile resources, ultimately enhancing the overall user experience.

Распределение осевой и радиальной скорости вблизи с круглым раструбом в воздуховоде

The purpose of the article is to increase the energy efficiency of ventilation systems in mining enterprises using a round socket installed in the air duct. The article presents numerical and experimental results of studying the outlines of vortex zones formed at the installation site of a round bell. Numerical studies were carried out using the Ansys Fluent software package. We obtained graphical and analytical dependences of the distribution of the axial and radial components of the velocity near the bell, depending on its radius and angle of inclination

Interactive Abstract Interpretation with Demanded Summarization

We consider the problem of making expressive, interactive static analyzers compositional . Such a technique could help bring the power of server-based static analyses to integrated development environments (IDEs), updating their results live as the code is modified. Compositionality is key for this scenario, as it enables reuse of already-computed analysis results for unmodified code. Previous techniques for interactive static analysis either lack compositionality, cannot express arbitrary abstract domains, or are not from-scratch consistent. We present demanded summarization, the first algorithm for incremental compositional analysis in arbitrary abstract domains that guarantees from-scratch consistency. Our approach analyzes individual procedures using a recent technique for demanded analysis, computing summaries on demand for procedure calls. A dynamically updated summary dependency graph enables precise result invalidation after program edits, and the algorithm is carefully designed to guarantee from-scratch-consistent results after edits, even in the presence of recursion and in arbitrary abstract domains. We formalize our technique and prove soundness, termination, and from-scratch consistency. An experimental evaluation of a prototype implementation on synthetic and real-world program edits provides evidence for the feasibility of this theoretical framework, showing potential for major performance benefits over non-demanded compositional analyses.

О зависимости процесса промерзания грунтов от влажности

Purpose: the temperatures at which soils begin to freeze during the onset of frost are of interest primarily to agricultural workers and construction workers. It was previously established that many factors influence soil freezing. However, not enough research has been carried out on the influence of individual factors on the freezing process. The article examines the influence of soil moisture on their supercooling and freezing temperatures. Methods: the studies were carried out in a microrefrigerator with three freezing modes. Results: it was found that with constant shaking, the supercooling temperature increased, but the freezing temperature did not change. Graphic dependences of the temperatures of supercooling and freezing of soils on the initial humidity were obtained. The degree of soil compaction did not affect these temperatures. The temperatures of supercooling and freezing of soils depend to a greater extent on the dispersion of soils than on the content of organic substances in them. Practical significance: the results of the work are important for construction as they expand the understanding of the features of the mechanism of soil freezing.

FEATURES OF MAGNETIC OSCILLATIONS IN A TWO-LAYER STRUCTURE WITH EXCHANGE COUPLING

Graphs of time and frequency dependences of the components of magnetic oscillations of the layers of a planar two-layer structure and their portraits of oscillations were constructed. The excitation of the structure layers for different interlayer coupling coefficients was carried out by a microwave magnetic field of circular polarization. The interlayer bond is characterized by an additional local energy minimum, the spatial position of which depends on the coupling coefficient.

A Variational Autoencoder for Neural Temporal Point Processes with Dynamic Latent Graphs

Continuously observed event occurrences, often exhibit self and mutually exciting effects, which can be well modeled using temporal point processes. Beyond that, these event dynamics may also change over time, with certain periodic trends. We propose a novel variational autoencoder to capture such a mixture of temporal dynamics. More specifically, the whole time interval of the input sequence is partitioned into a set of sub intervals. The event dynamics are assumed to be stationary within each subinterval, but could be changing across those subintervals. In particular, we use a sequential latent variable model to learn a dependency graph between the observed dimensions, for each subinterval. The model predicts the future event times, by using the learned dependency graph to remove the non contributing influences of past events. By doing so, the proposed model demonstrates its higher accuracy in predicting inter event times and event types for several real world event sequences, compared with existing state of the art neural point processes.

Optimizing the Optimization of Planning Domains by Automatic Action Schema Splitting

Most planners are based on grounding, that is, generating all instances of a parameterized action during a preprocessing phase. For some problems the number of ground actions is too high, causing a performance bottleneck. Building upon an existing approach, we present an enhanced method to split action schemas automatically during the grounding phase, to reduce the number of ground actions. First, we propose to exploit the structural knowledge of the problems to have a more informative dependency graph. Then, we suggest a better objective function to define and choose the best split. Finally, we present a more effective search to find it. We experimentally measure the impact of each of these improvements, and show that our approach significantly outperforms the state of the art.

Tyche: An Efficient and General Prefetcher for Indirect Memory Accesses

Indirect memory accesses (IMAs, i.e., A [ f ( B [ i ])]) are typical memory access patterns in applications such as graph analysis, machine learning, and database. IMAs are composed of producer-consumer pairs, where the consumers’ memory addresses are derived from the producers’ memory data. Due to the built-in value-dependent feature, IMAs exhibit poor locality, making prefetching ineffective. Hindered by the challenges of recording the potentially complex graphs of instruction dependencies among IMA producers and consumers, current state-of-the-art hardware prefetchers either (a) exhibit inadequate IMA identification abilities or (b) rely on the run-ahead mechanism to prefetch IMAs intermittently and insufficiently. To solve this problem, we propose Tyche, 1 an efficient and general hardware prefetcher to enhance IMA performance. Tyche adopts a bilateral propagation mechanism to precisely excavate the instruction dependencies in simple chains with moderate length (rather than complex graphs). Based on the exact instruction dependencies, Tyche can accurately identify various IMA patterns, including nonlinear ones, and generate accurate prefetching requests continuously. Evaluated on broad benchmarks, Tyche achieves an average performance speedup of 16.2% over the state-of-the-art spatial prefetcher Berti. More importantly, Tyche outperforms the state-of-the-art IMA prefetchers IMP, Gretch, and Vector Runahead, by 15.9%, 12.8%, and 10.7%, respectively, with a lower storage overhead of only 0.57 KB.

DoppelGanger++: Towards Fast Dependency Graph Generation for Database Replay

A database replay system (DRS) captures workloads on a production system and then replays them in a test system to test various system changes, avoiding any risk before realizing them in production. The dependency graph generation in a DRS is crucial in preserving output determinism while maximizing concurrency. The state-of-the-art dependency graph generation algorithm deployed in a commercial DBMS uses a generate-and-prune strategy. It first generates a dependency graph by performing backward scans for each request in a workload. It then prunes all redundant edges using an expensive, transitive reduction algorithm. However, we notice that this generates a large dependency graph that contains many redundant edges and its worst-case time complexity is quadratic to the number of requests in a workload. In order to solve these challenging problems, we formally propose four classes of dependency graphs for DRSs. We then present a stateful single forward scan algorithm, SSFS, to generate any class of dependency graphs by performing a single scan over all requests while succinctly maintaining states. Here, states refer to information that is stored and maintained for efficient dependency graph generation. We also propose the parallel SSFS to utilize the computation power with multi-core CPUs while balancing the loads. We implemented our DRS in a leading commercial DBMS. Extensive experiments using the TPC-C, SD benchmarks, and a real-world customer workload show that our DRS significantly improves the dependency graph generation time by up to two orders of magnitude, compared to the state-of-the-art.

REDUCING THE KINEMATIC ERROR OF AN ECCENTRIC TRANSMISSION
 WITH A PARALLEL LOCATION OF INPUT AND OUTPUT SHAFT
 AS A RESULT OF THE APPLICATION OF A DOUBLE-FLOW LOADING SCHEME

The article presents kinematic diagrams and computer analysis of three types of eccentric transmission schemes.
 The graphical dependences of the kinematic error of the eccentric transmission are presented for the coaxial and
 parallel arrangement of the input and output shafts in two single-flow loading schemes. Computer analysis of an
 eccentric transmission with single-flow loading schemes showed that the kinematic error with the coaxial arrangement
 of the input and output shafts is 30 times lower than with the parallel arrangement of these shafts. In order to reduce
 the kinematic error of an eccentric transmission with a parallel arrangement of input and output shafts, a two-flow
 loading scheme was proposed. It has been established that the use of a double-flow loading scheme makes it possible
 to reduce the kinematic error by 12 times compared to a single-flow loading scheme with a load on the output shaft
 of 10 N∙m.
 It is planned to use the design of an eccentric transmission with a parallel arrangement of input and output
 shafts with several power flows when designing various types of gearboxes for cultivators.

Optimisation of production and modelling of production costs in farms

A significant area of improvement of the economic efficiency of agricultural enterprises, especially in the context of martial law, is to optimise production and use of resource potential. The purpose of this study was to develop scientific and practical recommendations for optimising the production activities of farms. The study employed the following methods: system analysis and synthesis to determine the reserves of the types of resources involved; economic-mathematical modelling and optimisation to determine best solutions; analytical-calculation method to calculate production indicators; correlation and regression analysis to determine the dependence of milk production costs on resource consumption; graphical method and extrapolation to find the values of the regression function. The principal stages and features of building an economic-mathematical model for optimising the resource potential of enterprise were identified. The model was used to analyse data, identify reserves of resource potential, find an optimisation solution for product sales volumes using the Solution Search spreadsheet tool, and adopt a strategy for improving economic efficiency. The study offered a solution for the economic and mathematical modelling of the best structure of production of a farm, which factors in the available production resources. The modelling found that the maximum income can be obtained by redistributing the production volumes of certain types of products and, accordingly, the resources for their production, considering the standard costs of production per unit of product, prices for products and resources. Using the modelling, the study obtained a regression dependence of the cost of milk produced in household farms on the cost of feed, labour costs, wages, and the number of cows. The study found the impact of certain types of resources on the production cost and builds the corresponding graphical dependencies. The practical value of the findings of this study lies in the possibility of using the recommendations directly by members of farms in planning, organising production activities, and optimising the use of resource potential

A neural machine translation method based on split graph convolutional self-attention encoding

With the continuous advancement of deep learning technologies, neural machine translation (NMT) has emerged as a powerful tool for enhancing communication efficiency among the members of cross-language collaborative teams. Among the various available approaches, leveraging syntactic dependency relations to achieve enhanced translation performance has become a pivotal research direction. However, current studies often lack in-depth considerations of non-Euclidean spaces when exploring interword correlations and fail to effectively address the model complexity arising from dependency relation encoding. To address these issues, we propose a novel approach based on split graph convolutional self-attention encoding (SGSE), aiming to more comprehensively utilize syntactic dependency relationships while reducing model complexity. Specifically, we initially extract syntactic dependency relations from the source language and construct a syntax dependency graph in a non-Euclidean space. Subsequently, we devise split self-attention networks and syntactic semantic self-attention networks, integrating them into a unified model. Through experiments conducted on multiple standard datasets as well as datasets encompassing scenarios related to team collaboration and enterprise management, the proposed method significantly enhances the translation performance of the utilized model while effectively mitigating model complexity. This approach has the potential to effectively enhance communication among cross-language team members, thereby ameliorating collaborative efficiency.

Graph Convolutional Network with Syntactic Dependency for Aspect-Based Sentiment Analysis

AbstractAspect-based sentiment analysis (ABSA) aims to mine the sentiment tendencies expressed by specific aspect terms. The studies of ABSA mainly focus on the attention-based approaches and the graph neural network approaches based on dependency trees. However, the attention-based methods usually face difficulties in capturing long-distance syntactic dependencies. Additionally, existing approaches using graph neural networks have not made sufficient exploit the syntactic dependencies among aspects and opinions. In this paper, we propose a novel Syntactic Dependency Graph Convolutional Network (SD-GCN) model for ABSA. We employ the Biaffine Attention to model the sentence syntactic dependencies and build syntactic dependency graphs from aspects and emotional words. This allows our SD-GCN to learn both the semantic relationships of aspects and the overall semantic meaning. According to these graphs, the long-distance syntactic dependency relationships are captured by GCNs, which facilitates SD-GCN to capture the syntactic dependencies between aspects and viewpoints more comprehensively, and consequently yields enhanced aspect features. We conduct extensive experiments on four aspect-level sentiment datasets. The experimental results show that our SD-GCN outperforms other methodologies. Moreover, ablation experiments and visualization of attention further substantiate the effectiveness of SD-GCN.

Оцінка ресурсу фрикційних поверхонь гальмівних дискових механізмів за показниками відносного зношення для легкових автомобілів

Modern development of vehicle designs requires paying great attention to braking properties, which will depend on the design parameters of the brake mechanisms. The article discusses a scheme where a disc brake is installed on the front wheels, and drum brakes are installed on the rear wheels. From the diagram of the distribution of forces that act on the vehicle during braking, the maximum friction forces for the front and rear axles were determined. A general formula was obtained for the braking distance of a vehicle, during which wear of the brake mechanism occurs. We used the results of the well-known theory of friction and wear by I.V. Kragelsky. The mathematical wear model was built for each friction pair. The wear model takes into account the design parameters of the vehicle, the wear resistance coefficient of materials, the initial braking speed of the vehicle, the mileage and braking distance. The main design parameters of the brake system are the friction radius, the kinematic rolling radius of the wheel, and the amount of drive pressure.
 To assess the service life of the brake mechanism, it was proposed to use such an indicator as the relative wear of associated parts. A formula has been obtained for calculating this indicator based on changes in geometric parameters and operating modes of the brake mechanism under operating conditions. A forecast was made of the service life of the brake mechanisms of the front and rear axles of passenger cars, which is proposed to be carried out according to the indicator of relative wear of friction surfaces. Graphic dependences of the distribution of relative wear of the friction surfaces of brake mechanisms for Chevrolet Aveo and Forza cars were constructed. It was shown using the example of Chevrolet Aveo passenger cars that the relative wear of the front axle brakes is maximum and it varies from 22.5 to 26.1%, and for the rear axle this figure varies from 21.0 to 22.5%. The service life of the brake disc is 4.44 times greater than the service life of the friction lining for the Chevrolet Aveo. For the Forza car this figure is 4.76. The results of the work can be used to estimate the residual life of brake mechanisms, taking into account operating conditions.

LoHDP: Adaptive local differential privacy for high‐dimensional data publishing

SummaryThe increasing availability of high‐dimensional data collected from numerous users has led to the need for multi‐dimensional data publishing methods that protect individual privacy. In this paper, we investigate the use of local differential privacy for such purposes. Existing solutions calculate pairwise attribute marginals to construct probabilistic graphical models for generating attribute clusters. These models are then used to derive low‐dimensional marginals of these clusters, allowing for an approximation of the distribution of the original dataset and the generation of synthetic datasets. Existing solutions have limitations in computing the marginals of pairwise attributes and multi‐dimensional distribution on attribute clusters, as well as constructing relational dependency graphs that contain large clusters. To address these problems, we propose LoHDP, a high‐dimensional data publishing method composed of adaptive marginal computing and an effective attribute clustering method. The adaptive local marginal calculates any k‐dimensional marginals required in the algorithm. In particular, methods such as sampling‐based randomized response are used instead of privacy budget splits to perturb user data. The attribute clustering method measures the correlation between pairwise attributes using an effective method, reduces the search space during the construction of the dependency graph using high‐pass filtering technology, and realizes dimensionality reduction by combining sufficient triangulation operation. We demonstrate through extensive experiments on real datasets that our LoHDP method outperforms existing methods in terms of synthetic dataset quality.