Weight Allocation Research Articles

Coordination Control Strategy for Human-Machine Cooperative Steering of Intelligent Vehicles: A Reinforcement Learning Approach

This paper proposes a novel coordination control strategy through reinforcement learning approach for human-machine cooperative steering of intelligent vehicles, so as to realize a more flexible and efficient way for the human driver and the automated driving system to jointly complete the path-following. Firstly, the human-machine cooperative steering is modeled by the optimal preview driver model with adaptive preview time and the MPC lateral tracking model with adaptive prediction horizon and step, as well as the steering system with a realistic dual-motor steering-by-wire structure is also built into the human-machine cooperative steering system. Then, the human-machine coordination control strategy is designed and trained based on two reinforcement learning agents to further optimize the allocation of cooperative steering weights. Finally, the strategy is fully verified in lane departure simulation scenarios and also in real-world Steering-in-the-Loop experiments with real-time controller, which shows that both agents can effectively keep the vehicle with the small lateral and yaw errors in the simulation scenarios, and also can be successfully applied in the realistic human-machine cooperative system to maintain the lateral and yaw errors within a safe range during path-following.

Global Resource Allocation for High Throughput and Low Delay in High-Density VANETs

Medium access control (MAC) plays a crucial role in ensuring proper operation in vehicular ad hoc networks (VANETs). However, existing solutions cannot meet the strict requirements of high throughput and low latency in high-density scenarios. In this paper, we propose a novel MAC protocol to meet such demands for VANETs. The roadside unit (RSU) pattern and the dual-transceiver manner are adopted to assign channel resources for all packets. The striking features of our approach are twofold: the time slot allocation based on global vehicle information and the consideration of different delay requirements of different applications. First, we design a time slot exchange mechanism, which avoids any transmission conflict between two adjacent RSUs, to reduce channel resource waste. Then, we design a packet weight allocation mechanism, by which the packets of any network edge area are assigned higher priorities to further reduce channel resource waste. Moreover, we devise a packet quality evaluation mechanism, by which our multi-objective problem is transformed into a single-objective problem. In addition, we devise a greedy branch-and-bound algorithm to address the multiple-knapsack problem, which is transformed into a single-knapsack problem. Extensive simulation results show the advantages of our approach in terms of throughput and latency.

Does crude oil fire the emerging markets currencies contagion spillover? A systemic perspective

The paper lays the empirical foundation for the significance of Crude in explaining the variation in implied volatilities (IVs) of emerging markets nations constituting the MSCI emerging market index. Guided by the significance of Crude as a significant regressor, the study aims to investigate the association of currency IVs with Crude using a connectedness-based approach by Diebold and Yilmaz (2012). The spillover pattern highlights the strong interconnectedness of Asian currencies, with the Taiwanese dollar and Thai Baht feeding the systemic risk, thus the currencies to watch out for the policymakers. An important finding is that the Polish zloty possesses a high spillover risk in the Eastern European economies due to improved economic conditions and a large flow of capital during quantitative easing. On the other hand, Russia is a huge exporter of Crude and shares a limited spillover relationship with Crude, implying domestic macroeconomic conditions and geopolitical risk contribute more to the ruble fall. Based on the spillover pattern of IVs, a portfolio universe selection and weight allocation with dynamic balancing have been devised for investors of the forex market for spillover risk minimization. Findings show that the Chinese Yuan and Chilean Peso are the most favorable currency alongside Crude. However, Indian Rupee serves as the most promising currency pair to be inducted with Crude. The study is particularly beneficial for investors and portfolio managers investing in the forex market to induct the assets in the portfolio to mitigate systemic risk fear, especially during times of distress.

An online reviews-driven large-scale group decision making approach for evaluating user satisfaction of sharing accommodation

To promote the development of the peer-to-peer (P2P) accommodation in sharing economy, it is important to understand and ensure the determinants of high-level user satisfaction. Focusing on factors that affect the travel experience of P2P accommodation users, this article proposes a large-scale group decision making (LSGDM) based method with online reviews to evaluate user satisfaction of sharing accommodation. Firstly, the user demands (UDs) reflecting the actual concerns of users are extracted by combining negative and positive reviews from P2P accommodation platform Airbnb, where negative reviews are classified by sentiment analysis, TF-IDF and Word2Vec technology are used for extraction and the further verification of UDs from all online reviews is performed. Secondly, the level of satisfaction is evaluated through online responses from P2P accommodation users in a large-scale group of decision makers. Thirdly, the final degrees of satisfaction are ascertained by the proposed LSGDM approach, which includes subgroup clustering and a minimal variance weights based feedback mechanism for fair weights allocation under the condition of reaching consensus. Finally, the conclusions further serve as references for improving the performance of P2P sharing accommodation.

A Multi-Indicator Evaluation Method for Spatial Distribution of Urban Emergency Shelters

Evaluation of the spatial distribution of urban emergency shelters can effectively identify defects in the current distribution of urban emergency shelters and weaknesses in the overall evacuation service capacity of the city and provide reference for improving the level of urban emergency shelters and evacuation and disaster relief capacity. At present, evaluation of the spatial distribution of urban emergency shelters is mainly carried out on three aspects: effectiveness, accessibility, and safety. However, there are problems, such as individual evaluation scales and incomplete indicator systems, unreasonable allocation of indicator weights, and ignoring the influence of fuzzy incompatibility between different indicator attributes on the evaluation results. In this paper, we start from two scales, the individual emergency shelter and the regional groups of emergency shelters. Based on the five criteria of effectiveness, accessibility, safety, suitability, and fairness, the evaluation indicator system of the spatial distribution of urban emergency shelters was constructed. It was combined with AHP, CRITIC, the optimal weight coefficient solution method based on the maximum deviation sum of squares theory, and fuzzy optimization theory to construct a multi-indicator evaluation model. Further, the spatial distribution condition of the existing emergency shelter in Shanghai was evaluated. The results show that: among the existing ninety-one emergency shelters in Shanghai, there are nine places with unreasonable spatial distribution; nineteen places are comparatively unreasonable. From the scale of regional groups, there is one district (Pudong New District) with unreasonable spatial distribution: its relative superiority value is far lower than other districts, and there are three districts that are comparatively unreasonable. Further, the evaluation scores of the spatial distribution reasonableness of emergency shelters in each region of Shanghai show a high–low–middle distribution from the downtown area of Shanghai outward. The evaluation indicator system and evaluation method used in this paper can effectively reflect the deficiencies in the spatial distribution of urban emergency shelters, thus providing a reference for the relevant departments to improve and plan emergency shelters.

Wildfire Risk Assessment in Liangshan Prefecture, China Based on An Integration Machine Learning Algorithm

Previous wildfire risk assessments have problems such as subjectivity of weight allocation and the linearization of statistical models, resulting in generally low robustness and low generalization ability of fire risk assessment models. Therefore, in this paper, we explored the potential of integration machine learning algorithms to build wildfire risk assessment models. Based on analyzing fire data’s spatial and temporal distribution, we selected 10 triggering factors of topography, meteorology, vegetation, and human activities, using frequency ratio (FR) to provide uniform data representation of triggering factors. Next, we used the Bayesian optimization (BO) algorithm to perform hyperparametric optimization solutions for various machine learning models: support vector machine (SVM), random forest (RF), and extreme gradient boosting (XGBoost). Finally, we constructed an integration machine learning algorithm to acquire a fire risk grading map and the importance evaluation corresponding to each triggering factor. For validation purposes, we selected Liangshan Prefecture in Sichuan Province as the specific study area and obtained MCD64A1 burned area product to extract the extent of burned areas in Liangshan Prefecture from 2011 to 2020. The accuracy, kappa coefficient, and area under curve (AUC) were then applied to assess the predictive power and consistency of the fire risk classification maps. The experimental analysis showed that among the three models, FR-BO-XGBoost had the best performance in wildfire risk assessment in the Liangshan region (AUC = 0.887), followed by FR-BO-RF (AUC = 0.876) and FR-BO-SVM (AUC = 0.820). The feature importance result indicated that the study area’s most significant effects on wildfires were precipitation, NDVI, land cover, and maximum temperature. The proposed method avoided the subjective weighting and model linearization problems. Compared with the previous methods, it automatically acquired the importance of the triggering factors to the wildfire, which had certain advantages in wildfire risk assessment, and was worthy of further promotion.

Robust unsupervised feature selection via sparse and minimum-redundant subspace learning with dual regularization

Unsupervised feature selection, one of the important dimensionality reduction methods for high-dimensional data, has been paid more and more attention by researchers due to its effectiveness of processing the data without labels. However, most unsupervised feature selection methods do not take into account the fact that real data tends to be mixed with noise or outliers, or only consider the sensitivity of the model to them. In addition, the local manifold structure of data is usually preserved by a simple graph based on fixed k nearest neighbors. On the one hand, the different sample distributions of different data are considered without distinction. On the other hand, simple graph can not well capture the inherent relations between samples when facing multi-modal data. In view of the above problems, a robust unsupervised feature selection algorithm, sparse and minimum-redundant subspace learning with dual regularization (SMRSDR), is proposed in this paper. Specifically, a self-paced learning regularization based on soft weight allocation is introduced into SMRSDR to strictly control the samples’ entry into model learning. Normal samples are allowed to enter model learning in order of their importance, while noise or outliers are strictly blocked out of model learning. Besides, considering the difference in sample distribution and the multimodal nature of data, the traditional simple graph Laplacian regularization is replaced by the hypergraph Laplacian regularization based on adaptive nearest neighbors selection. Furthermore, the sparsity and minimum-redundancy constraints are imposed on the subspace learning framework so that the most representative and minimum-redundant features can be selected. Finally, the objective function of SMRSDR is solved by an alternating iterative optimization algorithm. And a series of experiments are performed to comprehensively prove the effectiveness and superiority of SMRSDR.

A new combination model using decomposition ensemble framework and error correction technique for forecasting hourly PM2.5 concentration.

PM2.5 pollutants are seriously harmful to human health, which is of great significance for the forecasting of PM2.5 concentration. To accurately forecast hourly PM2.5 concentration, a new combination model based on agreement index variational mode decomposition (AIVMD), radial basis function neural network (RBF), induced ordered weighted averaging (IOWA) operator, long short-term memory neural network (LSTM) and error correction (EC), named AIVMD-RBF-IOWA-LSTM-EC, is proposed, which uses decomposition ensemble framework and error correction technique. Taking the reduction of reconstruction error in the process of VMD as the goal, an adaptive method to determine the mode number of VMD by agreement index (AI), named AIVMD, is proposed. Firstly, PM2.5 concentration data are decomposed into simple intrinsic mode function components (IMFs) by AIVMD to reduce the complexity of the data. Secondly, LSTM and RBF models are established for each IMF component, and the prediction results of each model are combined separately. Thirdly, an error correction model based on RBF is established to correct the prediction results. The predicted values of error are not only used to correct the prediction results, but also can be used as the induced value of IOWA operators to solve the weight allocation problem. Finally, the IOWA operator is used to weight the error correction prediction results, and the final result is obtained. To solve the problem that the forecasting accuracy of the combination model based on IOWA operators is low when the complementarity between single models is poor, a combination forecasting method with complementary disadvantage based on IOWA operators is proposed, which effectively improves the robustness of the model. A formula for calculating the proportion of complementary points is given. By solving the formula, the complementarity of the models can be judged, and the method of calculating the weight of the combined model can be selected accordingly. The proposed model is used to forecast PM2.5 concentration in Xi'an, and compared with the predicted results of contrast models. The results show that the proposed model has a great advantage in short-term forecasting of PM2.5 concentration.

A novel few-shot learning approach for wind power prediction applying secondary evolutionary generative adversarial network

The accuracy and stability of wind power forecasting are very important for the operation of wind farms. However, for the newly built wind farms without sufficient historical data, it is difficult to make a more accurate prediction. Therefore, it is of great significance to explore a method to improve the wind power prediction accuracy with no sufficient historical data available. In this paper, a novel prediction model is proposed to address the few-shot learning problem of wind power prediction in new-built wind farms based on secondary evolutionary generative adversarial networks (SEGAN) and dual-dimension attention mechanism (DDAM) assisted bidirectional gate recurrent unit (BiGRU). The SEGAN first introduces the secondary evolutionary learning paradigm into learning GAN, aiming to learn the marginal distribution of real data and generate high-quality realistic data to augment the training dataset. In the prediction stage, the DDAM is attempted to obtain a new input matrix with global weight allocation and improve the sensitivity of the BiGRU model to the key information of the input data. The proposed SEGAN-DDAM-BiGRU model is validated on the data from the Galicia Wind Farm in Sotavento and the experimental results show that the proposed model is applicative for short-term prediction of new-built wind farms.

How to select a best-value biological medicine? A practical model to support hospital pharmacists.

DisclaimerIn an effort to expedite the publication of articles related to the COVID-19 pandemic, AJHP is posting these manuscripts online as soon as possible after acceptance. Accepted manuscripts have been peer-reviewed and copyedited, but are posted online before technical formatting and author proofing. These manuscripts are not the final version of record and will be replaced with the final article (formatted per AJHP style and proofed by the authors) at a later time.PurposeWith the growing availability of biosimilars on the global market, clinicians and pharmacists have multiple off-patent biological products to choose from. Besides the competitiveness of the product’s price, other criteria should be considered when selecting a best-value biological. This article aims to provide a model to facilitate transparent best-value biological selection in the off-patent biological medicines segment.SummaryThe presented model was developed on the basis of established multicriteria decision analysis tools for rational and transparent medicine selection, ie, the System of Objectified Judgement Analysis and InforMatrix. Criteria for the model were informed by earlier research, a literature search, and evaluation by the authors. The developed model includes up-to-date guidance on criteria that can be considered in selection and provides background on the allocation of weights that may aid hospital pharmacists and clinicians with decision-making in practice. Three main categories of criteria besides price were identified and included in the model: (1) product-driven criteria, (2) service-driven criteria, and (3) patient-driven criteria. Product-driven criteria include technical product features and licensed therapeutic indications. Service-driven criteria consist of supply conditions, value-added services, and environment and sustainability criteria. Patient-driven criteria contain product administration elements such as ease of use and service elements such as patient support programs. Relative weighting of the criteria is largely context dependent and should in a given setting be determined at the beginning of the process.ConclusionThe practical model described here may support hospital pharmacists and clinicians with transparent and evidence-based best-value biological selection in clinical practice.

Comprehensive Rules-Based and Preferences Induced Weights Allocation in Group Decision-Making with BUI

Decision-makers’ subjective preferences can be well modeled using preference aggregation operators and related induced weights allocation mechanisms. However, when several different types of preferences occur in some decision environment with more complex uncertainties, repeated uses of preferences induced weights allocation sometimes become unsuitable or less reasonable. In this work, we discuss a common decision environment where several invited experts will offer their respective evaluation values for a certain object. There are three types of preferences which will significantly affect the weights allocations from experts. Instead of unsuitably performing preference induced weights allocation three times independently and then merging the results together using convex combination as some literatures recently did, in this work, we propose some organic and comprehensive rules-based screen method to first rule out some unqualified experts and then take preference induced weights allocation for the refined group of experts. A numerical example in business management and decision-making is presented to show the cognitive reasonability and practical feasibility.

Short-Term Traffic Flow Prediction via Improved Mode Decomposition and Self-Attention Mechanism Based Deep Learning Approach

Short-term traffic flow prediction (STFP) is one of the key technologies in Intelligence Transportation System (ITS). With the development of artificial intelligence technology, deep learning has been employed to STFP and certain achievements have been obtained. However, further improvement of STFP accuracy is constrained by the presence of noise, modal aliasing in the modal components and insufficient feature extraction of neural networks. Therefore, to more accurately capture the changing trend of traffic flow in different time periods, and increase the reliability and interpretability of the prediction models, improved variational mode decomposition (IVMD) and self-attention mechanism (SAM) based hybrid convolutional neural network (CNN) and long short term memory network (LSTM) are proposed for STFP in this study, benefited from the modal decomposition of IVMD and redistribution of the neural weights in CNN-LSTM networks by SAM, the proposed IVMD-CNN-LSTM-SAM effectively suppresses the influence of randomness and volatility of traffic flow, and accurately predict the short-term lane occupancy in the designated area. Furthermore, this study analyses the mechanism of SAM and IVMD in STFP, and proves the superiority of IVMD and SAM in signal decomposition with physical significance and weight allocation respectively. Therefore, the interpretability of the proposed neural network model is significantly improved. Eleven competitive neural networks forecasting methods are used as benchmarks and numerical studies based on actual traffic flow validate the accuracy and stability of the proposed IVMD-CNN-LSTM-SAM. Mean absolute percentage error and goodness of fit of the proposed model are 0.81% and 0.9968, respectively.

An ensemble learning prognostic method for capacity estimation of lithium-ion batteries based on the V-IOWGA operator

Capacity estimation is crucial for assessing the health statuses of lithium-ion batteries to develop better battery usage and maintenance strategies. However, it is difficult to satisfy multiple application situations in which each individual prognostic method has its own particular preconditions and application limitations. Thus, in this paper, an ensemble prognostic framework is proposed to integrate several individual prognostic methods to achieve better capacity estimation accuracy. In the proposed framework, a measurement- and calculation-based combined feature extraction method is first applied to the battery charging phase to better capture the extracted features that are related to the health statuses of lithium-ion batteries. Then, a novel validation dataset-based induced ordered weighted geometric averaging (V-IOWGA) operator is proposed to realize the time-varying weight allocation of each individual prognostic method to solve issue by which the performances of different prognostic algorithms vary in different phases. The advantages of the proposed ensemble model are verified on lithium-ion battery datasets from NASA PCoE and the University of Maryland CALCE Laboratory, and its prediction accuracy is better than that of other individual prognostic models. In addition, comparison experiments involving three types of ensemble models validate the superiority of the proposed model.

A concept for weighting sentiment phrase using deterministic solution of algebraic equations

Many text mining methods have used statistical information as text and language-independent procedures that are not deterministic. On the other hand, grammatical structure-based methods are limited to use in a certain language and text. We aim to suggest an algorithmic algebraic equation in a deterministic and nonprobabilistic way while maintaining the advantage of language independence. We propose a mathematical approach that transforms text and labels into a set of dumb equations. By solving the equations, each word is assigned a weight that can reflect the semantic information of that word, then we use the proposed algorithm to build a novel sentiment dictionary. We propose a purely mathematical approach to remove less informative tokens preprocessing steps and to pay attention to specific semantically rich words and contents. This is done by applying automatic weight allocation capability to understand each word?s meaning in the user?s notes in various texts. Solving a set of dumb equations is one of the strengths of the proposed algorithm. Finally, we evaluated the proposed algorithm in a sentiment analysis (SA) case study, and the Taboada database and its capability and efficiency in weight allocation and creation of automated dictionaries have been demonstrated. The numerical results show up to 15% of improvement in all parts of the database compared to existing methods.

Porcellio scaber Algorithm with t-Distributed Elite Mutation for Global Optimization

As the convergence accuracy of the Porcellio scaber algorithm (PSA) is low, this study proposes an improved algorithm based on the t-distribution elite mutation mechanism. First, the improved algorithm applies a t-distribution mutation to each dimension of the optimal solution of each generation. Using the dominant information of the optimal solution and t-distribution characteristics, the result of the mutation is then employed as the updated location of the selected porcellio; thus, the algorithm enhances the ability to jump out of local extreme values and improves the convergence speed. Second, the updated iterative rule of PSA may lead to the loss of information of the elite porcellio in the last generation. To solve this problem, the judgment mechanisms of the current and previous optimal solutions are included in the algorithm process. Finally, dynamic self-adaptive improvement is applied to the weight allocation parameters of PSA. Simulation results on 24 benchmark functions show that the improved algorithm has significant advantages in convergence accuracy, convergence speed, and stability when compared with basic PSA, PSO, GSA, and FPA. This indicates that the improved algorithm has certain advantages in terms of optimization. An optimal solution with good practicability is obtained by solving three practical engineering problems: three-bar truss, welded beam, and tension/compression-spring design.

A Heterogeneous Information-Based Multi-Attribute Decision Making Framework for Teaching Model Evaluation in Economic Statistics

A teaching model is a stable teaching procedure established under the guidance of certain teaching ideas or theories. As a methodological major in higher education, economic statistics cross various fields of natural science and social science, showing the characteristics of intersection, integration, and marginality. Therefore, this paper proposes a multi-attribute decision-making (MADM) framework for teaching model evaluation based on heterogeneous information. First, the attribute system of competition–academic research–master of knowledge–practical operation (CAMP) is constructed. Second, heterogeneous information is introduced in the process of teaching model evaluation; Third, a weight determination method based on a trust relationship of the fuzzy–social network is proposed, which provides a better solution to the problem of decision makers’ (DMs’) weight allocation in teaching model evaluation. Furthermore, a combined attribute weights determination method under an intuitionistic fuzzy number is constructed, which improves the shortcomings of the weight method in teaching model evaluation. Finally, through empirical research and stability analysis, the proposed evaluation framework has good effectiveness and feasibility, and policy suggestions for improvements to the economic statistical teaching model are then proposed.

Water quality assessment using optimized CWQII in Taihu Lake

To improve the rationality of weight allocation and weight proportion of different periods in the process of water quality assessment, the comprehensive water quality identification index (CWQII) model was optimized in this study. A new improved comprehensive water quality identification index (ICWQIIG) model based on game theory was established to combine subjective weight and objective weight. Based on ICWQIIG, an improved comprehensive water quality identification index (ICWQIIP) model with phased period combination weights was established to determine determined the weight proportion of phased periods was established. In this study, CWQII, ICWQIIG, and ICWQIIP were used to evaluate the water quality of seventeen sites in Taihu Lake in 2020. The models selected nine water quality parameters and six water quality indicators. The assessment results of water quality classification were between “slightly polluted” and “moderately polluted”. The pollution level on the east bank was lower than that on the west bank and north bank. Furthermore, it was also affected by seasonal change, water quality was worse in January and February but better in October and November. The mean value of Iwq calculated by CWQII, ICWQIIG, and ICWQIIP were 2.405, 2.833, and 3.000, respectively. The compared results showed that the ICWQIIG method can more representative identify the location of polluted water than CWQII. Moreover, the ICWQIIP method calculation results not only retained the representative polluted water samples in the ICWQIIG method but can also identify more pollution sites and worse polluted water bodies. Both ICWQIIG and ICWQIIP had high reliability and accuracy in assessment results, and ICWQIIP was more accurate under sufficient data conditions. This study can offer a scientific basis for local water resource management in Taihu Lake, while simultaneously proposing a science-based and valid methodology for the assessment of other similar water bodies.

Infrared and Visible Image Fusion with Deep Neural Network in Enhanced Flight Vision System

The Enhanced Flight Vision System (EFVS) plays a significant role in the Next-Generation low visibility aircraft landing technology, where the involvement of optical sensing systems increases the visual dimension for pilots. This paper focuses on deploying infrared and visible image fusion systems in civil flight, particularly generating integrated results to contend with registration deviation and adverse weather conditions. The existing enhancement methods push ahead with metrics-driven integration, while the dynamic distortion and the continuous visual scene are overlooked in the landing stage. Hence, the proposed visual enhancement scheme is divided into homography estimation and image fusion based on deep learning. A lightweight framework integrating hardware calibration and homography estimation is designed for image calibration before fusion and reduces the offset between image pairs. The transformer structure adopting the self-attention mechanism in distinguishing composite properties is incorporated into a concise autoencoder to construct the fusion strategy, and the improved weight allocation strategy enhances the feature combination. These things considered, a flight verification platform accessing the performances of different algorithms is built to capture image pairs in the landing stage. Experimental results confirm the equilibrium of the proposed scheme in perception-inspired and feature-based metrics compared to other approaches.

An Efficient AdaBoost Algorithm with the Multiple Thresholds Classification

Adaptive boost (AdaBoost) is a prominent example of an ensemble learning algorithm that combines weak classifiers into strong classifiers through weighted majority voting rules. AdaBoost’s weak classifier, with threshold classification, tries to find the best threshold in one of the data dimensions, dividing the data into two categories-1 and 1. However, in some cases, this Weak Learning algorithm is not accurate enough, showing poor generalization performance and a tendency to over-fit. To solve these challenges, we first propose a new Weak Learning algorithm that classifies examples based on multiple thresholds, rather than only one, to improve its accuracy. Second, in this paper, we make changes to the weight allocation scheme of the Weak Learning algorithm based on the AdaBoost algorithm to use potential values of other dimensions in the classification process, while the theoretical identification is provided to show its generality. Finally, comparative experiments between the two algorithms on 18 datasets on UCI show that our improved AdaBoost algorithm has a better generalization effect in the test set during the training iteration.

A Temporal–Spatial network embedding model for ICT supply chain market trend forecasting

Market trend forecasting for the information and communication technology (ICT) supply chain strengthens external regulation. The existing models treat the influence weight and time granularity equally, ignoring the timeliness and accuracy of trading information, which influences the result of prediction. In addition, these methods do not consider the topological and sector hierarchical relationship of enterprises. In this work, a Temporal–Spatial hybrid market trend forecasting model (TSMTF) is proposed. First, in time domain instead of modeling time-varying transaction amount, transaction event probability prediction is modeled by Hawkes​ process. Furthermore, the attention mechanism is used to optimize the accuracy of weight allocation. Second, in spacial domain, the topological dependency relation between the different enterprises with transaction information, share information, and sector information is constructed by network embedding. The experimental results show that the model is superior to other baseline algorithms in ICT data sets. The effectiveness and applicability of this method are verified by ablation experiments and examples of products in the communication industry, and the model provides a practical tool for the external management of ICT supply chain market supervision.