scholarly journals PM2.5 Concentration Forecasting in Industrial Parks Based on Attention Mechanism Spatiotemporal Graph Convolutional Networks

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Qingtian Zeng ◽  
Chao Wang ◽  
Geng Chen ◽  
Hua Duan
Keyword(s):  
Mean Squared Error ◽  
Attention Mechanism ◽  
Percentage Error ◽  
Industrial Park ◽  
Learning Technology ◽  
Concentration Data ◽  
Convolutional Network ◽  
Industrial Parks ◽  
The Impact ◽  
Pm2.5 Concentration

Industrial parks are one of the main sources of air pollution; the ability to forecast PM2.5, the main pollutant in the industrial park, is of great significance to the health of the workers in the industrial park and environmental governance, which can improve the decision-making ability of environmental management. Most of the existing PM2.5 concentration forecast methods lack the ability to model the dynamic temporal and spatial correlations of PM2.5 concentration. In an industrial park environment, in order to improve the accuracy of PM2.5 concentration forecast, based on deep learning technology, this paper proposes a spatiotemporal graph convolutional network based on the attention mechanism (STAM-STGCN) to solve the PM2.5 concentration forecast problem. When constructing the adjacency matrix, we not only use the Euclidean distance between sites but also consider the impact of wind fields and the impact of pollution sources near the nodes. In the process of model construction, we first use the spatiotemporal attention mechanism to capture the dynamic spatiotemporal correlations in PM2.5 data. In the spatiotemporal convolution module, we use graph convolutional neural networks to capture spatial features and standard convolution to describe temporal features. Finally, the output module adjusts the output shape of the data to produce the final forecast result. In this paper, the mean absolute error (MAE), root mean squared error (RMSE), and mean absolute percentage error (MAPE) are used as the performance evaluation metrics of the model, and the Dongmingnan Industrial Park atmospheric dataset is used to verify the effectiveness of the proposed algorithm. The experimental results show that our STAM-STGCN model can more fully capture the spatial-temporal characteristics of PM2.5 concentration data; compared with the most advanced model in the comparison model, the RMSE can be improved about 24.2%, the MAE is improved about 35.8%, and the MAPE is improved about 34.6%.

International arrivals forecasting for Australian airports and the impact of tourism marketing expenditure

2016 ◽  
Vol 23 (2) ◽  
pp. 403-428 ◽  
Author(s):  
Wai Hong Kan Tsui ◽  
Faruk Balli
Keyword(s):  
Mean Squared Error ◽  
Absolute Error ◽  
Percentage Error ◽  
Endogenous Factors ◽  
Tourism Marketing ◽  
Passenger Demand ◽  
Volatility Models ◽  
International Tourist ◽  
The Impact ◽  
The Empirical Analysis

An airport’s international passenger arrivals are susceptible to exogenous and endogenous factors (such as economic conditions, flight services, fluctuations and shocks). Accurate and reliable airport passenger demand forecasts are imperative for policymaking and planning by airport and airline management as well as by tourism authorities and operators. This article employs the Box–Jenkins SARIMA, SARIMAX and SARIMAX/EGARCH volatility models to forecast international passenger arrivals for the eight key Australian airports (Adelaide, Brisbane, Cairns, Darwin, Gold Coast, Melbourne, Perth and Sydney). Monthly international tourist arrivals between January 2006 and September 2012 are used for the empirical analysis. All the forecasting models are highly accurate with the lower values of mean absolute percentage error, mean absolute error and root mean squared error. The findings suggest that the international passenger arrivals of Australian airports are affected by positive and negative shocks and tourism marketing expenditure is also a significant factor influencing the majority of Australian airports’ international passenger arrivals.

scholarly journals A complex of factors of increasing the competitiveness of industrial park residents

2018 ◽  
Vol 193 ◽  
pp. 05076
Author(s):  
E.A. Tikhanov ◽  
V.V. Krivorotov ◽  
P.V. Chepur ◽  
A.A. Tarasenko ◽  
A.A. Gruchenkova
Keyword(s):  
Performance Indicators ◽  
Industrial Park ◽  
Considerable Influence ◽  
Effective Mechanism ◽  
Competitive Position ◽  
Local Factors ◽  
Industrial Enterprises ◽  
Industrial Parks ◽  
Regional Factors ◽  
The Impact

In the paper, industrial parks are considered as the most dynamically developing, universal and effective format of the investment infrastructure organization. A whole range of advantages for enterprises resident in industrial parks when placing production in such investment sites actualizes the need to study industrial parks as an effective mechanism to increase the competitiveness of Russian industrial enterprises and to identify a set of factors that contribute to the growth of competitiveness of industries located within the boundaries of industrial parks. Based on the analysis of the aggregate of advantages of industrial park residents, the authors proposed a system of factors of increasing their competitiveness, which includes three aggregated blocks: "intra-park" factors, local factors and regional factors. A considerable influence of each block of factors on key performance indicators and the competitive position of the resident enterprises of industrial parks has been discovered. The basis for the development of a system of indices for the functioning of industrial parks has been created, which makes it possible to quantify the impact of factors proposed by the authors of the system.

scholarly journals MODELING THE DEVELOPMENT OF INDUSTRIAL PRODUCTION OF SMALL BUSINESSES IN THE ECONOMY OF THE REGION THROUGH THE CREATION OF INDUSTRIAL PARKS AND TECHNOPARKS

2020 ◽  
Vol 1 (31(58)) ◽  
pp. 23-26
Author(s):  
Svetlana Vladimirovna Radygina ◽  
Yuliya Vasilievna Chipeeva
Keyword(s):  
Industrial Production ◽  
Small Businesses ◽  
Industrial Park ◽  
State Support ◽  
Foreign Experience ◽  
Industrial Sites ◽  
Industrial Parks ◽  
The Creation ◽  
The Impact

The article discloses the concept of an "industrial park," provides examples of industry parks and statistics on Russia. It also considered the domestic and foreign experience of forming ready-made industrial sites for business and possible measures of state support for industrial parks and their residents. It is characterized by the impact of the creation of an industrial park on the development of industrial production in the region.

scholarly journals Short-Term Load Forecasting Using Convolutional Neural Networks in COVID-19 Context: The Romanian Case Study

Energies ◽  
2021 ◽  
Vol 14 (13) ◽  
pp. 4046
Author(s):  
Andrei M. Tudose ◽  
Irina I. Picioroaga ◽  
Dorian O. Sidea ◽  
Constantin Bulac ◽  
Valentin A. Boicea
Keyword(s):  
Power Systems ◽  
Mean Squared Error ◽  
Load Forecasting ◽  
Absolute Error ◽  
Percentage Error ◽  
Linear Regression Method ◽  
Short Term ◽  
Short Term Load Forecasting ◽  
The Mean ◽  
The Impact

Short-term load forecasting (STLF) is fundamental for the proper operation of power systems, as it finds its use in various basic processes. Therefore, advanced calculation techniques are needed to obtain accurate results of the consumption prediction, taking into account the numerous exogenous factors that influence the results’ precision. The purpose of this study is to integrate, additionally to the conventional factors (weather, holidays, etc.), the current aspects regarding the global COVID-19 pandemic in solving the STLF problem, using a convolutional neural network (CNN)-based model. To evaluate and validate the impact of the new variables considered in the model, the simulations are conducted using publicly available data from the Romanian power system. A comparison study is further carried out to assess the performance of the proposed model, using the multiple linear regression method and load forecasting results provided by the Romanian Transmission System Operator (TSO). In this regard, the Mean Squared Error (MSE), the Mean Absolute Error (MAE), the Mean Absolute Percentage Error (MAPE), and the Root Mean Square Error (RMSE) are used as evaluation indexes. The proposed methodology shows great potential, as the results reveal better error values compared to the TSO results, despite the limited historical data.

scholarly journals KGGCN: Knowledge-Guided Graph Convolutional Networks for Distantly Supervised Relation Extraction

2021 ◽  
Vol 11 (16) ◽  
pp. 7734
Author(s):  
Ningyi Mao ◽  
Wenti Huang ◽  
Hai Zhong
Keyword(s):  
Prior Knowledge ◽  
Structural Information ◽  
Relation Extraction ◽  
Attention Mechanism ◽  
Knowledge Graph ◽  
Convolutional Network ◽  
Convolutional Networks ◽  
Lexical Resource ◽  
Sentence Level ◽  
The Impact

Distantly supervised relation extraction is the most popular technique for identifying semantic relation between two entities. Most prior models only focus on the supervision information present in training sentences. In addition to training sentences, external lexical resource and knowledge graphs often contain other relevant prior knowledge. However, relation extraction models usually ignore such readily available information. Moreover, previous works only utilize a selective attention mechanism over sentences to alleviate the impact of noise, they lack the consideration of the implicit interaction between sentences with relation facts. In this paper, (1) a knowledge-guided graph convolutional network is proposed based on the word-level attention mechanism to encode the sentences. It can capture the key words and cue phrases to generate expressive sentence-level features by attending to the relation indicators obtained from the external lexical resource. (2) A knowledge-guided sentence selector is proposed, which explores the semantic and structural information of triples from knowledge graph as sentence-level knowledge attention to distinguish the importance of each individual sentence. Experimental results on two widely used datasets, NYT-FB and GDS, show that our approach is able to efficiently use the prior knowledge from the external lexical resource and knowledge graph to enhance the performance of distantly supervised relation extraction.

scholarly journals System of industrial park functioning indicators reflecting the effect of competitiveness factors of resident enterprises

2018 ◽  
Vol 193 ◽  
pp. 01036
Author(s):  
Petr Chepur ◽  
Aleksandr Tarasenko ◽  
Evgeniy Tikhanov ◽  
Vadim Krivorotov ◽  
Alesya Gruchenkova
Keyword(s):  
Quantitative Assessment ◽  
Development Program ◽  
Industrial Park ◽  
Competitive Advantages ◽  
Industrial Parks ◽  
Regional Factors ◽  
The One ◽  
Structural Blocks ◽  
The Impact ◽  
Further Development

Recently, industrial parks, demonstrating their effectiveness, have turned into a locomotive of business development providing the resident enterprises with a whole range of competitive advantages. In order to analyze the impact of factors enhancing the competitiveness of residents of industrial parks, the authors have developed a comprehensive system of indicators for the functioning of the industrial park which provide a quantitative assessment and a comprehensive account of the aggregate of "intra-park", local and regional factors. Considering the requirements formulated by the authors, a system of indicators for the functioning of the industrial park has been developed, which includes two structural blocks: indicators of the industrial park performance and indicators of the industrial park's base area potential. Options of practical use of the formed system of indicators are proposed, on the one hand, to establish targets for further development of the industrial park based on the comparison of the studied industrial park with the projects of competitors, and on the other hand, to design an industrial park development program that ensures the competitiveness of the site residents.

scholarly journals Economic and environmental assessment of water reuse in industrial parks: case study based on a Model Industrial Park

2020 ◽  
Vol 10 (4) ◽  
pp. 475-489 ◽  
Author(s):  
Birte Boysen ◽  
Jorge Cristóbal ◽  
Jens Hilbig ◽  
Almut Güldemund ◽  
Liselotte Schebek ◽  
...  
Keyword(s):  
Water Reuse ◽  
Economies Of Scale ◽  
Wastewater Reuse ◽  
Industrial Park ◽  
Water Shortages ◽  
Economic Dimension ◽  
Reuse Water ◽  
Industrial Parks ◽  
Reuse Options ◽  
The Impact

Abstract Industrial wastewater reuse is a major measure to mitigate the depletion of available freshwater resources in the catchments around industrial areas and to prevent possible future water shortages and the resulting problems for industry, economy and society. Combining a set of environmental aspects and economic aspects of different wastewater treatment technologies, the authors developed a model-based approach for planning and evaluating water reuse concepts in industrial parks. This paper is based on an exemplary Model Industrial Park. The results based on data primarily calculated for Germany show that, for the majority of the indicators, the installation of the Water Reuse Plant seems to be beneficial for all examined reuse options. Considering the economic dimension, due to economies of scale, reuse options with larger volumes of treated water are preferable since the costs per m3 of reuse water are reduced by up to 33%. On the other hand, the environmentally preferable option depends on the respective indicator, e.g. for freshwater eutrophication, the higher the reuse factor, the lower the impact, leading to reductions between 8 and 12%. For climate change, the best option is dependent on the reuse purpose leading to reductions between 8 and 52%.

scholarly journals PM2.5 Concentration Prediction Based on CNN-BiLSTM and Attention Mechanism

Algorithms ◽  
2021 ◽  
Vol 14 (7) ◽  
pp. 208
Author(s):  
Jinsong Zhang ◽  
Yongtao Peng ◽  
Bo Ren ◽  
Taoying Li
Keyword(s):  
Neural Network ◽  
Air Quality ◽  
Dropout Rate ◽  
Attention Mechanism ◽  
Quality Data ◽  
Short Term ◽  
Concentration Data ◽  
Test Set ◽  
Term Prediction ◽  
Pm2.5 Concentration

The concentration of PM2.5 is an important index to measure the degree of air pollution. When it exceeds the standard value, it is considered to cause pollution and lower the air quality, which is harmful to human health and can cause a variety of diseases, i.e., asthma, chronic bronchitis, etc. Therefore, the prediction of PM2.5 concentration is helpful to reduce its harm. In this paper, a hybrid model called CNN-BiLSTM-Attention is proposed to predict the PM2.5 concentration over the next two days. First, we select the PM2.5 concentration data in hours from January 2013 to February 2017 of Shunyi District, Beijing. The auxiliary data includes air quality data and meteorological data. We use the sliding window method for preprocessing and dividing the corresponding data into a training set, a validation set, and a test set. Second, CNN-BiLSTM-Attention is composed of the convolutional neural network, bidirectional long short-term memory neural network, and attention mechanism. The parameters of this network structure are determined by the minimum error in the training process, including the size of the convolution kernel, activation function, batch size, dropout rate, learning rate, etc. We determine the feature size of the input and output by evaluating the performance of the model, finding out the best output for the next 48 h. Third, in the experimental part, we use the test set to check the performance of the proposed CNN-BiLSTM-Attention on PM2.5 prediction, which is compared by other comparison models, i.e., lasso regression, ridge regression, XGBOOST, SVR, CNN-LSTM, and CNN-BiLSTM. We conduct short-term prediction (48 h) and long-term prediction (72 h, 96 h, 120 h, 144 h), respectively. The results demonstrate that even the predictions of the next 144 h with CNN-BiLSTM-Attention is better than the predictions of the next 48 h with the comparison models in terms of mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R2).

scholarly journals An Empirical Analysis of the Impact of Local Officials’ Characteristics on Environmental Governance Performance

2021 ◽  
Vol 251 ◽  
pp. 02079
Author(s):  
Feng Zhu
Keyword(s):  
Environmental Governance ◽  
Bachelor's Degree ◽  
Graduate Degree ◽  
Lasso Regression ◽  
Concentration Data ◽  
Party Committee ◽  
Local Officials ◽  
The Impact ◽  
Pm2.5 Concentration

This paper uses China’s 2010-2018 city-level panel data and the annual average PM2.5 concentration data processed by ArcGIS software and uses the LASSO regression model to empirically analyze the impact of local officials’ characteristics environmental governance performance. The results show that younger officials, municipal party committee secretaries who graduated from ordinary colleges and universities, municipal party committee secretaries who have been vacated, and general mayors are more conducive to environmental governance; those who have worked in state-owned enterprises, are older, have studied The secretary of the municipal party committee and a mayor who is promoted from the grassroots in economics and management, the secretary of the municipal party committee with a bachelor’s degree, the mayor who has a graduate degree, the mayor who has committed corruption and discipline, and the mayors who graduated from the party school are not conducive to the jurisdiction Environmental governance. The research results of this article help to understand the role of individual differences in local officials in environmental governance, and can also provide reference suggestions for cadres and personnel reform.

Rural Industrialization in Korea: Policy Program, Performance and Rural Entrepreneurship

2013 ◽  
pp. 49-73
Author(s):  
Suh Chong-Hyuk ◽  
Kim Hyong-Mo
Keyword(s):  
Rural Development ◽  
Farm Income ◽  
Industrial Park ◽  
Income Source ◽  
Rural Industrialization ◽  
Rural Entrepreneurship ◽  
Industrial Parks ◽  
Policy Program ◽  
Industrialization Policy ◽  
Stagnation Period

From the early seventies the Korean Government has adopted a rural industrialization policy as an important measure for promoting rural development. It has been perceived that through this measure the over-concentration of economic activity would be controlled and dispersed. Development of rural industrialization has passed through three different phases: i) the period of promoting rural cottage-type industries (1960-80); ii) the period of rural industrial park establishment; and iii) a stagnation period after the early 1990s. Throughout the overall period government policy changed from an individual project-oriented approach to a diversified and comprehensive policy program. The policy programs, such as the development of rural industrial parks, off-farm income source development and vocational training programs for farm youths, have helped in promoting rural industrialization. On the other hand, policy programs promoting rural out-migration and unbalanced regional development policy have impacted negatively on rural industrialization. Presently one of the serious policy issues facing rural industries is how to secure a young labor force and how to promote rural entrepreneurship. In addition, rural development efforts by local government and authorities are necessary in order to increase investment from urban-based entrepreneur firms. Keywords:Rural industrialization, farm household, off-farm income, rural development, rural industrial park, rural

Sign in / Sign up

Export Citation Format

Share Document