Search results

This paper presents a hybrid artificial intelligence (AI) system capable of integrating techniques of case‐based reasoning, rule induction and expert system, using them for knowledge acquisition and problem solving of selecting appropriate retaining wall systems at the project planning stage. The proposed hybrid system can eliminate the bottleneck of knowledge acquisition in developing a knowledge‐based system and improve the solution quality of the AI‐based system. Test results indicate that solutions generated by the proposed hybrid system are better than those generated by using a single technique.

Forecasts of commodity prices are vital issues to market participants and policy makers. Those of corn are of no exception, considering its strategic importance. In the present study, the authors assess the forecast problem for the weekly wholesale price index of yellow corn in China during January 1, 2010–January 10, 2020 period.

The authors employ the nonlinear auto-regressive neural network as the forecast tool and evaluate forecast performance of different model settings over algorithms, delays, hidden neurons and data splitting ratios in arriving at the final model.

The final model is relatively simple and leads to accurate and stable results. Particularly, it generates relative root mean square errors of 1.05%, 1.08% and 1.03% for training, validation and testing, respectively.

Through the analysis, the study shows usefulness of the neural network technique for commodity price forecasts. The results might serve as technical forecasts on a standalone basis or be combined with other fundamental forecasts for perspectives of price trends and corresponding policy analysis.

This paper aims to introduce a systematic computing and analytical procedure that is applied to the co-author network to identify the temporal evolution and growth of research collaborations in the area of e-governance. The empirical analysis of the temporal co-author network can trace the emerging authors and knowledge bursts over time.

The study applied social network theory to trace the author collaboration patterns in the domain of e-governance. Analysis of the co-author network using micro and macro parameters was done to trace the temporal evolution of the author collaborations.

E-governance is a multi-disciplinary research domain split over streams of management, politics, information technology and electronics. Hence, research collaborations play a significant role in its advancement. The knowledge sharing between individual authors, institutions and groups through research collaborations, resulting in extensive sharing of data, equipment and research methods, has boosted research activities and development in e-governance. In this paper, the authors systematically analyse the current scenario of research collaborations in the area of e-governance using co-author network to estimate its impact on the advancement of the field. The authors also analysed the temporal evolution of the co-author networks, which show remarkable growth of research collaborations in the domain of e-governance from the year 2000.

The co-author network analysis is only a proxy measure for the analysis of research collaborations. The names of the authors and the university affiliations used in the article are as retrieved from the research repository of Scopus. The degree, citations and other parameters related with authors have scope only within the environment of the co-author network used in the analysis. The criteria used in the study is limited to the degree of research collaborations and the number of co-authored publications in the giant component of the co-author network.

Institutions, authors and governments can trace and select suitable topics and choose research groups of co-authors over the world for future research collaborations in e-governance. The knowledge about the emerging and most discussed topics gives an overview of the global research trends of e-governance.

The study identified the evolution of creative collaborations in e-governance in the global perspective. The methodology introduced here is helpful to detect the proficient and productive author collaborations and the spectrum of related e-governance research topics associated with them. As the author collaborations can be mapped to the institutional and country-level collaborations, the information is helpful for researchers, institutions and governments to establish the best collaborations in e-governance research based on the author proficiency, collaboration patterns and research topics as per the requirements.

The paper introduces a novel research methodology using temporal analysis of co-author network to identify the evolution of research patterns and the associated research topics.

Based on the context of the Internet of Things (IoT), the territorial public emergency supplies will be networked, platform-based management, unified emergency dispatch. The problem of supplies dispatching in the “last kilometer” of emergency is solved, and the supplies needed in the disaster area are promptly delivered to the hands of the victims so that they can quickly be rescued after the disaster and to save valuable time for rapid rescue, which can greatly decrease casualties and property losses. This paper aims to discuss these issues.

By analyzing the shortage of existing emergency supplies dispatching research and taking all factors such as disaster area demand, social reserve, road conditions, mode of transport, loading limit, disaster area satisfaction rate and road capacity into consideration under the background of IoT, a variety of the territorial emergency supplies dispatching model with more rescue points, more affected areas are constructed. The objective function of the model is to aim in finding the shortest rescue time, giving the solution algorithm, and finally simulating the simulation case.

Based on the context of the IoT, the territorial public emergency supplies will be networked, platform-based management, unified emergency dispatch. Considering factors such as road conditions, modes of transport and road capacity, the authors construct a number of emergency rescue plans, multiple disaster scenarios and various emergency supplies dispatching models. The authors simulate the situation through simulation cases with the shortest time being the ultimate goal. The problem of supplies dispatching in the “last kilometer” of emergency is solved, and the supplies needed in the disaster area are promptly delivered to the hands of the victims so that they can quickly be rescued after the disaster and to save valuable time for rapid rescue, which can greatly decrease casualties and property losses.

This paper provides little research on the dispatch of emergency supplies. The problems of direct dispatch from the rescue point to the affected area and dispatch of supplies without relying on the arrival of emergency supplies at the rear are addressed. Therefore, this study does not focus on the arrival of emergency supplies at the rear but on direct dispatching issues during territorial public emergency supplies from the rescue point to the disaster point.

The tender documents, an essential data source for internet-based logistics tendering platforms, incorporate massive fine-grained data, ranging from information on tenderee, shipping location and shipping items. Automated information extraction in this area is, however, under-researched, making the extraction process a time- and effort-consuming one. For Chinese logistics tender entities, in particular, existing named entity recognition (NER) solutions are mostly unsuitable as they involve domain-specific terminologies and possess different semantic features.

To tackle this problem, a novel lattice long short-term memory (LSTM) model, combining a variant contextual feature representation and a conditional random field (CRF) layer, is proposed in this paper for identifying valuable entities from logistic tender documents. Instead of traditional word embedding, the proposed model uses the pretrained Bidirectional Encoder Representations from Transformers (BERT) model as input to augment the contextual feature representation. Subsequently, with the Lattice-LSTM model, the information of characters and words is effectively utilized to avoid error segmentation.

The proposed model is then verified by the Chinese logistic tender named entity corpus. Moreover, the results suggest that the proposed model excels in the logistics tender corpus over other mainstream NER models. The proposed model underpins the automatic extraction of logistics tender information, enabling logistic companies to perceive the ever-changing market trends and make far-sighted logistic decisions.

(1) A practical model for logistic tender NER is proposed in the manuscript. By employing and fine-tuning BERT into the downstream task with a small amount of data, the experiment results show that the model has a better performance than other existing models. This is the first study, to the best of the authors' knowledge, to extract named entities from Chinese logistic tender documents. (2) A real logistic tender corpus for practical use is constructed and a program of the model for online-processing real logistic tender documents is developed in this work. The authors believe that the model will facilitate logistic companies in converting unstructured documents to structured data and further perceive the ever-changing market trends to make far-sighted logistic decisions.

With the rapid-growing house market in the past decade, the purpose of this paper is to study the important issue of house price information flows among 12 major cities in China, including Shanghai, Beijing, Xiamen, Shenzhen, Guangzhou, Hangzhou, Ningbo, Nanjing, Zhuhai, Fuzhou, Suzhou and Dongguan, during the period of June 2010 to May 2019.

The authors approach this issue in both time and frequency domains, latter of which is facilitated through wavelet analysis and by exploring both linear and nonlinear causality under the vector autoregressive framework.

The main findings are threefold. First, in the long run of the time domain and for timescales beyond 16 months of the frequency domain, house prices of all cities significantly affect each other. For timescales up to 16 months, linear causality is weaker and is most often identified for the scale of four to eight months. Second, while nonlinear causality is seldom determined in the time domain and is never found for timescales up to four months, it is identified for scales beyond four months and particularly for those beyond 32 months. Third, nonlinear causality found in the frequency domain is partly explained by the volatility spillover effect.

Results here should be of use to policymakers in certain policy analysis.

This paper aims to examine whether rewards incentives of non-state-owned enterprises can settle the matters of motivation lack, strained labor relations and frequent labor-capital conflicts and realize co-win cooperation of workers, enterprises and the society.

Based on the data of 1,617 questionnaires in 257 enterprises, this research reveals the total rewards factors that affect the labor motivation of non-stated-owned enterprises in China and improve labor productivity by adopting the hierarchical linear regression analysis and multi-group path analysis, and establishes a new model of win-win cooperation between labor and capital and the society through the incentive function of these elements by stimulating the enthusiasm of workers, improving labor productivity, increasing profits, expanding capital accumulation and absorbing labor force.

The authors have discovered that in general the main incentives that stimulate the enthusiasm of employees are the factors of performance and recognition and development and career opportunity in total rewards. The factor of benefits also has a significant incentive effect on employees in the western area of China, migrant workers with lower education and male employees, but negative effect on the post-1990s employees in non-state-owned enterprises. However, the compensation factor should be used with caution when encouraging employees in eastern region and the post-1980s. The total rewards factors of development and career opportunities and the performance and the recognition and benefits should be used to motivate workers to improve labor productivity, increase corporate profits and absorb more labor force, which is a long-term solution to win-win cooperation between labor and capital and social sustainable development. It is an important way to increase profits and absorb more labor force by increasing employee’s human capital investment and improving labor proficiency of employees under age 45. The conclusions provide new effective management methods for non-state-owned enterprises in China.

As a consequence, it will encourage employees to improve labor productivity and increase profits and thus absorb more labor force, if we use these factors of performance and recognition, development and career opportunity and benefits integratedly, we will find a permanent solution that the two sides of the labor and management and the society enjoy a win-win cooperation.

The research will provide theoretical basis for non-state-owned enterprises to apply a new and effective management style so that we can establish a win-win cooperation between the labor and management. What’s more, the research will develop the Dual Economy Theory of Lewis and the employment theory of Keynes and will also provide a theoretical basis for the realization of Taylor’s harmonious industrial relations.

This study aims to analyze information on vessel traffic between the two Koreas with a probability distribution for each route/vessel type. The study will then conduct an estimate for maritime transport patterns of inter-Korean trade in the future. To analyze the flow of inter-Korean coastal shipping, this study conducted visualization analysis of shipping status between North and South Korea by year, ship type, and port using navigation data of three years from Port Logistics Information System (Port-MIS) sources during 2006 to 2008, which saw the most active exchanges between the two governments. Also, this study analyzes shipping status between the two governments as a probability distribution for each port and provides the prospects for future maritime transport for inter-Korean trade by means of Bayesian Networks and simulation. The results of the analysis are as follows: i) when North-South routes are reopened, the import volume for sand from North Korea will be increased; ii) investment in the modernization of ports in North Korea is required so that shipping companies can generate profit through economies of scale; iii) the number of the operating vessels including container ships between the two governments is expected to increase like when the tensions and conflict on the Korean Peninsula was release, especially between Busan port in South Korea and Nampo port in North Korea; and iv) among container ships, transshipment containers imported and exported through Busan Port will be shipped to North Korea by feeder transportation.

Autonomous driving depends on the collection, processing and analysis of environmental information and vehicle information. Environmental perception and processing are important prerequisite for the safety of self-driving of vehicles; it involves road boundary detection, vehicle detection, pedestrian detection using sensors such as laser rangefinder, video camera, vehicle borne radar, etc.

Subjected to various environmental factors, the data clock information is often out of sync because of different data acquisition frequency, which leads to the difficulty in data fusion. In this study, according to practical requirements, a multi-sensor environmental perception collaborative method was first proposed; then, based on the principle of target priority, large-scale priority, moving target priority and difference priority, a multi-sensor data fusion optimization algorithm based on convolutional neural network was proposed.

The average unload scheduling delay of the algorithm for test data before and after optimization under different network transmission rates. It can be seen that with the improvement of network transmission rate and processing capacity, the unload scheduling delay decreased after optimization and the performance of the test results is the closest to the optimal solution indicating the excellent performance of the optimization algorithm and its adaptivity to different environments.

In this paper, the results showed that the proposed method significantly improved the redundancy and fault tolerance of the system thus ensuring fast and correct decision-making during driving.

Gives a bibliographical review of the finite element methods (FEMs) applied for the linear and nonlinear, static and dynamic analyses of basic structural elements from the theoretical as well as practical points of view. The range of applications of FEMs in this area is wide and cannot be presented in a single paper; therefore aims to give the reader an encyclopaedic view on the subject. The bibliography at the end of the paper contains 2,025 references to papers, conference proceedings and theses/dissertations dealing with the analysis of beams, columns, rods, bars, cables, discs, blades, shafts, membranes, plates and shells that were published in 1992‐1995.