Search results

The purpose of this work is to bridge FL and blockchain technology through designing a blockchain-based smart agent system architecture and applying in FL. and blockchain technology through designing a blockchain-based smart agent system architecture and applying in FL. FL is an emerging collaborative machine learning technique that trains a model across multiple devices or servers holding private data samples without exchanging their data. The locally trained results are aggregated by a centralized server in a privacy-preserving way. However, there is an assumption where the centralized server is trustworthy, which is impractical. Fortunately, blockchain technology has opened a new era of data exchange among trustless strangers because of its decentralized architecture and cryptography-supported techniques.

In this study, the author proposes a novel design of a smart agent inspired by the smart contract concept. Specifically, based on the proposed smart agent, a fully decentralized, privacy-preserving and fair deep learning blockchain-FL framework is designed, where the agent network is consistent with the blockchain network and each smart agent is a participant in the FL task. During the whole training process, both the data and the model are not at the risk of leakage.

A demonstration of the proposed architecture is designed to train a neural network. Finally, the implementation of the proposed architecture is conducted in the Ethereum development, showing the effectiveness and applicability of the design.

The author aims to investigate the feasibility and practicality of linking the three areas together, namely, multi-agent system, FL and blockchain. A blockchain-FL framework, which is based on a smart agent system, has been proposed. The author has made several contributions to the state-of-the-art. First of all, a concrete design of a smart agent model is proposed, inspired by the smart contract concept in blockchain. The smart agent is autonomous and is able to disseminate, verify the information and execute the supported protocols. Based on the proposed smart agent model, a new architecture composed by these agents is formed, which is a blockchain network. Then, a fully decentralized, privacy-preserving and smart agent blockchain-FL framework has been proposed, where a smart agent acts as both a peer in a blockchain network and a participant in a FL task at the same time. Finally, a demonstration to train an artificial neural network is implemented to prove the effectiveness of the proposed framework.

The purpose of this paper is to estimate the real urbanization level in China so as to provide a measurement that can be compared with the international level.

Taking into consideration 300m residents living in the administrative towns (300m residents here are referred to the population in administrative towns, including those in all counties), the gap between the urbanization rate of China and that of the world average becomes much wider.

China, however, implements the administrative system of government at the central, provincial, municipal, county and township levels. By city, it means the jurisdiction at and above the level of county, which includes the municipality directly under the central government, prefecture-level municipal and county. By town, it means the jurisdiction below the level of county (including the Chengguan Town, or capital town, where the county government is located) and exclusive of rural townships.

China has witnessed rapid development for 40 years since the reform and opening up in 1978. Nowadays, China has already stepped into the period of post-industrialization, with its urbanization rate (UR) of permanent population reaching 58.58 percent. However, on the basis of registered population, the UR is 43.37 percent, which is not only far below the average level of 81.3 percent in high-income countries, but also lower than the average of 65.8 percent in upper middle-income countries which are comparable to China in terms of per capita income. (The classification of state income level is based on the data of national income per capita and division standards in 2016 from the World Bank, in which annual revenue per capita in high-income countries reaches over US$12,736 and that in upper middle-income countries between US$4,126 and US$12,735.)

To achieve the Sustainable Development Goals (SDGs) in the era of Logistics 4.0, machine learning (ML) techniques and simulations have emerged as highly optimized tools. This study examines the operational dynamics of a supply chain (SC) in Vietnam as a case study utilizing an ML simulation approach.

A robust fuel consumption estimation model is constructed by leveraging multiple linear regression (MLR) and artificial neural network (ANN). Subsequently, the proposed model is seamlessly integrated into a cutting-edge SC simulation framework.

This paper provides valuable insights and actionable recommendations, empowering SC practitioners to optimize operational efficiencies and fostering an avenue for further scholarly investigations and advancements in this field.

This study introduces a novel approach assessing sustainable SC performance by utilizing both traditional regression and ML models to estimate transportation costs, which are then inputted into the discrete event simulation (DES) model.

Transfer relations represent analytical solutions of the linear theory of circular arches, relating each one of the kinematic and static variables at an arbitrary cross-section to the kinematic and static variables at the initial cross-section. The purpose of this paper is to demonstrate the significance of the transfer relations for structural analysis by means of three examples taken from civil engineering.

The first example refers to an arch bridge, the second one to the vault of a metro station and the third one to a real-scale test of a segmental tunnel ring.

The main conclusions drawn from these three examples are as follows: increasing the number of hangers/columns of the investigated arch bridge entails a reduction of the maximum bending moment of the arch, allowing it to approach, as much as possible, the desired thrust-line behavior; compared to the conventional in situ cast method, a combined precast and in situ cast method results in a decrease of the maximum bending moment of an element of the vault of the studied underground station by 46%; and the local behavior of the joints governs both the structural convergences and the bearing capacity of the tested segmental tunnel ring.

The three examples underline that the transfer relations significantly facilitate computer-aided engineering of circular arch structures, including arch bridges, vaults of metro stations and segmental tunnel rings.

A better understanding of the processes that shape households’ adaptation decisions is essential for developing pertinent policies locally, thereby enabling better adaptation across scales and multiple stakeholders. This paper aims to examine the determinants of household decisions to adapt, it is also possible to target factors that facilitate or constrain adaptation. This helps to identify key components of current adaptive capacity, which leads to important insights into households’ competence to adapt in the future.

This paper takes a full-pledged approach examining factors and processes that shape households’ climate adaptation decision-making in rural Cambodia at three levels: adaptation status, adaptation intensity and choices of adaptation strategy. The three-stage analyses are materialized by applying the double hurdle model and multivariate probit model, which provides a potential way to systematically assess household adaptation decision-making in rural settings.

Results show a high level of involvement in adaptation among local households who are facing multiple stressors including climatic risks. The findings suggest that perceived climate change influence households’ decisions in both adaptation status and intensity. Access to financial credit, farmland size, water availability and physical asset holdings are identified as key factors promoting the adoption of more adaptation measures. To facilitate adaptation, collective effort and support at community level is important in providing knowledge based climate information dissemination and early warning systems. Public sector support and development aid programs should focus on positive triggers for targeted community and household adaptation.

The study, to the authors’ best knowledge, is one of the first studies to investigate the determinants of local adaptation decision-making systematically in Cambodia. It also provides a comprehensive approach to improve understanding of adaptation decision-making processes by exploring how various capital assets are associated with different stages of adaptation decisions. The findings contribute to policy implications enlightening adaptation planning at multi-scales with knowledge of key factors, which enhance local adaptive capacity to reduce climate change vulnerability.

Currently, China’s economy is in the critical phase of transforming economic development patterns and replacing old growth drivers with new ones. Whether it can successfully overcome the “middle-income trap” has become a significant issue attracting wide attention.

Driven by underlying digital technologies such as artificial intelligence, blockchain, cloud computing and big data, the fourth industrial revolution featuring the booming digital economy has provided significant opportunities for China’s economy to “overtake” and overcome the “middle-income trap”. The transformation of economic development pattern, the optimization of industrial structure, and the change of growth drivers, brought by the deep integration of digital and real economies are the keys to leaping over the “middle-income trap”.

From the supply side, the digital economy can improve the quality and efficiency of the supply side and promote the supply-side structural reform and economic growth from the following three aspects: First, promote the quality, efficiency and diversification of the supply system; second, promote networking, opening-up and synergy in the innovation system and third, promote the socialization, modularization and flexibility of production pattern. From the demand side, the digital economy can boost the new drivers of the “troika” of economic growth consisting of consumption, exports and investment by changing the market investment direction, promoting consumption upgrade and fostering export strengths. However, once these two attributes interact with each other, especially when data is combined with capital, the most adhesive factor in the market economy, a series of new social relations will then be produced based on the technical attribute, resulting in significant adjustments in social relations, involving both positive and negative externalities.

To overcome the “middle-income trap”, it is necessary to adapt to the laws of economic evolution and promote a fundamental change in economic growth drivers; boost the high-quality development of the digital economy by strengthening the support role of data in the digital economy; and accelerate digital industrialization and industrial digitalization to realize the integration of digital and real economies.

Vision, audition, olfactory, tactile and taste are five important senses that human uses to interact with the real world. As facing more and more complex environments, a sensing system is essential for intelligent robots with various types of sensors. To mimic human-like abilities, sensors similar to human perception capabilities are indispensable. However, most research only concentrated on analyzing literature on single-modal sensors and their robotics application.

This study presents a systematic review of five bioinspired senses, especially considering a brief introduction of multimodal sensing applications and predicting current trends and future directions of this field, which may have continuous enlightenments.

This review shows that bioinspired sensors can enable robots to better understand the environment, and multiple sensor combinations can support the robot’s ability to behave intelligently.

The review starts with a brief survey of the biological sensing mechanisms of the five senses, which are followed by their bioinspired electronic counterparts. Their applications in the robots are then reviewed as another emphasis, covering the main application scopes of localization and navigation, objection identification, dexterous manipulation, compliant interaction and so on. Finally, the trends, difficulties and challenges of this research were discussed to help guide future research on intelligent robot sensors.