Search results

The purpose of this paper is to present a Differential Immune Clone Clustering Algorithm (DICCA) to solve image segmentation.

DICCA combines immune clone selection and differential evolution, and two populations are used in the evolutionary process. Clone reproduction and selection, differential mutation, crossover and selection are adopted to evolve two populations, which can increase population diversity and avoid local optimum. After extracting the texture features of an image and encoding them with real numbers, DICCA is used to partition these features, and the final segmentation result is obtained.

This approach is applied to segment all sorts of images into homogeneous regions, including artificial synthetic texture images, natural images and remote sensing images, and the experimental results show the effectiveness of the proposed algorithm.

The method presented in this paper represents a new approach to solving clustering problems. The novel method applies the idea two populations are used in the evolutionary process. The proposed clustering algorithm is shown to be effective in solving image segmentation.

The purpose of this paper is to obtain the optimal N₂/Ar ratio parameters for preparing Ta (C, N) coating. Three coatings with different N₂/Ar ratios were prepared on the TA15 substrate, and their effects on the wear properties of the coatings were discussed.

Ta(C, N) coatings with three different N₂/Ar ratios were prepared on TA15 substrates using the double cathode glow metallurgical plasma alloying technique (DGMPA) using a step-by-step diffusion method.

With the increase of N₂/Ar flow ratio, the hardness and elastic modulus of the coating first increase and then decrease. Compared with the S1 sample (N₂/Ar gas ratio 25: 75) and the S3 sample (N₂/Ar gas ratio 75: 25), the S2 sample (N₂/Ar gas ratio 50: 50) has better mechanical properties, with hardness increased by 48.45% and 6.8%, respectively, and elastic strain ratio increased by 22.8% and 28.5%, respectively. Moreover, the wear degree of the S2 sample is less than other samples. The wear rate of the S2 sample was 32.4% lower than the S3 sample at 300°C and 14.3% lower than the S3 sample at 500°C. Therefore, the S2 sample has the best mechanical properties and the best high temperature wear resistance.

Ta(C, N) coatings were prepared by DGMPA technology, and the wear mechanism of Ta(C, N) coatings with different N₂/Ar ratios was investigated to reduce the wear rate.

Patent trade recommendations necessitate recommendation interpretability in addition to recommendation accuracy because of patent transaction risks and the technological complexity of patents. This study designs an interpretable knowledge-aware patent recommendation model (IKPRM) for patent trading. IKPRM first creates a patent knowledge graph (PKG) for patent trade recommendations and then leverages paths in the PKG to achieve recommendation interpretability.

First, we construct a PKG to integrate online company behaviors and patent information using natural language processing techniques. Second, a bidirectional long short-term memory network (BiLSTM) is utilized with an attention mechanism to establish the connecting paths of a company — patent pair in PKG. Finally, the prediction score of a company — patent pair is calculated by assigning different weights to their connecting paths. The semantic relationships in connecting paths help explain why a candidate patent is recommended.

Experiments on a real dataset from a patent trading platform verify that IKPRM significantly outperforms baseline methods in terms of hit ratio and normalized discounted cumulative gain (nDCG). The analysis of an online user study verified the interpretability of our recommendations.

A meta-path-based recommendation can achieve certain explainability but suffers from low flexibility when reasoning on heterogeneous information. To bridge this gap, we propose the IKPRM to explain the full paths in the knowledge graph. IKPRM demonstrates good performance and transparency and is a solid foundation for integrating interpretable artificial intelligence into complex tasks such as intelligent recommendations.

45 steel is a common material for the manufacture of various components such as shafts or gears. However, its poor surface properties often limit its applications. The purpose of this paper is to find a way to enhance the surface performance of 45 steel, which is expected to improve the wear resistance of 45 steel.

Double glow plasma surface metallurgy technique was used to prepare hafnium carbide (HfC) coatings on the surface of the 45 steel with two preparation process; one is to diffuse two elements together, while the other is to diffuse step by step. The scanning electronic microscopy and the X-ray diffraction were used to analyze the morphology and phase of the HfC coatings. And then the wear tests were carried out for this coating.

Coating diffused step by step shows better performance; it has a 15-µm alloyed layer which is uniform and dense and its hardness can reach up to 1326.5 Vickers-hardness (HV). While the coating fabricated by diffusing elements together owns a 10-µm alloyed layer and its hardness is 1204.1 HV. According to the wear test results, both coatings have a protective effect on the substrate and the coating prepared by step-by-step diffusion process has less wear volume, indicating that it possesses better friction reduction.

A new method which diffuses elements together was successfully used to prepare compound HfC coating, which can reduce the cost of coating preparation and improve the efficiency of coating preparation.

The purpose of this paper is to prepare Ti(C,N) coatings on TA15 treated and not treated by shot peening using double glow plasma alloying technique. The effect of shot peening on the wear behavior of Ti(C,N) coatings is discussed.

The Ti(C,N) coatings were prepared by double glow plasma alloying technique on two different TA15 substrate; one is shot peened and the other is not.

Ti(C,N) coating on SP-treated TA15 was thicker and denser, and the grain size was smaller compared with that on original TA15. Compared with the Ti(C,N) coating on original TA15, the wear resistance of that on SP-treated TA15 is improved. Ti(C,N) coating on SP-treated TA15 showed higher nanohardness and bearing capacity than that on original TA15.

For double glow plasma alloying technique, surface quality, surface activity and other factors will have influence on the thickness and density of the coating. The wear mechanisms of Ti(C,N) coating on original TA15 are serious abrasive wear and oxidation wear. However, the wear mechanism of Ti(C,N) coating on SP-treated TA15 is slightly oxidation wear.

The peer review history for this article is available at: https://publons.com/publon/10.1108/ILT-07-2020-0283/

Soy protein has been considered as a renewable and environmentally friendly source of adhesives. The purpose of this paper is to investigate a new approach for making a soy protein adhesive modified by SiO₂ nanoparticles.

The objective of this investigation was to evaluate the adhesive properties by determining the viscosity, wettability and shear strength of soy protein adhesive. The effects of nano‐SiO₂ content, wood surface roughness and processing pressure on shear strength between soy protein adhesive and wood were investigated. Four nano‐SiO₂ contents (0, 0.5, 1 and 2 percent), two wood surface roughness (40 and 280 grits), and two processing pressure (1 and 2 MPa) were tested. Adhesive performance was evaluated based on the maximum force required for shearing the adhesive bond between cherry wood pieces.

The modified soy protein adhesives by SiO₂ nanoparticles showed a significant enhancement in dry strength with nano‐SiO₂ content of 1 percent. The mechanism appears to be related to the increased interaction between adhesive and wood and the elimination of voids on the wood surface by SiO₂ nanoparticles.

The adhesive resins used in the present context was soy protein isolate, not from commercially available soy flour. The wet strength was not satisfactory. Further study is needed to solve this problem.

The method developed provided a simple and practical solution to improving the shear strength of soy protein adhesives.

The enhancement method for adhesion strength of soy protein was novel and could find numerous applications in wood industry, avoiding formaldehyde emission and reducing the dependence on petroleum products.

Social media facilitates consumer exchanges on product opinions and provides comprehensive knowledge of online products. The interaction between consumers and e-retailers evolves into a collective set of dynamics within a complex system. Agent-based modeling is well suited to stimulate such complex systems. The purpose of this paper is to integrate agent-based model and technique for order performance by similarity to ideal solution (TOPSIS) to simulate decision behaviors of e-retailers in competitive online markets.

An agent-based network model using the TOPSIS driven by actual price data is developed. The authors ran an experimental model to simulate interactions between online consumers and e-retailers and to record simulation data. A nonparametric test is used to conduct data analysis and evaluate the sensibility of parameters.

Simulation results showed that different profits could be obtained for various brands under different social network structures. E-retailers could achieve more profits through cross-selling than single-selling; however, the highest profits can be achieved when some adopt cross-selling, whereas others use single-selling. From a game perspective, the equilibrium for price-adjustment frequency can be determined from the simulation data. Thus, price adjustment differences significantly affect e-retailer profit.

This study provides new insights into the evolutionary dynamics of online markets. This work also indicates how to build an integrated simulation model with an agent-based model and TOPSIS and how to use an integrated simulation model and interpret its results.

The purpose of this study is to undertake an evaluation of the resilient capacity of the infrastructure systems in the city of Wuhan. This evaluation focuses on the ability of the infrastructure to cope with extreme weather from multiple dimensions and to propose effective interventions against such risks.

This research draws on a review and synthesis of the theory of resilience and adopts the literature induction method to build an evaluation index for five urban systems, namely: roads; water supply and drainage; energy and power; urban disaster reduction; and communications. Index data from the period of 1990–2019 are combined with the views of experts from Wuhan and analyzed using principal component analysis (PCA) to calculate the weightings of the five urban systems. A fuzzy comprehensive evaluation method is then used to investigate the resilient capacity of these five urban infrastructure systems in the city.

Generally, the results show that the resilience of the infrastructure systems in Wuhan are at a high level. Based on the results, the communications and roads systems are found to have higher levels of resilience, while the disaster mitigation system is found to have a relatively low level of resilience. Recommendations are suggested to help improve resilience and prioritize investments in the development of the city's infrastructure systems.

The development of these specific indicators and quantitative requirements have not been studied in detail, so a more comprehensive, systematic evaluation of quantitative indicators and methods of urban infrastructure resilience is still required. In addition, the research on the resilience of urban infrastructure under extreme weather is still in its infancy, and it is essential to further increase the quantitative assessment of the resilience of urban infrastructure under construction. This will also be indispensable information in the subsequent implementation of a resilient planning process.

This research builds a rigorous and reliable evaluation model that avoids any subjective bias in the results and represents a new approach to evaluate the resilience of the infrastructure systems in the city of Wuhan, which could be applied to other cities.

Flooding is China’s most frequent and catastrophic natural hazard, causing extensive damage. The aim of this study is to develop a comprehensive assessment of urban flood risk in the Hubei Province of China, focusing on the following three issues: (1) What are the factors that cause floods? (2) To what extent do these factors affect flood risk management? (3) How to build an effective comprehensive assessment system that can be used to reduce flood risk?

This study combines expert opinion and evidence from the extent literature to identify flood risk indicators across four dimensions: disaster risk, susceptibility, exposure and prevention and mitigation. The Criteria Importance Through Intercriteria Correlation (CRITIC) and the Grey Relational Analysis (RA)-based Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) decision-making approach were applied to calculate the weighting of factors and develop a model of urban flood risk. Then, ArcGIS software visualizes risk levels and spatial distribution in the cities of Hubei Province; uncertainty analysis verified method accuracy.

The results show that there are significant differences in the level of urban flood risk in Hubei Province, with cities such as Tianmen, Qianjiang, Xiantao and Ezhou being at high risk, while cities such as Shiyan, Xiangyang, Shennongjia, Yichang, Wuhan and Huanggang are at lower flood risk.

The innovative method of combining CRITIC-GRA-TOPSIS reduces the presence of subjective bias found in many other flood risk assessment frameworks. Regional data extraction and uncertainty analysis enhance result reliability, supporting long-term decision-making and urban planning. Overall, the methodological approach developed provides an advanced, highly effective and efficient analysis and visualization of flood risk. This study deepens the understanding of flood risk assessment mechanisms and more broadly supports the development of resilient cities.

The purpose of this study is to prepare WC-10Co-4Cr coatings using two processes of plasma spraying and high-velocity oxygen fuel (HVOF) spraying. The decarburization behaviors of the different processes are analyzed individually. The microstructural characteristics of the as-sprayed coatings are presented and the wear mechanisms of the different WC–10Co–4Cr coatings are discussed in detail.

The WC–10Co–4Cr coatings were formed on the surface of Q235 steel by plasma and HVOF spraying.

Plasma spraying causes more decarburizing decomposition of the WC phase than HVOF spraying. In the plasma spraying process, η(Cr25Co25W8C2) phase appears and the C content decreases from the top surface of the coating to the substrate.

In this study, two WC–10Co–4Cr coatings on Q235 steel prepared by plasma and HVOF spraying were compared with respect to the sliding wear behavior.

The wear mechanisms of the plasma- and HVOF-sprayed coatings were abrasive and oxidation, respectively.