Search results

Automatic segmentation of brain tumor from medical images is a challenging task because of tumor's uneven and irregular shapes. In this paper, the authors propose an attention-based nested segmentation network, named DAU-Net. In total, two types of attention mechanisms are introduced to make the U-Net network focus on the key feature regions. The proposed network has a deep supervised encoder–decoder architecture and a redesigned dense skip connection. DAU-Net introduces an attention mechanism between convolutional blocks so that the features extracted at different levels can be merged with a task-related selection.

In the coding layer, the authors designed a channel attention module. It marks the importance of each feature graph in the segmentation task. In the decoding layer, the authors designed a spatial attention module. It marks the importance of different regional features. And by fusing features at different scales in the same coding layer, the network can fully extract the detailed information of the original image and learn more tumor boundary information.

To verify the effectiveness of the DAU-Net, experiments were carried out on the BRATS 2018 brain tumor magnetic resonance imaging (MRI) database. The segmentation results show that the proposed method has a high accuracy, with a Dice similarity coefficient (DSC) of 89% in the complete tumor, which is an improvement of 8.04 and 4.02%, compared with fully convolutional network (FCN) and U-Net, respectively.

The experimental results show that the proposed method has good performance in the segmentation of brain tumors. The proposed method has potential clinical applicability.

The precise segmentation of brain tumors is the most important and crucial step in their diagnosis and treatment. Due to the presence of noise, uneven gray levels, blurred boundaries and edema around the brain tumor region, the brain tumor image has indistinct features in the tumor region, which pose a problem for diagnostics. The paper aims to discuss these issues.

In this paper, the authors propose an original solution for segmentation using Tamura Texture and ensemble Support Vector Machine (SVM) structure. In the proposed technique, 124 features of each voxel are extracted, including Tamura texture features and grayscale features. Then, these features are ranked using the SVM-Recursive Feature Elimination method, which is also adopted to optimize the parameters of the Radial Basis Function kernel of SVMs. Finally, the bagging random sampling method is utilized to construct the ensemble SVM classifier based on a weighted voting mechanism to classify the types of voxel.

The experiments are conducted over a sample data set to be called BraTS2015. The experiments demonstrate that Tamura texture is very useful in the segmentation of brain tumors, especially the feature of line-likeness. The superior performance of the proposed ensemble SVM classifier is demonstrated by comparison with single SVM classifiers as well as other methods.

The authors propose an original solution for segmentation using Tamura Texture and ensemble SVM structure.

To ensure the stable operation of ironmaking process and the quality and output of sinter, the multi-objective optimization of sintering machine batching process was carried out.

The purpose of this study is to establish a multi-objective optimization model with iron taste content and batch cost as targets, constrained by field process requirements and sinter quality standards, and to propose an improved balance optimizer algorithm (LILCEO) based on a lens imaging anti-learning mechanism and a population redundancy error correction mechanism. In this method, the lens imaging inverse learning strategy is introduced to initialize the population, improve the population diversity in the early iteration period, avoid falling into local optimal in the late iteration period and improve the population redundancy error correction mechanism to accelerate the convergence rate in the early iteration period.

By selecting nine standard test functions of BT series for simulation experiments, and comparing with NSGA-?, MOEAD, EO, LMOCSO, NMPSO and other mainstream optimization algorithms, the experimental results verify the superior performance of the improved algorithm. The results show that the algorithm can effectively reduce the cost of sintering ingredients while ensuring the iron taste of sinter, which is of great significance for the comprehensive utilization and quality assurance of sinter iron ore resources.

An optimization model with dual objectives of TFe content and raw material cost was developed taking into account the chemical composition and quality indicators required by the blast furnace as well as factors such as raw material inventory and cost constraints. This model was used to adjust and optimize the sintering raw material ratio. Addressing the limitations of existing optimization algorithms for sintering raw materials including low convergence accuracy slow speed limited initial solution production and difficulty in practical application we proposed the LILCEO algorithm. Comparative tests with NSGA-III MOEAD EO LMOCSO and NMPSO algorithms demonstrated the superiority of the proposed algorithm. Practical applications showed that the proposed method effectively overcomes many limitations of the current manual raw material ratio model providing scientific and stable decision-making guidance for sintering production operations.

The face-centered cubic structured single-phase FeCoNiCrMn high-entropy alloys (HEAs) were prepared to study the friction and wear behavior of HEAs under MoS₂-oil lubrication.

FeCoNiCrMn alloys were subjected to ball-on-disc reciprocating sliding against the GCr15 ball. L₂₅(5⁶) orthogonal wear tests were designed for velocity V_rel (4.167-20.833 mm/s), load F_N (10-50 N), temperature T (RT-140 °C) and time t (5-20 min). Based on orthogonal test results, multivariate repeated measures ANOVA was performed, and further comparative experiments were conducted for V_rel, F_N and T. Energy dispersive spectrometer and scanning electron microscope were applied to characterize the surface morphology of wear scar and its element distribution.

V_rel, F_N and t exerted the most significant influence (p < 0.01) on the average friction coefficient f. V_rel and F_N were identified as the momentous effect (p < 0.01) on wear volume ΔV. T (≥50 °C) had positive correlation with f and ΔV, and both V_rel and F_N correlated negatively with f. The dominant abrasive wear was attributed to the large hardness difference of the friction pair. Fatigue wear and delamination wear were experienced at higher speeds (V_rel  ≥ 12.5 mm/s) and loading levels (F_N ≥ 40 N). Elevated temperature weakens the lubrication effect of MoS₂-oil and the mechanical properties of FeCoNiCrMn matrix, intensifying abrasive wear.

This study is expected to provide references for exploration on the wear behavior of single-phase HEAs under complex working conditions with lubrication and hence will help develop the application of HEAs in practical engineering.

The peer review history for this article is available at: https://publons.com/publon/10.1108/ILT-08-2019-0303

This chapter examines the similarities and differences between the concepts of transformational leadership as developed within North America and the Confucian idea of transformation. It argues that Confucian tradition encompasses the essential elements embedded in the concept of transformational leadership. The former differentiates from the latter in its deeper degree of transformation, emphasis on morality and culture, and its focus on transformation from the inside outwards. The two greatest educators in Chinese history, Confucius and Cai Yuanpei, are evaluated in terms of their transformational leadership qualities in the Western sense. By looking at Confucius and Cai Yuanpei as successful transformational leaders, the chapter identifies four important factors from Chinese cases that may contribute to the success of this type of leadership. Implications of this comparison are discussed as they may inform the knowledge, research and practices of transformational leadership.

The purpose of this article is to put forward China’s Hanyu Pinyin word guanli as an academic basic term to the world.

GUANLI as an academic basic term, which holds multiple meanings of several English words, such as management, administration, governance, etc. As a basic term, GUANLI, derived several words, such as GUANLIOLOGY, GUANLIST/GUANLIER and GUANLIWORK/GUANLIJOB, to precisely and exactly convey the Chinese GUANLI ideas. It is the historical mission and opportunity for the authors to research and establish the Chinese School of Modern GUANLI Science (CSMGS).

It is inevitably necessary to build the combined Chinese–Western discourse system of GUANLI science (CCWDSGS). Some other research results of CSMGS are also presented in this paper.

It is needless to say that there are still lots of problems in China, including in the GUANLI field. These problems will gradually be solved in China’s reform and development that takes place continuously. New problems will come up while old problems are being solved and settled; problems producing in a loop, problems solving in a loop, this is the dialectics. The authors have full confidence in solving problems, as well as in China’s development and future.

Practice comes first and then it is followed by theory. The authors first have the “China Model”, followed by the “Chinese School” consequently. The “China Model” has already been there, and the “Chinese School” relies on the author’s proactive research and innovation. It is just the right time for the authors to study and create the CSMGS. This is the historical mission and opportunity awaited by contemporary Chinese.

The main goal of this paper is to present a synthetic multiple criteria group decision-making (MCGDM) methodology for assessing the enterprise digital maturity with linear Diophantine fuzzy (LDF) setting.

This paper utilizes the presented LDF generalized Dombi operator to aggregate assessment information of experts. The developed combined weight model through merging the rank sum (RS) model and symmetry point of criterion (SPC) method is used to ascertain the comprehensive importance of criterion. The evaluation based on distance from average solution (EDAS) approach based upon regret theory (RT) is presented to achieve the sorting of candidate enterprises.

Firstly, the proposed method has strong stability. Secondly, the proposed method takes into consideration the psychological behavior of experts during the decision-making process which further enhances the rationality of the decision results. Finally, the proposed method integrates expert and criterion weight determination models which provides a practical evaluation framework for assessing the digital maturity of enterprises. The research outcomes confirm that the proposed approach fails to resolve the decision problems with unknown weight information flexibly, but also reflect the psychological behavior of expert in decision process. The presented weight approach also provides a rational algorithm to ascertain the weight more accurate.

A composite LDF group decision-making approach is presented by aggregating the proposed generalized Dombi operator, combined weight model and the EDAS model, which make the outcome more reasonable. Sensitivity analysis and comparison study are conducted to reflect the superiority of the proposed approach.

The purpose of this paper is to focus on the performance of three typical nonlinear least-squares estimation algorithms in atmospheric density model calibration.

The error of Jacchia-Roberts atmospheric density model is expressed as an objective function about temperature parameters. The estimation of parameter corrections is a typical nonlinear least-squares problem. Three algorithms for nonlinear least-squares problems, Gauss–Newton (G-N), damped Gauss–Newton (damped G-N) and Levenberg–Marquardt (L-M) algorithms, are adopted to estimate temperature parameter corrections of Jacchia-Roberts for model calibration.

The results show that G-N algorithm is not convergent at some sampling points. The main reason is the nonlinear relationship between Jacchia-Roberts and its temperature parameters. Damped G-N and L-M algorithms are both convergent at all sampling points. G-N, damped G-N and L-M algorithms reduce the root mean square error of Jacchia-Roberts from 20.4% to 9.3%, 9.4% and 9.4%, respectively. The average iterations of G-N, damped G-N and L-M algorithms are 3.0, 2.8 and 2.9, respectively.

This study is expected to provide a guidance for the selection of nonlinear least-squares estimation methods in atmospheric density model calibration.

The study analyses the performance of three typical nonlinear least-squares estimation methods in the calibration of atmospheric density model. The non-convergent phenomenon of G-N algorithm is discovered and explained. Damped G-N and L-M algorithms are more suitable for the nonlinear least-squares problems in model calibration than G-N algorithm and the first two algorithms have slightly fewer iterations.

This paper aims to investigate the actual impact, mechanism and internal and external environmental adjustment effect of ESG performance on the persistence of green innovation using data from China’s A-share manufacturing listed companies from 2009 to 2021.

Panel data regression models are used to explore the effect of ESG performance of manufacturing enterprises on the persistence of green innovation. To examine the mechanism of ESG performance affecting the persistence of green innovation of manufacturing enterprises, this paper refers to the research of Wen and Ye (2014) and constructs an analysis framework of intermediary effect.

This research was funded by Shandong Provincial Natural Science Foundation, grant number ZR2023MG075 & ZR2024QE171.

There are a few more limitations to this study that might be discussed from the following angles: first, due to data availability, this paper examines the persistence of green innovation from the output perspective. The authors can expand the data sources in the future and investigate the input-output combinations in green innovation as a means of understanding its sustainability. Second, the mechanism studied in this paper includes management costs, entry of green investors and risk-taking ability. In fact, it is possible that ESG performance influences green innovation persistence in other ways as well; these can be investigated more in the future.

First, it concentrates on the persistence of green innovation in manufacturing enterprises, surpassing the quantitative aspect and thereby broadening the research scope. Second, by including the “management expense ratio,” “green investor entry” and “risk-taking” as mediating factors, the study delves deeper into the mechanisms through which ESG performance impacts the persistence of green innovation in manufacturing enterprises, further broadening the research scope. Third, this research incorporates the internal and external environments encountered by manufacturing enterprises into the analytical framework to investigate their adjustment effects in the process of ESG performance influencing persistent green innovation, thus widening the research perspective. Fourth, this study introduces the subdimensions of ESG performance, specifically environmental responsibility, social responsibility and corporate governance, and assesses their impacts on the persistence of green innovation in manufacturing enterprises, thus enriching the research narrative.