Search results

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.

Mean absolute percentage error (MAPE) is the primary forecast evaluation metric in hospitality and tourism research; however its main shortcoming is that it is asymmetric. The asymmetry occurs due to over or under forecasts that introduce bias into forecast evaluation. This study aims to explore the nature of asymmetry and designs a new measure, one that reduces the asymmetric properties while maintaining MAPE’s scale-free and intuitive interpretation characteristics.

The study proposes and tests a new forecasting accuracy measure for hospitality revenue management (RM). A computer simulation is used to assess and demonstrate the problem of asymmetry when forecasting with MAPE, and the new measures’ (MSapeMER, that is, Mean of Selectively applied Absolute Percentage Error or Magnitude of Error Relative to the estimate) ability to reduce it. The MSapeMER’s effectiveness is empirically validated by using a large set of hotel forecasts.

The study demonstrates the ability of the MSapeMER to reduce the asymmetry bias generated by MAPE. Furthermore, this study demonstrates that MSapeMER is more effective than previous attempts to correct for asymmetry bias. The results show via simulation and empirical investigation that the error metric is more stable and less swayed by the presence of over and under forecasts.

It is recommended that hospitality RM researchers and professionals adopt MSapeMER when using MAPE to evaluate forecasting performance. The MSapeMER removes the potential bias that MAPE invites due to its calculation and presence of over and under forecasts. Therefore, forecasting evaluations may be less affected by the presence of over and under forecasts and their ability to bias forecasting results.

Hospitality RM should adopt this measure when MAPE is used, to reduce biased decisions driven by the “asymmetry of MAPE.”

The MAPE error metric exhibits an asymmetry problem, and this paper proposes a more effective solution to reduce biased results with two major methodological contributions. It is first to systematically study the characteristics of MAPE’s asymmetry, while proposing and testing a measure that considerably reduces the amount of asymmetry. This is a critical contribution because MAPE is the primary forecasting metric in hospitality and tourism studies. The second methodological contribution is a procedure developed to “quantify” the asymmetry. The approach is demonstrated and allows future research to compare asymmetric characteristics among various accuracy measures.

Statistical modeling has been successfully applied to integrated circuit (IC) solder joint inspection. However, there are some inherent problems in previous statistical modeling methods. This paper aims to propose an adaptive statistical modeling method to further improve the inspection performance for IC solder joints.

First, different pixels in the IC solder joint image were modeled by different templates, each of which was composed of the hue value of the pixel and a proposed template significance factor. Then, the potential defect image was obtained by adaptive template matching and the potential defect threshold for each pixel. It was noted that the number of templates, matching distance threshold, potential defect threshold and updating rate were adaptively updated during model training. Finally, the trained statistical model was used to inspect the IC solder joints by means of defect degree.

Experimental results indicated that the proposed adaptive schemes greatly contributed to the inspection performance of statistical modeling. Also, the proposed inspection method achieved better performance compared with some state-of-the-art inspection methods.

The proposed method offers a promising approach for IC solder joint inspection, which establishes different numbers of templates constructed by pixel values and template significance factors for different pixels. Also, some important parameters were adaptively updated with the updating of the model, which contributed to the inspection performance of the model.

The focus of industrial cluster innovation lies in the cooperation between enterprises and universities/scientific research institutes to make a theoretical breakthrough in the system and mechanism of industrial cluster network. Under the theoretical framework of cluster network, industrial structure can be optimized and upgraded, and enterprise benefit can be improved. Facing the increasing proliferation and multi-structured enterprise data, how to obtain potential and high-quality innovation features will determine the ability of industrial cluster network innovation, as well as the paper aims to discuss these issues.

Based on complex network theory and machine learning method, this paper constructs the structure of “three-layer coupling network” (TLCN), predicts the innovation features of industrial clusters and focuses on the theoretical basis of industrial cluster network innovation model. This paper comprehensively uses intelligent information processing technologies such as network parameters and neural network to predict and analyze the industrial cluster data.

From the analysis of the experimental results, the authors obtain five innovative features (policy strength, cooperation, research and development investment, centrality and geographical position) that help to improve the ability of industrial clusters, and give corresponding optimization strategy suggestions according to the result analysis.

Building a TLCN structure of industrial clusters. Exploring the innovation features of industrial clusters. Establishing the analysis paradigm of machine learning method to predict the innovation features of industrial clusters.

The defect detection problem of color-patterned fabric is still a huge challenge due to the lack of manual defect labeling samples. Recently, many fabric defect detection algorithms based on feature engineering and deep learning have been proposed, but these methods have overdetection or miss-detection problems because they cannot adapt to the complex patterns of color-patterned fabrics. The purpose of this paper is to propose a defect detection framework based on unsupervised adversarial learning for image reconstruction to solve the above problems.

The proposed framework consists of three parts: a generator, a discriminator and an image postprocessing module. The generator is able to extract the features of the image and then reconstruct the image. The discriminator can supervise the generator to repair defects in the samples to improve the quality of image reconstruction. The multidifference image postprocessing module is used to obtain the final detection results of color-patterned fabric defects.

The proposed framework is compared with state-of-the-art methods on the public dataset YDFID-1(Yarn-Dyed Fabric Image Dataset-version1). The proposed framework is also validated on several classes in the MvTec AD dataset. The experimental results of various patterns/classes on YDFID-1 and MvTecAD demonstrate the effectiveness and superiority of this method in fabric defect detection.

It provides an automatic defect detection solution that is convenient for engineering applications for the inspection process of the color-patterned fabric manufacturing industry. A public dataset is provided for academia.

In recent years, rough set theory has evolved as one of the most promising classification techniques. One of the cardinal uses of rough set theory is its application for rule generation. The purpose of this paper is to propose a real-time fabric inspection technique. This work deals with the multi-class classification of fabric defects using rough set theory.

This technique focuses on the classification of fabric defects using the effective decision rules envisaged by rough set theory. In the proposed work, the six features of 50 images have been used for multiclass classification of fabric defects.

In this work, 40 images were used for generation of decision rules and 10 unseen images were used for validation out of which nine images are accurately predicted by the proposed technique.

The proposed method accurately identified 9 out of 10 testing defects. The obtained decision rules provide an insight about the classification method which ensures that the prediction accuracy can be improved further by framing more robust decision rules with the help of a large training data set. Thus, with the support of modern computational systems this method is potent in getting recognition from the textile industry as a real-time classification technique.

Online brand communities (OBCs) are important platforms to obtain consumers' ideas. The purpose of this study is to examine how peer influence and consumer contribution behavior simulate innovative behaviors in OBCs to increase idea quality.

Using a firm-hosted popular online brand community – Xiaomi Community (MIUI), the authors collected a set of data from 6567 consumers and then used structural equation modeling (SEM) and fuzzy-set qualitative comparative analysis (fsQCA) to empirically test the impact of peer influence and consumer contribution behaviors on idea quality in OBCs.

The results of this study show that both peer influence breadth and depth have a positive effect on idea adoption and peer recognition, wherein proactive contribution behavior positively mediates these relationships, and responsive contribution behavior negatively mediates the impact of peer influence breadth and peer influence depth on peer recognition. A more detailed analysis using the fsQCA method further identifies four types of antecedent configurations for better idea quality.

Based on the attention-based view and the theory of learning by feedback, this study explores the factors that affect idea quality in the context of social networks and extends the research of peer influence in the digital age. The paper helps improve our understanding of how to promote customer idea quality in OBCs.

This study aims to clarify the impact of agriculture–tourism integration (ATI) on in situ urbanization (ISURB) of rural residents, to highlight the role of industrial integration in the process of China's ISURB and to provide industrial integration suggestions for promoting urbanization quality in Chinese counties.

By sorting out the panel data of China's 1868 counties, the evaluation index system of ISURB was constructed. Difference in difference (DID) and spatial Durbin-difference in difference (SDM-DID) model is used for estimate the relationship between ATI and ISURB.

First, ATI can improve ISURB by 11.4% higher than other regions. Second, theoretical analysis model of ATI on ISURB is constructed from four aspects of “drive–push–pull–block.” The results show that ATI can promote ISURB by increasing upgrading of rural industries, rural employment demand and income capacity, whereas ATI may inhibit ISURB by reducing farmland. Third, considering changes in institutional, hard and soft factors, rural collective economy, information infrastructure and digital finance all promote positive impact of ATI on ISURB. Fourth, ATI will produce spillover effects on ISURB in neighboring regions, which is more pronounced in the central and western regions.

This study lacks quantification of ATI, so future studies are encouraged to further quantify ATI at the county level.

This study has policy significance for constructing ATI demonstration counties and promoting ISURB in China's counties.

It is of great practical value to promote China's ISURB. By stimulating ATI, it can improve income and employment capacity of rural residents and stimulate ISURB of China.

This study enriches the theoretical and practical research on industrial integration behaviors during the process of ISURB.

1. Use county data to measure in situ urbanization (ISURB)

2. Agriculture–tourism integration (ATI) can increase ISURB

3. Constructs a “drive-push-pull-block” model to explain the influence mechanism

4. Use spatial Durbin-difference in difference (SDM-DID) models

5. Consider collective economy, rural information infrastructure and digital finance

Use county data to measure in situ urbanization (ISURB)

Agriculture–tourism integration (ATI) can increase ISURB

Constructs a “drive-push-pull-block” model to explain the influence mechanism

Use spatial Durbin-difference in difference (SDM-DID) models

Consider collective economy, rural information infrastructure and digital finance

People often look to the opinions and actions of others to guide their food choices, especially when they are uncertain or unfamiliar with a particular food. This influence can be positive or negative depending on the context and can have an impact on food consumption and health outcomes.

The paper analysed data from 500 young adult consumers in China and employed a multi-study design to examine various aspects of social proof and herd behaviour in food choices. Experiment 1 examined the influence of testimonials from an influential person on buying decisions and eating behaviour. Experiment 2 explored whether herd behaviour drives food options. Experiment 3 assessed the influence of social proof on food choices. Chi-square tests of independence were conducted to examine the relationship between social proof and food choice, as well as herd behaviour and food decision-making. Several logit regression analyses were performed to identify the factors that drive consumers' susceptibility to social proof and herding.

The results indicated that the source of feedback, whether from an influential person or a family member, did not have a statistically significant effect on the likelihood of following the food guide recommendations. The preference for a healthier food option was stronger than following the herd. In contrast, social proof in the form of reviews and ratings influenced participants' choices. The paper highlights the usefulness for stakeholders and policymakers seeking to promote healthier eating habits.

The originality lies in its comprehensive approach, combining multiple experiments and analytical methods.

This paper seeks to investigate the differences in the teachers’ professional development (TPD) by mentorship in workplace. The authors examined the role of mentorship in the PD of teachers and conducted a meta-analysis of pertinent empirical data.

Using data from over 2,900 individuals, 66 experiments and 12 countries, the authors presented a meta-analysis of the association between workplace mentorship and TPD.

The authors concluded that mentoring activities could boost the TPD to some extent. It contributes positively to the discipline of science and language, kindergarten, individual mentoring and curriculum research. In addition, the periodicity should not exceed 1 year.

The results of the meta-analysis are restricted to short-term mentorship activities, and the sample size is modest. Building upon the findings from the literature review and meta-analysis, the authors delineated a research agenda for prospective investigations. This includes an imperative for further exploration into the nexus between mentoring and the PD of educators.

Based on the available literature and meta-analysis findings, the authors developed a framework for the “Experts in the classroom” TPD pattern.

This is the first meta-analysis evaluating the association between mentorship and TPD.