Search results

Automation of detecting cracked surfaces on buildings or in any industrially manufactured products is emerging nowadays. Detection of the cracked surface is a challenging task for inspectors. Image-based automatic inspection of cracks can be very effective when compared to human eye inspection. With the advancement in deep learning techniques, by utilizing these methods the authors can create automation of work in a particular sector of various industries.

In this study, an upgraded convolutional neural network-based crack detection method has been proposed. The dataset consists of 3,886 images which include cracked and non-cracked images. Further, these data have been split into training and validation data. To inspect the cracks more accurately, data augmentation was performed on the dataset, and regularization techniques have been utilized to reduce the overfitting problems. In this work, VGG19, Xception and Inception V3, along with Resnet50 V2 CNN architectures to train the data.

A comparison between the trained models has been performed and from the obtained results, Xception performs better than other algorithms with 99.54% test accuracy. The results show detecting cracked regions and firm non-cracked regions is very efficient by the Xception algorithm.

The proposed method can be way better back to an automatic inspection of cracks in buildings with different design patterns such as decorated historical monuments.

This paper aims to disentangle Chinese-English-rich resources linguistic and speaker timbre features, achieving cross-lingual speaker transfer for Cambodian.

This study introduces a novel approach: the construction of a cross-lingual feature disentangler coupled with the integration of time-frequency attention adaptive normalization to proficiently convert Cambodian speaker timbre into Chinese-English without altering the underlying Cambodian speech content.

Considering the limited availability of multi-speaker corpora in Cambodia, conventional methods have demonstrated subpar performance in Cambodian speaker voice transfer.

The originality of this study lies in the effectiveness of the disentanglement process and precise control over speaker timbre feature transfer.

Existing studies have paid less attention to the impact of knowledge accumulation on digital transformation and its boundary conditions. Hence, this study aims to investigate the effects of ambidextrous knowledge accumulation on manufacturing digital transformation under the moderation of dynamic capability.

This study divides knowledge accumulation into exploratory and exploitative knowledge accumulation and divides dynamic capability into alliance management capability and new product development capability. To clarify the relationship among ambidextrous knowledge accumulation, dynamic capability and manufacturing digital transformation, the authors collect data from 421 Chinese listed manufacturing enterprises from 2016 to 2020 and perform analysis by multiple hierarchical regression method, heterogeneity test and robustness analysis.

The empirical results show that both exploratory and exploitative knowledge accumulation can significantly promote manufacturing digital transformation. Keeping ambidextrous knowledge accumulation in parallel is more conducive than keeping single-dimensional knowledge accumulation. Besides, dynamic capability positively moderates the relationship between ambidextrous knowledge accumulation and manufacturing digital transformation. Moreover, the heterogeneity test shows that the impact of ambidextrous knowledge accumulation and dynamic capabilities on manufacturing digital transformation varies widely across different industry segments or different regions.

First, this paper shifts attention to the role of ambidextrous knowledge accumulation in manufacturing digital transformation and expands the connotation and extension of knowledge accumulation. Second, this study reveals that dynamic capability is a vital driver of digital transformation, which corroborates the previous findings of dynamic capability as an important driver and contributes to enriching the knowledge management literature. Third, this paper provides a comprehensive micro measurement of ambidextrous knowledge accumulation and digital transformation based on the development characteristics of the digital economy era, which provides a theoretical basis for subsequent research.

The purpose of this study is to explore a new assembly process planning and execution mode to realize rapid response, reduce the labor intensity of assembly workers and improve the assembly efficiency and quality.

Based on the related concepts of digital twin, this paper studies the product assembly planning in digital space, the process execution in physical space and the interaction between digital space and physical space. The assembly process planning is simulated and verified in the digital space to generate three-dimensional visual assembly process specification documents, the implementation of the assembly process specification documents in the physical space is monitored and feed back to revise the assembly process and improve the assembly quality.

Digital twin technology enhances the quality and efficiency of assembly process planning and execution system.

It provides a new perspective for assembly process planning and execution, the architecture, connections and data acquisition approaches of the digital twin-driven framework are proposed in this paper, which is of important theoretical values. What is more, a smart assembly workbench is developed, the specific image classification algorithms are presented in detail too, which is of some industrial application values.

Although businesses continue to take up artificial intelligence (AI), concerns remain that companies are not realising the full value of their investments. The study aims to provide insights into how AI creates business value by investigating the mediating role of Business Process Management (BPM) capabilities.

The integrative model of IT Business Value was contextualised, and structural equation modelling was applied to validate the proposed serial multiple mediation model using a sample of 448 organisations based in the EU.

The results validate the proposed serial multiple mediation model according to which AI adoption increases organisational performance through decision-making and business process performance. Process automation, organisational learning and process innovation are significant complementary partial mediators, thereby shedding light on how AI creates business value.

In pursuing a complex nomological framework, multiple perspectives on realising business value from AI investments were incorporated. Several moderators presenting complementary organisational resources (e.g. culture, digital maturity, BPM maturity) could be included to identify behaviour in more complex relationships. The ethical and moral issues surrounding AI and its use could also be examined.

The provided insights can help guide organisations towards the most promising AI activities of process automation with AI-enabled decision-making, organisational learning and process innovation to yield business value.

While previous research assumed a moderated relationship, this study extends the growing literature on AI business value by empirically investigating a comprehensive nomological network that links AI adoption to organisational performance in a BPM setting.

This paper provides practical advice for archaeologists and heritage specialists wishing to use ML approaches to identify archaeological features in high-resolution satellite imagery (or other remotely sensed data sources). We seek to balance the disproportionately optimistic literature related to the application of ML to archaeological prospection through a discussion of limitations, challenges and other difficulties. We further seek to raise awareness among researchers of the time, effort, expertise and resources necessary to implement ML successfully, so that they can make an informed choice between ML and manual inspection approaches.

Automated object detection has been the holy grail of archaeological remote sensing for the last two decades. Machine learning (ML) models have proven able to detect uniform features across a consistent background, but more variegated imagery remains a challenge. We set out to detect burial mounds in satellite imagery from a diverse landscape in Central Bulgaria using a pre-trained Convolutional Neural Network (CNN) plus additional but low-touch training to improve performance. Training was accomplished using MOUND/NOT MOUND cutouts, and the model assessed arbitrary tiles of the same size from the image. Results were assessed using field data.

Validation of results against field data showed that self-reported success rates were misleadingly high, and that the model was misidentifying most features. Setting an identification threshold at 60% probability, and noting that we used an approach where the CNN assessed tiles of a fixed size, tile-based false negative rates were 95–96%, false positive rates were 87–95% of tagged tiles, while true positives were only 5–13%. Counterintuitively, the model provided with training data selected for highly visible mounds (rather than all mounds) performed worse. Development of the model, meanwhile, required approximately 135 person-hours of work.

Our attempt to deploy a pre-trained CNN demonstrates the limitations of this approach when it is used to detect varied features of different sizes within a heterogeneous landscape that contains confounding natural and modern features, such as roads, forests and field boundaries. The model has detected incidental features rather than the mounds themselves, making external validation with field data an essential part of CNN workflows. Correcting the model would require refining the training data as well as adopting different approaches to model choice and execution, raising the computational requirements beyond the level of most cultural heritage practitioners.

Improving the pre-trained model’s performance would require considerable time and resources, on top of the time already invested. The degree of manual intervention required – particularly around the subsetting and annotation of training data – is so significant that it raises the question of whether it would be more efficient to identify all of the mounds manually, either through brute-force inspection by experts or by crowdsourcing the analysis to trained – or even untrained – volunteers. Researchers and heritage specialists seeking efficient methods for extracting features from remotely sensed data should weigh the costs and benefits of ML versus manual approaches carefully.

Our literature review indicates that use of artificial intelligence (AI) and ML approaches to archaeological prospection have grown exponentially in the past decade, approaching adoption levels associated with “crossing the chasm” from innovators and early adopters to the majority of researchers. The literature itself, however, is overwhelmingly positive, reflecting some combination of publication bias and a rhetoric of unconditional success. This paper presents the failure of a good-faith attempt to utilise these approaches as a counterbalance and cautionary tale to potential adopters of the technology. Early-majority adopters may find ML difficult to implement effectively in real-life scenarios.

Unlike many high-profile reports from well-funded projects, our paper represents a serious but modestly resourced attempt to apply an ML approach to archaeological remote sensing, using techniques like transfer learning that are promoted as solutions to time and cost problems associated with, e.g. annotating and manipulating training data. While the majority of articles uncritically promote ML, or only discuss how challenges were overcome, our paper investigates how – despite reasonable self-reported scores – the model failed to locate the target features when compared to field data. We also present time, expertise and resourcing requirements, a rarity in ML-for-archaeology publications.

The food industry is continuously developing its online services called food delivery applications (FDAs). This study aims to evaluate FDA's importance–performance and identify strategies to maximize its potential gains from a business partner's perspective.

Data are collected from 208 FDA partners in Indonesia. Importance–performance analysis (IPA) is applied to evaluate the FDA feature and extended the theory of potential gain in customer value (PGCV) to achieve potential gains from FDA business partners.

This study provides a clear and measurable direction for future research to develop FDA performance. Owning customer data, revenue sharing and competitive advantage are the most potential gains from joining the FDA from the business partner perspective.

The respondents are restaurants from the micro, small, and medium enterprises levels. Further research should involve middle to upper level restaurants to discover all business partners' perceptions. This will be very helpful for FDA providers interested in improving the best performance for all their partners.

FDA providers must focus on improving and maintaining the features of owning customer data, revenue sharing, competitive advantage, stable terms and conditions, customer interface, building customer loyalty, online presence, user credit rating, promotion and offers, delivery service and sales enhancement to increase consumer satisfaction and meet the expectations desired by business partners.

This research provides a meaningful theoretical foundation for future work. It extends the theory of PGCV using the value of a partner perspective as a substitute for customer value; hence, the authors call it a potential gain in partner value.

Unstructured data such as images have defied usage in property valuation for a long time. Instead, structured data in tabular format are commonly employed to estimate property prices. This study attempts to quantify the shape of land lots and uses the resultant output as an input variable for subsequent land valuation models.

Imagery data containing land lot shapes are fed into a convolutional neural network, and the shape of land lots is classified into two categories, regular and irregular-shaped. Then, the intermediate output (regularity score) is utilized in four downstream models to estimate land prices: random forest, gradient boosting, support vector machine and regression models.

Quantification of the land lot shapes and their exploitation in valuation led to an improvement in the predictive accuracy for all subsequent models.

The study findings are expected to promote the adoption of elusive price determinants such as the shape of a land lot, appearance of a house and the landscape of a neighborhood in property appraisal practices.

The paper aims to tackle the classification of Remote Sensing Images (RSIs), which presents a significant challenge for computer algorithms due to the inherent characteristics of clustered ground objects and noisy backgrounds. Recent research typically leverages larger volume models to achieve advanced performance. However, the operating environments of remote sensing commonly cannot provide unconstrained computational and storage resources. It requires lightweight algorithms with exceptional generalization capabilities.

This study introduces an efficient knowledge distillation (KD) method to build a lightweight yet precise convolutional neural network (CNN) classifier. This method also aims to substantially decrease the training time expenses commonly linked with traditional KD techniques. This approach entails extensive alterations to both the model training framework and the distillation process, each tailored to the unique characteristics of RSIs. In particular, this study establishes a robust ensemble teacher by independently training two CNN models using a customized, efficient training algorithm. Following this, this study modifies a KD loss function to mitigate the suppression of non-target category predictions, which are essential for capturing the inter- and intra-similarity of RSIs.

This study validated the student model, termed KD-enhanced network (KDE-Net), obtained through the KD process on three benchmark RSI data sets. The KDE-Net surpasses 42 other state-of-the-art methods in the literature published from 2020 to 2023. Compared to the top-ranked method’s performance on the challenging NWPU45 data set, KDE-Net demonstrated a noticeable 0.4% increase in overall accuracy with a significant 88% reduction in parameters. Meanwhile, this study’s reformed KD framework significantly enhances the knowledge transfer speed by at least three times.

This study illustrates that the logit-based KD technique can effectively develop lightweight CNN classifiers for RSI classification without substantial sacrifices in computation and storage costs. Compared to neural architecture search or other methods aiming to provide lightweight solutions, this study’s KDE-Net, based on the inherent characteristics of RSIs, is currently more efficient in constructing accurate yet lightweight classifiers for RSI classification.

This paper aims to realize an in-situ quality inspection system rapidly for new injection molding (IM) tasks via transfer learning (TL) approach and automation technology.

The proposed in-situ quality inspection system consists of an injection machine, USB camera, programmable logic controller and personal computer, interconnected via OPC or USB communication interfaces. This configuration enables seamless automation of the IM process, real-time quality inspection and automated decision-making. In addition, a MobileNet-based deep learning (DL) model is proposed for quality inspection of injection parts, fine-tuned using the TL approach.

Using the TL approach, the MobileNet-based DL model demonstrates exceptional performance, achieving validation accuracy of 99.1% with the utilization of merely 50 images per category. Its detection speed and accuracy surpass those of DenseNet121-based, VGG16-based, ResNet50-based and Xception-based convolutional neural networks. Further evaluation using a random data set of 120 images, as assessed through the confusion matrix, attests to an accuracy rate of 96.67%.

The proposed MobileNet-based DL model achieves higher accuracy with less resource consumption using the TL approach. It is integrated with automation technologies to build the in-situ quality inspection system of injection parts, which improves the cost-efficiency by facilitating the acquisition and labeling of task-specific images, enabling automatic defect detection and decision-making online, thus holding profound significance for the IM industry and its pursuit of enhanced quality inspection measures.