Search results

Identifying the flow regime is a prerequisite for accurately modeling two-phase flow. This paper aims to introduce a comprehensive data-driven workflow for flow regime identification.

A numerical two-phase flow model was validated against experimental data and was used to generate dynamic pressure signals for three different flow regimes. First, four distinct methods were used for feature extraction: discrete wavelet transform (DWT), empirical mode decomposition, power spectral density and the time series analysis method. Kernel Fisher discriminant analysis (KFDA) was used to simultaneously perform dimensionality reduction and machine learning (ML) classification for each set of features. Finally, the Shapley additive explanations (SHAP) method was applied to make the workflow explainable.

The results highlighted that the DWT + KFDA method exhibited the highest testing and training accuracy at 95.2% and 88.8%, respectively. Results also include a virtual flow regime map to facilitate the visualization of features in two dimension. Finally, SHAP analysis showed that minimum and maximum values extracted at the fourth and second signal decomposition levels of DWT are the best flow-distinguishing features.

This workflow can be applied to opaque pipes fitted with pressure sensors to achieve flow assurance and automatic monitoring of two-phase flow occurring in many process industries.

This paper presents a novel flow regime identification method by fusing dynamic pressure measurements with ML techniques. The authors’ novel DWT + KFDA method demonstrates superior performance for flow regime identification with explainability.

Automatic anatomical therapeutic chemical (ATC) classification is progressing at a rapid pace because of its potential in drug development. Predicting an unknown compound's therapeutic and chemical characteristics in terms of how it affects multiple organs and physiological systems makes automatic ATC classification a vital yet challenging multilabel problem. The aim of this paper is to experimentally derive an ensemble of different feature descriptors and classifiers for ATC classification that outperforms the state-of-the-art.

The proposed method is an ensemble generated by the fusion of neural networks (i.e. a tabular model and long short-term memory networks (LSTM)) and multilabel classifiers based on multiple linear regression (hMuLab). All classifiers are trained on three sets of descriptors. Features extracted from the trained LSTMs are also fed into hMuLab. Evaluations of ensembles are compared on a benchmark data set of 3883 ATC-coded pharmaceuticals taken from KEGG, a publicly available drug databank.

Experiments demonstrate the power of the authors’ best ensemble, EnsATC, which is shown to outperform the best methods reported in the literature, including the state-of-the-art developed by the fast.ai research group. The MATLAB source code of the authors’ system is freely available to the public at https://github.com/LorisNanni/Neural-networks-for-anatomical-therapeutic-chemical-ATC-classification.

This study demonstrates the power of extracting LSTM features and combining them with ATC descriptors in ensembles for ATC classification.

Text classification is a widely accepted and adopted technique in organizations to mine and analyze unstructured and semi-structured data. With advancement of technological computing, deep learning has become more popular among academicians and professionals to perform mining and analytical operations. In this work, the authors study the research carried out in field of text classification using deep learning techniques to identify gaps and opportunities for doing research.

The authors adopted bibliometric-based approach in conjunction with visualization techniques to uncover new insights and findings. The authors collected data of two decades from Scopus global database to perform this study. The authors discuss business applications of deep learning techniques for text classification.

The study provides overview of various publication sources in field of text classification and deep learning together. The study also presents list of prominent authors and their countries working in this field. The authors also presented list of most cited articles based on citations and country of research. Various visualization techniques such as word cloud, network diagram and thematic map were used to identify collaboration network.

The study performed in this paper helped to understand research gaps that is original contribution to body of literature. To best of the authors' knowledge, in-depth study in the field of text classification and deep learning has not been performed in detail. The study provides high value to scholars and professionals by providing them opportunities of research in this area.

Automatic DNA-binding protein (DNA-BP) classification is now an essential proteomic technology. Unfortunately, many systems reported in the literature are tested on only one or two datasets/tasks. The purpose of this study is to create the most optimal and universal system for DNA-BP classification, one that performs competitively across several DNA-BP classification tasks.

Efficient DNA-BP classifier systems require the discovery of powerful protein representations and feature extraction methods. Experiments were performed that combined and compared descriptors extracted from state-of-the-art matrix/image protein representations. These descriptors were trained on separate support vector machines (SVMs) and evaluated. Convolutional neural networks with different parameter settings were fine-tuned on two matrix representations of proteins. Decisions were fused with the SVMs using the weighted sum rule and evaluated to experimentally derive the most powerful general-purpose DNA-BP classifier system.

The best ensemble proposed here produced comparable, if not superior, classification results on a broad and fair comparison with the literature across four different datasets representing a variety of DNA-BP classification tasks, thereby demonstrating both the power and generalizability of the proposed system.

Most DNA-BP methods proposed in the literature are only validated on one (rarely two) datasets/tasks. In this work, the authors report the performance of our general-purpose DNA-BP system on four datasets representing different DNA-BP classification tasks. The excellent results of the proposed best classifier system demonstrate the power of the proposed approach. These results can now be used for baseline comparisons by other researchers in the field.

Accurate and rapid tracking and counting of building materials are crucial in managing on-site construction processes and evaluating their progress. Such processes are typically conducted by visual inspection, making them time-consuming and error prone. This paper aims to propose a video-based deep-learning approach to the automated detection and counting of building materials.

A framework for accurately counting building materials at indoor construction sites with low light levels was developed using state-of-the-art deep learning methods. An existing object-detection model, the You Only Look Once version 4 (YOLO v4) algorithm, was adapted to achieve rapid convergence and accurate detection of materials and site operatives. Then, DenseNet was deployed to recognise these objects. Finally, a material-counting module based on morphology operations and the Hough transform was applied to automatically count stacks of building materials.

The proposed approach was tested by counting site operatives and stacks of elevated floor tiles in video footage from a real indoor construction site. The proposed YOLO v4 object-detection system provided higher average accuracy within a shorter time than the traditional YOLO v4 approach.

The proposed framework makes it feasible to separately monitor stockpiled, installed and waste materials in low-light construction environments. The improved YOLO v4 detection method is superior to the current YOLO v4 approach and advances the existing object detection algorithm. This framework can potentially reduce the time required to track construction progress and count materials, thereby increasing the efficiency of work-in-progress evaluation. It also exhibits great potential for developing a more reliable system for monitoring construction materials and activities.

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.

The purpose of this paper is to expand and analyze deeply customer emotions, concretize the levels of positive or negative emotions with the aim of using machine learning methods, and build a model to identify customer emotions.

The study proposed a customer emotion detection model and data mining method based on the collected dataset, including 80,593 online reviews on agoda.com and booking.com from 2009 to 2022.

By discerning specific emotions expressed in customers' comments, emotion detection, which refers to the process of identifying users' emotional states, assumes a crucial role in evaluating the brand value of a product. The research capitalizes on the vast and diverse data sources available on hotel booking websites, which, despite their richness, remain largely unexplored and unanalyzed. The outcomes of the model, pertaining to the detection and classification of customer emotions based on ratings and reviews into four distinct emotional states, offer a means to address the challenge of determining customer satisfaction regarding their actual service experiences. These findings hold substantial value for businesses operating in this domain, as the findings facilitate the evaluation and formulation of improvement strategies within their business models. The experimental study reveals that the proposed model attains an exact match ratio, precision, and recall rates of up to 81%, 90% and 90%, respectively.

The study has yet to mine real-time data. Prediction results may be influenced because the amount of data collected from the web is insufficient and preprocessing is not completely suppressed. Furthermore, the model in the study was not tested using all algorithms and multi-label classifiers. Future research should build databases to mine data in real-time and collect more data and enhance the current model.

The study's results suggest that the emotion detection models can be applied to the real world to quickly analyze customer feedback. The proposed models enable the identification of customers' emotions, the discovery of customer demand, the enhancement of service, and the general customer experience. The established models can be used by many service sectors to learn more about customer satisfaction with the offered goods and services from customer reviews.

The research paper helps businesses in the hospitality area analyze customer emotions in each specific aspect to ensure customer satisfaction. In addition, managers can come up with appropriate strategies to bring better products and services to society and people. Subsequently, fostering the growth of the hotel tourism sector within the nation, thereby facilitating sustainable economic development on a national scale.

This study developed a customer emotions detection model for detecting and classifying customer ratings and reviews as 4 specific emotions: happy, angry, depressed and hopeful based on online booking hotel websites agoda.com and booking.com that contains 80,593 reviews in Vietnamese. The research results help businesses check and evaluate the quality of their services, thereby offering appropriate improvement strategies to increase customers' satisfaction and demand more effectively.

Climate change is a problem that concerns all of us. Despite the information produced by organizations such as the Expert Team on Climate Change Detection and Indices and the United Nations, only a few cities have been planned taking into account the climate changes indices. This paper aims to study climatic variations, how climate conditions might change in the future and how these changes will affect the activities and living conditions in cities, specifically focusing on Mexico city.

In this approach, two distinct machine learning regression models, k-Nearest Neighbors and Support Vector Regression, were used to predict variations in climate change indices within select urban areas of Mexico city. The calculated indices are based on maximum, minimum and average temperature data collected from the National Water Commission in Mexico and the Scientific Research Center of Ensenada. The methodology involves pre-processing temperature data to create a training data set for regression algorithms. It then computes predictions for each temperature parameter and ultimately assesses the performance of these algorithms based on precision metrics scores.

This paper combines a geospatial perspective with computational tools and machine learning algorithms. Among the two regression algorithms used, it was observed that k-Nearest Neighbors produced superior results, achieving an R² score of 0.99, in contrast to Support Vector Regression, which yielded an R² score of 0.74.

The full potential of machine learning algorithms has not been fully harnessed for predicting climate indices. This paper also identifies the strengths and weaknesses of each algorithm and how the generated estimations can then be considered in the decision-making process.

Our study examines how artificial intelligence (AI) can enhance decision-making processes to promote circular economy practices within the utility sector.

A unique case study of Alia Servizi Ambientali Spa, an Italian multi-utility company using AI for waste management, is analyzed using the Gioia method and semi-structured interviews.

Our study discovers the proactive role of the user in waste management processes, the importance of economic incentives to increase the usefulness of the technology and the role of AI in waste management transformation processes (e.g. glass waste).

The present study enhances the circular economy model (transformation, distribution and recovery), uncovering AI’s role in waste management. Finally, we inspire managers with algorithms used for data-driven decisions.

This study aims to propose a combined effect framework to explore the relationship between research and development (R&D) team networks, knowledge diversity and breakthrough technological innovation. In contrast to conventional linear net effects, the article explores three possible types of team configuration within enterprises and their breakthrough innovation-driving mechanisms based on machine learning methods.

Based on the patent application data of 2,337 Chinese companies in the biopharmaceutical manufacturing industry to construct the R&D team network, the study uses the K-Means method to explore the configuration types of R&D teams with the principle of greatest intergroup differences. Further, a decision tree model (DT) is utilized to excavate the conditional combined relationships between diverse team network configuration factors, knowledge diversity and breakthrough innovation. The network driving mechanism of corporate breakthrough innovation is analyzed from the perspective of team configurations.

It has been discerned that in the biopharmaceutical manufacturing industry, there exist three main types of enterprise R&D team configurations: tight collaboration, knowledge expansion and scale orientation, which reflect the three resource investment preferences of enterprises in technological innovation, network relationships, knowledge resources and human capital. The results highlight both the crowding-out effects and complementary effects between knowledge diversity and team network characteristics in tight collaborative teams. Low knowledge diversity and high team structure holes (SHs) are found to be the optimal team configuration conditions for breakthrough innovation in knowledge-expanding and scale-oriented teams.

Previous studies have mainly focused on the relationship between the external collaboration network and corporate innovation. Moreover, traditional regression methods mainly describe the linear net effects between variables, neglecting that technological breakthroughs are a comprehensive concept that requires the combined action of multiple factors. To address the gap, this article proposes a combination effect framework between R&D teams and enterprise breakthrough innovation, further improving social network theory and expanding the applicability of data mining methods in the field of innovation management.