Search results

In gearbox fault diagnosis, identifying the fault type and severity simultaneously, as well as the compound fault containing multiple faults, is necessary.

To diagnose multiple faults simultaneously, this paper proposes a multichannel and multi-task convolutional neural network (MCMT-CNN) model.

Experiments were conducted on a bearing dataset containing different fault types and severities and a gearbox compound fault dataset. The experimental results show that MCMT-CNN can effectively extract features of different tasks from vibration signals, with a diagnosis accuracy of more than 97%.

Vibration signals at different positions and in different directions are taken as the MC inputs to ensure the integrity of the fault features. Fault labels are established to retain and distinguish the unique features of different tasks. In MCMT-CNN, multiple task branches can connect and share all neurons in the hidden layer, thus enabling multiple tasks to share information.

Image classification is becoming a supporting technology in several image-processing tasks. Due to rich semantic information contained in the images, it is very popular for an image to have several labels or tags. This paper aims to develop a novel multi-label classification approach with superior performance.

Many multi-label classification problems share two main characteristics: label correlations and label imbalance. However, most of current methods are devoted to either model label relationship or to only deal with unbalanced problem with traditional single-label methods. In this paper, multi-label classification problem is regarded as an unbalanced multi-task learning problem. Multi-task least-squares support vector machine (MTLS-SVM) is generalized for this problem, renamed as multi-label LS-SVM (ML²S-SVM).

Experimental results on the emotions, scene, yeast and bibtex data sets indicate that the ML²S-SVM is competitive with respect to the state-of-the-art methods in terms of Hamming loss and instance-based F1 score. The values of resulting parameters largely influence the performance of ML²S-SVM, so it is necessary for users to identify proper parameters in advance.

On the basis of MTLS-SVM, a novel multi-label classification approach, ML²S-SVM, is put forward. This method can overcome the unbalanced problem but also explicitly models arbitrary order correlations among labels by allowing multiple labels to share a subspace. In addition, the multi-label classification approach has a wider range of applications. That is to say, it is not limited to the field of image classification.

This study aims to investigate the literature related to the use of digital technologies for promoting circular economy (CE) in the construction industry.

A comprehensive approach was adopted, involving bibliometric analysis, text-mining analysis and content analysis to meet three objectives (1) to unveil the evolutionary progress of the field, (2) to identify the key research themes in the field and (3) to identify challenges hindering the implementation of digital technologies for CE.

A total of 365 publications was analysed. The results revealed eight key digital technologies categorised into two main clusters including “digitalisation and advanced technologies” and “sustainable construction technologies”. The former involved technologies, namely machine learning, artificial intelligence, deep learning, big data analytics and object detection and computer vision that were used for (1) forecasting construction and demolition (C&D) waste generation, (2) waste identification and classification and (3) computer vision for waste management. The latter included technologies such as Internet of Things (IoT), blockchain and building information modelling (BIM) that help optimise resource use, enhance transparency and sustainability practices in the industry. Overall, these technologies show great potential for improving waste management and enabling CE in construction.

This research employs a holistic approach to provide a status-quo understanding of the digital technologies that can be utilised to support the implementation of CE in construction. Further, this study underlines the key challenges associated with adopting digital technologies, whilst also offering opportunities for future improvement of the field.

Digital computing and machine learning-driven predictive analysis in the diagnosis of non-communicable diseases are gaining significance. Globally many research studies are focusing on developing comprehensive models for such detection. Categorically in the proposed diagnosis for arrhythmia, which is a critical diagnosis to prevent cardiac-related deaths, any constructive models can be a value proposition. In this study, the focus is on developing a holistic system that predicts the scope of arrhythmia from the given electrocardiogram report. The proposed method is using the sequential patterns of the electrocardiogram elements as features.

Considering the decision accuracy of the contemporary classification methods, which is not adequate to use in clinical practices, this manuscript coined a new dimension of features to perform supervised learning and classification using the AdaBoost classifier. The proposed method has titled “Electrocardiogram stream level correlated patterns as features (ESCPFs),” which takes electrocardiograms (ECGs) signal streams as input records to perform supervised learning-based classification to detect the arrhythmia scope in given ECG record.

From the results and comparative reports generated for the study, it is evident that the model is performing with higher accuracy compared to some of the earlier models. However, focusing on the emerging solutions and technologies, if the accuracy factors for the model can be improved, it can lead to compelling predictions and accurate outcome from the process.

The authors represent complete automatic and rapid arrhythmia as classifier, which could be applied online and examine long ECG records sequence efficiently. By releasing the needs for extraction of features, the authors project an application based on raw signals, one result to heart rates date, whose objective is to lessen computation time when attaining minimum classification error outcomes.

The purpose of this paper is to study heterogeneous transfer learning for activity recognition using heuristic search techniques. Many pervasive computing applications require information about the activities currently being performed, but activity recognition algorithms typically require substantial amounts of labeled training data for each setting. One solution to this problem is to leverage transfer learning techniques to reuse available labeled data in new situations.

This paper introduces three novel heterogeneous transfer learning techniques that reverse the typical transfer model and map the target feature space to the source feature space and apply them to activity recognition in a smart apartment. This paper evaluates the techniques on data from 18 different smart apartments located in an assisted-care facility and compares the results against several baselines.

The three transfer learning techniques are all able to outperform the baseline comparisons in several situations. Furthermore, the techniques are successfully used in an ensemble approach to achieve even higher levels of accuracy.

The techniques in this paper represent a considerable step forward in heterogeneous transfer learning by removing the need to rely on instance – instance or feature – feature co-occurrence data.

Existing labor estimation models typically consider only certain construction project types or specific influencing factors. These models are focused on quantifying the total labor hours required, while the utilization rate of the labor during the project is not usually accounted for. This study aims to develop a novel machine learning model to predict the time series of labor resource utilization rate at the work package level.

More than 250 construction work packages collected over a two-year period are used to identify the main contributing factors affecting labor resource requirements. Also, a novel machine learning algorithm – Recurrent Neural Network (RNN) – is adopted to develop a forecasting model that can predict the utilization of labor resources over time.

This paper presents a robust machine learning approach for predicting labor resources’ utilization rates in construction projects based on the identified contributing factors. The machine learning approach is found to result in a reliable time series forecasting model that uses the RNN algorithm. The proposed model indicates the capability of machine learning algorithms in facilitating the traditional challenges in construction industry.

The findings point to the suitability of state-of-the-art machine learning techniques for developing predictive models to forecast the utilization rate of labor resources in construction projects, as well as for supporting project managers by providing forecasting tool for labor estimations at the work package level before detailed activity schedules have been generated. Accordingly, the proposed approach facilitates resource allocation and enables prioritization of available resources to enhance the overall performance of projects.

This paper reviews 105 Scopus-indexed articles to identify the degree, scope and purposes of machine learning (ML) adoption in the core functions of human resource management (HRM).

A semi-systematic approach has been used in this review. It allows for a more detailed analysis of the literature which emerges from multiple disciplines and uses different methods and theoretical frameworks. Since ML research comes from multiple disciplines and consists of several methods, a semi-systematic approach to literature review was considered appropriate.

The review suggests that HRM has embraced ML, albeit it is at a nascent stage and is receiving attention largely from technology-oriented researchers. ML applications are strongest in the areas of recruitment and performance management and the use of decision trees and text-mining algorithms for classification dominate all functions of HRM. For complex processes, ML applications are still at an early stage; requiring HR experts and ML specialists to work together.

Given the current focus of organizations on digitalization, this review contributes significantly to the understanding of the current state of ML integration in HRM. Along with increasing efficiency and effectiveness of HRM functions, ML applications improve employees' experience and facilitate performance in the organizations.

Automatically extracting stance information from natural language texts is a significant research problem with various applications, particularly after the recent explosion of data on the internet via platforms like social media sites. Stance detection system helps determine whether the author agree, against or has a neutral opinion with the given target. Most of the research in stance detection focuses on the English language, while few research was conducted on the Arabic language.

This paper aimed to address stance detection on Arabic tweets by building and comparing different stance detection models using four transformers, namely: Araelectra, MARBERT, AraBERT and Qarib. Using different weights for these transformers, the authors performed extensive experiments fine-tuning the task of stance detection Arabic tweets with the four different transformers.

The results showed that the AraBERT model learned better than the other three models with a 70% F1 score followed by the Qarib model with a 68% F1 score.

A limitation of this study is the imbalanced dataset and the limited availability of annotated datasets of SD in Arabic.

Provide comprehensive overview of the current resources for stance detection in the literature, including datasets and machine learning methods used. Therefore, the authors examined the models to analyze and comprehend the obtained findings in order to make recommendations for the best performance models for the stance detection task.

The increase of turbulence sources and risk points under the complex social information network has brought severe challenges. This paper discusses risk perception and intelligent decision-making under the complex social information network to maintain social security and financial security.

Cross-modal semantic fusion and social risk perception, temporal knowledge graph and analysis, complex social network intelligent decision-making methods have been studied. A big data computing platform of software and hardware integration for security combat is constructed based on the technical support.

The software and hardware integration platform driven by big data can realize joint identification of significant risks, intelligent analysis and large-scale group decision-making.

The integrated platform can monitor the abnormal operation and potential associated risks of Listed Companies in real-time, reduce information asymmetry and accounting costs and improve the capital market's ability to serve the real economy. It can also provide critical technical support and decision support in necessary public opinion monitoring and control business.

In this paper, the theory of knowledge-enhanced multi-modal multi-granularity dynamic risk analysis and intelligent group decision-making and the idea of an inference think tank (I-aid-S) is proposed. New technologies and methods, such as association analysis, time series evolution and super large-scale group decision-making, have been established. It's also applied in behavior and situation deduction, public opinion and finance and provides real-time, dynamic, fast and high-quality think tank services.

This paper aims to provide a comprehensive analysis of the state of the art in energy efficiency for autonomous mobile robots (AMRs), focusing on energy sources, consumption models, energy-efficient locomotion, hardware energy consumption, optimization in path planning and scheduling methods, and to suggest future research directions.

The systematic literature review (SLR) identified 244 papers for analysis. Research articles published from 2010 onwards were searched in databases including Google Scholar, ScienceDirect and Scopus using keywords and search criteria related to energy and power management in various robotic systems.

The review highlights the following key findings: batteries are the primary energy source for AMRs, with advances in battery management systems enhancing efficiency; hybrid models offer superior accuracy and robustness; locomotion contributes over 50% of a mobile robot’s total energy consumption, emphasizing the need for optimized control methods; factors such as the center of mass impact AMR energy consumption; path planning algorithms and scheduling methods are essential for energy optimization, with algorithm choice depending on specific requirements and constraints.

The review concentrates on wheeled robots, excluding walking ones. Future work should improve consumption models, explore optimization methods, examine artificial intelligence/machine learning roles and assess energy efficiency trade-offs.

This paper provides a comprehensive analysis of energy efficiency in AMRs, highlighting the key findings from the SLR and suggests future research directions for further advancements in this field.