Search results
1 – 10 of 182Rong Jiang, Bin He, Zhipeng Wang, Xu Cheng, Hongrui Sang and Yanmin Zhou
Compared with traditional methods relying on manual teaching or system modeling, data-driven learning methods, such as deep reinforcement learning and imitation learning, show…
Abstract
Purpose
Compared with traditional methods relying on manual teaching or system modeling, data-driven learning methods, such as deep reinforcement learning and imitation learning, show more promising potential to cope with the challenges brought by increasingly complex tasks and environments, which have become the hot research topic in the field of robot skill learning. However, the contradiction between the difficulty of collecting robot–environment interaction data and the low data efficiency causes all these methods to face a serious data dilemma, which has become one of the key issues restricting their development. Therefore, this paper aims to comprehensively sort out and analyze the cause and solutions for the data dilemma in robot skill learning.
Design/methodology/approach
First, this review analyzes the causes of the data dilemma based on the classification and comparison of data-driven methods for robot skill learning; Then, the existing methods used to solve the data dilemma are introduced in detail. Finally, this review discusses the remaining open challenges and promising research topics for solving the data dilemma in the future.
Findings
This review shows that simulation–reality combination, state representation learning and knowledge sharing are crucial for overcoming the data dilemma of robot skill learning.
Originality/value
To the best of the authors’ knowledge, there are no surveys that systematically and comprehensively sort out and analyze the data dilemma in robot skill learning in the existing literature. It is hoped that this review can be helpful to better address the data dilemma in robot skill learning in the future.
Details
Keywords
The purpose of this study is to examine the state of research into adoption of machine learning systems within the health sector, to identify themes that have been studied and…
Abstract
Purpose
The purpose of this study is to examine the state of research into adoption of machine learning systems within the health sector, to identify themes that have been studied and observe the important gaps in the literature that can inform a research agenda going forward.
Design/methodology/approach
A systematic literature strategy was utilized to identify and analyze scientific papers between 2012 and 2022. A total of 28 articles were identified and reviewed.
Findings
The outcomes reveal that while advances in machine learning have the potential to improve service access and delivery, there have been sporadic growth of literature in this area which is perhaps surprising given the immense potential of machine learning within the health sector. The findings further reveal that themes such as recordkeeping, drugs development and streamlining of treatment have primarily been focused on by the majority of authors in this area.
Research limitations/implications
The search was limited to journal articles published in English, resulting in the exclusion of studies disseminated through alternative channels, such as conferences, and those published in languages other than English. Considering that scholars in developing nations may encounter less difficulty in disseminating their work through alternative channels and that numerous emerging nations employ languages other than English, it is plausible that certain research has been overlooked in the present investigation.
Originality/value
This review provides insights into future research avenues for theory, content and context on adoption of machine learning within the health sector.
Details
Keywords
Ambica Ghai, Pradeep Kumar and Samrat Gupta
Web users rely heavily on online content make decisions without assessing the veracity of the content. The online content comprising text, image, video or audio may be tampered…
Abstract
Purpose
Web users rely heavily on online content make decisions without assessing the veracity of the content. The online content comprising text, image, video or audio may be tampered with to influence public opinion. Since the consumers of online information (misinformation) tend to trust the content when the image(s) supplement the text, image manipulation software is increasingly being used to forge the images. To address the crucial problem of image manipulation, this study focusses on developing a deep-learning-based image forgery detection framework.
Design/methodology/approach
The proposed deep-learning-based framework aims to detect images forged using copy-move and splicing techniques. The image transformation technique aids the identification of relevant features for the network to train effectively. After that, the pre-trained customized convolutional neural network is used to train on the public benchmark datasets, and the performance is evaluated on the test dataset using various parameters.
Findings
The comparative analysis of image transformation techniques and experiments conducted on benchmark datasets from a variety of socio-cultural domains establishes the effectiveness and viability of the proposed framework. These findings affirm the potential applicability of proposed framework in real-time image forgery detection.
Research limitations/implications
This study bears implications for several important aspects of research on image forgery detection. First this research adds to recent discussion on feature extraction and learning for image forgery detection. While prior research on image forgery detection, hand-crafted the features, the proposed solution contributes to stream of literature that automatically learns the features and classify the images. Second, this research contributes to ongoing effort in curtailing the spread of misinformation using images. The extant literature on spread of misinformation has prominently focussed on textual data shared over social media platforms. The study addresses the call for greater emphasis on the development of robust image transformation techniques.
Practical implications
This study carries important practical implications for various domains such as forensic sciences, media and journalism where image data is increasingly being used to make inferences. The integration of image forgery detection tools can be helpful in determining the credibility of the article or post before it is shared over the Internet. The content shared over the Internet by the users has become an important component of news reporting. The framework proposed in this paper can be further extended and trained on more annotated real-world data so as to function as a tool for fact-checkers.
Social implications
In the current scenario wherein most of the image forgery detection studies attempt to assess whether the image is real or forged in an offline mode, it is crucial to identify any trending or potential forged image as early as possible. By learning from historical data, the proposed framework can aid in early prediction of forged images to detect the newly emerging forged images even before they occur. In summary, the proposed framework has a potential to mitigate physical spreading and psychological impact of forged images on social media.
Originality/value
This study focusses on copy-move and splicing techniques while integrating transfer learning concepts to classify forged images with high accuracy. The synergistic use of hitherto little explored image transformation techniques and customized convolutional neural network helps design a robust image forgery detection framework. Experiments and findings establish that the proposed framework accurately classifies forged images, thus mitigating the negative socio-cultural spread of misinformation.
Details
Keywords
Miaoxian Guo, Shouheng Wei, Chentong Han, Wanliang Xia, Chao Luo and Zhijian Lin
Surface roughness has a serious impact on the fatigue strength, wear resistance and life of mechanical products. Realizing the evolution of surface quality through theoretical…
Abstract
Purpose
Surface roughness has a serious impact on the fatigue strength, wear resistance and life of mechanical products. Realizing the evolution of surface quality through theoretical modeling takes a lot of effort. To predict the surface roughness of milling processing, this paper aims to construct a neural network based on deep learning and data augmentation.
Design/methodology/approach
This study proposes a method consisting of three steps. Firstly, the machine tool multisource data acquisition platform is established, which combines sensor monitoring with machine tool communication to collect processing signals. Secondly, the feature parameters are extracted to reduce the interference and improve the model generalization ability. Thirdly, for different expectations, the parameters of the deep belief network (DBN) model are optimized by the tent-SSA algorithm to achieve more accurate roughness classification and regression prediction.
Findings
The adaptive synthetic sampling (ADASYN) algorithm can improve the classification prediction accuracy of DBN from 80.67% to 94.23%. After the DBN parameters were optimized by Tent-SSA, the roughness prediction accuracy was significantly improved. For the classification model, the prediction accuracy is improved by 5.77% based on ADASYN optimization. For regression models, different objective functions can be set according to production requirements, such as root-mean-square error (RMSE) or MaxAE, and the error is reduced by more than 40% compared to the original model.
Originality/value
A roughness prediction model based on multiple monitoring signals is proposed, which reduces the dependence on the acquisition of environmental variables and enhances the model's applicability. Furthermore, with the ADASYN algorithm, the Tent-SSA intelligent optimization algorithm is introduced to optimize the hyperparameters of the DBN model and improve the optimization performance.
Details
Keywords
Meng Zhu and Xiaolong Xu
Intent detection (ID) and slot filling (SF) are two important tasks in natural language understanding. ID is to identify the main intent of a paragraph of text. The goal of SF is…
Abstract
Purpose
Intent detection (ID) and slot filling (SF) are two important tasks in natural language understanding. ID is to identify the main intent of a paragraph of text. The goal of SF is to extract the information that is important to the intent from the input sentence. However, most of the existing methods use sentence-level intention recognition, which has the risk of error propagation, and the relationship between intention recognition and SF is not explicitly modeled. Aiming at this problem, this paper proposes a collaborative model of ID and SF for intelligent spoken language understanding called ID-SF-Fusion.
Design/methodology/approach
ID-SF-Fusion uses Bidirectional Encoder Representation from Transformers (BERT) and Bidirectional Long Short-Term Memory (BiLSTM) to extract effective word embedding and context vectors containing the whole sentence information respectively. Fusion layer is used to provide intent–slot fusion information for SF task. In this way, the relationship between ID and SF task is fully explicitly modeled. This layer takes the result of ID and slot context vectors as input to obtain the fusion information which contains both ID result and slot information. Meanwhile, to further reduce error propagation, we use word-level ID for the ID-SF-Fusion model. Finally, two tasks of ID and SF are realized by joint optimization training.
Findings
We conducted experiments on two public datasets, Airline Travel Information Systems (ATIS) and Snips. The results show that the Intent ACC score and Slot F1 score of ID-SF-Fusion on ATIS and Snips are 98.0 per cent and 95.8 per cent, respectively, and the two indicators on Snips dataset are 98.6 per cent and 96.7 per cent, respectively. These models are superior to slot-gated, SF-ID NetWork, stack-Prop and other models. In addition, ablation experiments were performed to further analyze and discuss the proposed model.
Originality/value
This paper uses word-level intent recognition and introduces intent information into the SF process, which is a significant improvement on both data sets.
Details
Keywords
Muhammad Arif Mahmood, Chioibasu Diana, Uzair Sajjad, Sabin Mihai, Ion Tiseanu and Andrei C. Popescu
Porosity is a commonly analyzed defect in the laser-based additive manufacturing processes owing to the enormous thermal gradient caused by repeated melting and solidification…
Abstract
Purpose
Porosity is a commonly analyzed defect in the laser-based additive manufacturing processes owing to the enormous thermal gradient caused by repeated melting and solidification. Currently, the porosity estimation is limited to powder bed fusion. The porosity estimation needs to be explored in the laser melting deposition (LMD) process, particularly analytical models that provide cost- and time-effective solutions compared to finite element analysis. For this purpose, this study aims to formulate two mathematical models for deposited layer dimensions and corresponding porosity in the LMD process.
Design/methodology/approach
In this study, analytical models have been proposed. Initially, deposited layer dimensions, including layer height, width and depth, were calculated based on the operating parameters. These outputs were introduced in the second model to estimate the part porosity. The models were validated with experimental data for Ti6Al4V depositions on Ti6Al4V substrate. A calibration curve (CC) was also developed for Ti6Al4V material and characterized using X-ray computed tomography. The models were also validated with the experimental results adopted from literature. The validated models were linked with the deep neural network (DNN) for its training and testing using a total of 6,703 computations with 1,500 iterations. Here, laser power, laser scanning speed and powder feeding rate were selected inputs, whereas porosity was set as an output.
Findings
The computations indicate that owing to the simultaneous inclusion of powder particulates, the powder elements use a substantial percentage of the laser beam energy for their melting, resulting in laser beam energy attenuation and reducing thermal value at the substrate. The primary operating parameters are directly correlated with the number of layers and total height in CC. Through X-ray computed tomography analyses, the number of layers showed a straightforward correlation with mean sphericity, while a converse relation was identified with the number, mean volume and mean diameter of pores. DNN and analytical models showed 2%–3% and 7%–9% mean absolute deviations, respectively, compared to the experimental results.
Originality/value
This research provides a unique solution for LMD porosity estimation by linking the developed analytical computational models with artificial neural networking. The presented framework predicts the porosity in the LMD-ed parts efficiently.
Details
Keywords
B. Vasavi, P. Dileep and Ulligaddala Srinivasarao
Aspect-based sentiment analysis (ASA) is a task of sentiment analysis that requires predicting aspect sentiment polarity for a given sentence. Many traditional techniques use…
Abstract
Purpose
Aspect-based sentiment analysis (ASA) is a task of sentiment analysis that requires predicting aspect sentiment polarity for a given sentence. Many traditional techniques use graph-based mechanisms, which reduce prediction accuracy and introduce large amounts of noise. The other problem with graph-based mechanisms is that for some context words, the feelings change depending on the aspect, and therefore it is impossible to draw conclusions on their own. ASA is challenging because a given sentence can reveal complicated feelings about multiple aspects.
Design/methodology/approach
This research proposed an optimized attention-based DL model known as optimized aspect and self-attention aware long short-term memory for target-based semantic analysis (OAS-LSTM-TSA). The proposed model goes through three phases: preprocessing, aspect extraction and classification. Aspect extraction is done using a double-layered convolutional neural network (DL-CNN). The optimized aspect and self-attention embedded LSTM (OAS-LSTM) is used to classify aspect sentiment into three classes: positive, neutral and negative.
Findings
To detect and classify sentiment polarity of the aspect using the optimized aspect and self-attention embedded LSTM (OAS-LSTM) model. The results of the proposed method revealed that it achieves a high accuracy of 95.3 per cent for the restaurant dataset and 96.7 per cent for the laptop dataset.
Originality/value
The novelty of the research work is the addition of two effective attention layers in the network model, loss function reduction and accuracy enhancement, using a recent efficient optimization algorithm. The loss function in OAS-LSTM is minimized using the adaptive pelican optimization algorithm, thus increasing the accuracy rate. The performance of the proposed method is validated on four real-time datasets, Rest14, Lap14, Rest15 and Rest16, for various performance metrics.
Details
Keywords
Priya Mishra and Aleena Swetapadma
Sleep arousal detection is an important factor to monitor the sleep disorder.
Abstract
Purpose
Sleep arousal detection is an important factor to monitor the sleep disorder.
Design/methodology/approach
Thus, a unique nth layer one-dimensional (1D) convolutional neural network-based U-Net model for automatic sleep arousal identification has been proposed.
Findings
The proposed method has achieved area under the precision–recall curve performance score of 0.498 and area under the receiver operating characteristics performance score of 0.946.
Originality/value
No other researchers have suggested U-Net-based detection of sleep arousal.
Research limitations/implications
From the experimental results, it has been found that U-Net performs better accuracy as compared to the state-of-the-art methods.
Practical implications
Sleep arousal detection is an important factor to monitor the sleep disorder. Objective of the work is to detect the sleep arousal using different physiological channels of human body.
Social implications
It will help in improving mental health by monitoring a person's sleep.
Details
Keywords
Byung-Gak Son, Samuel Roscoe and ManMohan S. Sodhi
This study aims to answer the question: What dynamic capabilities do diverse humanitarian organizations have?
Abstract
Purpose
This study aims to answer the question: What dynamic capabilities do diverse humanitarian organizations have?
Design/methodology/approach
We examine this question through the lens of dynamic capabilities with sensing, seizing and reconfiguring capacities. The research team interviewed 15 individuals from 12 humanitarian organizations that had (a) different geographic scopes (global versus local) and (b) different missions (emergency response versus long-term development aid). We also gathered data from secondary sources, including standard operating procedures, company websites, and news databases (Factiva, Reuters and Bloomberg).
Findings
The findings identify the operational and dynamic capabilities of global and local humanitarian organizations while distinguishing between their mission to provide long-term development aid or emergency relief. (1) The global organizations, with their beneficiary responsiveness, reconfigured their sensing and seizing capacities throughout the COVID-19 pandemic by pivoting quickly to local procurement or regional supply chains. The long-term development organizations pivoted to multi-year supplier agreements with fixed pricing to counter price uncertainty and accessed social capital with government bodies. In contrast, emergency response organizations developed end-to-end supply chain visibility to sense changes in supply and demand. (2) Local humanitarian organizations developed the capacity to sense demand and supply changes to reconfigure based on their experiential learning working with the local community. The long-term-development local organizations used un-owned and scalable relief infrastructure to seize opportunities to rebuild affected areas. In contrast, emergency response organizations developed their capacity to seize opportunities to provide aid stemming from their decentralized decision-making, a lack of structured procedures, and the authority for increased expenditure.
Originality/value
We propose a theoretical framework to identify humanitarian organizations' operational and dynamic capabilities, distinguishing between global and local organizations and their emergency response and long-term aid missions.
Details
Keywords
Jingrui Ge, Kristoffer Vandrup Sigsgaard, Bjørn Sørskot Andersen, Niels Henrik Mortensen, Julie Krogh Agergaard and Kasper Barslund Hansen
This paper proposes a progressive, multi-level framework for diagnosing maintenance performance: rapid performance health checks of key performance for different equipment groups…
Abstract
Purpose
This paper proposes a progressive, multi-level framework for diagnosing maintenance performance: rapid performance health checks of key performance for different equipment groups and end-to-end process diagnostics to further locate potential performance issues. A question-based performance evaluation approach is introduced to support the selection and derivation of case-specific indicators based on diagnostic aspects.
Design/methodology/approach
The case research method is used to develop the proposed framework. The generic parts of the framework are built on existing maintenance performance measurement theories through a literature review. In the case study, empirical maintenance data of 196 emergency shutdown valves (ESDVs) are collected over a two-year period to support the development and validation of the proposed approach.
Findings
To improve processes, companies need a separate performance measurement structure. This paper suggests a hierarchical model in four layers (objective, domain, aspect and performance measurement) to facilitate the selection and derivation of indicators, which could potentially reduce management complexity and help prioritize continuous performance improvement. Examples of new indicators are derived from a case study that includes 196 ESDVs at an offshore oil and gas production plant.
Originality/value
Methodological approaches to deriving various performance indicators have rarely been addressed in the maintenance field. The proposed diagnostic framework provides a structured way to identify and locate process performance issues by creating indicators that can bridge generic evaluation aspects and maintenance data. The framework is highly adaptive as data availability functions are used as inputs to generate indicators instead of passively filtering out non-applicable existing indicators.
Details