Pub Date : 2023-03-27DOI: 10.3390/informatics10020033
Amanda L. Luo, Akshay Ravi, Simone Arvisais-Anhalt, Anoop Muniyappa, Xinran Liu, Sha Wang
(1) One in four hospital readmissions is potentially preventable. Machine learning (ML) models have been developed to predict hospital readmissions and risk-stratify patients, but thus far they have been limited in clinical applicability, timeliness, and generalizability. (2) Methods: Using deidentified clinical data from the University of California, San Francisco (UCSF) between January 2016 and November 2021, we developed and compared four supervised ML models (logistic regression, random forest, gradient boosting, and XGBoost) to predict 30-day readmissions for adults admitted to a UCSF hospital. (3) Results: Of 147,358 inpatient encounters, 20,747 (13.9%) patients were readmitted within 30 days of discharge. The final model selected was XGBoost, which had an area under the receiver operating characteristic curve of 0.783 and an area under the precision-recall curve of 0.434. The most important features by Shapley Additive Explanations were days since last admission, discharge department, and inpatient length of stay. (4) Conclusions: We developed and internally validated a supervised ML model to predict 30-day readmissions in a US-based healthcare system. This model has several advantages including state-of-the-art performance metrics, the use of clinical data, the use of features available within 24 h of discharge, and generalizability to multiple disease states.
{"title":"Development and Internal Validation of an Interpretable Machine Learning Model to Predict Readmissions in a United States Healthcare System","authors":"Amanda L. Luo, Akshay Ravi, Simone Arvisais-Anhalt, Anoop Muniyappa, Xinran Liu, Sha Wang","doi":"10.3390/informatics10020033","DOIUrl":"https://doi.org/10.3390/informatics10020033","url":null,"abstract":"(1) One in four hospital readmissions is potentially preventable. Machine learning (ML) models have been developed to predict hospital readmissions and risk-stratify patients, but thus far they have been limited in clinical applicability, timeliness, and generalizability. (2) Methods: Using deidentified clinical data from the University of California, San Francisco (UCSF) between January 2016 and November 2021, we developed and compared four supervised ML models (logistic regression, random forest, gradient boosting, and XGBoost) to predict 30-day readmissions for adults admitted to a UCSF hospital. (3) Results: Of 147,358 inpatient encounters, 20,747 (13.9%) patients were readmitted within 30 days of discharge. The final model selected was XGBoost, which had an area under the receiver operating characteristic curve of 0.783 and an area under the precision-recall curve of 0.434. The most important features by Shapley Additive Explanations were days since last admission, discharge department, and inpatient length of stay. (4) Conclusions: We developed and internally validated a supervised ML model to predict 30-day readmissions in a US-based healthcare system. This model has several advantages including state-of-the-art performance metrics, the use of clinical data, the use of features available within 24 h of discharge, and generalizability to multiple disease states.","PeriodicalId":37100,"journal":{"name":"Informatics","volume":"10 1","pages":"33"},"PeriodicalIF":3.1,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41548295","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-16DOI: 10.3390/informatics10010032
Ezekiel Bernardo, R. Seva
Explainable Artificial Intelligence (XAI) has successfully solved the black box paradox of Artificial Intelligence (AI). By providing human-level insights on AI, it allowed users to understand its inner workings even with limited knowledge of the machine learning algorithms it uses. As a result, the field grew, and development flourished. However, concerns have been expressed that the techniques are limited in terms of to whom they are applicable and how their effect can be leveraged. Currently, most XAI techniques have been designed by developers. Though needed and valuable, XAI is more critical for an end-user, considering transparency cleaves on trust and adoption. This study aims to understand and conceptualize an end-user-centric XAI to fill in the lack of end-user understanding. Considering recent findings of related studies, this study focuses on design conceptualization and affective analysis. Data from 202 participants were collected from an online survey to identify the vital XAI design components and testbed experimentation to explore the affective and trust change per design configuration. The results show that affective is a viable trust calibration route for XAI. In terms of design, explanation form, communication style, and presence of supplementary information are the components users look for in an effective XAI. Lastly, anxiety about AI, incidental emotion, perceived AI reliability, and experience using the system are significant moderators of the trust calibration process for an end-user.
{"title":"Affective Design Analysis of Explainable Artificial Intelligence (XAI): A User-Centric Perspective","authors":"Ezekiel Bernardo, R. Seva","doi":"10.3390/informatics10010032","DOIUrl":"https://doi.org/10.3390/informatics10010032","url":null,"abstract":"Explainable Artificial Intelligence (XAI) has successfully solved the black box paradox of Artificial Intelligence (AI). By providing human-level insights on AI, it allowed users to understand its inner workings even with limited knowledge of the machine learning algorithms it uses. As a result, the field grew, and development flourished. However, concerns have been expressed that the techniques are limited in terms of to whom they are applicable and how their effect can be leveraged. Currently, most XAI techniques have been designed by developers. Though needed and valuable, XAI is more critical for an end-user, considering transparency cleaves on trust and adoption. This study aims to understand and conceptualize an end-user-centric XAI to fill in the lack of end-user understanding. Considering recent findings of related studies, this study focuses on design conceptualization and affective analysis. Data from 202 participants were collected from an online survey to identify the vital XAI design components and testbed experimentation to explore the affective and trust change per design configuration. The results show that affective is a viable trust calibration route for XAI. In terms of design, explanation form, communication style, and presence of supplementary information are the components users look for in an effective XAI. Lastly, anxiety about AI, incidental emotion, perceived AI reliability, and experience using the system are significant moderators of the trust calibration process for an end-user.","PeriodicalId":37100,"journal":{"name":"Informatics","volume":"10 1","pages":"32"},"PeriodicalIF":3.1,"publicationDate":"2023-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43184778","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Recent technology implementation in learning has inspired language educators to employ various e-learning techniques, strategies, and applications in their pedagogical practices while aiming at improving specific learning efficiencies of students. The current study attempts to blend e-learning activities, including blogging, video making, online exercises, and digital storyboarding, with English language teaching and explores its impact on engineering cohorts at a public university in Malaysia. The longitudinal research study used three digital applications—Voyant Tools, Lumos Text Complexity Analyzer, and Advanced Text Analyzer—to analyze the data collected through a variety of digital assignments and activities from two English language courses during the researched academic semesters. Contributing to the available literature on the significance of integrating technology innovation with language learning, the study found that implementing e-learning activities can provide substantial insights into improving the learners’ different linguistic competencies, including writing competency, reading comprehension, and vocabulary enhancement. Moreover, the implementation of such innovative technology can motivate students to engage in more peer interactivity, learning engagement, and self-directed learning.
{"title":"Impact of E-Learning Activities on English as a Second Language Proficiency among Engineering Cohorts of Malaysian Higher Education: A 7-Month Longitudinal Study","authors":"Dipima Buragohain, Grisana Punpeng, Sureenate Jaratjarungkiat, Sushank Chaudhary","doi":"10.3390/informatics10010031","DOIUrl":"https://doi.org/10.3390/informatics10010031","url":null,"abstract":"Recent technology implementation in learning has inspired language educators to employ various e-learning techniques, strategies, and applications in their pedagogical practices while aiming at improving specific learning efficiencies of students. The current study attempts to blend e-learning activities, including blogging, video making, online exercises, and digital storyboarding, with English language teaching and explores its impact on engineering cohorts at a public university in Malaysia. The longitudinal research study used three digital applications—Voyant Tools, Lumos Text Complexity Analyzer, and Advanced Text Analyzer—to analyze the data collected through a variety of digital assignments and activities from two English language courses during the researched academic semesters. Contributing to the available literature on the significance of integrating technology innovation with language learning, the study found that implementing e-learning activities can provide substantial insights into improving the learners’ different linguistic competencies, including writing competency, reading comprehension, and vocabulary enhancement. Moreover, the implementation of such innovative technology can motivate students to engage in more peer interactivity, learning engagement, and self-directed learning.","PeriodicalId":37100,"journal":{"name":"Informatics","volume":"10 1","pages":"31"},"PeriodicalIF":3.1,"publicationDate":"2023-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41880646","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-12DOI: 10.3390/informatics10010030
I. Redondo, Gloria Aznar
Website publishers cannot monetize the ad impressions that are prevented by ad-blockers. Publishers can then employ anti-ad-blockers that force users to choose between either accepting ad impressions by whitelisting the website in the ad-blocker, or leaving the website without accessing the content. This study delineates the mechanisms of how willingness to whitelist/leave the website are affected by the request’s sensitivity to recipients as well as the users’ psychological reactance and evaluation of the website advertising. We tested the proposed relationships using an online panel sample of 500 ad-blocker users, who were asked about their willingness to whitelist/leave their favorite online newspaper after receiving a hypothetical anti-ad-blocker request—four alternative requests with different sensitivity levels were created and randomly assigned to the participants. The results confirmed that (a) the request’s sensitivity can improve the recipient’s compliance, (b) users’ psychological reactance plays an important role in explaining the overall phenomenon, and (c) a favorable evaluation of the website advertising can improve willingness to whitelist. These findings help to better understand user response to anti-ad-blockers and may also help publishers increase their whitelist ratios.
{"title":"Whitelist or Leave Our Website! Advances in the Understanding of User Response to Anti-Ad-Blockers","authors":"I. Redondo, Gloria Aznar","doi":"10.3390/informatics10010030","DOIUrl":"https://doi.org/10.3390/informatics10010030","url":null,"abstract":"Website publishers cannot monetize the ad impressions that are prevented by ad-blockers. Publishers can then employ anti-ad-blockers that force users to choose between either accepting ad impressions by whitelisting the website in the ad-blocker, or leaving the website without accessing the content. This study delineates the mechanisms of how willingness to whitelist/leave the website are affected by the request’s sensitivity to recipients as well as the users’ psychological reactance and evaluation of the website advertising. We tested the proposed relationships using an online panel sample of 500 ad-blocker users, who were asked about their willingness to whitelist/leave their favorite online newspaper after receiving a hypothetical anti-ad-blocker request—four alternative requests with different sensitivity levels were created and randomly assigned to the participants. The results confirmed that (a) the request’s sensitivity can improve the recipient’s compliance, (b) users’ psychological reactance plays an important role in explaining the overall phenomenon, and (c) a favorable evaluation of the website advertising can improve willingness to whitelist. These findings help to better understand user response to anti-ad-blockers and may also help publishers increase their whitelist ratios.","PeriodicalId":37100,"journal":{"name":"Informatics","volume":"10 1","pages":"30"},"PeriodicalIF":3.1,"publicationDate":"2023-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47392643","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-10DOI: 10.3390/informatics10010029
G. Kaisara, K. Bwalya
Mobile learning is a global trend, which has become more widespread in the post-COVID-19 pandemic era. However, with the adoption of mobile learning comes new assessment approaches to evaluate the understanding of the acquired information and knowledge. Nevertheless, there is scant knowledge of how to enhance assessment information integrity in mobile learning assessments. Due to the importance of assessments in evaluating knowledge, integrity is the sine qua non of online assessments. This research focuses on the strategies universities could use to improve assessment information integrity. This research adopts a qualitative design, employing interviews with academics as well as teaching and learning support staff for data collection. The findings reveal five strategies that academics and support staff recommend to enhance assessment information integrity in mobile learning. The theoretical and practical implications are discussed, as well as future research directions.
{"title":"Strategies for Enhancing Assessment Information Integrity in Mobile Learning","authors":"G. Kaisara, K. Bwalya","doi":"10.3390/informatics10010029","DOIUrl":"https://doi.org/10.3390/informatics10010029","url":null,"abstract":"Mobile learning is a global trend, which has become more widespread in the post-COVID-19 pandemic era. However, with the adoption of mobile learning comes new assessment approaches to evaluate the understanding of the acquired information and knowledge. Nevertheless, there is scant knowledge of how to enhance assessment information integrity in mobile learning assessments. Due to the importance of assessments in evaluating knowledge, integrity is the sine qua non of online assessments. This research focuses on the strategies universities could use to improve assessment information integrity. This research adopts a qualitative design, employing interviews with academics as well as teaching and learning support staff for data collection. The findings reveal five strategies that academics and support staff recommend to enhance assessment information integrity in mobile learning. The theoretical and practical implications are discussed, as well as future research directions.","PeriodicalId":37100,"journal":{"name":"Informatics","volume":"10 1","pages":"29"},"PeriodicalIF":3.1,"publicationDate":"2023-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42217086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-08DOI: 10.3390/informatics10010028
Mohammad Alauthman, Ahmad Al-qerem, Bilal I. Sowan, A. Alsarhan, Mohammed Eshtay, A. Aldweesh, N. Aslam
Developing an effective classification model in the medical field is challenging due to limited datasets. To address this issue, this study proposes using a generative adversarial network (GAN) as a data-augmentation technique. The research aims to enhance the classifier’s generalization performance, stability, and precision through the generation of synthetic data that closely resemble real data. We employed feature selection and applied five classification algorithms to thirteen benchmark medical datasets, augmented using the least-square GAN (LS-GAN). Evaluation of the generated samples using different ratios of augmented data showed that the support vector machine model outperforms other methods with larger samples. The proposed data augmentation approach using a GAN presents a promising solution for enhancing the performance of classification models in the healthcare field.
{"title":"Enhancing Small Medical Dataset Classification Performance Using GAN","authors":"Mohammad Alauthman, Ahmad Al-qerem, Bilal I. Sowan, A. Alsarhan, Mohammed Eshtay, A. Aldweesh, N. Aslam","doi":"10.3390/informatics10010028","DOIUrl":"https://doi.org/10.3390/informatics10010028","url":null,"abstract":"Developing an effective classification model in the medical field is challenging due to limited datasets. To address this issue, this study proposes using a generative adversarial network (GAN) as a data-augmentation technique. The research aims to enhance the classifier’s generalization performance, stability, and precision through the generation of synthetic data that closely resemble real data. We employed feature selection and applied five classification algorithms to thirteen benchmark medical datasets, augmented using the least-square GAN (LS-GAN). Evaluation of the generated samples using different ratios of augmented data showed that the support vector machine model outperforms other methods with larger samples. The proposed data augmentation approach using a GAN presents a promising solution for enhancing the performance of classification models in the healthcare field.","PeriodicalId":37100,"journal":{"name":"Informatics","volume":"10 1","pages":"28"},"PeriodicalIF":3.1,"publicationDate":"2023-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41461009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This study aimed to examine the use of light and color in digital paintings and their effect on audiences’ perceptions of environmental issues. Five digital paintings depicting environmental issues have been designed. Digital painting techniques created black-and-white, monochrome, and color images. Each image used utopian and dystopian visualization concepts to communicate hope and despair. In the experiment, 225 volunteers representing students in colleges were separated into three independent groups: the first group was offered black-and-white images, the second group was offered monochromatic images, and the third group was offered color images. After viewing each image, participants were asked to complete questionnaires about their emotions and cognitions regarding environmental issues, including identifying hope and despair and the artist’s perspective at the end. The analysis showed no differences in emotions and cognitions among participants. However, monochromatic images were the most emotionally expressive. The results indicated that the surrounding atmosphere of the images created despair, whereas objects inspired hope. Artists should emphasize the composition of the atmosphere and the objects in the image to convey the concepts of utopia and dystopia to raise awareness of environmental issues.
{"title":"The Influence of Light and Color in Digital Paintings of Environmental Issues on Emotions and Cognitions","authors":"Witthaya Hosap, Chaowanan Khundam, Patibut Preeyawongsakul, Varunyu Vorachart, Frédéric Noël","doi":"10.3390/informatics10010026","DOIUrl":"https://doi.org/10.3390/informatics10010026","url":null,"abstract":"This study aimed to examine the use of light and color in digital paintings and their effect on audiences’ perceptions of environmental issues. Five digital paintings depicting environmental issues have been designed. Digital painting techniques created black-and-white, monochrome, and color images. Each image used utopian and dystopian visualization concepts to communicate hope and despair. In the experiment, 225 volunteers representing students in colleges were separated into three independent groups: the first group was offered black-and-white images, the second group was offered monochromatic images, and the third group was offered color images. After viewing each image, participants were asked to complete questionnaires about their emotions and cognitions regarding environmental issues, including identifying hope and despair and the artist’s perspective at the end. The analysis showed no differences in emotions and cognitions among participants. However, monochromatic images were the most emotionally expressive. The results indicated that the surrounding atmosphere of the images created despair, whereas objects inspired hope. Artists should emphasize the composition of the atmosphere and the objects in the image to convey the concepts of utopia and dystopia to raise awareness of environmental issues.","PeriodicalId":37100,"journal":{"name":"Informatics","volume":"10 1","pages":"26"},"PeriodicalIF":3.1,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41373895","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-03DOI: 10.3390/informatics10010027
Sara G. Fahmy, Sayed AbdelGaber, Omar H. Karam, Doaa S. Elzanfaly
The mechanisms of information diffusion in Online Social Networks (OSNs) have been studied extensively from various perspectives with some focus on identifying and modeling the role of heterogeneous nodes. However, none of these studies have considered the influence of fake accounts on human accounts and how this will affect the rumor diffusion process. This paper aims to present a new information diffusion model that characterizes the role of bots in the rumor diffusion process in OSNs. The proposed SIhIbR model extends the classical SIR model by introducing two types of infected users with different infection rates: the users who are infected by human (Ih) accounts with a normal infection rate and the users who are infected by bot accounts (Ib) with a different diffusion rate that reflects the intent and steadiness of this type of account to spread the rumors. The influence of fake accounts on human accounts diffusion rate has been measured using the social impact theory, as it better reflects the deliberate behavior of bot accounts to spread a rumor to a large portion of the network by considering both the strength and the bias of the source node. The experiment results show that the accuracy of the SIhIbR model outperforms the SIR model when simulating the rumor diffusion process in the existence of fake accounts. It has been concluded that fake accounts accelerate the rumor diffusion process as they impact many people in a short time.
在线社交网络(Online Social Networks, OSNs)中的信息扩散机制已经从不同的角度进行了广泛的研究，其中一些重点是识别和建模异构节点的作用。然而，这些研究都没有考虑到假账号对真人账号的影响，以及这将如何影响谣言的传播过程。本文旨在提出一种新的信息扩散模型，该模型描述了机器人在社交网络谣言传播过程中的作用。本文提出的SIhIbR模型对经典SIR模型进行了扩展，引入了两种感染率不同的感染用户:感染率正常的人账号(Ih)感染用户和传播速率不同的机器人账号(Ib)感染用户，这反映了这类账号传播谣言的意图和稳定性。虚假账户对人类账户扩散率的影响已经使用社会影响理论进行了测量，因为它更好地反映了机器人账户通过考虑源节点的强度和偏差，将谣言传播到网络的大部分的故意行为。实验结果表明，SIhIbR模型在模拟虚假账户存在情况下的谣言传播过程时，准确性优于SIR模型。结论是，虚假账号在短时间内影响了很多人，加速了谣言的传播过程。
{"title":"Modeling the Influence of Fake Accounts on User Behavior and Information Diffusion in Online Social Networks","authors":"Sara G. Fahmy, Sayed AbdelGaber, Omar H. Karam, Doaa S. Elzanfaly","doi":"10.3390/informatics10010027","DOIUrl":"https://doi.org/10.3390/informatics10010027","url":null,"abstract":"The mechanisms of information diffusion in Online Social Networks (OSNs) have been studied extensively from various perspectives with some focus on identifying and modeling the role of heterogeneous nodes. However, none of these studies have considered the influence of fake accounts on human accounts and how this will affect the rumor diffusion process. This paper aims to present a new information diffusion model that characterizes the role of bots in the rumor diffusion process in OSNs. The proposed SIhIbR model extends the classical SIR model by introducing two types of infected users with different infection rates: the users who are infected by human (Ih) accounts with a normal infection rate and the users who are infected by bot accounts (Ib) with a different diffusion rate that reflects the intent and steadiness of this type of account to spread the rumors. The influence of fake accounts on human accounts diffusion rate has been measured using the social impact theory, as it better reflects the deliberate behavior of bot accounts to spread a rumor to a large portion of the network by considering both the strength and the bias of the source node. The experiment results show that the accuracy of the SIhIbR model outperforms the SIR model when simulating the rumor diffusion process in the existence of fake accounts. It has been concluded that fake accounts accelerate the rumor diffusion process as they impact many people in a short time.","PeriodicalId":37100,"journal":{"name":"Informatics","volume":"10 1","pages":"27"},"PeriodicalIF":3.1,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42773589","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-22DOI: 10.3390/informatics10010025
P. Nogueira, L. Pereira, Ana Simões, Á. Dias, R. Costa
Companies try to acquire the finest advantages and techniques in a technologically advanced and end-to-end market to have a stronger foothold there. Although empirical research on this topic links IT to a decline in vertical integration, corporations are increasingly using this corporate strategy. The goal of this study is to show how over the past 22 years, scientific literature has changed with regard to how information technology (IT) affects vertical integration, one of the main types of corporate strategies. The findings demonstrated that vertical integration has been evolving in a balanced manner in a technological environment. Three categories—information technology, innovation, and processes—help explain this association and were discovered through cluster analysis. The direction of operational integration, the degree of industry concentration, demand unpredictability, and innovation should all be considered while making integration decisions.
{"title":"Vertical Integration Dynamics to Innovate in Technology Business","authors":"P. Nogueira, L. Pereira, Ana Simões, Á. Dias, R. Costa","doi":"10.3390/informatics10010025","DOIUrl":"https://doi.org/10.3390/informatics10010025","url":null,"abstract":"Companies try to acquire the finest advantages and techniques in a technologically advanced and end-to-end market to have a stronger foothold there. Although empirical research on this topic links IT to a decline in vertical integration, corporations are increasingly using this corporate strategy. The goal of this study is to show how over the past 22 years, scientific literature has changed with regard to how information technology (IT) affects vertical integration, one of the main types of corporate strategies. The findings demonstrated that vertical integration has been evolving in a balanced manner in a technological environment. Three categories—information technology, innovation, and processes—help explain this association and were discovered through cluster analysis. The direction of operational integration, the degree of industry concentration, demand unpredictability, and innovation should all be considered while making integration decisions.","PeriodicalId":37100,"journal":{"name":"Informatics","volume":"10 1","pages":"25"},"PeriodicalIF":3.1,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48084819","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-15DOI: 10.3390/informatics10010024
Giuseppe Ciaburro, Sankar Padmanabhan, Yassine Maleh, Virginia Puyana-Romero
The modern conception of industrial production recognizes the increasingly crucial role of maintenance. Currently, maintenance is thought of as a service that aims to maintain the efficiency of equipment and systems while also taking quality, energy efficiency, and safety requirements into consideration. In this study, a new methodology for automating the fan maintenance procedures was developed. An approach based on the recording of the acoustic emission and the failure diagnosis using deep learning was evaluated for the detection of dust deposits on the blades of an axial fan. Two operating conditions have been foreseen: No-Fault, and Fault. In the No-Fault condition, the fan blades are perfectly clean while in the Fault condition, deposits of material have been artificially created. Utilizing a pre-trained network (SqueezeNet) built on the ImageNet dataset, the acquired data were used to build an algorithm based on convolutional neural networks (CNN). The transfer learning applied to the images of the spectrograms extracted from the recordings of the acoustic emission of the fan, in the two operating conditions, returned excellent results (accuracy = 0.95), confirming the excellent performance of the methodology.
{"title":"Fan Fault Diagnosis Using Acoustic Emission and Deep Learning Methods","authors":"Giuseppe Ciaburro, Sankar Padmanabhan, Yassine Maleh, Virginia Puyana-Romero","doi":"10.3390/informatics10010024","DOIUrl":"https://doi.org/10.3390/informatics10010024","url":null,"abstract":"The modern conception of industrial production recognizes the increasingly crucial role of maintenance. Currently, maintenance is thought of as a service that aims to maintain the efficiency of equipment and systems while also taking quality, energy efficiency, and safety requirements into consideration. In this study, a new methodology for automating the fan maintenance procedures was developed. An approach based on the recording of the acoustic emission and the failure diagnosis using deep learning was evaluated for the detection of dust deposits on the blades of an axial fan. Two operating conditions have been foreseen: No-Fault, and Fault. In the No-Fault condition, the fan blades are perfectly clean while in the Fault condition, deposits of material have been artificially created. Utilizing a pre-trained network (SqueezeNet) built on the ImageNet dataset, the acquired data were used to build an algorithm based on convolutional neural networks (CNN). The transfer learning applied to the images of the spectrograms extracted from the recordings of the acoustic emission of the fan, in the two operating conditions, returned excellent results (accuracy = 0.95), confirming the excellent performance of the methodology.","PeriodicalId":37100,"journal":{"name":"Informatics","volume":"10 1","pages":"24"},"PeriodicalIF":3.1,"publicationDate":"2023-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48052801","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：