Cognitive analytics platform with AI solutions for anomaly detection

Rousopoulou, Vaia; Vafeiadis, Thanasis; Nizamis, Alexandros; Iakovidis, Ioannis; Samaras, Leonidas; Kirtsoglou, Alkis; Georgiadis, Konstantinos; Ioannidis, Dimosthenis; Tzovaras, Dimitrios

doi:10.1016/j.compind.2021.103555

Cited by 31 publications

(9 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…the system aims to detect signals for potential failures before they occur by using machine learning methods [14]. Rousopoulou et al present a cognitive analytics platform for anomaly detection, so as to support the emerging and growing needs of manufacturing industry [59]. In order to achieve demand satisfaction and scheduling planning of downstream service providers, Khan et al and Kiangala and Wang respectively built mechanism platforms through gradient boost regression Tree (GBDT), XGBoost and RF [60,61].…”

Section: Application In I Categorymentioning

confidence: 99%

Ensemble Learning Applications in Multiple Industries: A Review

Lin¹,

Huang²

2023

IDA

View full text Add to dashboard Cite

This study proposes a systematic review of the application of Ensemble learning (EL) in multiple industries. This study aims to review prevailing application in multiple industries to guide for the future landing application. This study also proposes a research method based on Systematic Literature Review (SLR) to address EL literature and help advance our understanding of EL for future optimization. The literature is divided three categories by the National Bureau of Statistics of China (NBSC): the primary industry, the secondary industry and the tertiary industry. Among existing problems in industrial management systems, the frequently discussed are quality control, prediction, detection, efficiency and satisfaction. In addition, given the huge potential in various fields, the gap and further directions are also suggested. This study is essential to industry managers and cross-disciplinary scholars to lead a guideline to solve the issues in practical work, as it provided a panorama of application domains and current problems. This is the first review of the application of EL in multiple industries in the literature. The paper has potential values to broaden the application area of EL, and to proposed a novel research method based SLR to sort out literature.

show abstract

Section: Application In I Categorymentioning

confidence: 99%

Ensemble Learning Applications in Multiple Industries: A Review

Lin¹,

Huang²

2023

IDA

View full text Add to dashboard Cite

show abstract

“…These studies have employed complex DL architectures rather than simple network structures to achieve enhanced outcomes [2,13]. Moreover, these studies have sought to advance smart systems by proposing ML frameworks that consider realworld factory environments [11,32]. Consequently, there is a need to introduce practical anomaly detection models suitable for manufacturing processes.…”

Section: Related Workmentioning

confidence: 99%

“…Taking into account the aforementioned challenges, this study employs a suitable detection model approach within the manufacturing context. This is achieved by conducting interviews with practitioners and combining their domain expertise with AI technology to develop an efficient system architecture [9,11,35]. Furthermore, this study proposes real-time model utilization methods, such as early warnings in the manufacturing process, by building an anomaly detection model through a step-by-step procedure (Fig.…”

Section: B Approaches For Anomaly Detectionmentioning

confidence: 99%

“…In other words, the reality is insufficient to tackle tasks such as the development of capabilities for new technologies among workers [9]. This can be explained by the fact that, as more complexity is added to AI technology operations, the sustainability of technology operations decreases [10,11]. From an organizational perspective, solutions such as technology should be considered for selfoperation by relevant organizations with minimal effort [12].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Enhanced Anomaly Detection in Manufacturing Processes Through Hybrid Deep Learning Techniques

Lee,

Kim,

Kim

2023

IEEE Access

View full text Add to dashboard Cite

Smart factory systems have been introduced to prevent the decline in overall equipment effectiveness caused by the presence of defects within factory manufacturing equipment. In this context, it is crucial to predict process downtime using manufacturing equipment data and take preemptive actions. However, anomaly detection models for preemptive actions have limitations in labeling anomaly alarms. Moreover, from real-time data collection to model deployment, it needs to consider the model-based service implementation for stakeholders. Our research develops a hybrid deep learning-based anomaly detection model that does not require data labeling. The advantage of this model stems from its ability to identify anomalous patterns via the reconstruction of the sequential progression inherent in the data. According to our experimental findings, the proposed hybrid model demonstrated superior efficacy compared to alternative anomaly detection algorithms. By preemptively predicting downtime within the manufacturing process, it contributes to enhanced production efficiency. Furthermore, we develop an anomaly detection system based on a real-time service framework from the data collection step to improve the activation of smart factories. This research contributes to the literature on the monitoring and management of anomaly detection in smart factories. It also has practical implications for the manufacturing industry by recommending efficiency measures for smart factories to reduce downtime in manufacturing processes and improve product quality.

show abstract

“…According to (Rousopoulou, Vafeiadis, Nizamis, Iakovidis, Samaras, Kirtsoglou et al, 2022), prescriptive analysis not only seeks the characterization of past, present, and future systemic behaviors, it also links, through inferential analytics, knowledge of the causes of behavior. The main characteristic of this type of analysis is the technological synergy of data, business guidelines and mathematical models.…”

Section: Data Analytics and Dashboard Presentationmentioning

confidence: 99%

Sustainable manufacturing in the fourth industrial revolution: A big data application proposal in the textile industry

González

Hernández²,

Vásquez³

et al. 2022

JIEM

View full text Add to dashboard Cite

Purpose: Design an industrial production model with a focus on industry 4.0 (Big Data) and decision-making analysis for small and medium-sized enterprises (SMEs) in the clothing sector that allows improving procedures, jobs and related costs within the study organization Develop a sustainable manufacturing proposal for the industrial textile sector with a focus on Big data (entry, transformation, data loading and analysis) in organizational decision making, in search of time and cost optimization and environmental impact mitigation related.Design/methodology/approach: The present research, of an applied nature, raises a value proposition focused on the planning, design and structuring of an industrial model focused on Big Data, specifically in the apparel manufacturing sector for decision-making in a structured and automated way with the methodological approach to follow: 1) Approach of production strategies oriented in Big Data for the textile sector; 2) Definition of the production model and configuration of the operational system; 3) Data science and industrial analysis, 4) Production model approach (Power BI) and 5) model validation. Methodological design of the investigation. 1) Presentation of the case study, where the current situational analysis of the company is carried out, formulation of the problem and proposal of solution for the set of data analyzed; 2) Presentation of a solution proposal focused on Big Data, on the identification of the industrial ecosystem and integration with the company's information systems, as well as the solution approach in the study and science of data in real time; 3) Presentation of the Model proposal for SQL structured databases in the loading, transformation and loading of important information for this study; 4) Information processing, in the edition of data in the M language of Power BI software, construction and elaboration of the model; 5) Presentation of the related databases, in the integration with the foreign key of the Master table and the transactional Tables; 6) Data analysis and presentation of the Dashboard, in the design, construction and analysis of the related study variables, as well as the approach of solution scenarios in the correct organizational decision makingFindings: The results obtained show an improvement in operational efficiency from the value-added proposal. Research limitations/implications: Currently, the number of studies applying Big Data technology for organizations in the textile and manufacturing sector in organizational decision making are limited. If analyzed from the local scene, there are few cases of Big Data implementation in the textile sector, as a consequence of the lack of projects and financing of value propositions. Another limiting factor in this research is the absence of digital information of high relevance for study and analysis, which leads to longer times in data entry and placement in information systems in real time. Finally, there is no data organizational culture, where there are processes and/or procedures for data registration and its transformation into clean data.Originality/value: This research integrates, as well as the correct organizational decision making For the verification of originality, the project search and systematic review of literature in the main online search engines are carried out for this research; In addition, the percentages of coincidence with online reviewers such as turnitin and plag.es are reviewed in the transparency of this study project.

show abstract

Cognitive analytics platform with AI solutions for anomaly detection

Cited by 31 publications

References 29 publications

Ensemble Learning Applications in Multiple Industries: A Review

Ensemble Learning Applications in Multiple Industries: A Review

Enhanced Anomaly Detection in Manufacturing Processes Through Hybrid Deep Learning Techniques

Sustainable manufacturing in the fourth industrial revolution: A big data application proposal in the textile industry

Contact Info

Product

Resources

About