Integrating deep learning and rule-based systems into a smart devices decision support system for visual inspection in production

Mende, Hendrik; Peters, A.; Ibrahim, Faruk; Schmitt, Robert

doi:10.1016/j.procir.2022.05.254

Cited by 4 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A number of studies have been carried out in the criteria-based design and utilization of decision support systems (DSSs) for solving decision-making problems of various nature [60]. Researchers have utilized DSS in project portfolio selection problem, resource allocation problem, manufacturing parts and tools in a production line and enterprise mergers and acquisitions scenario, respectively [61][62][63][64][65]. They have found promising results of DSS application.…”

Section: Rule-based Decision Support System (Rbdss)mentioning

confidence: 99%

Factors Hindering Solar Photovoltaic System Implementation in Buildings and Infrastructure Projects: Analysis through a Multiple Linear Regression Model and Rule-Based Decision Support System

Mustafa

Malik

2023

Buildings

View full text Add to dashboard Cite

Energy plays a predominant role in the development of society. With advancements in technology and the growth of society (buildings and infrastructures), the demand for energy is rapidly increasing. Developing countries typically rely on the import of fossil fuels and capital investments in infrastructure development to meet their energy needs. The execution of solar PV projects in developing countries is currently not being implemented promisingly. Therefore, the determination of the critical success factors hindering the implementation of solar PV projects is the need of the hour. The aim of this study is to determine the factors that hinder the implementation of solar PV projects through the use of a multiple linear regression model (MLRM) and a rule-based decision support system (RBDSS). Seven categories of factors were identified through a detailed literature review and interviews with energy experts. Four hundred and twenty-nine complete responses were collected in total through a questionnaire, and they were analyzed using relative importance indexing (RII) and MLRM and RBDSS approaches. A comparison was carried out against both methodologies to determine the most critical barriers to the implementation of solar PV projects. The findings regarding the MLRM approach showed that the top seven critical factors were economic conditions, encouraging policies, technological knowledge, organizational support, social awareness, market stability, and miscellaneous aspects. Similarly, the results for the RBDSS approach identified that the top seven critical factors were encouraging policies, economic conditions, organizational support, technological knowledge, market stability, social awareness, and miscellaneous aspects. The application of MLRM and RBDSS will help stakeholders in making timely decisions and corrections during the implementation phase, providing a systematic way to support the performance and execution of solar projects.

show abstract

Section: Rule-based Decision Support System (Rbdss)mentioning

confidence: 99%

Factors Hindering Solar Photovoltaic System Implementation in Buildings and Infrastructure Projects: Analysis through a Multiple Linear Regression Model and Rule-Based Decision Support System

Mustafa

Malik

2023

Buildings

View full text Add to dashboard Cite

show abstract

Werkerassistenz und Deep Learning für die Sichtprüfung

Mende,

Schmitt

2023

Masch.Bau

View full text Add to dashboard Cite

Classifying forensically important flies using deep learning to support pathologists and rescue teams during forensic investigations

Gohe,

Kottek,

Buettner

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Forensic entomology can help estimate the postmortem interval in criminal investigations. In particular, forensically important fly species that can be found on a body and in its environment at various times after death provide valuable information. However, the current method for identifying fly species is labor intensive, expensive, and may become more serious in view of a shortage of specialists. In this paper, we propose the use of computer vision and deep learning to classify adult flies according to three different families, Calliphoridae, Sarcophagidae, Rhiniidae, and their corresponding genera Chrysomya, Lucilia, Sarcophaga, Rhiniinae, and Stomorhina, which can lead to efficient and accurate estimation of time of death, for example, with the use of camera-equipped drones. The development of such a deep learning model for adult flies may be particularly useful in crisis situations, such as natural disasters and wars, when people disappear. In these cases drones can be used for searching large areas. In this study, two models were evaluated using transfer learning with MobileNetV3-Large and VGG19. Both models achieved a very high accuracy of 99.39% and 99.79%. In terms of inference time, the MobileNetV3-Large model was faster with an average time per step of 1.036 seconds than the VGG19 model, which took 2.066 seconds per step. Overall, the results highlight the potential of deep learning models for the classification of fly species in forensic entomology and search and rescue operations.

show abstract

Integrating deep learning and rule-based systems into a smart devices decision support system for visual inspection in production

Cited by 4 publications

References 19 publications

Factors Hindering Solar Photovoltaic System Implementation in Buildings and Infrastructure Projects: Analysis through a Multiple Linear Regression Model and Rule-Based Decision Support System

Factors Hindering Solar Photovoltaic System Implementation in Buildings and Infrastructure Projects: Analysis through a Multiple Linear Regression Model and Rule-Based Decision Support System

Werkerassistenz und Deep Learning für die Sichtprüfung

Classifying forensically important flies using deep learning to support pathologists and rescue teams during forensic investigations

Contact Info

Product

Resources

About