Multimodal deep learning for predicting the choice of cut parameters in the milling process

Kounta, Cheick Abdoul Kadir A.; Foguem, Bernard Kamsu; NOUREDDINE, Farid; Tangara, Fana

doi:10.1016/j.iswa.2022.200112

Cited by 8 publications

(7 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If optical images are unavailable due to poor weather conditions, co-learning can help compensate for missing optical image fragments (Zheng et al,2021). The applications of multimodal learning can relate to the contexts of information sciences (speech recognition and synthesis, event detection, emotion and affect, media description and Multimedia retrieval) or industrial contexts such as the verification of the quality of the surfaces of parts obtained after machining processes (Kounta et al, 2022).…”

Section: ) Representationmentioning

confidence: 99%

“…Contributions dealing with some safety, particularly hardware failures such as Dubrawski & Sondheimer, 2011, Ignat et al, 2006, Furst 2019, Rajaram, 2020, Sridharan & Kaeli 2010, and Vankeirsbilck et al, 2015 have no AI or ML consideration. Papers with some AI support particularly multimodaly, such as Junchi et al, 2016, Kounta et al, 2022, Nie et al, 2021and Poria et al, 2016 are implemented without any functional safety component. Work proposed by Arrieta et al, 2020, Coulibaly et al, 2022, Gohel et al, 2016, and Khan & Vice, 2022 deals with some AI and Explainability without any functional safety consideration.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Autonomous Systems Functional Safety Overview with Multimodality and Explainability Perspectives

Tiako,

Kamsu-Foguem

2023

Chronicle of Computing

View full text Add to dashboard Cite

Functional safety is crucial in automation systems, particularly for autonomous vehicles. It is important because it protects humans, systems or vehicles, and operating environments from harm. Automated systems can expose operators to severe safety risks. Functional safety aims to minimize safety risks associated with autonomous systems to protect operators, the environment with nearby infrastructure and people, and the systems themselves. This paper overviews multiple facets of Artificial Intelligence (AI) techniques that reduce functional safety risks. As AI and Machine Learning (ML) progress theoretically and in their application, we face new technical challenges in dealing with Multimodality and Explainability. We will discuss these concepts before briefly providing their perspectives on minimizing safety risks in autonomous systems.

show abstract

Section: ) Representationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Autonomous Systems Functional Safety Overview with Multimodality and Explainability Perspectives

Tiako,

Kamsu-Foguem

2023

Chronicle of Computing

View full text Add to dashboard Cite

show abstract

“…Traditional machine learning (ML) algorithms have limitations with the uniform data format, but integrating more than one type of data is the need of the hour. Multimodal functionalities [1], [2] have recently garnered the attention of researchers to overcome this limitation. Multimodal applications have proven to be effective for hybridizing the models [3], [4] for text and image data types.…”

Section: Introductionmentioning

confidence: 99%

A multimodal machine learning approach to generate news articles from geo-tagged images

Gotmare,

Thite,

Bewoor

2024

IJECE

View full text Add to dashboard Cite

Classical machine learning algorithms typically operate on unimodal data and hence it can analyze and make predictions based on data from a single source (modality). Whereas multimodal machine learning algorithm, learns from information across multiple modalities, such as text, images, audio, and sensor data. The paper leverages the functionalities of multimodal machine learning (ML) application for generating text from images. The proposed work presents an innovative multimodal algorithm that automates the creation of news articles from geo-tagged images by leveraging cutting-edge developments in machine learning, image captioning, and advanced text generation technologies. Employing a multimodal approach that integrates machine learning and transformer algorithms, such as visual geometry group network16 (VGGNet16), convolutional neural network (CNN) and a long short-term memory (LSTM) based system, the algorithm initiates by extracting the location from exchangeable image file format (Exif) data from the image. The features are extracted from the image and corresponding news headline is generated. The headlines are used for generating a comprehensive article with contemporary large language model (LLM). Further, the algorithm generates the news article big-science large open-science open-access multilingual language model (BLOOM). The algorithm was tested on real time photographs as well as images from the internet. In both the cases the news articles generated were validated with ROUGE and BULE score. The proposed work is found to be successful attempt in journalism field.

show abstract

“…Selection and calculation of cutting parameters are necessary for planning machining product work. Selection of the appropriate combination of cutting parameters will produce geometric quality and surface roughness as expected (Bodzas & Krakko, 2017;Fahrizal et al, 2022;Katta, 2018;Kounta et al, 2022;Nagandran, 2017).…”

Section: Introductionmentioning

confidence: 99%

Analysis of the Ability to Develop CNC Machine Part Programs for Vocational High School Students in Indonesia

Kurniawan,

S. Wijanarka

2023

EJEDU

View full text Add to dashboard Cite

The aims of this study are (1) to analyze the effect of the ability to read technical drawings on the ability to make CNC program parts; (2) to analyze the effect of geometry skills on the ability to make CNC program parts; (3) to analyze the effect of cutting parameter knowledge on the ability to make CNC program parts; and (4) analyze the effect of the ability to read technical drawings, geometry skills, and knowledge of cutting parameters simultaneously on the ability to make CNC program parts. This research is quantitative correlational research. The subjects of the study were 360 students of SMK class XII in the field of Mechanical Engineering in the city of Palembang, Indonesia, using a random sampling technique by Isaac and Michael equations so that a total sample of 187 students was obtained. The data collection method uses the test method. The data analysis used is a correlational statistical analysis between the three dependent variables and one independent variable. The results of the study: (1) The ability to read technical drawings has a positive and significant effect on the ability to make CNC programs by 11.17%; (2) Geometry ability has no significant effect on the ability to make CNC programs; (3) Knowledge of cutting parameters has a positive and significant effect on the ability to make CNC programs by 75.36%; and, (4) the ability to read technical drawings, geometry skills, and knowledge of cutting parameters have a positive and significant effect on the ability to make CNC programs by 89.9%.

show abstract

Multimodal deep learning for predicting the choice of cut parameters in the milling process

Cited by 8 publications

References 44 publications

Autonomous Systems Functional Safety Overview with Multimodality and Explainability Perspectives

Autonomous Systems Functional Safety Overview with Multimodality and Explainability Perspectives

A multimodal machine learning approach to generate news articles from geo-tagged images

Analysis of the Ability to Develop CNC Machine Part Programs for Vocational High School Students in Indonesia

Contact Info

Product

Resources

About