scholarly journals Deploying an Artificial Intelligence-Based Defect Finder for Manufacturing Quality Management

AI Magazine ◽  
2021 ◽  
Vol 42 (2) ◽  
pp. 5-18
Author(s):  
Kyoung Jun Lee ◽  
Jun Woo Kwon ◽  
Soohong Min ◽  
Jungho Yoon
Keyword(s):  
Artificial Intelligence ◽  
Quality Management ◽  
Response Time ◽  
Large Scale ◽  
Classification Model ◽  
Group Model ◽  
Accuracy Rate ◽  
Intelligence System ◽  
Time Requirements ◽  
Visual Geometry

This paper describes how the Big Data Research Center of Kyung Hee University and Benple Inc. developed and deployed an artificial intelligence system to automate the quality management process for Frontec, an SME company that manufactures automobile parts. Various constraints, such as response time requirements and the limited computing resources available, needed to be considered in this project. Defect finders using large-scale images are expected to classify weld nuts within 0.2 s with an accuracy rate of over 95%. Our system uses Circular Hough Transform for preprocessing as well as an adjusted VGG (Visual Geometry Group) model. Our convolutional neural network (CNN) system shows an accuracy of over 99% and a response time of about 0.14 s. To embed the CNN model into the factory, we reimplemented the preprocessing modules using LabVIEW and had the classification model server communicate with an existing vision inspector. We share our lessons from this experience by explain-ing the procedure and real-world issues developing and embedding a deep learn-ing framework in an existing manufacturing environment without implementing any hardware changes.

scholarly journals Embedding Convolution Neural Network-Based Defect Finder for Deployed Vision Inspector in Manufacturing Company Frontec

2020 ◽  
Vol 34 (08) ◽  
pp. 13164-13171
Author(s):  
Kyoung Jun Lee ◽  
Jun Woo Kwon ◽  
Soohong Min ◽  
Jungho Yoon
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Response Time ◽  
Automobile Industry ◽  
Large Scale ◽  
Group Model ◽  
Quality Inspection ◽  
Circular Hough Transform ◽  
Learning Framework ◽  
Visual Geometry

In collaboration with Frontec, which produces parts such as bolts and nuts for the automobile industry, Kyung Hee University and Benple Inc. develop and deploy AI system for automatic quality inspection of weld nuts. Various constraints to consider exist in adopting AI for the factory, such as response time and limited computing resources available. Our convolutional neural network (CNN) system using large-scale images must classify weld nuts within 0.2 seconds with accuracy over 95%. We designed Circular Hough Transform based preprocessing and an adjusted VGG (Visual Geometry Group) model. The system showed accuracy over 99% and response time of about 0.14 sec. We use TCP / IP protocol to communicate the embedded classification system with an existing vision inspector using LabVIEW. We suggest ways to develop and embed a deep learning framework in an existing manufacturing environment without a hardware change.

scholarly journals Automation of gender determination in human canines using artificial intelligence

2018 ◽  
Vol 50 (3) ◽  
pp. 116
Author(s):  
F. Fidya ◽  
Bayu Priyambadha
Keyword(s):  
Artificial Intelligence ◽  
Sexual Dimorphism ◽  
Decision Tree ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
Classification Model ◽  
Accuracy Rate ◽  
Identification Process ◽  
Gender Determination ◽  
Lower Canine

Background: Gender determination is an important aspect of the identification process. The tooth represents a part of the human body that indicates the nature of sexual dimorphism. Artificial intelligence enables computers to perform to the same standard the same tasks as those carried out by humans. Several methods of classification exist within an artificial intelligence approach to identifying sexual dimorphism in canines. Purpose: This study aimed to quantify the respective accuracy of the Naive Bayes, decision tree, and multi-layer perceptron (MLP) methods in identifying sexual dimorphism in canines. Methods: A sample of results derived from 100 measurements of the diameter of mesiodistal, buccolingual, and diagonal upper and lower canine jaw models of both genders were entered into an application computer program that implements the algorithm (MLP). The analytical process was conducted by the program to obtain a classification model with testing being subsequently carried out in order to obtain 50 new measurement results, 25 each for males and females. A comparative analysis was conducted on the program-generated information. Results: The accuracy rate of the Naive Bayes method was 82%, while that of the decision tree and MLP amounted to 84%. The MLP method had an absolute error value lower than that of its decision tree counterpart. Conclusion: The use of artificial intelligence methods produced a highly accurate identification process relating to the gender determination of canine teeth. The most appropriate method was the MLP with an accuracy rate of 84%.

Cloud-Based Artificial Intelligence System for Large-Scale Arrhythmia Screening

Computer ◽  
2019 ◽  
Vol 52 (11) ◽  
pp. 40-51 ◽  
Author(s):  
Chi-Ho Tseng ◽  
Men-Tzung Lo ◽  
Chen Lin ◽  
Hsiang-Chih Chang ◽  
Cyuan-Cin Liu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Large Scale ◽  
Artificial Intelligence System ◽  
Intelligence System

scholarly journals Detection of elusive polyps via a large-scale artificial intelligence system (with videos)

2021 ◽  
Author(s):  
Dan M. Livovsky ◽  
Danny Veikherman ◽  
Tomer Golany ◽  
Amit Aides ◽  
Valentin Dashinsky ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Large Scale ◽  
Artificial Intelligence System ◽  
Intelligence System

Artificial Intelligence as a Tool to Improve the Administration of Justice?

2020 ◽  
Vol 8 (2) ◽  
pp. 179-189
Author(s):  
Maria Dymitruk
Keyword(s):  
Artificial Intelligence ◽  
Large Scale ◽  
Technological Development ◽  
Legal Compliance ◽  
Judicial Decision Making ◽  
Scientific Discussion ◽  
Intelligence System ◽  
Administration Of Justice ◽  
Legal Informatics ◽  
Judicial Proceedings

Recently, technological development made a significant impact on the administration of justice. Lawyers, both legal practitioners and academics, can no longer afford to ignore the potential that the technology offers. The development of new fields in legal informatics, such as the applicability of Artificial Intelligence (AI) in law, opened up new opportunities which have hitherto been unthinkable. In the not too distant future, lawyers will need to answer the question whether AI can be engaged in the process of judicial decision making. On the other hand, the creation of a well-functioning artificial intelligence system which can carry out numerous adjudicating activities and reasoning processes is not the only requirement for using artificial intelligence in the automation process of judicial activities. Detailed analysis of its legal compliance is needed as well. This paper analyses the admissibility of using artificial intelligence tools in the judiciary and contains considerations on ethical aspects of AI application in judicial proceedings (whether an AI system is capable of taking over the role of a decision maker in judicial proceedings, thereby replacing, or supporting the judge). The research presented in the paper may provide an impulse to start a large-scale scientific discussion on the possibility and admissibility of AI application in the judicial system and may also be the basis for formulating proposals addressed to lawmakers and policymakers.

scholarly journals Development of an Artificial Intelligence System (AI) Based on Patterns Recognition for the Analysis of Vehicular Routes

2020 ◽  
Vol 23 (65) ◽  
pp. 67-85
Author(s):  
Leonardo Luís Röpke ◽  
Manuel Osório Binelo
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Accuracy Rate ◽  
Artificial Intelligence System ◽  
Intelligence System ◽  
Artificial Neural

This work presents the study and development of an Artificial Intelligence system, with focus on K-means algorithms and Artificial Neural Networks, to assist fleet managers in the identification of routes and route deviations. The developed tool has the objective of modernizing the process of identification of routes and deviations of routes. The results show that the Artificial Neural Networks obtained a 100% accuracy rate in the identification of routes, and in the identification of route deviations the RNAs were able to identify 61% of the routes presented. Therefore, RNAs are an excellent technique to be applied to the identification of routes and deviations of routes. The K-means algorithm presented good results when applied in the discovery of similar routes, thus becoming an important tool applied to the work of monitoring vehicles routes.

AI-Provided Instant Differential Diagnosis of Pemphigus Vulgaris and Bullous Pemphigoid: Qualitative Study (Preprint)

2020 ◽  
Author(s):  
Xiaoyu He ◽  
Juan Su ◽  
Guangyu Wang ◽  
Kang Zhang ◽  
Navarini Alexander ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Early Diagnosis ◽  
Image Classification ◽  
Bullous Pemphigoid ◽  
Skin Diseases ◽  
Pemphigus Vulgaris ◽  
Classification Model ◽  
Clinical Image ◽  
Clinical Images ◽  
Multimodal Classification

BACKGROUND Pemphigus vulgaris (PV) and bullous pemphigoid (BP) are two rare but severe inflammatory dermatoses. Due to the regional lack of trained dermatologists, many patients with these two diseases are misdiagnosed and therefore incorrectly treated. An artificial intelligence diagnosis framework would be highly adaptable for the early diagnosis of these two diseases. OBJECTIVE Design and evaluate an artificial intelligence diagnosis framework for PV and BP. METHODS The work was conducted on a dermatological dataset consisting of 17,735 clinical images and 346 patient metadata of bullous dermatoses. A two-stage diagnosis framework was designed, where the first stage trained a clinical image classification model to classify bullous dermatoses from five common skin diseases and normal skin and the second stage developed a multimodal classification model of clinical images and patient metadata to further differentiate PV and BP. RESULTS The clinical image classification model and the multimodal classification model achieved an area under the receiver operating characteristic curve (AUROC) of 0.998 and 0.942, respectively. On the independent test set of 20 PV and 20 BP cases, our multimodal classification model (sensitivity: 0.85, specificity: 0.95) performed better than the average of 27 junior dermatologists (sensitivity: 0.68, specificity: 0.78) and comparable to the average of 69 senior dermatologists (sensitivity: 0.80, specificity: 0.87). CONCLUSIONS Our diagnosis framework based on clinical images and patient metadata achieved expert-level identification of PV and BP, and is potential to be an effective tool for dermatologists in remote areas in the early diagnosis of these two diseases.

scholarly journals BattleNet: Capturing Advantageous Battlefield in RTS Games (Student Abstract)

2020 ◽  
Vol 34 (10) ◽  
pp. 13849-13850
Author(s):  
Donghyeon Lee ◽  
Man-Je Kim ◽  
Chang Wook Ahn
Keyword(s):  
Artificial Intelligence ◽  
Decision Making ◽  
Real Time ◽  
Large Scale ◽  
Outcome Predictor ◽  
Short Term ◽  
Rts Game

In a real-time strategy (RTS) game, StarCraft II, players need to know the consequences before making a decision in combat. We propose a combat outcome predictor which utilizes terrain information as well as squad information. For training the model, we generated a StarCraft II combat dataset by simulating diverse and large-scale combat situations. The overall accuracy of our model was 89.7%. Our predictor can be integrated into the artificial intelligence agent for RTS games as a short-term decision-making module.

Sign in / Sign up

Export Citation Format

Share Document