Curved Hull Plate Classification for Determining Forming Method using Deep Learning

2019 ◽  
Vol 35 (4) ◽  
pp. 328-337
Author(s):  
Byeongseop Kim ◽  
Seunghyeok Son ◽  
Cheolho Ryu ◽  
Jong Gye Shin
Keyword(s):  
Deep Learning ◽  
Cross Validation ◽  
Three Dimensional ◽  
Learning Technologies ◽  
Learning Technology ◽  
Production Plan ◽  
Forming Process ◽  
Thermal Forming ◽  
Constant Size ◽  
Plate Shape

Curved hull plate forming, the process of forming a flat plate into a curved surface that can fit into the outer shell of a ship’s hull, can be achieved through either cold or thermal forming processes, with the latter processes further subcategorizable into line or triangle heating. The appropriate forming process is determined from the plate shape and surface classification, which must be determined in advance to establish a precise production plan. In this study, an algorithm to extract two-dimensional features of constant size from three-dimensional design information was developed to enable the application of machine and deep learning technologies to hull plates with arbitrary polygonal shapes. Several candidate classifiers were implemented by applying learning algorithms to datasets comprising calculated features and labels corresponding to various hull plate types, with the performance of each classifier evaluated using cross-validation. A classifier applying a convolution neural network as a deep learning technology was found to have the highest prediction accuracy, which exceeded the accuracies obtained in previous hull plate classification studies. The results of this study demonstrate that it is possible to automatically classify hull plates with high accuracy using deep learning technologies and that a perfect level of classification accuracy can be approached by obtaining further plate data.

Development of Curvature Gap Estimation System for Deciding Thermal Forming Instructions of Ship Curved Shell Plates Using Laser Scanner

2018 ◽  
Vol 12 (3) ◽  
pp. 339-347 ◽  
Author(s):  
Kazuo Hiekata ◽  
Taiga Mitsuyuki ◽  
Kota Okada ◽  
Yoshiyuki Furukawa ◽  
◽  
...  
Keyword(s):  
Evaluation Method ◽  
Three Dimensional ◽  
Laser Scanner ◽  
Measuring Device ◽  
Outer Plate ◽  
Thermal Forming ◽  
Forming Accuracy ◽  
Plate Shape ◽  
Estimation System ◽  
Selection Of

A thick steel plate with a unique curvature was employed to make the outer shell of a ship. This curved shell plate is shaped one at a time by craftsmen carrying out plastic deformation using gas heating. The process includes evaluation of forming accuracy and selection of thermal forming instructions. Both are done using fitting molds called “wooden templates” in a manner that is qualitative but dependent on individual skills. Thus, there is a problem of variation in quality. To solve the problem, research and development have been promoted on a manufacturing process assisted by a laser scanner that is a highly accurate three-dimensional measuring device. An evaluation method for forming accuracy has been established and has reached a satisfactory level for operation on site. However, the method of automatic selection of thermal forming instructions is still immature. Focusing on the curvature of frame lines on the outer plate that acts as an index when instructions for thermal forming are decided upon, a curvature gap estimation system was developed for outer plate frame lines using a laser scanner. Here, a frame line refers to the standard to be compared with a design shape to evaluate the forming accuracy of the members. The system extracts from measured data a point cloud that makes up each frame line, calculates curvature at a given point on the frame line, and visualizes it with a graph and a color map. This system uses an evaluation method whose curvature calculation has sufficiently appropriate accuracy and that is feasible and useful on site. First, the sufficiently appropriate accuracy of the curvature calculation was confirmed using a measurement form of a cylindrical model that simulated a gap between the distance direction generated by measurement with the laser scanner and the direction of laser irradiation. Next, the feasibility and usefulness on site were confirmed by applying the measurement method to the processing data of the ship shell outer plate shape that was obtained through the curving process in the shipyard, and then by comparing the record of regions thermally formed by the worker with index calculation results made by the system.

scholarly journals Real-Time Object Detection For Wayang Punakawan Identification Using Deep Learning

2019 ◽  
Vol 11 (4) ◽  
Author(s):  
Afandi Nur Aziz Thohari ◽  
Rifki Adhitama
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Three Dimensional ◽  
Learning Technology ◽  
Single Shot ◽  
Training Process ◽  
Real Time System ◽  
Good Ability ◽  
Object Based ◽  
Wayang Kulit

Indonesia is a country that has a variety of cultures, one of which is wayang kulit. This typical javanese performance art must continue to be preserved so that to be known by future generations. There are many wayang figures in Indonesia, and the most famous is punakawan. Wayang punakawan consists of four character namely semar, gareng petruk, and bagong. To preserve wayang punakawan to be known by the next generation, then in this study created a system that is able to identify real-time punakawan object using deep learning technology. The method that used is Single Shot Multiple Detector (SSD) as one of the models of deep learning that has a good ability in classifying data with three-dimensional structures such as real-time video. SSD model with MobileNet layer can work in slight computation, so that it can be run in real-time system. To classify object there are two steps that must be done such as training process and testing process. Training process takes 28 hours with 100.000 steps of iteration.The result of training process is a model which used to identify object. Based on the test result obtained an accuracy to detect object was 98,86%. This prove that the system has been able to optimize object in real-time accurately.

scholarly journals Review of Machine Learning Technologies and Neural Networks in Drug Synergy Combination pharmacological research

2020 ◽  
Vol 6 (3) ◽  
pp. 27-32
Author(s):  
Artur S. Ter-Levonian ◽  
Konstantin A. Koshechkin
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Learning Technologies ◽  
Learning Technology ◽  
Preclinical Research ◽  
Processing Technologies ◽  
Drug Synergy ◽  
Positive Effects ◽  
The Past ◽  
The Right

Introduction: Nowadays an increase in the amount of information creates the need to replace and update data processing technologies. One of the tasks of clinical pharmacology is to create the right combination of drugs for the treatment of a particular disease. It takes months and even years to create a treatment regimen. Using machine learning (in silico) allows predicting how to get the right combination of drugs and skip the experimental steps in a study that take a lot of time and financial expenses. Gradual preparation is needed for the Deep Learning of Drug Synergy, starting from creating a base of drugs, their characteristics and ways of interacting. Aim: Our review aims to draw attention to the prospect of the introduction of Deep Learning technology to predict possible combinations of drugs for the treatment of various diseases. Materials and methods: Literary review of articles based on the PUBMED project and related bibliographic resources over the past 5 years (2015–2019). Results and discussion: In the analyzed articles, Machine or Deep Learning completed the assigned tasks. It was able to determine the most appropriate combinations for the treatment of certain diseases, select the necessary regimen and doses. In addition, using this technology, new combinations have been identified that may be further involved in preclinical studies. Conclusions: From the analysis of the articles, we obtained evidence of the positive effects of Deep Learning to select “key” combinations for further stages of preclinical research.

scholarly journals Evaluation of Automated Measurement of Hair Density Using Deep Neural Networks

Sensors ◽  
2022 ◽  
Vol 22 (2) ◽  
pp. 650
Author(s):  
Minki Kim ◽  
Sunwon Kang ◽  
Byoung-Dai Lee
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
Hair Loss ◽  
Medical Image Analysis ◽  
Density Measurement ◽  
Hair Follicles ◽  
Learning Technologies ◽  
Tissue Imaging ◽  
Learning Technology ◽  
Hair Density

Recently, deep learning has been employed in medical image analysis for several clinical imaging methods, such as X-ray, computed tomography, magnetic resonance imaging, and pathological tissue imaging, and excellent performance has been reported. With the development of these methods, deep learning technologies have rapidly evolved in the healthcare industry related to hair loss. Hair density measurement (HDM) is a process used for detecting the severity of hair loss by counting the number of hairs present in the occipital donor region for transplantation. HDM is a typical object detection and classification problem that could benefit from deep learning. This study analyzed the accuracy of HDM by applying deep learning technology for object detection and reports the feasibility of automating HDM. The dataset for training and evaluation comprised 4492 enlarged hair scalp RGB images obtained from male hair-loss patients and the corresponding annotation data that contained the location information of the hair follicles present in the image and follicle-type information according to the number of hairs. EfficientDet, YOLOv4, and DetectoRS were used as object detection algorithms for performance comparison. The experimental results indicated that YOLOv4 had the best performance, with a mean average precision of 58.67.

scholarly journals Applications of deep-learning approaches in horticultural research: a review

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Biyun Yang ◽  
Yong Xu
Keyword(s):  
Deep Learning ◽  
Relevant Literature ◽  
Heterogeneous Data ◽  
Learning Technologies ◽  
Growth Monitoring ◽  
Learning Technology ◽  
Learning Approaches ◽  
Performance Results ◽  
Estimation Quality ◽  
Horticultural Research

AbstractDeep learning is known as a promising multifunctional tool for processing images and other big data. By assimilating large amounts of heterogeneous data, deep-learning technology provides reliable prediction results for complex and uncertain phenomena. Recently, it has been increasingly used by horticultural researchers to make sense of the large datasets produced during planting and postharvest processes. In this paper, we provided a brief introduction to deep-learning approaches and reviewed 71 recent research works in which deep-learning technologies were applied in the horticultural domain for variety recognition, yield estimation, quality detection, stress phenotyping detection, growth monitoring, and other tasks. We described in detail the application scenarios reported in the relevant literature, along with the applied models and frameworks, the used data, and the overall performance results. Finally, we discussed the current challenges and future trends of deep learning in horticultural research. The aim of this review is to assist researchers and provide guidance for them to fully understand the strengths and possible weaknesses when applying deep learning in horticultural sectors. We also hope that this review will encourage researchers to explore some significant examples of deep learning in horticultural science and will promote the advancement of intelligent horticulture.

scholarly journals Multiple Feature Dependency Detection for Deep Learning Technology—Smart Pet Surveillance System Implementation

Electronics ◽  
2020 ◽  
Vol 9 (9) ◽  
pp. 1387
Author(s):  
Ming-Fong Tsai ◽  
Pei-Ching Lin ◽  
Zi-Hao Huang ◽  
Cheng-Hsun Lin
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Learning Technologies ◽  
Learning Technology ◽  
Image Identification ◽  
Detection And Identification ◽  
Multiple Feature ◽  
Feature Dependency ◽  
Traditional Image ◽  
Dependency Detection

Image identification, machine learning and deep learning technologies have been applied in various fields. However, the application of image identification currently focuses on object detection and identification in order to determine a single momentary picture. This paper not only proposes multiple feature dependency detection to identify key parts of pets (mouth and tail) but also combines the meaning of the pet’s bark (growl and cry) to identify the pet’s mood and state. Therefore, it is necessary to consider changes of pet hair and ages. To this end, we add an automatic optimization identification module subsystem to respond to changes of pet hair and ages in real time. After successfully identifying images of featured parts each time, our system captures images of the identified featured parts and stores them as effective samples for subsequent training and improving the identification ability of the system. When the identification result is transmitted to the owner each time, the owner can get the current mood and state of the pet in real time. According to the experimental results, our system can use a faster R-CNN model to improve 27.47%, 68.17% and 26.23% accuracy of traditional image identification in the mood of happy, angry and sad respectively.

Evaluation of Model-Based Engineering Tools for Thermal Forming of a Complex Hull Plate

2013 ◽  
Author(s):  
Hyunok Kim ◽  
Yu-Ping Yang ◽  
Harvey Castner ◽  
Jong-Gye Shin ◽  
T. D. Huang ◽  
...  
Keyword(s):  
Finite Element ◽  
Induction Heating ◽  
Process Parameters ◽  
Forming Process ◽  
Heating Source ◽  
Thermal Forming ◽  
Model Based ◽  
Fe Simulations ◽  
Plate Shape

Two model-based engineering tools, Automated Thermal Plate Forming (ATPF) software and Wise Heating (WH) software were used to predict the thermal forming process parameters for a selected complex hull plate shape. The predicted process parameters and heating plan were evaluated by conducting finite-element (FE) simulations of thermal forming and comparing the final predicted geometry with the target hull shape (Fig. 1). The ATPF demonstrated the capability to generate heating plans with an induction heating source and the WH demonstrated its capability to predict a heating plan with an oxy-fuel torch heating source.

scholarly journals Wearables, Biomechanical Feedback, and Human Motor-Skills’ Learning & Optimization

2019 ◽  
Vol 9 (2) ◽  
pp. 226 ◽  
Author(s):  
Xiang Zhang ◽  
Gongbing Shan ◽  
Ye Wang ◽  
Bingjun Wan ◽  
Hua Li
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Motion Capture ◽  
Three Dimensional ◽  
Feedback System ◽  
Measurement Unit ◽  
Learning Technology ◽  
3D Motion ◽  
The Real ◽  
3D Motion Capture

Biomechanical feedback is a relevant key to improving sports and arts performance. Yet, the bibliometric keyword analysis on Web of Science publications reveals that, when comparing to other biofeedback applications, the real-time biomechanical feedback application lags far behind in sports and arts practice. While real-time physiological and biochemical biofeedback have seen routine applications, the use of real-time biomechanical feedback in motor learning and training is still rare. On that account, the paper aims to extract the specific research areas, such as three-dimensional (3D) motion capture, anthropometry, biomechanical modeling, sensing technology, and artificial intelligent (AI)/deep learning, which could contribute to the development of the real-time biomechanical feedback system. The review summarizes the past and current state of biomechanical feedback studies in sports and arts performance; and, by integrating the results of the studies with the contemporary wearable technology, proposes a two-chain body model monitoring using six IMUs (inertial measurement unit) with deep learning technology. The framework can serve as a basis for a breakthrough in the development. The review indicates that the vital step in the development is to establish a massive data, which could be obtained by using the synchronized measurement of 3D motion capture and IMUs, and that should cover diverse sports and arts skills. As such, wearables powered by deep learning models trained by the massive and diverse datasets can supply a feasible, reliable, and practical biomechanical feedback for athletic and artistic training.

Smart teaching mode based on particle swarm image recognition and human-computer interaction deep learning

2020 ◽  
Vol 39 (4) ◽  
pp. 5699-5711
Author(s):  
Shirong Long ◽  
Xuekong Zhao
Keyword(s):  
Feature Extraction ◽  
Particle Swarm Optimization ◽  
Deep Learning ◽  
Real Time ◽  
Image Recognition ◽  
Particle Swarm ◽  
Learning Technology ◽  
Search Performance ◽  
Swarm Optimization ◽  
Teaching Mode

The smart teaching mode overcomes the shortcomings of traditional teaching online and offline, but there are certain deficiencies in the real-time feature extraction of teachers and students. In view of this, this study uses the particle swarm image recognition and deep learning technology to process the intelligent classroom video teaching image and extracts the classroom task features in real time and sends them to the teacher. In order to overcome the shortcomings of the premature convergence of the standard particle swarm optimization algorithm, an improved strategy for multiple particle swarm optimization algorithms is proposed. In order to improve the premature problem in the search performance algorithm of PSO algorithm, this paper combines the algorithm with the useful attributes of other algorithms to improve the particle diversity in the algorithm, enhance the global search ability of the particle, and achieve effective feature extraction. The research indicates that the method proposed in this paper has certain practical effects and can provide theoretical reference for subsequent related research.

Sign in / Sign up

Export Citation Format

Share Document