Development of auto inspection system for Defect Detection of Automotive Rubber Boot

Corresponding Author(s)

Donghwoon Kwon1), Tae Han Kim2), and Jeong-tak Ryu3)

1)Dept. of Math, Computer Science, and Physics, Rockford University, Rockford, IL 61108, USA

E-mail: dkwon@rockford.edu

2)Dept. of Mechatronics Engineering, Daegu University, Gyeongsan-Si 38453, Korea

E-mail: jet8332@naver.com

3)School of Electric and Communication Engineering, Daegu University, Gyeongsan-Si 38453, Korea

E-mail: jryu@daegu.ac.kr

This paper proposes an automatic defect inspection system for rubber boots, one of the core automobiles parts. Automotive rubber boots are used for the joint parts of the drive system, block foreign substances from the outside and moisture, and prevent lubricants from leaking out [1-3]. Therefore, as automobile performance improves, the importance of rubber boots is increasing. In particular, since rubber boots are applied as protective caps for electric parts and connectors, they are widely used for both internal combustion engine vehicles and electric vehicles. Rubber boots have a steel ring inserted inside to maintain shape, improve airtightness, and increase assembly at the top and bottom of a body made of rubber. In addition to this, automotive rubber boots are manufactured and applied in various ways depending upon the size and shape of the applied structure [4].

In general, automotive rubber boot products are manufactured through a number of unit processes. Several problems, e.g., missing steel-ring insertion, defects caused by double steel-ring insertion, and insufficient weight of rubber boots, could occur in these processes. In the case of the automobile parts process, if each defective product is not sorted in a timely manner, another defective product could be produced in the next process, resulting in significant economic and productivity loss.

In this study, a system was developed that automatically inspects the presence or absence of steel-rings in the automotive rubber boot, excessive insertion, and defective weight of the automotive rubber boot itself using a high-frequency inductive proximity sensor and a load cell sensor. Fig. 1 below shows the driving concept diagram of the inspection system. The designed system was evaluated by randomly supplying 11 normal products, 3 underweight products, 3 uninserted steel-rings, and 3 overlapping steel-rings. A total of 20 product types were tested, and we achieved 100% reliability.

Keywords- Auto inspection system, Automotive Rubber Boot, Defect
Detection, high-frequency inductive proximity sensor and a load cell sensor

Corresponding Author(s)

1)Zhongnan
Liu / Mechatronics and robotic
system, School of Advanced Technology, Xi’an Jiaotong-Liverpool University,
Suzhou, China/ student/ Zhongnan.liu18@student.xjtlu.edu.cn

2)Fan Yang/ Electrical
Engineering, School of Advanced Technology, Xi’an Jiaotong-Liverpool
University, Suzhou, China/ student/ Fan.Yang1802@student.xjtlu.edu.cn

3)Kaiwen
Chen / Electronic
science and technology, School of Advanced Technology, Xi’an Jiaotong-Liverpool
University, Suzhou, China/ student/ Kaiwen.chen19@student.xjtlu.edu.cn

4)Sanghyuk Lee/ Depantment
of Mechatronics and Robotics, School of Advanced Technology, Xi’an
Jiaotong-Liverpool University, Suzhou, China/ Professor/Sanghyuk.Lee@xjtlu.edu.cn

An Analysis of Diabetics Data Using k-Means Clustering Algorithm

Corresponding Author(s)

Name:T. Velmurugan¹, A.Dharmarajan²

²Assistant Professor, Department of Computer Science, Ayya Nadar Janaki Ammal College,Sivakasi, India

e-mail:velmurugan_dgvc@yahoo.co.in, mailtodharmarajan@gmail.com
Tel:

²Assistant Professor, Department of Computer Science, Ayya Nadar Janaki Ammal College,Sivakasi, India

e-mail:velmurugan_dgvc@yahoo.co.in, mailtodharmarajan@gmail.com
Tel:

In the medical field, huge data is available, which leads to the need of a powerful data analysis for the extraction of useful information. Several studies have been carried out in the domain of data mining to improve the capability of data analysis on large datasets. Clustering is the important aspect of data mining which is used to analyze much kind of data. It is the process of grouping of data, where the grouping is recognized by finding similarities between data based on their features. There are number of techniques proposed by several developers, they were analyzed the clustering algorithms in data mining. In this research work, the large dataset of diabetics is collected from the reputed hospitals among the specific city. The received information can have the details of person who are affected by diabetics in young age. The Diabetician suggested parameters are only used for the input data in this analysis. For this k-Means algorithm is applied. To evaluate the clustering quality, the distance between two data points are taken for analysis and creation of proper clusters. The result of clustering quality, performance and computer complexity is also analyzed. Highly affected persons are identified through this clustering approach. Finally, the explicit result is generated by using the outcome cluster. The resulted clusters have the details of person who are affected diabetic in young age and specific reason. This type of outcome is used to continue the treatment type or help for the physician or diabetician.

Keywords: Diabetic data analysis, k-Means algorithm, Performance Analysis, Clustering Method.

using HOMER for sizing hybrid pv/wind/hydrokinetic/battery energy system for  Isolated City in Egypt (Shalateen)

Corresponding Author(s)

3)safaa saleh / department of Electric Engineering, Faculty of Engineering,  Assuit university / safaasaleh@aun.edu.eg

Corresponding Author(s)

There is an
increasing demand for an advanced safety assist device for construction



equipment that can prevent accidents in advance by detecting various blind



spots during work at construction sites. Various sensors like ultrasonic sensors,



RFID, lidar, cameras, and radar are being developed as advanced safety assist



devices used in construction equipment. Especially, radar is attractive as the



most competitive core parts because they provide the best and most reliable



performance in various adverse conditions at the construction site. However,



when the construction equipment moves, the radar mounted on the construction



equipment also has Doppler information generated from the movement by itself.



The Doppler information from motion should be removed before detecting of



targets of interest. To solve this problem, this paper proposes advanced safety



assist device based on combining an IMU(Inertial Measurement Unit) and multi-radar.



The IMU is utilized to know how tilted the direction of the sensor is. The



movement of construction equipment is measured using IMU sensors. The IMU



combined multi-radar can be used as dynamic safety assistant monitoring system



for construction heavy vehicles in a moving as well as stationary state.

Corresponding Author(s)

Corresponding Author(s)

According to the Korea Consumer Agency, out of 645 applications for medical damage related to misdiagnosis received from 2012 to 2016, 374 cases (58% of all applications) were misdiagnoses of cancer. Most of them were cancer, but 81.4 percent misdiagnosed as non-cancer, and 8.6 percent misdiagnosed as cancer. The most common causes were the image reading error and negligence of additional examination. Among the cancer types, lung cancer is most often misdiagnosed. Also, as the diagnosis is delayed, so cancer already advances and usually occurs at stage 3 or stage 4. According to the Disease Policy Division of the Ministry of Health and Welfare, the incidence of lung cancer (people per 100,000 population) increased every year from 28 in 1999 to 55.8 in 2018, doubling. The death rate also increased every year from 22.1 in 1999 to 34.8 in 2018. In 2019, lung cancer was the number one cause of death from cancer.

In this paper, we design and implement a lung cancer diagnosis system using medical image data of individuals. The proposed system obtains a dataset with medical images acquired from The Cancer Imaging Archive (TCIA) of the National Cancer Institute (NCI). Our system trains the constructed dataset using a CNN (Convolutional Neural Network) model widely used in deep learning. Our system receives medical images from users for cancer diagnosis and then applies the CNN model to learn the obtained dataset. It then uses the trained CNN model to analyze new medical images and reasons out their results. Our system is developed for medical image readers and doctors. With the learning results of medical images, our system can reduce the false positive by comparing the other conventional methods.

Corresponding Author(s)

Name:Yoosoo Oh
Affiliation: Dept. of ICT Convergence, Dept. of AI, Daegu University

e-mail: yoosoo.oh@daegu.ac.kr

Tel:+82-53-850-6654

To ensure the integrity of collected data in deep learning, we need to apply the data preprocessing process. This paper proposes an algorithm that identifies the learning data type and recommends the data preprocessing method for deep learning. Learning in deep learning models has different preprocessing processes depending on image files (jpg, png, etc.) and numerical files (CSV, XML, etc.). Thus we classify collected data as numeration and image files using file extensions to determine the file type. Then we use knowledge-based filtering techniques to recommend the data preprocessing process for the deep learning model. In addition, we utilize Titanic's analytical data set as training datasets to evaluate recommendation algorithms.

Usually, numerical files are less accurate in the learned model when outliers exist. Accordingly, the numeration file uses the mean and standard deviation among learning data to explore outlier values and perform preprocessing to remove outlier values or replace them with others. Primarily,  we apply z-score and z-test methods to explore outliers. Image files in a deep learning model perform preprocessing that changes the image's size, color, etc. Also, the proposed method receives input from the user and processes the image size and data type required for the deep learning model.

Moreover, this paper designs an algorithm that uses a knowledge-based filtering model to recommend suitable preprocessing methods according to the numerical file and image file. In particular, the proposed recommendation algorithm recommends preprocessing techniques such as removing missing values, substituting missing values, and inserting predicted values ​​depending on the presence or absence of abnormal data in the case of a numerical file. Furthermore, in an image file, pre-processing methods such as image size change, image transparency processing, color classification, and boundary detection are recommended.

Consequently, we compare the recommended preprocessing method with the pretreatment method by user analysis to evaluate the proposed recommended algorithm. For evaluation, we use the dataset, which is the collected data concerning Titanic. As experimental results, we obtained that the proposed preprocessing method has higher result values ​​than the existing preprocessing method performed by user analysis.

Corresponding Author(s)

Name: Wei Qun

Affiliation: School of Medicine


e-mail: weiqun@kmu.ac.kr


Tel: +82-10-8843-0716

1) Soo-min Lee, Graduate School of Medicine, e_soomin@naver.com

2) Bu-seong Kim, Graduate School of Medicine

3) Jung-woo Koo, School of Medicine

4) Hee-jun Park, hjpark@kmu.ac.kr

Although kidney disease is underestimated in severity compared to other diseases such as heart disease and stroke, chronic kidney disease (CDK) mortality increased by 14.5% from 1990 to 2017, making it the twelfth leading cause of death due to kidney failure. It is estimated that about 1.4 million people die from complications caused by this. As such, the incidence and mortality of CDK are increasing worldwide, and since it can cause complications and have a fatal effect on life, early diagnosis and prevention of the disease is very important. In general, urinalysis, which is a relatively simple test that is easy to collect for diagnosis, puts less burden on the patient, and is relatively simple, is performed. Urinalysis is classified into physical property test, chemical test, and urine sediment test method, and the double chemical test is used for home urine analyzers in that, unlike physical feature test, quantitative data extraction is possible, and it is cheaper and more accurate than urine sediment test. have. However, in a typical home urine analyzer, the position of a 10-parameter urine dipstick is fixed, and there is a limitation in that it causes a high cost by using an expensive optical sensor. Therefore, in this paper, we developed a motor-based urine analysis system and proposed a low-cost household urine analyzer that can measure 10 parameters of urine with a single optical sensor. And it was designed to be linked with a mobile device through USB serial communication for data storage and processing by analyzing the concentration of metabolites measured through the calibration algorithm in the MCU. As a result of performing a performance experiment using a 10-parameter urine dipstick for diagnosis by implementing the prototype of the proposed device, it showed more than 90% accuracy in the identification of negative and positive first-stage hit rates and abnormal values ​​for each element. Up to now, the average of 10 types of test accuracy was over 80%, proving the high measurement and analysis accuracy of the proposed device.

Corresponding Author(s)

Sentiment analysis studies opinion text to identify positive and negative opinions or sentiments expressed in the review text. With the rapid development of online shopping, it becomes increasingly essential to analyze online customer reviews and explore and incorporate them into product design. One of the most challenging online review analyses is the aspect-level sentiment analysis to determine how to connect multiple product features and opinions in one review sentence. We have provided a step-by-step straightforward, but practical approach to addresses the above problem and implemented a sentiment analysis prototype system. We have also gathered and tested the review data set for the Hair Dryer from five Korean online shopping malls, demonstrating that the proposed approach is valid.

Corresponding Author(s)

1) Hojong Chang / KAIST / hojoungc@kaist.ac.kr

2) Yongho Kim / CN Frontier Co.,Ltd. / gilbert@cnfrontier.kr

3) Byunghun Han / KAIST / luna988@kaist.ac.kr

4) Kyungdon Choi / CM Data, Ltd. / miakaj@gmail.com

5) Chae-Seok Lee / KAIST / quarry@kaist.ac.kr

6) Heejung Kang / DAEYOMEDI Co., Ltd. / dadaeyo@daeyomedi.com

7) Youngsang Kun / DAEYOMEDI Co., Ltd. / tdykys@daeyomedi.com

8) Hyoungho Nam / CN Frontier Co.,Ltd. / ska90mcp@naver.com

Increase of cardiovascular disease patients is observed due to the aging population and westernized nutrition. There are many cardiovascular disease monitors developed such as hemodynamic monitoring technology for cardiac skill evaluation.  Hemodynamic monitoring performs 3 dimensional 

Pulse imaging test by using blood pressure, blood vessel aging, pulse, cardiac skill evaluation to analyse the blood vessel status. To provide a good health care monitoring service, important data such as cardiac output, pulse information, vascular response information can be measured simultaneously and continuously by using hemodynamic monitoring. Domestic cause of death by cardiovascular disease, High blood pressure, ischemic heart disease, coronary artery disease, arteriosclerosis, arrhythmia, is the second highest. After the COVID-19 pandemic, the correlation between COVID-19 vaccine side effect and cardiovascular disease correlation is under investigation to prevent the severe side effect for underlying disease patients. 

Cardiovascular angiography and blood test are considered to be invasive method and electrocardiogram and ultrasounds are considered to be non-invasive method. The aim of this study is to analyze the operating mechanism of DMP-Lifeplus tonometry Digital Arterial Pulse-wave Analyzer, which is the product of Daeyomedi. DMP-Lifeplus is non-invasively measures blood pressure pulse wave by measuring pressure wave. As the demand of non-face-to-face medical and home care service arise, it is necessary to collect and use data during the service. Thus, platform development by using Information and Communication Technologies and cloud computing is studied as well.