Lee Seo-El1
Choi So-Eun2
Park Geon3
Kang Ye-Yeon3
Baek Ji-Won4
Chung Kyungyong5*
-
(Department of Public Safety BigData, Kyonggi University / Suwon, Korea lse_1031@kyonggi.ac.kr)
-
(Department of Industrial Management Engineering, Kyonggi University / Suwon, Korea
soeun_2021@naver.com)
-
(Division of Computer Science and Engineering, Kyonggi University / Suwon, Korea
bongran8@naver.com, bboya0517@kyonggi.ac.kr
)
-
(Department of Computer Science, Kyonggi University / Suwon, Korea jwbaek@kyonggi.ac.kr)
-
(Division of AI Computer Science and Engineering, Kyonggi University / Suwon, Korea
dragonhci@gmail.com )
Copyright © The Institute of Electronics and Information Engineers(IEIE)
Keywords
Manufacturing process, Orientation, Object detection, Mask R-CNN, Anomaly detection
1. Introduction
In the manufacturing process, combined with advanced technologies, the Artificial
Intelligence (AI) model for collecting sensor data in various industrial domains for
fault prediction, defect detection, and anomaly detection has been developed. Accurate
descriptions of defects, faults, and conditions are needed to apply an AI model to
manufacturing equipment. Given the sensitivity, multi-variance, irregularity, and
time-series features according to external environmental factors, it is necessary
to suggest a plan for securing quality. Unfortunately, there are practical difficulties
in meeting the execution conditions of industrial systems [1]. In industrial domains, anomaly detection is performed by comparing with training
data and checking if the data distribution is consistent. Hence, overfitting can occur
with data imbalances in which data for a specific class fail to be distributed evenly
[2]. Overfitting can also come about if the goodness-of-fit of a model is overemphasized
in the production line. In this respect, it is essential to reduce the number of feature
extractions of sensing data, or to make normalization through linear regression or
logistics regression [3]. In addition, it is essential to collect sensing data from heterogeneous sensors
and present the risk factors of the manufacturing process, including failures and
faults of equipment, through explainable prediction.
Cynthia Changxin Wang [4] performed an axis-aligned instance segmentation and proposed a safety warning algorithm
to prevent on-the-job accidents of mobile devices. The proposed axis-aligned instance
segmentation calculated and bounded the major axis of an object and rotated the slanted
object for detection. This method accurately detected an asymmetrical object through
the orientation. On the other hand, in the method, the object boundary became increasingly
obscure the farther the object was from a recognition axis, and it detected only a
single object.
In an industrial site, it is impossible to explain the prediction results, and it
is challenging to apply an AI model in which the performance is guaranteed only if
features of large sensing data are extracted. In addition, it is important to minimize
the false positive and false negative rates of each item in the manufacturing process,
and to advance and optimize the Mask R-CNN [5]-based occlusion area detection and anomaly algorithm. In this way, it is possible
to find a particular area of data, extract a feature from that area, and determine
if there is any defect.
This study proposes the Mask R-CNN-based occlusion anomaly detection considering the
orientation of manufacturing process data. Occlusion anomaly detection refers to a
mechanism for performing two tasks, which detects occlusions and abnormal objects
presented in the image area. Compared to a conventional algorithm based on Mask R-CNN,
the proposed method increases the accuracy of object recognition in detecting an object.
Data preprocessing is performed to express images of manufacturing at various angles
in the manufacturing process. Subsequently, Mask R-CNN is used to determine if they
have an object in pixels, extract the bounding box and masking information, and detect
the occlusion and anomaly of an image. By applying Mask R-CNN capable of detecting
an area, the proposed method enhances the defect detection ability to decrease the
false positive rate and the false negative rate in a manufacturing line by combining
with occlusion area detection in image preprocessing.
Chapter 2 describes the related works on object detection-based anomaly detection.
Chapter 3 introduces the Mask R-CNN-based occlusion anomaly detection considering
the orientation in manufacturing process data. Chapter 4 reports the results and performance
evaluation. Chapter 5 describes the conclusions of this study.
2. Related Work
In manufacturing, methods for detecting defective products using camera image data
are being studied. Mohr et al. classify them into CNNs by learning normal and abnormal
image data [6]. Suh et al. proposed a method to locate defective products using infrared cameras
[7]. On the other hand, the above studies detected defective products with models learned
using single object image data without considering occluded objects generated in a
real manufacturing process. In addition, the process is limited by the expensive infrared
cameras. Therefore, this study presents a model that uses data augmentation techniques
to increase the anomaly detection accuracy among occluded objects at low cost.
2.1 Object Detection
Object detection classifies an instance through a bounding box and finds the location
and classes of various objects. Object detection is made possible through the classification,
localization, and detection of image data. In other words, the location of an object
in an image is found through localization, and the object is detected and classified.
Deep learning-based object detection consists of one-stage detector and two-stage
detector [8]. As a typical method of a one-stage detector, there is YOLO [9]. Because it performs both classification and localization, it features a fast speed
[10]. YOLO finds anchors saved after an input image is segmented by a grid and predicts
an anchor box. The anchor box is a box in which an object is possibly located in the
input image. It obtains a confidence score according to which an object is classified.
Mask R-CNN is a typical algorithm of a two-stage detector. Fast R-CNN [11] and Faster R-CNN are models for object detection [12]. These object detection methods use a bounding box to classify an instance, identify
multiple objects, and detect the location and class of each object. Unlike these methods,
Mask R-CNN utilizes instance segmentation that has the combined concept of object
detection with semantic segmentation. For the same class, conventional semantic segmentation
makes segments into the same area without classification, whereas instance segmentation
classifies an instance differently, even in the same class. Fig. 1 shows the object detection process in Mask R-CNN.
In Fig. 1, all three are forks in the same class but are recognized as instances where they
are segmented into different colors. In the manufacturing process, there are multiple
objects whose shape is equal. Therefore, Mask R-CNN-based model using instance segmentation,
rather than a conventional model, can improve the detection performance [13].
Fig. 1. Object Detection Process in Mask R-CNN.
2.2 Anomaly Detection
Anomaly detection is the task of finding the features of normal and abnormal samples
of datasets and classifying them. The task consists of supervised and unsupervised
learning following dataset and model configuration. The supervised learning approach
utilizes the dataset that includes the label information suitable for each image,
and a model learns the features of abnormal classes for inference [14]. With the label as meta information of data, bounding box, and passively collected
data, it is possible to expect an improvement in model performance. Because the anomaly
detection task has different probabilities of abnormal and normal data, the class
distribution of the collected data is imbalanced. Such class imbalance induces biased
learning of a model that has data-driven inference and deteriorates the classification
performance. In addition, patterns of anomaly features are all different, so it is
vital to obtain appropriate meta information or domain knowledge. For the proper inference
of supervised learning models, a well-annotated dataset is required; a great deal
of time is needed, and an expert workforce is essential.
Several studies on semi-supervised learning-based anomaly detection have been conducted
to overcome these limitations [15]. Such methods include pseudo-labeling, one-class anomaly detection, and an unsupervised
learning approach. The problem of poor annotation can be solved by applying explicit
modeling for abnormal data lacking labels or pseudo-labeling through the data features
that a model learned. More time and an analysis procedure than actual annotation are
needed, and incorrect labeling can negatively influence the inference process of a
model.
One-class anomaly detection utilizes normal samples only for model learning. It sets
the discriminate boundary of normal samples. The method learns W (set of weight) and
R (radius) as weights of a neuron network, called parameters, to map anomaly examples
out of the hypersphere. In addition, it minimizes the distance between the center
of the hypersphere and each dataset [16]. Therefore, the method supplements the data imbalance, which is the problem of supervised
anomaly detection.
The unsupervised learning approach applies to data without labels or data lacking
labels. It utilizes a representation learning-based model to learn normal class data
only. Like AutoEncoder [17] and the Generative adversarial Network, the method applies the process of recovering
original data. It reflects the point that the network learning normal data only does
not regenerate the anomaly features. The model does not require professional knowledge
and explicit modeling for anomaly areas and can achieve more flexible anomaly detection.
3. Mask R-CNN-based Occlusion Anomaly Detection Considering Orientation in Manufacturing
Process
In a manufacturing process, one of the production processes may not be performed,
or a mechanical failure can occur, resulting in sub-normal production [18]. For example, in manufacturing forks, a fork without a blade or fork-head part is
sometimes produced. People can detect such products, but there are high associated
labor costs. Moreover, it is difficult to detect such products if they are occluded.
This study introduces the Mask R-CNN-based occlusion anomaly detection considering
the orientation in manufacturing process data to deal with the problem. The proposed
method proceeds in two steps. Fig. 2 shows the Mask R-CNN-based occlusion anomaly detection process considering the orientation
in manufacturing process data.
In Fig. 2, the first is the data preprocessing step in which the number of cases where defective
forks are mixed in the normal forks in manufacturing forks. The second is occlusion
anomaly detection using Mask R-CNN, in which defective forks occluded in normal forks
are detected by Mask R-CNN.
Fig. 2. Occlusion Anomaly Detection Process.
3.1 Data Preprocessing Considering Orientation
In this study, the manufacturing process data is fork class data of MS COCO (Microsoft
Common Objects in Context) [19]. The MS COCO dataset is an extensive dataset of object detection, segmentation, and
captioning. In manufacturing tableware, forks are not evenly aligned but are occluded
or produced in diverse directions. In addition, there is a lack of occlusion data
compared to the image dataset of non-occluded products. The OpenCV library was applied
for image preprocessing to solve the problem. OpenCV is an open-source library to
process images and videos in real time. It is used for the preprocessing work for
object detection. The accuracy of object recognition is increased using image augmentation.
This study utilizes the image augmentation method with orientation, compositing, and
pasting preprocessing, among various image augmentation methods using OpenCV.
First, orientation is applied to the image dataset [20]. There are transition and rotation functions usable for the orientation. The transition
function moves an image left and right, and up and down so that it is impossible to
consider angles. Because the rotation function considers the rotation axis and rotation
angle of an image, it is possible to consider angles and directions. Accordingly,
by rotating the image data of a fork at 15$^{\circ}$ intervals, it is possible to
generate new images, express the product images with diverse angles generated in the
manufacturing process, and produce occlusion images. Fig. 3 presents an image for the equation. Eq. (1) is the formula for image orientation.
In Eq. (1), $H_{p}$ is an increasing pixel height; $W_{p}$ is an increasing pixel width; $\theta
$ is the rotating angle. In the way of changing the coordinates of image pixels based
on the reference coordinates $x_{1}$, $y_{1}$ of the image, the coordinates $new_{x}$,
$new_{y}$ of the rotated pixels are calculated using Eq. (1).
Fig. 3. Image Orientation.
3.2 Occlusion Anomaly Detection using Mask R-CNN
This study proposes Mask R-CNN-based occlusion detection method considering the orientation
of manufacturing process data. The model was implemented based on FPN (Feature Pyramid
Network) [21] and ResNet101 backbone. Mask R-CNN produces a bounding box and a segmentation mask
for each instance of the object that appears in an image. Unlike other models for
object detection, it generates a segmentation mask to identify different instances
in the same class [22]. Fig. 4 shows the occlusion and anomaly detection process using Mask R-CNN.
Fig. 4. Occlusion and Anomaly Detection Process using Mask R-CNN.
The Mask R-CNN-based occlusion anomaly detection process is the same as the combination
of object detection with semantic segmentation. First, the image generated through
preprocessing is input into the model, and an anchor box is marked in the image position
in which an object can be found for object detection. In the later step, the most
optimal anchor box detected is marked. The model generates a mask for each instance
and adjusts the size for semantic segmentation [23]. The occlusion and anomaly areas of the image can be detected if the box and mask
obtained in the two steps are positioned correctly in the image. Mask R-CNN generates
three mask branches. That is the distinction of Mask R-CNN from conventional object
detection. The classification branch plays a role in class prediction. The bbox regression
branch changes the box coordinates. FCN-based mask branch plays a role in generating
a binary mask. The feature map produced by three branches is rescaled, and the mask
segment to compare with an actual mask is generated. Mask R-CNN solved the problem
of RoI Pooling in which a decimal point is ignored when coordinates are reduced and
is capable of predicting a class in the unit of the pixel through RoIAlign.
4. Performance Evaluation
For performance evaluation, based on the weight and preprocessed data of the model
pre-trained COCO dataset, the Mask R-CNN-based model proposed in this study was compared
with YOLOv2 [24] and YOLOv3 [25]. In particular, the Mask R-CNN and YOLO object detection algorithms were compared
in terms of whether to detect occlusion and anomaly considering the orientation and
precision, recall, and accuracy of object detection. The object detection performance
was evaluated with IoU (Intersection over Union) [26]. The IoU represents the union-intersection ratio of the ground truth bounding box
and predicted bounding box. The closer the IoU is to 1, the higher the object detection
accuracy. Eq. (2) presents the formula to calculate IoU.
In Eq. (2), $F_{gt}$ is the ground truth of the actual bounding box; $F_{P}$ is the predicted
value of the bounding box. A test was conducted assuming that the fork is a normal
object and the defective fork is an anomaly. First, the results of the raw image and
the image considering the orientation were compared.
Fig. 5 shows the case where object recognition is performed through Mask R-CNN on the original
image without considering the orientation. Fig. 6 presents the case where an object is recognized by Mask R-CNN after the original
image was changed by preprocessing considering the orientation. In Fig. 5, Mask R-CNN recognized eight out of nine normal objects. In addition, its recognition
rate of object detection was approximately 75.83%. Fig. 6 reveals a better recognition rate (83.41%) than the image without considering the
orientation and recognition rate. These results show that Mask R-CNN detects more
occluded objects in the image considering the orientation. In the case of anomaly
detection, Mask R-CNN did not detect anomaly objects as normal objects in the images
considering orientation. Hence, Mask R-CNN performs well in anomaly detection regardless
of the orientation. Table 1 presents the results of the IoU performance evaluation.
As shown in Table 1, Mask R-CNN showed better performance than YOLO for the original image without consideration
of the orientation. Hence, Mask R-CNN detected more objects in the image of an occluded
object. Nevertheless, occlusion anomaly detection in consideration of the orientation
was performed because each occluded object failed to be detected correctly. In the
performance evaluation, Mask R-CNN showed superior IoU performance than YOLO. This
is because Mask R-CNN is better for recognizing objects and detecting occluded objects
than YOLO. Therefore, Mask R-CNN shows the best performance in the anomaly detection
of occluded objects in a manufacturing process.
Precision and Recall were performed as performance indicators for anomaly detection.
Precision represents the degree to which only related objects are detected among objects
in image data. Recall indicates the degree to which all related objects have been
detected correctly in the input image data. For anomaly detection, 200 images of a
normal fork and defective fork images were validated using considering orientation
image data. For defective forks, they should not be classified as fork-object classes.
In other words, they are not classified into any class. Table 2 lists the Confusion Matrix of defective fork detection.
According to Table 2 and the performance evaluation index, the precision was 172/(172+25) = 0.87, and
the recall was 172/(172+28) = 0.86. This result was compared with the YOLOv3 and YOLOv2
models. The environmental conditions for the performance evaluation were the same
as the environment of Mask R-CNN. Table 3 lists the performance evaluation results of object feature detection.
The Mask R-CNN-based method proposed in this study showed superior results in all
performance evaluation indicators of precision and recall than YOLOv3 and YOLOv2.
Fig. 5. Result of the raw image.
Fig. 6. Result of the image considering the orientation.
Table 1. Results of IoU Performance Evaluation.
|
Method
|
IoU of Raw Image
|
IoU of Image considering the orientation
|
|
Mask R-CNN
|
0.5875
|
0.8994
|
|
YOLOv3
|
0.5478
|
0.8734
|
|
YOLOv2
|
0.4208
|
0.7325
|
Table 2. Confusion Matrix of detective fork detection.
|
|
Predict Image
|
|
Positive
|
Negative
|
|
Label Image
|
True
|
172
|
28
|
|
False
|
25
|
175
|
Table 3. Performance evaluation of object feature detection.
|
|
Precision
|
Recall
|
|
Mask R-CNN
|
0.87
|
0.86
|
|
YOLOv3
|
0.80
|
0.83
|
|
YOLOv2
|
0.71
|
0.78
|
5. Conclusion
This study proposed the Mask R-CNN-based occlusion anomaly detection considering the
orientation in the manufacturing process data. As the method for the anomaly detection
of occluded objects in the manufacturing process, Mask R-CNN was used to detect abnormal
objects hidden in normal objects from the data considering the orientation rather
than alignment data. The proposed method proceeds in two steps. First, the alignment
data was changed to the data considering the orientation. In other words, the rotation
function of the OpenCV library was used to rotate images of the dataset and generate
new images considering their orientation. In the second step, Mask R-CNN was applied
for occlusion anomaly detection. In this step, the box and mask obtained by Mask R-CNN
were used to detect an occlusion from the data, including occluded objects. Accordingly,
the abnormal object ‘defective fork’ occluded in the normal object ‘fork’ was detected.
For the performance evaluation of detection accuracy, Mask R-CNN was compared with
YOLOv2 and YOLOv3 using IoU. When anomaly detection was performed in the original
data without consideration of the orientation, Mask R-CNN had better object detection
accuracy. For the performance evaluation in consideration of the orientation, Mask
R-CNN had better object detection accuracy than YOLO. In addition, in the performance
evaluation of anomaly detection, Mask R-CNN shows the best performance in precision
and recall. Accordingly, for occlusion anomaly detection in the manufacturing process,
it is good to apply Mask R-CNN considering the orientation. In the case of occluded
objects that occur in a real manufacturing process, recognition accuracy is poor due
to problems, such as misrecognition due to texture bias. To solve this problem, it
is possible to increase the recognition performance of the occlusion object by Mask
R-CNN-based occlusion anomaly detection considering the orientation. Furthermore,
it is possible to prevent issues that may occur in the distribution process by finding
defective products that are occluded and difficult to identify in the anomaly detection
process in real manufacturing.
Future research will evaluate methods for anomaly detection in the data, including
more occluded objects in diverse manufacturing situations.
ACKNOWLEDGMENTS
This work was supported by the GRRC program of Gyeonggi province. [GRRC KGU 2020-B04,
Image/ Network-based Intellectual Information Manufacturing Service Research]
REFERENCES
Bache R., Müllerburg M., 1990, Measures of testability as a basis for quality assurance,
Software Engineering Journal, Vol. 5, No. 2, pp. 86-92
Dietterich T., 1995, Overfitting and under computing in machine learning, ACM computing
surveys (CSUR), Vol. 27, No. 3, pp. 326-327
Bartlett P. L., et al. , 2020, Benign overfitting in linear regression, Proceedings
of the National Academy of Sciences, Vol. 117, No. 48, pp. 30063-30070
Wang C. C., et al. , October 25, 2021, A Safety Warning Algorithm Based on Axis Aligned
Bounding Box Method to Prevent Onsite Accidents of Mobile Construction Machineries,
Sensors(Basel, Switzerland), Vol. 21, No. 21, pp. 7075
Kaiming H., et al. , 2017, Mask R-CNN, Proceedings of the IEEE international conference
on computer vision, pp. 2961-2969
Mohr G., et al. , 2020, In-Situ Defect Detection in Laser Powder Bed Fusion by Using
Thermography and Optical Tomography - Comparison to Computed Tomography, Metals, Vol.
10, No. 1, pp. 103
Suh S. W., Ko Y. H., Yoo S. G., Chong K. T., 2019, Development of Checker-Switch Error
Detection System using CNN Algorithm, The Korean Society of Manufacturing Process
Engineers, Vol. 18, No. 12, pp. 38-44
Carranza-Gracia M., et al. , 2020, On the performance of one-stage and two-stage object
detectors in autonomous vehicles using camera data, Remote Sensing, Vol. 13, No. 1,
pp. 89
Tianjiao L., Hong B., 2020, A optimized YOLO method for object detection, 2020 16th
International Conference on Computational Intelligence and Security (CIS), pp. 30-34
Hongtao W., Xi Y., 2020, Object Detection Method Based On Improved One-Stage Detector,
2020 5th International Conference on Smart Grid and Electrical Automation (ICSGEA),
pp. 209-212
Zhai S., Shang D., Wang S., Dong S., 2020, DF-SSD: An Improved SSD Object Detection
Algorithm Based on DenseNet and Feature Fusion, in IEEE Access, Vol. 8, pp. 24344-24357
Li Q., Mou L., Jiang K., Liu Q., Wang Y., Zhu X. X., 2018, Hierarchical Region Based
Convolution Neural Network for Multiscale Object Detection in Remote Sensing Images,
IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium, pp.
4355-4358
Hafiz A. M., Bhat G. M., 2020, A Survey on Instance Segmentation: State of the art,
International journal of multimedia information retrieval, Vol. 9, No. 3, pp. 171-189
Nguyen G. H., et al. , 2008, A supervised learning approach for imbalanced data sets,
2008 19th international conference on pattern recognition. IEEE, pp. 1-4
Zhu X. J., et al. , 2009, Introduction to semi-supervised learning, Synthesis lectures
on artificial intelligence and machine learning, Vol. 3, No. 1, pp. 1-130
Manevitz L. M., Yousef M., Dec 2001, One-class SVMs for document classification, Journal
of machine Learning research, Vol. 2, pp. 139-154
Bank D., Koenigstein N., Giryes R., 2020, Autoencoders, arXiv preprint arXiv:2003.05991
Marta S. P., Joanna N. G., 2019, Defective Products Management with Reverse Logistics
Processes in Micro, Small, and Medium-Sized Production Companies, Polish Journal of
Management Studies, Vol. 20, pp. 6780-6795
COCO dataset, http://cocodataset.org
Xie X., et al. , 2021, Oriented R-CNN for object detection, Proceedings of the IEEE/CVF
International Conference on Computer Vision., pp. 3520-3529
Lin T. Y., et al. , 2017, Feature pyramid networks for object detection, Proceedings
of the IEEE conference on computer vision and pattern recognition, pp. 2117-2125
Ren S., He K., Girshick R., Sun J., 2015, Faster R-CNN: Towards real-time object detection
with region proposal networks, Advances in neural information processing systems,
Vol. 28
Yu W., Kim S., Chen F., Choi J., 2020, Pedestrian Detection Based on Improved Mask
R-CNN Algorithm, International Conference on Intelligent and Fuzzy Systems. Springer,
Cham., pp. 1515-1522
Joseph R., Farhadi A., 2017, YOLO9000: better, faster, stronger, Proceedings of the
IEEE conference on computer vision and pattern recognition, pp. 7263-7271
Redmon J., Farhadi A., 2018, Yolov3: An incremental improvement, arXiv preprint arXiv:1804.02767
Padilla R., Netto S. L., da Silva E. A. B., 2020, A Survey on Performance Metrics
for Object-Detection Algorithms, 2020 International Conference on Systems, Signals
and Image Processing (IWSSIP), pp. 237-242
Author
Seo-El Lee received her B.S. degrees from the School of Psychology, Duksung Women’s
University, Korea, in 2022. She is currently in the Master course at the Department
of Public Safety Bigdata Psychological Analytics, Kyonggi University, Korea. She has
been a researcher at Data Mining Lab., Kyonggi University. Her research interests
include data mining, big data, deep learning, data analytics, and object detection.
So-Eun Choi is currently pursuing a B.S. degree with the Department of Industrial
Management Engineering, at Kyonggi University, Korea. She has been a researcher at
Data Mining Laboratory, Kyonggi University. Her research interests include data mining,
big data analytics, and deep learning.
Geon Park is currently pursuing a B.S. degree with the Division of Computer Science
and Engineering, Kyonggi University, Korea. He has been a researcher at Data Mining
Laboratory, Kyonggi University. His research interests include data mining, object
detection, and deep learning.
Ye-Yeon Kang is currently pursuing a B.S. degree with the Division of Computer
Science and Engineering, Kyonggi University, Korea. She has been a researcher at Data
Mining Laboratory, Kyonggi University. Her research interests include data mining,
object detection, and deep learning.
Ji-Won Back received a B.S. degree from the School of Computer Information Engineering,
Sangji University, Korea in 2017. She has worked for Data Management Department, Infiniq
Co., Ltd. She received an M.S. degree from the School of Department of Computer Science,
Kyonggi University, Korea, in 2020. She is currently in the PhD. course at the Department
of Computer Science, Kyonggi University, Korea. She has been a researcher at Data
Mining Lab., Kyonggi University. Her research interests include data mining, data
management, knowledge system, automotive testing, deep learning, healthcare, and recommendation.
Kyungyong Chung received B.S., M.S., and Ph.D. degrees in 2000, 2002, and 2005,
respectively, all from the Department of Computer Information Engineering, Inha University,
South Korea. He has worked for the Software Technology Leading Department, Korea IT
Industry Promotion Agency (KIPA). From 2006 to 2016, he was a professor at the School
of Computer Information Engineering, at Sangji University, South Korea. Since 2017,
he has been a professor in the Division of AI Computer Science and Engineering, at
Kyonggi University, South Korea. He was named a 2017 Highly Cited Researcher by Clarivate
Analytics. His research interests include data mining, artificial intelligence, healthcare,
knowledge systems, HCI, and recommendation systems.