This page has only limited features, please log in for full access.

Unclaimed
Jeonghong Kim
School of Computer Science and Engineering, Kyungpook National University, Daegu, South Korea

Honors and Awards

The user has no records in this section


Career Timeline

The user has no records in this section.


Short Biography

The user biography is not available.
Following
Followers
Co Authors
The list of users this user is following is empty.
Following: 0 users

Feed

Journal article
Published: 19 January 2021 in IEEE Access
Reads 0
Downloads 0

Considering importance of the autonomous driving applications for mobile devices, it is imperative to develop both fast and accurate semantic segmentation models. Thanks to emergence of Deep Learning (DL) techniques, the segmentation models enhanced their accuracy. However, this improved performance of currently popular DL models for self-driving car applications come at the cost of time and computational efficiency. Moreover, networks with efficient model architecture experience lack of accuracy. Therefore, in this study, we propose robust, efficient, and fast network (REF-Net) that combines carefully formulated encoding and decoding paths. Specifically, the contraction path uses mixture of dilated and asymmetric convolution layers with skip connections and bottleneck layers, while the decoding path benefits from nearest neighbor interpolation method that demands no trainable parameters to restore original image size. This model architecture considerably reduces the number of trainable parameters, required memory space, training, and inference time. In fact, the proposed model required nearly 90 times fewer trainable parameters and approximately 4 times less memory space that allowed 3-fold faster training runtime and 2-fold inference speedup in the conducted experiments using Cambridge-driving Labeled Video Database (CamVid) and Cityscapes datasets. Moreover, despite its notable efficiency in terms of memory and time, the REF-Net attained superior results in several segmentation evaluation metrics that showed roughly 2%, 4%, and 3% increase in pixel accuracy, Dice coefficient, and Jaccard Index, respectively.

ACS Style

Bekhzod Olimov; Jeonghong Kim; Anand Paul. REF-Net: Robust, Efficient, and Fast Network for Semantic Segmentation Applications Using Devices With Limited Computational Resources. IEEE Access 2021, 9, 15084 -15098.

AMA Style

Bekhzod Olimov, Jeonghong Kim, Anand Paul. REF-Net: Robust, Efficient, and Fast Network for Semantic Segmentation Applications Using Devices With Limited Computational Resources. IEEE Access. 2021; 9 ():15084-15098.

Chicago/Turabian Style

Bekhzod Olimov; Jeonghong Kim; Anand Paul. 2021. "REF-Net: Robust, Efficient, and Fast Network for Semantic Segmentation Applications Using Devices With Limited Computational Resources." IEEE Access 9, no. : 15084-15098.

Special issue paper
Published: 04 January 2021 in Multimedia Systems
Reads 0
Downloads 0

Recently, the introduction of Convolutional Neural Network (CNNs) has advanced the way of solving image segmentation tasks. Semantic image segmentation has considerably benefited from employing various CNN models. The most widely used network in this field is U-Net and its different variations. However, these models require significant number of trainable parameters, floating-point operations per second, and great computational power to be trained. These factors make real-time semantic segmentation in low powered devices very hard. Therefore, in the present paper, we aim to modify particular aspects of the U-Net model to improve its performance through developing a fast U-Net (FU-Net) relying on bottleneck convolution layers in the contraction and expansion paths of the model. The proposed model can be utilized in semantic segmentation applications even on the devices with limited computational power and memory by ensuring the state-of-the-art performance. The amount of memory required by the proposed model is reduced by 23 times when compared with the original U-Net. Moreover, the modifications allowed achieving better performance. In conducted experiments, we assessed the performance of the proposed model on two biomedical image segmentation datasets, namely 2018 Data Science Bowl and ICIS 2018: Skin Lesion Analysis Towards Melanoma Detection. FU-Net demonstrated the state-of-the-art results in biomedical image segmentation, requiring the number of trainable parameters reduced by eight times compared with the original U-Net model. In addition, using bottleneck layers decreased the number of computations, resulting in nearly 30% speed-up at the training, validation and test stages. Furthermore, despite relying on fewer parameters FU-Net achieved a slight improvement of the performance in terms of pixel accuracy, Jaccard index, and dice coefficient evaluation metrics.

ACS Style

Bekhzod Olimov; Karshiev Sanjar; Sadia Din; Awaise Ahmad; Anand Paul; Jeonghong Kim. FU-Net: fast biomedical image segmentation model based on bottleneck convolution layers. Multimedia Systems 2021, 27, 637 -650.

AMA Style

Bekhzod Olimov, Karshiev Sanjar, Sadia Din, Awaise Ahmad, Anand Paul, Jeonghong Kim. FU-Net: fast biomedical image segmentation model based on bottleneck convolution layers. Multimedia Systems. 2021; 27 (4):637-650.

Chicago/Turabian Style

Bekhzod Olimov; Karshiev Sanjar; Sadia Din; Awaise Ahmad; Anand Paul; Jeonghong Kim. 2021. "FU-Net: fast biomedical image segmentation model based on bottleneck convolution layers." Multimedia Systems 27, no. 4: 637-650.

Special issue paper
Published: 10 December 2020 in Concurrency and Computation: Practice and Experience
Reads 0
Downloads 0

Convolutional Neural Networks (CNNs) have made a great impact on attaining state‐of‐the‐art results in image task classification. Weight initialization is one of the fundamental steps in formulating a CNN model. It determines the failure or success of the CNN model. In this paper, we conduct a research based on the mathematical background of different weight initialization strategies to determine the one with better performance. To have smooth training, we expect the activation of each layer of the CNN model follow the standard normal distribution with mean 0 and SD 1. It prevents gradients from vanishing and leads to more smooth training. However, it was obtained that even with the appropriate weight initialization technique, a regular Rectified Linear Unit (ReLU) activation function increases the activation mean value. In this paper, we address this issue by proposing weight initialization based (WIB)‐ReLU activation function. The proposed method resulted in more smooth training. Moreover, the experiments showed that WIB‐ReLU outperforms ReLU, Leaky ReLU, parametric ReLU, and exponential linear unit activation functions and results in up to 20% decrease in loss value and 5% increase in accuracy score on both Fashion‐MNIST and CIFAR‐10 databases.

ACS Style

Bekhzod Olimov; Sanjar Karshiev; Eungyeong Jang; Sadia Din; Anand Paul; Jeonghong Kim. Weight initialization based‐rectified linear unit activation function to improve the performance of a convolutional neural network model. Concurrency and Computation: Practice and Experience 2020, 1 .

AMA Style

Bekhzod Olimov, Sanjar Karshiev, Eungyeong Jang, Sadia Din, Anand Paul, Jeonghong Kim. Weight initialization based‐rectified linear unit activation function to improve the performance of a convolutional neural network model. Concurrency and Computation: Practice and Experience. 2020; ():1.

Chicago/Turabian Style

Bekhzod Olimov; Sanjar Karshiev; Eungyeong Jang; Sadia Din; Anand Paul; Jeonghong Kim. 2020. "Weight initialization based‐rectified linear unit activation function to improve the performance of a convolutional neural network model." Concurrency and Computation: Practice and Experience , no. : 1.

Journal article
Published: 05 December 2020 in Microprocessors and Microsystems
Reads 0
Downloads 0

Blockchain is a new technology that demands more efficient and scalable techniques to incorporate it with business models. Therefore, in this paper, we propose a blockchain-based smart healthcare business model, which keeps customers at the center of business. Our proposed smart healthcare business model can predict customer's status and is able to give rewards according to the business rules set by participating organizations. However, businesses also demand something in return, and in our scenario, we are concerned about data in the wild. Our model fetches “data in the wild” from the Internet of Medical Things. Nevertheless, this model can be applied to any business scenario where a customer reward system exists. Our proposed model focuses more on customers and business while utilizing technology to ease the customer and other parties involved in the business. This fusion makes business more effective as the organization can determine the path of business and make decisions accordingly. Incorporating technologies with existing business models such as the “consumer centric model” makes it easy for businesses to modernize.

ACS Style

M. Junaid Gul; Barathi Subramanian; Anand Paul; Jeonghong Kim. Blockchain for public health care in smart society. Microprocessors and Microsystems 2020, 80, 103524 .

AMA Style

M. Junaid Gul, Barathi Subramanian, Anand Paul, Jeonghong Kim. Blockchain for public health care in smart society. Microprocessors and Microsystems. 2020; 80 ():103524.

Chicago/Turabian Style

M. Junaid Gul; Barathi Subramanian; Anand Paul; Jeonghong Kim. 2020. "Blockchain for public health care in smart society." Microprocessors and Microsystems 80, no. : 103524.

Journal article
Published: 02 December 2020 in IEEE Access
Reads 0
Downloads 0

Obtaining data with correct labels is crucial to attain the state-of-the-art performance of Convolutional Neural Network (CNN) models. However, labeling datasets is significantly time-consuming and expensive process because it requires expert knowledge in a particular domain. Therefore, real-life datasets often exhibit incorrect labels due to the involvement of nonexperts in the data-labeling process. Consequently, there are many cases of incorrectly labeled data in the wild. Although the issue of poorly labeled datasets has been studied, the existing methods are complex and difficult to reproduce. Thus, in this study, we proposed a simpler algorithm called “Deep Clean Before Training Net” (DCBT-Net) that is based on cleaning wrongly labeled data points using the information from eigenvalues of the Laplacian matrix obtained from similarities between the data samples. The cleaned data were trained using deep CNN (DCNN) to attain the state-of-the-art results. This system achieved better performance than the existing approaches. In conducted experiments, the performance of the DCBT-Net was tested on three commercially available datasets, namely, Modified National Institute of Standards and Technology (MNIST) database of handwritten digits, Canadian Institute for Advanced Research (CIFAR) and WebVision1000 datasets. The proposed method achieved better results when assessed using several evaluation metrics compared with the existing state-of-the-art methods. Specifically, the DCBT-Net attained an average 15%, 20%, and 3% increase in accuracy score using MNIST database, CIFAR-10 dataset, and WebVision dataset, respectively. Also, the proposed approach demonstrated better results in specificity, sensitivity, positive predictive value, and negative predictive value evaluation metrics.

ACS Style

Bekhzod Olimov; Jeonghong Kim; Anand Paul. DCBT-Net: Training Deep Convolutional Neural Networks With Extremely Noisy Labels. IEEE Access 2020, 8, 220482 -220495.

AMA Style

Bekhzod Olimov, Jeonghong Kim, Anand Paul. DCBT-Net: Training Deep Convolutional Neural Networks With Extremely Noisy Labels. IEEE Access. 2020; 8 (99):220482-220495.

Chicago/Turabian Style

Bekhzod Olimov; Jeonghong Kim; Anand Paul. 2020. "DCBT-Net: Training Deep Convolutional Neural Networks With Extremely Noisy Labels." IEEE Access 8, no. 99: 220482-220495.

Journal article
Published: 25 May 2020 in Applied Sciences
Reads 0
Downloads 0

The early and accurate diagnosis of skin cancer is crucial for providing patients with advanced treatment by focusing medical personnel on specific parts of the skin. Networks based on encoder–decoder architectures have been effectively implemented for numerous computer-vision applications. U-Net, one of CNN architectures based on the encoder–decoder network, has achieved successful performance for skin-lesion segmentation. However, this network has several drawbacks caused by its upsampling method and activation function. In this paper, a fully convolutional network and its architecture are proposed with a modified U-Net, in which a bilinear interpolation method is used for upsampling with a block of convolution layers followed by parametric rectified linear-unit non-linearity. To avoid overfitting, a dropout is applied after each convolution block. The results demonstrate that our recommended technique achieves state-of-the-art performance for skin-lesion segmentation with 94% pixel accuracy and a 88% dice coefficient, respectively.

ACS Style

Karshiev Sanjar; Olimov Bekhzod; Jaeil Kim; Jaesoo Kim; Anand Paul; Jeonghong Kim. Improved U-Net: Fully Convolutional Network Model for Skin-Lesion Segmentation. Applied Sciences 2020, 10, 3658 .

AMA Style

Karshiev Sanjar, Olimov Bekhzod, Jaeil Kim, Jaesoo Kim, Anand Paul, Jeonghong Kim. Improved U-Net: Fully Convolutional Network Model for Skin-Lesion Segmentation. Applied Sciences. 2020; 10 (10):3658.

Chicago/Turabian Style

Karshiev Sanjar; Olimov Bekhzod; Jaeil Kim; Jaesoo Kim; Anand Paul; Jeonghong Kim. 2020. "Improved U-Net: Fully Convolutional Network Model for Skin-Lesion Segmentation." Applied Sciences 10, no. 10: 3658.

Journal article
Published: 08 April 2020 in ISPRS International Journal of Geo-Information
Reads 0
Downloads 0

Accurate house price forecasts are very important for formulating national economic policies. In this paper, we offer an effective method to predict houses’ sale prices. Our algorithm includes one-hot encoding to convert text data into numeric data, feature correlation to select only the most correlated variables, and a technique to overcome the missing data. Our approach is an effective way to handle missing data in large datasets with the K-nearest neighbor algorithm based on the most correlated features (KNN–MCF). As far as we are concerned, there has been no previous research that has focused on important features dealing with missing observations. Compared to the typical machine learning prediction algorithms, the prediction accuracy of the proposed method is 92.01% with the random forest algorithm, which is more efficient than the other methods.

ACS Style

Karshiev Sanjar; Olimov Bekhzod; Jaesoo Kim; Anand Paul; Jeonghong Kim. Missing Data Imputation for Geolocation-based Price Prediction Using KNN–MCF Method. ISPRS International Journal of Geo-Information 2020, 9, 227 .

AMA Style

Karshiev Sanjar, Olimov Bekhzod, Jaesoo Kim, Anand Paul, Jeonghong Kim. Missing Data Imputation for Geolocation-based Price Prediction Using KNN–MCF Method. ISPRS International Journal of Geo-Information. 2020; 9 (4):227.

Chicago/Turabian Style

Karshiev Sanjar; Olimov Bekhzod; Jaesoo Kim; Anand Paul; Jeonghong Kim. 2020. "Missing Data Imputation for Geolocation-based Price Prediction Using KNN–MCF Method." ISPRS International Journal of Geo-Information 9, no. 4: 227.

Methodologies and application
Published: 28 March 2020 in Soft Computing
Reads 0
Downloads 0

Blockchain expansion is the high priority necessity to improve security. Hacking and other attacks are headway from system innovation and security measures for the cloud architecture. That is why the countermeasure deployed for such attacks should act in an opportune way and ought to be situated as close as possible to attacking device. As an example, DDoS attacks were not that complex as they are getting now with the new technology known as IoT. Imagine the consequences if 25 billion of IoT devices generate a huge amount of data for DDoS attacks. That is why we propose a new framework that can expand blockchain in a manner where more companies can share their resources to enhance security. So, we proposed a new and complete framework with cloud, fog, to secure configuration files with blockchain technology. Our framework considers the configuration files from SDN or NFV as an asset to secure with blockchain. By saving configuration files into blockchain, we can detect illegal changes occurred to configuration files after hacking attack. This study also focuses on expanding blockchain between the multiple service providers with ease to prevent waste of resources. This paper mainly provides opportunities for different could or companies to secure their assets by employing the power of blockchain and smart contracts.

ACS Style

M. Junaid Gul; Abdul Rehman; Anand Paul; Seungmin Rho; Rabia Riaz; Jeonghong Kim. Blockchain Expansion to secure Assets with Fog Node on special Duty. Soft Computing 2020, 24, 15209 -15221.

AMA Style

M. Junaid Gul, Abdul Rehman, Anand Paul, Seungmin Rho, Rabia Riaz, Jeonghong Kim. Blockchain Expansion to secure Assets with Fog Node on special Duty. Soft Computing. 2020; 24 (20):15209-15221.

Chicago/Turabian Style

M. Junaid Gul; Abdul Rehman; Anand Paul; Seungmin Rho; Rabia Riaz; Jeonghong Kim. 2020. "Blockchain Expansion to secure Assets with Fog Node on special Duty." Soft Computing 24, no. 20: 15209-15221.

Journal article
Published: 28 June 2017 in Sustainability
Reads 0
Downloads 0

In recent works on the Internet of Vehicles (IoV), “intelligent” and “sustainable” have been the buzzwords in the context of transportation. Maintaining sustainability in IoV is always a challenge. Sustainability in IoV can be achieved not only by the use of pollution-free vehicular systems, but also by maintenance of road traffic safety or prevention of accidents or collisions. With the aim of establishing an effective sustainable transportation planning system, this study performs a short analysis of existing sustainable transportation methods in the IoV. This study also analyzes various characteristics of sustainability and the advantages and disadvantages of existing transportation systems. Toward the end, this study provides a clear suggestion for effective sustainable transportation planning aimed at the maintenance of an eco-friendly environment and road traffic safety, which, in turn, would lead to a sustainable transportation system.

ACS Style

AnandKumar Balasubramaniam; Anand Paul; Won-Hwa Hong; Hyuncheol Seo; Jeong Hong Kim. Comparative Analysis of Intelligent Transportation Systems for Sustainable Environment in Smart Cities. Sustainability 2017, 9, 1120 .

AMA Style

AnandKumar Balasubramaniam, Anand Paul, Won-Hwa Hong, Hyuncheol Seo, Jeong Hong Kim. Comparative Analysis of Intelligent Transportation Systems for Sustainable Environment in Smart Cities. Sustainability. 2017; 9 (7):1120.

Chicago/Turabian Style

AnandKumar Balasubramaniam; Anand Paul; Won-Hwa Hong; Hyuncheol Seo; Jeong Hong Kim. 2017. "Comparative Analysis of Intelligent Transportation Systems for Sustainable Environment in Smart Cities." Sustainability 9, no. 7: 1120.

Journal article
Published: 13 October 2016 in SpringerPlus
Reads 0
Downloads 0

The analysis of leukocyte images has drawn interest from fields of both medicine and computer vision for quite some time where different techniques have been applied to automate the process of manual analysis and classification of such images. Manual analysis of blood samples to identify leukocytes is time-consuming and susceptible to error due to the different morphological features of the cells. In this article, the nature-inspired plant growth simulation algorithm has been applied to optimize the image processing technique of object localization of medical images of leukocytes. This paper presents a random bionic algorithm for the automated detection of white blood cells embedded in cluttered smear and stained images of blood samples that uses a fitness function that matches the resemblances of the generated candidate solution to an actual leukocyte. The set of candidate solutions evolves via successive iterations as the proposed algorithm proceeds, guaranteeing their fit with the actual leukocytes outlined in the edge map of the image. The higher precision and sensitivity of the proposed scheme from the existing methods is validated with the experimental results of blood cell images. The proposed method reduces the feasible sets of growth points in each iteration, thereby reducing the required run time of load flow, objective function evaluation, thus reaching the goal state in minimum time and within the desired constraints.

ACS Style

Deblina Bhattacharjee; Anand Paul; Jeong Hong Kim; Mucheol Kim. An object localization optimization technique in medical images using plant growth simulation algorithm. SpringerPlus 2016, 5, 1 -20.

AMA Style

Deblina Bhattacharjee, Anand Paul, Jeong Hong Kim, Mucheol Kim. An object localization optimization technique in medical images using plant growth simulation algorithm. SpringerPlus. 2016; 5 (1):1-20.

Chicago/Turabian Style

Deblina Bhattacharjee; Anand Paul; Jeong Hong Kim; Mucheol Kim. 2016. "An object localization optimization technique in medical images using plant growth simulation algorithm." SpringerPlus 5, no. 1: 1-20.