Skip to main content

Bo-Yeong Kang

Followers

4

Following

1

Public Views

Jonathan Zittrain

Harvard University

Vrije Universiteit Brussel

Julita Vassileva

University of Saskatchewan

Knox College

Université Gustave Eiffel

Roshan Chitrakar

Nepal College of Information Technology

Graduate Center of the City University of New York

Dr. Shadab Alam

Jazan University

PALIMOTE JUSTICE

RIVERS STATE POLYTECHNIC

Ataturk University

Interests

Uploads

Papers by Bo-Yeong Kang

Agricultural Robot-Centered Recognition of Early-Developmental Pest Stage Based on Deep Learning: A Case Study on Fall Armyworm (Spodoptera frugiperda)

Sensors

Accurately detecting early developmental stages of insect pests (larvae) from off-the-shelf stere... more Accurately detecting early developmental stages of insect pests (larvae) from off-the-shelf stereo camera sensor data using deep learning holds several benefits for farmers, from simple robot configuration to early neutralization of this less agile but more disastrous stage. Machine vision technology has advanced from bulk spraying to precise dosage to directly rubbing on the infected crops. However, these solutions primarily focus on adult pests and post-infestation stages. This study suggested using a front-pointing red-green-blue (RGB) stereo camera mounted on a robot to identify pest larvae using deep learning. The camera feeds data into our deep-learning algorithms experimented on eight ImageNet pre-trained models. The combination of the insect classifier and the detector replicates the peripheral and foveal line-of-sight vision on our custom pest larvae dataset, respectively. This enables a trade-off between the robot’s smooth operation and localization precision in the pest c...

Path planning for robot using Population-Based Incremental Learning

The 4th Annual IEEE International Conference on Cyber Technology in Automation, Control and Intelligent, 2014

Recently, genetic algorithms (GAs) have attracted great interest owing to efficiency and flexibil... more Recently, genetic algorithms (GAs) have attracted great interest owing to efficiency and flexibility against complex robot path planning problems. To accelerate the convergence speed, preceding researches adapted conventional GAs by using problem-specific techniques. However, such approaches increase computational burden and algorithmic complexity, resulting in subsequent additional problems. In this paper, we used Population-Based Incremental Learning (PBIL) algorithm for robot path planning as a probabilistic evolutionary approach. In addition to PBIL, we also proposed the probabilistic model of nodes and the edge bank to generate promising paths. The experimental results demonstrate that the proposed method gave markedly better performance than its conventional counter-parts(GA,kGA,fGA) in terms of success rates and the quality of obtained paths.

Conceptual Design of Multi-Cleaning Robots with Docking Mechanism

Advanced Science Letters, 2017

A Computational Study On The Optimization of Transcranial Temporal Interfering Stimulation With High-Definition Electrode Using Unsupervised Neural Network

Transcranial temporal interfering stimulation (tTIS) can focally stimulate deep parts of the brai... more Transcranial temporal interfering stimulation (tTIS) can focally stimulate deep parts of the brain, which are related to specific functions, by using beats at two high AC frequencies that do not affect the human brain. However, it has limitations in terms of calculation time and precision for optimization because of its complexity and non-linearity. We aimed to propose a method using an unsupervised neural network (USNN) for tTIS to optimize quickly the interfering current value of high-definition electrodes, which can finely stimulate the deep part of the brain, and analyze the performance and characteristics of tTIS. A computational study was conducted using 16 realistic head models. This method generated the strongest stimulation on the target, even when targeting deep areas or multi-target stimulation. The tTIS was robust with target depth compared with transcranial alternating current stimulation, and mis-stimulation could be reduced compared with the case of using two-pair inf...

Cooperative Robot for Table Balancing Using Q-learning

Journal of Korea Robotics Society, 2020

Multi-Cleaning Robots Using Cleaning Distribution Method Based on Map Decomposition in Large Environments

IEEE Access, 2020

Most cleaning robots have a good cleaning performance for small environments such as houses but r... more Most cleaning robots have a good cleaning performance for small environments such as houses but require a longer cleaning time due to problems such as slow cleaning progress and low battery capacity, making the robots unsuitable for large environments such as libraries and airports. Cleaning large environments with multiple robots is faster than cleaning them with a single robot. Multi-cleaning robots can utilize several robots to simultaneously clean and share the task of cleaning among the robots. However, as the number of robots increases and the effective distribution of cleaning is not efficient during the cleaning process, the cleaning time will consequently be longer due to the frequent collisions between the robots. Therefore, to shorten the cleaning time, multi-cleaning robots require a coverage path planning that uses an effective cleaning distribution method in the cleaning process. In this paper, a coverage path planning using a cleaning distribution method based on map decomposition is proposed to reduce the cleaning time of multi-cleaning robots. The experimental results demonstrated that the proposed multi-cleaning robots' coverage path planning could be used in large environments in the presence of several types of obstacles. Furthermore, the cleaning time was found to be shorter than that of the previous methods in the case of multi-cleaning robots. INDEX TERMS Coverage path planning, cleaning robot, computational efficiency, multi-robots system, robot path planning.

Extended BSA Coverage Algorithm for Large Unknown Map

Journal of Korean Institute of Intelligent Systems, 2017

Continuous emotion estimation of facial expressions on JAFFE and CK+ datasets for human–robot interaction

Intelligent Service Robotics, 2019

Human-robot interaction was always based on estimation of human emotions from human facial expres... more Human-robot interaction was always based on estimation of human emotions from human facial expressions, voice and gestures. Human emotions were always categorized in a discretized manner, while we estimate facial images from common datasets for continuous emotions. Linear regression was used in this study which numerically quantizes human emotions as valence and arousal by displaying the raw images on the two-respective coordinate axis. The face image datasets from the Japanese female facial expression (JAFFE) dataset and the extended Cohn-Kanade (CK+) dataset were used in this experiment. Human emotions for the above-mentioned datasets were interpreted by 85 participants who were used in the experimentation. The best result from a series of experiments shows that the minimum of root mean square error for the JAFFE dataset was 0.1661 for valence and 0.1379 for arousal. The proposed method has been compared with previous methods such as songs, sentences, and it is observed that the proposed method for common datasets testing showed an outstanding emotion estimation performance.

Estimation of Driver’s Danger Level when Accessing the Center Console for Safe Driving

Sensors, 2018

This paper proposes a system for estimating the level of danger when a driver accesses the center... more This paper proposes a system for estimating the level of danger when a driver accesses the center console of a vehicle while driving. The proposed system uses a driver monitoring platform to measure the distance between the driver’s hand and the center console during driving, as well as the time taken for the driver to access the center console. Three infrared sensors on the center console are used to detect the movement of the driver’s hand. These sensors are installed in three locations: the air conditioner or heater (temperature control) button, wind direction control button, and wind intensity control button. A driver’s danger level is estimated to be based on a linear regression analysis of the distance and time of movement between the driver’s hand and the center console, as measured in the proposed scenarios. In the experimental results of the proposed scenarios, the root mean square error of driver H using distance and time of movement between the driver’s hand and the cente...

Improving Clustering Performance Using Gene Ontology

Journal of Korean Institute of Intelligent Systems, 2009

Recently many researches have been presented to improve the clustering performance of gene expres... more Recently many researches have been presented to improve the clustering performance of gene expression data by incorporating Gene Ontology into the process of clustering. In particular, Kustra et al. showed higher performance improvement by exploiting Biological Process Ontology compared to the typical expression-based clustering. This paper extends the work of Kustra et al. by performing extensive experiments on the way of incorporating GO structures. To this end, we used three ontological distance measures (Lin's, Resnik's, Jiang's) and three GO structures (BP, CC, MF) for the yeast expression data. From all test cases, We found that clustering performances were remarkably improved by incorporating GO; especially, Resnik's distance measure based on Biological Process Ontology was the best.

An Ontology-Based Bayesian Network Approach for Representing Uncertainty in Clinical Practice Guidelines

Lecture Notes in Computer Science, 2008

Clinical Practice Guidelines (CPGs) play an important role in improving the quality of care and p... more Clinical Practice Guidelines (CPGs) play an important role in improving the quality of care and patient outcomes. Although several machine-readable representations of practice guidelines implemented with semantic web technologies have been presented, there is no implementation to represent uncertainty with respect to activity graphs in clinical practice guidelines. In this paper, we are exploring a Bayesian Network(BN) approach for representing the uncertainty in CPGs based on ontologies. Based on the representation of uncertainty in CPGs, when an activity occurs, we can evaluate its effect on the whole clinical process, which, in turn, can help doctors judge the risk of uncertainty for other activities, and make a decision. A variable elimination algorithm is applied to implement the BN inference and a validation of an aspirin therapy scenario for diabetic patients is proposed.

A novel approach to semantic indexing based on concept

Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - ACL '03, 2003

Continuous Emotion Estimation for Human Machine Interaction

Advanced Science Letters, 2015

ABSTRACT

Translation of Unknown Terms Via Web Mining for Information Retrieval

Lecture Notes in Computer Science, 2006

A Theme Allocation for a Sentence Based on Head Driven Patterns

Lecture Notes in Computer Science, 2005

Document Filtering for Domain Ontology Based on Concept Preferences

The Semantic Web – ASWC 2006, 2006

Page 1. Document Filtering for Domain Ontology Based on Concept Preferences Bo-Yeong Kang and Hon... more

Combining Semantic Based Indexing and Fuzzy Relevance Model in IR System

A semantic annotation tool to extract instances from korean web documents

Although there has been extensive research on developing semantic annotation tools recently, only... more Although there has been extensive research on developing semantic annotation tools recently, only few systems support automatic information extraction. In this paper, we propose a semantic annotation system named SARM, which has an automatic instance extraction module based on two machine learning techniques, Bayesian Classifier and Support Vector Machine. SARM has been tested to make a Korean Restaurant ontology evolve by automatically extracting instances from Web documents in Korean. The automatic instance extraction module can accelerate the annotation work which is very time-consuming and involves a lot of human labor. We describe the implementation of our system and also compare the performances of the two machine learning methods we used.

On Concept Based Approach for Determining Semantic Index Terms

Lecture Notes in Computer Science, 2003

Page 1. On Concept Based Approach for Determining Semantic Index Terms Bo-Yeong Kang and Sang-Jo ... more

Performance Analysis of Semantic Indexing in Text Retrieval

Lecture Notes in Computer Science, 2004

We developed a new indexing formalism that considers not only the terms in a document, but also t... more We developed a new indexing formalism that considers not only the terms in a document, but also the concepts to represent the semantic content of a document. In this approach, concept clusters are defined and a concept vector space model is proposed to represent the semantic importance of words and concepts within a document. Through experiments on the TREC-2 collection, we show that the proposed method outperforms an indexing method based on term frequency.

Agricultural Robot-Centered Recognition of Early-Developmental Pest Stage Based on Deep Learning: A Case Study on Fall Armyworm (Spodoptera frugiperda)

Sensors

Accurately detecting early developmental stages of insect pests (larvae) from off-the-shelf stere... more Accurately detecting early developmental stages of insect pests (larvae) from off-the-shelf stereo camera sensor data using deep learning holds several benefits for farmers, from simple robot configuration to early neutralization of this less agile but more disastrous stage. Machine vision technology has advanced from bulk spraying to precise dosage to directly rubbing on the infected crops. However, these solutions primarily focus on adult pests and post-infestation stages. This study suggested using a front-pointing red-green-blue (RGB) stereo camera mounted on a robot to identify pest larvae using deep learning. The camera feeds data into our deep-learning algorithms experimented on eight ImageNet pre-trained models. The combination of the insect classifier and the detector replicates the peripheral and foveal line-of-sight vision on our custom pest larvae dataset, respectively. This enables a trade-off between the robot’s smooth operation and localization precision in the pest c...

Path planning for robot using Population-Based Incremental Learning

The 4th Annual IEEE International Conference on Cyber Technology in Automation, Control and Intelligent, 2014

Recently, genetic algorithms (GAs) have attracted great interest owing to efficiency and flexibil... more Recently, genetic algorithms (GAs) have attracted great interest owing to efficiency and flexibility against complex robot path planning problems. To accelerate the convergence speed, preceding researches adapted conventional GAs by using problem-specific techniques. However, such approaches increase computational burden and algorithmic complexity, resulting in subsequent additional problems. In this paper, we used Population-Based Incremental Learning (PBIL) algorithm for robot path planning as a probabilistic evolutionary approach. In addition to PBIL, we also proposed the probabilistic model of nodes and the edge bank to generate promising paths. The experimental results demonstrate that the proposed method gave markedly better performance than its conventional counter-parts(GA,kGA,fGA) in terms of success rates and the quality of obtained paths.

Conceptual Design of Multi-Cleaning Robots with Docking Mechanism

Advanced Science Letters, 2017

A Computational Study On The Optimization of Transcranial Temporal Interfering Stimulation With High-Definition Electrode Using Unsupervised Neural Network

Transcranial temporal interfering stimulation (tTIS) can focally stimulate deep parts of the brai... more Transcranial temporal interfering stimulation (tTIS) can focally stimulate deep parts of the brain, which are related to specific functions, by using beats at two high AC frequencies that do not affect the human brain. However, it has limitations in terms of calculation time and precision for optimization because of its complexity and non-linearity. We aimed to propose a method using an unsupervised neural network (USNN) for tTIS to optimize quickly the interfering current value of high-definition electrodes, which can finely stimulate the deep part of the brain, and analyze the performance and characteristics of tTIS. A computational study was conducted using 16 realistic head models. This method generated the strongest stimulation on the target, even when targeting deep areas or multi-target stimulation. The tTIS was robust with target depth compared with transcranial alternating current stimulation, and mis-stimulation could be reduced compared with the case of using two-pair inf...

Cooperative Robot for Table Balancing Using Q-learning

Journal of Korea Robotics Society, 2020

Multi-Cleaning Robots Using Cleaning Distribution Method Based on Map Decomposition in Large Environments

IEEE Access, 2020

Most cleaning robots have a good cleaning performance for small environments such as houses but r... more Most cleaning robots have a good cleaning performance for small environments such as houses but require a longer cleaning time due to problems such as slow cleaning progress and low battery capacity, making the robots unsuitable for large environments such as libraries and airports. Cleaning large environments with multiple robots is faster than cleaning them with a single robot. Multi-cleaning robots can utilize several robots to simultaneously clean and share the task of cleaning among the robots. However, as the number of robots increases and the effective distribution of cleaning is not efficient during the cleaning process, the cleaning time will consequently be longer due to the frequent collisions between the robots. Therefore, to shorten the cleaning time, multi-cleaning robots require a coverage path planning that uses an effective cleaning distribution method in the cleaning process. In this paper, a coverage path planning using a cleaning distribution method based on map decomposition is proposed to reduce the cleaning time of multi-cleaning robots. The experimental results demonstrated that the proposed multi-cleaning robots' coverage path planning could be used in large environments in the presence of several types of obstacles. Furthermore, the cleaning time was found to be shorter than that of the previous methods in the case of multi-cleaning robots. INDEX TERMS Coverage path planning, cleaning robot, computational efficiency, multi-robots system, robot path planning.

Extended BSA Coverage Algorithm for Large Unknown Map

Journal of Korean Institute of Intelligent Systems, 2017

Continuous emotion estimation of facial expressions on JAFFE and CK+ datasets for human–robot interaction

Intelligent Service Robotics, 2019

Human-robot interaction was always based on estimation of human emotions from human facial expres... more Human-robot interaction was always based on estimation of human emotions from human facial expressions, voice and gestures. Human emotions were always categorized in a discretized manner, while we estimate facial images from common datasets for continuous emotions. Linear regression was used in this study which numerically quantizes human emotions as valence and arousal by displaying the raw images on the two-respective coordinate axis. The face image datasets from the Japanese female facial expression (JAFFE) dataset and the extended Cohn-Kanade (CK+) dataset were used in this experiment. Human emotions for the above-mentioned datasets were interpreted by 85 participants who were used in the experimentation. The best result from a series of experiments shows that the minimum of root mean square error for the JAFFE dataset was 0.1661 for valence and 0.1379 for arousal. The proposed method has been compared with previous methods such as songs, sentences, and it is observed that the proposed method for common datasets testing showed an outstanding emotion estimation performance.

Estimation of Driver’s Danger Level when Accessing the Center Console for Safe Driving

Sensors, 2018

This paper proposes a system for estimating the level of danger when a driver accesses the center... more This paper proposes a system for estimating the level of danger when a driver accesses the center console of a vehicle while driving. The proposed system uses a driver monitoring platform to measure the distance between the driver’s hand and the center console during driving, as well as the time taken for the driver to access the center console. Three infrared sensors on the center console are used to detect the movement of the driver’s hand. These sensors are installed in three locations: the air conditioner or heater (temperature control) button, wind direction control button, and wind intensity control button. A driver’s danger level is estimated to be based on a linear regression analysis of the distance and time of movement between the driver’s hand and the center console, as measured in the proposed scenarios. In the experimental results of the proposed scenarios, the root mean square error of driver H using distance and time of movement between the driver’s hand and the cente...

Improving Clustering Performance Using Gene Ontology

Journal of Korean Institute of Intelligent Systems, 2009

Recently many researches have been presented to improve the clustering performance of gene expres... more Recently many researches have been presented to improve the clustering performance of gene expression data by incorporating Gene Ontology into the process of clustering. In particular, Kustra et al. showed higher performance improvement by exploiting Biological Process Ontology compared to the typical expression-based clustering. This paper extends the work of Kustra et al. by performing extensive experiments on the way of incorporating GO structures. To this end, we used three ontological distance measures (Lin's, Resnik's, Jiang's) and three GO structures (BP, CC, MF) for the yeast expression data. From all test cases, We found that clustering performances were remarkably improved by incorporating GO; especially, Resnik's distance measure based on Biological Process Ontology was the best.

An Ontology-Based Bayesian Network Approach for Representing Uncertainty in Clinical Practice Guidelines

Lecture Notes in Computer Science, 2008

Clinical Practice Guidelines (CPGs) play an important role in improving the quality of care and p... more Clinical Practice Guidelines (CPGs) play an important role in improving the quality of care and patient outcomes. Although several machine-readable representations of practice guidelines implemented with semantic web technologies have been presented, there is no implementation to represent uncertainty with respect to activity graphs in clinical practice guidelines. In this paper, we are exploring a Bayesian Network(BN) approach for representing the uncertainty in CPGs based on ontologies. Based on the representation of uncertainty in CPGs, when an activity occurs, we can evaluate its effect on the whole clinical process, which, in turn, can help doctors judge the risk of uncertainty for other activities, and make a decision. A variable elimination algorithm is applied to implement the BN inference and a validation of an aspirin therapy scenario for diabetic patients is proposed.

A novel approach to semantic indexing based on concept

Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - ACL '03, 2003

Continuous Emotion Estimation for Human Machine Interaction

Advanced Science Letters, 2015

ABSTRACT

Translation of Unknown Terms Via Web Mining for Information Retrieval

Lecture Notes in Computer Science, 2006

A Theme Allocation for a Sentence Based on Head Driven Patterns

Lecture Notes in Computer Science, 2005

Document Filtering for Domain Ontology Based on Concept Preferences

The Semantic Web – ASWC 2006, 2006

Page 1. Document Filtering for Domain Ontology Based on Concept Preferences Bo-Yeong Kang and Hon... more

Combining Semantic Based Indexing and Fuzzy Relevance Model in IR System

A semantic annotation tool to extract instances from korean web documents

Although there has been extensive research on developing semantic annotation tools recently, only... more Although there has been extensive research on developing semantic annotation tools recently, only few systems support automatic information extraction. In this paper, we propose a semantic annotation system named SARM, which has an automatic instance extraction module based on two machine learning techniques, Bayesian Classifier and Support Vector Machine. SARM has been tested to make a Korean Restaurant ontology evolve by automatically extracting instances from Web documents in Korean. The automatic instance extraction module can accelerate the annotation work which is very time-consuming and involves a lot of human labor. We describe the implementation of our system and also compare the performances of the two machine learning methods we used.

On Concept Based Approach for Determining Semantic Index Terms

Lecture Notes in Computer Science, 2003

Page 1. On Concept Based Approach for Determining Semantic Index Terms Bo-Yeong Kang and Sang-Jo ... more

Performance Analysis of Semantic Indexing in Text Retrieval

Lecture Notes in Computer Science, 2004

We developed a new indexing formalism that considers not only the terms in a document, but also t... more We developed a new indexing formalism that considers not only the terms in a document, but also the concepts to represent the semantic content of a document. In this approach, concept clusters are defined and a concept vector space model is proposed to represent the semantic importance of words and concepts within a document. Through experiments on the TREC-2 collection, we show that the proposed method outperforms an indexing method based on term frequency.