|
A Deep Learning Based Approach for Strawberry Yield Prediction via Semantic Graphics |
|
Talha Ilyas, Hyongsuk Kim(JeonBuk National University, Korea) |
| Reliable estimation of the quantity of strawberry fruit with respect to their ripeness level is critical for forecasting the upcoming strawberry production. Typically, the quantity and ripeness of fruits are estimated manually, which is labor-intensive and time-consuming. In this case, automated yield prediction based on robotic agriculture is a realistic option. We provide in this study an automated strawberry fruit recognition and counting system for accurate and reliable yield prediction. |
|
|
Composite Momentum-based Observers for the Estimation of External Force on Robot Manipulators |
|
Wookyong Kwon, Seonghyeon Jo, Jeyoun Dong, Dongyeop Kang(ETRI, Korea), Sang Jun Lee(Jeonbuk National University, Korea) |
| This paper investigates the estimation of external force on robot manipulators. The issue is of great importance for the safety of human-robot collaborative tasks and for the human-robot interactive tasks. The estimation of external force using model-based approach suffers from model uncertainties and disturbances. To satisfy both fast convergence and robustness, composite observers are newly proposed, which is composed of sliding mode observers and polynomial observers based on momentum state. Through their complementary roles, a composite observer achieves improved performance in safety and estimation. |
|
|
HM-Prom: CNN based Prediction of TATA Promoters from Human and Mouse Sequences |
|
Muhammad Shujaat(Jeonbuk National University, Korea), Kil To Chong(Jeonbuk National University, Jeonju 54896, Ko, Korea) |
| A promoter is a DNA element that is found surrounding the transcription start site and can regulate gene
transcription. The detection of promoters is critical in defining transcription units, examining gene structure, assessing gene regulatory mechanisms. In this paper, we present HM-Prom, a strong deep learning model for analyzing the properties of short eukaryotic promoter sequences and properly recognizing human and mouse promoter sequences. We performed experiments on a benchmark dataset and compared our results to four cutting-edge tools to demonstrate our superiority. Comparative results show that our method outperforms other approaches for recognizing promoters |
|
|
A Neural Network Based Computational Model for Post-transcriptional Modification Site Identification |
|
Mobeen Ur Rehman, Kil To Chong(Jeonbuk National University, Korea) |
| Understanding the distributions of RNA modifications in genome sequences will lead to the discovery of their
functions. We built a new predictor in this paper that can identify m6A, m5C, and m1A for alterations in Homo sapiens, Mus musculus, and Saccharomyces cerevisiae at the same time. The proposed model uses k-mer encoding scheme to encode the input sequence. The encoded sequence is used by convolution neural network which automatically learns the features and performs classification between modified and unmodified sequences. The proposed model has exhibited good improvement in performance when compared with state-of-the-art techniques. |
|
|
Solar Radiation Prediction for Solar-Powered UAV using Deep Learning Algorithm |
|
Giancarlo Eder Guerra Padilla(Jeonbuk National University, Korea), Kun-Jung Kim, Kee-Ho Yu(Chonbuk National University, Korea) |
| This paper presents the analysis of the solar radiation prediction for an Unmanned Aerial Vehicle (UAV) for communication relay applications using deep learning algorithms. First, the meteorological data was acquired from Korea’s weather forecast system in order to train the model. Then, a long-short term memory (LSTM) and bidirectional LSTM (Bi-LSTM) algorithm were modeled according to the different meteorological parameters. The models were trained using historical weather data from the Korea Meteorological Administration, and tested with the next-day weather forecast for the following 48hrs. |
| |