• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.335-337
• /
• 2024

This paper presents a new open-world object detection method emphasizing uncertainty representation in machine learning models. The focus is on adapting to real-world uncertainties, incrementally updating the model's knowledge repository for dynamic scenarios. Applications like autonomous vehicles benefit from improved multi-class classification accuracy. The paper reviews challenges in existing methodologies, stressing the need for universal detectors capable of handling unknown classes. Future directions propose collaboration, integration of language models, to improve the adaptability and applicability of open-world object detection.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.11
• /
• pp.5392-5418
• /
• 2017

The primary aim of this paper is to propose a non-linear regression based technique for mapping different network Quality of Service (QoS) factors to an integrated end-user Quality of Experience (QoE) or Mean Opinion Score (MOS) value for an online video streaming service on a mobile phone. We use six network QoS factors for finding out the user QoE. The contribution of this paper is threefold. First, we investigate the impact of the network QoS factors on the perceived video quality. Next, we perform an individual mapping of the significant network QoS parameters obtained in stage 1 to the user QoE based upon a non-linear regression method. The optimal QoS to QoE mapping function is chosen based upon a decision variable. In the final stage, we evaluate the integrated QoE of the system by taking the combined effect of all the QoS factors considered. Extensive subjective tests comprising of over 50 people across a wide variety of video contents encoded with H.265/HEVC and VP9 codec have been conducted in order to gather the actual MOS data for the purpose of QoS to QoE mapping. Our proposed hybrid model has been validated against unseen data and reveals good prediction accuracy.

• International Journal of Advanced Culture Technology
• /
• v.11 no.4
• /
• pp.393-405
• /
• 2023

Accurate prediction of wind speed and power is vital for enhancing the efficiency of wind energy systems. Numerous solutions have been implemented to date, demonstrating their potential to improve forecasting. Among these, deep learning is perceived as a revolutionary approach in the field. However, despite their effectiveness, the noise present in the collected data remains a significant challenge. This noise has the potential to diminish the performance of these algorithms, leading to inaccurate predictions. In response to this, this study explores a novel feature engineering approach. This approach involves altering the data input shape in both Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) and Autoregressive models for various forecasting horizons. The results reveal substantial enhancements in model resilience against noise resulting from step increases in data. The approach could achieve an impressive 83% accuracy in predicting unseen data up to the 24th steps. Furthermore, this method consistently provides high accuracy for short, mid, and long-term forecasts, outperforming the performance of individual models. These findings pave the way for further research on noise reduction strategies at different forecasting horizons through shape-wise feature engineering.

• The Journal of Korea Robotics Society
• /
• v.19 no.3
• /
• pp.293-310
• /
• 2024

In this paper, we propose an agent model for Language-Driven Zero-Shot Object Navigation (L-ZSON) tasks, which takes in a freeform language description of an unseen target object and navigates to find out the target object in an inexperienced environment. In general, an L-ZSON agent should able to visually ground the target object by understanding the freeform language description of it and recognizing the corresponding visual object in camera images. Moreover, the L-ZSON agent should be also able to build a rich spatial context map over the unknown environment and decide efficient exploration actions based on the map until the target object is present in the field of view. To address these challenging issues, we proposes AML (Agent Model for L-ZSON), a novel L-ZSON agent model to make effective use of AI foundation models such as Large Language Model (LLM) and Vision-Language model (VLM). In order to tackle the visual grounding issue of the target object description, our agent model employs GLEE, a VLM pretrained for locating and identifying arbitrary objects in images and videos in the open world scenario. To meet the exploration policy issue, the proposed agent model leverages the commonsense knowledge of LLM to make sequential navigational decisions. By conducting various quantitative and qualitative experiments with RoboTHOR, the 3D simulation platform and PASTURE, the L-ZSON benchmark dataset, we show the superior performance of the proposed agent model.

• Korean Chemical Engineering Research
• /
• v.59 no.4
• /
• pp.532-541
• /
• 2021

Recently, research on the application of artificial intelligence in the chemical process has been increasing rapidly. However, overfitting is a significant problem that prevents the model from being generalized well to predict unseen data on test data, as well as observed training data. Cross validation is one of the ways to solve the overfitting problem. In this study, the time-series cross validation method was applied to optimize the number of batch and epoch in the hyperparameters of the prediction model for the 2,3-BDO distillation process, and it compared with K-fold cross validation generally used. As a result, the RMSE of the model with time-series cross validation was lower by 9.06%, and the MAPE was higher by 0.61% than the model with K-fold cross validation. Also, the calculation time was 198.29 sec less than the K-fold cross validation method.

• Imaging Science in Dentistry
• /
• v.49 no.1
• /
• pp.19-26
• /
• 2019

Purpose: It has been proposed that using new prediction methods, such as neural networks based on dental data, could improve age estimation. This study aimed to assess the possibility of exploiting neural networks for estimating age by means of the pulp-to-tooth ratio in canines as a non-destructive, non-expensive, and accurate method. In addition, the predictive performance of neural networks was compared with that of a linear regression model. Materials and Methods: Three hundred subjects whose age ranged from 14 to 60 years and were well distributed among various age groups were included in the study. Two statistical software programs, SPSS 21 (IBM Corp., Armonk, NY, USA) and R, were used for statistical analyses. Results: The results indicated that the neural network model generally performed better than the regression model for estimation of age with pulp-to-tooth ratio data. The prediction errors of the developed neural network model were acceptable, with a root mean square error (RMSE) of 4.40 years and a mean absolute error (MAE) of 4.12 years for the unseen dataset. The prediction errors of the regression model were higher than those of the neural network, with an RMSE of 10.26 years and a MAE of 8.17 years for the test dataset. Conclusion: The neural network method showed relatively acceptable performance, with an MAE of 4.12 years. The application of neural networks creates new opportunities to obtain more accurate estimations of age in forensic research.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.12
• /
• pp.509-516
• /
• 2022

Accurate pose prediction of objects in 3D space is an important visual recognition technique widely used in many applications such as scene understanding in both indoor and outdoor environments, robotic object manipulation, autonomous driving, and augmented reality. Most previous works for object pose estimation have the limitation that they require an exact 3D CAD model for each object. Unlike such previous works, this paper proposes a novel neural network model that can predict the poses of unknown objects based on only their RGB color images without the corresponding 3D CAD models. The proposed model can obtain depth maps required for unknown object pose prediction by using an adaptive depth estimator, AdaBins,. In this paper, we evaluate the usefulness and the performance of the proposed model through experiments using benchmark datasets.

• Journal of Astronomy and Space Sciences
• /
• v.12 no.2
• /
• pp.179-195
• /
• 1995

RT Per has been known as a close binary of which the orbital period has unpredictably varied so far. Although there are no agreements with the working mechanism for the changes of the period, two interpretations have been suggested and waiting for to be tested: 1) light-time effects due to the unseen 3rd and 4rd bodies (Panchatsaram 1981), 2) Abrupt period-changes, due to internal variations of the system (e.g. mass transfer or mass loss) superimposing to the light-time effect by a 3rd body (Frieboes-Conde & Herczeg 1973). In the point of view that the former interprepation models could predict the behavior of the changes of the orbital period theoretically, we checked whether the recent observed times of minimum lights follow the perdictions by the first model or not. We confirmed that the observed times of minimum lights have followed the variations calculated by the light-times effects due to the 3rd and 4rd bodies suggested by Panchatsatam. In this paper a total of 626 times of minimum lights were reanalyzed in terms of the light-time effects by the 3rd and 4rd bodies. We concluded that the eclipsing pair in SVCam system moves in an elliptic orbit about center of mass of the triple system with a period of about $42.^y2$, while the mass center of the triplet is in light-time orbit about the center of mass of the quadruple system with a period of $120^y$. The mean masses deduced for the 3rd and 4rd bodies were $0.89m_\odot$ and $0.82m_\odot$, respectively.

• The Korean Journal of Applied Statistics
• /
• v.31 no.6
• /
• pp.721-732
• /
• 2018

Latent class analysis (LCA) is an important tool to explore unseen latent groups in multivariate categorical data. In practice, it is important to select a suitable set of variables because the inclusion of too many variables in the model makes the model complicated and reduces the accuracy of the parameter estimates. Dean and Raftery (Annals of the Institute of Statistical Mathematics, 62, 11-35, 2010) proposed a headlong search algorithm based on Bayesian information criteria values to choose meaningful variables for LCA. In this paper, we propose a new variable selection procedure for LCA by utilizing posterior probabilities obtained from each fitted model. We propose a new statistic to measure the adequacy of LCA and develop a variable selection procedure. The effectiveness of the proposed method is also presented through some numerical studies.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.2
• /
• pp.173-179
• /
• 2004

Due to the insufficiency of training data in large vocabulary continuous speech recognition, similar context dependent phones can be clustered by decision trees to share the data. When the decision trees are built and used to predict unseen triphones, a phonetic question set is required. The phonetic question set, which contains categories of the phones with similar co-articulation effects, is usually generated by phonetic or linguistic experts. This knowledge-based approach for generating phonetic question set, however, may reduce the homogeneity of the clusters. Moreover, the experts must adjust the question sets whenever the language or the PLU (phone-like unit) of a recognition system is changed. Therefore, we propose a data-driven method to automatically generate phonetic question set. Since the proposed method generates the phone categories using speech data distribution, it is not dependent on the language or the PLU, and may enhance the homogeneity of the clusters. In large vocabulary speech recognition experiments, the proposed algorithm has been found to reduce the error rate by 14.3%.