• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.9
• /
• pp.407-418
• /
• 2023

The Multi-Object Goal Visual Navigation(MultiOn) is a visual navigation task in which an agent must visit to multiple object goals in an unknown indoor environment in a given order. Existing models for the MultiOn task suffer from the limitation that they cannot utilize an integrated view of multimodal context because use only a unimodal context map. To overcome this limitation, in this paper, we propose a novel deep neural network-based agent model for MultiOn task. The proposed model, MCFMO, uses a multimodal context map, containing visual appearance features, semantic features of environmental objects, and goal object features. Moreover, the proposed model effectively fuses these three heterogeneous features into a global multimodal context map by using a point-wise convolutional neural network module. Lastly, the proposed model adopts an auxiliary task learning module to predict the observation status, goal direction and the goal distance, which can guide to learn the navigational policy efficiently. Conducting various quantitative and qualitative experiments using the Habitat-Matterport3D simulation environment and scene dataset, we demonstrate the superiority of the proposed model.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.6
• /
• pp.783-788
• /
• 2004

Many reported methods assume that the faces in an image or an image sequence have been identified and localization. Face detection from image is a challenging task because of the variability in scale, location, orientation and pose. The difficulties in visual detection and recognition are caused by the variations in viewpoint, viewing distance, illumination. In this paper, we present an efficient linear discriminant for multi-view face detection and face location. We define the training data by using the Fisher`s linear discriminant in an efficient learning method. Face detection is very difficult because it is influenced by the poses of the human face and changes in illumination. This idea can solve the multi-view and scale face detection problems. In this paper, we extract the face using the Fisher`s linear discriminant that has hierarchical models invariant size and background. The purpose of this paper is to classify face and non-face for efficient Fisher`s linear discriminant.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3836-3854
• /
• 2022

The student group division is benefit for universities to do the student management based on the group profile. With the widespread use of student smart cards on campus, especially where students living in campus residence halls, students' daily activities on campus are recorded with information such as smart card swiping time and location. Therefore, it is feasible to depict the students with the daily activity data and accordingly group students based on objective measuring from their campus behavior with some regular student attributions collected in the management system. However, it is challenge in feature representation due to diverse forms of the student data. To effectively and comprehensively represent students' behaviors for further student group division, we proposed to adopt activity data from student smart cards and student attributes as input data with taking account of activity and attribution relationship types from different perspective. Specially, we propose a novel student group division method based on a multi-view student attribute heterogeneous information network (MSA-HIN). The network nodes in our proposed MSA-HIN represent students with their multi-dimensional attribute information. Meanwhile, the edges are constructed to characterize student different relationships, such as co-major, co-occurrence, and co-borrowing books. Based on the MSA-HIN, embedded representations of students are learned and a deep graph cluster algorithm is applied to divide students into groups. Comparative experiments have been done on a real-life campus dataset collected from a university. The experimental results demonstrate that our method can effectively reveal the variability of student attributes and relationships and accordingly achieves the best clustering results for group division.

• The Bulletin of The Korean Astronomical Society
• /
• v.40 no.1
• /
• pp.56.2-56.2
• /
• 2015

The KMTNet Supernovae Project utilizes the large $2^{\circ}{\times}2^{\circ}$ field of view of the three KMTNet telescopes to search and monitor supernovae, especially early ones, and other optical transients. A key component of the project is to build a data pipeline with a descent latency and an early alerting system that can handle the large volume of the data in an efficient and a prompt way, while minimizing false alarms, which casts a significant challenge to the software development. Here we present the current status of their development. The pipeline utilizes a difference image analysis technique to discover candidate transient sources after making correction of image distortion. In the early phase of the program, final selection of transient sources from candidates will mainly rely on multi-filter, multi-epoch and multi-site screening as well as human inspection, and an interactive web-based system is being developed for this purpose. Eventually, machine learning algorithms, based on the training set collected in the early phase, will be used to select true transient sources from candidates.

• Journal of Broadcast Engineering
• /
• v.24 no.4
• /
• pp.573-579
• /
• 2019

To achieve fully autonomous driving, the perceptual skills of the surrounding environment must be superior to those of humans. The $60^{\circ}$ angle, $120^{\circ}$ wide angle cameras, which are used primarily in autonomous driving, have their disadvantages depending on the viewing angle. This paper uses a multi-angle object recognition system to overcome each of the disadvantages of wide and narrow-angle cameras. Also, the aspect ratio of data acquired with wide and narrow-angle cameras was analyzed to modify the SSD(Single Shot Detector) algorithm, and the acquired data was learned to achieve higher performance than when using only monocular cameras.

• The Journal of Information Systems
• /
• v.29 no.3
• /
• pp.145-157
• /
• 2020

Purpose This study proposed an approach for predicting the efficiency rating of the cultural tourism festivals using DEA and machine learning techniques. The cultural tourism festivals are selected for the best festivals through peer reviews by tourism experts. However, only 10% of the festivals which are held in a year could be evaluated in the view of effectiveness without considering the efficiency of festivals. Design/methodology/approach Efficiency scores were derived from the results of DEA for the prediction of efficiency ratings. This study utilized BCC models to reflect the size effect of festivals and classified the festivals into four ratings according the efficiency scores. Multi-classification method were considered to build the prediction of four ratings for the festivals in this study. We utilized neural networks and SVMs with OAO(one-against-one), OAR(one-against-rest), C&S(crammer & singer) with Korea festival data from 2013 to 2018. Findings The number of total visitors in low efficient rating of DEA is more larger than the number of total visitors in high efficient ratings although the total expenditure of visitors is the highest in the most efficient rating when we analyzed the results of DEA for the characteristics of four ratings. SVM with OAO model showed the most superior performance in accuracy as SVM with OAR model was not trained well because of the imbalanced distribution between efficient rating and the other ratings. Our approach could predict the efficiency of festivals which were not included in the review process of culture tourism festivals without rebuilding DEA models each time. This enables us to manage the festivals efficiently with the proposed machine learning models.

• Korean Journal of Agricultural Science
• /
• v.39 no.4
• /
• pp.535-543
• /
• 2012

Botanic gardens are steadily increasing based on people's increased interests in environment and ecology, lengthened leisure hours and improved transportation. However, similar florae and undifferentiated display are considered as problems, while their functions, purposes and characteristics have been more diversified. This study aims to investigate the present conditions and problems of display at botanic gardens and to find out solutions to make them exhibit plants through various ways of display and have their own characteristic, through a case study of seven botanic gardens. As botanic gardens are being recognized as a cultural institution, they should have limitations in the aspect of places that simply collect and exhibit rare plants. The current problems are unclear setting of design goals and communication with visitors. The gardens should escape from the existing supplier-oriented view to a visitor-oriented view, thinking about what the visitors will be able to see and get there. In particular, their display lacks differency, aesthetics, eye-level display, and multi-layered display. In addition to the essential functions of collecting the world's plants, exhibiting them according to purposes and giving scientific learning, botanic gardens should also show a sense of seasons with plants, trigger interests and amusement through unique plants, make visitors more interested in florae and closer to plants, and include social functions. Botanic gardens should be capable of leaning resources display, speciated display, complex and convergent garden-type display, and display fit for local and cultural contexts.

• Journal of Digital Convergence
• /
• v.11 no.12
• /
• pp.295-302
• /
• 2013

Many reported methods assume that the people in an image or an image sequence have been identified and localization. People detection is one of very important variable to affect for the system's performance as the basis technology about the detection of other objects and interacting with people and computers, motion recognition. In this paper, we present an efficient linear discriminant for multi-view people detection. Our approaches are based on linear discriminant. We define training data with fisher Linear discriminant to efficient learning method. People detection is considerably difficult because it will be influenced by poses of people and changes in illumination. This idea can solve the multi-view scale and people detection problem quickly and efficiently, which fits for detecting people automatically. In this paper, we extract people using fisher linear discriminant that is hierarchical models invariant pose and background. We estimation the pose in detected people. The purpose of this paper is to classify people and non-people using fisher linear discriminant.

• The Bulletin of The Korean Astronomical Society
• /
• v.46 no.2
• /
• pp.74.2-75
• /
• 2021

We demonstrate that a deep learning classifier that only uses to gravitational wave (GW) detectors auxiliary channel data can distinguish various types of non-Gaussian noise transients (glitches) with significant accuracy, i.e., ≳ 80%. The classifier is implemented using the multi-scale neural networks (MSNN) with PyTorch. The glitches appearing in the GW strain data have been one of the main obstacles that degrade the sensitivity of the gravitational detectors, consequently hindering the detection and parameterization of the GW signals. Numerous efforts have been devoted to tracking down their origins and to mitigating them. However, there remain many glitches of which origins are not unveiled. We apply the MSNN classifier to the auxiliary channel data corresponding to publicly available GravitySpy glitch samples of LIGO O1 run without using GW strain data. Investigation of the auxiliary channel data of the segments that coincide to the glitches in the GW strain channel is particularly useful for finding the noise sources, because they record physical and environmental conditions and the status of each part of the detector. By only using the auxiliary channel data, this classifier can provide us with the independent view on the data quality and potentially gives us hints to the origins of the glitches, when using the explainable AI technique such as Layer-wise Relevance Propagation or GradCAM.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.34S no.9
• /
• pp.23-30
• /
• 1997

In this paper, a decision feedback recurrent neural equalization (DFRNE) scheme is proposed for adaptive equalization problems. The proposed equalizer models a nonlinear infinite impulse response (IIR) filter. The modified Real-Time recurrent Learning Algorithm (RTRL) is used to train the DFRNE. The DFRNE is applied to both linear channels with only intersymbol interference and nonlinear channels for digital video cassette recording (DVCR) system. And the performance of the DFRNE is compared to those of the conventional equalizaion schemes, such as a linear equalizer, a decision feedback equalizer, and neural equalizers based on multi-layer perceptron (MLP), in view of both bit error rate performance and mean squared error (MSE) convergence. It is shown that the DFRNE with a reasonable size not only gives improvement of compensating for the channel introduced distortions, but also makes the MSE converge fast and stable.