• Journal of Korea Port Economic Association
• /
• v.22 no.1
• /
• pp.175-198
• /
• 2006

This paper presents a network capacity model that can be used as an analytical tool for strategic planning and resource allocation for multimodal transportation systems. In the context of freight transportation, the multimodal network capacity problem (MNCP) is formulated as a mathematical model of nonlinear bi-level optimization problem. Given network configuration and freight demand for multiple origin-destination pairs, the MNCP model is designed to determine the maximum flow that the network can accommodate. To solve the MNCP, a heuristic solution algorithm is developed on the basis of a linear approximation method. A hypothetical exercise shows that the MNCP model and solution algorithm can be successfully implemented and applied to not only estimate the capacity of multimodal network, but also to identify the capacity gaps over all individual facilities in the network, including intermodal facilities. Transportation agencies and planners would benefit from the MNCP model in identifying investment priorities and thus developing sustainable transportation systems in a manner that considers all feasible modes as well as low-cost capacity improvements.

• Proceedings of the KSR Conference
• /
• 2011.10a
• /
• pp.607-613
• /
• 2011

This paper reviews search methods of multiple reasonable paths to implement multimodal public transportation network of Seoul. Such a large scale multimodal public transportation network as Seoul, the computation time of path finding algorithm is a key and the result of path should reflect route choice behavior of public transportation passengers. Search method of alternative path is divided by removing path method and deviation path method. It analyzes previous researches based on the complexity of algorithm for large-scale network. Applying path finding algorithm in public transportation network, transfer and loop constraints must be included to be able to reflect real behavior. It constructs the generalized cost function based on the smart card data to reflect travel behavior of public transportation. To validate the availability of algorithm, experiments conducted with Seoul metropolitan public multimodal transportation network consisted with 22,109 nodes and 215,859 links by using the deviation path method, suitable for large-scale network.

• THE INTERNATIONAL COMMERCE & LAW REVIEW
• /
• v.77
• /
• pp.145-168
• /
• 2018

The purpose of this paper is to introduce the limitation of liabilities of multimodal transport operators(MTO) in Korea. Also, this paper reviews the revised draft of Korean Commercial Code in 2015. This paper analyzes Korean multimodal transport systemand the limitation of liabilities of MTO by analyzing articles, regulations and practices of Korean Commercial Code and it's the draft in 2015. The paper, also, studies multimodal transport rules by comparing specifically international treaty, rules, or practices. In Korea, Article 816 of Commercial Code treats multimodal transportation adopting the network liability regime. The Article describes only the case of the multimodal transportation where the maritime carriage is engaged. Korea proposed the draft of multimodal transport regulation of Commercial Code in 2015 because present law could not apply for the multimodal transportation involved in the air or land carriage. This paper support the draft of Korean Commercial Code in 2015 because it is necessary to make a predictable legal system of multimodal transport and the limitation of liability reflecting practices or customs.

• Journal of Information Processing Systems
• /
• v.16 no.6
• /
• pp.1250-1260
• /
• 2020

This study proposes a novel deep neural network model that can accurately detect objects and their relationships in an image and represent them as a scene graph. The proposed model utilizes several multimodal features, including linguistic features and visual context features, to accurately detect objects and relationships. In addition, in the proposed model, context features are embedded using graph neural networks to depict the dependencies between two related objects in the context feature vector. This study demonstrates the effectiveness of the proposed model through comparative experiments using the Visual Genome benchmark dataset.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.2
• /
• pp.157-163
• /
• 2005

In this paper, we present the multimodal system based on the fusion of two user-friendly biometric modalities: Iris and Face. In order to reach robust identification and verification we are going to combine two different biometric features. we specifically apply 2-D discrete wavelet transform to extract the feature sets of low dimensionality from iris and face. And then to obtain Reduced Joint Feature Vector(RJFV) from these feature sets, Direct Linear Discriminant Analysis (DLDA) is used in our multimodal system. In addition, the Synergetic Neural Network(SNN) is used to obtain matching score of the preprocessed data. This system can operate in two modes: to identify a particular person or to verify a person's claimed identity. Our results for both cases show that the proposed method leads to a reliable person authentication system.

• THE INTERNATIONAL COMMERCE & LAW REVIEW
• /
• v.46
• /
• pp.181-210
• /
• 2010

The continuing advance of multimodal transport with the importance for efficient and effective logistics management emphasizes the need for uniform legal approach to international multimodal transport. However, the current fragmented instrument regulating such transport is being an obstacle to development of multimodal transport as it aggravates confusion and uncertainty. The Rotterdam rules, which was adopted in December 2008 by UNCITRAL, expands its scope of application to door-to-door transport. However, the new rules has some problems in its application to multimodal transport operation as it has been conceived not to regulate general multimodal carriage but to regulate contract of carriage by sea that extends its services to the transport by other modes. This article examines conflict of conventions in the Rotterdam Rules. The applicability of the Rotterdam Rules in international multimodal transport contract and possibility of potential conflict with other transport conventions are analyzed with some hypothetical cases. Furthermore, problems arising from application of the Rotterdam Rules under international multimodal transport Contracts are indicated in the chapter IV.

• THE INTERNATIONAL COMMERCE & LAW REVIEW
• /
• v.16
• /
• pp.155-181
• /
• 2001

International Trade has led to the increase of the demand of international transport, and also the development of international transport not only incurs claims concerning transportation but also establishes various international rules to settle the claims between the shippers and carriers incurred in the course of transport. With a view to settling the claims successfully, the men who are concerned in the transport have to know the principle and scopes of carrier's liability. In this paper, I would like to find out the scopes of liability of multimodal carriers based on the principles of liability. In order to perform the purpose of this study, I classify the liability principle of the international carrier under the UNs Convention on International Multimodal Transport of Good(1980) and UNCTDAD/ICC Rules(1991) in three system-Network Liability System, Uniform Liability System and Modified Liability System. And that I show the results-the scopes of multimodal carriers' liability based on the UN's Multimodal Convention(1980) and the ICC/UNCTAD Rules(1991), and transport vehicles.

• Proceedings of the KSPS conference
• /
• 2007.05a
• /
• pp.41-44
• /
• 2007

In this paper, we introduce a system in which car navigation scenario is plugged multimodal interface based on multimodal middleware. In map-based system, the combination of speech and pen input/output modalities can offer users better expressive power. To be able to achieve multimodal task in car environments, we have chosen SCXML(State Chart XML), a multimodal authoring language of W3C standard, to control modality components as XHTML, VoiceXML and GPS. In Network Manager, GPS signals from navigation software are converted to EMMA meta language, sent to MultiModal Interaction Runtime Framework(MMI). Not only does MMI handles GPS signals and a user's multimodal I/Os but also it combines them with information of device, user preference and reasoned RDF to give the user intelligent or personalized services. The self-simulation test has shown that middleware accomplish a navigational multimodal task over multiple users in car environments.

• Journal of Korea Multimedia Society
• /
• v.20 no.2
• /
• pp.170-178
• /
• 2017

Biometric recognition is one of the major challenging topics which needs high performance of recognition accuracy. Most of existing methods rely on a single source of biometric to achieve recognition. The recognition accuracy in biometrics is affected by the variability of effects, including illumination and appearance variations. In this paper, we propose a new multimodal biometrics recognition using convolutional neural network. We focus on multimodal biometrics from face and periocular regions. Through experiments, we have demonstrated that facial multimodal biometrics features deep learning framework is helpful for achieving high recognition performance.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.637-640
• /
• 2023

This paper presents multimodal image fusion with human pose for detecting abnormal human behaviors in low illumination conditions. Detecting human behaviors in low illumination conditions is challenging due to its limited visibility of the objects of interest in the scene. Multimodal image fusion simultaneously combines visual information in the visible spectrum and thermal radiation information in the long-wave infrared spectrum. We propose an abnormal event detection scheme based on the multimodal fused image and the human poses using the keypoints to characterize the action of the human body. Our method assumes that human behaviors are well correlated to body keypoints such as shoulders, elbows, wrists, hips. In detail, we extracted the human keypoint coordinates from human targets in multimodal fused videos. The coordinate values are used as inputs to train a multilayer perceptron network to classify human behaviors as normal or abnormal. Our experiment demonstrates a significant result on multimodal imaging dataset. The proposed model can capture the complex distribution pattern for both normal and abnormal behaviors.