• Journal of Korea Multimedia Society
• /
• v.22 no.9
• /
• pp.1000-1010
• /
• 2019

Image semantic segmentation and dehazing are key tasks in the computer vision. In recent years, researches in both tasks have achieved substantial improvements in performance with the development of Convolutional Neural Network (CNN). However, most of the previous works for semantic segmentation assume the images are captured in clear weather and show degraded performance under hazy images with low contrast and faded color. Meanwhile, dehazing aims to recover clear image given observed hazy image, which is an ill-posed problem and can be alleviated with additional information about the image. In this work, we propose a deep multi-task network for simultaneous semantic segmentation and dehazing. The proposed network takes single haze image as input and predicts dense semantic segmentation map and clear image. The visual information getting refined during the dehazing process can help the recognition task of semantic segmentation. On the other hand, semantic features obtained during the semantic segmentation process can provide cues for color priors for objects, which can help dehazing process. Experimental results demonstrate the effectiveness of the proposed multi-task approach, showing improved performance compared to the separate networks.

• International Journal of Knowledge Content Development & Technology
• /
• v.9 no.3
• /
• pp.23-41
• /
• 2019

This study combines the concept of degree centrality in complex network with the Term Frequency $^*$ Proportional Document Frequency ($TF^*PDF$) algorithm; the combined method, called PMCN (PDF-Modified similarity and Complex Network), constructs relationship networks among sentences for writing news summaries. The PMCN method is a multi-document summarization extension of the ideas of Bun and Ishizuka (2002), who first published the $TF^*PDF$ algorithm for detecting hot topics. In their $TF^*PDF$ algorithm, Bun and Ishizuka defined the publisher of a news item as its channel. If the PDF weight of a term is higher than the weights of other terms, then the term is hotter than the other terms. However, this study attempts to develop summaries for news items. Because the $TF^*PDF$ algorithm summarizes daily news, PMCN replaces the concept of "channel" with "the date of the news event", and uses the resulting chronicle ordering for a multi-document summarization algorithm, of which the F-measure scores were 0.042 and 0.051 higher than LexRank for the famous d30001t and d30003t tasks, respectively.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.49 no.5
• /
• pp.21-26
• /
• 2012

Intra-session network coding has been proposed to improve throughput by simplifying scheduling of multi-hop wireless network and efficiency of packet transmission. Multi-rate transmission has been used in multihop wireless networks. An opportunistic routing with multirate shows throughput improvement compared with single rate. In this paper, we propose a method of throughput improvement in multi-hop wireless network by using multi-rate and intra-session network coding. We suggest a method to select an local optimal transmission rate at each node. The maximum throughput is evaluated by using linear programming (LP). To solve the LP, we use MATLAB and lp_solve IDE program. The performance evaluation results show that end-to-end throughput is improved by using multirate and intra-session network coding can achieve better throughput than opportunistic routing.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1938-1943
• /
• 2005

Network human-robot interface is an important research topic. In home application, users access the robotic system directly via voice, gestures or through the network. Users explore a system by using the services provided by this system and to some extend users are enable to participate in a service as partners. A service may be provided by a robot, a group of robots or robots and other network connected systems (distributed sensors, information systems, etc). All these services are done in the network environment, where uncertainty such as the unstable network connection, the availability of the partners in a service, exists. Moreover, these services are controlled by several users, accessing at different time by different methods. Our research aimed at solving this problem to provide a high available level, flexible coordination system. In this paper, a multi-agent framework is proposed. This framework is validated by using our new concept of slave agents, a responsive multi-agent environment, a virtual directory facilitator (VDF), and a task allocation system using contract net protocol. Our system uses a mixed model between distributed and centralized model. It uses a centralized agent management system (AMS) to control the overall system. However, the partners and users may be distributed agents connected to the center through agent communication or centralized at the AMS container using the slave agents to represent the physical agents. The system is able to determine the task allocation for a group of robot working as a team to provide a service. A number of experiments have been conducted successfully in our lab environment using Issac robot, a PDA for user agent and a wireless network system, operated under our multi agent framework control. The experiments show that this framework works well and provides some advantages to existing systems.

• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.511-514
• /
• 1998

This paper proposes efficient methods that integrate and execute local plan rules of task agents in a multi-agent environment. In these methods, each agent's plan rules are represented in a network structure, and these networks are then collected by a single task agent to build a integrated domain network, which is exploited to achieve the goal. Agent problem solving by using the domain network enables a concurrent execution of plan rules that are sequential in nature.

• Proceedings of the KAIS Fall Conference
• /
• 2007.05a
• /
• pp.150-153
• /
• 2007

The intent of this paper is to describe a neural network structure called multi dynamic neural network(MDNN), and examine how it can be used in developing a learning scheme for computing robot inverse kinematic transformations. The architecture and learning algorithm of the proposed dynamic neural network structure, the MDNN, are described. Computer simulations are demonstrate the effectiveness of the proposed learning using the MDNN.

• 전기의세계
• /
• v.24 no.4
• /
• pp.80-82
• /
• 1975

This paper presents a synthesis procedure of multi-channel active filters, which realizes an arbitrary N*N matrix of real rational functions in the complex variable s as a voltage transfer matrix. The resultant network reveals a transformerless grounded active RC(2N+1)-terminal network. The active network is consisted of six 2N-port RC networks with 2N single-ended operational amplifiers.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2004.05a
• /
• pp.1-5
• /
• 2004

In this paper, we propose a novel approach for evolving the architecture of a multi-layer neural network. Our method uses combined ART1 algorithm and Max-Min neural network to self-generate nodes in the hidden layer. We have applied the. proposed method to the problem of recognizing ID number in student identity cards. Experimental results with a real database show that the proposed method has better performance than a conventional neural network.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.44 no.10
• /
• pp.127-136
• /
• 2007

It is easy to install and maintain a mobile multi-hop wireless network due to its self-organizing characteristics. However it has security weakness of the authentication of mobile multi-hop relay stations. Specially, the mobile multi-hop relay network in the IEEE 802.16j has the additional security weakness caused by the requirement of backward compatibility for mobile stations of the conventional IEEE 802.16 system. In this paper, we propose a novel mutual authentication scheme applicable to IEEE 802.16j-based mobile multi-hop relay network architecture. The scheme is able to resolve the initial trust gain problem of a multi-hop node at its entry to the network, the problem of rogue mobile multi-hop node and the problem of hop-by-hop authentication between multi-hop nodes. Effectively, the scheme is a hybrid scheme of the distributed authentication method and the centralized authentication method which have been considered to be deployed in the wireless ad-hoc network and the wireless network connected to wired authentication servers, respectively. Also, we analyze the effectiveness of the proposed hybrid authentication method.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.8 no.2
• /
• pp.117-130
• /
• 2012

Due to the development of network and device, it is called mobile age that boosts various distribution routes of multi-media content and it constructs a new digital content consumption trend. N-screen is one of the new-introduced examples in the digital age and broadcasting industry believes it as a crisis and challenge as well. It becomes a ubiquitous multi-media environment that people watch multi-media content everywhere and any time they want to and competition happens beyond the boundaries such as network industry, terminal industry, pay TV market, traditional terrestrial TV, etc. And then how should the broadcasting service prepare for the N-screen business? The present research proposes a few terrestial broadcasting content strategies in the multi platform environment. First, instead of N-screen, it proposes multi platform, especially One Source Multi Platform(OSMP). Second, so-called 'Integrated Terrestrial Broadcasting OSMP Alliance(IBPA)' must be founded. Third, IBPA should support multi-tasking UX for viewers to have rich experience. Last, it becomes more important and necessary to support local terrestrial broadcasting service for public service in the multi platform age.