學術出版;;Publications

Permanent URI for this communityhdl:11536/1

收集所有交通大學研究人員與學生個人或團體所發表之各項學術著作，涵蓋期刊論文、教師專書、學位論文等項。;;Collections of Publications of NCTU Researchers and Students Like Journal Papers and Thesis.

Browse

🏛️國立陽明交通大學機構典藏

Search Results

Now showing 1 - 6 of 6

A fall detection system using k-nearest neighbor classifier
(2010-10-01)
Liu, Chien-Liang
;
Lee, Chia-Hoang
;
Lin, Ping-Min
;
資訊工程學系
;
Department of Computer Science
The main purpose of this paper is to use off-the-shelf devices to develop a fall detection system. In human body identification, human body silhouette is adopted to improve privacy protection, and vertical projection histograms of the silhouette image and statistical scheme are used to reduce the effect of human body upper limb activities. The kNN classification algorithm is used to classify the postures using the ratio and difference of human body silhouette bounding box height and width. Meanwhile, since time difference is a vital factor to differentiate fall incident event and lying down event, the critical time difference is obtained from the experiment and verified by statistical hypothesis testing. With the help of the kNN classifier and the critical time difference, a fall incident detection system is developed to detect fall incident events. The experiment shows that it could reduce the effect of upper limb activities and the system has a correct rate of 84.44% on fall detection and lying down event detection. (C) 2010 Elsevier Ltd. All rights reserved.
WiFi assisted NAT traversal scheme for surveillance patrol robot
(2014-04-01)
Tseng, Chien-Chao
;
Lin, Chia-Liang
;
Shih, Bih-Yaw
;
Chen, Chia-Yen
;
Chen, Chen-Yuan
With the advances in wireless communication technology and artificial intelligence, robots are gradually being introduced as part of our life. Previous research proposed a SIP-enabled Surveillance Patrol Robot (SSPR), which tracks a moving object actively and informs the householder of such security alarm. However, the underlying signaling protocol for communication and data streams suffer from the network address translation (NAT) traversal problem as most peer-to-peer (P2P) applications. NAT is a commonly adopted technique to share one public IPv4 address among several hosts located behind a NAT device for alleviating the exhaustion of IPv4 address. NAT devices typically block session requests originating from outside, prevent the establishment of peer-to-peer (P2P) sessions and cause NAT traversal problem. This study proposes WANTS, a WiFi Assisted NAT Traversal Scheme for SSPR. When SSPR is activated, it retrieves the topology information from a server to choose the candidate access point (AP) for handoff. Then SSPR uses the collected network context information to assist its NAT traversal procedure after handoff. Experimental results confirm that WANTS reduces not only connectivity check delay but also protocol messages as compared to the Interactivity Connectivity Establishment (ICE), which is the most acknowledged approach to creating a session across NATs.
Incentive Learning in Monte Carlo Tree Search
(2013-12-01)
Kao, Kuo-Yuan
;
Wu, I-Chen
;
Yen, Shi-Jim
;
Shan, Yi-Chang
;
資訊工程學系
Monte Carlo tree search (MCTS) is a search paradigm that has been remarkably successful in computer games like Go. It uses Monte Carlo simulation to evaluate the values of nodes in a search tree. The node values are then used to select the actions during subsequent simulations. The performance of MCTS heavily depends on the quality of its default policy, which guides the simulations beyond the search tree. In this paper, we propose an MCTS improvement, called incentive learning, which learns the default policy online. This new default policy learning scheme is based on ideas from combinatorial game theory, and hence is particularly useful when the underlying game is a sum of games. To illustrate the efficiency of incentive learning, we describe a game named Heap-Go and present experimental results on the game.
Modeling and simulation of the open-end equity mutual fund market in Taiwan by using self-organizing map
(2013-08-01)
Chen, Chiu-Chin
;
Chen, An-Pin
;
Yeh, Pei-Yun
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
This research applies artificial intelligence (AI) of unsupervised learning self-organizing map neural network (SOM-NN) to establish a model to select the superior funds. This research period is from year 2000 to 2010 and picks 100 domestic equity mutual funds as study object. This research used 30 days prior to the beginning of each month's prior 30 days, 60 days, 90 days on fund's net asset value and the Taiwan Weighted Stock Index (TAIEX) return as the fund's relative performance evaluation indicators classified by month. Finally, based on the superior rate or the average return rate, this research select the superior funds and simulate investment transactions according to this model. The empirical results show that using the mutual fund's net asset value and the TAIEX's relative return as SOM-NN input variables not only finds out the superior fund but also has a good predictive ability. Applying this model to simulate investment transactions will be better than the random trading model and market. The experiments also found that the investment simulation of a three-month interval has the highest profitability. The model operation suggests that it is more suitable for short-term and medium-term investment. This research can assist investors in making the right investment decisions while facing rapid financial environment changes. (C) 2013 Elsevier B.V. All rights reserved.
Topology-aware handoff scheme for surveillance patrol robot
(2013-08-01)
Tseng, Chien-Chao
;
Lin, Chia-Liang
;
Shih, Bih-Yaw
;
Chen, Chia-Yen
;
Chen, Chen-Yuan
With the advances in wireless communication technology and artificial intelligence, robots are gradually being introduced as a part of our life. Similarly to most mobile devices, mobile robots suffer from handoff latency. This paper proposes TASPR, a Topology-Aware Surveillance Patrol Robot, which can integrate the robotic status and topology information to assist handoff between access points (APs). TASPR uses Topology-Aware Hand-Off Scheme (TAHOS) to find the most promising AP from a list of candidate APs. When TASPR decides to initiate a handoff procedure, it analyzes moving direction, received signal strength and topology information to filter out unnecessary scannings. Thus, TAHOS has less handoff latency compared to conventional handoff procedure and neighbor graph algorithm (NGA).
SIP-enabled Surveillance Patrol Robot
(2013-04-01)
Tseng, Chien-Chao
;
Lin, Chia-Liang
;
Shih, Bih-Yaw
;
Chen, Chen-Yuan
;
資訊工程學系
Robots are gradually being introduced as part of our life. With the advances in computational power and sophisticated sensors, home safety is being ensured with the help of robots. This study proposes SSPR, a SIP-enabled Surveillance Patrol Robot which tracks a moving object actively and informs the householder of security issues for the home environment. Such a robot is equipped with a camera and is aware of session initiation protocol (SIP). When SSPR senses a moving object, it starts tracking and initiates a SIP call to the mobile device of the householder. SIP will establish both audio and video streams between SSPR and the mobile device. Thus, the householder is able to get the whole picture of the home status through his/her mobile device. With the mobility support in SIP, SSPR can switch its wireless link adaptively to another access point (AP) and the audio and video streams will continue after handoff. As a result, SSPR can complement the security routine and make a home smarter and safer. (C) 2012 Elsevier Ltd. All rights reserved.

學術出版;;Publications

Browse

Filters

Settings

Sort By

Results per page

🏛️國立陽明交通大學機構典藏

Search Results