http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : Simon Fong (검색결과 17 건)
- 무료
- 기관 내 무료
- 유료
-
Stream-based Biomedical Classification Algorithms for Analyzing Biosignals
( Simon Fong ),( Yang Hang ),( Sabah Mohammed ),( Jinan Fiaidhi ) 한국정보처리학회 2011 Journal of information processing systems Vol.7 No.4
Classification in biomedical applications is an important task that predicts or classifies an outcome based on a given set of input variables such as diagnostic tests or the symptoms of a patient. Traditionally the classification algorithms would have to digest a stationary set of historical data in order to train up a decision-tree model and the learned model could then be used for testing new samples. However, a new breed of classification called stream-based classification can handle continuous data streams, which are ever evolving, unbound, and unstructured, for instance--biosignal live feeds. These emerging algorithms can potentially be used for real-time classification over biosignal data streams like EEG and ECG, etc. This paper presents a pioneer effort that studies the feasibility of classification algorithms for analyzing biosignals in the forms of infinite data streams. First, a performance comparison is made between traditional and stream-based classification. The results show that accuracy declines intermittently for traditional classification due to the requirement of model re-learning as new data arrives. Second, we show by a simulation that biosignal data streams can be processed with a satisfactory level of performance in terms of accuracy, memory requirement, and speed, by using a collection of stream-mining algorithms called Optimized Very Fast Decision Trees. The algorithms can effectively serve as a corner-stone technology for real-time classification in future biomedical applications.
-
-
Stream-based Biomedical Classification Algorithms for Analyzing Biosignals
Fong, Simon,Hang, Yang,Mohammed, Sabah,Fiaidhi, Jinan Korea Information Processing Society 2011 Journal of information processing systems Vol.7 No.4
Classification in biomedical applications is an important task that predicts or classifies an outcome based on a given set of input variables such as diagnostic tests or the symptoms of a patient. Traditionally the classification algorithms would have to digest a stationary set of historical data in order to train up a decision-tree model and the learned model could then be used for testing new samples. However, a new breed of classification called stream-based classification can handle continuous data streams, which are ever evolving, unbound, and unstructured, for instance--biosignal live feeds. These emerging algorithms can potentially be used for real-time classification over biosignal data streams like EEG and ECG, etc. This paper presents a pioneer effort that studies the feasibility of classification algorithms for analyzing biosignals in the forms of infinite data streams. First, a performance comparison is made between traditional and stream-based classification. The results show that accuracy declines intermittently for traditional classification due to the requirement of model re-learning as new data arrives. Second, we show by a simulation that biosignal data streams can be processed with a satisfactory level of performance in terms of accuracy, memory requirement, and speed, by using a collection of stream-mining algorithms called Optimized Very Fast Decision Trees. The algorithms can effectively serve as a corner-stone technology for real-time classification in future biomedical applications.
-
-
Lam, Simon Ching,Chong, Andy Chun Yin,Chung, Jessie Yuk Seng,Lam, Ming Yee,Chan, Lai Man,Shum, Cho Yee,Wong, Eliza Yi Ni,Mok, Yat Man,Lam, Ming Tat,Chan, Man Man,Tong, Ka Ying,Chu, Oi Lee,Siu, Fong Ki 한국성인간호학회 2020 성인간호학회지 Vol.32 No.1
Purpose: This study aimed to establish the translation adequacy and examine the psychometric properties of FaceMask Use Scale (FMUS). Methods: This methodological study employed a cross-sectional design with repeatedmeasures. Phase 1 examined the equivalence and relevance of English and Chinese versions of FMUS. Phase2 examined the internal consistency, stability and construct validity. Different sample batches (213 universitystudents and 971 general public) were used appropriately for psychometric testing. The 2-phase data were collectedbetween January and April 2017. Results: In Phase 1, the semantic equivalence and relevance (item- and scale-levelcontent-validity-index=100%) was satisfactory. Furthermore, from 133 paired test-retest responses, the quadraticweighted kappa (.53~.73, p<.001) and Intraclass Correlation Coefficient (ICC=.81) between the English andChinese version of FMUS were satisfactory. In Phase 2, FMUS demonstrated satisfactory internal consistency(Cronbach’s ⍺=.80~.81; corrected item-total correlation coefficients=.46~.67) and two-week test-retest stability(ICC=.84). The known-groups method (t=3.08, p<.001), exploratory (71.10% of total variance in two-factor model)and confirmatory factory analysis (x2/df=4.02, Root Mean Square Residual=.03, Root Mean Square Error ofApproximation=.06, Goodness of Fit Index=.99, Comparative Fit Index=.99) were all satisfactory for establishingthe construct validity. Conclusion: The FMUS has an equivalence Chinese and English versions, satisfactoryreliability and validity for measuring the practice of face mask use. This poses clinical and research implications forthose community health nurses who works on respiratory protection. Further research should be conducted on the‘negligent practice’ of FMU.
-
Computing Thresholds of Linguistic Saliency
( Siaw Fong Chung ),( Kathleen Ahrens ),( Chung Ping Cheng ),( Chu Ren Huang ),( Petr Simon ) 한국언어정보학회 2007 학술대회 논문집 Vol.2007 No.-
We propose and test several computational methods to automatically determine possible saliency cut-off points in Sketch Engine (Kilgarriff and Tugwell, 2001). Sketch Engine currently displays collocations in descending importance, as well as according to grammatical relations. However, Sketch Engine does not provide suggestions for a cut-off point such that any items above this cut-off point may be considered significantly salient. This proposal suggests improvement to the present Sketch Engine interface by calculating three different cut-off point methods, so that the presentation of results can be made more meaningful to users. In addition, our findings also contribute to linguistic analyses based on empirical data.
-
Simulation framework of ubiquitous network environments for designing diverse network robots
Cho, Seoungjae,Fong, Simon,Park, Yong Woon,Cho, Kyungeun North-Holland 2017 Future generations computer systems Vol.76 No.-
<P><B>Abstract</B></P> <P>Smart homes provide residents with services that offer convenience using sensor networks and a variety of ubiquitous instruments. Network robots based on such networks can perform direct services for these residents. Information from various ubiquitous instruments and sensors located in smart homes is shared with network robots. These robots effectively help residents in their daily routine by accessing this information. However, the development of network robots in an actual environment requires significant time, space, labor, and money. A network robot that has not been fully developed may cause physical damage in unexpected situations. In this paper, we propose a framework that allows the design and simulation of network robot avatars and a variety of smart homes in a virtual environment to address the above problems. This framework activates a network robot avatar based on information obtained from various sensors mounted in the smart home; these sensors identify the daily routine of the human avatar residing in the smart home. Algorithms that include reinforcement learning and action planning are integrated to enable the network robot avatar to serve the human avatar. Further, this paper develops a network robot simulator to verify whether the network robot functions effectively using the framework.</P> <P><B>Highlights</B></P> <P> <UL> <LI> We proposed a framework to simulate a network robot in a virtual smart home. </LI> <LI> A network robot agent identifies daily routines of a resident and executes service. </LI> <LI> The framework shows a network robot could help and reduce tasks of a human agent. </LI> <LI> The simulator verified the framework reduces costs of developing network robots. </LI> </UL> </P>
-
Cheong, Chi Po,Fong, Simon,Lei, Pouwan,Chatwin, Chris,Young, Rupert Korea Information Processing Society 2012 Journal of information processing systems Vol.8 No.3
A secure Electronic Payment System (EPS) is essential for the booming online shopping market. A successful EPS supports the transfer of electronic money and sensitive information with security, accuracy, and integrity between the seller and buyer over the Internet. SET, CyberCash, Paypal, and iKP are the most popular Credit Card-Based EPSs (CCBEPSs). Some CCBEPSs only use SSL to provide a secure communication channel. Hence, they only prevent "Man in the Middle" fraud but do not protect the sensitive cardholder information such as the credit card number from being passed onto the merchant, who may be unscrupulous. Other CCBEPSs use complex mechanisms such as cryptography, certificate authorities, etc. to fulfill the security schemes. However, factors such as ease of use for the cardholder and the implementation costs for each party are frequently overlooked. In this paper, we propose a Web service based new payment system, based on ANSI X9.59-2006 with extra features added on top of this standard. X9.59 is an Account Based Digital Signature (ABDS) and consumer-oriented payment system. It utilizes the existing financial network and financial messages to complete the payment process. However, there are a number of limitations in this standard. This research provides a solution to solve the limitations of X9.59 by adding a merchant authentication feature during the payment cycle without any addenda records to be added in the existing financial messages. We have conducted performance testing on the proposed system via a comparison with SET and X9.59 using simulation to analyze their levels of performance and security.
-
-
Pointwise CNN for 3D Object Classification on Point Cloud
( Wei Song ),( Zishu Liu ),( Yifei Tian ),( Simon Fong ) 한국정보처리학회 2021 Journal of information processing systems Vol.17 No.4
Three-dimensional (3D) object classification tasks using point clouds are widely used in 3D modeling, face recognition, and robotic missions. However, processing raw point clouds directly is problematic for a traditional convolutional network due to the irregular data format of point clouds. This paper proposes a pointwise convolution neural network (CNN) structure that can process point cloud data directly without preprocessing. First, a 2D convolutional layer is introduced to percept coordinate information of each point. Then, multiple 2D convolutional layers and a global max pooling layer are applied to extract global features. Finally, based on the extracted features, fully connected layers predict the class labels of objects. We evaluated the proposed pointwise CNN structure on the ModelNet10 dataset. The proposed structure obtained higher accuracy compared to the existing methods. Experiments using the ModelNet10 dataset also prove that the difference in the point number of point clouds does not significantly influence on the proposed pointwise CNN structure.
KCI
KISS연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
