• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1073-1075
• /
• 1996

This paper presents a neuro fuzzy system(NFS) for implementing fuzzy inference system with a monotonic membership function. The modeling and control of a discrete nonlinear system using a NFS is described. The membership function parameters of a identifier and controller are adjusted by back-propagation algorithm. These identifier and controller is constructed to proposed NFS. A on-line identification and control are accomplished by this NFS. A controller is gived information of the system, that is variation of the system output according to that of the control input by a identifier. A controller makes control input in order to control discrete-time nonlinear system. A Simulation is presented to demonstrate the efficiency of a suggested method.

• Proceedings of the KIEE Conference
• /
• 2004.05a
• /
• pp.59-61
• /
• 2004

Researches about scheduling distributed real-time systems have some weak points, not scheduling both sporadic and periodic tasks and messages or being unable to guaranteeing the end-to-end constraints due to omitting precedence relations between sporadic tasks. This paper describes the application model of sporadic tasks with precedence constraints in a distributed real-time system. It is shown that existing scheduling methods such as Rate Monotonic scheduling are not proper to be applied to the system having sporadic tasks with precedence constraints. So this paper proposes an end-to-end laxity-based priority assignment algorithm which considers the practical laxity of a task and allocates a proper priority to a task.

• Journal of Korea Multimedia Society
• /
• v.25 no.8
• /
• pp.1242-1250
• /
• 2022

When recommending cold items that do not have user-item interactions to users, even we adopt state-of-the-arts algorithms, the predicted information of cold items tends to have lower accuracy compared to warm items which have enough user-item interactions. The lack of information makes for recommender systems to recommend monotonic items which have a few top popular contents matched to user preferences. As a result, under-diversified items have a negative impact on not only recommendation diversity but also on recommendation accuracy when recommending cold items. To address the problem, we adopt a diversification algorithm which tries to make distributions of accumulated contents embedding of the two items groups, recommended items and the items in the target user's already interacted items, similar. Evaluation on a real world data set CiteULike shows that the proposed method improves not only the diversity but also the accuracy of cold item recommendation.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.9
• /
• pp.2007-2012
• /
• 2011

To reduce huge computation in the block matching, this paper proposes a fast block matching algorithm which limits search points in the search area. On the basis of two facts that most motion vectors are located in central part of search area and matching error is monotonic decreasing toward the best similar block, the proposed algorithm moves a matching pattern between steps by the one pixel, predicts the motion direction for the best similar block from similar blocks decided in previous steps, and limits movements of search points to ${\pm}45^{\circ}C$ on it. As a result, it could remove the needless search points and reduce the block matching computation. In comparison with the conventional similar algorithms, the proposed algorithm caused the trivial image degradation in images with fast motion but kept the equivalent image quality in images with normal motion, and it, meanwhile, reduced from about 20% to over 67% of the their block matching computation.

• Journal of KIISE
• /
• v.44 no.2
• /
• pp.115-123
• /
• 2017

A message processor is server software that receives non-realtime messages as well as realtime messages from clients that need to be processed within a deadline. With the recent advances of micro-processor technologies and Linux, the message processor is often implemented in Linux-based multi-core servers and it is important to use cores efficiently to maximize the performance of system in multi-core environments. Numerous research efforts on a real-time scheduler for the efficient utilization of the multi-core environments have been conducted. Typically, though, they have been conducted theoretically or via simulation, making a subsequent real-system application difficult. Moreover, many Linux-based real-time schedulers can only be used in a specific Linux version, or the Linux source code needs to be modified. This paper presents the design of a Linux-based message processor for multi-core environments that maps the threads to the cores at user level. The message processor is implemented through a modification of the traditional RM algorithm that consolidates the real-time messages into certain cores using a first-fit-based bin-packing algorithm; this minimizes the response-time delay of the non-real-time messages, while guaranteeing the violation rate of the real-time messages. To compare the performances, the message processor was implemented using the two multi-core-scheduling algorithms GSN-EDF and P-FP, which are provided by the LITMUS framework. The benchmarking results show that the response-time delay of non-real-time messages in the proposed system was improved up to a maximum of 17% to 18%.

• Journal of KIISE:Databases
• /
• v.33 no.7
• /
• pp.682-692
• /
• 2006

Searching for gene products which have similar biological functions are crucial for bioinformatics. Modern day biological databases provide the functional description of gene products using Gene Ontology(GO). In this paper, we propose a technique for semantic similarity search for gene products using the GO annotation information. For this purpose, an information-theoretic measure for semantic similarity between gene products is defined. And an algorithm for semantic similarity search using this measure is proposed. We adapt Fagin's Threshold Algorithm to process the semantic similarity query as follows. First, we redefine the threshold for our measure. This is because our similarity function is not monotonic. Then cluster-skipping and the access ordering of the inverted index lists are proposed to reduce the number of disk accesses. Experiments with real GO and annotation data show that GORank is efficient and scalable.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.11 no.1
• /
• pp.128-136
• /
• 2003

In today's design trend of vehicle structure, crush zone is fiequently reinforced by adding a box-shaped sub-frame in order to avoid an excessive deformation against a high-speed offset barrier such as EU Directive 96/97 EC, IIHS offset test. That kind of vehicle structure design results in a relatively monotonic crash pulse for airbag ECU(Electronic Control Unit) located at non-crush zone. As for an angular crash event, the measured crash signal using a single-axis accelerometer in a longitudinal direction is usually weaker than that of frontal barrier crash. Therefore, it is not so easy task to achieve a satisfactory crash discrimination performance for offset and angular crash events. In this paper, we introduce a new crash discrimination algorithm using an electronic X-Y 2-axis accelerometer in order to improve crash discrimination performance especially for those crash events. The proposed method uses a crash signal in lateral direction(Y-axis) as well as in longitudinal direction(X-axis). A crash severity measure obtained from Y-axis acceleration is used to improve the discrimination between fire and no-fire events. The result obtained by the proposed measure is logically ORed with an existing algorithm block using X-axis crash signal. Simulation and pulse injection test have been conducted to verify the performance of proposed algorithm by using real crash data of a 2,000cc passenger vehicle.

• Journal of Korea Game Society
• /
• v.7 no.2
• /
• pp.33-40
• /
• 2007

Smoothing is a transmission plan where variable rate video data is converted to a constant bit rate stream. Among them are CBA, MCBA, MVBA and others. However, these smoothing algorithms produce a transmission plan where extra bandwidth in server is not considered. This may cause difficulty in providing videos to many clients in a server. In this paper, we propose the smoothing algorithm with monotonic transmission rate increase and abrupt transmission rate decrease, in order to provide videos to as many clients in server with limited network bandwidth as possible. In order to show the performance of our proposed algorithm, various evaluation factors were used such as the maximum number of clients, the average number of clients, and so on. Experiments demonstrated that the proposed algorithm outperformed other algorithms in evaluation factors such as the maximum number of clients and the average number of clients.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.15 no.3
• /
• pp.231-241
• /
• 2004

This paper drives the exact expression of bit error rate(BER) performance for groupwise iterative-multipath interference cancellation(GWI-MPIC) algorithm for cancelling multipath interference components in a coherent high-speed downlink packet access(HSDPA) system of W-CDMA downlink and the BER performance is evaluated by numerical analysis. The performance of GWI-MPIC is compared to the successive interference cancellation(SIC) algorithm for multipath components. From numerical results, the optimal average BER performance of weighting factor ${\beta}$$\_$h/ for interference cancellation is obtained at ‘${\beta}$$\_$h/=0.8’ and then this weighting factor is hereafter applied to other performance analysis. Numerical results showed that the average BER performance of GWI-MPIC algorithm is rapidly degraded at multipath L=6, but is revealed the good performance than that of SIC algorithm in terms of increasing the number of multipath. This results also indicated that the average BER performance is greatly degraded due to increasing interference power more than multicode K=8. The average BER performance of the proposed algorithm is superior to the performance of SIC algorithm about 3 ㏈ for processing gain PG=128 at multipath L=2 and Average BER=1.0${\times}$10$\^$-5/. And also, the results produced good performance in case of linear monotonic reduction of multipath fading channel gain than that of constant channel gain variation, because multipath fading channel gain which is arrived later is small.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.7
• /
• pp.1705-1720
• /
• 2013

Human face gender recognition requires fast image processing with high accuracy. Existing face gender recognition methods used traditional local features and machine learning methods have shortcomings of low accuracy or slow speed. In this paper, a new framework for face gender recognition to reach fast face gender recognition is proposed, which is based on Local Ternary Pattern (LTP) and Extreme Learning Machine (ELM). LTP is a generalization of Local Binary Pattern (LBP) that is in the presence of monotonic illumination variations on a face image, and has high discriminative power for texture classification. It is also more discriminate and less sensitive to noise in uniform regions. On the other hand, ELM is a new learning algorithm for generalizing single hidden layer feed forward networks without tuning parameters. The main advantages of ELM are the less stringent optimization constraints, faster operations, easy implementation, and usually improved generalization performance. The experimental results on public databases show that, in comparisons with existing algorithms, the proposed method has higher precision and better generalization performance at extremely fast learning speed.