• 대한전기학회논문지:시스템및제어부문D
• /
• 제52권9호
• /
• pp.533-539
• /
• 2003

Reinforcement learning (RL) has been widely used as a learning mechanism of an artificial life system. However, RL usually suffers from slow convergence to the optimum state-action sequence or a sequence of stimulus-response (SR) behaviors, and may not correctly work in non-Markov processes. In this paper, first, to cope with slow-convergence problem, if some state-action pairs are considered as disturbance for optimum sequence, then they no to be eliminated in long-term memory (LTM), where such disturbances are found by a shortest path-finding algorithm. This process is shown to let the system get an enhanced learning speed. Second, to partly solve a non-Markov problem, if a stimulus is frequently met in a searching-process, then the stimulus will be classified as a sequential percept for a non-Markov hidden state. And thus, a correct behavior for a non-Markov hidden state can be learned as in a Markov environment. To show the validity of our proposed learning technologies, several simulation result j will be illustrated.

• 정보과학회 컴퓨팅의 실제 논문지
• /
• 제22권11호
• /
• pp.614-618
• /
• 2016

인터넷 상 데이터와 스마트 디바이스가 증가함에 따라 순차적으로 유입되는 스트림 형식의 데이터가 늘어나고 있다. 잠재적인 빅데이터인 스트림 데이터를 다루기 위해서는 온라인 학습이 가능해야 한다. 이에 본 고에서는 스트림 데이터 학습을 위한 새로운 모델인 예측적 컨볼루션 신경망과 온라인 학습방법을 제안한다. 이 모델은 탐지와 풀링을 반복하는 컨볼루션 연산을 통해 탐지 패턴을 계층화하여 상위 계층이 될수록 긴 길이의 패턴의 정보를 다루도록 한다. 본 모델의 기초적 검증을 위해 스마트폰으로 2달간 수집한 GPS 데이터를 이산화하여 관측데이터로 삼았다. 이를 제안모델을 통해 학습하여 계층을 따라 추상화된 정보로부터 복원한 데이터와 관측데이터를 비교하여, 긴 시간의 패턴을 다루면서도 관측 수준의 데이터를 복원하는 것을 확인하였다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2022년도 춘계학술발표대회
• /
• pp.517-519
• /
• 2022

In 5G network environment, proactive mobility management is essential as 5G mobile networks provide new services with ultra-low latency through dense deployment of small cells. The importance of a system that actively controls device handover is emerging and it is essential to predict mobile trajectory during handover. Sequence-to-sequence model is a kind of deep learning model where it converts sequences from one domain to sequences in another domain, and mainly used in natural language processing. In this paper, we developed a system for predicting mobile trajectory in a wireless network environment using sequence-to-sequence model. Handover speed can be increased by utilize our sequence-to-sequence model in actual mobile network environment.

• 산업경영시스템학회지
• /
• 제36권4호
• /
• pp.130-137
• /
• 2013

In this paper, we consider a two-agent scheduling with sequence-dependent exponential learning effects consideration, where two agents A and B have to share a single machine for processing their jobs. The objective function for agent A is to minimize the total completion time of jobs for agent A subject to a given upper bound on the objective function of agent B, representing the makespan of jobs for agent B. By assuming that the learning ratios for all jobs are the same, we suggest an enumeration-based backward allocation scheduling for finding an optimal solution and exemplify it by using a small numerical example. This problem has various applications in production systems as well as in operations management.

• 한국전기전자재료학회논문지
• /
• 제16권4호
• /
• pp.351-357
• /
• 2003

An easy learning elevator originated is opened to compare the existed teaming equipment, and it had a high studied efficiency that the sequence control circuit can open and close with the wire. The structure of equipment to be controlled from the first floor to the fifth floors is demostrated by the constructive apparatus with the lamps to express the function of the open-close of the door according to the cage moving with a mechanical actuation of the forward reverse breaker and the motor of load, and the mechanical actuation of hand-operation control components of push-button S/W and L/S and relay etc. These components let connect each other in order to control of the elevator function with the auto program and the designed sequence control circuit. Consequently the cage could go and come till 1∼5 steps with an auto program of the elevator and the sequence control circuit. The sequence control circuit is controlled by the step of forward and reverse to follow as that the sensor function of L/S1 ∼ L/S5 let posit with the control switchs of S/W1 ∼ S/W5 of PLC testing panel and switchs of S/W1 ∼ S/W5 installed on the transparent acryl plate of the frame. In here, improved apparatus is the hand-auto operation combined learning equipment to study the principle and technique of the originate sequence control circuit and the auto program of PLC.

• IEIE Transactions on Smart Processing and Computing
• /
• 제3권5호
• /
• pp.319-324
• /
• 2014

Web applications make life more convenient. Many web applications have several kinds of user input (e.g. personal information, a user's comment of commercial goods, etc.) for the activities. On the other hand, there are a range of vulnerabilities in the input functions of Web applications. Malicious actions can be attempted using the free accessibility of many web applications. Attacks by the exploitation of these input vulnerabilities can be achieved by injecting malicious web code; it enables one to perform a variety of illegal actions, such as SQL Injection Attacks (SQLIAs) and Cross Site Scripting (XSS). These actions come down to theft, replacing personal information, or phishing. The existing solutions use a parser for the code, are limited to fixed and very small patterns, and are difficult to adapt to variations. A machine learning method can give leverage to cover a far broader range of malicious web code and is easy to adapt to variations and changes. Therefore, this paper suggests the adaptable classification of malicious web code by machine learning approaches for detecting the exploitation user inputs. The approach usually identifies the "looks-like malicious" code for real malicious code. More detailed classification using sequence information is also introduced. The precision for the "looks-like malicious code" is 99% and for the precise classification with sequence is 90%.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2002년도 추계학술대회 논문집 Vol.15
• /
• pp.596-602
• /
• 2002

An easy elevator for learning originated is opened to compare the existed learning equipment, and it had a high studying efficient that the sequence control circuit can opens and closes with the wire. The structure of equipment to be controlled from the first floor to the fifth floors is demonstrated a constructive apparatus by a lamp atc to express the function of the open-close of the door according to the cage moving with a mechanical actuation of the forward-reverse breaker and the motor of load and a mechanical actuation of hand-operation control components of push-button S/W and L/S and relay etc. These components let connects each other in order to control of the elevator function with the auto program and the designed sequence control circuit. Consequent1y the process of these functions of 1~5steps could operates the cage with an auto program of the elevator and the sequence control circuit. The sequence control circuit is controlled by the step of forward and reverse to follow as that the sensor function of the L/S1~L/S5 let posit with the control switchs of S/W1~S/W5 of PLC testing panel and switchs of S/W1~S/W5 installed on the transparent acryl plate of the frame. In here, improved apparatus is a hand-auto operation combined learning equipment to study the principle and a technique of the originated sequence control circuit and the auto program of PLC.

• 한국수학교육학회지시리즈A:수학교육
• /
• 제17권2호
• /
• pp.1-13
• /
• 1979

This study aimed at studying the sequence of the Figure Transformation Learning, inquiring relationship among these transformations and then researching whether there is the difference of the learning ability or not between by teaching them as it is independent and by teaching them as it is contains. (Hypothesis 1) It may be more effective to teach The Sequence of Transformation Learning by beginning with peculiar field, ending with general field than vice versa At the result of verification-C $R_{M}$=2.59, 0.005$R_{M}$=5.19, p<0.005-significant difference appeared. It is proved more effective to teach the Figure Transformation Learning the way it contains than the way it is independent. Synthesizing two hypothesises of the above, the conclusion is following The Figure Transformation Learning should be taught by beginning with peculiar field. ending with general field (congruent transformationlongrightarrowsimilar transformationlongrightarrowprojective transformationlongrightarrowtopological transformation). To teach it the way it contains is more effective.ive.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2002년도 하계학술대회 논문집 Vol.3 No.2
• /
• pp.1107-1112
• /
• 2002

An easy elevator originated is an opened system to compare an existing equipment, and learning efficient is high as a wiring that the sequence control circuit is on and off. The structure of an equipment to be controled from the first floor to the fifth floor is constructed by a lamp to express the function of the open-close of the door according to the cage moving, to express the mechanical actuation of the forward-reverse break and motor of load and of hand-worked control component of Push-Button S/W, L/S and Relay. In order to act of the elevator function that these components connected, designed the auto program and the sequence control circuit. Consequently the process that these(1~5steps) operated the cage with an auto program of the elevator and the sequence control circuit is controled by the step of forward and reverse that the L/S1~L/S5 of sensor adjust function let posit, by the adjustable S/W1~S/W5 of PLC testing panel and the S/W1~S/W5 which installed on the transparent acryl plate of a frame. In here, improved apparatus is the learning equipment of combined use to study the principle and the technique of the originated sequence control circuit and the auto program of PLC.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제25권4호
• /
• pp.296-311
• /
• 2021

Topological Data Analysis (TDA), a relatively new field of data analysis, has proved very useful in a variety of applications. The main persistence tool from TDA is persistent homology in which data structure is examined at many scales. Representations of persistent homology include persistence barcodes and persistence diagrams, both of which are not straightforward to reconcile with traditional machine learning algorithms as they are sets of intervals or multisets. The problem of faithfully representing barcodes and persistent diagrams has been pursued along two main avenues: kernel methods and vectorizations. One vectorization is the Betti sequence, or Betti curve, derived from the persistence barcode. While the Betti sequence has been used in classification problems in various applications, to our knowledge, the stability of the sequence has never before been discussed. In this paper we show that the Betti sequence is unstable under the 1-Wasserstein metric with regards to small perturbations in the barcode from which it is calculated. In addition, we propose a novel stabilized version of the Betti sequence based on the Gaussian smoothing seen in the Stable Persistence Bag of Words for persistent homology. We then introduce the normalized cumulative Betti sequence and provide numerical examples that support the main statement of the paper.