• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.25-26
• /
• 2023

본 논문에서는 OpenAI Gym 환경에서 제공하는 CartPole-v1에 대해 강화학습을 통해 에이전트를 학습시키고, 학습에 적용되는 활성화함수의 성능을 비교분석하였다. 본 논문에서 적용한 활성화함수는 Sigmoid, ReLU, ReakyReLU 그리고 softplus 함수이며, 각 활성화함수를 DQN(Deep Q-Networks) 강화학습에 적용했을 때 보상 값을 비교하였다. 실험결과 ReLU 활성화함수를 적용하였을 때의 보상이 가장 높은 것을 알 수 있었다.

• Nuclear Medicine and Molecular Imaging
• /
• v.41 no.3
• /
• pp.263-264
• /
• 2007

Splenic metastasis from colon carcinoma are rare and usually occur in the presence of disseminated visceral metastasis. The liver is the most common site of metastatic spread from colon cancer. Several hypotheses have attempted to explain the low incidence of splenic metastasis. It should be difficult for colorectal cancer cells to reach the spleen through the portal venous system, in which the blood flow is usually from the spleen to the liver. Reticuloendothelial system or rhythmic contraction of the spleen may squeeze out the tumor in the spleen. The absence of afferent lymphatic to the spleen, phagocytic activity and humoral anticancer substances are considered to be other reason for low incidence of splenic metastasis. We report the case of $^{18}F-FDG$ PET/CT finding in a 70-year-old woman who develop isolated splenic metastasis of sigmoid colon cancer.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.7 no.5
• /
• pp.47-60
• /
• 2007

In this paper, we investigate the natural frequencies and buckling loads of functionally graded material (FGM) plates and shells, using a quasi-conforming shell element that accounts for the transverse shear strains and rotary inertia. The eigenvalue of the FGM plates and shells are calculated by varying the volume fraction of the ceramic and metallic constituents using a sigmoid function, but their Poisson's ratios of the FGM plates and shells are assumed to be constant. The expressions of the membrane, bending and shear stiffness of FGM shell element are more complicated combination of material properties than a homogeneous element. In order to validate the finite element numerical solutions, the Navier's solutions of rectangular plates based on the first-order shear deformation theory are presented. The present numerical solutions of composite and sigmoid FGM (S-FGM) plates are proved by the Navier's solutionsand various examples of composite and FGM structures are presented. The present results are in good agreement with the Navier's theoretical solutions.

• Journal of the Korea Computer Industry Society
• /
• v.5 no.1
• /
• pp.9-18
• /
• 2004

Successful project planning relies on a good estimation of the manpower required to complete a project in addition to the schedule options that may be available. Existing software manpower estimation models present the total manpower and instantaneous manpower distribution for the software life cycle. Putnam's Rayleigh and Phillai et al.'s Gamma models present a model with assumption that the manpower is needed at the system delivery. This means that 40 percent of total manpower is applied at the software development, and the other 60% is applied during maintenance phase. However Warburton observes the manpower is needed during development phase with the peak at the completion of the software design phase. So, the existing models were not appropriate to be applied to practical projects. This paper suggests the Sigmoid model which does not consider the point of manpower peak to fix the problem above. The suggested model showed some improvement when practical data was applied. Therefore, the Sigmoid model can be used as alternative of Rayleigh and Gamma model to estimate distribution of manpower during software development phas.

• Journal of Korea Multimedia Society
• /
• v.14 no.9
• /
• pp.1175-1181
• /
• 2011

Practice education using virtual medical simulation has been recently introduced to maximize the learning efficiency in clinical environment. Specially, in minimally invasive surgery, the necessity of virtual surgery medical simulation has been substantially increased. Since cauterizing effect occurred frequently in minimally invasive surgery has been represented by simple bleeding, realistic cauterizing effect animation has not been proposed yet. In this paper, we propose realistic real-time cauterizing effect animation. Proposed method changes the individual element of each vertex color of the mesh and uses sigmoid function to impose weights for the smooth color change inside the valid mesh region so that the results of cauterizing effect animation was realistic. In addition, by proposing cauterizing color buffer, overlapped cauterizing effects can be realistically represented. Proposed method greatly improves the sense of the real and absorption in virtual surgery medical simulation so that the education efficiency of doctors and students using medical simulation can be maximized.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.2
• /
• pp.381-389
• /
• 1996

A simple modification of the standard back-propagation algorithm to eliminate redundant connections(weights and biases) is described. It was motivated by speculations from the distribution of the magnitudes of the weights and the biases, analysis of the classification boundary, and the nonlinearity of the sigmoid function. After initial training, this algorithm eliminates all connections of which magnitude is below a threshold by setting them to zero. The algorithm then conducts retraining in which all weights and biases are adjusted to allow important ones to recover. In studies with Boolean functions, the algorithm reconstructed the theoretical minimum architecture and eliminated the connections which are not necessary to solve the functions. For simulated random signal classification problems, the algorithm produced the result which is consistent with the idea that easier problems require simpler networks and yield lower misclassification rates. Furthermore, in comparison, our algorithm produced better generalization than the standard algorithm by reducing over fitting and pattern memorization problems.

• The Korean Journal of Mycology
• /
• v.22 no.2
• /
• pp.160-171
• /
• 1994

Microscopic observations of arbuscular mycorrhizae (AM) were done with the colonizations of AM and the determinations of chitin in the plant roots of Sorghum bicolor, Cassia mimosoides, Capsicum annuum and Allium fistulosum. The intercellular and intracellular hyphae, arbuscules and vesicles were microscopically observed, according to increases of colonization of AM in the roots of four plants. The growth of AM fungi appeared sigmoid with the cultivation days after inoculation. The growth of AM fungi were inversely influenced by the additions of commercial fertilizers, P

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.10a
• /
• pp.553-559
• /
• 2004

In todays security industry, personal identification is also based on biometric. Biometric identification is performed basing on the measurement and comparison of physiological and behavioral characteristics, Biometric for recognition includes voice dynamics, signature dynamics, hand geometry, fingerprint, iris, etc. Iris can serve as a kind of living passport or living password. Iris recognition system is the one of the most reliable biometrics recognition system. This is applied to client/server system such as the electronic commerce and electronic banking from stand-alone system or networks, ATMs, etc. A new algorithm using nonlinear function in recognition process is proposed in this paper. An algorithm is proposed to determine the localized iris from the iris image received from iris input camera in client. For the first step, the algorithm determines the center of pupil. For the second step, the algorithm determines the outer boundary of the iris and the pupillary boundary. The localized iris area is transform into polar coordinates. After performing three times Wavelet transformation, normalization was done using sigmoid function. The converting binary process performs normalized value of pixel from 0 to 255 to be binary value, and then the converting binary process is compare pairs of two adjacent pixels. The binary code of the iris is transmitted to the by server. the network. In the server, the comparing process compares the binary value of presented iris to the reference value in the University database. Process of recognition or rejection is dependent on the value of Hamming Distance. After matching the binary value of presented iris with the database stored in the server, the result is transmitted to the client.

• Journal of Yeungnam Medical Science
• /
• v.25 no.2
• /
• pp.182-186
• /
• 2008

Ulcerative colitis (UC) is a chronic inflammatory disorder of the gastrointestinal tract that affects the large bowel. Its etiology remains controversial. However, an infectious or immunologic origin is considered the primary cause. The onset of UC is typically slow and insidious, but some patients may present acutely with symptoms mimicking infectious colitis. We report a case of ulcerative colitis mimicking acute hemorrhagic colitis at initial presentation. A 60-year-old man was referred to Yeungnam University Hospital for bloody diarrhea and abdominal pain. Sigmoidoscopy revealed mildly edematous mucosa in the rectum and hyperemic mucosa with petechiae in the sigmoid colon. The patient was treated with antibiotics for several days, and his symptoms improved. However, after one month, his bloody diarrhea relapsed. Follow-up sigmoidoscopy revealed mucosal friability in the rectum and sigmoid colon. He was diagnosed with ulcerative colitis, and his symptoms were improved with mesalazine and a steroid enema.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.2 s.34
• /
• pp.21-30
• /
• 2005

In general, the robust estimation method is well known for a good statistical estimator that is insensitive to small departures from the idealized assumptions for which the estimation is optimized. While there are many existing robust estimation techniques that have been proposed in the literature, two main techniques used in computer vision are M-estimators and least-median of squares (LMS). Among these. we utilized the M-estimators since they are known to provide an optimal estimation of affine motion parameters. The M-estimators have higher statistical efficiency but tolerate much lower percentages of outliers unless properly initialized. To resolve these problems, we proposed an adaptive M-estimators algorithm that effectively separates outliers from non-outliers and estimate affine model parameters, using a continuous sigmoid weight function. The experimental results show the superiority of our method.