• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권1호
• /
• pp.74-90
• /
• 2014

Routing in mobile wireless sensor networks (MWSNs) is an extremely challenging issue due to the features of MWSNs. In this paper, we present a novel bio-inspired trusted routing protocol (B-iTRP) based on artificial immune system (AIS), ant colony optimization (ACO) and Physarum optimization (PO). For trust mechanism, B-iTRP monitors neighbors' behavior in real time and then assesses neighbors' trusts based on AIS. For routing strategy, each node proactively finds routes to the Sink based on ACO. When a backward ant is on the way to return source, it senses the energy residual and trust value of each node on the discovered route, and calculates the link trust and link energy of the route. Moreover, B-iTRP also assesses the availability of route based on PO to maintain the route table. Simulation results show how B-iTRP can achieve the effective performance compared to existing state-of-the-art algorithms.

• International Journal of Computer Science & Network Security
• /
• 제22권10호
• /
• pp.1-10
• /
• 2022

Nowadays software defect prediction (SDP) is most active research going on in software engineering. Early detection of defects lowers the cost of the software and also improves reliability. Machine learning techniques are widely used to create SDP models based on programming measures. The majority of defect prediction models in the literature have problems with class imbalance and high dimensionality. In this paper, we proposed Centroid and Nearest Neighbor based Class Imbalance Reduction (CNNCIR) technique that considers dataset distribution characteristics to generate symmetry between defective and non-defective records in imbalanced datasets. The proposed approach is compared with SMOTE (Synthetic Minority Oversampling Technique). The high-dimensionality problem is addressed using Ant Colony Optimization (ACO) technique by choosing relevant features. We used nine different classifiers to analyze six open-source software defect datasets from the PROMISE repository and seven performance measures are used to evaluate them. The results of the proposed CNNCIR method with ACO based feature selection reveals that it outperforms SMOTE in the majority of cases.

• International Journal of Computer Science & Network Security
• /
• 제22권10호
• /
• pp.352-358
• /
• 2022

In this paper, we study the relationship between infection rates of covid 19 and the precautionary measures and strict protocols taken by Saudi Arabia to combat the spread of the coronavirus disease and minimize the number of infected people. Based on the infection rates and the timetable of precautionary measures, the best framework of precautionary measures was identified by applying the traveling salesman problem (TSP) that relies on ant colony optimization (ACO) algorithms. The proposed algorithm was applied to daily infected cases data in Saudi Arabia during three periods of precautionary measures: partial curfew, whole curfew, and gatherings penalties. The results showed the partial curfew and the whole curfew for some cities have the minimum total cases over other precautionary measures. The gatherings penalties had no real effect in reducing infected cases as the other two precautionary measures. Therefore, in future similar circumstances, we recommend first applying the partial curfew and the whole curfew for some cities, and not considering the gatherings penalties as an effective precautionary measure. We also recommend re-study the application of the grouping penalty, to identify the reasons behind the lack of its effectiveness in reducing the number of infected cases.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권2호
• /
• pp.438-455
• /
• 2024

Recently, many unsupervised learning-based models have emerged for Just Noticeable Difference (JND) estimation, demonstrating remarkable improvements in accuracy. However, these models suffer from a significant drawback is that their heavy reliance on handcrafted priors for guidance. This restricts the information for estimating JND simply extracted from regions that are highly related to handcrafted priors, while information from the rest of the regions is disregarded, thus limiting the accuracy of JND estimation. To address such issue, on the one hand, we extract the information for estimating JND in an Adversarial Complementary Learning (ACoL) way and propose an ACoL-JND network to estimate the JND by comprehensively considering the handcrafted priors-related regions and non-related regions. On the other hand, to make the handcrafted priors richer, we take two additional priors that are highly related to JND modeling into account, i.e., Patterned Masking (PM) and Contrast Masking (CM). Experimental results demonstrate that our proposed model outperforms the existing JND models and achieves state-of-the-art performance in both subjective viewing tests and objective metrics assessments.

• Journal of Korean Neurosurgical Society
• /
• 제45권1호
• /
• pp.11-15
• /
• 2009

Objective : The aim of study was to review our patient population to determine whether there is a critical aneurysm size at which the incidence of rupture increases and whether there is a correlation between aneurysm size and location. Methods : We reviewed charts and radiological findings (computed tomography (CT) scans, angiograms, CT angiography, magnetic resonance angiography) for all patients operated on for intracranial aneurysms in our hospital between September 2002 and May 2004. Of the 336 aneurysms that were reviewed, measurements were obtained from angiograms for 239 ruptured aneurysms by a neuroradiologist at the time of diagnosis in our hospital. Results : There were 115 male and 221 female patients assessed in this study. The locations of aneurysms were the middle cerebral artery (MCA, 61), anterior communicating artery (ACoA, 66), posterior communicating artery (PCoA, 52), the top of the basilar artery (15), internal carotid artery (ICA) including the cavernous portion (13), anterior choroidal artery (AChA, 7), A1 segment of the anterior cerebral artery (3), A2 segment of the anterior cerebral artery (11), posterior inferior cerebellar artery (PICA, 8), superior cerebellar artery (SCA, 2), P2 segment of the posterior cerebral artery (1), and the vertebral artery (2). The mean diameter of aneurysms was $5.47{\pm}2.536\;mm$ in anterior cerebral artery (ACA), $6.84{\pm}3.941\;mm$ in ICA, $7.09{\pm}3.652\;mm$ in MCA and $6.21{\pm}3.697\;mm$ in vertebrobasilar artery. The ACA aneurysms were smaller than the MCA aneurysms. Aneurysms less than 6 mm in diameter included 37 (60.65%) in patients with aneurysms in the MCA, 43 (65.15%) in patients with aneurysms in the ACoA and 29 (55.76%) in patients with aneurysms in the PCoA. Conclusion : Ruptured aneurysms in the ACA were smaller than those in the MCA. The most prevalent aneurysm size was 3-6 mm in the MCA (55.73%), 3-6 mm in the ACoA (57.57%) and 4-6 mm in the PCoA (42.30%). The more prevalent size of the aneurysm to treat may differ in accordance with the location of the aneurysm.

• 생명과학회지
• /
• 제25권11호
• /
• pp.1223-1229
• /
• 2015

Oryzalin은 미세소관을 분열시키는 dinitroaniline계의 제초제이다. 미세소관과 미세섬유는 평형석 침강과 세포벽을 구성하는 세포골격들이다. 평형석은 뿌리 끝에 있는 columella 세포에서 중력 인지 조절을 한다. 본 연구는 oryzalin이 옥수수 일차 뿌리에서 ethylene 생성을 통하여 굴중성 반응에 미치는 영향을 연구하였다. 뿌리 끝 부분에 10^-4 M oryzalin의 처리는 뿌리 성장과 굴중성 반응을 저해하였으나, 신장대에 처리하게 되면 저해현상은 관찰되지 않았다. 10^-4 M oryzalin을 뿌리 끝에 15시간 처리하면 뿌리 끝의 생장이 억제되고 둥근 형태로 부풀었다. 에틸렌의 전구물질인 ACC를 뿌리 끝에 처리하여도 굴중성 반응이 억제되었다. Oryzalin의 작용과 에틸렌 생성에 대한 관련성을 연구하기 위하여 oryzalin 처리 후 에틸렌 생성을 측정하였다. Oryzalin 처리에 의해 ACC oxidase와 ACC synthase의 활성이 증가되어 에틸렌 생성이 촉진되었다. Oryzalin은 ACO와 ACS의 유전자의 발현도 증가 시켰다. Indole-3-acetic acid (IAA)는 굴중성 반응 동안 관찰되는 비 대칭적 신장에 중요한 역할을 한다. 이러한 연구 결과는 oryzalin이 뿌리 끝에서 IAA transport를 억제하여 뿌리 신장대의 윗면과 아랫면의 IAA 양의 차이를 감소시키고, 또한 에틸렌 생성을 촉진하며 미세소관의 배열을 방해하여 뿌리 글중성과 생장을 억제할 가능성을 제시하고 있다.

• Journal of Korean Neurosurgical Society
• /
• 제60권4호
• /
• pp.424-432
• /
• 2017

Objective : Small unruptured aneurysms (<5 mm) are known for their very low risk of rupture, and are recommended to be treated conservatively. However, we encounter many patients with small ruptured aneurysms in the clinical practice. We aimed to investigate the incidence and characteristics of patients with small ruptured aneurysms. Methods : We reviewed all patients admitted to our hospital with subarachnoid hemorrhage from January 2005 to December 2015. The patients were divided into two groups : those with aneurysms <5 mm (group S) and those with aneurysms ${\geq}5mm$ (group L). The patient's age and sex, size and location of aneurysms, and risk factors such as hypertension, diabetes, alcohol use, and smoking were compared between the two groups. Results : Eight-hundred eleven patients were diagnosed with ruptured aneurysms, and 337 (41.6%) were included in group S. The mean size of all aneurysms was $6.10{\pm}2.99mm$ (range, 0.7-37.7); aneurysms with a diameter of 4-5 mm accounted for the largest subgroup of all aneurysms. Female sex was significantly associated with the incidence of small ruptured aneurysms (odds ratio [OR] 1.50, 95% confidence intervals [CI] 1.02-2.19, p=0.037). Despite female predominance in the incidence of small ruptured aneurysms, the proportion of small ruptured aneurysms in young (<50 years) men was high. In men, there were no significant differences regarding the location of the aneurysms between group S and group L (p=0.267), with the most frequent location being the anterior communicating artery (ACoA) in both group S (50.9%) and group L (51.4%). However, in women, there were significant differences regarding the location of the aneurysms between group S and group L (p=0.023), with the most frequent locations being the ACoA (33.0%) in group S, and the posterior communicating artery (30.6%) in group L. In women, two locations were significantly associated with small (<5 mm) ruptured aneurysms: the ACoA (OR 2.14, 95% CI 1.01-4.54, p=0.047) and anterior cerebral artery (OR 3.54, 95% CI 1.19-10.54, p=0.023). Multiplicity and smoking were significantly associated with large (${\geq}5mm$) ruptured aneurysms in women. The use of alcohol was related to small ruptured aneurysms in men over 50 years of age (OR 2.23, 95% CI 1.03-4.84, p=0.042). Conclusion : In this study, small (<5 mm) ruptured aneurysms exhibited different incidences by age, sex, location, and risk factors such as multiplicity, smoking, and alcohol use.

• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제10권4호
• /
• pp.117-122
• /
• 2021

최근 태풍, 지진, 산불, 산사태, 전쟁 등 다양한 재난 상황으로 인한 인명피해와 자금 손실이 꾸준히 발생하고 있고 현재 이를 예방하고 복구하기 위해 많은 인력과 자금이 소요되고 있는 실정이다. 이러한 여러 재난 상황을 미리 감시하고 재난 발생의 빠른 인지 및 대처를 위해 본 논문에서는 인공지능 기반의 재난 드론 시스템을 설계 및 개발하였다. 본 연구에서는 사람이 감시하기 힘든 지역에 여러 대의 재난 드론을 이용하며 딥러닝 기반의 객체 인식 알고리즘과 최적 경로 탐색 알고리즘을 적용해 각각의 드론이 최적의 경로로 효율적 탐색을 실시한다. 또한 드론의 근본적 문제인 배터리 용량 부족에 대한 문제점을 해결하기 위해 Ant Colony Optimization (ACO) 기술을 이용하여 각 드론의 최적 경로를 결정하게 된다. 제안한 시스템 구현을 위해 여러 재난 상황 중 산불 상황에 적용하였으며 전송된 데이터를 기반으로 산불지도를 만들고, 빔 프로젝터를 탑재한 드론이 출동한 소방관에게 산불지도를 시각적으로 보여주었다. 제안한 시스템에서는 여러 대의 드론이 최적 경로 탐색 및 객체인식을 동시에 수행함으로써 빠른 시간 내에 재난 상황을 인지할 수 있다. 본 연구를 바탕으로 재난 드론 인프라를 구축하고 조난자 탐색(바다, 산, 밀림), 드론을 이용한 자체적인 화재진압, 방범 드론 등에 활용할 수 있다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2007년도 춘계학술대회 학술발표 논문집 제17권 제1호
• /
• pp.241-244
• /
• 2007

본 논문에서는 박테리아의 주화성에 기초한 Bacteria Cooperative Optimization(BCO) 알고리즘을 소개한다. BCO는 Ant Colony Optimization (ACO)처럼 자연계에 존재하는 생명체의 행동양식을 모방하여 만든 최적화 알고리즘으로 크게 초기화, 측정, 행동결정, 이동으로 구성된다. 우리는 먼저 BCO 알고리즘을 설명하고 2차원 함수 최적화 문제를 이용하여 BCO알고리즘과 Genetic Algorithm(GA) 그리고 Bacterial Foraging for Distributed Optimization(BFO)의 성능 측정 결과를 기술한다. 실험 결과 BCO의 성능이 GA나 BFO보다 우수함을 보였다.

• 한국병원경영학회지
• /
• 제spc호
• /
• pp.39-50
• /
• 2016

This paper discusses the strategic concepts applied to integrated delivery system(IDS). IDS is rooted in vertical integration(VI) and strategic alliance(SA), but only few knows about the theoretical backbone of the IDS. The paper explains how VI and SA applies to IDS, then provides cases of IDS rooted in strategic concepts; Kaiser Permanante Model, Mayo Clinic Model, and ACO(Accountable Care Organizations). Finally the paper provides the implication of IDS on Korean healthcare delivery system.