A Simple Stable Method in Real-time Lane Tracking of Broken Lanes

Sudan Xu(쉬수단),Yaohuan Cui(최요환),Kwon Kim(김권),Chang Woo Lee(이창우) 한국정보과학회 2007 한국정보과학회 학술발표논문집 Vol.34 No.2A

Lane detection is one of the major components of traffic intelligence. It is impossible to recognize lanes as human do in all kinds of special situations; however, we can try to solve special problems with special methods. In this paper we propose a simple method using color segmentation, the Probabilistic Hough Transform (PHT), and the Least-Square in real-time lane tracking. Vehicles in neighborhood can be eliminated with one simple threshold in segmentation. Meanwhile, broken shape lanes in different road conditions can be successfully detected using the combination of PHT and Least-Square method. Eventually, this method is tested with groups of static images downloaded from internet and video sequences shot randomly on some highways. Satisfactory results are received.

Financial leverage and performance of Nepalese commercial banks

Sudan Kumar Oli 아시아사회과학학회 2021 Jornal of Asia Social Science Vol.2 No.3

This study examines the determinants of return on assets, net profit margin, and earnings per share in Nepalese commercial banks to examine the performance proxy of commercial banks by using the secondary sources of data that are collected from the 20 Nepalese commercial banks through 2011/12 to 2016/17. The OLS regression models are estimated to test the significance and importance of leverage on the bank’s performance. The study reveals that debt to assets ratio, long term debt ratio, debt to equity ratio, interest coverage ratio, and liquidity ratio have a positive relationship with return on assets, net profit margin, and earning per share but the board size and Tobin’s q have a negative relationship with return on assets. Likewise, the debt to assets ratio, debt to equity ratio, interest coverage ratio, and board size have a positive relationship with net profit margin and earnings per share. However, long-term debt ratio, debt to equity ratio, bank size, and Tobin s q have a negative impact on net profit margin and earnings per share. The study also shows that the most influencing factor for determining return on assets is the interest coverage ratio followed by the debt to assets ratio, debt to equity ratio, and liquidity.

An “Energy Aware” routing protocol for pre-detection and its prevention of Fault Tolerance for WSN

Sudan Jha 한국디지털융합학회 2018 IJICTDC Vol.3 No.1

Energy has been a major concern in almost all networks, especially the consumption and optimized utilization of energy. Lots of work has been experimented and proposed in the past with relevant evidences for fault detection too. However, researchers have yet to find the absolute solution to routing protocol for pre - “fault tolerance and prevention” using energy efficient awareness. In this paper, we have designed a protocol, if in case of failure which selects succeeding node in energy efficient manner; and if in case of its failure, sensitively restores the connectivity of the neighbors of a cluster around that node.

정보시스템 인력의 선발 및 평가를 위한 퍼지 ART 접근방법

수단프라사드우프리티 ( Sudan Prasad Uprety ),정승렬 ( Seung Ryul Jeong ) 한국인터넷정보학회 2013 인터넷정보학회논문지 Vol.14 No.6

국제적 경쟁이 치열해지고 급속한 기술발전이 진행되고 있는 기업환경에서 좋은 정보시스템 인력을 선발하고 평가할 수 있는 방법은 매우 중요한 이슈이다. 그럼에도 불구하고 정보시스템 인력이 보유해야 할 지식과 스킬에 대해서는 많은 연구가 진행되었지만 이들 인력을 선발하고 평가하는 방법에 대해서는 그렇지 못한 것이 사실이다. 인력 선발은 정성적인 측정치와 정략적인 측정치 모두를 포함하는 다기준 의사결정 문제인데 본 연구에서는 정보시스템 인력의 스킬, 능력, 지식에 기초하여 이들의 선발과 평가 과정에서 이들을 분류할 수 있는 모형을 제시하였다. 본 모형은 신경망 알고리즘 모형에서 도출한 것으로서 Jaccard 선택함수 기반의 퍼지ART 알고리즘을 적용하였다. 실제 인사자료를 활용하여 제안된 모형의 사용 용이성과 효과성을 검정해 본 결과 본 접근방법이 필드에서 충분히 활용될 수 있는 것으로 판단되었다. Due to increasing competition of globalization and fast technological improvements the appropriate method for evaluating and selecting IS-personnel is one of the key factors for an organization`s success. Personnel selection is a multi-criteria decision-making (MCDM) problem which consists of both qualitative and quantitative metrics. Although many articles have discussed various knowledge and skills IS personnel should possess, no specific model for IS personnel selection and evaluation, to our knowledge, has been published up to now. After reviewing the IS personnel`s important characteristics, we propose an approach for categorizing the IS personnel based on their skills, ability, and knowledge during evaluation and selection process. Our proposed approach is derived from a model of neural network algorithm. We have adapted and implemented the fuzzy ART algorithm with Jaccard choice function. The result of an illustrative numerical example is proposed to demonstrate the easiness and effectiveness of our approach.

청정환기장치 최적제어를 위한 IoT 기반 실시간 공기질 모니터링 플랫폼 구현

수던프라사드우프레티 ( Sudan Prasad Uprety ),김유신 ( Yoosin Kim ) 한국인터넷정보학회 2020 인터넷정보학회논문지 Vol.21 No.6

본 연구는 사물인터넷(IoT) 센서를 이용해 실내공기질에 주요한 영향을 미치는 미세먼지, 초미세먼지, 이산화탄소, 유기화학물과 온도, 습도 데이터를 실시간으로 수집/분석할 수 있는 실시간 실내공기질 모니터링 서비스를 클라우드 플랫폼으로 구현하였다. 이를 실내공기 정화시설인 청정환기장치와 연동하여 실시간 실내공기질 상태에 따라 환기장치 최적관리할 수 있도록 하였다. 본 플랫폼은 청정환기장치 내외부에 장착된 실내공기질 측정 센서로부터 실시간으로 데이터를 수집하는 IoT 데이터 수집부, 수집된 데이터를 클라우드 환경에서 가공/처리/적재하는 클라우드 데이터 처리부, 적재된 빅데이터를 분석하고 공기질 현황을 웹과 모바일에 시각화하여 보여주는 데이터 분석 서비스부로 구성된다. 그리고 이러한 플랫폼의 가동과 효과를 검증하기 위해 공기질에 민감한 영유아의 교육 생활환경인 국공립 어린이집 교실을 대상으로 실증을 실시하였다. 모든 분석 결과는 웹과 모바일에서 실시간으로 시각화 서비스될 수 있도록 실증 구현하였고, 환기장치의 실내공기질 개선효과는 실내공기질 측정 센서들의 측정값을 통계적으로 검증하여 공기질 개선에 기여하고 있음을 확인하였다. In this paper, we propose the real time indoor air quality monitoring and controlling platform on cloud using IoT sensor data such as PM10, PM2.5, CO2, VOCs, temperature, and humidity which has direct or indirect impact to indoor air quality. The system is connected to air ventilator to manage and optimize the indoor air quality. The proposed system has three main parts; First, IoT data collection service to measure, and collect indoor air quality in real time from IoT sensor network, Second, Big data processing pipeline to process and store the collected data on cloud platform and Finally, Big data analysis and visualization service to give real time insight of indoor air quality on mobile and web application. For the implication of the proposed system, IoT sensor kits are installed on three different public day care center where the indoor pollution can cause serious impact to the health and education of growing kids. Analyzed results are visualized on mobile and web application. The impact of ventilation system to indoor air quality is tested statistically and the result shows the proper optimization of indoor air quality.

An Efficient Method for Real-Time Broken Lane Tracking Using PHT and Least-Square Method

쉬수단(Sudan Xu),이창우(Chang Woo Lee) 한국정보과학회 2008 정보과학회 컴퓨팅의 실제 논문지 Vol.14 No.6

차선검출시스템은 지능형 차량 시스템의 중요한 요소이다. 차선검출 시, 주변 환경과 날씨의 변화 때문에 차선검출은 다양한 어려움에 직면하게 된다. 본 논문에서는 차선검출 및 추적을 위해 다양한 환경에서도 안정적으로 동작하는 간단하면서 효율적인 방법을 제안한다. 제안된 방법에서는 차선을 추적하고 차선의 기울기를 수정하기 위해 확률적 허프 변환(Probabilistic Hough Transform, PHT)과 최소자승법(Least-square method, LSM)를 이용한다. 일반적으로 차량의 내부에 설치된 카메라로부터 획득된 영상은 영상의 하단부분에서 차선이 비교적 뚜렷이 나타나고, 주변의 간섭을 적게 받는다는 가정 하에 제안된 방법에서는 차선검출 및 추적의 효율성을 증대시키기 위해 영상의 하단부분에 관심의 대상이 되는 두 개의 영역을 설정한다. 제안된 방법의 효율성을 입증하기 위해 정지영상과 비디오 영상을 사용하여 실험 하였고, 실험결과 제안된 방법이 강건하고, 신뢰성있는 결과를 얻었음을 보였다. A lane detection system is one of the major components of intelligent vehicle systems. Difficulties Difficulties in lane detection mainly come from not only various weather conditions but also a variety of special environment. This paper describes a simple and stable method for the broken lane tracking in various environments. Probabilistic Hough Transform (PHT) and the Least-square method (LSM) are used to track and correct the lane orientation. For the efficiency of the proposed method, two regions of interest (ROIs) are placed in the lower part of each image, where lane marking areas usually appear with less intervention in our system view. By testing in both a set of static images and video sequences, the experiments showed that the proposed approach yielded robust and reliable results.

Cyber Threat Analysis and Prediction Using Machine Learning

Subhalaxmi Sahoo,Sudan Jha 한국디지털융합학회 2021 디지털경영연구 Vol.8 No.1

With the increase in cyber data attacks, the manual method of investigating cyber-attacks is more prone to errors and is time consuming. With the increase in advanced cyber threat attacks with the same patterns, timely investigation is not possible. There are many systems proposed which analyse and predict threats using various machine learning methods. In this various models apply machine learning algorithms to analyse and predict cyber-attacks.

No Association between the CCR5Δ32 Polymorphism and Sporadic Esophageal Cancer in Punjab, North-West India

Sambyal, Vasudha,Manjari, Mridu,Sudan, Meena,Uppal, Manjit Singh,Singh, Neeti Rajan,Singh, Harpreet,Guleria, Kamlesh Asian Pacific Journal of Cancer Prevention 2015 Asian Pacific journal of cancer prevention Vol.16 No.10

Background: Chemokines and their receptors influence carcinogenesis and cysteine-cysteine chemokine receptor 5 (CCR5) directs spread of cancer to other tissues. A 32 base pair deletion in the coding region of CCR5 that might alter the expression or function of the protein has been implicated in a variety of immune-mediated diseases. The action of antiviral drugs being proposed as adjuvant therapy in cancer is dependent on CCR5 wild type status. In the present study, distribution of CCR5${\Delta}32$ polymorphism was assessed in North Indian esophageal cancer patients to explore the potential of using chemokine receptors antagonists as adjuvant therapy. Materials and Methods: DNA samples of 175 sporadic esophageal cancer patients (69 males and 106 females) and 175 unrelated healthy control individuals (69 males and 106 females) were screened for the CCR5${\Delta}32$ polymorphism by direct polymerase chain reaction (PCR). Results: The frequencies of wild type homozygous (CCR5/CCR5), heterozygous (CCR5/${\Delta}32$) and homozygous mutant (${\Delta}32/{\Delta}32$) genotypes were 96.0 vs 97.72%, 4.0 vs 1.71% and 0 vs 0.57% in patients and controls respectively. There was no difference in the genotype and allele frequencies of CCR5${\Delta}32$ polymorphism in esophageal cancer patients and control group. Conclusions: The CCR5${\Delta}32$ polymorphism is not associated with esophageal cancer in North Indians. As the majority of patients express the wild type allele, there is potential of using antiviral drug therapy as adjuvant therapy.

Association of +405C>G and +936C>T Polymorphisms of the Vascular Endothelial Growth Factor Gene with Sporadic Breast Cancer in North Indians

Kapahi, Ruhi,Manjari, Mridu,Sudan, Meena,Uppal, Manjit Singh,Singh, Neeti Rajan,Sambyal, Vasudha,Guleria, Kamlesh Asian Pacific Journal of Cancer Prevention 2014 Asian Pacific journal of cancer prevention Vol.15 No.1

Background: Vascular endothelial growth factor (VEGF), an endothelial cell specific mitogen, has been implicated as a critical factor influencing tumor related angiogenesis. The aim of present study was to evaluate the relationship between VEGF +936C>T and +405C>G polymorphisms of VEGF with risk of breast cancer in Punjab, India. Materials and Methods: We screened DNA samples of 192 sporadic breast cancer patients and 192 unrelated healthy, gender and age matched control individuals for VEGF +936C>T and +405C>G polymorphisms using the PCR-RFLP method. Results: For the VEGF +405C>G polymorphism, we observed significantly increased frequency of GG genotype in cases as compared to controls and strong association of +405GG genotype was observed with three fold risk for breast cancer (OR=3.07; 95%CI 1.41-6.65; p=0.003). For the +936C>T polymorphism, significant associations of CT and combined CT+TT genotypes were observed with elevated risk of breast cancer (p=0.021; 0.023). The combined genotype combinations of GG-CC and GG-CT of +405C>G and +936C>T polymorphisms were found to be significantly associated with increased risk of breast cancer (p=0.04; 0.0064). Conclusions: The findings of the present study indicated significant associations of VEGF +936C>T and +405C>G polymorphisms with increased breast cancer risk in patients from Punjab, North India.

암반터널에서의 변위파악을 위한 암반 탄성계수 추정

손무락(Son Moorak),이소단(Li Sudan),이원기(Lee Wonki) 대한토목학회 2011 대한토목학회논문집 C Vol.31 No.2

암반에서의 탄성계수는 암반의 변형특성을 나타내는 매우 중요한 인자로서 암반에서의 터널굴착으로 인한 내공변위를 파악하는데 이용된다. 그럼에도 불구하고 현재까지는 암석종류 및 절리특성을 반영하여 탄성계수를 산정하는 연구는 미흡한 것으로 판단된다. 따라서, 본 연구는 다양한 암석 및 절리상태에서 암반의 탄성계수를 추정하는 방법과 그 결과를 제시하고자 한다. 이를 위해서 2차원 개별요소법에 근거한 수치해석이 수행될 것이며 이를 통해 암석과 절리상태가 고려된 터널굴착 유발 내공변위가 조사될 것이다. 조사된 변위결과는 암반에서의 원형터널에 대한 탄성이론을 역이용하여 암석종류 및 절리특성이 반영된 탄성계수를 추정하는데 사용될 것이다. 본 연구를 통해 암석종류 및 절리특성을 고려하여 추정된 탄성계수는 향후 실무에서 절리가 형성된 암반터널에서의 발생변위를 파악함에 있어서 그 활용도가 매우 클 것으로 기대된다. Elastic modulus in rockmass is an important factor to represent the characteristic of rock deformation and is used to estimate the displacement due to tunnel excavation. Nevertheless, the study to estimate the elastic modulus, which condisiders the rock type and joint characteristics (joint shear strength and joint inclination angle), has been done in less frequency. Accordingly, this study is aimed at providing the method to estimate the elastic modulus of rockmass in the various rock and joint conditons and the results grasped from the study. For this purpose, the 2D discrete numerical analysis will be carried out and the displacements due to tunnel excavation will be investigated with the consideration of rock and joint conditions. Then the displacement results will be used to estimate the elastic modulus of rockmass in which rock and joint conditions are considered with the utilization of the elastic theory of circular tunnel. The results of elastic modulus, which considers the conditions of various rock and joint, would be expected to have a great practical use in field.