• Title/Summary/Keyword: least-squares problems

Search Result 185, Processing Time 0.019 seconds

Locally adaptive intelligent interpolation for population distribution modeling using pre-classified land cover data and geographically weighted regression (지표피복 데이터와 지리가중회귀모형을 이용한 인구분포 추정에 관한 연구)

  • Kim, Hwahwan
    • Journal of the Korean association of regional geographers
    • /
    • v.22 no.1
    • /
    • pp.251-266
    • /
    • 2016
  • Intelligent interpolation methods such as dasymetric mapping are considered to be the best way to disaggregate zone-based population data by observing and utilizing the internal variation within each source zone. This research reviews the advantages and problems of the dasymetric mapping method, and presents a geographically weighted regression (GWR) based method to take into consideration the spatial heterogeneity of population density - land cover relationship. The locally adaptive intelligent interpolation method is able to make use of readily available ancillary information in the public domain without the need for additional data processing. In the case study, we use the preclassified National Land Cover Dataset 2011 to test the performance of the proposed method (i.e. the GWR-based multi-class dasymetric method) compared to four other popular population estimation methods (i.e. areal weighting interpolation, pycnophylactic interpolation, binary dasymetric method, and globally fitted ordinary least squares (OLS) based multi-class dasymetric method). The GWR-based multi-class dasymetric method outperforms all other methods. It is attributed to the fact that spatial heterogeneity is accounted for in the process of determining density parameters for land cover classes.

  • PDF

An Empirical Study on the Impact of Quality Oriented Corporate Culture on Sustainability Management Performances (공급사슬 내에서 품질지향적 기업문화가 지속가능경영성과에 미치는 영향에 관한 실증연구)

  • Woo, Moo-Jin;Park, Jong-Woo;Jung, Byeong-Yeong
    • Journal of Distribution Science
    • /
    • v.12 no.6
    • /
    • pp.31-39
    • /
    • 2014
  • Purpose - Environmental issues, climatic changes, and greenhouse gases are problems to be solved at a global level. With an increased emphasis on the environmental and social responsibility of the management of companies, the manner in which companies approach quality-oriented culture and their individual sustainability management are being discussed as truly important issues to help them secure their competitiveness and growth strategies. This study proposes strategic directions to help manufacturers not only in expanding their competitive quality-oriented company culture but also in strengthening their sustainability management abilities. This study conducts a literature review and empirical research to examine how significantly the variables of a quality-oriented company culture, customer-centered management, and process-centered and supply chain management-centered cooperation affect sustainability management performance in relation to economic profitability, environmental integrity, and social responsibility. Research design, data, and methodology - To verify research models and hypotheses, the study examined 170 companies using a questionnaire survey conducted over six weeks, and involved the performance of data analysis on 146 samples. Questionnaire responses were calibrated based on a Likert scale. The study used the Smart PLS 2.0 program designed for PLS (partial least squares), an analysis instrument of SEM (structural equation modeling). The study then verified empirical research hypotheses working on reliability analysis, validity analysis, factorial analysis, and path analysis. Results - Among the nine hypotheses, four are accepted and the rest are rejected. A quality-oriented company culture focusing on customer-centered management significantly influenced the maintainability management performance of environmental integrity and social responsibility, while economic profitability was dismissed. A process-focused quality-oriented company culture was significantly concerned with economic profitability but not with environmental integrity or social responsibility. A supply-chain cooperative company culture had a significant effect on economic profitability but not on environmental integrity or social responsibility. Conclusion - This study proposes strategic directions to help manufacturers expand their competitive quality-oriented company culture as well as strengthen abilities with sustainability management. It conducts a literature review and empirical research to examine how significantly the variables of quality-oriented company culture, customer-centered management, and process-centered and supply chain management-centered cooperation affect sustainability management performance in relation to economic profitability, environmental integrity, and social responsibility. There are two main conclusions. First, companies should consider the need for social responsibility management and environmental transparent management-focused maintainability management as avenues to create new markets and business, thereby helping the companies secure a reputation for having a customer and process-centered quality-oriented company culture by creating shared values between supply chains and enabling win-win situations through cooperation. Second, we are marching towards a creative win-win era from a society of conflicts and ruptures. Companies should understand that social responsibility management and supply chain management (SCM)-focused cooperation are the foundations of sustainable development, as they try to improve their culture while pursuing both win-win relationships with interested parties and equity in various conflictive relations.

A Study of Rayleigh Damping Effect on Dynamic Crack Propagation Analysis using MLS Difference Method (MLS 차분법을 활용한 동적 균열전파해석의 Rayleigh 감쇠영향 분석)

  • Kim, Kyeong-Hwan;Lee, Sang-Ho;Yoon, Young-Cheol
    • Journal of the Computational Structural Engineering Institute of Korea
    • /
    • v.29 no.6
    • /
    • pp.583-590
    • /
    • 2016
  • This paper presents a dynamic crack propagation algorithm with Rayleigh damping effect based on the MLS(Moving Least Squares) Difference Method. Dynamic equilibrium equation and constitutive equation are derived by considering Rayliegh damping and governing equations are discretized by the MLS derivative approximation; the proportional damping, which has not been properly treated in the conventional strong formulations, was implemented in both the equilibrium equation and constitutive equation. Dynamic equilibrium equation including time relevant terms is integrated by the Central Difference Method and the discrete equations are simplified by lagging the velocity one step behind. A geometrical feature of crack is modeled by imposing the traction-free condition onto the nodes placed at crack surfaces and the effect of movement and addition of the nodes at every time step due to crack growth is appropriately reflected on the construction of total system. The robustness of the proposed numerical algorithm was proved by simulating single and multiple crack growth problems and the effect of proportional damping on the dynamic crack propagation analysis was effectively demonstrated.

Object Tracking Based on Exactly Reweighted Online Total-Error-Rate Minimization (정확히 재가중되는 온라인 전체 에러율 최소화 기반의 객체 추적)

  • JANG, Se-In;PARK, Choong-Shik
    • Journal of Intelligence and Information Systems
    • /
    • v.25 no.4
    • /
    • pp.53-65
    • /
    • 2019
  • Object tracking is one of important steps to achieve video-based surveillance systems. Object tracking is considered as an essential task similar to object detection and recognition. In order to perform object tracking, various machine learning methods (e.g., least-squares, perceptron and support vector machine) can be applied for different designs of tracking systems. In general, generative methods (e.g., principal component analysis) were utilized due to its simplicity and effectiveness. However, the generative methods were only focused on modeling the target object. Due to this limitation, discriminative methods (e.g., binary classification) were adopted to distinguish the target object and the background. Among the machine learning methods for binary classification, total error rate minimization can be used as one of successful machine learning methods for binary classification. The total error rate minimization can achieve a global minimum due to a quadratic approximation to a step function while other methods (e.g., support vector machine) seek local minima using nonlinear functions (e.g., hinge loss function). Due to this quadratic approximation, the total error rate minimization could obtain appropriate properties in solving optimization problems for binary classification. However, this total error rate minimization was based on a batch mode setting. The batch mode setting can be limited to several applications under offline learning. Due to limited computing resources, offline learning could not handle large scale data sets. Compared to offline learning, online learning can update its solution without storing all training samples in learning process. Due to increment of large scale data sets, online learning becomes one of essential properties for various applications. Since object tracking needs to handle data samples in real time, online learning based total error rate minimization methods are necessary to efficiently address object tracking problems. Due to the need of the online learning, an online learning based total error rate minimization method was developed. However, an approximately reweighted technique was developed. Although the approximation technique is utilized, this online version of the total error rate minimization could achieve good performances in biometric applications. However, this method is assumed that the total error rate minimization can be asymptotically achieved when only the number of training samples is infinite. Although there is the assumption to achieve the total error rate minimization, the approximation issue can continuously accumulate learning errors according to increment of training samples. Due to this reason, the approximated online learning solution can then lead a wrong solution. The wrong solution can make significant errors when it is applied to surveillance systems. In this paper, we propose an exactly reweighted technique to recursively update the solution of the total error rate minimization in online learning manner. Compared to the approximately reweighted online total error rate minimization, an exactly reweighted online total error rate minimization is achieved. The proposed exact online learning method based on the total error rate minimization is then applied to object tracking problems. In our object tracking system, particle filtering is adopted. In particle filtering, our observation model is consisted of both generative and discriminative methods to leverage the advantages between generative and discriminative properties. In our experiments, our proposed object tracking system achieves promising performances on 8 public video sequences over competing object tracking systems. The paired t-test is also reported to evaluate its quality of the results. Our proposed online learning method can be extended under the deep learning architecture which can cover the shallow and deep networks. Moreover, online learning methods, that need the exact reweighting process, can use our proposed reweighting technique. In addition to object tracking, the proposed online learning method can be easily applied to object detection and recognition. Therefore, our proposed methods can contribute to online learning community and object tracking, detection and recognition communities.

The Gains To Bidding Firms' Stock Returns From Merger (기업합병의 성과에 영향을 주는 요인에 대한 실증적 연구)

  • Kim, Yong-Kap
    • Management & Information Systems Review
    • /
    • v.23
    • /
    • pp.41-74
    • /
    • 2007
  • In Korea, corporate merger activities were activated since 1980, and nowadays(particuarly since 1986) the changes in domestic and international economic circumstances have made corporate managers have strong interests in merger. Korea and America have different business environments and it is easily conceivable that there exists many differences in motives, methods, and effects of mergers between the two countries. According to recent studies on takeover bids in America, takeover bids have information effects, tax implications, and co-insurance effects, and the form of payment(cash versus securities), the relative size of target and bidder, the leverage effect, Tobin's q, number of bidders(single versus multiple bidder), the time period (before 1968, 1968-1980, 1981 and later), and the target firm reaction (hostile versus friendly) are important determinants of the magnitude of takeover gains and their distribution between targets and bidders at the announcement of takeover bids. This study examines the theory of takeover bids, the status quo and problems of merger in Korea, and then investigates how the announcement of merger are reflected in common stock returns of bidding firms, finally explores empirically the factors influencing abnormal returns of bidding firms' stock price. The hypotheses of this study are as follows ; Shareholders of bidding firms benefit from mergers. And common stock returns of bidding firms at the announcement of takeover bids, shows significant differences according to the condition of the ratio of target size relative to bidding firm, whether the target being a member of the conglomerate to which bidding firm belongs, whether the target being a listed company, the time period(before 1986, 1986, and later), the number of bidding firm's stock in exchange for a stock of the target, whether the merger being a horizontal and vertical merger or a conglomerate merger, and the ratios of debt to equity capital of target and bidding firm. The data analyzed in this study were drawn from public announcements of proposals to acquire a target firm by means of merger. The sample contains all bidding firms which were listed in the stock market and also engaged in successful mergers in the period 1980 through 1992 for which there are daily stock returns. A merger bid was considered successful if it resulted in a completed merger and the target firm disappeared as a separate entity. The final sample contains 113 acquiring firms. The research hypotheses examined in this study are tested by applying an event-type methodology similar to that described in Dodd and Warner. The ordinary-least-squares coefficients of the market-model regression were estimated over the period t=-135 to t=-16 relative to the date of the proposal's initial announcement, t=0. Daily abnormal common stock returns were calculated for each firm i over the interval t=-15 to t=+15. A daily average abnormal return(AR) for each day t was computed. Average cumulative abnormal returns($CART_{T_1,T_2}$) were also derived by summing the $AR_t's$ over various intervals. The expected values of $AR_t$ and $CART_{T_1,T_2}$ are zero in the absence of abnormal performance. The test statistics of $AR_t$ and $CAR_{T_1,T_2}$ are based on the average standardized abnormal return($ASAR_t$) and the average standardized cumulative abnormal return ($ASCAR_{T_1,T_2}$), respectively. Assuming that the individual abnormal returns are normal and independent across t and across securities, the statistics $Z_t$ and $Z_{T_1,T_2}$ which follow a unit-normal distribution(Dodd and Warner), are used to test the hypotheses that the average standardized abnormal returns and the average cumulative standardized abnormal returns equal zero.

  • PDF