• Journal of Information Processing Systems
• /
• v.11 no.3
• /
• pp.370-388
• /
• 2015

The localization of multi-agents, such as people, animals, or robots, is a requirement to accomplish several tasks. Especially in the case of multi-robotic applications, localization is the process for determining the positions of robots and targets in an unknown environment. Many sensors like GPS, lasers, and cameras are utilized in the localization process. However, these sensors produce a large amount of computational resources to process complex algorithms, because the process requires environmental mapping. Currently, combination multi-robots or swarm robots and sensor networks, as mobile sensor nodes have been widely available in indoor and outdoor environments. They allow for a type of efficient global localization that demands a relatively low amount of computational resources and for the independence of specific environmental features. However, the inherent instability in the wireless signal does not allow for it to be directly used for very accurate position estimations and making difficulty associated with conducting the localization processes of swarm robotics system. Furthermore, these swarm systems are usually highly decentralized, which makes it hard to synthesize and access global maps, it can be decrease its flexibility. In this paper, a simple pyramid RAM-based Neural Network architecture is proposed to improve the localization process of mobile sensor nodes in indoor environments. Our approach uses the capabilities of learning and generalization to reduce the effect of incorrect information and increases the accuracy of the agent's position. The results show that by using simple pyramid RAM-base Neural Network approach, produces low computational resources, a fast response for processing every changing in environmental situation and mobile sensor nodes have the ability to finish several tasks especially in localization processes in real time.

• Safety and Health at Work
• /
• v.9 no.3
• /
• pp.265-276
• /
• 2018

Background: Resilience engineering is a paradigm for safety management that focuses on coping with complexity to achieve success, even considering several conflicting goals. Modern sociotechnical systems have to be resilient to comply with the variability of everyday activities, the tight-coupled and under-specified nature of work, and the nonlinear interactions among agents. At organizational level, resilience can be described as a combination of four cornerstones: monitoring, responding, learning, and anticipating. Methods: Starting from these four categories, this article aims at defining a semiquantitative analytic framework to measure organizational resilience in complex sociotechnical systems, combining the resilience analysis grid and the analytic hierarchy process. Results: This article presents an approach for defining resilience abilities of an organization, creating a structured domain-dependent framework to define a resilience profile at different levels of abstraction, and identifying weaknesses and strengths of the system and potential actions to increase system's adaptive capacity. An illustrative example in an anesthesia department clarifies the outcomes of the approach. Conclusion: The outcome of the resilience analysis grid, i.e., a weighed set of probing questions, can be used in different domains, as a support tool in a wider Safety-II oriented managerial action to bring safety management into the core business of the organization.

• Journal of Korea Multimedia Society
• /
• v.3 no.2
• /
• pp.201-208
• /
• 2000

In this paper We describe an algorithm which is devised for 4he partition o# the input space and the generation of fuzzy rules by the fuzzy entropy and tested with the time series prediction problem using Mackey-Glass chaotic time series. This method divides the input space into several fuzzy regions and assigns a degree of each of the generated rules for the partitioned subspaces from the given data using the Shannon function and fuzzy entropy function generating the optimal knowledge base without the irrelevant rules. In this scheme the basic idea of the fuzzy neural network is to realize the fuzzy rules base and the process of reasoning by neural network and to make the corresponding parameters of the fuzzy control rules be adapted by the steepest descent algorithm. The Proposed algorithm has been naturally derived by means of the synergistic combination of the approximative approach and the descriptive approach. Each output of the rule's consequences has expressed with its connection weights in order to minimize the system parameters and reduce its complexities.

• Archives of Craniofacial Surgery
• /
• v.12 no.1
• /
• pp.17-21
• /
• 2011

Purpose: It is difficult to objectively evaluate the outcomes of plastic surgical procedures. The combination of aesthetic and medical factors makes outcome quantification difficult. In this study, fracture reduction accuracy was objectively evaluated in patients with zygomatic complex fractures. Patients satisfaction with the accuracy was also examined. In addition, the patients' overall satisfaction and discomfort due to complications were analyzed. Methods: Eighty-five patients who had surgeries via bicoronal incision for zygomatic complex fracture from March 2006 to December 2009 were included in this study. Two plastic surgeons evaluated the accuracy of the fracture reduction with postoperative computed tomography. A survey questionnaire was administered to evaluate the patients' overall satisfaction and the impact of symptoms associated with the procedure on the patients' daily lives. Results: The overall patient satisfaction rate was $82.1{\pm}10.9%$ (range, 45~100%). The level of deformation was $6.7{\pm}10.9%$, the levels of discomfort in daily life due to pain, paresthesia, scar, and facial palsy were $8.5{\pm}13.2%$, $5.8{\pm}8.9%$, $4.4{\pm}9.9%$, and $1.9{\pm}9.2%$, respectively. According to the visual analogue scale, paresthesia was found to be the most frequent symptom (43.5%), and pain was the most troublesome symptom. Conclusion: The use of bicoronal incision for treating zygomatic complex fractures can cause various complications due to wide incision and dissection. However, this technique can provide optimized reduction and rigid fixation. Most of these postoperative complications can cause significant discomfort in the patient. It is thought that the use of correct surgical technique and the accurate knowledge of craniofacial anatomy will result in a reduction of complications and significantly increase patient satisfaction.

• Atmosphere
• /
• v.31 no.1
• /
• pp.29-43
• /
• 2021

In this study, two-step statistical approach including Principal Component Analysis (PCA) and Multiple Linear Regression (MLR) was employed, and main meteorological factors explaining the high-PM2.5 episodes were identified in two regions: Seoul and Busan. We first performed PCA to isolate the Principal Component (PC) that is linear combination of the meteorological variables observed at two levels: surface and 850 hPa level. The employed variables at surface are: temperature (T2m), wind speed, sea level pressure, south-north and west-east wind component and those at 850 hPa upper level variables are: south-north (v850) and west-east (u850) wind component and vertical stability. Secondly we carried out MLR analysis and verified the relationships between PM2.5 daily mean concentration and meteorological PCs. Our two-step statistical approach revealed that in Seoul, dominant factors for influencing the high PM2.5 days are mainly composed of upper wind characteristics in winter including positive u850 and negative v850, indicating that continental (or Siberian) anticyclone had a strong influence. In Busan, however, the dominant factors in explanaining in high PM2.5 concentrations were associated with high T2m and negative u850 in summer. This is suggesting that marine anticyclone had a considerable effect on Busan's high PM2.5 with high temperature which is relevant to the vigorous photochemical secondary generation. Our results of both differences and similarities between two regions derived from only statistical approaches imply the high-PM2.5 episodes in Korea show their own unique characteristics and seasonality which are mostly explainable by two layer (surface and upper) mesoscale meteorological variables.

• Proceedings of the National Institute of Ecology of the Republic of Korea
• /
• v.3 no.3
• /
• pp.139-148
• /
• 2022

Saxifraga hirculus is classified as a vulnerable plant species in Europe, and it is confined to base-rich flushes in the British uplands. However, a lack of available information about its conservation status hampers the development of adaptive strategies for its in-situ conservation, especially with respect to grazing. To assess the effectiveness of sheep grazing in maintaining viable populations of S. hirculus, we compared the community dynamics of the vegetation in a base-rich flush over 44 years in two plots: one sheep-grazed under business-as-usual sheep grazing densities and the other fenced to exclude grazing. The plots were established in 1972, and the abundances of all vascular plants, bryophytes, and litter were measured at six intervals until 2016. Our results showed that although the presence of S. hirculus was maintained in both plots over the 44 years, it declined and reached a minimum between 1995 and 2010, when it was close to extinction. Since 2013, Saxifraga has recovered only slightly. Interestingly, the S. hirculus response appeared to be independent of grazing treatment, but it mirrored wider changes in the vegetation composition and structure within the flush over the 44 years. These changes are similar to others reported in broader uplands that have been attributed to a combination of reduced nitrogen and sulfur deposition and global warming. Thus, the simple adaptive management approach of "just managing" sheep grazing appeared ineffectual for preserving the S. hirculus population. S. hirculus showed signs of recovery at the end of the study period within this base-rich flush.

• Nuclear Engineering and Technology
• /
• v.54 no.9
• /
• pp.3516-3525
• /
• 2022

The high capture cross-section (𝜎_c) of Gadolinium (Gd-155 and Gd-157) causes reactivity penalty and swing at the initial stage of fuel burnup in Pressurized Water Reactor (PWR). The present study is concerned with the feasibility of the combination of mixed burnable poison with both low and high 𝜎_c as an approach to minimize these effects. Two considered reference designs are fuel assemblies with 24 IBA rods of Gd₂O₃ and Er₂O₃ respectively. Models comprise nuclear fuel with a homogeneous mixture of Er₂O₃, AmO₂, SmO₂, and HfO₂ with Gd₂O₃ as well as the coating of PaO₂ and ZrB₂ on the Gd₂O₃ pellet's outer surface. The infinite multiplication factor was determined and reactivity was calculated considering 3% neutron leakage rate. All models except Er₂O₃ and SmO₂ showed expected results namely higher values of these parameters than the reference design of Gd₂O₃ at the early burnup period. The highest value was found for the model of PaO₂ and Gd₂O₃ followed by ZrB₂ and HfO₂. The cycle burnup, discharge burnup, and cycle length for three batch refueling were calculated using Linear Reactivity Model (LRM). The pin power distribution, energy-dependent neutron flux and Fuel Temperature Coefficient (FTC) were also studied. An optimization of model 1 was carried out to investigate effects of different isotopic compositions of Gd₂O₃ and absorber coating thickness.

• Journal of the Korean Society of Systems Engineering
• /
• v.18 no.2
• /
• pp.75-93
• /
• 2022

Machine learning (ML) data-driven meta-model is proposed as a surrogate model to reduce the excessive computational cost of the physics-based model and facilitate the real-time prediction of a nuclear power plant's transient response. To forecast the transient response three machine learning (ML) meta-models based on recurrent neural networks (RNNs); specifically, Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), and a sequence combination of Convolutional Neural Network (CNN) and LSTM are developed. The chosen accident scenario is a control element assembly withdrawal at power concurrent with the Loss Of Offsite Power (LOOP). The transient response was obtained using the best estimate thermal hydraulics code, MARS-KS, and cross-validated against the Design and control document (DCD). DAKOTA software is loosely coupled with MARS-KS code via a python interface to perform the Best Estimate Plus Uncertainty Quantification (BEPU) analysis and generate a time series database of the system response to train, test and validate the ML meta-models. Key uncertain parameters identified as required by the CASU methodology were propagated using the non-parametric Monte-Carlo (MC) random propagation and Latin Hypercube Sampling technique until a statistically significant database (181 samples) as required by Wilk's fifth order is achieved with 95% probability and 95% confidence level. The three ML RNN models were built and optimized with the help of the Talos tool and demonstrated excellent performance in forecasting the most probable NPP transient response. This research was guided by the Systems Engineering (SE) approach for the systematic and efficient planning and execution of the research.

• Smart Media Journal
• /
• v.12 no.2
• /
• pp.9-14
• /
• 2023

In this paper, we proposed a face recognition network which attempts to use more facial features awhile using smaller number of training sets. When combining the neural network together for face recognition, we want to use networks that use different part of the facial features. However, the network training chooses randomly where these facial features are obtained. Other hand, the judgment basis of the network model can be expressed as a saliency map through gradCAM. Therefore, in this paper, we use gradCAM to visualize where the trained face recognition model has made a observations and recognition judgments. Thus, the network combination can be constructed based on the different facial features used. Using this approach, we trained a network for small face recognition problem. In an simple toy face recognition example, the recognition network used in this paper improves the accuracy by 1.79% and reduces the equal error rate (EER) by 0.01788 compared to the conventional approach.

• International Journal of Computer Science & Network Security
• /
• v.23 no.8
• /
• pp.17-25
• /
• 2023

The alarming global prevalence of Type 2 Diabetes Mellitus (T2DM) has catalyzed an urgent need for robust, early diagnostic methodologies. This study unveils a pioneering approach to predicting T2DM, employing the Extreme Gradient Boosting (XGBoost) algorithm, renowned for its predictive accuracy and computational efficiency. The investigation harnesses a meticulously curated dataset of 4303 samples, extracted from a comprehensive Chinese research study, scrupulously aligned with the World Health Organization's indicators and standards. The dataset encapsulates a multifaceted spectrum of clinical, demographic, and lifestyle attributes. Through an intricate process of hyperparameter optimization, the XGBoost model exhibited an unparalleled best score, elucidating a distinctive combination of parameters such as a learning rate of 0.1, max depth of 3, 150 estimators, and specific colsample strategies. The model's validation accuracy of 0.957, coupled with a sensitivity of 0.9898 and specificity of 0.8897, underlines its robustness in classifying T2DM. A detailed analysis of the confusion matrix further substantiated the model's diagnostic prowess, with an F1-score of 0.9308, illustrating its balanced performance in true positive and negative classifications. The precision and recall metrics provided nuanced insights into the model's ability to minimize false predictions, thereby enhancing its clinical applicability. The research findings not only underline the remarkable efficacy of XGBoost in T2DM prediction but also contribute to the burgeoning field of machine learning applications in personalized healthcare. By elucidating a novel paradigm that accentuates the synergistic integration of multifaceted clinical parameters, this study fosters a promising avenue for precise early detection, risk stratification, and patient-centric intervention in diabetes care. The research serves as a beacon, inspiring further exploration and innovation in leveraging advanced analytical techniques for transformative impacts on predictive diagnostics and chronic disease management.