• Economic and Environmental Geology
• /
• v.57 no.3
• /
• pp.329-342
• /
• 2024

The exponential increase in nitrate pollution of river water poses an immediate threat to public health and the environment. This contamination is primarily due to various human activities, which include the overuse of nitrogenous fertilizers in agriculture and the discharge of nitrate-rich industrial effluents into rivers. As a result, the accurate prediction and identification of contaminated areas has become a crucial and challenging task for researchers. To solve these problems, this work leads to the prediction of nitrate contamination using machine learning approaches. This paper presents a novel approach known as Grey Wolf Optimizer (GWO) based on the Stacked Ensemble approach for predicting nitrate pollution in the Cauvery Delta region of Tamilnadu, India. The proposed method is evaluated using a Cauvery River dataset from the Tamilnadu Pollution Control Board. The proposed method shows excellent performance, achieving an accuracy of 93.31%, a precision of 93%, a sensitivity of 97.53%, a specificity of 94.28%, an F1-score of 95.23%, and an ROC score of 95%. These impressive results underline the demonstration of the proposed method in accurately predicting nitrate pollution in river water and ultimately help to make informed decisions to tackle these critical environmental problems.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.7
• /
• pp.55-62
• /
• 2017

Recently, there has been an increasing need for the sharing of microdata containing information regarding an individual entity. As microdata usually contains sensitive information on an individual, releasing it directly for public use may violate existing privacy requirements. Thus, to avoid the privacy problems that occur through the release of microdata for public use, extensive studies have been conducted in the area of privacy-preserving data publishing (PPDP). The k-anonymity algorithm, which is the most popular method, guarantees that, for each record, there are at least k-1 other records included in the released data that have the same values for a set of quasi-identifier attributes. Given an original table, the corresponding k-anonymous table is obtained by generalizing each record in the table into an indistinguishable group, called the equivalent class, by replacing the specific values of the quasi-identifier attributes with more general values. However, query processing over the anonymized data is a very challenging task, due to generalized attribute values. In particular, the problem becomes more challenging with an equi-join query (which is the most common type of query in data analysis tasks) over k-anonymous tables, since with the generalized attribute values, it is hard to determine whether two records can be joinable. Thus, to address this challenge, in this paper, we develop a novel scheme that is able to effectively perform an equi-join between k-anonymous tables. The experiment results show that, through the proposed method, significant gains in accuracy over using a naive scheme can be achieved.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.8
• /
• pp.1148-1157
• /
• 2022

In 2019, COVID-19 changed many people's lives. Among them, metaverse supports non-face-to-face services through various methods, replacing daily tasks. This phenomenon was created and formed like a culture due to the prolonged COVID-19. In this paper, the fun elements used in the existing game were organized to find out the fun factors of the metaverse, and the items and contents were reclassified according to the metaverse with five experts. Classification was classified using reproducibility, sensory fun [graphic, auditory, text, manipulation, empathy, play, perspective], challenging fun [absorbedness, challenging, discovery, thrill, reward, problem-solving], imaginative fun [new story, love, freedom, agency, expectation, change], social fun[rules, competition, social behavior, status, cooperation, participation, exchange, belonging, currency transaction], interactive fun[decision making, communication sharing, hardware, empathy, nurturing, autonomy], realistic fun[sense of unity in reality, easy of learning, adaptation, intellectual problems solving, pattern recognition, sense of reality, community], and creative fun[application, creation, customizing, virtual world].

• Journal of international Conference on Electrical Machines and Systems
• /
• v.3 no.2
• /
• pp.148-154
• /
• 2014

This paper describes problems of the sensorless starting of horizontal axis washing machines with direct drive and suggests solution, which was experimentally verified. Horizontal axis washing machines have very difficult conditions for the drive starting, especially at full load. Inertia of the tub and water, torque from the laundry make load torque at starting higher than rated one and sometimes even higher than the maximum torque of the motor, which makes sensorless starting extremely challenging task. This paper suggests modified open-loop starting, where control system is closed shortly after beginning at low speed and rotates the drum until laundry restructuring. To ensure proper work of the sensorless algorithm at low speed additional measures for increasing of the estimation algorithm performance have been taken. These measures include special algorithm for the drive parameters estimation, which has been developed and verified by the experimental results.

• Journal of the Korean Mathematical Society
• /
• v.38 no.5
• /
• pp.883-914
• /
• 2001

We present a survey of research results obtained for infra-nilmanifolds, their fundamental groups and some of their generalizations. This is presented from two different approaches and covers achievements obtained during the past four decades and showing a remarkable amount of mathematical interdisciplinarity. We go more in depth concerning the existence and construction of polynomial structures for these manifolds and groups, a direction where significant progress was made in the past few years. The bounded-degree polynomial structures developed by the authors triggered a number of challenging open problems. Also, their study already has lead to some interesting results concerning e.g. Anosov diffeomorphisms and expanding maps.

• ETRI Journal
• /
• v.38 no.4
• /
• pp.714-723
• /
• 2016

Considerable attention has been given to processing graph data in recent years. An efficient method for computing the node proximity is one of the most challenging problems for many applications such as recommendation systems and social networks. Regarding large-scale, mutable datasets and user queries, top-k query processing has gained significant interest. This paper presents a novel method to find top-k answers in a node proximity search based on the well-known measure, Personalized PageRank (PPR). First, we introduce a distribution state transition graph (DSTG) to depict iterative steps for solving the PPR equation. Second, we propose a weight distribution model of a DSTG to capture the states of intermediate PPR scores and their distribution. Using a DSTG, we can selectively follow and compare multiple random paths with different lengths to find the most promising nodes. Moreover, we prove that the results of our method are equivalent to the PPR results. Comparative performance studies using two real datasets clearly show that our method is practical and accurate.

• Genomics & Informatics
• /
• v.17 no.4
• /
• pp.44.1-44.3
• /
• 2019

Artificial intelligence (AI), big data, and ubiquitous robotic companions -the three most notable technologies of the 4th Industrial Revolution-are receiving renewed attention each day. Technologies that can be experienced in daily life, such as autonomous navigation, real-time translators, and voice recognition services, are already being commercialized in the field of information technology. In the biosciences field in Korea, such technologies have become known to the local public with the introduction of the AI doctor Watson in large number of hospitals. Additionally, AlphaFold, a technology resembling the AI AlphaGo for the game Go, has surpassed the limit on protein folding predictions-the most challenging problems in the field of protein biology. This report discusses the significance of AI technology and big data on the bioscience field. The introduction of automated robots in this field is not just only for the purpose of convenience but a prerequisite for the real sense of AI and the consequent accumulation of basic scientific knowledge.

• Archives of Reconstructive Microsurgery
• /
• v.5 no.1
• /
• pp.92-98
• /
• 1996

The rectus abdominis myocutaneous flap is frequently used in the field of plastic and reconstructive surgery such as breast reconstruction and as a donor of free tissue transfer. Major problems with this flap is bulkiness, the possibility of postoperative abdominal herniation and muscle weakness following the removal of the rectus abdominis muscle. We used paraumbilical perforator based skin flap fed by a muscle perforator from the deep inferior epigastric artery, with no or little muscle and fatty tissue, in three patients for the resurfacing of relatively wide and thin defects. This technique has all of the advantages of the conventional rectus abdominis myocutaneous flap with decreased possibility of postoperative abdominal herniation or muscle weakness. Another challenging merit is possibility of skin flap thinning.

• International Journal of Concrete Structures and Materials
• /
• v.5 no.2
• /
• pp.97-111
• /
• 2011

Modeling creep of concrete has been one of the most challenging problems in concrete. Over the years, research has proven the significance of creep and its ability to influence structural behavior through loss of prestress, violation of serviceability limit states or stress redistribution. Because of this, interest in modeling and simulation of creep has grown significantly. A research program was planned to investigate the significance of different factors affecting creep of concrete. This research investigation is divided into two folds: first, an in-depth study of the RILEM creep database and development of a homogenous database that can be used for blind computational analysis. Second: developing a probabilistic Bayesian screening method that enables identifying the significance of the different factors affecting creep of concrete. The probabilistic analysis revealed a group of interacting parameters that seem to significantly influence creep of concrete.

• Industrial Engineering and Management Systems
• /
• v.13 no.1
• /
• pp.1-14
• /
• 2014

With a steep increase of the global disaster relief efforts around the world, the relief supply chain and humanitarian logistics play an important role to address this issue. A broad overview of operations research ranges from a principle or conceptual framework to analytical methodology and case study applied in this field. In this paper, we provide an overview of this challenging research area with emphasis on the corresponding optimization problems. The scope of this study begins with classification by the stage of the disaster lifecycle system. The characteristics of each optimization problem for the disaster supply chain are considered in detail as well as the logistics features. We found that the papers related to disaster relief can be grouped in three aspects in terms of logistics attributes: facility location, distribution model, and inventory model. Furthermore, the literature also analyzes objectives and solution algorithms proposed in each optimization model in order to discover insights, research gaps and findings. Finally, we offer future research directions based on our findings from the investigation of literature review.