• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.421-436
• /
• 2023

This paper presents a vibration displacement measurement and damage identification method for a space truss structure from its vibration videos. Features from Accelerated Segment Test (FAST) algorithm is combined with adaptive threshold strategy to detect the feature points of high quality within the Region of Interest (ROI), around each node of the truss structure. Then these points are tracked by Kanade-Lucas-Tomasi (KLT) algorithm along the video frame sequences to obtain the vibration displacement time histories. For some cases with the image plane not parallel to the truss structural plane, the scale factors cannot be applied directly. Therefore, these videos are processed with homography transformation. After scale factor adaptation, tracking results are expressed in physical units and compared with ground truth data. The main operational frequencies and the corresponding mode shapes are identified by using Subspace Stochastic Identification (SSI) from the obtained vibration displacement responses and compared with ground truth data. Structural damages are quantified by elemental stiffness reductions. A Bayesian inference-based objective function is constructed based on natural frequencies to identify the damage by model updating. The Success-History based Adaptive Differential Evolution with Linear Population Size Reduction (L-SHADE) is applied to minimise the objective function by tuning the damage parameter of each element. The locations and severities of damage in each case are then identified. The accuracy and effectiveness are verified by comparison of the identified results with the ground truth data.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.4
• /
• pp.127-135
• /
• 2023

Nowadays, the number of patients committing suicide due to depression and stress is rapidly increasing. In addition, if stress and depression last for a long time, they are dangerous factors that can cause heart disease, brain disease, and high blood pressure. However, no matter how modern medicine has developed, it is a very difficult situation for patients with depression and heart disease without special drugs or treatments. Therefore, in many countries around the world, studies are being actively conducted to determine patients at risk of depression and patients at risk of suicide at an early stage using electrocardiogram, oxygen saturation, and brain wave analysis functions. In this paper, in order to analyze these problems, a computer simulation was performed to determine heart disease risk patients by establishing heart disease hypothesis data. In particular, in order to improve the predictive rate of heart disease by more than 10%, a simulation using fuzzy inference was performed.

• Mycobiology
• /
• v.51 no.3
• /
• pp.139-147
• /
• 2023

Aspergillus sojae has long been considered a domesticated strain of Aspergillus parasiticus. This study delineated relationships among the two species and an Aspergillus PWE36 isolate. Of 25 examined clustered aflatoxin genes of PWE36, 20 gene sequences were identical to those of A. sojae, but all had variations to those of A. parasiticus. Additionally, PWE36 developmental genes of conidiation and sclerotial formation, overall, shared higher degrees of nucleotide sequence identity with A. sojae genes than with A. parasiticus genes. Examination of defective cyclopiazonic acid gene clusters revealed that the PWE36 deletion pattern was identical only to those of A. sojae. Using A. sojae SMF134 genome sequence as a reference, visualization of locally collinear blocks indicated that PWE36 shared higher genome sequence homologies with A. sojae than with A. parasiticus. Phylogenetic inference based on genome-wide single nucleotide polymorphisms (SNPs) and total SNP counts showed that A. sojae strains formed a monophyletic clade and were clonal. Two (Argentinian and Ugandan) A. parasiticus isolates but not including an Ethiopian isolate formed a monophyletic clade, which showed that A. parasiticus population is genetically diverse and distant to A. sojae. PWE36 and A. sojae shared a most recent common ancestor (MRCA). The estimated divergence time for PWE36 and A. sojae was about 0.4 mya. Unlike Aspergillus oryzae, another koji mold that includes genetically diverse populations, the findings that current A. sojae strains formed a monophyletic group and shared the MRCA with PWE36 allow A. sojae to be continuously treated as a species for food safety reasons.

• The Korean Journal of Applied Statistics
• /
• v.35 no.6
• /
• pp.685-701
• /
• 2022

FDR is widely used in high-dimensional data inference since it provides more liberal criterion contrary to FWER which is known to be very conservative by controlling Type-1 errors. This paper proposes a sparse VHAR model estimation method controlling FDR by adapting the knockoff introduced by Barber and Candès (2015). We also compare knockoff with conventional method using adaptive Lasso (AL) through extensive simulation study. We observe that AL shows sparsistency and decent forecasting performance, however, AL is not satisfactory in controlling FDR. To be more specific, AL tends to estimate zero coefficients as non-zero coefficients. On the other hand, knockoff controls FDR sufficiently well under desired level, but it finds too sparse model when the sample size is small. However, the knockoff is dramatically improved as sample size increases and the model is getting sparser.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.11
• /
• pp.235-244
• /
• 2017

This paper aims to design a system for psychological diagnosis in sandbox play by applying rule based expert system. Sandbox play is one of play therapy and it is a technique that can be combined with psychological diagnosis and treatment using sand and various kinds of figures. In this technique, we focus on psychological diagnostic factors and try to implement a system that automatically diagnoses psychological types when input values are given. Therefore, six kinds of language objects are set and the rules are created according to the types of figures, arrangement of figures, and production time in the sand box used as a reference element in the diagnosis method. In this system, it is assumed that the client recognizes the finished sandbox as a sensor device. Then, when the recognized state enters the input value, the rules based on the language object are ignited in order. Through this, the client is diagnosed with one of 26 types of psychology. As a result, the diagnostic process is simplified and automated. Accordingly, a more detailed psychological diagnosis and treatments are provided.

• Steel and Composite Structures
• /
• v.48 no.2
• /
• pp.179-190
• /
• 2023

Many recent attempts have sought accurate prediction of pile pullout resistance (P_ul) using classical machine learning models. This study offers an improved methodology for this objective. Adaptive neuro-fuzzy inference system (ANFIS), as a popular predictor, is trained by a capable metaheuristic strategy, namely equilibrium optimizer (EO) to predict the P_ul. The used data is collected from laboratory investigations in previous literature. First, two optimal configurations of EO-ANFIS are selected after sensitivity analysis. They are next evaluated and compared with classical ANFIS and two neural-based models using well-accepted accuracy indicators. The results of all five models were in good agreement with laboratory P_uls (all correlations > 0.99). However, it was shown that both EO-ANFISs not only outperform neural benchmarks but also enjoy a higher accuracy compared to the classical version. Therefore, utilizing the EO is recommended for optimizing this predictive tool. Furthermore, a comparison between the selected EO-ANFISs, where one employs a larger population, revealed that the model with the population size of 75 is more efficient than 300. In this relation, root mean square error and the optimization time for the EO-ANFIS (75) were 19.6272 and 1715.8 seconds, respectively, while these values were 23.4038 and 9298.7 seconds for EO-ANFIS (300).

• Journal of Convergence for Information Technology
• /
• v.12 no.2
• /
• pp.47-53
• /
• 2022

Recently, with the change of the intelligent security paradigm, study to apply various information generated from various information security systems to AI-based anomaly detection is increasing. Therefore, in this study, in order to convert log-like time series data into a vector, which is a numerical feature, the CBOW and Skip-gram inference methods of deep learning-based Word2Vec model and statistical method based on the coincidence frequency were used to transform the published ADFA system call data. In relation to this, an experiment was carried out through conversion into various embedding vectors considering the dimension of vector, the length of sequence, and the window size. In addition, the performance of the embedding methods used as well as the detection performance were compared and evaluated through GRU-based anomaly detection model using vectors generated by the embedding model as an input. Compared to the statistical model, it was confirmed that the Skip-gram maintains more stable performance without biasing a specific window size or sequence length, and is more effective in making each event of sequence data into an embedding vector.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.4B
• /
• pp.389-397
• /
• 2010

This study introduced a Bayesian based frequency analysis in which the statistical trend analysis for hydrologic extreme series is incorporated. The proposed model employed Gumbel extreme distribution to characterize extreme events and a fully coupled bayesian frequency model was finally utilized to estimate design rainfalls in Seoul. Posterior distributions of the model parameters in both Gumbel distribution and trend analysis were updated through Markov Chain Monte Carlo Simulation mainly utilizing Gibbs sampler. This study proposed a way to make use of nonstationary frequency model for dynamic risk analysis, and showed an increase of hydrologic risk with time varying probability density functions. The proposed study showed advantage in assessing statistical significance of parameters associated with trend analysis through statistical inference utilizing derived posterior distributions.

• Communications of Mathematical Education
• /
• v.37 no.4
• /
• pp.591-614
• /
• 2023

For a long time, mathematics education institutions such as NCTM(National Council of Teachers of Mathematics) have emphasized the essential role of writing, and recent surveys by the Ministry of Education report a decline in foundational academic skills in the post-COVID19 period. The purpose of this study is to redefine the significance of mathematics writing in mathematics education, focusing on competencies highlighted in the field, particularly in the areas of problem-solving, communication, and reasoning. The research findings indicate that writing in problem-solving enhances cognitive organization, fostering the ability to grasp concepts and methods. Writing in communication builds confidence through the meta-cognitive process, and writing in inference allows self-awareness of step-by-step identification of areas lacking understanding. Particularly in the future society where artificial intelligence(AI) is utilized, changes in the learning environment necessitate research for the establishment of authenticity judgment through writing and the cultivation of a proper writing culture.

• Smart Media Journal
• /
• v.12 no.9
• /
• pp.89-94
• /
• 2023

Recommender systems provide users with the most favorable items by analyzing explicit or implicit feedback of users on items. Recently, as the size of deep-learning-based models employed in recommender systems has increased, many studies have focused on reducing inference time while maintaining high recommendation accuracy. As one of them, a study on recommender systems with a knowledge distillation (KD) technique is actively conducted. By KD, a small-sized model (i.e., student) is trained through knowledge extracted from a large-sized model (i.e., teacher), and then the trained student is used as a recommendation model. Existing studies on KD for recommender systems have been mainly performed only for implicit feedback settings. Thus, in this paper, we try to investigate the performance and accuracy when applied to explicit feedback settings. To this end, we leveraged a total of five state-of-the-art KD methods and three real-world datasets for recommender systems.