• Proceedings of the Korean Geotechical Society Conference
• /
• 2000.11a
• /
• pp.231-236
• /
• 2000

In order to predict depth of the pile forward modeling and inversion of magnetic logging data was conducted by using a finite line of dipoles model. The horizontal component as well as the vertical component of magnetic fields can be measured in the borehole, and the magnetic anomalies can be obtained by subtracting the Earth's magnetic field from the measurement. The magnetic anomalies of the pile are considered as vector sum of induced magnetization due to the Earth's magnetic field and remnant magnetization possessed by steel strings in the pile. The magnetic anomalies are used as input data for inversion from which the length, the magnetic moment per unit length, and the dip angle of the pile can be obtained. From the inversion of synthetic noisy data, and the data obtained from the field model test it is found that the driving depth of the pile can be determined as close to the order of measuring interval (5∼10㎝). It is also found that the resultant magnetic anomalies due to an individual steel string in the pile are almost same as those due to a group of steel strings located at the center of the pile. The magnetic logging method also can be used for locating reinforced bars, pipes, and steel casings.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.12
• /
• pp.77-86
• /
• 2015

It is difficult to extract small valve automatically in noisy 3D point cloud obtained from LIDAR because small object is affected by noise considerably. In this paper, we assume that the valve is a complex model consisting of torus, cylinder and plane represents handle, rib and center plane to extract a pose of the valve. And to extract the pose, we received additional input: center of the valve. We generated histogram of distance between the center and each points of point cloud, and obtain pose of valve by extracting parameters of handle, rib and center plane. Finally, the valve is reconstructed.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.37 no.11
• /
• pp.1315-1321
• /
• 2013

This study presents a prognostic technique for the damage state of a ball bearing. A stochastic bearing fatigue defect-propagation model is applied to estimate the damage progression rate. The damage state and the time to failure are computed by using RMS data from noisy acceleration signals. The parameters of the stochastic defect-propagation model are identified by conducting a series of run-to-failure tests for ball bearings. A regularized particle filter is applied to predict the damage progression rate and update the degradation state based on the acceleration RMS data. The future damage state is predicted based on the most recently measured data and the previously predicted damage state. The developed method was validated by comparing the prognostic results and the test data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.1
• /
• pp.172-185
• /
• 2019

In this paper, we investigate the performance of the diffusion adaptation strategies for parameter estimation in wireless adaptive networks, where the nodes exchange information over noisy and fading wireless channels. This paper shows the differences between the effect of Rayleigh and Rician fading over wireless adaptive networks and proves that the Rician fading is a more practical model in such kinds of networks. Simulation results imply that the effect of Rayleigh fading is more degrading for the estimation process than Rician fading. Also, the simulation results show the performance of adapt then combine (ATC) diffusion algorithm is better than the combine then adapt (CTA) algorithm by merely considering noise in wireless channels. While the performance of CTA prevails ATC over the wireless adaptive network in the presence of noise plus channel fading.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.2
• /
• pp.19-25
• /
• 2021

In this paper proposes a method of finding missing persons based on face-recognition technology and deep learning. In this paper, a real-time face-recognition technology was developed, which performs face verification and improves the accuracy of face identification through data fortification for face recognition and convolutional neural network(CNN)-based image learning after the pre-processing of images transmitted from a mobile device. In identifying a missing person's image using the system implemented in this paper, the model that learned both original and blur-processed data performed the best. Further, a model using the pre-learned Noisy Student outperformed the one not using the same, but it has had a limitation of producing high levels of deflection and dispersion.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.10
• /
• pp.3230-3255
• /
• 2022

Causality mining in NLP is a significant area of interest, which benefits in many daily life applications, including decision making, business risk management, question answering, future event prediction, scenario generation, and information retrieval. Mining those causalities was a challenging and open problem for the prior non-statistical and statistical techniques using web sources that required hand-crafted linguistics patterns for feature engineering, which were subject to domain knowledge and required much human effort. Those studies overlooked implicit, ambiguous, and heterogeneous causality and focused on explicit causality mining. In contrast to statistical and non-statistical approaches, we present Bidirectional Encoder Representations from Transformers (BERT) integrated with Multi-level Feature Networks (MFN) for causality recognition, called BERT+MFN for causality recognition in noisy and informal web datasets without human-designed features. In our model, MFN consists of a three-column knowledge-oriented network (TC-KN), bi-LSTM, and Relation Network (RN) that mine causality information at the segment level. BERT captures semantic features at the word level. We perform experiments on Alternative Lexicalization (AltLexes) datasets. The experimental outcomes show that our model outperforms baseline causality and text mining techniques.

• International Journal of Contents
• /
• v.18 no.2
• /
• pp.68-80
• /
• 2022

The health of the human heart is commonly measured using ECG (Electrocardiography) signals. To identify any anomaly in the human heart, the time-sequence of ECG signals is examined manually by a cardiologist or cardiac electrophysiologist. Lightweight anomaly detection on ECG signals in an embedded system is expected to be popular in the near future, because of the increasing number of heart disease symptoms. Some previous research uses deep learning networks such as LSTM and BiLSTM to detect anomaly signals without any handcrafted feature. Unfortunately, lightweight LSTMs show low precision and heavy LSTMs require heavy computing powers and volumes of labeled dataset for symptom classification. This paper proposes an ECG anomaly detection system based on two level BiLSTM for acceptable precision with lightweight networks, which is lightweight and usable at home. Also, this paper presents a new threshold technique which considers statistics of the current ECG pattern. This paper's proposed model with BiLSTM detects ECG signal anomaly in 0.467 ~ 1.0 F₁ score, compared to 0.426 ~ 0.978 F₁ score of the similar model with LSTM except one highly noisy dataset.

• International Journal of Computer Science & Network Security
• /
• v.23 no.9
• /
• pp.95-99
• /
• 2023

Recently Machine Learning has been considered as one of the active research areas of Computer Science. The various Artificial Intelligence techniques are used to solve the classification problems of environmental sciences, biological sciences, and medical sciences etc. Due to the heterogynous and malfunctioning weather sensors a considerable amount of noisy data with missing is generated, which is alarming situation for weather prediction stockholders. Filling of these missing values with proper method is really one of the significant problems. The data must be cleaned before applying prediction model to collect more precise & accurate results. In order to solve all above stated problems, this research proposes a novel weather forecasting system which consists upon two steps. The first step will prepare data by reducing the noise; whereas a decision model is constructed at second step using regression algorithm. The Confusion Matrix will be used to evaluation the proposed classifier.

• Smart Structures and Systems
• /
• v.33 no.3
• /
• pp.227-241
• /
• 2024

Safety and structural integrity of civil structures, like bridges and buildings, can be substantially enhanced by employing appropriate structural health monitoring (SHM) techniques for timely diagnosis of incipient damages. The information gathered from health monitoring of important infrastructure helps in making informed decisions on their maintenance. This ensures smooth, uninterrupted operation of the civil infrastructure and also cuts down the overall maintenance cost. With an early warning system, SHM can protect human life during major structural failures. A real-time online damage localization technique is proposed using only the vibration measurements in this paper. The concept of the 'Degree of Scatter' (DoS) of the vibration measurements is used to generate a spatial profile, and fractal dimension theory is used for damage detection and localization in the proposed two-phase algorithm. Further, it ensures robustness against environmental and operational variability (EoV). The proposed method works only with output-only responses and does not require correlated finite element models. Investigations are carried out to test the presented algorithm, using the synthetic data generated from a simply supported beam, a 25-storey shear building model, and also experimental data obtained from the lab-level experiments on a steel I-beam and a ten-storey framed structure. The investigations suggest that the proposed damage localization algorithm is capable of isolating the influence of the confounding factors associated with EoV while detecting and localizing damage even with noisy measurements.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.7
• /
• pp.2633-2648
• /
• 2015

The problem of visual words' synonymy and ambiguity always exist in the conventional bag of visual words (BoVW) model based object category methods. Besides, the noisy visual words, so-called "visual stop-words" will degrade the semantic resolution of visual dictionary. In view of this, a novel bag of visual words method based on PLSA and chi-square model for object category is proposed. Firstly, Probabilistic Latent Semantic Analysis (PLSA) is used to analyze the semantic co-occurrence probability of visual words, infer the latent semantic topics in images, and get the latent topic distributions induced by the words. Secondly, the KL divergence is adopt to measure the semantic distance between visual words, which can get semantically related homoionym. Then, adaptive soft-assignment strategy is combined to realize the soft mapping between SIFT features and some homoionym. Finally, the chi-square model is introduced to eliminate the "visual stop-words" and reconstruct the visual vocabulary histograms. Moreover, SVM (Support Vector Machine) is applied to accomplish object classification. Experimental results indicated that the synonymy and ambiguity problems of visual words can be overcome effectively. The distinguish ability of visual semantic resolution as well as the object classification performance are substantially boosted compared with the traditional methods.