• Journal of Information Processing Systems
• /
• v.14 no.3
• /
• pp.751-770
• /
• 2018

Web applications are indispensable in the software industry and continuously evolve either meeting a newer criteria and/or including new functionalities. However, despite assuring quality via testing, what hinders a straightforward development is the presence of defects. Several factors contribute to defects and are often minimized at high expense in terms of man-hours. Thus, detection of fault proneness in early phases of software development is important. Therefore, a fault prediction model for identifying fault-prone classes in a web application is highly desired. In this work, we compare 14 machine learning techniques to analyse the relationship between object oriented metrics and fault prediction in web applications. The study is carried out using various releases of Apache Click and Apache Rave datasets. En-route to the predictive analysis, the input basis set for each release is first optimized using filter based correlation feature selection (CFS) method. It is found that the LCOM3, WMC, NPM and DAM metrics are the most significant predictors. The statistical analysis of these metrics also finds good conformity with the CFS evaluation and affirms the role of these metrics in the defect prediction of web applications. The overall predictive ability of different fault prediction models is first ranked using Friedman technique and then statistically compared using Nemenyi post-hoc analysis. The results not only upholds the predictive capability of machine learning models for faulty classes using web applications, but also finds that ensemble algorithms are most appropriate for defect prediction in Apache datasets. Further, we also derive a consensus between the metrics selected by the CFS technique and the statistical analysis of the datasets.

• Journal of Korean Neurosurgical Society
• /
• v.67 no.1
• /
• pp.103-114
• /
• 2024

Objective : Decompressive craniectomy (DC) with duroplasty is one of the common surgical treatments for life-threatening increased intracranial pressure (ICP). Once ICP is controlled, cranioplasty (CP) with reinsertion of the cryopreserved autologous bone flap or a synthetic implant is considered for protection and esthetics. Although with the risk of autologous bone flap resorption (BFR), cryopreserved autologous bone flap for CP is one of the important material due to its cost effectiveness. In this article, we performed conventional statistical analysis and the machine learning technique understand the risk factors for BFR. Methods : Patients aged >18 years who underwent autologous bone CP between January 2015 and December 2021 were reviewed. Demographic data, medical records, and volumetric measurements of the autologous bone flap volume from 94 patients were collected. BFR was defined with absolute quantitative method (BFR-A) and relative quantitative method (BFR%). Conventional statistical analysis and random forest with hyper-ensemble approach (RF with HEA) was performed. And overlapped partial dependence plots (PDP) were generated. Results : Conventional statistical analysis showed that only the initial autologous bone flap volume was statistically significant on BFR-A. RF with HEA showed that the initial autologous bone flap volume, interval between DC and CP, and bone quality were the factors with most contribution to BFR-A, while, trauma, bone quality, and initial autologous bone flap volume were the factors with most contribution to BFR%. Overlapped PDPs of the initial autologous bone flap volume on the BRF-A crossed at approximately 60 mL, and a relatively clear separation was found between the non-BFR and BFR groups. Therefore, the initial autologous bone flap of over 60 mL could be a possible risk factor for BFR. Conclusion : From the present study, BFR in patients who underwent CP with autologous bone flap might be inevitable. However, the degree of BFR may differ from one to another. Therefore, considering artificial bone flaps as implants for patients with large DC could be reasonable. Still, the risk factors for BFR are not clearly understood. Therefore, chronological analysis and pathophysiologic studies are needed.

• Journal of Industrial Convergence
• /
• v.21 no.12
• /
• pp.55-62
• /
• 2023

Recent ransomware attacks employ various techniques and pathways, posing significant challenges in early detection and defense. Consequently, the scale of damage is continually growing. This paper introduces a machine learning-based approach for effective ransomware detection by focusing on file encryption and encryption patterns, which are pivotal functionalities utilized by ransomware. Ransomware is identified by analyzing password behavior and encryption patterns, making it possible to detect specific ransomware variants and new types of ransomware, thereby mitigating ransomware attacks effectively. The proposed machine learning-based encryption behavior detection technique extracts encryption and encryption pattern characteristics and trains them using a machine learning classifier. The final outcome is an ensemble of results from two classifiers. The classifier plays a key role in determining the presence or absence of ransomware, leading to enhanced accuracy. The proposed technique is implemented using the numpy, pandas, and Python's Scikit-Learn library. Evaluation indicators reveal an average accuracy of 94%, precision of 95%, recall rate of 93%, and an F1 score of 95%. These performance results validate the feasibility of ransomware detection through encryption behavior analysis, and further research is encouraged to enhance the technique for proactive ransomware detection.

• Annual Conference on Human and Language Technology
• /
• 2017.10a
• /
• pp.324-326
• /
• 2017

개체명 인식은 입력 문장에서 인명, 지명, 기관명, 날짜, 시간 등과 같은 고유한 의미를 갖는 단어 열을 찾아 범주를 부착하는 기술이다. 기존의 연구에서는 단어 단위나 음절 단위를 입력으로 사용하였다. 하지만 단어 단위의 경우 미등록어 처리가 어려우며 음절 단위의 경우 단어 고유의 의미가 희석되는 문제가 발생한다. 이러한 문제들을 해결하기 위해 본 논문에서는 형태소 단위 개체명 인식기와 음절 단위 개체명 인식기를 앙상블하여 보정된 결과를 예측하는 개체명 인식기를 제안한다. 제안된 모델은 각각의 단일 입력 모델보다 향상된 F1-점수(0.8049)를 보였다.

• 한국어정보학회:학술대회논문집
• /
• 2017.10a
• /
• pp.324-326
• /
• 2017

개체명 인식은 입력 문장에서 인명, 지명, 기관명, 날짜, 시간 등과 같은 고유한 의미를 갖는 단어 열을 찾아 범주를 부착하는 기술이다. 기존의 연구에서는 단어 단위나 음절 단위를 입력으로 사용하였다. 하지만 단어 단위의 경우 미등록어 처리가 어려우며 음절 단위의 경우 단어 고유의 의미가 희석되는 문제가 발생한다. 이러한 문제들을 해결하기 위해 본 논문에서는 형태소 단위 개체명 인식기와 음절 단위 개체명 인식기를 앙상블하여 보정된 결과를 예측하는 개체명 인식기를 제안한다. 제안된 모델은 각각의 단일 입력 모델보다 향상된 F1-점수(0.8049)를 보였다.

• The Bulletin of The Korean Astronomical Society
• /
• v.46 no.1
• /
• pp.61.2-61.2
• /
• 2021

SkyMapper is the largest-aperture optical wide-field telescope in Australia and can be used for transient detection in the Southern sky. Reference images from its Southern Survey cover the sky at δ <+10 deg to a depth of I ~ 20 mag. It has been used for surveys of extragalactic transients such as supernovae, optical counterparts to gravitational-wave (GW) and fast radio bursts. We adopt an ensemble-based machine learning technique and further filtering scheme that provides high completeness ~98% and purity ~91% across a wide magnitude range. Here we present an important use-case of our robotic transient search, which is the follow-up of GW event triggers from LIGO/Virgo. We discuss the facility's performance in the case of the second binary neutron star merger GW190425. In time for the LIGO/Virgo O4 run, we will have deeper reference images for galaxies within out to ~200 Mpc distance, allowing rapid transient detection to i ~ 21 mag.

• Journal of Intelligence and Information Systems
• /
• v.5 no.1
• /
• pp.95-101
• /
• 1999

In this paper, a comparison between different methods to combine predictions from neural networks will be given. These methods are bagging, bumping, and balancing. Those are based on the analysis of the ensemble generalization error into an ambiguity term and a term incorporating generalization performances of individual networks. Neural Networks and AI machine learning models are prone to overfitting. A strategy to prevent a neural network from overfitting, is to stop training in early stage of the learning process. The complete data set is spilt up into a training set and a validation set. Training is stopped when the error on the validation set starts increasing. The stability of the networks is highly dependent on the division in training and validation set, and also on the random initial weights and the chosen minimization procedure. This causes early stopped networks to be rather unstable: a small change in the data or different initial conditions can produce large changes in the prediction. Therefore, it is advisable to apply the same procedure several times starting from different initial weights. This technique is often referred to as training ensembles of neural networks. In this paper, we presented a comparison of three statistical methods to prevent overfitting of neural network.

• Geophysics and Geophysical Exploration
• /
• v.25 no.3
• /
• pp.140-161
• /
• 2022

Seismic data with missing traces are often obtained regularly or irregularly due to environmental and economic constraints in their acquisition. Accordingly, seismic data interpolation is an essential step in seismic data processing. Recently, research activity on machine learning-based seismic data interpolation has been flourishing. In particular, convolutional neural network (CNN) and generative adversarial network (GAN), which are widely used algorithms for super-resolution problem solving in the image processing field, are also used for seismic data interpolation. In this study, CNN-based algorithm, U-Net and GAN-based algorithm, and conditional Wasserstein GAN (cWGAN) were used as seismic data interpolation methods. The results and performances of the methods were evaluated thoroughly to find an optimal interpolation method, which reconstructs with high accuracy missing seismic data. The work process for model training and performance evaluation was divided into two cases (i.e., Cases I and II). In Case I, we trained the model using only the regularly sampled data with 50% missing traces. We evaluated the model performance by applying the trained model to a total of six different test datasets, which consisted of a combination of regular, irregular, and sampling ratios. In Case II, six different models were generated using the training datasets sampled in the same way as the six test datasets. The models were applied to the same test datasets used in Case I to compare the results. We found that cWGAN showed better prediction performance than U-Net with higher PSNR and SSIM. However, cWGAN generated additional noise to the prediction results; thus, an ensemble technique was performed to remove the noise and improve the accuracy. The cWGAN ensemble model removed successfully the noise and showed improved PSNR and SSIM compared with existing individual models.

• Journal of the Korea Convergence Society
• /
• v.9 no.12
• /
• pp.9-15
• /
• 2018

The main goal of extended data expression is to develop a data structure suitable for common problems in ubiquitous environments. The greatest feature of this method is that the attribute values can be represented with probability. The next feature is that each event in the training data has a weight value that represents its importance. After this data structure has been developed, an algorithm has been devised that can learn it. In the meantime, this algorithm has been applied to various problems in various fields to obtain good results. This paper first introduces the extended data expression technique, UChoo, and rule refinement method, which are the theoretical basis. Next, this paper introduces some examples of application areas such as rule refinement, missing data processing, BEWS problem, and ensemble system.

• International Journal of Computer Science & Network Security
• /
• v.22 no.2
• /
• pp.214-222
• /
• 2022

Convolutional Neural networks (CNNs) are a category of deep learning networks that have proven very effective in computer vision tasks such as image classification. Notwithstanding, not much has been seen in its use for remote sensing image classification in developing countries. This is majorly due to the scarcity of training data. Recently, transfer learning technique has successfully been used to develop state-of-the art models for remote sensing (RS) image classification tasks using training and testing data from well-known RS data repositories. However, the ability of such model to classify RS test data from a different dataset has not been sufficiently investigated. In this paper, we propose a deep CNN model that can classify RS test data from a dataset different from the training dataset. To achieve our objective, we first, re-trained a ResNet-50 model using EuroSAT, a large-scale RS dataset to develop a base model then we integrated Augmentation and Ensemble learning to improve its generalization ability. We further experimented on the ability of this model to classify a novel dataset (Nig_Images). The final classification results shows that our model achieves a 96% and 80% accuracy on EuroSAT and Nig_Images test data respectively. Adequate knowledge and usage of this framework is expected to encourage research and the usage of deep CNNs for land cover mapping in cases of lack of training data as obtainable in developing countries.