• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.5
• /
• pp.119-125
• /
• 2021

As the electricity grid systems has been intelligent with the development of ICT technology, power consumption information of users connected to the grid is available to acquired and analyzed for the power utilities. In this paper, the energy theft problem is solved by feature selection methods, which is emerging as the main cause of economic loss in smart grid. The data preprocessing steps of the proposed system consists of five steps. In the feature selection step, features are selected using analysis of variance and mutual information (MI) based method, which are filtering-based feature selection methods. According to the simulation results, the performance of support vector machine classifier is higher than the case of using all the input features of the input data for the case of the MI based feature selection method.

• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.2
• /
• pp.231-243
• /
• 2021

In Recent years the way we analyze the breast cancer has changed dramatically. Breast cancer is the most common and complex disease diagnosed among women. There are several subtypes of breast cancer and many options are there for the treatment. The most important is to educate the patients. As the research continues to expand, the understanding of the disease and its current treatments types, the researchers are constantly being updated with new researching techniques. Breast cancer survival rates have been increased with the use of new advanced treatments, largely due to the factors such as earlier detection, a new personalized approach to treatment and a better understanding of the disease. Many machine learning classification models have been adopted and modified to diagnose the breast cancer disease. In order to enhance the performance of classification model, our research proposes a model using A Hybrid Modified K-Means Clustering with Modified SVM (Support Vector Machine) Machine learning algorithm to create a new method which can highly improve the performance and prediction. The proposed Machine Learning model is to improve the performance of machine learning classifier. The Proposed Model rectifies the irregularity in the dataset and they can create a new high quality dataset with high accuracy performance and prediction. The recognized datasets Wisconsin Diagnostic Breast Cancer (WDBC) Dataset have been used to perform our research. Using the Wisconsin Diagnostic Breast Cancer (WDBC) Dataset, We have created our Model that can help to diagnose the patients and predict the probability of the breast cancer. A few machine learning classifiers will be explored in this research and compared with our Proposed Model "A Hybrid Modified K-Means with Modified SVM Machine Learning Algorithm to Enhance the Cancer Prediction" to implement and evaluated. Our research results show that our Proposed Model has a significant performance compared to other previous research and with high accuracy level of 99% which will enhance the Cancer Prediction.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.4
• /
• pp.337-346
• /
• 2021

Detection of abnormal signal generally can be done by using features of normal signals as main information because of data imbalance. This paper propose an efficient method for abnormal signal detection using parallel AutoEncoder (AE) which can use features of abnormal signals as well. The proposed Parallel AE (PAE) is composed of a normal and an abnormal reconstructors having identical AE structure and train features of normal and abnormal signals, respectively. The PAE can effectively solve the imbalanced data problem by sequentially training normal and abnormal data. For further detection performance improvement, additional binary classifier can be added to the PAE. Through experiments using public acoustic data, we obtain that the proposed PAE shows Area Under Curve (AUC) improvement of minimum 22 % at the expenses of training time increased by 1.31 ~ 1.61 times to the single AE. Furthermore, the PAE shows 93 % AUC improvement in detecting abnormal underwater acoustic signal when pre-trained PAE is transferred to train open underwater acoustic data.

• Journal of Digital Convergence
• /
• v.17 no.9
• /
• pp.79-88
• /
• 2019

This study analyzes the influential factors and patterns associated with death from aircraft accidents and incidents using data mining techniques. To this end, we used two datasets for aircraft accidents and incidents, one from the National Transportation Safety Board (NTSB) and the other from the Federal Aviation Administration (FAA). We developed our prediction models using the decision tree classifier to predict death from aircraft accidents or aircraft incidents and thereby derive the main cause factors and patterns that can cause death based on these prediction models. In the NTSB data, deaths occurred frequently when the aircraft was destroyed or people were performing dangerous missions or maneuver. In the FAA data, deaths were mainly caused by pilots who were less skilled or less qualified when their aircraft were partially destroyed. Several death-related patterns were also found for parachute jumping and aircraft ascending and descending phases. Using the derived patterns, we proposed helpful strategies to prevent death from the aircraft accidents or incidents.

• Biomedical Science Letters
• /
• v.25 no.1
• /
• pp.99-106
• /
• 2019

Amyloid positron emission tomography (PET) allows early and accurate diagnosis in suspected cases of Alzheimer's disease (AD) and contributes to future treatment plans. In the present study, a method of implementing a diagnostic system to distinguish ${\beta}$-Amyloid ($A{\beta}$) positive from $A{\beta}$ negative with objectiveness and accuracy was proposed using a machine learning approach, such as the Principal Component Analysis (PCA) and Support Vector Machine (SVM). $^{18}F$-Florbetaben (FBB) brain PET images were arranged in control and patients (total n = 176) with mild cognitive impairment and AD. An SVM was used to classify the slices of registered PET image using PET template, and a system was created to diagnose patients comprehensively from the output of the trained model. To compare the per-slice classification, the PCA-SVM model observing the whole brain (WB) region showed the highest performance (accuracy 92.38, specificity 92.87, sensitivity 92.87), followed by SVM with gray matter masking (GMM) (accuracy 92.22, specificity 92.13, sensitivity 92.28) for $A{\beta}$ positivity. To compare according to per-subject classification, the PCA-SVM with WB also showed the highest performance (accuracy 89.21, specificity 71.67, sensitivity 98.28), followed by PCA-SVM with GMM (accuracy 85.80, specificity 61.67, sensitivity 98.28) for $A{\beta}$ positivity. When comparing the area under curve (AUC), PCA-SVM with WB was the highest for per-slice classifiers (0.992), and the models except for SVM with WM were highest for the per-subject classifier (1.000). We can classify $^{18}F$-Florbetaben amyloid brain PET image for $A{\beta}$ positivity using PCA-SVM model, with no additional effects on GMM.

• Journal of the Korea Convergence Society
• /
• v.9 no.11
• /
• pp.15-21
• /
• 2018

In this study, we try to detect anomalies on the network intrusion detection system by learning only one class. We use KDD CUP 1999 dataset, an intrusion detection dataset, which is used to evaluate classification performance. One class classification is one of unsupervised learning methods that classifies attack class by learning only normal class. When using unsupervised learning, it difficult to achieve relatively high classification efficiency because it does not use negative instances for learning. However, unsupervised learning has the advantage for classifying unlabeled data. In this study, we use one class classifiers based on support vector machines and density estimation to detect new unknown attacks. The test using the classifier based on density estimation has shown relatively better performance and has a detection rate of about 96% while maintaining a low FPR for the new attacks.

• The Journal of Korean Institute of Information Technology
• /
• v.16 no.11
• /
• pp.105-113
• /
• 2018

In this paper, we proposed a method for effective classification of eye, nose, and mouth of human face. Most recent image classification uses Convolutional Neural Network(CNN). However, the features extracted by CNN are not sufficient and the classification effect is not too high. We proposed a new algorithm to improve the classification effect. The proposed method can be roughly divided into three parts. First, the Haar feature extraction algorithm is used to construct the eye, nose, and mouth dataset of face. The second, the model extracts CNN features of image using AlexNet. Finally, Haar-CNN features are extracted by performing convolution after Haar feature extraction. After that, CNN features and Haar-CNN features are fused and classify images using softmax. Recognition rate using mixed features could be increased about 4% than CNN feature. Experiments have demonstrated the performance of the proposed algorithm.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.14 no.4
• /
• pp.35-45
• /
• 2018

Users are sharing many of contents such as text, image, video, and so on in SNS. There are various information as like as personal interesting, opinion, and relationship in social media contents. Therefore, many of recommendation systems or search systems are being developed through analysis of social media contents. In order to extract subject-related topics of social context being collected from social media channels in developing those system, it is necessary to develop ontologies for semantic analysis. However, it is difficult to develop formal ontology because social media contents have the characteristics of non-formal data. Therefore, we develop a social topic system based on semantic and subject correlation. First of all, an extracting system of social topic based on semantic relationship analyzes semantic correlation and then extracts topics expressing semantic information of corresponding social context. Because the possibility of developing formal ontology expressing fully semantic information of various areas is limited, we develop a self-extensible architecture of ontology for semantic correlation. And then, a classifier of social contents and feed back classifies equivalent subject's social contents and feedbacks for extracting social topics according semantic correlation. The result of analyzing social contents and feedbacks extracts subject keyword, and index by measuring the degree of association based on social topic's semantic correlation. Deep Learning is applied into the process of indexing for improving accuracy and performance of mapping analysis of subject's extracting and semantic correlation. We expect that proposed system provides customized contents for users as well as optimized searching results because of analyzing semantic and subject correlation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.331-337
• /
• 2014

Paradigm shift to cloud computing has increased the importance of security. Even though public cloud computing providers such as Amazon, already provides security related service like firewall and identity management services, it is not suitable to protect data in cloud environments. Because in public cloud computing environments do not allow to use client's own security solution nor equipments. In this environments, user are supposed to do something to enhance security by their hands, so the needs of visualized security management arises. To implement visualized security management, developing near realtime data handling & packet classification mechanisms are crucial. The key technical challenges in packet classification is how to classify packet in the manner of unsupervised way without human interactions. To achieve the goal, this paper presents automated packet classification mechanism based on naive-bayesian and packet Chunking techniques, which can identify signature and does machine learning by itself without human intervention.

• Phonetics and Speech Sciences
• /
• v.11 no.3
• /
• pp.39-47
• /
• 2019

We propose a method to improve the performance of spontaneous speech recognizers by extending their phone set using speech data. In the proposed method, we first extract variable-length phoneme-level segments from broadcast speech signals, and convert them to fixed-length latent vectors using an long short-term memory (LSTM) classifier. We then cluster acoustically similar latent vectors and build a new phone set by choosing the number of clusters with the lowest Davies-Bouldin index. We also update the lexicon of the speech recognizer by choosing the pronunciation sequence of each word with the highest conditional probability. In order to analyze the acoustic characteristics of the new phone set, we visualize its spectral patterns and segment duration. Through speech recognition experiments using a larger training data set than our own previous work, we confirm that the new phone set yields better performance than the conventional phoneme-based and grapheme-based units in both spontaneous speech recognition and read speech recognition.