• Journal of the Korea Society of Computer and Information
• /
• v.28 no.11
• /
• pp.53-63
• /
• 2023

This study developed a cognitive impairment predictive model as one of the screening tests for preventing dementia in the elderly by using Automated Machine Learning(AutoML). We used 'Wearable lifelog data for high-risk dementia patients' of National Information Society Agency, then conducted using PyCaret 3.0.0 in the Google Colaboratory environment. This study analysis steps are as follows; first, selecting five models demonstrating excellent classification performance for the model development and lifelog data analysis. Next, using ensemble learning to integrate these models and assess their performance. It was found that Voting Classifier, Gradient Boosting Classifier, Extreme Gradient Boosting, Light Gradient Boosting Machine, Extra Trees Classifier, and Random Forest Classifier model showed high predictive performance in that order. This study findings, furthermore, emphasized on the the crucial importance of 'Average respiration per minute during sleep' and 'Average heart rate per minute during sleep' as the most critical feature variables for accurate predictions. Finally, these study results suggest that consideration of the possibility of using machine learning and lifelog as a means to more effectively manage and prevent cognitive impairment in the elderly.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.8
• /
• pp.17-25
• /
• 2013

TIn this paper, we propose a model automatically scoring a student's answer for a descriptive problem by using a voting method. Considering the model construction cost, the proposed model does not separately construct the automatic scoring model per problem type. In order to utilize features useful for automatically scoring the descriptive answers, the proposed model extracts feature values from the results, generated by comparing the student's answer with the answer sheet. For the purpose of improving the precision of the scoring result, the proposed model collects the scoring results classified by a few machine learning based classifiers, and unanimously selects the scoring result as the final result. Experimental results show that the single machine learning based classifier C4.5 takes 83.00% on precision while the proposed model improve the precision up to 90.57% by using three machine learning based classifiers C4.5, ME, and SVM.

• The Journal of Bigdata
• /
• v.6 no.1
• /
• pp.133-144
• /
• 2021

This paper derives the fire risk of buildings in Seoul through the prediction of property damage and the occurrence of fires. This study differs from prior research in that it utilizes variables that include not only a building's characteristics but also its affiliated administrative area as well as the accessibility of nearby fire-fighting facilities. We use Ensemble Voting techniques to merge different machine learning algorithms to predict property damage and fire occurrence, and to extract feature importance to produce fire risk. Fire risk prediction was made on 300 buildings in Seoul utilizing the established model, and it has been derived that with buildings at Level 1 for fire risks, there were a high number of households occupying the building, and the buildings had many factors that could contribute to increasing the size of the fire, including the lack of nearby fire-fighting facilities as well as the far location of the 119 Safety Center. On the other hand, in the case of Level 5 buildings, the number of buildings and businesses is large, but the 119 Safety Center in charge are located closest to the building, which can properly respond to fire.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.10
• /
• pp.35-41
• /
• 2012

We propose a new marker driven Watershed algorithm for automated segmentation of clustered cell from microscopy image with less over segmentation. The Watershed Transform is able to segment extremely complex objects which are highly touched and overlapped each other. The success of the Watershed Transform depends essentially on the finding markers for each of the objects of interest. For extracting of markers positioning around center of each cell we used radial symmetry and iterative voting algorithms. With synthetic and real images, we quantitatively demonstrate the performance of our method and achieved better results than the other compared methods.

• Journal of Information Processing Systems
• /
• v.15 no.3
• /
• pp.604-615
• /
• 2019

Single-user spectrum sensing is susceptible to multipath effects, shadow effects, hidden terminals and other unfavorable factors, leading to misjudgment of perceived results. In order to increase the detection accuracy and reduce spectrum sensing cost, we propose an adaptive cooperative sensing strategy based on an estimated signal-to-noise ratio (SNR). Which can adaptive select different sensing strategy during the local sensing phase. When the estimated SNR is higher than the selection threshold, adaptive double threshold energy detector (ED) is implemented, otherwise cyclostationary feature detector is performed. Due to the fact that only a better sensing strategy is implemented in a period, the detection accuracy is improved under the condition of low SNR with low complexity. The local sensing node transmits the perceived results through the control channel to the fusion center (FC), and uses voting rule to make the hard decision. Thus the transmission bandwidth is effectively saved. Simulation results show that the proposed scheme can effectively improve the system detection probability, shorten the average sensing time, and has better robustness without largely increasing the costs of sensing system.

• Journal of KIISE:Software and Applications
• /
• v.31 no.4
• /
• pp.498-504
• /
• 2004

This paper presents a new text classifier based on a feature projection technique. In feature projections, training documents are represented as the projections on each feature. A classification process is based on individual feature projections. The final classification is determined by the sum from the individual classification of each feature. In our experiments, the proposed classifier showed high performance. Especially, it have fast execution speed and robustness with noisy data in comparison with k-NN and SVM, which are among the state-of-art text classifiers. Since the algorithm of the proposed classifier is very simple, its implementation and training process can be done very simply. Therefore, it can be a useful classifier in text classification tasks which need fast execution speed, robustness, and high performance.

• Journal of Korea Multimedia Society
• /
• v.15 no.2
• /
• pp.195-203
• /
• 2012

This paper proposes ground target classification algorithm based on decision fusion and feature extraction method using multi-sensor images. The decisions obtained from the individual classifiers are fused by applying a weighted voting method to improve target recognition rate. For classifying the targets belong to the individual sensors images, features robust to scale and rotation are extracted using the difference of brightness of CM images obtained from CCD image and the boundary similarity and the width ratio between the vehicle body and turret of target in FLIR image. Finally, we verity the performance of proposed ground target classification algorithm and feature extraction method by the experimentation.

• International Journal of Computer Science & Network Security
• /
• v.23 no.12
• /
• pp.101-106
• /
• 2023

Chronic illnesses are among the most common serious problems affecting human health. Early diagnosis of chronic diseases can assist to avoid or mitigate their consequences, potentially decreasing mortality rates. Using machine learning algorithms to identify risk factors is an exciting strategy. The issue with existing feature selection approaches is that each method provides a distinct set of properties that affect model correctness, and present methods cannot perform well on huge multidimensional datasets. We would like to introduce a novel model that contains a feature selection approach that selects optimal characteristics from big multidimensional data sets to provide reliable predictions of chronic illnesses without sacrificing data uniqueness.[1] To ensure the success of our proposed model, we employed balanced classes by employing hybrid balanced class sampling methods on the original dataset, as well as methods for data pre-processing and data transformation, to provide credible data for the training model. We ran and assessed our model on datasets with binary and multivalued classifications. We have used multiple datasets (Parkinson, arrythmia, breast cancer, kidney, diabetes). Suitable features are selected by using the Hybrid feature model consists of Lassocv, decision tree, random forest, gradient boosting,Adaboost, stochastic gradient descent and done voting of attributes which are common output from these methods.Accuracy of original dataset before applying framework is recorded and evaluated against reduced data set of attributes accuracy. The results are shown separately to provide comparisons. Based on the result analysis, we can conclude that our proposed model produced the highest accuracy on multi valued class datasets than on binary class attributes.[1]

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.2
• /
• pp.643-661
• /
• 2018

This paper proposes a novel algorithm for lane detection based on inverse perspective transformation and Kalman filter. A simple inverse perspective transformation method is presented to remove perspective effects and generate a top-view image. This method does not need to obtain the internal and external parameters of the camera. The Gaussian kernel function is used to convolute the image to highlight the lane lines, and then an iterative threshold method is used to segment the image. A searching method is applied in the top-view image obtained from the inverse perspective transformation to determine the lane points and their positions. Combining with feature voting mechanism, the detected lane points are fitted as a straight line. Kalman filter is then applied to optimize and track the lane lines and improve the detection robustness. The experimental results show that the proposed method works well in various road conditions and meet the real-time requirements.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.10
• /
• pp.1347-1357
• /
• 1995

In this paper, we describe a modularized neuroclassifier for enhancing the recognition accuracy of mixed printed and handwritten numerals. This classifier combines four modularized subclassifiers using multi-layer perceptron module. The input of each subclassifier is comprised of a group of specialized feature sets. On applying this method to combining several subclassifiers for unconstrained handwritten numerals, the experimental result shows that the performance of individual subclassifier can be improved. In winner-take-all voting method, the result of subclassifier having the highest RF value is selected as the output. The generality of this classifier is tested with 1,080 printed and 3,000 handwritten numerals that was not shown in training the neural networks. Experimental results show 98.2% recognition rate. The typical recognition test with a threshold value(RF=1.5) has shown 97% recognition, 1% substitution and 2% rejection rates.