• Journal of the Korea Society of Computer and Information
• /
• v.25 no.11
• /
• pp.41-50
• /
• 2020

Sentimental analysis begins with the search for words that determine the sentimentality inherent in data. Managers can understand market sentimentality by analyzing a number of relevant sentiment words which consumers usually tend to use. In this study, we propose exploring performance of feature selection methods embedded with Particle Swarm Optimization Multi Objectives Evolutionary Algorithms. The performance of the feature selection methods was benchmarked with machine learning classifiers such as Decision Tree, Naive Bayesian Network, Support Vector Machine, Random Forest, Bagging, Random Subspace, and Rotation Forest. Our empirical results of opinion mining revealed that the number of features was significantly reduced and the performance was not hurt. In specific, the Support Vector Machine showed the highest accuracy. Random subspace produced the best AUC results.

• Journal of KIISE:Software and Applications
• /
• v.28 no.11
• /
• pp.822-832
• /
• 2001

We have implemented an inductive learning system that learns PROSPECTOR-rule-style classification rules from sets of examples. In our a approach, a genetic algorithm is used in which a population consists of rule-sets and rule-sets generate offspring through the exchange of rules relying on genetic operators such as crossover, mutation, and inversion operators. In this paper, we describe our learning environment centering on the syntactic structure and meaning of classification rules, the structure of a population, and the implementation of genetic operators. We also present a method to evaluate the performance of rules and a heuristic approach to generate rules, which are developed to implement mutation operators more efficiently. Moreover, a method to construct a classification system using multiple learned rule-sets to enhance the performance of a classification system is also explained. The performance of our learning system is compared with other learning algorithms, such as neural networks and decision tree algorithms, using various data sets.

• Journal of the Institute of Convergence Signal Processing
• /
• v.15 no.2
• /
• pp.24-29
• /
• 2014

Digital mammography is the most common technique for the early detection of breast cancer. To diagnose the breast cancer in early stages and treat efficiently, many image enhancement methods have been developed. This paper presents a multi-scale contrast enhancement method in the Laplacian pyramid for the digital mammogram. The proposed method decomposes the image into the contrast measures by the Gaussian and Laplacian pyramid, and the pyramid coefficients of decomposed multi-resolution image are defined as the frequency limited local contrast measures by the ratio of high frequency components and low frequency components. The decomposed pyramid coefficients are modified by the contrast measure for enhancing the contrast, and the final enhanced image is obtained by the composition process of the pyramid using the modified coefficients. The proposed method is compared with other existing methods, and demonstrated to have quantitatively good performance in the contrast measure algorithm.

• Health Policy and Management
• /
• v.26 no.4
• /
• pp.289-304
• /
• 2016

Background: Rehabilitations in subacute phase are different from acute treatments regarding the characteristics and required resource consumption of the treatments. Lack of accuracy and validity of the Korean Diagnosis Related Group and Korean Out-Patient Group for the acute patients as the case-mix and payment tool for rehabilitation inpatients have been problematic issues. The objective of the study was to develop the Korean Rehabilitation Patient Group (KRPG) reflecting the characteristics of rehabilitation inpatients. Methods: As a retrospective medical record survey regarding rehabilitation inpatients, 4,207 episodes were collected through 42 hospitals. Considering the opinions of clinical experts and the decision-tree analysis, the variables for the KRPG system demonstrating the characteristics of rehabilitation inpatients were derived, and the splitting standards of the relevant variables were also set. Using the derived variables, we have drawn the rehabilitation inpatient classification model reflecting the clinical situation of Korea. The performance evaluation was conducted on the KRPG system. Results: The KRPG was targeted at the inpatients with brain or spinal cord injury. The etiologic disease, functional status (cognitive function, activity of daily living, muscle strength, spasticity, level and grade of spinal cord injury), and the patient's age were the variables in the rehabilitation patients. The algorithm of KRPG system after applying the derived variables and total 204 rehabilitation patient groups were developed. The KRPG explained 11.8% of variance in charge for rehabilitation inpatients. It also explained 13.8% of variance in length of stay for them. Conclusion: The KRPG version 1.0 reflecting the clinical characteristics of rehabilitation inpatients was classified as 204 groups.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.9
• /
• pp.811-819
• /
• 2014

Activity recognition is a key component in identifying the context of a user for providing services based on the application such as medical, entertainment and tactical scenarios. Instead of applying numerous sensor devices, as observed in many previous investigations, we are proposing the use of smartphone with its built-in multimodal sensors as an unobtrusive sensor device for recognition of six physical daily activities. As an improvement to previous works, accelerometer, gyroscope and magnetometer data are fused to recognize activities more reliably. The evaluation indicates that the IBK classifier using window size of 2s with 50% overlapping yields the highest accuracy (i.e., up to 99.33%). To achieve this peak accuracy, simple time-domain and frequency-domain features were extracted from raw sensor data of the smartphone.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.5
• /
• pp.388-402
• /
• 2003

In this paper, we carried out the word, 4 continuous digits. continuous, and task-independent word recognition experiments to verify the effectiveness of the re-defined phoneme-likely units (PLUs) for the phonetic decision tree based HM-Net (Hidden Markov Network) context-dependent (CD) acoustic modeling in Korean appropriately. In case of the 48 PLUs, the phonemes /ㅂ/, /ㄷ/, /ㄱ/ are separated by initial sound, medial vowel, final consonant, and the consonants /ㄹ/, /ㅈ/, /ㅎ/ are also separated by initial sound, final consonant according to the position of syllable, word, and sentence, respectively. In this paper. therefore, we re-define the 39 PLUs by unifying the one phoneme in the separated initial sound, medial vowel, and final consonant of the 48 PLUs to construct the CD acoustic models effectively. Through the experimental results using the re-defined 39 PLUs, in word recognition experiments with the context-independent (CI) acoustic models, the 48 PLUs has an average of 7.06%, higher recognition accuracy than the 39 PLUs used. But in the speaker-independent word recognition experiments with the CD acoustic models, the 39 PLUs has an average of 0.61% better recognition accuracy than the 48 PLUs used. In the 4 continuous digits recognition experiments with the liaison phenomena. the 39 PLUs has also an average of 6.55% higher recognition accuracy. And then, in continuous speech recognition experiments, the 39 PLUs has an average of 15.08% better recognition accuracy than the 48 PLUs used too. Finally, though the 48, 39 PLUs have the lower recognition accuracy, the 39 PLUs has an average of 1.17% higher recognition characteristic than the 48 PLUs used in the task-independent word recognition experiments according to the unknown contextual factor. Through the above experiments, we verified the effectiveness of the re-defined 39 PLUs compared to the 48PLUs to construct the CD acoustic models in this paper.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.24 no.5
• /
• pp.839-850
• /
• 2014

As the social and financial damages caused by APT attack such as 3.20 cyber terror are increased, the technical solution against APT attack is required. It is, however, difficult to protect APT attack with existing security equipments because the attack use a zero-day malware persistingly. In this paper, we propose a host based anomaly detection method to overcome the limitation of the conventional signature-based intrusion detection system. First, we defined 39 features to identify between normal and abnormal behavior, and then collected 8.7 million feature data set that are occurred during running both malware and normal executable file. Further, each process is represented as 83-dimensional vector that profiles the frequency of appearance of features. the vector also includes the frequency of features generated in the child processes of each process. Therefore, it is possible to represent the whole behavior information of the process while the process is running. In the experimental results which is applying C4.5 decision tree algorithm, we have confirmed 2.0% and 5.8% for the false positive and the false negative, respectively.

• Journal of KIISE
• /
• v.42 no.5
• /
• pp.558-565
• /
• 2015

Recently, the number of new malware and malware variants has dramatically increased. As a result, the time for analyzing malware and the efforts of malware analyzers have also increased. Therefore, malware classification helps malware analyzers decrease the overhead of malware analysis, and the classification is useful in studying the malware's genealogy. In this paper, we proposed a set of key opcode to classify the malware. In our experiments, we selected the top 10-opcode as key opcode, and the key opcode decreased the training time of a Supervised learning algorithm by 91% with preserving classification accuracy.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.4
• /
• pp.605-616
• /
• 2021

While malwares must be accurately identifiable from arbitrary programs, existing studies using classification techniques have limitations that they can only be applied to limited samples. In this work, we propose a method to utilize API call frequency to detect and classify malware families from arbitrary programs. Our proposed method defines a rule that checks whether the call frequency of a particular API exceeds the threshold, and identifies a specific family by utilizing the rate information on the corresponding rules. In this paper, decision tree algorithm is applied to define the optimal threshold that can accurately identify a particular family from the training set. The performance measurements using 4,443 samples showed 85.1% precision and 91.3% recall rate for family detection, 97.7% precision and 98.1% reproduction rate for classification, which confirms that our method works to distinguish malware families effectively.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.316-318
• /
• 2019

Recently, healthy life has become an issue in an aging society, and the number of people who have been interested in continuous health care for better life is increasing. In this paper, we implemented a personalized recommendation systm to provide convenient healthcare management for user. The PHR (Personal Health Record) of user could be stored in the server along with health related information such as lifestyle, disease, and physical condition. The users could be classified into similar clusters according to the PHR profile in order to provide healthcare contents to the users who had similar PHR profile. K-Means clustering was applied to generate clusters based on PHR profile and ACDT(Ant Colony Decision Tree) algorithm was used to provide personalised recommendation of health information stored in knowledge base. The app system developed in this paper is useful for users to perform healthcare themselves by providing information on serious diseases and lifestyle habits to be improved according to the clusters classified by PHR profile.