• The Journal of the Acoustical Society of Korea
• /
• v.23 no.7
• /
• pp.532-539
• /
• 2004

In this Paper, we propose a content-based music information retrieval (MIR) system base on the query-by-example (QBE) method. The proposed system is implemented to retrieve queried music from a dataset where 60 music samples were collected for each of the four genres in Classical, Hiphop. Jazz. and Reck. resulting in 240 music files in database. From each query music signal, the system extracts 60 dimensional feature vectors including spectral centroid. rolloff. flux base on STFT and also the LPC. MFCC and Beat information. and retrieves queried music from a trained database set using Euclidean distance measure. In order to choose optimum features from the 60 dimension feature vectors, SFS method is applied to draw 10 dimension optimum features and these are used for the Proposed system. From the experimental result. we can verify the superior performance of the proposed system that provides success rate of 84% in Hit Rate and 0.63 in MRR which means near 10% improvements over the previous methods. Additional experiments regarding system Performance to random query Patterns (or portions) and query lengths have been investigated and a serious instability problem of system Performance is Pointed out.

• Korean Journal of Remote Sensing
• /
• v.21 no.6
• /
• pp.505-516
• /
• 2005

The Communications, Oceanography and Meteorology Satellite(COMS) will be launched in 2008. Ground processing for COMS includes the process of automatic image navigation. Image navigation requires landmark detection by matching COMS images against landmark chips. For automatic image navigation, a matching must be performed automatically However, if matching results contain errors, the accuracy of Image navigation deteriorates. To overcome this problem, we propose use of a robust estimation technique called Random Sample Consensus (RANSAC) to automatically detect erroneous matching. We tested GOES-9 satellite images with 30 landmark chips that were extracted from the world shoreline database. After matching, mismatch results were detected automatically by RANSAC. All mismatches were detected correctly by RANSAC with a threshold value of 2.5 pixels.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.11
• /
• pp.33-40
• /
• 2021

Due to advanced complex strategies, the complexity of information that a commander must analyze is increasing. An intelligent service that can analyze battlefield is needed for the commander's timely judgment. This service consists of extracting knowledge from battlefield information, building a knowledge base, and analyzing the battlefield information from the knowledge base. This paper extract information similar to an input query by embedding the knowledge base built in the 2^nd step. The transformation model is needed to generate the embedded knowledge base and uses the random-walk algorithm. The transformed information is embedding using Word2Vec, and Similar information is extracted through cosine similarity. In this paper, 980 sentences are generated from the open knowledge base and embedded as a 100-dimensional vector and it was confirmed that similar entities were extracted through cosine similarity.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.2
• /
• pp.61-68
• /
• 2021

Recently, various technologies that use machine learning to classify malicious code have been studied. In order to enhance the effectiveness of machine learning, it is most important to extract properties to identify malicious codes and normal binaries. In this paper, we propose a feature extraction method for use in machine learning using recursive methods. The proposed method selects the final feature using recursive methods for individual features to maximize the performance of machine learning. In detail, we use the method of extracting the best performing features among individual feature at each stage, and then combining the extracted features. We extract features with the proposed method and apply them to machine learning algorithms such as Decision Tree, SVM, Random Forest, and KNN, to validate that machine learning performance improves as the steps continue.

• Journal of Korean Society on Water Environment
• /
• v.39 no.1
• /
• pp.46-60
• /
• 2023

Climate change causes fluctuations in water quality in the aquatic environment, which can cause changes in water circulation patterns and severe adverse effects on aquatic ecosystems in the future. Therefore, research is needed to predict and respond to water quality changes caused by climate change in advance. In this study, we tried to predict the dissolved oxygen (DO), chlorophyll-a, and turbidity of the Paldang reservoir for about two weeks using long short-term memory (LSTM) and gated recurrent units (GRU), which are deep learning algorithms based on recurrent neural networks. The model was built based on real-time water quality data and meteorological data. The observation period was set from July to September in the summer of 2021 (Period 1) and from March to May in the spring of 2022 (Period 2). We tried to select an algorithm with optimal predictive power for each water quality parameter. In addition, to improve the predictive power of the model, an important variable extraction technique using random forest was used to select only the important variables as input variables. In both Periods 1 and 2, the predictive power after extracting important variables was further improved. Except for DO in Period 2, GRU was selected as the best model in all water quality parameters. This methodology can be useful for preventive water quality management by identifying the variability of water quality in advance and predicting water quality in a short period.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.1
• /
• pp.11-19
• /
• 2024

Multi-agent systems can be utilized in various real-world cooperative environments such as battlefield engagements and unmanned transport vehicles. In the context of battlefield engagements, where dense reward design faces challenges due to limited domain knowledge, it is crucial to consider situations that are learned through explicit sparse rewards. This paper explores the collaborative potential among allied agents in a battlefield scenario. Utilizing the Multi-Robot Warehouse Environment(RWARE) as a sparse reward environment, we define analogous problems and establish evaluation criteria. Constructing a learning environment with the QMIX algorithm from the reinforcement learning library Ray RLlib, we enhance the Agent Network of QMIX and integrate Random Network Distillation(RND). This enables the extraction of patterns and temporal features from partial observations of agents, confirming the potential for improving the acquisition of sparse reward experiences through intrinsic rewards.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.6
• /
• pp.1478-1499
• /
• 2024

Coronavirus disease (COVID-19) is an infectious disease caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus. COVID-19 become an active epidemic disease due to its spread around the globe. The main causes of the spread are through interaction and transmission of the droplets through coughing and sneezing. The spread can be minimized by isolating the susceptible patients. However, it necessitates remote monitoring to check the breathing issues of the patient remotely to minimize the interactions for spread minimization. Thus, in this article, we offer a wearable-IoTs-centered framework for remote monitoring and recognition of the breathing pattern and abnormal breath detection for timely providing the proper oxygen level required. We propose wearable sensors accelerometer and gyroscope-based breathing time-series data acquisition, temporal features extraction, and machine learning algorithms for pattern detection and abnormality identification. The sensors provide the data through Bluetooth and receive it at the server for further processing and recognition. We collect the six breathing patterns from the twenty subjects and each pattern is recorded for about five minutes. We match prediction accuracies of all machine learning models under study (i.e. Random forest, Gradient boosting tree, Decision tree, and K-nearest neighbor. Our results show that normal breathing and Bradypnea are the most correctly recognized breathing patterns. However, in some cases, algorithm recognizes kussmaul well also. Collectively, the classification outcomes of Random Forest and Gradient Boost Trees are better than the other two algorithms.

• The korean journal of orthodontics
• /
• v.47 no.6
• /
• pp.401-413
• /
• 2017

Objective: The aim of this systematic review was to assess the occlusal outcome and duration of fixed orthodontic therapy from clinical trials in humans with the Objective Grading System (OGS) proposed by the American Board of Orthodontics. Methods: Nine databases were searched up to October 2016 for prospective/retrospective clinical trials assessing the outcomes of orthodontic therapy with fixed appliances. After duplicate study selection, data extraction, and risk of bias assessment according to the Cochrane guidelines, random-effects meta-analyses of the mean OGS score and treatment duration were performed and 95% confidence intervals (CIs) were calculated. Results: A total of 34 relevant clinical trials including 6,207 patients (40% male, 60% female; average age, 18.4 years) were identified. The average OGS score after treatment was 27.9 points (95% CI, 25.3-30.6 points), while the average treatment duration was 24.9 months (95% CI, 24.6-25.1 months). There was no significant association between occlusal outcome and treatment duration, while considerable heterogeneity was identified. In addition, orthodontic treatment involving extraction of four premolars appeared to have an important effect on both outcomes and duration of treatment. Finally, only 10 (39%) of the identified studies matched compared groups by initial malocclusion severity, although meta-epidemiological evidence suggested that matching may have significantly influenced their results. Conclusions: The findings from this systematic review suggest that the occlusal outcomes of fixed appliance treatment vary considerably, with no significant association between treatment outcomes and duration. Prospective matched clinical studies that use the OGS tool are needed to compare the effectiveness of orthodontic appliances.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.5
• /
• pp.136-144
• /
• 2010

Two types of informations are used for content-based video copy detection: spatial information and temporal information. The spatial information means content-based image fingerprint. This image fingerprint must have following characteristic. First, Extraction is simple. Second, pairwise independence for random selected two images. At last, Robust for modifications. This paper proposed image fingerprint method for contents based video copy detection. Proposed method's extraction speed is fast because this method's using block average, first order differentiation and second order differentiation that can be calculated add and minus operation. And it has pairwise independence and robust against modifications. Also, proposed method feature makes binary by comparisons and using coarse to fine structure, so it's matching speed is fast. Proposed method is verified by modified image that modified by VCE7's experimental conditions in MPEG7.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.1020-1042
• /
• 2019

Reversible data hiding in encrypted images (RDHEI) provides some real-time cloud applications; i.e. the cloud, acting as a data-hider, automatically embeds timestamp in the encrypted image uploaded by a content owner. Many existing methods of RDHEI only satisfy user privacy in which the data-hider does not know the original image, but leaks owner privacy in which the receiver can obtains the original image by decryption and extraction. In the literature, the method of Zhang et al. is the one providing weak content-owner privacy in which the content-owner and data-hider have to share a data-hiding key. In this paper, we take care of the stronger notion, called strong content-owner privacy, and achieve it by presenting a new reversible data hiding in encrypted images. In the proposed method, image decryption and message extraction are separately controlled by different types of keys, and thus such functionalities are decoupled to solve the privacy problem. At the technique level, the original image is segmented along a Hilbert filling curve. To keep image privacy, segments are transformed into an encrypted image by using random permutation. The encrypted image does not reveal significant information about the original one. Data embedment can be realized by using pixel histogram-style hiding, since this property, can be preserved before or after encryption. The proposed method is a modular method to compile some specific reversible data hiding to those in encrypted image with content owner privacy. Finally, our experimental results show that the image quality is 50.85dB when the averaged payload is 0.12bpp.