• Journal of the Korea Society of Computer and Information
• /
• v.18 no.6
• /
• pp.21-28
• /
• 2013

This paper proposes an effective fire detection approach that includes the following multiple heterogeneous algorithms: moving region detection using grey level histograms, color segmentation using fuzzy c-means clustering (FCM), feature extraction using a grey level co-occurrence matrix (GLCM), and fire classification using support vector machine (SVM). The proposed approach determines the optimal threshold values based on grey level histograms in order to detect moving regions, and then performs color segmentation in the CIE LAB color space by applying the FCM. These steps help to specify candidate regions of fire. We then extract features of fire using the GLCM and these features are used as inputs of SVM to classify fire or non-fire. We evaluate the proposed approach by comparing it with two state-of-the-art fire detection algorithms in terms of the fire detection rate (or percentages of true positive, PTP) and the false fire detection rate (or percentages of true negative, PTN). Experimental results indicated that the proposed approach outperformed conventional fire detection algorithms by yielding 97.94% for PTP and 4.63% for PTN, respectively.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.11
• /
• pp.1-11
• /
• 2023

Breast cancer is the disease that affects women the most worldwide. Due to the development of computer technology, the efficiency of machine learning has increased, and thus plays an important role in cancer detection and diagnosis. Deep learning is a field of machine learning technology based on an artificial neural network, and its performance has been rapidly improved in recent years, and its application range is expanding. In this paper, we propose a DNN-SVM hybrid model that combines the structure of a deep neural network (DNN) based on transfer learning and a support vector machine (SVM) for breast cancer classification. The transfer learning-based proposed model is effective for small training data, has a fast learning speed, and can improve model performance by combining all the advantages of a single model, that is, DNN and SVM. To evaluate the performance of the proposed DNN-SVM Hybrid model, the performance test results with WOBC and WDBC breast cancer data provided by the UCI machine learning repository showed that the proposed model is superior to single models such as logistic regression, DNN, and SVM, and ensemble models such as random forest in various performance measures.

• Journal of Broadcast Engineering
• /
• v.16 no.6
• /
• pp.1058-1068
• /
• 2011

Video FRUC (Frame Rate Up Conversion) is one of the main issues that have arisen in recent years with the explosive growth of video sources and display formats in consumer electronics. Most advanced FRUC algorithms adopt an efficient motion interpolation technique to determine the motion vector field of interpolated frames. But, in some application areas such as post processing in receiver side, it is necessary to evaluate how well the MCI (Motion Compensated Interpolation) frame was reconstructed. In order to achieve this aim, first, this paper introduces some cost functions to estimate the reliability of a block in the MCI frame. Then, by using these functions, this paper proposes two distortion estimation models for evaluating how much noise was produced in the MCI frame. Through computer simulations, it is shown that the proposed estimation methods perform effectively in estimating the noises of the MCI frame.

• Journal of the Korea Computer Graphics Society
• /
• v.14 no.1
• /
• pp.1-10
• /
• 2008

In this paper, we present a novel method for creating a hand-painted painterly animation, starting from a video input. One of the most important aspects in painterly animation is to maintain the temporal coherence of brush strokes between frames, which plays a vital role to warrant a smooth transition between frames. Our unique utilization of motion areas enables users to produce a smooth movement of brush strokes. The motion areas are the parts where objects move between frames and they are categorized in two main types. A strong motion area is the part where the movement of real edges and hidden edges is determined by the motion vector between frames. The real edge is the outline of an object and the hidden edge is the boundary to represent the direction of a grain of intensity in the areas with gradations. A weak motion area is the remainder after subtracting the strong motion area from the entire motion area. Temporally coherent painterly animation is achieved by re-painting the brush strokes on the canvas using two motion areas, resulting in a natural and hand-painted appearance.

• Journal of Intelligence and Information Systems
• /
• v.10 no.2
• /
• pp.79-89
• /
• 2004

Since the amount of E-mail messages has increased , we need a new technique for efficient e-mail classification. E-mail classifications are grouped into two classes: binary classification, multi-classification. The current binary classification methods are mostly spm mail classification methods which are based on rule driven, bayesian, SVM, etc. The current multi- classification methods are based on clustering which groups e-mails by similarity. In this paper, we propose a novel method for e-mail classification. It combines the automatic category generation method based on the vector model and the dynamic category hierarchy construction method. This method can multi-classify e-mail automatically and manage a large amount of e-mail efficiently. In addition, this method increases the search accuracy by dynamic reclassification of e-mails.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.11
• /
• pp.2784-2799
• /
• 2012

Biological data have been increased exponentially in recent years, and analyzing these data using data mining tools has become one of the major issues in the bioinformatics research community. This paper focuses on the protein construction process in higher organisms where the deoxyribonucleic acid, or DNA, sequence is filtered. In the process, "unmeaningful" DNA sub-sequences (called introns) are removed, and their meaningful counterparts (called exons) are retained. Accurate recognition of the boundaries between these two classes of sub-sequences, however, is known to be a difficult problem. Conventional approaches for recognizing these boundaries have sought for solely enhancing machine learning techniques, while inherent nature of the data themselves has been overlooked. In this paper we present an approach which makes use of the data attributes inherent to species in order to increase the accuracy of the boundary recognition. For experimentation, we have taken the data sets for four different species from the University of California Santa Cruz (UCSC) data repository, divided the data sets based on the species types, then trained a preprocessed version of the data sets on neural network(NN)-based and support vector machine(SVM)-based classifiers. As a result, we have observed that each species has its own specific features related to the splice sites, and that it implies there are related distances among species. To conclude, dividing the training data set based on species would increase the accuracy of predicting splicing junction and propose new insight to the biological research.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.1
• /
• pp.321-340
• /
• 2016

The Compressive Video Sensing (CVS) is a useful technology for wireless systems requiring simple encoders but handling more complex decoders, and its rate-distortion performance is highly affected by the quantization of measurements and reconstruction of video frame, which motivates us to presents the Space-Time Quantization (ST-Q) and Motion-Aligned Reconstruction (MA-R) in this paper to both improve the performance of CVS system. The ST-Q removes the space-time redundancy in the measurement vector to reduce the amount of bits required to encode the video frame, and it also guarantees a low quantization error due to the fact that the high frequency of small values close to zero in the predictive residuals limits the intensity of quantizing noise. The MA-R constructs the Multi-Hypothesis (MH) matrix by selecting the temporal neighbors along the motion trajectory of current to-be-reconstructed block to improve the accuracy of prediction, and besides it reduces the computational complexity of motion estimation by the extraction of static area and 3-D Recursive Search (3DRS). Extensive experiments validate that the significant improvements is achieved by ST-Q in the rate-distortion as compared with the existing quantization methods, and the MA-R improves both the objective and the subjective quality of the reconstructed video frame. Combined with ST-Q and MA-R, the CVS system obtains a significant rate-distortion performance gain when compared with the existing CS-based video codecs.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.1
• /
• pp.116-122
• /
• 2010

As the importance of HCI(Human-Computer Interface) caused by dramatically developed computer technology is getting high, the requirement for the design of human friendly systems is also getting high. First of all, the personality and Emotional factor should be considered for implementing more human friendly systems. Many studies on Knowledge, Emotion and personality have been made, but the combined methods connecting these three factors is not so many investigated yet. It is known that memorizing process includes not only knowledge but also the emotion and the emotion state has much effects on the process of reasoning and decision making step. Accordingly, for implementing more human friendly efficient sophisticated intelligent system, the system considering these three factors should be modeled and designed. In this paper, knowledge-emotion reaction model was designed. Five types are defined for representing the personality and emotion reaction mechanism calculating emotion vector based on the extracted Thought threads by Type matching selection was proposed. This system is applied to the virtual memory and its emotional reactions are simulated.

• Proceedings of the Korean Magnestics Society Conference
• /
• 2011.12a
• /
• pp.7-8
• /
• 2011

Although yttrium iron garnet (YIG) has provided a great vehicle for the study of spin waves in the past, associated difficulties in film deposition and device fabrication using YIG had limited the applicability of spin waves to practical devices. However, microfabrication techniques have made it possible to characterize both the resonant as well as the travelling characteristics of spin waves in permalloy (Py). A variety of methods have been used for measuring spin waves, including Brillouin light scattering (BLS), magneto-optic Kerr effect (MOKE), vector network analyzer ferromagnetic resonance (VNA-FMR), and pulse inductive microwave magnetometry (PIMM). PIMM is one of the most preferred methodologies of measuring travelling spin waves. In this method, an electrical impulse is applied at one of two coplanar waveguides patterned on top of oxide-insulated Py, producing a local disturbance in the magnetization of the Py. The resulting disturbance travels down the Py in the form of waves, and is inductively picked up by the other coplanar waveguide. We investigate the effect of the pulse width of excitation pulses on the generated spin wave packets using both experimental results and micromagnetic simulations. We show that spin wave packets generated from electrical pulses are a superposition of two separate spin wave packets, one generated from the rising edge and the other from the falling edge, which interfere either constructively or destructively with one another, depending upon the magnitude and direction of the field bias conditions. A method of spin wave amplitude modulation is also presented by the linear superposition of spin waves. We use interfering spin waves resulting from two closely spaced voltage impulses for the modulation of the magnitude of the resultant spin wave packets.

• Journal of Communications and Networks
• /
• v.9 no.3
• /
• pp.296-311
• /
• 2007

Mobile multi-robot teams are useful in many critical applications such as search and rescue. Explicit communication among robots in such mobile multi-robot teams is useful for the coordination of such teams as well as exchanging data. Since many applications for mobile robots involve scenarios in which communication infrastructure may be damaged or unavailable, mobile robot teams frequently need to communicate with each other via ad hoc networking. In such scenarios, low-overhead and energy-efficient routing protocols for delivering messages among robots are a key requirement. Two important primitives for communication are essential for enabling a wide variety of mobile robot applications. First, unicast communication (between two robots) needs to be provided to enable coordination and data exchange. Second, in many applications, group communication is required for flexible control, organization, and management of the mobile robots. Multicast provides a bandwidth-efficient communication method between a source and a group of robots. In this paper, we first propose and evaluate two unicast routing protocols tailored for use in ad hoc networks formed by mobile multi-robot teams: Mobile robot distance vector (MRDV) and mobile robot source routing (MRSR). Both protocols exploit the unique mobility characteristics of mobile robot networks to perform efficient routing. Our simulation study show that both MRDV and MRSR incur lower overhead while operating in mobile robot networks when compared to traditional mobile ad hoc network routing protocols such as DSR and AODV. We then propose and evaluate an efficient multicast protocol mobile robot mesh multicast (MRMM) for deployment in mobile robot networks. MRMM exploits the fact that mobile robots know what velocity they are instructed to move at and for what distance in building a long lifetime sparse mesh for group communication that is more efficient. Our results show that MRMM provides an efficient group communication mechanism that can potentially be used in many mobile robot application scenarios.