• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.3
• /
• pp.117-122
• /
• 2023

Gaze estimation, which automatically recognizes where a user is currently staring, and object detection based on estimated gaze point, can be a more accurate and efficient way to understand human visual behavior. in this paper, we propose a method to detect the objects within the region of interest around the gaze point. Specifically, after estimating the 3D gaze point, a region of interest based on the estimated gaze point is created to ensure that object detection occurs only within the region of interest. In our experiments, we compared the performance of general object detection, and the proposed object detection based on region of interest, and found that the processing time per frame was 1.4ms and 1.1ms, respectively, indicating that the proposed method was faster in terms of processing speed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.12
• /
• pp.3242-3265
• /
• 2023

Ensuring reliability of a machinery system involve the prediction of remaining useful life (RUL). In most RUL prediction approaches, noise is always considered for removal. Nevertheless, noise could be properly utilized to enhance the prediction capabilities. In this paper, we proposed a novel RUL prediction approach based on noise injection and a Kalman filter ensemble of modified bagging predictors. Firstly, we proposed a new method to insert Gaussian noises into both observation and feature spaces of an original training dataset, named GN-DAFC. Secondly, we developed a modified bagging method based on Kalman filter averaging, named KBAG. Then, we developed a new ensemble method which is a Kalman filter ensemble of KBAGs, named DKBAG. Finally, we proposed a novel RUL prediction approach GN-DAFC-DKBAG in which the optimal noise-injected training dataset was determined by a GN-DAFC-based searching strategy and then inputted to a DKBAG model. Our approach is validated on the NASA C-MAPSS dataset of aero-engines. Experimental results show that our approach achieves significantly better performance than a traditional Kalman filter ensemble of single learning models (KESLM) and the original DKBAG approaches. We also found that the optimal noise-injected data could improve the prediction performance of both KESLM and DKBAG. We further compare our approach with two advanced ensemble approaches, and the results indicate that the former also has better performance than the latters. Thus, our approach of combining optimal noise injection and DKBAG provides an effective solution for RUL estimation of machinery systems.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.1
• /
• pp.144-150
• /
• 2017

Recently, deep learning is used for intelligent processing and accuracy improvement of data. It is formed calculation model composed of multi data processing layer that train the data representation through an abstraction of the various levels. A category of deep learning, convolution neural network is utilized in various research fields, which are human pose estimation, face recognition, image classification, speech recognition. When using the deep layer and lots of class, CNN that show a good performance on image classification obtain higher classification rate but occur the overfitting problem, when using a few data. So, we design the training network based on convolution neural network and trained our image data set for object classification in few class problem. The experiment show the higher classification rate of 7.06% in average than the previous networks designed to classify the object in 1000 class problem.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.5
• /
• pp.49-57
• /
• 2012

In P2P streaming management, peer's churning and finding efficient topology architecture optimization algorithm that reduces streaming delay is important. This paper studies a topology optimization algorithm based on the P2P streaming using peer's link information. The proposed algorithm is based on the estimation of peer's upload bandwidth using peer's link information on mesh-network. The existing algorithm that uses the information of connected links is efficient to reduce message overload in the point of resource management. But it has a risk of making unreliable topology not considering upload bandwidth. And when some network error occurs in a server-closer-peer, it may make the topology worse. In this paper we propose an algorithm that makes up for the weak point of the existing algorithm. We compare the existing algorithm with the proposed algorithm using test data and analyze each simulation result.

• International Journal of Computer Science & Network Security
• /
• v.24 no.2
• /
• pp.101-112
• /
• 2024

Telugu language is considered as fourth most used language in India especially in the regions of Andhra Pradesh, Telangana, Karnataka etc. In international recognized countries also, Telugu is widely growing spoken language. This language comprises of different dependent and independent vowels, consonants and digits. In this aspect, the enhancement of Telugu Handwritten Character Recognition (HCR) has not been propagated. HCR is a neural network technique of converting a documented image to edited text one which can be used for many other applications. This reduces time and effort without starting over from the beginning every time. In this work, a Unicode based Handwritten Character Recognition(U-HCR) is developed for translating the handwritten Telugu characters into English language. With the use of Centre of Gravity (CG) in our model we can easily divide a compound character into individual character with the help of Unicode values. For training this model, we have used both online and offline Telugu character datasets. To extract the features in the scanned image we used convolutional neural network along with Machine Learning classifiers like Random Forest and Support Vector Machine. Stochastic Gradient Descent (SGD), Root Mean Square Propagation (RMS-P) and Adaptative Moment Estimation (ADAM)optimizers are used in this work to enhance the performance of U-HCR and to reduce the loss function value. This loss value reduction can be possible with optimizers by using CNN. In both online and offline datasets, proposed model showed promising results by maintaining the accuracies with 90.28% for SGD, 96.97% for RMS-P and 93.57% for ADAM respectively.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.3
• /
• pp.11-20
• /
• 2024

Among the generative models in Artificial Intelligence (AI), especially Generative Adversarial Network (GAN) has been successful in various applications such as image processing, density estimation, and style transfer. While the GAN models including Conditional GAN (CGAN), CycleGAN, BigGAN, have been extended and improved, researchers face challenges in real-world applications in specific domains such as disaster simulation, healthcare, and urban planning due to data scarcity and unstable learning causing Image distortion. This paper proposes a new progressive learning methodology called Progressive Step Training (PST) based on the Auxiliary Classifier GAN (ACGAN) that discriminates class labels, leveraging the progressive learning approach of the Progressive Growing of GAN (PGGAN). The PST model achieves 70.82% faster stabilization, 51.3% lower standard deviation, stable convergence of loss values in the later high resolution stages, and a 94.6% faster loss reduction compared to conventional methods.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.8
• /
• pp.23-32
• /
• 2024

NVS (Novel View Synthesis) is a field in computer vision that reconstructs new views of a scene from a set of input views. Real-time rendering and high performance are essential for NVS technology to be effectively utilized in various applications. Recently, 3D-GS (3D Gaussian Splatting) has gained popularity due to its faster training and inference times compared to those of NeRF (Neural Radiance Fields)-based methodologies. However, since 3D-GS reconstructs a 3D (Three-Dimensional) scene by splitting and cloning (Density Control) Gaussian points, the number of Gaussian points continuously increases, causing the model to become heavier as training progresses. To address this issue, we propose two methodologies: 1) Gaussian blending, an improved density control methodology that removes unnecessary Gaussian points, and 2) a performance enhancement methodology using a depth estimation model to minimize the loss in representation caused by the blending of Gaussian points. Experiments on the Tanks and Temples Dataset show that the proposed methodologies reduce the number of Gaussian points by up to 4% while maintaining performance.

• Journal of Digital Contents Society
• /
• v.19 no.4
• /
• pp.789-799
• /
• 2018

This article presents machine learning based approach on Big data to analyzing time series data for anomaly detection in such industrial complex system. Long Short-Term Memory (LSTM) network have been demonstrated to be improved version of RNN and have become a useful aid for many tasks. This LSTM based model learn the higher level temporal features as well as temporal pattern, then such predictor is used to prediction stage to estimate future data. The prediction error is the difference between predicted output made by predictor and actual in-coming values. An error-distribution estimation model is built using a Gaussian distribution to calculate the anomaly in the score of the observation. In this manner, we move from the concept of a single anomaly to the idea of the collective anomaly. This work can assist the monitoring and management of Smart Factory in minimizing failure and improving manufacturing quality.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.4 no.6
• /
• pp.1098-1115
• /
• 2010

An inseparable challenge associated with every random access network is the design of an efficient Collision Resolution Algorithm (CRA), since collisions cannot be completely avoided in such network. To maximize the collision resolution efficiency of a popular CRA, namely Binary Exponential Backoff (BEB), we propose a reactive backoff algorithm. The proposed backoff algorithm is reactive in the sense that it updates the contention window based on the previously selected backoff value in the failed contention stage to avoid a typical type of collision, referred as cross-collision. Cross-collision would occur if the contention slot pointed by the currently selected backoff value appeared to be present in the overlapped portion of the adjacent (the previous and the current) windows. The proposed reactive algorithm contributes to significant performance improvements in the network since it offers a supplementary feature of Cross Collision Exclusion (XCE) and also retains the legacy collision mitigation features. We formulate a Markovian model to emulate the characteristics of the proposed algorithm. Based on the solution of the model, we then estimate the throughput and delay performances of WLAN following the signaling mechanisms of the Distributed Coordination Function (DCF) considering IEEE 802.11b system parameters. We validate the accuracy of the analytical performance estimation framework by comparing the analytically obtained results with the results that we obtain from the simulation experiments performed in ns-2. Through the rigorous analysis, based on the validated model, we show that the proposed reactive cross collision exclusionary backoff algorithm significantly enhances the throughput and reduces the average packet delay in the network.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.11
• /
• pp.149-156
• /
• 2021

Among various implementation techniques of recommender systems, collaborative filtering selects nearest neighbors with high similarity based on past rating history, recommends products preferred by them, and has been successfully utilized by many commercial sites. Accurate estimation of similarity is an important factor that determines performance of the system. Various similarity measures have been developed, which are mostly based on integrating traditional similarity measures and several indices already developed. This study suggests a similarity measure of a novel approach. It separates the common rating area between two users by the magnitude of ratings, estimates similarity for each subarea, and integrates them with weights. This enables identifying similar subareas and reflecting it onto a final similarity value. Performance evaluation using two open datasets is conducted, resulting in that the proposed outperforms the previous one in terms of prediction accuracy, rank accuracy, and mean average precision especially with the dense dataset. The proposed similarity measure is expected to be utilized in various commercial systems for recommending products more suited to user preference.