• Journal of Ocean Engineering and Technology
• /
• v.34 no.6
• /
• pp.442-453
• /
• 2020

Underwater color images suffer from low visibility and color cast effects caused by light attenuation by water and floating particles. This study applied single image enhancement techniques to enhance the quality of underwater images and compared their performance with real underwater images taken in Korean waters. Dark channel prior (DCP), gradient transform, image fusion, and generative adversarial networks (GAN), such as cycleGAN and underwater GAN (UGAN), were considered for single image enhancement. Their performance was evaluated in terms of underwater image quality measure, underwater color image quality evaluation, gray-world assumption, and blur metric. The DCP saturated the underwater images to a specific greenish or bluish color tone and reduced the brightness of the background signal. The gradient transform method with two transmission maps were sensitive to the light source and highlighted the region exposed to light. Although image fusion enabled reasonable color correction, the object details were lost due to the last fusion step. CycleGAN corrected overall color tone relatively well but generated artifacts in the background. UGAN showed good visual quality and obtained the highest scores against all figures of merit (FOMs) by compensating for the colors and visibility compared to the other single enhancement methods.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.221-235
• /
• 2022

Manual inspection of steel box girders on long span bridges is time-consuming and labor-intensive. The quality of inspection relies on the subjective judgements of the inspectors. This study proposes an automated approach to detect and segment cracks in high-resolution images. An end-to-end cascaded framework is proposed to first detect the existence of cracks using a deep convolutional neural network (CNN) and then segment the crack using a modified U-Net encoder-decoder architecture. A Naïve Bayes data fusion scheme is proposed to reduce the false positives and false negatives effectively. To generate the binary crack mask, first, the original images are divided into 448 × 448 overlapping image patches where these image patches are classified as cracks versus non-cracks using a deep CNN. Next, a modified U-Net is trained from scratch using only the crack patches for segmentation. A customized loss function that consists of binary cross entropy loss and the Dice loss is introduced to enhance the segmentation performance. Additionally, a Naïve Bayes fusion strategy is employed to integrate the crack score maps from different overlapping crack patches and to decide whether a pixel is crack or not. Comprehensive experiments have demonstrated that the proposed approach achieves an 81.71% mean intersection over union (mIoU) score across 5 different training/test splits, which is 7.29% higher than the baseline reference implemented with the original U-Net.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.10
• /
• pp.3302-3320
• /
• 2014

An allocation of sensing and reporting times is proposed to improve the sensing performance by scheduling them in an efficient way for cognitive radio networks with cluster-based cooperative spectrum sensing. In the conventional cooperative sensing scheme, all secondary users (SUs) detect the primary user (PU) signal to check the availability of the spectrum during a fixed sensing time slot. The sensing results from the SUs are reported to cluster heads (CHs) during the reporting time slots of the SUs and the CHs forward them to a fusion center (FC) during the reporting time slots of the CHs through the common control channels for the global decision, respectively. However, the delivery of the local decision from SUs and CHs to a CH and FC requires a time which does not contribute to the performance of spectrum sensing and system throughput. In this paper, a super-allocation technique, which merges reporting time slots of SUs and CHs to sensing time slots of SUs by re-scheduling the reporting time slots, has been proposed to sense the spectrum more accurately. In this regard, SUs in each cluster can obtain a longer sensing duration depending on their reporting order and their clusters except for the first SU belonged to the first cluster. The proposed scheme, therefore, can achieve better sensing performance under -28 dB to -10 dB environments and will thus reduce reporting overhead.

• Journal of Communications and Networks
• /
• v.17 no.6
• /
• pp.568-581
• /
• 2015

Predicting locations of users with portable devices such as IP phones, smart-phones, iPads and iPods in public wireless local area networks (WLANs) plays a crucial role in location management and network resource allocation. Many techniques in machine learning and data mining, such as sequential pattern mining and clustering, have been widely used. However, these approaches have two deficiencies. First, because they are based on profiles of individual mobility behaviors, a sequential pattern technique may fail to predict new users or users with movement on novel paths. Second, using similar mobility behaviors in a cluster for predicting the movement of users may cause significant degradation in accuracy owing to indistinguishable regular movement and random movement. In this paper, we propose a novel fusion technique that utilizes mobility rules discovered from multiple similar users by combining clustering and sequential pattern mining. The proposed technique with two algorithms, named the clustering-based-sequential-pattern-mining (CSPM) and sequential-pattern-mining-based-clustering (SPMC), can deal with the lack of information in a personal profile and avoid some noise due to random movements by users. Experimental results show that our approach outperforms existing approaches in terms of efficiency and prediction accuracy.

• Journal of Information Processing Systems
• /
• v.17 no.3
• /
• pp.556-570
• /
• 2021

The existing video expression recognition methods mainly focus on the spatial feature extraction of video expression images, but tend to ignore the dynamic features of video sequences. To solve this problem, a multi-mode convolution neural network method is proposed to effectively improve the performance of facial expression recognition in video. Firstly, OpenFace 2.0 is used to detect face images in video, and two deep convolution neural networks are used to extract spatiotemporal expression features. Furthermore, spatial convolution neural network is used to extract the spatial information features of each static expression image, and the dynamic information feature is extracted from the optical flow information of multiple expression images based on temporal convolution neural network. Then, the spatiotemporal features learned by the two deep convolution neural networks are fused by multiplication. Finally, the fused features are input into support vector machine to realize the facial expression classification. Experimental results show that the recognition accuracy of the proposed method can reach 64.57% and 60.89%, respectively on RML and Baum-ls datasets. It is better than that of other contrast methods.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.5A
• /
• pp.429-435
• /
• 2009

Cooperative spectrum sensing allows secondary users of a cognitive radio(CR) network to collaborate to determine whether a primary user occupies the spectrum of interest or not. It usually performs spectrum sensing by combining the individual decisions of each second user into a final one and the k-out-of-n fusion rule is a general approach for decision fusion. This rule declares that the spectrum is occupied only when the decisions from more than k-1 secondary users indicate the presence of a primary user. In this paper, we analyze a cooperative spectrum sensing scheme with the fusion rule under the constraint that its detection probability is maintained to be no less than a given level and its numerical results for the case of a CR network with 10 secondary users.

• Journal of information and communication convergence engineering
• /
• v.14 no.1
• /
• pp.1-8
• /
• 2016

Spectrum sensing in cognitive radio networks allows secondary users to sense the unused spectrum without causing interference to primary users. Cognitive radio requires more accurate sensing results from unused portions of the spectrum. Accurate spectrum sensing techniques can reduce the probability of false alarms and misdetection. In this paper, a two-stage spectrum sensing scheme is proposed for cooperative spectrum sensing in cognitive radio networks. In the first stage, spectrum sensing is executed for each secondary user using energy detection based on double adaptive thresholds to determine the spectrum condition. If the energy value lies between two thresholds, a fuzzy logic scheme is applied to determine the channel conditions more accurately. In the second stage, a fusion center combines the results of each secondary user and uses a fuzzy logic scheme for combining all decisions. The simulation results show that the proposed scheme provides increased sensing accuracy by about 20% in some cases.

• Journal of Korea Multimedia Society
• /
• v.13 no.6
• /
• pp.890-900
• /
• 2010

The Bayesian networks methods provide an efficient tool for performing information fusion and decision making under conditions of uncertainty. This paper proposes Bayes estimators for the system effectiveness in energy saving of the wireless sensor networks by use of the Bayesian method under the non-informative prior knowledge about means of active and sleep times based on time frames of sensor nodes in a wireless sensor network. And then, we conduct a case study on some Bayesian estimation models for the system energy saving effectiveness of a wireless sensor network, and evaluate and compare the performance of proposed Bayesian estimates of the system effectiveness in energy saving of the wireless sensor network. In the case study, we have recognized that the proposed Bayesian system energy saving effectiveness estimators are excellent to adapt in evaluation of energy efficiency using non-informative prior knowledge from previous experience with robustness according to given values of parameters.

• Proceedings of the KIEE Conference
• /
• 2000.11d
• /
• pp.800-802
• /
• 2000

In this paper, we propose the Self-Organizing Networks(SON) based on competitive Fuzzy Polynomial Neuron(FPN) for the optimal design of nonlinear process system. The SON architectures consist of layers with activation nodes based on fuzzy inference rules. Here each activation node is presented as FPN which includes either the simplified or regression Polynomial fuzzy inference rules. The proposed SON is a network resulting from the fusion of the Polynomial Neural Networks(PNN) and a fuzzy inference system. The conclusion part of the rules, especially the regression polynomial uses several types of high-order polynomials such as liner, quadratic and modified quadratic. As the premise part of the rules, both triangular and Gaussian-like membership functions are studied. Chaotic time series data used to evaluate the performance of our proposed model.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.456-459
• /
• 2009

Sensor network has been a hot research topic for the past decade and has moved its phase into using multimedia sensors such as cameras and microphones [1]. Combining many types of sensor data will lead to more accurate and precise information of the environment. However, the use of sensor network data is still limited to closed circumstances. Thus, in this paper, we propose a web-service based framework to deploy multimedia sensor networks. In order to unify different types of sensor data and also to support heterogeneous client applications, we used ROA (Resource Oriented Architecture [2]).