• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 D
• /
• pp.2380-2382
• /
• 2000

Fuzzy system which are based on membership functions and rules, can control nonlinear, uncertian, complex system well. However, Fuzzy controller has problems: It is difficult to design a stable for amateur. To update the then-part membership functions of the fuzzy controller can be designed using the error back-propagation algorithm to be minimized error. Then we could be optimized the system choosing a good performance index. The proposed fuzzy controller based on neural network is applied to control an inverted pendulum for demonstration of the robustness of proposed methodology.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2015년도 추계학술대회
• /
• pp.54-55
• /
• 2015

In this paper, we propose a method pursuing robustness in ad hoc network system when the CSI of interferers is unavailable. The non-parametric linear minimum mean square error filter is exploited to achieve large fraction of the MMSE filter transmission capacity employing the perfect covariance matrix information. From the numerical results, we show that the proposed scheme brings substantial transmission capacity gain over conventional MMSE filter using sample covariance matrix.

• 한국자동차공학회논문집
• /
• 제1권2호
• /
• pp.49-59
• /
• 1993

A new signal processing technique is applied to four-cylinder spark and compression ignition engines for the diagnosis of power faults inside the cylinders. This technique utilizes two-sided directional power spectra(예S) of complex vibration signals measured from engine blocks as the patterns for engine cylinder power faults. The dPSs feature that they give not only the frequency contents but also the directivity of the engine block motion. For the automatic detection/diagnosis of cylinder power faults, pattern recognition method using multi-layer neural networks is employed. Experimental results show that the sucess rate for diagnosis of cylinder power faults using dPSs is higher than that using the conventional one-sided power spectra. The proposed technique is also tested to check the robustness to the sensor position and the engine rotational speed.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2019년도 학술발표회
• /
• pp.159-159
• /
• 2019

In this study, the simulation of sediment deposition at Sangju weir reservoir, South Korea, was carried out using artificial neural networks. The ANNs have typically been used in water resources engineering problems for their robustness and high degree of accuracy. Three basic variables namely turbid water inflow, outflow, and water stage have been used as input variables. It was found that ANNs were able to establish valid relationship between input variables and target variable of sedimentation. The R value was 0.9806, 0.9091, and 0.8758 for training, validation, and testing phase respectively. Comparative analysis was also performed to find optimum structure of ANN for sediment deposition prediction. 3-14-1 network architecture using BR algorithm outperformed all other combinations. It was concluded that ANN possess mapping capabilities for complex, non-linear phenomenon of reservoir sedimentation.

• 한국멀티미디어학회논문지
• /
• 제22권3호
• /
• pp.357-365
• /
• 2019

In this paper, we suggest the tracking method of moving multi-objects in maritime environments. The image acquisition is conducted using IR(InfraRed) camera sensors on an airborne platform. Under the circumstance of maritime, the qualities of IR images can be significantly degraded due to the clutter influence, which directly gives rise to a tracking loss problem. In order to reduce the effects from the clutters, we introduce a technical approach under Man-In-The-Loop(MITL) system for enhancing the tracking performance. To demonstrate the robustness of the proposed approach based on VTG(Valid Tracking Gate), the simulations are conducted utilizing the airborne IR video sequences: Then, the tracking performances are compared with the existing Kalman Filter tracking techniques.

• Journal of Information Processing Systems
• /
• 제15권1호
• /
• pp.169-180
• /
• 2019

Transmitting visual information over a broadcasting network is not only prone to a copyright violation but also is a forgery. Authenticating such information and protecting its authorship rights call for more advanced data encoding. To this end, electronic watermarking is often adopted to embed inscriptive signature in imaging data. Most existing watermarking methods while focusing on robustness against degradation remain lacking of measurement against security loophole in which the encrypting scheme once discovered may be recreated by an unauthorized party. This could reveal the underlying signature which may potentially be replaced or forged. This paper therefore proposes a novel digital watermarking scheme in temporal-frequency domain. Unlike other typical wavelet based watermarking, the proposed scheme employed the Lorenz chaotic map to specify embedding positions. Effectively making this is not only a formidable method to decrypt but also a stronger will against deterministic attacks. Simulation report herein highlights its strength to withstand spatial and frequent adulterations, e.g., lossy compression, filtering, zooming and noise.

• 대한임베디드공학회논문지
• /
• 제16권1호
• /
• pp.1-8
• /
• 2021

Detecting Out-of-Distribution (OOD) data is fundamentally required when Deep Neural Network (DNN) is applied to real-world AI such as autonomous driving. However, modern DNNs are quite vulnerable to the over-confidence problem even if the test data are far away from the trained data distribution. To solve the problem, this paper proposes a novel Adversarial-Mixup training method to let the DNN model be more robust by detecting OOD data effectively. Experimental results show that the proposed Adversarial-Mixup method improves the overall performance of OOD detection by 78% comparing with the State-of-the-Art methods. Furthermore, we show that the proposed method can alleviate the over-confidence problem by reducing the confidence score of OOD data than the previous methods, resulting in more reliable and robust DNNs.

• 한국군사과학기술학회지
• /
• 제25권4호
• /
• pp.381-389
• /
• 2022

Detecting partially occluded objects is difficult due to the appearances and shapes of occluders are highly variable. These variabilities lead to challenges of localizing accurate bounding box or classifying objects with visible object parts. To address these problems, we propose a two-stage part-based attention approach for robust object detection under partial occlusion. First, our part attention network(PAN) captures the important object parts and then it is used to generate weighted object features. Based on the weighted features, the re-weighted object features are produced by our reinforced PAN(RPAN). Experiments are performed on our collected military vehicle dataset and synthetic occlusion dataset. Our method outperforms the baselines and demonstrates the robustness of detecting objects under partial occlusion.

• 자동차안전학회지
• /
• 제14권3호
• /
• pp.71-76
• /
• 2022

In autonomous driving cars, 3D pose estimation can be one of the effective methods to enhance safety control for OOP (Out of Position) passengers. There have been many studies on human pose estimation using a camera. Previous methods, however, have limitations in automotive applications. Due to unexplainable failures, CNN methods are unreliable, and other methods perform poorly. This paper proposes robust real-time multi-human 3D pose estimation architecture in vehicle using monocular RGB camera. Using particle filter, our approach integrates CNN 2D/3D pose measurements with available information in vehicle. Computer simulations were performed to confirm the accuracy and robustness of the proposed algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권2호
• /
• pp.405-423
• /
• 2022

The distance vector-hop (DV-Hop) is one of the emblematic algorithms that use node connectivity for locating, which often accompanies by a large positioning error. To reduce positioning error, the bio-inspired algorithm and weight optimization model are introduced to address positioning. Most scholars argue that the weight value decreases as the hop counts increases. However, this point of view ignores the intrinsic relationship between the error and weight. To address this issue, this paper constructs the relationship model between error and hop counts based on actual communication characteristics of sensor nodes in wireless sensor network. Additionally, we prove that the error converges to 1/6CR when the hop count increase and tendency to infinity. Finally, this paper presents a modified error-oriented weight positioning model, and implements it with genetic algorithm. The experimental results demonstrate excellent robustness and error removal.