• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3729-3749
• /
• 2021

At present, deep convolution network-based salient object detection (SOD) has achieved impressive performance. However, it is still a challenging problem to make full use of the multi-scale information of the extracted features and which appropriate feature fusion method is adopted to process feature mapping. In this paper, we propose a new adjacency auxiliary network (AANet) based on multi-scale feature fusion for SOD. Firstly, we design the parallel connection feature enhancement module (PFEM) for each layer of feature extraction, which improves the feature density by connecting different dilated convolution branches in parallel, and add channel attention flow to fully extract the context information of features. Then the adjacent layer features with close degree of abstraction but different characteristic properties are fused through the adjacent auxiliary module (AAM) to eliminate the ambiguity and noise of the features. Besides, in order to refine the features effectively to get more accurate object boundaries, we design adjacency decoder (AAM_D) based on adjacency auxiliary module (AAM), which concatenates the features of adjacent layers, extracts their spatial attention, and then combines them with the output of AAM. The outputs of AAM_D features with semantic information and spatial detail obtained from each feature are used as salient prediction maps for multi-level feature joint supervising. Experiment results on six benchmark SOD datasets demonstrate that the proposed method outperforms similar previous methods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.3
• /
• pp.422-429
• /
• 2022

In this paper, the intermediate frequency transmission signal level between the network system-based baseband and RF unit consisting of multi-channel airborne relay devices and a lot of mission devices, which are currently undergoing technology development tasks, is kept constant at the reference signal level. Considering the other party's receiving input range, despite changes in the short-range long-range wireless communication environment, it presents a multi-link protection and MLP-A algorithm that allows signals to be transmitted stably and reliably through signal detection automatic gain control, and experiments and analysis considering short-distance and long-distance wireless environments were performed by designing, manufacturing, and implementing RF units to which MLP-A algorithms were applied, and applying distance calculation equations to the configuration of multiple air movements and verification networks. Through this, it was confirmed that a stable and reliable RF communication system can be operated.

• Korean Journal of Remote Sensing
• /
• v.40 no.1
• /
• pp.115-122
• /
• 2024

Multi-object tracking (MOT) is a vital component in understanding the surrounding environments. Previous research has demonstrated that MOT can successfully detect and track surrounding objects. Nonetheless, inaccurate classification of the tracking objects remains a challenge that needs to be solved. When an object approaching from a distance is recognized, not only detection and tracking but also classification to determine the level of risk must be performed. However, considering the erroneous classification results obtained from the detection as the track class can lead to performance degradation problems. In this paper, we discuss the limitations of classification in tracking under the classification uncertainty of the detector. To address this problem, a class update module is proposed, which leverages the class uncertainty estimation of the detector to mitigate the classification error of the tracker. We evaluated our approach on the VisDrone-MOT2021 dataset,which includes multi-class and uncertain far-distance object tracking. We show that our method has low certainty at a distant object, and quickly classifies the class as the object approaches and the level of certainty increases.In this manner, our method outperforms previous approaches across different detectors. In particular, the You Only Look Once (YOLO)v8 detector shows a notable enhancement of 4.33 multi-object tracking accuracy (MOTA) in comparison to the previous state-of-the-art method. This intuitive insight improves MOT to track approaching objects from a distance and quickly classify them.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.4 no.3
• /
• pp.174-181
• /
• 2004

In this paper, we review the four receiver architectures and four methods for multi-standard receiver design. Propose reconfigurable RF block can be used for both low-IF and direct conversion architecture. Also, using reconfigurable mixer method, it can be operated at $2{\sim}6$ GHz range for multi-standard receiver. It consists of wideband mixer, filter, and automatic gain control amplifier and to get wide-band operation, $2{\sim}6$ GHz, wide-band mixer use flexible input matching method. Besides, to design multi-standard receiver, LNA bank that support each standard is necessary and it has good performance to compensate the performance of wide-band mixer. Finally, we design and simulate proposed reconfigurable RF block and to prove that it has acceptable performances for various wireless standards, the LNA bank that supports both IEEE 802.11a/b/g and WCDMA is also designed and simulated with it.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.19 no.10
• /
• pp.976-983
• /
• 2006

Multi-resolution Signal Decomposition (MSD) Technique of Wavelet Transform has interesting properties of capturing the embedded horizontal, vertical and diagonal variations within an image in a separable form. This feature was exploited to identify individual partial discharge sources present in multi-source PD pattern, usually encountered during practical PD measurement. Employing the Daubechies wavelet, feature were extracted from the third level decomposed and reconstructed horizontal and vertical component images. These features were found to contain the necessary discriminating information corresponding to the individual PD sources and multi-PD soruces.

• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.8
• /
• pp.697-702
• /
• 2001

The ring laser gyro(RLG) has been used extensively in strapdown inertial navigation system(SDINS) because of the apparent of having wide dynamic range, digital output and high accuracy. The dithered RLG system has dynamic motion at sensor level, caused by the dithering motion to overcome the lock-in threshold. In this case, an attitude error is produced by not only the true coning of the vehicle motion but also the pseudo coning of the sensor motion. This paper describes the definition of the multi-frequency coning motion and its noncommutativity error to reject the pseudo coning error produced by the sensor motion such as the dithered RLG. The simulation results are presented to minimize the multi-frequency coning error.

• Proceedings of the KIEE Conference
• /
• 2009.07a
• /
• pp.127_128
• /
• 2009

A new technique using a search method which is based on fuzzy multi-criteria function is proposed for GMS(generator maintenance scheduling) in order to consider multi-objective function. Not only minimization of probabilistic production cost but also maximization of system reliability level are considered for fuzzy multi-criteria function. To obtain an optimal solution for generator maintenance scheduling under fuzzy environment, fuzzy multi-criteria relaxation method(fuzzy search method) is used. The practicality and effectiveness of the proposed approach are demonstrated by simulation studies for a real size power system model in Korea in 2010.

• Proceedings of the KIPE Conference
• /
• 2004.07b
• /
• pp.620-624
• /
• 2004

Th is paper presents a systematical approach to study carrier based PWM techniques (CPWM) in diode-clamped and cascade multilevel inverters by using the proposed multi-modulating pattern method. This method is based on the vector correlation between CPWM and space vector PWM (SVPWM) and applicable to both multilevel inverter topologies. The CPWM technique can be described in a general mathematical equation, and obtain the same outputs similarly as of corresponding SVPWM. Control of the fundamental voltage, vector redundancies and phase redundancies in multilevel inverter can be formulated separately in the CPWM equation. The deduced CPWM can obtain a full vector redundancy control, and fully utilize phase redundancy in a cascade inverter. In the paper, CPWM equations and corresponding algorithm for generating multi-modulating signals will be performed, in which SVPWM attributes will be presented by corresponding controllable factors.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.3C
• /
• pp.224-232
• /
• 2012

Priority MAC is an important issue in every communication system when we consider differentiated service applications. In this paper, we propose a mechanism to support priority MAC based on multi-parameters for IEEE 802.15.7 visible light communication (VLC). By using three parameters such as number of backoff times (NB), backoff exponent (BE) and contention window (CW), we provide priority for multi-level differentiated service applications. We consider beacon-enabled VLC personal area network (VPAN) mode with slotted version for random access algorithm in this paper. Based on a discrete-time Markov chain, we analyze the performance of proposed mechanism under non-saturation environments. By building a Markov chain model for multi-parameters, this paper presents the throughput and transmission delay time for VLC system. Numerical results show that we can apply three parameters to control the priority for VLC MAC protocol.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.661-664
• /
• 2018

온라인 게시판 글과 채팅창에서 주고받는 대화는 실제 사용되고 있는 구어체 특성이 잘 반영된 텍스트 코퍼스로 음성인식의 언어 모델 재료로 활용하기 좋은 학습 데이터이다. 하지만 온라인 특성상 노이즈가 많이 포함되어 있기 때문에 학습에 직접 활용하기가 어렵다. 본 논문에서는 사용자 입력오류가 다수 포함된 문장에서의 한글 오류 보정을 위한 sequence-to-sequence Denoising Autoencoder 모델을 제안한다.