• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제4권1호
• /
• pp.5-24
• /
• 2010

Data fusion is an attractive technology because it allows various trade-offs related to performance metrics, e.g., energy, latency, accuracy, fault-tolerance and security in wireless sensor networks (WSNs). Under a complicated environment, each sensor node must be equipped with more than one type of sensor module to monitor multi-targets, so that the complexity for the fusion process is increased due to the existence of various physical attributes. In this paper, we first investigate the process and performance of multi-attribute fusion in data gathering of WSNs, and then propose a self-adaptive threshold method to balance the different change rates of each attributive data. Furthermore, we present a method to measure the energy-conservation efficiency of multi-attribute fusion. Based on our proposed methods, we design a novel energy equilibrium routing method for WSNs, viz., multi-attribute fusion tree (MAFT). Simulation results demonstrate that MAFT achieves very good performance in terms of the network lifetime.

• 한국컴퓨터정보학회논문지
• /
• 제22권12호
• /
• pp.69-77
• /
• 2017

This paper represents a novel framework for multi-scale image fusion. Multi-scale Kalman Smoothing (MKS) algorithm with quad-tree structure can provide a powerful multi-resolution image fusion scheme by employing Markov property. In general, such approach provides outstanding image fusion performance in terms of accuracy and efficiency, however, quad-tree based method is often limited to be applied in certain applications due to its stair-like covariance structure, resulting in unrealistic blocky artifacts at the fusion result where finest scale data are void or missed. To mitigate this structural artifact, in this paper, a new scheme of multi-scale fusion framework is proposed. By employing Super Resolution (SR) technique on MKS algorithm, fine resolved measurement is generated and blended through the tree structure such that missed detail information at data missing region in fine scale image is properly inferred and the blocky artifact can be successfully suppressed at fusion result. Simulation results show that the proposed method provides significantly improved fusion results in the senses of both Root Mean Square Error (RMSE) performance and visual improvement over conventional MKS algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권7호
• /
• pp.1907-1928
• /
• 2024

In recent years, multi-focus image fusion has emerged as a prominent area of research, with transformers gaining recognition in the field of image processing. Current approaches encounter challenges such as boundary artifacts, loss of detailed information, and inaccurate localization of focused regions, leading to suboptimal fusion outcomes necessitating subsequent post-processing interventions. To address these issues, this paper introduces a novel multi-focus image fusion technique leveraging the Swin Transformer architecture. This method integrates a frequency layer utilizing Wavelet Transform, enhancing performance in comparison to conventional Swin Transformer configurations. Additionally, to mitigate the deficiency of local detail information within the attention mechanism, Convolutional Neural Networks (CNN) are incorporated to enhance region recognition accuracy. Comparative evaluations of various fusion methods across three datasets were conducted in the paper. The experimental findings demonstrate that the proposed model outperformed existing techniques, yielding superior quality in the resultant fused images.

• Structural Engineering and Mechanics
• /
• 제31권3호
• /
• pp.333-347
• /
• 2009

Due to structural complicacy, structural health monitoring for civil engineering needs more accurate and effectual methods of damage identification. This study aims to import multi-source information fusion (MSIF) into structural damage diagnosis to improve the validity of damage detection. Firstly, the essential theory and applied mathematic methods of MSIF are introduced. And then, the structural damage identification method based on multi-mode information fusion is put forward. Later, on the basis of a numerical simulation of a concrete continuous box beam bridge, it is obviously indicated that the improved modal strain energy method based on multi-mode information fusion has nicer sensitivity to structural initial damage and favorable robusticity to noise. Compared with the classical modal strain energy method, this damage identification method needs much less modal information to detect structural initial damage. When the noise intensity is less than or equal to 10%, this method can identify structural initial damage well and truly. In a word, this structural damage identification method based on multi-mode information fusion has better effects of structural damage identification and good practicability to actual structures.

• Journal of Astronomy and Space Sciences
• /
• 제20권4호
• /
• pp.359-364
• /
• 2003

In this paper, we present multi-sensor data fusion for telematics application. Successful telematics can be realized through the integration of navigation and spatial information. The well-determined acquisition of vehicle's position plays a vital role in application service. The development of GPS is used to provide the navigation data, but the performance is limited in areas where poor satellite visibility environment exists. Hence, multi-sensor fusion including IMU (Inertial Measurement Unit), GPS(Global Positioning System), and DMI (Distance Measurement Indicator) is required to provide the vehicle's position to service provider and driver behind the wheel. The multi-sensor fusion is implemented via algorithm based on Kalman filtering technique. Navigation accuracy can be enhanced using this filtering approach. For the verification of fusion approach, land vehicle test was performed and the results were discussed. Results showed that the horizontal position errors were suppressed around 1 meter level accuracy under simulated non-GPS availability environment. Under normal GPS environment, the horizontal position errors were under 40㎝ in curve trajectory and 27㎝ in linear trajectory, which are definitely depending on vehicular dynamics.

• Journal of Information Processing Systems
• /
• 제15권5호
• /
• pp.1243-1257
• /
• 2019

As current algorithms unable to perform effective fusion processing of unknown complex radar signals lacking database, and the result is unstable, this paper presents a multi-level fusion processing algorithm for complex radar signals based on evidence theory as a solution to this problem. Specifically, the real-time database is initially established, accompanied by similarity model based on parameter type, and then similarity matrix is calculated. D-S evidence theory is subsequently applied to exercise fusion processing on the similarity of parameters concerning each signal and the trust value concerning target framework of each signal in order. The signals are ultimately combined and perfected. The results of simulation experiment reveal that the proposed algorithm can exert favorable effect on the fusion of unknown complex radar signals, with higher efficiency and less time, maintaining stable processing even of considerable samples.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권6호
• /
• pp.1833-1848
• /
• 2022

Named entity recognition (NER) is an important basic task in the field of Natural Language Processing (NLP). Recently deep learning approaches by extracting word segmentation or character features have been proved to be effective for Chinese Named Entity Recognition (CNER). However, since this method of extracting features only focuses on extracting some of the features, it lacks textual information mining from multiple perspectives and dimensions, resulting in the model not being able to fully capture semantic features. To tackle this problem, we propose a novel Multi-view Semantic Feature Fusion Model (MSFM). The proposed model mainly consists of two core components, that is, Multi-view Semantic Feature Fusion Embedding Module (MFEM) and Multi-head Self-Attention Mechanism Module (MSAM). Specifically, the MFEM extracts character features, word boundary features, radical features, and pinyin features of Chinese characters. The acquired font shape, font sound, and font meaning features are fused to enhance the semantic information of Chinese characters with different granularities. Moreover, the MSAM is used to capture the dependencies between characters in a multi-dimensional subspace to better understand the semantic features of the context. Extensive experimental results on four benchmark datasets show that our method improves the overall performance of the CNER model.

• Journal of Information Processing Systems
• /
• 제14권1호
• /
• pp.176-190
• /
• 2018

This paper presents a novel convolutional neural network based multi-feature fusion learning method for non-rigid 3D model retrieval, which can investigate the useful discriminative information of the heat kernel signature (HKS) descriptor and the wave kernel signature (WKS) descriptor. At first, we compute the 2D shape distributions of the two kinds of descriptors to represent the 3D model and use them as the input to the networks. Then we construct two convolutional neural networks for the HKS distribution and the WKS distribution separately, and use the multi-feature fusion layer to connect them. The fusion layer not only can exploit more discriminative characteristics of the two descriptors, but also can complement the correlated information between the two kinds of descriptors. Furthermore, to further improve the performance of the description ability, the cross-connected layer is built to combine the low-level features with high-level features. Extensive experiments have validated the effectiveness of the designed multi-feature fusion learning method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권5호
• /
• pp.2253-2272
• /
• 2018

We propose a deep learning method for multi-focus image fusion. Unlike most existing pixel-level fusion methods, either in spatial domain or in transform domain, our method directly learns an end-to-end fully convolutional two-stream network. The framework maps a pair of different focus images to a clean version, with a chain of convolutional layers, fusion layer and deconvolutional layers. Our deep fusion model has advantages of efficiency and robustness, yet demonstrates state-of-art fusion quality. We explore different parameter settings to achieve trade-offs between performance and speed. Moreover, the experiment results on our training dataset show that our network can achieve good performance with subjective visual perception and objective assessment metrics.

• 전자공학회논문지
• /
• 제52권12호
• /
• pp.142-149
• /
• 2015

단일 카메라 센서를 기반으로 한 차선검출 시스템은 급격한 조도 변화, 열악한 기상환경 등에 취약하다. 이러한 단일 센서 시스템의 한계를 극복하기 위한 방안으로 센서 융합을 통해 성능 안정화를 도모할 수 있다. 하지만, 기존 센서 융합의 연구는 대부분 물체 및 차량을 대상으로 한 융합 모델에 국한되어 차용하기 어렵거나, 차선 센서의 다양한 신호 주기 및 인식범위에 대한 상이성을 고려하지 않은 경우가 대부분이었다. 따라서 본 연구에서는 다중센서의 상이성을 고려하여 차선 정보를 최적으로 융합하는 기법을 제안한다. 제안하는 융합 프레임워크는 센서 별 가변적인 신호처리 주기와 인식 신뢰 범위를 고려하므로 다양한 차선 센서 조합으로도 정교한 융합이 가능하다. 또한, 새로운 차선 예측 모델의 제안을 통해 간헐적으로 들어오는 차선정보를 세밀한 차선정보로 정밀하게 예측하여 다중주기 신호를 동기화한다. 조도환경이 열악한 환경에서의 실험과 정량적 평가를 통해, 제안하는 융합 시스템이 기존 단일 센서 대비 인식 성능이 개선됨을 검증한다.