Multi-sensor data fusion based on soft likelihood functions and OWA aggregation and its application in target recognition system

Mi, Xiangjun; Lv, Tongxuan; Tian, Ye; Kang, Bingyi

doi:10.1016/j.isatra.2020.12.009

Cited by 20 publications

(8 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, with the geometric multiple growth of the amount of multimedia information on the Internet, this method has begun to appear somewhat ineffective. It not only requires a lot of time and labor costs but also requires manual annotation [18]. Often with a certain subjectivity, it is difficult to completely and objectively describe the accurate information of the multimedia resource itself, and it is easy to cause additional adverse effects during retrieval, and for multimedia forms containing a large amount of information such as audio or video, manual processing is even more difficult [19].…”

Section: Related Workmentioning

confidence: 99%

[Retracted] Multisensor Cross‐Media Data Mining Method Assisted by Expert System

Shan¹

2023

Journal of Sensors

View full text Add to dashboard Cite

The information generated by the multifaceted and multilevel processing of the data of multiple sensors is more meaningful than the information obtained by a single sensor and provides accurate information and decision-making basis for various application systems. How to apply data mining theory to the multisensor cross-media field has become a research hotspot. Through the analysis of multisensor cross-media data, it is of great significance to dig out the important rules, information, or knowledge hidden in it and use it for cross-media retrieval engine. The rule acquisition is the “bottleneck” problem of the expert system. This paper adopts the data mining method based on the rough set to acquire the rules and improves the basic algorithm of attribute reduction. Using the attribute reduction algorithm and the heuristic value reduction algorithm, the calculation is simplified and the reduction efficiency is improved. In the presentation, according to the characteristics of cross-media and the application requirements of expert systems, this paper takes the case representation based on features as the basis and classifies cases according to feature attributes. In case retrieval, according to the hierarchical structure of case features, the entire case database is organized into a multilevel hierarchical index structure. In this paper, a cross-media retrieval engine is constructed from the perspective of classifier design, and the Euclidean distance is used as the similarity matching model of image content. The mutual retrieval of images and audios preliminarily forms the design process of retrieval from one media type to another and establishes a corresponding cross-media index. The experimental results show that the algorithm has better processing effect and higher accuracy than other algorithms. Different k-nearest neighbor values were selected in the experiment, and it reached about 96% in the test environment of libsvm toolbox, which is better than the processing results of LE and LLE algorithms.

show abstract

Section: Related Workmentioning

confidence: 99%

[Retracted] Multisensor Cross‐Media Data Mining Method Assisted by Expert System

Shan¹

2023

Journal of Sensors

View full text Add to dashboard Cite

show abstract

“…Such musical features can be specially designed or postprocessed to extract the "Onset" information of the notes. For example, in the study by Mi et al, a chromatic onset-based feature was designed [12].…”

Section: Related Workmentioning

confidence: 99%

Application of 5G Internet of Things Multisensor Information Fusion Model in Piano Performance

Wang

2022

Journal of Sensors

View full text Add to dashboard Cite

In this paper, we use melodic multisensor information fusion combined with 5G IoT to conduct an in-depth study and analysis of the experience model of piano performance. In the form of multimodal data, two main storage forms, audio and MIDI, are chosen. First, audio signal processing technology and deep learning technology are used to extract shallow and high-level feature sequences in turn, and then, the alignment of the two modal data is completed with the help of sequence alignment algorithm. For the problem that encrypted data cannot be queried by uploading blockchain, this paper proposes an IoT encrypted data query mechanism based on blockchain and Bloom’s filter. The blockchain stores IoT encrypted indexes by temporal attributes to ensure data consistency, tamper-evident, and traceability. A new loss function training multimodal model is designed for piano performance signals. The piano performance generated by this model differs from the traditional piano performance generation in that it does not need to add complex piano performance rules manually but generates piano performance directly with piano performance theory rules by training the initial piano performance dataset and improves the stability of the generated piano performance by chord constraints and enhances the note dependence on time. In the analysis of the experimental results, the generated melodies were invited 50 for evaluation and analysis. The overall style-based GAN network piano performance generation model proposed in the study makes the generated piano performance melodies more pleasing to the ear through chord constraints and the content of autonomous learning moments, which has important theoretical and practical implications for the creation and realization of mass and batch piano performances.

show abstract

“…However, with the increasing complexity of the electromagnetic environment, the intelligence reconnaissance based on a single sensor has no sufficient adaptability. In contrast, the multi-sensor data fusion, as a processing method that comprehensively analyses the intercepted information from different sensors, has more accurate and stable performance than a single sensor [3][4][5]. Hence, research based on multi-sensor fusion is of great significance to improve the performance of radar countermeasures and reconnaissance systems.…”

Section: Introductionmentioning

confidence: 99%

A high‐precision frequency estimation algorithm based on multi‐segment signal fusion

Liu¹,

Liu²,

He³

et al. 2022

IET Radar Sonar & Navi

View full text Add to dashboard Cite

As the current multi-segment signal fusion algorithms cannot meet the requirement of high-precision frequency estimation at different signal-to-noise ratios (SNRs), an adaptive fusion algorithm is proposed in this paper. At high SNR, an autocorrelation weighted fusion algorithm is utilised, which adopts the real-time weighted fusion of multi-segment autocorrelation signals, resulting in denoised sinusoidal signals. Then the frequency is obtained by minimising the error function based on coarse estimation. At low SNR, an improved spectrum fusion algorithm is adopted, which uses the three-parameter sinefitting method to determine the phase difference compensation factor, and the multisegment signal spectrum is weighted to obtain a long signal spectrum with continuous phase. As a result, the frequency can be estimated by spectral peak search. Simulation results show that the proposed algorithm, compared with existing algorithms, not only improves the estimation accuracy by about 20%-50% but also can perform highprecision frequency estimation for multi-segment signals of different lengths, frequencies, and abnormal situations.

show abstract

Multi-sensor data fusion based on soft likelihood functions and OWA aggregation and its application in target recognition system

Cited by 20 publications

References 68 publications

[Retracted] Multisensor Cross‐Media Data Mining Method Assisted by Expert System

[Retracted] Multisensor Cross‐Media Data Mining Method Assisted by Expert System

Application of 5G Internet of Things Multisensor Information Fusion Model in Piano Performance

A high‐precision frequency estimation algorithm based on multi‐segment signal fusion

Contact Info

Product

Resources

About