Automatic noise reduction of domain-specific bibliographic datasets using positive-unlabeled learning
1
Citation
48
Reference
10
Related Paper
Citation Trend
This paper deals with approaches to knowledge reduction in inconsistent decision systems. The judgment theorem with respect to attribute reduction is obtained, from which the novel approaches to maximum distribution reduction, distribution reduction and possible reduction are presented. In addition, its time complexity is analyzed in detail. Experimental results show that the reduction algorithms are more efficient than those existing algorithms.
Cite
Citations (1)
Non canonical
Cite
Citations (0)
Fracture reduction
Cite
Citations (24)
The main intention of proposing an alternative technique is to ensure consistency is been upheld besides successfully reducing the file. Of all the reduction techniques available currently, only normal parameter reduction has managed to address the issue of consistency at optimal and suboptimal level. In this paper, we initiated another form of reduction known as hybrid reduction by complementing the normal parameter reduction with object reduction. It has already demonstrated that the proposed hybrid reduction has successfully reduced data by 55% with the sample used, thus proving that it as a good alternative for the process of decision making using less amount of data.
Soft set
Data Reduction
Sample (material)
Cite
Citations (2)
Attribute reduction is the most important technique of rough set.Once it gets whole reductions,the reasoning capability under multi attribute absent can behave well.How to get whole reductions based on reduction's concept is discussed.After getting rough reduction by pruning,and whole really reductions with back elimination,reduction pruning and discernibility matrix based heuristic reduction algorithm are compared.The experimental results show reduction-pruning algorithm is effective.
Pruning
Matrix (chemical analysis)
Cite
Citations (5)
As PET imaging is accompanied by substantial radiation exposure and cancer risk, reducing radiation dose in PET scans is an important topic. However, low-count PET scans often suffer from high image noise, which can negatively impact image quality and diagnostic performance. Recent advances in deep learning have shown great potential for recovering underlying signal from noisy counterparts. However, neural networks trained on a specific noise level cannot be easily generalized to other noise levels due to different noise amplitude and variances. To obtain optimal denoised results, we may need to train multiple networks using data with different noise levels. But this approach may be infeasible in reality due to limited data availability. Denoising dynamic PET images presents additional challenge due to tracer decay and continuously changing noise levels across dynamic frames. To address these issues, we propose a Unified Noise-aware Network (UNN) that combines multiple sub-networks with varying denoising power to generate optimal denoised results regardless of the input noise levels. Evaluated using large-scale data from two medical centers with different vendors, presented results showed that the UNN can consistently produce promising denoised results regardless of input noise levels, and demonstrate superior performance over networks trained on single noise level data, especially for extremely low-count data.
Image noise
Cite
Citations (1)
The mechanism and progress of soft reduction technology was introduced,the effect of the reduction on central segregation and solidified structure was analysed. The results show that soft reduction can eliminate the segregation of both sides,followed by the central segregation. The degree of central segregation decreases with increasing the reduction when the real reduction is not above the maxium reduction.
Cite
Citations (0)
Consistent exposure to elevated sound levels results in noise health effects. The industrial environment represents a major source of such effects. There is significant variation in noise at different sections of such industries due to which most of the workers are exposed to these sounds at one or another level. In this study, a noise level measuring methodology is used for fixed and moving workers. This article introduces an algorithm for optimum selection of earmuff and earplug for different working places depending upon the exposure to noise. Medium density fiber industry is considered as a case for this study. It considers workers who are busy at a single point and face a consistent amount of noise as well as the workers who move and are exposed to a varying level of the noise. Noise level meters are used to measure the noise level at different points. At each point, the average value of the samples is taken. Based on the data collected, earmuff with high noise reduction rate is assigned to the workers closed to the machines. Implementation of the developed algorithm reduced the effect of noise on workers by 6.9%, 5%, and 16.3% for the chipper machine, pneumatic fan, and sanding machine, respectively, that were identified as the major source of noise at medium density fiber industry. This percentage reduction helped the workers to bring them to the optimum safe level of noise that is 85 dB and protect them from hearing loss severity due to frequency variations.
Cite
Citations (0)
The principle of the noise control device and its design methods were described in the previous reports, and it was indicated that a great noise reduction can be obtained when the noise control device with an appropriate barrier, that is, the noise control device system was used. Before the noise control device system is applied to a real noise source, for example, a machine noise, a traffic noise, etc., it is necessary to estimate the noise reduction effect. For this purpose, the noise reduction effect of application to a machine noise was measured and its prediction method by a scale model experiment was considered. In this paper, the noise reduction effect of application to a real noise source and its prediction method are described.
Value noise
Gradient noise
Cite
Citations (0)
Decision table
Matrix (chemical analysis)
Decision system
Cite
Citations (8)