2022
DOI: 10.1016/j.sigpro.2021.108318
|View full text |Cite
|
Sign up to set email alerts
|

Censored regression distributed functional link adaptive filtering algorithm over nonlinear networks

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
3
0
1

Year Published

2022
2022
2024
2024

Publication Types

Select...
7

Relationship

0
7

Authors

Journals

citations
Cited by 13 publications
(4 citation statements)
references
References 29 publications
0
3
0
1
Order By: Relevance
“…Figure 2 shows the LMS schematic. Since the noise signal contained in the music can affect the detection accuracy of the piano performance technique analysis algorithm, the filter designed for filtering the noisy music signal in piano performance technique analysis is required to minimize the error caused by the noise without changing the signal waveform, and both fixed filters and adaptive filters can be used [16]. The former must use a priori knowledge of the signal and noise, while the latter has the ability to automatically adjust its own parameters and requires less a priori knowledge, so the adaptive LMS filter (minimum mean square error filter) is adopted in this paper.…”
Section: Lms Adaptive Filtering Algorithmmentioning
confidence: 99%
“…Figure 2 shows the LMS schematic. Since the noise signal contained in the music can affect the detection accuracy of the piano performance technique analysis algorithm, the filter designed for filtering the noisy music signal in piano performance technique analysis is required to minimize the error caused by the noise without changing the signal waveform, and both fixed filters and adaptive filters can be used [16]. The former must use a priori knowledge of the signal and noise, while the latter has the ability to automatically adjust its own parameters and requires less a priori knowledge, so the adaptive LMS filter (minimum mean square error filter) is adopted in this paper.…”
Section: Lms Adaptive Filtering Algorithmmentioning
confidence: 99%
“…Son zamanlarda, büyük veri alanında popüler hale gelen OC stratejisi [11,18]'de genellikle zamanla değişen parametrelerle dinamik süreçlerin izlenmesine ilişkin büyük veri sorunlarının, [19]'da enerji kaynaklarının sınırlı olduğu senaryolarda adaptif ağlar üzerinden dağıtılmış tahmin için enerji bütçesini düşürmenin ve [20]'de merkezi olmayan bir algılama sisteminde azaltılmış iletişim oranı elde etmenin üstesinden başarıyla gelmiştir. Bu çalışmalara ek olarak, OC stratejisi son zamanlarda merkezileştirilmiş büyük-ölçekli ağlarda [21], dağıtılmış kablosuz ağlarda [22], yapay sinir ağları eğitimi için bilgilendirici eğitim verisi çıkarmada [23], yapay sinir ağının eğitiminde [24], grafik sinyallerinin kestiriminde [25] ve doğrusal olmayan ağlar üzerinde adaptif filtreleme işlemlerinde [26], giyilebilir işitme cihazlarında akustik geri besleme yolunun kestiriminde [27], patolojik el tremorünün kestiriminde [28] kullanılmasıyla daha da popüler hale gelmiştir. Her ne kadar [11]'de tasarlanan OC stratejisi; büyük veri akışları için büyük-ölçekli doğrusal regresyon yöntemleri başlığı altında anılsa da, aslında literatürde klasik ASP algoritmaları olarak bilinen en küçük ortalama kare (Least mean square, LMS) ve özyinelemeli en küçük kareler (Recursive least squares, RLS) algoritmalarının yapısına yerleştirilmiştir (yani OC tabanlı LMS ve OC-tabanlı RLS algoritmaları önerilmiştir).…”
Section: Introductionunclassified
“…According to the multitask case in the real world application [6]- [8], the authors in [6] has described the adaptation and learning of nonlinear filtering over the distributed network. A distributed with sparsity-aware adaptive algorithm [7] has been proposed to verify the Voterra system that can provide a good performance in the wireless sensor network (WSN).…”
Section: Introductionmentioning
confidence: 99%
“…A distributed with sparsity-aware adaptive algorithm [7] has been proposed to verify the Voterra system that can provide a good performance in the wireless sensor network (WSN). In [8], a censored-regression has been introduced to compensate the bias estimation over the nonlinear WSN.…”
Section: Introductionmentioning
confidence: 99%