Sliding-Window Belief Propagation with Unequal Window Size for Nonstationary Heterogeneous Source

2020 ◽  
pp. 375-381
Author(s):  
Jiao Fan ◽  
Bowei Shan ◽  
Yong Fang
Keyword(s):  
Belief Propagation ◽  
Window Size ◽  
Sliding Window ◽  
Heterogeneous Source

Approximate Range Querying over Sliding Windows

2009 ◽  
pp. 2037-2050
Author(s):  
Francesco Buccafurri ◽  
Gianluca Caminiti ◽  
Gianluca Lax
Keyword(s):  
Knowledge Discovery ◽  
Data Reduction ◽  
Experimental Analysis ◽  
Window Size ◽  
Sliding Window ◽  
Knowledge Discovery In Databases ◽  
Flat Structure ◽  
Sliding Windows ◽  
Reduction Techniques ◽  
Processing Step

In the context of Knowledge Discovery in Databases, data reduction is a pre-processing step delivering succinct yet meaningful data to sequent stages. If the target of mining are data streams, then it is crucial to suitably reduce them, since often analyses on such data require multiple scans. In this chapter, we propose a histogram-based approach to reducing sliding windows supporting approximate arbitrary (i.e., non biased) range-sum queries. The histogram is based on a hierarchical structure (as opposed to the flat structure of traditional ones) and it results suitable to directly support hierarchical queries, such as drill-down and roll-up operations. In particular, both sliding window shifting and quick query answering operations are logarithmic in the sliding window size. Experimental analysis shows the superiority of our method in terms of accuracy w.r.t. the state-of-the-art approaches in the context of histogram-based sliding window reduction techniques.

Improved detection of motifs with preferential location in promoters

Genome ◽  
2010 ◽  
Vol 53 (9) ◽  
pp. 739-752 ◽  
Author(s):  
Virginie Bernard ◽  
Alain Lecharny ◽  
Véronique Brunaud
Keyword(s):  
In Silico ◽  
Gene Expression Regulation ◽  
Window Size ◽  
Sliding Window ◽  
In Silico Prediction ◽  
Distribution Profile ◽  
Topological Constraints ◽  
Automatic Adaptation ◽  
Preferential Location

Many transcription factor binding sites (TFBSs) involved in gene expression regulation are preferentially located relative to the transcription start site. This property is exploited in in silico prediction approaches, one of which involves studying the local overrepresentation of motifs using a sliding window to scan promoters with considerable accuracy. Nevertheless, the consequences of the choice of the sliding window size have never before been analysed. We propose an automatic adaptation of this size to each motif distribution profile. This approach allows a better characterization of the topological constraints of the motifs and the lists of genes containing them. Moreover, our approach allowed us to highlight a nonconstant frequency of occurrence of spurious motifs that could be counter-selected close to their functional area. Therefore, to improve the accuracy of in silico prediction of TFBSs and the sensitivity of the promoter cartography, we propose, in addition to automatic adaptation of window size, consideration of the nonconstant frequency of motifs in promoters.

Approximate Range Querying over Sliding Windows

2010 ◽  
pp. 273-287
Author(s):  
Francesco Buccafurri
Keyword(s):  
Knowledge Discovery ◽  
Data Reduction ◽  
Experimental Analysis ◽  
Window Size ◽  
Sliding Window ◽  
Knowledge Discovery In Databases ◽  
Flat Structure ◽  
Sliding Windows ◽  
Reduction Techniques ◽  
Processing Step

In the context of Knowledge Discovery in Databases, data reduction is a pre-processing step delivering succinct yet meaningful data to sequent stages. If the target of mining are data streams, then it is crucial to suitably reduce them, since often analyses on such data require multiple scans. In this chapter, we propose a histogram-based approach to reducing sliding windows supporting approximate arbitrary (i.e., non biased) range-sum queries. The histogram is based on a hierarchical structure (as opposed to the flat structure of traditional ones) and it results suitable to directly support hierarchical queries, such as drill-down and roll-up operations. In particular, both sliding window shifting and quick query answering operations are logarithmic in the sliding window size. Experimental analysis shows the superiority of our method in terms of accuracy w.r.t. the state-of-the-art approaches in the context of histogram-based sliding window reduction techniques.

scholarly journals OPTIMASI PREDIKSI INFLASI DENGAN NEURAL NETWORK PADA TAHAP WINDOWING ADAKAH PENGARUH PERBEDAAN WINDOW SIZE

2021 ◽  
Vol 12 (3) ◽  
pp. 176
Author(s):  
Rizchi Eka Wahyuni
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Window Size ◽  
Sliding Window ◽  
Backpropagation Neural Network ◽  
Cross Sectional

AbstrakInflasi adalah indikator yang penting dalam penentuan kebijakan pemerintah. Data inflasi dirilis oleh Badan Pusat Statistik (BPS) di setiap awal bulan. Jika data inflasi dapat diprediksi lebih awal, pemerintah bisa menerapkan kebijakan yang tepat. Backpropagation neural network adalah salah satu metode prediksi yang lazim digunakan. Dengan menggunakan data bulan-bulan sebelumnya, inflasi dapat diprediksi menggunakan metode neural network dengan menggunakan teknik sliding window yang juga disebut metode windowing. Windowing adalah pembentukan struktur dari data time series menjadi data cross sectional. Ukuran dari windowing akan mempengaruhi akurasi dari hasil prediksi. Pada penelitian ini, penulis melakukan percobaan dengan tiga window size yaitu 6, 12, dan 18 untuk melihat adakah perbedaan akurasi hasil dari beberapa window size tersebut. Hasil percobaan menyimpulkan bahwa window size 6 memiliki akurasi paling baik untuk memprediksi inflasi dengan RMSE 0,435.Keywords: backpropagation, prediksi, sliding window

Sign in / Sign up

Export Citation Format

Share Document