A Multi-level Data Fusion Approach for Early Fire Detection

2010 ◽  
Author(s):  
Odysseas Sekkas ◽  
Stathes Hadjiefthymiades ◽  
Evangelos Zervas
Keyword(s):  
Data Fusion ◽  
Fire Detection ◽  
Level Data ◽  
Multi Level ◽  
Fusion Approach ◽  
Early Fire Detection

A Decision-Level Data Fusion Approach to Surface Roughness Prediction

2019 ◽  
Author(s):  
Yupeng Wei ◽  
Dazhong Wu ◽  
Janis Terpenny
Keyword(s):  
Surface Roughness ◽  
Data Fusion ◽  
Process Monitoring ◽  
Predictive Models ◽  
Sensor Data ◽  
Fused Deposition ◽  
Decision Level ◽  
Level Data ◽  
Fusion Approach

Abstract To improve the quality of additively manufactured parts, it is crucial to develop real-time process monitoring systems and data-driven predictive models. While various sensor- and image-based process monitoring methods have been developed to improve the quality of additively manufactured parts, very limited research has been conducted to predict surface roughness. To fill this gap, this paper presents a decision-level data fusion approach to predicting surface roughness in the fused deposition modeling (FDM) process. The predictive models are trained by the random forests method using multiple sensor signals. A decision-level data fusion method is introduced to integrate sensor data sources. Experimental results have shown that the decision-level data fusion approach can predict surface roughness in FDM with high accuracy.

A modified mid-level data fusion approach on electronic nose and FT-NIR data for evaluating the effect of different storage conditions on rice germ shelf life

Talanta ◽  
2020 ◽  
Vol 206 ◽  
pp. 120208 ◽  
Author(s):  
Cristina Malegori ◽  
Susanna Buratti ◽  
Simona Benedetti ◽  
Paolo Oliveri ◽  
Simona Ratti ◽  
...  
Keyword(s):  
Data Fusion ◽  
Shelf Life ◽  
Electronic Nose ◽  
Storage Conditions ◽  
Level Data ◽  
Fusion Approach

scholarly journals Serum Metabolomic Profiles of Paratuberculosis Infected and Infectious Dairy Cattle by Ambient Mass Spectrometry

2021 ◽  
Vol 7 ◽  
Author(s):  
Alessandra Tata ◽  
Ivana Pallante ◽  
Andrea Massaro ◽  
Brunella Miano ◽  
Massimo Bottazzari ◽  
...  
Keyword(s):  
Mass Spectrometry ◽  
Data Fusion ◽  
Dairy Cattle ◽  
High Resolution Mass Spectrometry ◽  
Clinical Signs ◽  
Direct Analysis ◽  
Economic Losses ◽  
Molecular Features ◽  
Level Data ◽  
Fusion Approach

Mycobacterium avium subsp. paratuberculosis (MAP) is the causative agent of paratuberculosis [Johne's disease (JD)], a chronic disease that causes substantial economic losses in the dairy cattle industry. The long incubation period means clinical signs are visible in animals only after years, and some cases remain undetected because of the subclinical manifestation of the disease. Considering the complexity of JD pathogenesis, animals can be classified as infected, infectious, or affected. The major limitation of currently available diagnostic tests is their failure in detecting infected non-infectious animals. The present study aimed to identify metabolic markers associated with infected and infectious stages of JD. Direct analysis in real time coupled with high resolution mass spectrometry (DART-HRMS) was, hence, applied in a prospective study where cohorts of heifers and cows were followed up annually for 2–4 years. The animals' infectious status was assigned based on a positive result of both serum ELISA and fecal PCR, or culture. The same animals were retrospectively assigned to the status of infected at the previous sampling for which all JD tests were negative. Stored sera from 10 infected animals and 17 infectious animals were compared with sera from 20 negative animals from the same herds. Two extraction protocols and two (-/+) ionization modes were tested. The three most informative datasets out of the four were merged by a mid-level data fusion approach and submitted to partial least squares discriminant analysis (PLS-DA). Compared to the MAP negative subjects, metabolomic analysis revealed the m/z signals of isobutyrate, dimethylethanolamine, palmitic acid, and rhamnitol were more intense in infected animals. Both infected and infectious animals showed higher relative intensities of tryptamine and creatine/creatinine as well as lower relative abundances of urea, glutamic acid and/or pyroglutamic acid. These metabolic differences could indicate altered fat metabolism and reduced energy intake in both infected and infectious cattle. In conclusion, DART-HRMS coupled to a mid-level data fusion approach allowed the molecular features that identified preclinical stages of JD to be teased out.

A robot control approach based on multi-level data fusion

ICCAS 2010 ◽  
2010 ◽  
Author(s):  
Sangseung Kang ◽  
Jaehong Kim ◽  
Joochan Sohn
Keyword(s):  
Data Fusion ◽  
Robot Control ◽  
Control Approach ◽  
Level Data ◽  
Multi Level
Sign in / Sign up

Export Citation Format

Share Document