Quantifying relative moisture content in dielectric models using CW-THz spectroscopy and supervised machine learning regression

2021 ◽  
Author(s):  
Mayuri Kashyap ◽  
Aparajita Bandyopadhyay ◽  
Karl Bertling ◽  
Amartya Sengupta ◽  
Aleksandar D. Rakic
Keyword(s):  
Machine Learning ◽  
Moisture Content ◽  
Supervised Machine Learning ◽  
Thz Spectroscopy ◽  
Relative Moisture Content ◽  
Relative Moisture

scholarly journals Study on the Mitigative Effect of Controlled Permeable Formwork (CPF) Liner on Early-Age Shrinkage of Box-Girder Concrete

2019 ◽  
Vol 2019 ◽  
pp. 1-8 ◽  
Author(s):  
Jianxiong Ye ◽  
Linwen Yu ◽  
Yong Chen
Keyword(s):  
Moisture Content ◽  
Concrete Surface ◽  
Early Age ◽  
Working Mechanism ◽  
Box Girder ◽  
Relative Moisture Content ◽  
Relative Moisture ◽  
Bridge Structures ◽  
Girder Bridge ◽  
Surface Covering

Because of its high binder content and severe construction environment, early-age cracking is one of the most important threats to concrete used in continuous box-girder bridge structures. In this study, controlled permeable formwork (CPF) liner was used to mitigate the early-age shrinkage and reduce the early-age cracking risk of box-girder concrete. Early-age shrinkage was measured by a noncontact method and started at 30 min after adding mix water until 7 d. Internal relative moisture content and pore distribution tests were also carried out to reveal the working mechanism of CPF liner. The results show that covering the concrete surface with CPF liner decreased early-age shrinkage significantly. Under the temperature of 20°C and the relative humidity of 60%, two-surface-covering and three-surface-covering CPF liner on concrete decreased the shrinkage by 44% and 48%, respectively, at 7 d compared with concrete without CPF liner covered on it. The main reason is that CPF liner enhanced the internal relative moisture content and resulted in better performance of the surface concrete.

Myxomycetes on the bark of Banksia attenuata and B. menziesii (Proteaceae)

2006 ◽  
Vol 54 (4) ◽  
pp. 357 ◽  
Author(s):  
C. C. Jordan ◽  
M. H. Brims ◽  
E. J. Speijers ◽  
E. M. Davison
Keyword(s):  
Moisture Content ◽  
New Records ◽  
Common Species ◽  
Species Assemblage ◽  
Decomposition Level ◽  
Moist Chamber ◽  
Relative Moisture Content ◽  
Relative Moisture ◽  
Banksia Attenuata ◽  
Chamber Technique

Myxomycetes on the bark of dead Banksia attenuata and B. menziesii from the Perth metropolitan area of Western Australia were surveyed by the moist chamber technique, to determine whether the flora was similar on both hosts and what were the most important variables that determined the distribution of the most common species. Twenty-seven species of myxomycetes were recovered, including six new records for Australia (Comatricha rigidireta, Echinostelium elachiston, Paradiacheopsis cf. cribrata, P. rigida, Stemonitopsis amoena and S. cf. hyperopta). Members of the order Stemonitales comprised the largest number of species, whereas members of the Liceales occurred on the most bark pieces. The most common species were Licea kleistobolus, Echinostelium minutum, Comatricha elegans, Cribraria minutissima and Paradiacheopsis fimbriata. Overall, B. menziesii and B. attenuata had very similar myxomycete productivity, diversity and species assemblage, as did the tops and bottoms of the logs. It was concluded that they provided very similar microhabitats for myxomycetes. Both pH and the relative moisture content of the bark had an effect on myxomycete productivity. Bark decomposition level, pH and bark surface (top or bottom) were the most important variables determining the distribution of the most common myxomycete species.

Changes of surface soil relative moisture content in Hengduan Mountains, China, during 1992–2010

2013 ◽  
Vol 298 ◽  
pp. 161-170 ◽  
Author(s):  
Zhu Guo-feng ◽  
Shi Pei-ji ◽  
Pu Tao ◽  
He Yuan-qing ◽  
Zhang Tao ◽  
...  
Keyword(s):  
Moisture Content ◽  
Surface Soil ◽  
Hengduan Mountains ◽  
Relative Moisture Content ◽  
Relative Moisture

scholarly journals Role of Gypsum and Corn Cobs in Linkage of Peds in Cracking Soils

2018 ◽  
Vol 7 (1) ◽  
pp. 120-127
Author(s):  
S. K. Essa ◽  
Raid Shaalan Jarallah
Keyword(s):  
Organic Matter ◽  
Moisture Content ◽  
Clay Minerals ◽  
Control Sample ◽  
College Of Agriculture ◽  
Relative Moisture Content ◽  
X Ray ◽  
Corn Cobs ◽  
Relative Moisture

To study role of gypsum and corn cobs in linkage of fractions in cracking soils. Three soils (Al-Diwaniya , Al-Wihda and college of Agriculture / Abu Ghraib) were chosen for this study . They were  treated with two levels of gypsum (0.5 and 1) % with one level (4%) of corncobs . In this experiment , 2 kg of each studied soil were treated with same levels of corn cobs and gypsum above and incubated at 30 + 2 °C for 90 days and 80% relative moisture content at 33 kpa. And then the soils were sieved with 1 mm sieve to measured the x-ray diffractions . The results showed : The intensity of clay minerals peaks which treated with gypsum and corn cobs were decreased comparing with control sample. We believed that the gypsum should be facculated on clay minerals surfaces and mask them to appear clearly , and suggested that the gypsum was played an important role in conjugated of soil particles. Results of X-ray diffractions showed that there was no evidence of interaction between organic matter (corn cobs) and clay mineral inter layers.  

Exploring the Use of Machine Learning to Automate the Qualitative Coding of Church-related Tweets

2020 ◽  
Vol 14 (2) ◽  
pp. 140-159
Author(s):  
Anthony-Paul Cooper ◽  
Emmanuel Awuni Kolog ◽  
Erkki Sutinen
Keyword(s):  
Machine Learning ◽  
Online Community ◽  
High Volume ◽  
Machine Learning Algorithms ◽  
Supervised Machine Learning ◽  
Social Media Data ◽  
Twitter Data ◽  
Resource Intensity ◽  
Media Data ◽  
Better Than

This article builds on previous research around the exploration of the content of church-related tweets. It does so by exploring whether the qualitative thematic coding of such tweets can, in part, be automated by the use of machine learning. It compares three supervised machine learning algorithms to understand how useful each algorithm is at a classification task, based on a dataset of human-coded church-related tweets. The study finds that one such algorithm, Naïve-Bayes, performs better than the other algorithms considered, returning Precision, Recall and F-measure values which each exceed an acceptable threshold of 70%. This has far-reaching consequences at a time where the high volume of social media data, in this case, Twitter data, means that the resource-intensity of manual coding approaches can act as a barrier to understanding how the online community interacts with, and talks about, church. The findings presented in this article offer a way forward for scholars of digital theology to better understand the content of online church discourse.

Mol2vec: Unsupervised Machine Learning Approach with Chemical Intuition

2017 ◽  
Author(s):  
Sabrina Jaeger ◽  
Simone Fulle ◽  
Samo Turk
Keyword(s):  
Machine Learning ◽  
Language Processing ◽  
Supervised Machine Learning ◽  
Learning Approach ◽  
Learning Approaches ◽  
Unsupervised Machine Learning ◽  
Feature Representations ◽  
Machine Learning Approach ◽  
The Individual ◽  
Vector Representations

Inspired by natural language processing techniques we here introduce Mol2vec which is an unsupervised machine learning approach to learn vector representations of molecular substructures. Similarly, to the Word2vec models where vectors of closely related words are in close proximity in the vector space, Mol2vec learns vector representations of molecular substructures that are pointing in similar directions for chemically related substructures. Compounds can finally be encoded as vectors by summing up vectors of the individual substructures and, for instance, feed into supervised machine learning approaches to predict compound properties. The underlying substructure vector embeddings are obtained by training an unsupervised machine learning approach on a so-called corpus of compounds that consists of all available chemical matter. The resulting Mol2vec model is pre-trained once, yields dense vector representations and overcomes drawbacks of common compound feature representations such as sparseness and bit collisions. The prediction capabilities are demonstrated on several compound property and bioactivity data sets and compared with results obtained for Morgan fingerprints as reference compound representation. Mol2vec can be easily combined with ProtVec, which employs the same Word2vec concept on protein sequences, resulting in a proteochemometric approach that is alignment independent and can be thus also easily used for proteins with low sequence similarities.

Sign in / Sign up

Export Citation Format

Share Document