Machine learning-assisted ammonium detection using zinc oxide/multi-walled carbon nanotube composite based impedance sensors

AbstractWe report a machine learning approach to accurately correlate the impedance variations in zinc oxide/multi walled carbon nanotube nanocomposite (F-MWCNT/ZnO-NFs) to NH4+ ions concentrations. Impedance response of F-MWCNT/ZnO-NFs nanocomposites with varying ZnO:MWCNT compositions were evaluated for its sensitivity and selectivity to NH4+ ions in the presence of structurally similar analytes. A decision-making model was built, trained and tested using important features of the impedance response of F-MWCNT/ZnO-NF to varying NH4+ concentrations. Different algorithms such as kNN, random forest, neural network, Naïve Bayes and logistic regression are compared and discussed. ML analysis have led to identify the most prominent features of an impedance spectrum that can be used as the ML predictors to estimate the real concentration of NH4+ ion levels. The proposed NH4+ sensor along with the decision-making model can identify and operate at specific operating frequencies to continuously collect the most relevant information from a system.

Download Full-text

The Effect of Accounting Information and Organizational Culture on Decision Making

Budapest International Research and Critics Institute (BIRCI-Journal) Humanities and Social Sciences ◽

10.33258/birci.v3i1.800 ◽

2020 ◽

Vol 3 (1) ◽

pp. 522-530

Author(s):

Teresa Paulina Sihombing ◽

Nasirwan Nasirwan ◽

Chandra Situmeang

Keyword(s):

Decision Making ◽

Organizational Culture ◽

Catholic Education ◽

Accounting Information ◽

Relevant Information ◽

Partial Least Square ◽

Least Square ◽

Education Foundations ◽

Organizational Culture Theory ◽

Decision Making Model

This study examines the educational foundation's organizational decision making model that is the influence of accounting information and organizational culture on decision making. This research is a quantitative study with descriptive and inferential analysis. The sample of this study was 72 Catholic education foundations in Indonesia, which were tested by Partial Least Square (PLS) based analysis and data processing methods with the Smart PLS 3.0 program. This study obtains some empirical evidence, namely, first, accounting information significantly influences decision making. These results are consistent with the theory that the main purpose of the foundation's financial statements is to provide relevant information to meet the foundation's internal and external interests to help decision makers make the best decisions for the organization. Second, organizational culture significantly influences decision making. This result is in line with organizational culture theory which states that organizational culture is a value that is used as a reference in all decisions and actions of members of the organization and that reflects the goals, identity, and standard of evaluation of everything in the organization. So it was concluded that the best decision was a decision made based on accounting information and organizational culture at a Catholic education foundation in Indonesia

Download Full-text

Decision Making Model for Choosing Normal Maternity or Cesarean Section with Machine Learning Approach

Proceedings of the International Conference on Health Informatics, Medical, Biological Engineering, and Pharmaceutical ◽

10.5220/0010289200880095 ◽

2020 ◽

Author(s):

. Rimin ◽

Ermi Girsang ◽

Sri Lestari R. Nasution

Keyword(s):

Machine Learning ◽

Decision Making ◽

Cesarean Section ◽

Learning Approach ◽

Machine Learning Approach ◽

Decision Making Model

Download Full-text

Performance Improvement of Zinc Oxide Photoanode-Based Dye-Sensitized Solar Cells by Multi-Walled Carbon Nanotube

Journal of Nanoscience and Nanotechnology ◽

10.1166/jnn.2010.2773 ◽

2010 ◽

Vol 10 (11) ◽

pp. 7217-7220

Author(s):

Anon Chindaduang ◽

Pattasuda Duangkaew ◽

Sirapat Pratontep ◽

Gamolwan Tumcharern

Keyword(s):

Zinc Oxide ◽

Solar Cells ◽

Carbon Nanotube ◽

Performance Improvement ◽

Dye Sensitized Solar Cells ◽

Dye Sensitized ◽

Multi Walled Carbon Nanotube ◽

Sensitized Solar Cells

Download Full-text

Synthesis and characterization of a novel non-enzymatic glucose biosensor based on polyaniline/zinc oxide/multi-walled carbon nanotube ternary nanocomposite

Journal of Electrochemical Science and Engineering ◽

10.5599/jese.666 ◽

2019 ◽

Vol 9 (3) ◽

pp. 207-222 ◽

Cited By ~ 3

Author(s):

Soha Mohajeri ◽

Abolghassem Dolati ◽

Khashayar Yazdanbakhsh

Keyword(s):

Zinc Oxide ◽

Carbon Nanotube ◽

Limit Of Detection ◽

Industrial Applications ◽

Glucose Biosensor ◽

Potential Cycling ◽

Cobalt Sulfate ◽

X Ray ◽

Ternary Nanocomposite ◽

Multi Walled Carbon Nanotube

Novel polyaniline/zinc oxide/multi-walled carbon nanotube (PANI/ZnO/MWCNT) ternary nanocomposite was fabricated as a non-enzymatic glucose biosensor. Thermal chemical vapor deposition (CVD) process was employed to synthesize vertically aligned MWCNTs on stainless steel substrates coated by Co catalyst nanoparticles. In order to fabricate sensitive and reliable MWCNT-based biosensors, nanotubes density and alignment were adjusted by varying the CVD reaction time and cobalt sulfate concentration. The fabricated nanotubes were modified by ZnO particles through the potentiostatic electrodeposition technique. Optimal electrodeposition potential, electrodeposition time, and electrolyte concentration values were determined. The optimized ZnO/MWCNT nanocomposite was reinforced by polyaniline (PANI) nanofibers through the potential cycling technique, and the morphology, elemental composition, and phase structure of the fabricated nanocomposites were characterized by scanning electron microscopy (SEM), energy dispersive X-ray spectroscopy (EDX), and X-ray diffraction (XRD), respectively. The sensing mechanism of the PANI/ZnO/MWCNT electrode for the electrochemical detection of glucose was investigated, and the limit of detection and sensitivity values of the designed sensor were determined. The fast response time of the ternary nanocomposite-based sensor as well as its satisfactory stability and reproducibility, makes it a promising candidate for non-enzymatic detection of glucose in biomedical, environmental, and industrial applications.

Download Full-text

Unsupervised Learning and Robust Optimization in the Portfolio Problem

UNIVERSITY NEWS. NORTH-CAUCASIAN REGION. NATURAL SCIENCES SERIES ◽

10.18522/1026-2237-2020-4-4-9 ◽

2020 ◽

pp. 4-9

Author(s):

Grigorii I. Beliavsky ◽

Natalia V. Danilova ◽

Alexey D. Logunov

Keyword(s):

Machine Learning ◽

Decision Making ◽

Robust Optimization ◽

Unsupervised Learning ◽

Optimization Problem ◽

Clustering Algorithm ◽

Learning Problems ◽

Portfolio Problem ◽

Robust Optimization Problem ◽

Decision Making Model

Robust optimization in various problems of science and technology arises from the uncertainty of the parameters that determine the decision-making model. The parameters can be judged on the basis of a large number of observed examples. This challenge is to customize a solution based on a large number of examples that works well for examples that were not involved in customizing the solution. In this sense, the robust optimization problem belongs to machine learning problems. The paper uses a dichotomous clustering algorithm to determine the range of parameters for the optimal portfolio problem.

Download Full-text