KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Search Results

Now showing 1 - 6 of 6

Some of the metrics are blocked by your
consent settings
A novel strategy of NIR spectra multivariate calibration in the presence both of small dataset and non-linearity: A comparative study
(2023-12-01)
Devianti
;
Ismy, Adi Saputra
;
Siahaan, Herbert Hasudungan
;
Sitorus, Agustami
The presence of non-linearity and, at the same time, the small number of datasets are often the constraints that appear together in the case of NIR spectra (381–1065nm). This makes some chemometricians think again about presenting a reasonable and robust calibration model using the linear calibration method. On the other hand, even though obtaining a high and robust calibration model, the NIR spectra-based approach is still an alternative method that must still consider low cost and ease of getting it. This study introduces a novel strategy for developing robust calibration models from small and non-linearity NIR spectra datasets. The prediction performance of two groups of chemometric methods, linear (partial least squares regression, PLSR) and non-linear calibration techniques (k-nearest neighbor, k-NN; Ada boosting, AB; Bayesian ridge regression, BRR), were also compared and investigated in depth. A total of forty raw NIR spectral data was used to develop a calibration model to predict the content of B-pinene, D-limonene, and safrole from the nutmeg fruit. The first strategy, non-linearity due to the effect of light scattering on the NIR spectral data, will be handled directly by the non-linear calibration technique algorithm from machine learning to generate the non-linearity model without preprocessing techniques. The second strategy, the robustness of the model, is tested by performing random splitting of data several times without supervision and ending with a rigorous statistical procedure adopted to ensure reliable comparison. The results suggest that the non-linear calibration method is the most promising among the investigated methods. Furthermore, although none of the techniques is always the best to predict on all references, k-NN (for prediction of B-pinene and safrole) and BRR (for prediction of B-pinene and D-limonene), some of them are found to be the most promising in terms of low prediction error (the maximum R<inf>p</inf><sup>2</sup> is 81.6%, and RMSE is less than 1.139%). There are non-linear calibration techniques explored with limited success being achieved.
Some of the metrics are blocked by your
consent settings
Effect of Handwashing During COVID-19 Pandemic to Domestic Water Estimation: Case Study in Banda Aceh City, Indonesia
(2023-02-01)
Devianti
;
Syahrul
;
Afriza, Ridhofa Hafira
;
Sitorus, Agustami
;
Thamren, Dewi Sartika
New normal routines have continued to campaign since the COVID-19 pandemic broke out in 2019. One of these new habits is to keep washing your hands after every activity. Hand washing can be done using hand sanitizer or soap and washed in running water. As a result, the need for water to meet the habit of washing hands is expected to affect domestic water needs in a certain area. Therefore, this study aims to estimate the increase in domestic water demand during the COVID-19 pandemic caused by the new routine of washing hands in the research area in the city of Banda Aceh, Indonesia. In addition, this study will also estimate domestic water needs until 2030 if the COVID-19 pandemic has not ended. Innovations in this research can help increase efficiency in water use and help prevent the spread of disease. This study uses a sampling method in several places in Banda Aceh city to obtain data related to the volumetric water used, handwashing time, and frequency of handwashing. Besides, data in water discharge from water supply companies in Banda Aceh city from 2018 to 2020 was also collected. Finally, data on the population of Banda Aceh city was also collected. The information and data are then analyzed using a statistical approach between supply and demand. Although it appears that there is a projected increase in domestic water demand of 1.89% per year due to the COVID-19 pandemic from 2021 to 2030, this is still 41.48% greater than the ability of water supply companies in the city of Banda Aceh to meet domestic water needs up to 2030. In conclusion, if the pandemic continues until 2030, with the expected increase in population, the domestic water needs in Banda Aceh city will still be fulfilled.
Some of the metrics are blocked by your
consent settings
Vis-NIR spectra combined with machine learning for predicting soil nutrients in cropland from Aceh Province, Indonesia
(2022-12-01)
Devianti
;
Sufardi
;
Bulan, Ramayanty
;
Sitorus, Agustami
Rapid analytical methods are needed to measure soil nutrient content in cropland, especially in Aceh Province, Indonesia. This is necessary for quick and accurate decision-making on the suitability of the land in terms of soil nutrients and the types of plants to be cultivated on its cropland. Visible near-infrared (Vis-NIR) spectroscopy with suitable chemometric methods through applied machine learning algorithms could be used to predict soil nutrients in the land of agriculture. The current study compared the implementations of machine learning algorithms (support vector machine for regression (SVR), partial least squares artificial neural network (PLS-ANN) and gradient-boosted tree regression (GBRT)) to predict soil nutrients (TN,TP, and TK content) in cropland in Aceh province (Indonesia). The approaches studied used three algorithms of machine learning with four preprocessing employed from spectral data. Samples (n = 102) of soil horizons (0–60 cm) were taken from ten regions in the province of Aceh (Indonesia) and the soil nutrient was measured, including the TN content by the Kjeldahl method and the TP and TK content by the Bray method. Their Vis-NIR spectra (400–2150 nm) were scanned after air drying and ground into powder. 71 examples were used to create the models, while the remaining 31 were used for validation. All of the machine learning algorithms tested as a chemometric approach yielded outstanding models for quantitative estimations of TN, TP, and TK content. Generally, the accuracy of the SVR models of the algorithm utilizing the full spectra was equivalent to that of the PLS-ANN models. Nevertheless, the ANN algorithm using reduced component spectral data (PLS-ANN) served more usefulness than the SVR algorithm depending on the preprocessing method. The most precise models for the content of TN, TP and TK were obtained using the GBRT algorithm (RPD = 2.64, 3.93 and 2.38 for the content of TN, TP and TK, respectively). The results demonstrate that Vis-NIR related to the machine learning algorithm is trustworthy to apply to measure the content of TN, TP, and TK in soil cropland.
Some of the metrics are blocked by your
consent settings
Performance Evaluation of Pre-Processing and Pre-Treatment Algorithm for Near-Infrared Spectroscopy Signals: Case Study pH of Intact Mango “Arumanis”
(2022-08-01)
Agustina, Sri
;
Devianti
;
Bulan, Ramayanty
;
Muslih, Muhamad
;
Sitorus, Agustami
pH is one of the important physical parameters to characterize mango damage because it can indicate changes in the structure and chemical content of the fruit. Thus, the present work evaluated the possibility of NIRs as a rapid and non-destructive tool for measuring the pH properties of intact mango from the cultivar "Arumanis" (Mangifera indica L.) using several algorithms for pre-processing, pre-treatment, and prediction. Three different algorithm predictions, namely principal component regression (PCR), partial least squares regression (PLSR), and support vector machine regression (SVMR), were used and compared to predict the pH of mangos. A total of 16 pre-processing and pretreatment algorithms are used to support algorithm prediction, and the results are also compared with the raw data spectra. The NIR spectral data used range from 1000 to 2500 nm. Algorithm performance will be evaluated using RMSE, error differences and concluded using RPD. The results show that the prediction of the PLSR algorithm can be performed with an RPD of 8.17, which is more significant than the PCR and SVMR algorithms, which are 1.04, and 1.90, respectively. To support this, pre-processing and pretreatment of the second derivative Savitzky–Golay is the best algorithm that can be used to predict the pH of the whole mango cultivar "Arumanis".
Some of the metrics are blocked by your
consent settings
Influence of Biopores Infiltration Holes on the Level Erosion in Oil Palm Plantations Area
(2022-04-01)
Devianti
;
Irwansyah
;
Yunus, Yuswar
;
Arianti, Nunik Destria
;
Thamren, Dewi Sartika
The extension of oil palm plantations in Indonesia has encroached on land with a slope of more than 15%, which impacts the possibility of erosion and landslides. However, conservation efforts to reduce erosion are yet to be fully established. Therefore, the present work studies the effect of biopores infiltration holes on erosion at oil palm plantations area with land slopes greater than 15%. Besides, surface runoff with erosion is modeled to find the relationship. The method used in this study is to combine mechanical conservation methods in the form of biopores infiltration holes in an area that already has cover crops, such as Mucuna Bracteata. Two experimental plots were designed, namely (i) plots without biopores infiltration holes and (ii) plots with biopores infiltration holes. The results showed that soil erodibility in the oil palm plantations area was of a high of 0.65. Applying biopores infiltration holes in the field reduced surface runoff and erosion rates by 31.81% and 29.66%, respectively. The relationship of surface runoff with erosion rates on the land shows a very close case where the coefficient of determination in each plot is 0.96 and 0.92.
Some of the metrics are blocked by your
consent settings
Modeling of Surface Runoff Estimation in Tropical Palm Dates Plantations: A Case Study in Aceh Province, Indonesia
(2022-02-01)
Devianti
;
Syahrul
;
Kamisna, Dian
;
Sitorus, Agustami
;
Thamren, Dewi Sartika
One of the most popular surface runoff estimation methods is the rational method. Unfortunately, this method has several concentration-time approaches that have been developed, as one of the parameters, which are specific to the environment to increase the accuracy of the runoff estimation. Therefore, this study aims to estimate surface runoff using a rational method with several concentration-time approaches in order to obtain the best accuracy in tropical palm dates plantations in Aceh Province, Indonesia. The concentration-time approaches studied were Kerby, Kirpich, Manning, Bransby Williams, Federal Aviation Agency (FAA), and Natural Resources Conservation Service (NRCS). This research was conducted by making a test plot in the plantation with the length, width, and slope of 22 m, 4 m, and 25%, respectively. Each side of the test plot is given a barrier plate with a height of 15 cm and embedded as deep as 30 cm. In addition, on the bottom side, there is a runoff collection tank with a capacity of 50 L. The physical properties of the soil on the test plots in the form of structure, texture, porosity, permeability, and organic C were granular, sandy loam, 0.43%, 1.84 cm/day, and 1.25%, respectively. The test was carried out from March to November 2020 with 37 days of rain. The results of this study indicate that there are significant differences between each concentration-time approach being tested. The best runoff estimation uses the Bransby William method in units of l/hr with the root mean square of 7.95.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results