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
Prediction of CO2 emissions using machine learning
(2024-01-01)
Bussaban, Kanyarat
;
Kularbphettong, Kunyanuth
;
Raksuntorn, Nareenart
;
Boonseng, Chongrag
Carbon dioxide (CO<inf>2</inf>) contributes significantly to climate change as a greenhouse gas. The Earth's atmosphere is naturally kept warm enough to support life by greenhouse gases which trap heat in the atmosphere. However, human activity has significantly increased the amount of CO2 in the atmosphere because of deforestation and the use of fossil fuels. One of the key concerns with human evolution that fuels global climate change is carbon dioxide (CO<inf>2</inf>). It is released as fuels burn and as a result, people worldwide are gradually becoming more conscious of environmental issues. Effective policy formulation requires an investigation of the factors influencing CO<inf>2</inf> emissions, yet tiny datasets and traditional research methodologies have hampered prior investigations. This research uses three prediction models to estimate CO<inf>2</inf> trapping efficiency among CO<inf>2</inf> emissions, energy use and GDP: Multiple Linear Regression (MLR), Support Vector Machine (SVM) and Random Forest (RF). The machine learning (ML) techniques used in this work have demonstrated strong performance with multiple linear regressions, support vector machines and random forest models with mean absolute error (MAE), mean absolute percentage error (MAPE) and root mean square error (RMSE). The investigation has proposed a technique for approximating CO<inf>2</inf> emissions and the results indicate that Support Vector Machine (SVM) can attain the highest degree of precision. The outcome could be a useful model for the decision support system to enhance an appropriate course of action for reducing CO<inf>2</inf> emissions worldwide.
Some of the metrics are blocked by your
consent settings
Enriched sewage sludge from anaerobic pre-treatment in spurring valorization potential of black soldier fly larvae
(2022-09-01)
Raksasat, Ratchaprapa
;
Abdelfattah, Eman Alaaeldin
;
Liew, Chin Seng
;
Rawindran, Hemamalini
;
Kiatkittipong, Kunlanan
The valorization of sewage sludge by black soldier fly larvae (BSFL) has gained attentions for sewage sludge management since the sludge can be reduced securely as well as larval biomass can be used for biorefineries application. Nevertheless, the BSFL growth was impeded while assimilating nutrition from sewage sludge due to the presence of extracellular polymeric substances (EPS) that had entrapped the essential nutrients inside. Accordingly, the pre-treatment of sewage sludge via anaerobic digestion at different pH was employed in this work to rupture the EPS structure and release more nutrients for larval growth. The results showed that larvae fed with raw sewage sludge had attained the lowest final larval weight (2.05 ± 0.38 mg/larva) as opposed to batches fed with pre-treated sewage sludges. This was because the soluble carbohydrate (more than 6.81 ± 1.31 mg of glucose/g sewage sludge) in EPS was released after anaerobic pre-treatment, facilitating larval assimilation for growth. Furthermore, it was observed that further increasing of pH for sewage sludge pre-treatment had led to lower final larval weight gained due to the inhibitory effect stemming from ammonia production at higher pH. The anaerobic pre-treatment of sewage sludge being executed at pH 3 for 8 days had achieved the highest final larval weight at 7.34 ± 0.97 mg/larva. The still low quality of sewage sludges after the pre-treatment also offered benefit, where high sewage sludge reduction and waste reduction index were recorded due to the necessity of BSFL to consume more sewage sludge in compensating the nutrients destitution in sludge. Lastly, the possibility of predicting final larval weight was successfully materialized via a statistical model derived from the multiple linear regression method. The derived model incorporated the interactive parameters of anaerobic pre-treated pH and durations at various combinations could predict the final larval weight.
Some of the metrics are blocked by your
consent settings
Multiple linear regression using gradient descent: A case study on Thailand car sales
(2017-01-01)
Netisopakul, Ponrudee
;
Leenawong, Chartchai
Severe fluctuations in Thailand car sales had enormous impacts on the automobile and related industries. A reliable forecasting model is needed to accurately forecast the car sales for the next production batch. Using ten-year car sales data, this research proposes a machine learning approach using gradient descent (GD) to fitting multiple linear regression for Thailand car sales forecasts. The resulted forecasting accuracy is then compared with that of a normal equation method (NE) as well as that obtained from a statistical package (SP). First, two independent variables (2IVs): Thailand’s Gross Domestic Product and the 12-month Loan Rate are used in the proposed models. Then, dummy seasonal variables (Season) are added to the regression equations. Finally, dummy event flag variables (Event) are added. Totally, five sets of experiments are conducted. The experiment results show that NE produces the same regression equations as SP. Both GD and NE methods yield exactly the same results for 2IVs, but GD yields slightly less prediction accuracy than NE’s in Season and Event experiments. This research concludes that gradient descent has comparable forecasting accuracy to those from other methods. Nevertheless, when the regression contains dummy variables, caution is recommended.
Some of the metrics are blocked by your
consent settings
A statistical assessment of the impact of land uses on surface water quality indexes
(2012-06-30)
Seeboonruang, Uma
The release of wastewater from various land uses is threatening the quality of surface water. Different land uses pose varying degrees of danger to water resources. The hazardous extent of each activity depends on the amount and characteristics of the wastewater. The concept of the contamination potential index (CPI) of an activity is introduced and applied here. The index depends on the quantity of wastewater from a single source and on various chemicals in the waste whose concentrations are above allowable standards. The CPI concept and the land use impact assessment are applied to the surface water conditions in Nakhon Nayok Province in the central region of Thailand. The land uses considered in this study are residential area, industrial zone, in-season and off-season rice farming, and swine and poultry livestock. Multiple linear regression analysis determines the impact of the CPIs of these land uses on certain water quality characteristics, i.e., total dissolved solids, electrical conductivity, phosphate, and chloride concentrations, using CPI. s and previous water quality measurements. The models are further verified according to the current CPIs and measured concentrations. The results of the backward and forward modeling show that the land uses that affect water quality are off-season rice farming, raising poultry, and residential activity. They demonstrate that total dissolved solids and conductivity are reasonable parameters to apply in the land use assessment. © 2012 Elsevier Ltd.
Some of the metrics are blocked by your
consent settings
An Assessment of saline soil effects on land use activities: A case study in Nakhon Panom Province, Thailand
(2010-02-01)
Seeboonruang, Uma
The Northeastern Part of Thailand contains wide area of saline affected soil. Among these, Nakhon Panom Province has received a great deal of attention and thus national budgets in order to raise the economic and social conditions. Many reports have stated that various land uses are likely to be declined due to the salinity problem to some certain extent. However, little to none research has been trying to quantify the effects of such the problem on the land use patterns. This study introduces a simple but practical technique to quantitatively relate the degree of salinity to land use densities. The technique utilizes the multiple linear regression technique to relate the basin salinity index with many land use activities, e.g. community and housing, rice farmings, and livestocks. This method is applied on the subdistrict or "amphoe" units in Nakhon Panom. Initially, the densities of various land use activities are computed based on all secondary data. Subsequently, an equation for basin salinity index (BSI) is formulated in order to figure the severity of salinity problem in specific amphoes. Then, simple linear regression is performed between amphoe BSI and land use densities. Finally, multiple linear regression is obtained linking between the BSI and all the densities. BSI = 23.18 - 176.09 × (population density) - 70.96 × (in-season rice farming density) + 8.17 × (off-season rice farming density) + 55.53 × (cow livestock density) + 3.67 × (poultry livestock density) - 16.19 × (swine livestock density) + 0.00 × (catched fish density). It is found that the salinity has a great negative impact on the population density, in-season rice farming, and swine livestock, while it establishes positive influence on off-season rice farming, cow livestock, and poultry livestock.
Some of the metrics are blocked by your
consent settings
Evaluation of pectin constituents of Japanese pear by near infrared spectroscopy
(2007-01-01)
Sirisomboon, Panmanas
;
Tanaka, Munehiro
;
Fujita, Shuji
;
Kojima, Takayuki
Japanese pears (Pyrus serotina Rehder var. culta 'Housui') collected in 1997 and 1998 were measured for their pectin constituents including alcohol insoluble solids, water soluble pectin, oxalate soluble pectin, non-soluble pectin and total pectin. Near infrared (NIR) spectra (1100-2500 nm) were measured within the range of at 2 nm intervals. The NIR spectra of intact Japanese pear were measured by fiber optics in interactance mode and the spectra of juice were measured by diffuse trans-reflectance. The spectral data used were raw spectra and their second derivative. By using multiple linear regression, calibration equations developed from the intact fruit spectra and juice spectra, the alcohol insoluble solids in the fresh weight (AIS in the FW) and the oxalate soluble pectin content in the alcohol insoluble solids (OSP in the AIS) were accurately predicted (For intact fruit spectra: R = 0.93, SEP = 0.62 for AIS in the FW, and R = 0.95, SEP = 8.48 for OSP in the AIS; For juice spectra: R = 0.93, SEP = 0.63 for AIS in the FW and R = 0.91, SEP = 7.93 for OSP in the FW). In addition, the equations from the juice spectra could be used to predict the water soluble pectin in the alcohol insoluble solids (WSP in the AIS), and the total pectin in the alcohol insoluble solids (TP in the AIS) (R = 0.91, SEP = 1.41 for WSP in the AIS and R = 0.94, SEP = 11.52 for TP in the AIS). The NIR models developed with the data collected in 1998 were not able to predict the 1997 data. This study showed that near infrared spectroscopy has potential to measure the pectin constituents of the Japanese pear. © 2005 Elsevier Ltd. All rights reserved.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results