An Artificial Neural Network Examination Of The Intention To Implement Blockchain In The Supply Chains Of SMEs In Tonga

The research intends to examine the impacts of the technology, organization, and environmental factors on the implementation of blockchain in the supply chains of SMEs in the Kingdom of Tonga. These include regulatory support, competitive pressure, cost, upper management support, complexity, and relative advantage. The research uses SEM-PLS to test the hypotheses and the Artificial Neural Network method to analyze and classify survey data from 201 SMEs. Findings show that relative advantage, cost, complexity, and competitive pressure significantly affect implementing blockchain in the supply chains. As SMEs frequently have limited capital to invest in technology but meets the same obligations to streamline business operations to optimize profits, blockchain provides a feasible choice for the firms’ sustainability with its characteristics of security, transparency, and immutability that are prospective to develop SMEs’ performance. Thus, the paper provides novel insight regarding the determinants of SMEs' intention to implement blockchain in their supply chains.

Application of Artificial Neural Network Method as A Detection of Blood Fat Disorders in Images of Complete Blood Examination

Based on various epidemiological studies, it is stated that blood lipids are the main risk factor for atherosclerosis that leads to coronary heart disease. In patients with blood lipid disorders, red blood cells undergo deformability so that their shape is flatter than normal red blood cells, which are round. The research entitled Application of Artificial Neural Network Method as Detection of Blood Fat Abnormalities in Image of Complete Blood Examination Results was conducted to help facilitate laboratory examinations. This research hopes that it will provide appropriate early detection to support the expert diagnosis. This research consists of two stages. The first stage is digital image processing to obtain area, perimeter, and eccentricity features. These three features will be used as input to the Backpropagation Neural Network program as the second stage. At this stage, blood lipid abnormalities are detected from features that have been obtained from image processing. The accuracy of detecting blood lipid abnormalities with ANN Backpropagation is 85%.

Machine learning methods for Precipitable Water Vapor estimation by radiometric data in millimetre wavelength

This work deals with the first try to calculate the amount of Precipitable Water Vapor (PWV) in atmosphere by using machine learning and AI methods. We use the detector voltages series measured by radiometric system “MIAP-2” as the initial data for machine learning. The radiometer MIAP-2 works by “atmospheric dip method” in 2mm and 3mm atmospheric transparency windows. We also have PWV data series collected by Water Vapor Radiometer and GNSS receiver for data validation. The best convergence results were demonstrated by the independent component analysis (ICA) method with coefficient of determination R2= 0.53 and artificial neural network method (ANN) with R2= 0.8. These methods allow to reduce the systematic errors due to direct PWV calculation from raw radiometric data avoiding unnecessary steps opacity calculation.

The application of artificial neural network for quality prediction of industrial standard water

Industrial Standard water is a source of water before being distributed in industry and household in a certain area. For the sake of health, quality water is a must to fulfill and control. Quality of water having several variables as indicators. One indicator, namely, Turbidity. It is defined as the level of cloudiness of water due to the presence of particles, mud or microorganisms. The highest of turbidity value meaning the index of water quality is low. In this study, we apply the Artificial neural network method for predicting the turbidity value. Three input variables are engaged, PH level, color spectrum, and electrical conductivity. As much of 827 data were collected during six months. Seventy percent are used for training and the rest thirty percent were used for testing. The ANN architecture consists of 3-6-1 configuration, 3 input variables, 6 hidden layers, and 1 output variable. The training was set into 1000 epoch and the MSE shows 0,0013, meaning that the ANN has the power of prediction. The prediction of turbidity level has a managerial implication as supporting information for purchasing decision of material in water processing

Prakiraan Beban Puncak Pada Transformator GITET 150 kV Kesugihan Cilacap Menggunakan Jaringan Syaraf Tiruan Multilayer Feedforward Dengan Algoritma Backpropagation

The increasing population and the growth of the industrial world, offices, hotels, and modern markets must be directly proportional to Indonesia's availability of electrical energy. The availability of sufficient electrical energy can affect the quality of life of the people and foster investor confidence in our country. Studies on the prediction (estimation) of peak electrical loads in electricity in Indonesia can be carried out using the Artificial Neural Network (ANN) method. The estimation of electricity load for the next 5 years is strongly influenced by several parameters, including population growth and peak load data of 150 kV GITET, Kesugihan Cilacap. This study took population data and peak load data at GITET 150 KV Kesugihan Cilacap in the past 5 years. The data used in this study were actual data, starting from 2015 to 2019. To display the results of the estimated electrical load on the 150 kV GITET transformer, the authors used the artificial neural network method. The peak electrical loads estimation results using artificial neural networks for electricity loads in the next 5 years, to wit from 2020 - 2024. The estimated peak load in Lomanis District is20.0311 MW, 24.443 MW, 19.9707 MW, 19.9705 MW and 19, 9705 MW. In Gombong District, the estimated peak load is 57,398 MW, 57,472 MW, 57,476 MW, 57,474 MW, and 57,479 MW.

Slide Type Landslide Susceptibility Assessment of the Büyük Menderes Watershed Using Artificial Neural Network Method

The Büyük Menderes watershed is the largest drainage watershed in Western Anatolia with an area of approximately 26000 km2. In the study area, almost 863 landslides occurred, extending over 222 km2 with a mean landslide area of 0.21 km2. In this study, landslide susceptibility assessment was carried out using Artificial Neural Network method which is one of the data driven methods. Geology, digital elevation model, slope, topographic wetness index, roughness index, plan, profile curvatures, and proximity to the active faults and rivers were used as landslide conditioning factors. In susceptibility assessments, landslides were separated by 70 % analysis, 15 % test and validation data sets by random selection method. The performance of the landslide susceptibility map was assessed by the area under the receiver operating characteristic curves, error histogram, and confusion matrix, respectively. The area under the receiver operating characteristic curves, analysis, testing, validation, landslides and study ares was found 0.82, 0.84, 0.86, 0.82. The susceptibility map had a high perediction rate in which high and very high susceptible zones corresponded to 26 % of the study area including 82 % of the recorded landslides.