This paper introduces UV-vis spectroscopy as a potential technique for sensing benzotriazole passivator content in thermally aged transformer insulating oils. The progression of benzotriazole is tracked employing the changes in transmittance value at 500 nm wavelength, which is measured using UV-vis spectroscopy. The results show that the change of transmittance value at 500 nm wavelength is a function of the level of passivator compounds (i.e., in ppm).
Cardiovascular diseases (CVDs) are group disorders affecting the heart or involving constricted blood arteries. Early disease detection increases the likelihood of survival. As a result, newer methods such as machine learning emerged, capable of processing and analysing vast quantities of complex medical data and providing a more accurate prediction of diseases, including CVDs. However, due to factors such as overfitting and bias, the single classifier could not ensure optimum prediction. Thus, this study proposes a stacking ensemble classifier, which combines several single classifiers to produce an optimal predictive model. The Framingham Heart Study dataset was used to train the machine learning algorithms. The exploratory data analysis indicates that CVD was more common in males and diabetic individuals. Furthermore, individuals above the age of 65 were more susceptible to CVDs. Feature selection, missing value imputation, and data sampling were performed as part of data preprocessing. The results show that the proposed stacked ensemble classifier achieved 88.33% accuracy, 89.95% precision, 86.27% recall and 88.07% F1-score. Furthermore, the significance test results indicate that the proposed model performs significantly better than most models evaluated in this research. Finally, the comparative analysis showed that the proposed ensemble classifier performs better than most studies using the same dataset. The proposed model achieved a high F1-score, indicating it can accurately predict the cases with and without CVD.
Radar is a sensor that monitors surrounding areas with electromagnetic waves, detects targets, and is vital equipment for military use. Recently, it has evolved into a form that can simultaneously search, track, and avoid external jamming signals with digital beam formation using a phased array radar. However, errors can occur if the side lobes do not receive accurate results or if the target is located too close. There is also a problem that the price is high. This paper reduces the module of an antenna and shows that its accuracy is similar to before reducing the number of modules. In addition, we analyze the received results from the target using convolution and deconvolution techniques and propose a method to improve image resolution. In this paper, the proposed technique proposes increasing target detection accuracy through simulation.
Image classification is a fundamental task that attempts to classify the images into the classes they belong to. CNN is commonly used for the classification due to its flexibility and stability. This paper treats Curriculum Learning as an assistant method that decides the procedure the CNN ought to be trained. Curriculum Learning is generally defined as a method that divides and orders the training datasets into several different levels of learning difficulties. This paper utilizes the idea of ensemble classification that trains according to the order based on the consensus of different machine learning models. As a result, the proposed Ensemble-Generated Curriculum Learning model achieves higher accuracy compared to that of a single-stage CNN learning with dog face recognition and CIFAR-10 datasets.
PT. XYZ is a company that produces cardboard packaging. The product that is most in demand by customers is snack packaging. Snack packaging products have an erratic demand that affects the production process and ordering of raw materials. Therefore, companies need a more effective improvement proposal design starting from forecasting, inventory, distribution, production planning, and ERP simulation. The data needed to start the research are the raw materials used, data on demand for snack packaging products for the past 1 year, lead times for raw materials, machines used, and other data. Data processing begins with forecasting using the Double Moving Average, Single Moving Average, Weight Moving Average, Double Exponential Smoothing, Single Exponential Smoothing, Cyclic, Linear Regression, and decomposition methods followed by validation and verification of forecasting methods Mean Absolute Deviation, Mean Square Error, Mean Absolute Percent Error, and Standard Error of Estimate. Forecasting results that have been verified are followed by aggregate planning, Rough Cut Capacity Planning with Capacity Planning using Overall Factors, Bill of Labour Approach, Resource Profile Approach, safety stock methods, Material Requirement Planning with the Least Unit Cost, Lot for Lot, Silver Meal, Economic Order Quantity, Period Order Quantity, Capacity Requirement Planning, Distribution Requirement Planning, and Enterprise Resource Planning methods. The proper forecasting method used is the decomposition method which has the least error compared to PT. XYZ methods. The calculation of mixed aggregate planning (overtime and shifts) is the right method because it costs the least total cost, namely ${\$}$ 34023.54. The results of Capacity Requirement Planning and Rough-Cut Capacity Planning calculations do not indicate a lack of capacity to meet the demand for the Master Production Schedule. The proper Material Requirement Planning method is the Period Order Quantity lotsizing method with a 47.6% savings compared to PT. XYZ. Proper distribution planning using the Distribution Requirement Planning method with a savings of 36.3% compared to PT. XYZ methods.
