Smallest Error Value Research Articles

Analysis of the Impact of Meteorological Factors on Predicting Air Quality in South Tangerang City using Random Forest Method

Air pollution has become one of the most significant environmental problems in many cities throughout the world, which can endanger public health and the environment. Understanding the impact of meteorological conditions on air quality is very important to understanding air pollution patterns. This study investigates the influence of meteorological variables on air quality predictions in South Tangerang City, Indonesia, using the Random Forest method. Modeling is carried out by building two scenarios, namely predictions using meteorological variables and predictions without meteorological variables. Prediction performance analysis is measured using MAE, MSE, RMSE, R-square, and accuracy. The accuracy results of the research show that predictions without meteorological variables provide good prediction results with a value of 86.42%, but predictions with meteorological variables have better performance with a value reaching 98.99%. The largest error values from each model were 2.58 MAE, 71.82 MSE, and 8.4747 RMSE obtained in prediction modeling without meteorological variables, while the smallest error values were obtained in prediction modeling using meteorological variables, namely 0.00, 0.01, and 0.0219, respectively, for MAE, MSE, and RMSE. This research contributes to a better understanding of the relationship between meteorology and air pollution and air quality in urban areas and helps develop targeted mitigation strategies to improve air quality and public health, especially in South Tangerang City and the surrounding area.

Prediction of alkali–silica reaction expansions of mortars containing glass waste

The majority of existing findings regarding expansion (EXP) risks in concretes containing waste glass stem from experimental studies. There is a need for rapid assessment methods to ensure safer recycling of glass waste in cementitious composites. In this study, an artificial neural network (ANN) model was developed to accurately predict alkali–silica reaction EXP/mitigation resulting from the integration of glass waste in mortars. The analysis considered glass incorporation either separately as waste glass powder (WGP) and waste glass aggregates (WGAs), or in combination, at contents of up to 100% for WGA and 30% for WGP. A set of 175 mixtures was analysed, considering five distinct variables, which encompassed different mix proportions, involving varying components of cement, natural aggregates, WGP and WGA, in addition to the duration of environmental exposure. The results show that the EXP of WGA mortars decreased with the increased incorporation of WGP. The EXP values obtained from validation and experience confirm the high accuracy of the developed ANN model, with validation coefficients reaching up to 98.061% and a small value of the mean square error.

Development of a High Flow Oxygen Analyzer for Monitoring Oxygen Therapy in Adults Using High Flow Nasal Cannula (HFNC)

Oxygen is a necessity of life that is very rarely owned even though it has a very high value for humans. Our respiratory system directly takes oxygen intake from the surrounding air either or not consciously. Oxygen therapy is a method of administering oxygen at a higher concentration than ambient oxygen, with the treatment or prevention of symptoms and the appearance of hypoxia. The oxygen concentration to be administered to a person is determined by the flow titration required for sufficient SPO2. The accuracy of the oxygen flow delivery system to the patient is very high, so it is necessary to calibrate to determine the correctness of the indication of measuring instruments and measuring instruments stated. This study uses an Arduino microcontroller to process the oxygen concentration output from the OOA101-1 oxygen concentration sensor, then the processed oxygen concentration will be displayed on the TFT LCD. The variable in this study is the oxygen concentration setting value, while the independent variable is the OOA101-1 oxygen concentration sensor. The concentration value is set using an oxygen blender, while the comparison tool used is a gas flow analysis (Citrex H3). At the testing stage, the measurement value is 50% to 100% with a time of 1 minute at each point. Based on the measurements that have been made, the largest error value is obtained at a concentration of 50%, which is 3.07% and the smallest error value is at 100%, which is 0.40%. Data retrieval using a compressor and central oxygen is very influential on the results of the flow and oxygen concentration. The results obtained are more stable than without the use of a compressor and central oxygen.From these results, the calibrator module has an error (value) that is still within the relative limits of the conclusion, which is ±5%. And also the design of this tool is portable and low cost and made for use in hospital establishments as maintenance of HFNC equipment.

Feature selection using non-parametric correlations and important features on recursive feature elimination for stock price prediction

Stock price prediction using machine learning is a rapidly growing area of research. However, the large number of features that can be used can complicate the learning process. The feature selection method that can be used to overcome this problem is recursive feature elimination. Standard recursive feature elimination carries the risk of producing inaccurate algorithms because the top-ranked features are not necessarily the most important features. This research proposes a feature selection method that combines important features and nonparametric correlation in recursive feature elimination for stock price prediction. The data features used are technical indicators and stock price history. The recursive feature elimination method is modified with important features and nonparametric correlation features. The strategy for combining important features and non-parametric features is average weight, 25:75% weight, 75:25% weight, maximum weight, and minimum weight. The performance evaluation results show that the proposed feature selection method succeeded in obtaining small error values. The proposed method for predicting PT Bank Rakyat Indonesia Tbk (BBRI) stock prices obtains mean squared error, root mean square error, mean absolute error, and mean absolute percentage error evaluation values of 0.0000336, 0.00577, 0.00459, and 1.78%, respectively. This shows that recursive feature elimination with feature selection that combines important features and non-parametric correlation works better than the original recursive feature elimination at predicting stock prices.

Fuzzy Logic Method to Control Evenly Distributed and Stable Waterbath Temperature with Four Heaters

Water baths are commonly used in scientific fields to incubate samples at specific temperatures. The temperature of the water bath must be controlled precisely, because even the slightest temperature variation can affect the results of the experiment. It can handle imprecise, uncertain and incomplete information, making it suitable for temperature control in water baths. This research aims to determine the distribution and stability of fuzzy logic control to control the temperature of a water bath with four heaters. Even heat distribution from the four heaters will ensure consistent water bath temperature throughout the bath. This research uses an Arduino microcontroller to process the temperature sensor output from the DS18B20, then the processed temperature value will be displayed on the TFT LCD. The independent variable in this research is the temperature value, while the dependent variable is the DS18B20 temperature sensor. The largest error value from the module measurements is at a temperature setting of 30 ºC on the 2nd temperature sensor with an error value of 1.43%. Meanwhile, the smallest error value is found at a temperature setting of 35 ºC on the 1st and 4th temperature sensors with an error value of 0.01%. Data collection used a digital thermometer comparison tool with 10 repetitions as a temperature sensor reference tool. The results obtained using this sensor are more stable and have a high accuracy value. The results of the research show that the temperature difference between points 1 to 4 when viewed from the error percentage is very small, or it can be said that the temperature distribution is even. The conclusion from these results is that the module has a stable temperature value and the error value is low and is still within the tolerance limit. permitted is ±5%.

APPLICATION OF THE FORECASTING METHOD TO THE DEMAND FOR PRINTING RECEIPTS WITH GTO 46 ENGINE

Forecasting is an important part of every business organization and for every very significant management decision. The purpose of forecasting is to reduce the risk or uncertainty faced by a company in making short-term operational decisions and in planning for long-term growth. The company that is the object of this research is a company operating in the printing sector. Focus on observing receipt products because receipt orders are the highest every month. In the implementation of the production process, there are often shortages of raw materials such as NCR paper or non-carbon required paper so that delivery times are late to reach consumers. The effort used to eliminate/reduce the gap between production and sales is to use a forecasting method which aims to determine product quantity adjustments and when they are needed. Based on data processing using cyclical and linear methods, the method used in calculating the next month's forecast is the Linear method. The linear method has the smallest error values, namely SEE = 1100.57, MAD = 871 and MAPE = 26.34. The total forecast demand for receipt products in November is 4839 pieces

Analisis Pengaruh Ukuran Lantai Muatan Timbangan Terhadap Nilai Error Pada Pengujian Eksentrisitas Timbangan Elektronik Sesuai OIML R76

The use of high-intensity non-automatic weighing instruments can cause users to overlook the load's location during weighing. However, electronic non-automatic weighing instruments maintain measurement accuracy regardless of the load's position. This study aims to analyze the effect of load receptor size on error values when testing non-automatic weighing instruments eccentricity using the OIML R-76 recommended method. Testing the eccentricity of electronic non-automatic weighing instruments with the same construction model, load cell, and indicator but different load receptor sizes can affect the non-automatic weighing instruments' error values. The largest error value on Instrument A, with a load floor size of 40x30cm, is -0.025kg at test point 4. On Instrument A, the smallest error value at test points 1, 2, and 5 is -0.005kg. On Instrument B, with a load floor size of 60x50cm, the largest error value at test points 1 and 4 is -0.005kg, respectively. At test points 2-3-5, the smallest error value on Instrument B is 0kg. The average error on Instrument A is -0.01kg, while on Instrument B it is 0kg. The size of the load receptor affects the increase in the error value of a non-automatic weighing instrument, with larger load receptor resulting in greater error values, even if the construction design of the load receptor support is the same.

Analysis of New 4D Hyperchaotic Systems MACM and Implementation Using Runge-kutta

In general, hyperchaotic system is defined as a chaotic system with more than one positive Lyapunov exponent, this implies that its chaotic dynamics extend in several different directions simultaneously. The discovery of reliable and effective methods for solving hyperchaotic systems is carried out extensively. The aim of this research is to implement nonlinear hyperchaotic using runge-kutta. The NHS system is built by inspecting, modifying and adding one state to the MACM chaotic system. In this study, we use the same initial conditions x_0=y_0=z_0=w_0=1 and the parameters a = 2,b = 2,c = 0.5, and d = 14.5. At first we experiments modified approaches, namely Classic Runge-Kutta Method 3 Order, Runge-Kutta Method Based On Arithmetic Mean, Metode Runge-Kutta Method Based On Geometric Mean, Modified Runge-Kutta Geometric Mean Based Method-1, RKLCM Approaches Instead of RKGM using MAPLE software as a calculation tool. In this work, we observe that the Runge-Kutta Method Based on Arithmetic Mean has the smallest error value with an average variable x of 0.000606953, variable y of 0.009280181, variable z of 0.000378639 and variable w of 0.60781585. Then also in RKLCM Approaches Instead of RKGM it has the largest error value with an average variable x of 0.483789793, variable y of 0.620803849, variable z of 0.92097139, and variable w of 0.596137549.

Solusi Eksak Sistem Imun Terhadap Virus Ebola

The Ebola virus is a deadly disease that causes blood clots in the body's organs and is spread through direct contact with the blood or body fluids of sufferers. Based on this, the immune system in the body will continue to decrease and cause Ebola Hemorrhagic Fever. The 2014-2016 Ebola outbreak in West Africa has accelerated the development of several preventive vaccines against the Ebola virus. The goal of the vaccination is to induce immunity against infectious diseases. And also to stimulate the immune system and its ability to store and remember information about specific pathogens, leading to long-term protective immunity. The model equation for the Ebola virus vaccine in this study involves the concentration of the antigen which is a variable , by means of which the vaccine is inserted into the patient's body where it will attach to B memory cells which are variable , which will then be stimulated by the cells short-lived antibodies are denoted by variables or long-lived cells are denoted by variables , while antibodies will prove efficacy denoted by variables on the patient's immune response. The simulation of the exact solution for the Ebola vaccine uses the integration factor method which will later be compared with numerical simulations according to the parameter values from the research of Irene Balelli et al (2020). The simulation obtained has a very small calculation error value for each variable, which means that the exact value of the Ebola virus vaccination model shows that there is no significant difference to the numerical solution using the order 45 Rungge Kutta method, the largest resulting numerical error is 2.29640283510782×〖10〗^9.

Demand Forecasting Analysis of Body Scrub Product at PT. XYZ Using Autoregressive Integrated Moving Average (ARIMA) Method

PT. XYZ is one of the private companies engaged in the cosmetics industry, especially as a manufacturer of SPA products with natural raw materials. The SPA products produced by PT. XYZ are various kinds of scrubs, body scrubs, masks, essential oils, soaps and other products. Body scrub is the most popular product or best seller in this company. The purpose of this study is to find the best ARIMA model in calculating demand forecasting of body scrub products at PT. XYZ for the period January to December 2024. The method used in this research is the Autoregressive Moving Average (ARIMA) method. There are two ARIMA models that can be used in this study, namely ARIMA (1,1,0) and ARIMA (0,1,1). The selected ARIMA model used to calculate body scrub forecasting at PT. XYZ is the ARIMA (1,1,0) model because it has a smaller error value, namely MSE = 745.46 and MAPE = 7.40%. The results of forecasting the demand for body scrub products at PT. XYZ for the period January to December 2024 using the ARIMA (1,1,0) model show that demand has increased every month with an average demand of 343.4 kg. The error obtained by comparing the forecasting results with the actual sales data for 6 months, namely January - June 2024 is 2.45%, which means that the accuracy of forecasting in 6 months reaches 97.55%.

FPGA Implementation of Kalman Filter for Visible Light

Visible Light (VL) has received significant attention due to its benefits in energy efficiency, wide bandwidth availability, and resistance to electromagnetic interference. This final project discusses VL utilizing the Kalman Filter (KF) to predict and estimate the position of related data. The development of the VL method is carried out using Xilinx FPGA Arty A7 hardware, and the KF implementation is carried out in a two-dimensional framework with the Linear KF approach. The main objective of this Final Project is to implement VL using Photodetectors (Photodiode and Photoresistor LM393) on FPGA. The use of Xilinx FPGA Arty A7 hardware and Xilinx SDK software provides the flexibility and reliability required for system implementation. The results indicate that the implementation of Xilinx FPGA Arty A7-35T with KF and the use of 16 LED and 8 LED configurations yield relatively accurate estimations. While the Photodiode LM393 (PD LM393) sensor does not exhibit superior results compared to the Photoresistor LM393 (PR LM393) sensor, this research effectively optimizes light measurements by utilizing the sensor and KF algorithm. The Root Mean Squared Error (RMSE) results show that for the system with 16 LEDs, KF with PR LM393 has an RMSE of approximately ). This RMSE value indicates that KF with PR LM393 can provide relatively more accurate estimations. Similarly, for the system with 8 LEDs, KF with PR LM393 has an RMSE of around ). In this case, KF with PR LM393 again provides relatively more accurate estimations. Meanwhile, the RMSE result for 2D KF in this system is approximately ), indicating that the KF estimation has a relatively small error value compared to the actual measurement value. This demonstrates that KF effectively reduces noise and measurement data fluctuations in the LM393 Photodetector system with 16 LEDs.

Pemodelan Peramalan Untuk Meningkatkan Efisiensi Penggunaan Thinner No. 17 Jotun di PT.XYZ

PT.XYZ is a company engaged in the business of trading industrial and fabricated goods. PT.XYZ often experiences excessive accumulation of thinner which will cause the storage warehouse to pile up. Therefore, this research aims to develop an effective forecasting model in anticipating the use of Thinner No.17 Jotun at Indonesia . The right forecasting method can help companies plan inventory, reduce the risk of overstock or stockout, and increase efficiency in the supply chain. The development of usage from month to month is increasingly uncertain, so the company wants to know how much Thinner expenditure will be used in the following month by referring to the previous month's expenditure using the single moving average, weighted moving average and single exponential smoothing methods. The software used to assist in this research is POM-QM. From the results of research using the Simple Moving Average method, this method has a MAPE value of 5,841%, the forecast size for the next period, namely period 13, is 285 pcs. This shows that the Simple Moving Average method is the most appropriate method to use to solve the problem of using Thinner No.17 Jotun experienced by PT. XYZ because it has the smallest error value. So it can be concluded that the application of this method provides the right solution for the needs of Thinner No.17 Jotun in the next period.

PERENCANAAN KEBUTUHAN TANDAN BUAH SEGAR DENGAN PERAMALAN METODE SINGLE MOVING AVERAGE DAN SINGLE EXPONENTIAL SMOOTHING

This research examines the problem of procuring raw materials for production in a state-owned enterprise which operates in the oil palm plantation business and processing palm oil Fresh Fruit Bunches (FFB) into CPO (Crude Palm Oil) and Palm Kernel. The factory has a FFB processing capacity of 20 tons/hour, while the company experiences fluctuating supplies of raw materials so that it does not match the available factory capacity and causes loss of production time. With this problem, researchers are trying to find a more accurate forecast that is useful for meeting demand in order to increase the optimization of factory production capacity. The methods used in this research are single moving average and single exponential smoothing. These two methods will be compared by looking for the smallest error value in terms of MAD MSE and MAPE values.. The method with the smallest error value can be a proposed forecasting method for the future. The calculation results show that the single exponential smoothing method has a smaller error value.

The One-Dimensional (1D) Numerical Model: An Application to Oxygen Diffusion in Mitochondria Cell

The first model of oxygen transport was formulated by August Krogh. However, the investigations conducted have yet to yield a complete analytical model and a widely applicable solution for One-Dimensional (1D) network construction. The research sought to provide numerical and analytical solutions for the oxygen transfer model in mitochondrial cells to enable researchers to estimate the molecular dynamics and diffusion characteristics in mitochondrial cells. The oxygen diffusion process in mitochondria was modeled with ID numerical models. The numerical models used to solve the equations were explicit and implicit. The explicit model consisted of Forward Time Center Space (FTCS) and DuFort-Frankel. Meanwhile, the implicit model had Crank-Nicholson and Laasonen. The numerical solutions of the explicit and implicit were divided into four scenarios with a variation of Δt and compared with the analytical solutions. The results show that the Laasonen method is the best in describing the diffusion process. The best scenario with the lowest slope value and small Root Mean Square Error (RMSE) value is scenario 2 (Δt = 3,33E-4 s and Δx = 2,00E-5 cm). The numerical model and analytical solution show that the time required to reach a steady state is 0,7 s. It indicates oxygen exchange in two sides of the mitochondrial cell after 0,7 s.

Automated non-contact measurement of the spine curvature at the sagittal plane using a deep neural network

BackgroundNon-radiographical techniques have been suggested to measure the spine curvature at the sagittal plane. However, a neural network has not been used to measure the curvature. MethodsA single video camera captured images of a standing posture at the sagittal plane from twenty healthy males. Six marker positions along the spine's contour in each image were identified for measuring inclination, thoracic kyphosis, and lumbar lordosis angles. We estimated three inflection points around the neck, hip, and between the neck and hip, followed by identifying two adjacent marker positions per inflection point to compute its tangent. The angular deviation of each tangent line from the horizontal was computed to measure inclination angles. Thoracic kyphosis and lumbar lordosis angles were computed by the angular difference between the two adjacent tangents. A deep neural network was trained with 500,000 iterations using the labeled images from 18 participants (388 and 44 images for training and test set) and then evaluated using the unseen images (2 participants, 48 images; evaluation set). FindingsThe mean total training and test errors were <2 pixels (∼ 0.6 cm). The total error in the evaluation set was qualitatively comparable (∼ 3 pixels = ∼ 0.9 cm), suggesting the model performance was maintained in the unseen data. The angle values between labeled and network-predicted marker positions were similar in the evaluation set. InterpretationThe network training with a relatively small number of images was successful based on the small error values observed in the evaluation set. The model may be an affordable, automated, and non-contact measurement tool for the human spine curvature.

Parameters of pubertal growth spurt in children and adolescents living at high altitude in Peru

ObjectivesThe aim was to estimate the pubertal growth height of children and adolescents living in a high-altitude region of Peru using the Preece-Baines model 1 (1 PB). MethodsA cross-sectional study was conducted in schoolchildren from the department of Puno (Peru) between 3841 and 3874 masl. The age range was between 4 and 17 years. Standing height was evaluated. 1 PB was used to infer the mathematical and biological parameters of stature. ResultsMathematical parameters estimated by the 1 PB model reflected small residual standard error (RSE) values in both sexes (0.25 in boys and 0.27 in girls). In boys, the age at which peak velocity was reached (APHV) was estimated at 13.21 ± 0.33years. While in girls it was 9.96 ± 0.26years (p < 0.05). In general, girls reached APHV (y) 3.25 years earlier than boys. On the other hand, the growth velocity of maximum height [APHV (cm/y)] of boys was higher (6.33 ± 6.06 cm/y) relative to girls (6.06 ± 0.32 cm/y). Estimated final adult height (EFAH) in boys was reached at 166.020 ± 0.99 cm and height at maximum growth velocity (HPHV) was 153.07 ± 0.67 cm, while in girls they were significantly lower (EFAH; 153.74 ± 0.44 cm and HPHV: 139.73 ± 0.84 cm). ConclusionsThis study showed that girls living in Puno at a high altitude in Peru reached APHV 3 years earlier than boys and at the same time reflected slower PHV. These results suggest that pubertal growth at high altitudes is slower in both sexes and especially in girls. Thus, modeling physical growth may be an important step in understanding the onset of puberty at different latitudes.

Penerapan Metode Double Exponential Smoothing dan Regresi Linier pada Peramalan Persediaan Packaging di PT. XYZ

PT. XYZ is one of the company that produces packaging materials, one of which is sacks. This study aims to determine forecasting on sack raw material packaging using the Double Exponential Smoothing method and Linear Regression in these calculations using manual calculation methods using Microsoft excel. The two methods are then identified as having the smallest error value. The data used in this study uses secondary data in the form of sales reports of raw material packaging in the past. Based on the forecasting results obtained using the Double Exponential Smoothing and Linear Regression methods, the smallest error value was obtained in the linear regression method with an error value of 275,711. The forecasting results in the next period were 16,713 by manual calculation. Thus, among the predicted results of the two methods, the linear regression method is the most optical. Keywords: Double Exponential Smoothing; Forecasting; Regresi Linier

Improving Value-at-Risk forecast using GA-ARMA-GARCH and AI-KDE models

The classical autoregressive moving average (ARMA) and generalized autoregressive conditional heteroskedastic (GARCH) models have been widely adopted to forecast Value-at-Risk (VaR), the most popular risk measure in quantitative risk management. Their parameters are commonly estimated using the maximum likelihood estimation (MLE) method, which may show biasedness. This reason motivated us to require optimization through a genetic algorithm (GA) or implement artificial intelligence (AI) to improve the VaR forecast. In this paper, we aimed to compare the performances of the GA-based ARMA-GARCH model and the AI models (linear regression, support vector regression, multilayer perceptron, and long short-term memory) in forecasting the VaR. More specifically, we examined which model performs best. Using Bitcoin, crude oil, and stock index returns, we showed that the GA-ARMA-GARCH and AI models outperformed the benchmark MLE-ARMA-GARCH model. We also revealed that the AI models (particularly multilayer perceptron) integrated with kernel density estimation (KDE) performed relatively better than the GA-ARMA-GARCH model because the former resulted in a higher p-value of the VaR backtesting with a smaller error value. In addition, the cross combination between our models was found to have a higher potential to produce an improvement in the VaR forecast.

Building The Prediction of Sales Evaluation on Exponential Smoothing using The OutSystems Platform

To get a large profit in a company or business is to determine sales predictions for the next period. Prediction or forecasting is one of the keys to the success of sales because the predicted value of sales can be used as a reference to determine the order of goods, so there is no loss. Exponential smoothing method is a fairly superior forecasting method in long-term, medium-term and short-term forecasting. The data to be processed is sales data for the 2020-2022 period. The single exponential smoothing method was chosen because it can determine sales predictions for the next period with the smallest error value. The evaluation method used is MAPE, ME, MAD and MSE where this forecasting method is used to find the smallest error value. Based on the calculation results, the smallest error value obtained is ME at 62.8, MAD at 179.9, MSE at 55564.5, and MAPE at 9.20%. The value is at alpha 0.3. The next stage is to design a prediction system using the out-systems platform version 11.14.1 as a place to design the system. The test results of the system that has been designed to assist business owners in making decisions on product inventory estimates.

Studies on crystallization process for pharmaceutical compounds using ANN modeling and model based control

Solvent selection and Controlling of operating parameters play a crucial role in batch cooling crystallization process. Choosing a best solvent for crystallization process involves more experimentation and time. To overcome this problem, an Artificial Neural Network (ANN) model technique is used to predict the carbamazepine form Ⅲ solubility by considering the thermodynamic properties of different solvents i.e. critical temperature, critical pressure, temperature, molecular weight, and acentric factor. The ANN model was trained and evaluated for solubility at various input data sets using experimental solubility data available in the literature. The ANN model with 20 hidden neurons has given the R2 value of 0.9943 which shows that the developed ANN model can be used for the selection of best solvent for batch crystallization process. Further, to determine the optimal cooling profile of batch cooling crystallization process, a multi-objective optimization problem is formulated by considering objectives as minimizing the coefficient of variation (CV) and maximizing the Number mean size (NMS) of crystals subjected to population balance equations using “method of moments” technique. Two types of temperature strategies i.e., piece-wise constant and piece-wise linear are developed and solved using NSGA-Ⅱ dynamic optimization procedure. The optimal NMS value attained through piece-wise linear strategy was 197.1 µm. This value has been increased by 28.3 µm from the nominal case (without optimization) and the coefficient of variation has decreased from 0.951 to 0.76. Further, optimal NMS value attained through piece-wise constant strategy was 205 µm. The value has been increased by 36.2 µm and the coefficient of variation has decreased from 0.951 to 0.73. This proves that the crystal attributes can be improved by optimal cooling temperature profile obtained by multi-objective optimization framework. For implementing the optimal cooling profile an advanced model-based control, i.e., Generic Model Control (GMC) was developed. It was observed that the GMC controller has the good tracking profile with no offset with/without disturbances and small value of root mean square error (RMSE) of 0.0016 using piece-wise constant as set point temperature. Using piece-wise linear as set point temperature, the RMSE value was 0.0018. In particular, it is advantageous to operate the batch cooling crystallization process with piece-wise linear strategy for set point trajectory tracking problems.