Sum Of Squared Errors Research Articles

Optimal parameters extracting of fuel cell based on Gorilla Troops Optimizer

Proton exchange membrane fuel cell (PEMFC) designs include multiple variable quantities with various nonlinear factors, which must be determined precisely to guarantee reliable modeling. The characteristic model of fuel cells (FCs) has an essential role in examining these cells' effective investigation. The FC design substantially influences simulation investigations of such methods, which has emerged in various applications. In this paper, a new identification method for the parameters' of the PEMFC is proposed based on using Gorilla Troops Optimizer (GTO). The optimized fitness function in the proposed method is used by the minimum value of the sum of squared errors (SSEs) of the current and estimated voltage cases. Various test cases are utilized to validate the effectiveness of the proposed method. After carrying many independent runs, the comparative algorithms are analyzed using SSEs, and the standard deviation measures. The high ability of the proposed method is investigated using steady-state and dynamic situations. The results showed that the proposed method got promising results and achieved better performance than other well-known comparative methods.

Calibration of Vissim for Bus Rapid Transit Systems in Beijing Using GPS Data

Bus Rapid Transit systems have grown in popularity in recent years. With the rapid development of computer technologies, using microscopic simulation models to study various strategies on planning, implementation and operation of BRT systems has become a hot research area in the field of public transportation. To make the simulation models accurately replicate field traffic conditions, model calibration is crucial. This paper presents an approach for calibrating the microscopic traffic simulation model VISSIM using GPS data for application to Beijing BRT systems. The Sum of Squared Error (SSE) of the collected versus simulated vehicle speeds at the cross-sections along the test route is specified as the evaluation index. A Genetic Algorithm is adopted as the optimization tool to minimize the SSE. Taking the Beijing North-South Central Axis BRT Corridor as a case study, it shows that the proposed approach is a practical and effective method for the model calibration.

Mathematical Models of the Generation of Radiation-induced DNA Double-strand Breaks and Misrepair Cells by Direct and Indirect Action

Free radical carries an unpaired electron in the outer shell which is very reactive and becomes toxic to DNA. The direct action hits cell directly, while indirect action is the interaction between ionizing radiation and water molecule which later produces free radical. Hydrated electron (e), hydroxyl radical (OH), hydrogen radical (OH), ionized water, hydroperoxyl radical and hydrogen peroxide are examples of free radical products. Among of these three free radicals, DNA damage dominantly caused by hydroxyl radical (OH) because it is found to be highly reactive compared to others. This paper aimed to develop a model by using structured population dynamics approach to study the effects of ionizing radiation by direct and indirect actions. The effects of ionizing radiation are mathematically described in a model using Ordinary Differential Equations (ODEs). The simulation results are fitted to the Linear Quadratic (LQ) formulation to give the ratio for alpha/beta . Next, the parameter estimation of the model is carried out using experimental data of human colon carcinoma cell by the aid of the MATLAB programming. The estimated parameter values can explain the biological meaning, which can support the result of the experimental design. The result showed that the sum-squared error (SSE) between simulation data and experimental data obtained is 0.0019 which indicates an excellent t to the experimental data. Thus, the model developed is in line with the experimental result. The model is able to explain the dynamics process of the direct and indirect effect of ionizing radiation on the cell population.

Evaluation of Intracerebral Haemorrhage’s Surface Area Using Artificial Intelligence in Computed Tomography

Introduction: AI-based techniques can be used to localize and measure the intracerebral haemorrhage (ICH) in computed tomography (CT). This study aims to develop an automated detection algorithm with higher sensitivity in ICH evaluation in comparison to the conventional method. This indirectly influences the patient’s prognosis by reducing the risk of delay or misdiagnosis. Methods: Selected 50 CT brain images with primary ICH were used for three different measurement approaches including the conventional Kothari method (Conventional), AI-based method (A.I.), and manually marking by the radiologist, which is the ground truth (G.T.). In the automated system, a convolutional neural network (CNN) is used to localize the ICH, followed by a thresholding technique to segment the ICH, and finally, the measurements are computed. The segmentation performance is measured using Dice similarity coefficient. The automated ICH measurements are compared against the ground truth (A.I. vs G.T.). Concurrently, the ICH measurements calculated using the conventional method are also compared against the ground truth (Conventional vs G.T). The t-test analysis is performed between the sum squared error (SSE) of ICH measurements from the automated-ground truth and the conventional-ground truth. Results: The mean volumetric Dice similarity coefficient for the automated segmentation algorithm when tested against the ground truth, is 0.859±0.135. The t-test analysis of the SSE between conventional-ground truth (median=5.45, SD=3.96) and automated-ground truth (median=0.73, SD=0.78) achieved p-value < 0.001 (p=5.10E-9). Conclusion: The automated AI-based algorithm significantly improved the ICH surface area measurement from the CT brain with higher accuracy and efficiency in comparison to the conventional method.

NATURAL DISASTER EVENT MAPPING IN WEST JAVA USING K-MEANS ALGORITM

<p><em> Natural disaster is an event that cannot be avoided, therefore a mapping of occurrence of the natural disaster is needed. In additional to mapping, clustering of natural disaster events is also needed to determine which areas have low to high intensity events. In performing the clustering, a method or algorithm can be used, namely the k-means algorithm.</em></p><p><em>In the research conducter, the scope of natural disasters is West Java Province with the attributes used are floods, landslides and tornadoes. And also from this research, it was conducted to find out how many optimal number of clusters that can be clustered.</em></p><p><em>The method that used in this study is the K-Means algorithm which is used to perform clustering. The Elbow method is used to determine the optimal K value from the dataset by calculate the SSE (Sum Square Error) of each predetermined cluster.</em></p><p><em>From the result of its application, the K-Means algorithm can cluster datasets of Natural Disaster in West Java with predetermined attributes. Based on the calculation results from the elbow method, the value of K from the dataset is 4. And from the research conducter, the accuracy rate of each cluster is 0,04% to 0,56%.</em></p><p><strong><em>Keywords: </em></strong><em> </em><em>K-Means, Natural Disaster, Elbow Method, Cluster, Machine Learning</em></p>

A Data-Driven Approach for Electric Bus Energy Consumption Estimation

Along with the battery technology advancements and government policy support, the penetration level of electric buses (EBs) in the urban public transportation system has been increasing in recent years. Considering the potential influence of the increasing EB charging demand on power systems, estimating the real-time energy consumption of EBs has become a principal issue. In this work, a data-driven approach for EB energy consumption estimation is proposed. In particular, a detailed physical model of EB is constructed to model its energy consumption considering the randomness in EB operation, including speed, acceleration, and passenger count. In order to improve the estimation accuracy, the conventional Kalman filter (KF) is modified involving EB mass estimation considering stochastic real-time passenger count, motion data dimension deduction based on EB operation route. To estimate the EB acceleration accurately and reduce the noise caused by the unimportant features, we extended the feature discarding algorithm of decision trees to the regression trees. In the case study, an Android application is developed to collect the EB motion data so that any general Android smartphone can be used for data collection. The performance of the proposed approach is evaluated based on real-world EB operation data collected from St. Albert Transit, AB, Canada. According to the results, our APP can track the real-time EB trace, and the proposed modified KF can filter most of the noises caused by the GPS data collection process and stochastic passenger count. Also, with the extended random forest algorithm, the unimportant features can be discarded and the real-time EB acceleration is estimated efficiently with a small sum of square error (SSE). Compared with the existing approaches, the proposed approach achieves a more accurate real-time energy consumption estimation of EBs, which in turn, provides a better characterization of power system loading and voltage variation.

An evolutionary computing approach for reducing bias in the dynamic modulus predictive models of hot mix asphalt

Various published literature has indicated significant bias issues with dynamic modulus (E∗) predictive models for the hot mix asphalt. This study proposes Gene Expression Programming (GEP) based approach to reduce such bias. Bias analysis was carried out using database developed during national cooperative highway research program. GEP based predictive models for bias correction factors were developed and subsequently used in conjunction with E∗ predictive models to update E∗ values. Application of correction factors and subsequent statistical analysis showed improvement in the accuracy of predicted E∗ values. The extent of improvement (using sum of squared error) was dependent on model under consideration and ranged between 19 and 36%.

Seleksi Fitur Menggunakan Eigen Vector Untuk Peningkatan Kinerja K-Means Clustering Dalam Pengelompokan Data

The large number of data set attributes from the data grouping process with K-Means Clustering can affect the number of iterations produced. In this research, Eigen Vector is used to perform feature selection on the data set. The selected data set is then clustered using K-Means Clustering. The data set used in this research is the Wine Quality Dataset obtained from the UCI Machine Learning Repository, with 11 attributes, 4898 data records and 7 attribute classes. Then the South German Credit Dataset was obtained from kaggle.com with 20 attributes, 1000 data records and 2 attribute classes. The results of this research indicate that the number of iterations obtained from the comparison of tests using K-Means without feature selection is that in the Wine Quality Dataset, 11 iterations are obtained, and in the South German Credit Dataset, there are 10 iterations. Meanwhile, K-Means with Eigen Vector feature selection obtained the number of iterations in the Wine Quality Dataset with a total of 5 iterations, and in the South German Credit Dataset with a total of 4 iterations. Clustering evaluation was calculated using Sum of Square Error (SSE). The SSE value in K-Means Clustering without feature selection from the Wine Quality Dataset is 678.5735, while in the South German Credit Dataset it is 1534.3167. While the K-Means Clustering with Eigen Vector from the Wine Quality Dataset is 383.0517, and the South German Credit Dataset is 469.0698. From the results of the proposed method is able to reduce the percentage of errors and minimize the number of iterations on K-Means Clustering with feature selection using Eigen Vector

A self-compensated spin-locking scheme for quantitative R1ρ dispersion MR imaging in ordered tissues

PurposeTo propose a self-compensated spin-locking (SL) method for quantitative R1ρ dispersion imaging in ordered tissues. MethodsTwo pairs of antiphase rotary-echo SL pulses were proposed in a new scheme with each pairs sandwiching one refocusing RF pulse. This proposed SL method was evaluated by Bloch simulations and experimental studies relative to three prior schemes. Quantitative R1ρR dispersion imaging studies with constant SL duration (TSL = 40 ms) were carried out on an agarose (1–4% w/v) phantom and one in vivo human knee at 3 T, using six SL RF strengths ranging from 50 to 1000 Hz. The performances of these SL schemes were characterized with an average coefficient of variation (CV) of the signal intensities in agarose gels and the sum of squared errors (SSE) for quantifying in vivo R1ρ dispersion of the femoral and tibial cartilage. ResultsThe simulations demonstrate that the proposed SL scheme was less prone to B0 and B1 field inhomogeneities. This theoretical prediction was supported by fewer image banding artifacts and less signal fluctuation signified by a reduced CV (%) on the phantom without R1ρ dispersion (i.e., 4.04 ± 1.36 vs. 18.87 ± 4.46 or 6.66 ± 2.92 or 5.71 ± 2.05 for others), and further by mostly decreased SSE (*10–3) for characterizing R1ρ dispersion of the femoral (i.e., 0.3 vs. 1.2 or 0.4 or 0.1) and tibial (i.e., 0.4 vs. 7.2 or 3.2 or 2.8) cartilage. ConclusionThe proposed SL scheme is less sensitive to B0 and B1 field artifacts for a wide range of SL RF strengths and thus more suitable for quantitative R1ρ dispersion imaging in ordered tissues.

Bone Mineral Content Estimation in People Living with HIV: Prediction and Validation of Sex-Specific Anthropometric Models.

People living with HIV (PWH) experience an accelerated reduction in bone mineral content (BMC), and a high risk of osteopenia and osteoporosis. Anthropometry is an accurate and low-cost method that can be used to monitor changes in body composition in PWH. To date, no studies have used anthropometry to estimate BMC in PWH. To propose and validate sex-specific anthropometric models to predict BMC in PWH. This cross-sectional study enrolled 104 PWH (64 males) aged >18 years at a local university hospital. BMC was measured using dual energy X-ray absorptiometry (DXA). Anthropometric measures were collected. We used linear regression analysis to generate the models. Cross-validations were conducted using the “leave one out”, from the predicted residual error sum of squares (PRESS) method. Bland–Altman plots were used to explore distributions of errors. We proposed models with high coefficient of determination and reduced standard error of estimate for males (r2 = 0.70; SEE = 199.97 g; Q2PRESS = 0.67; SEEPRESS = 208.65 g) and females (r2 = 0.65; SEE = 220.96 g; Q2PRESS = 0.62; SEEPRESS = 221.90 g). Our anthropometric predictive models for BMC are valid, practical, and a low-cost alternative to monitoring bone health in PWH.

Mining Factors Affecting Stock Prices from the Perspective of Asset Pricing Based on ANN-RBF Algorithm

Pricing of assets through machine learning has been given more attention. This article attempts to study the factors affecting the stock value. In addition to the Fama French factor, this article selects the stocks in the A-share market and adds seven other factors affecting stock value to construct a stock pricing model. The sum of squares error (SSE) of the RBF neural network's prediction results was 0.4, and the relative error was 0.955. Among the 12 factors, the economic prosperity index (HJ), consumer expectations index (CEI), and an inflation index (CPI) were significantly crucial for the growth of the A-share market value. This study is conducive to exploring the factors affecting stock prices, helping investors and other stakeholders identify significant influencing factors, and making correct responses to changes in factors to obtain additional returns.

Model parameters estimation of the proton exchange membrane fuel cell by a Modified Golden Jackal Optimization

Due to the growing use of fuel cell systems in electricity generation instead of conventional power generation systems for various reasons, such as high efficiency, non-environmental pollution, optimal dynamic response, and higher durability reliability, in this paper, by presenting an optimal model of the proton exchange membrane fuel cell (PEMFC) model and simulating it, the efficiency, and the output power of the fuel cell will be predicted. The main idea is to use a PSO-based Golden Jackal Optimization method to reduce the sum of squared errors (SSE) of the measured output voltage and the output voltage of the PEMFC stack. To validate the proposed approach, it is applied to two examined cases, and the results are compared with those of various new optimizers. The results reveal that the proposed ICSO outperforms the other comparison methods for the optimal estimate of the PEMFC model.

Biodegradation modeling of phenol using Curtobacterium flaccumfaciens as plant-growth-promoting bacteria

Phenol is a major worry pollutant resulting from industrialized manufacturing and chemical reactions. The growth kinetics and biodegradation of phenol were initially investigated using C. flaccumfaciens, a recently identified plant growth stimulating bacterium. Based on the Haldane inhibition model, Haldane's growth kinetics inhibition coefficient (Ki), half-saturation coefficient (Ks), and the maximum specific growth rate (max) for phenol-dependent growth kinetics were estimated to be 329 (mg/L), 9.14 (mg/L), and 1.05 (h−1), respectively. With a sum of squared error (SSR) of 1.36 × 10−3, the Haldane equation is well adapted to empirical data. The improved Gombertz model also accurately predicts phenol biodegradation trends. The rate of phenol biodegradation and the lag time both increased as the initial phenol concentrations were increased. C. flaccumfaciens growth and phenol biodegradation were best achieved at a pH of 7.0 at a temperature of 28 °C incubation. A phenol biodegradation mechanism by C. flaccumfaciens has been proposed. In conclusion, this study revealed the ability of C. flaccumfaciens to promote plant growth and biodegrade phenol simultaneously. This could aid in rhizoremediation and crop yield preservation in phenol-stressed conditions.

Model parameters identification of the PEMFCs using an improved design of Crow Search Algorithm

There is an increasing trend for fuel cell systems applications in electricity generation systems instead of traditional power generation systems because of their advantages such as high efficiency and almost no environmental pollution, desirable dynamic response, and reliability. Due to this reason, herein, a new method has been presented for optimum identification of the model of the proton exchange membrane fuel cell (PEMFC) model. The major concept is to lessen the sum of squared error (SSE) amount of the observed output voltage and the output voltage of the PEMFC stack by an improved version of Crow Search optimizer (ICSO). To validate the suggested technique, it is applied to two studied cases and the achievements are put in comparison with several newest optimizers, which are Genetic algorithm (GA), Grasshopper Optimizer (GHO), and Salp Swarm Optimizer (SSO). The achievements show that the suggested ICSO gives a better superiority to the other comparative algorithms for optimum estimation of the PEMFC model.

Developed Design of Battle Royale Optimizer for the Optimum Identification of Solid Oxide Fuel Cell

One of the most appropriate electricity production systems is solid oxide fuel cells (SOFCs), which are important because they are highly efficient, flexible to fuel, and have fewer environmental degradation effects. A new optimum technique has been provided for providing well-organized unknown parameters identification of the solid oxide fuel cell system. The main idea is to achieve the lowest amount of the sum of square error between the model’s output voltage and the empirical voltage datapoints. To get efficient results, the minimum error value has been achieved by designing a new metaheuristic algorithm, called the Developed version of Battle Royale algorithm. The reason for using this version of Battle Royale algorithm is to achieve results with higher accuracy and better convergence. The proposed technique was then applied to a 96-cell SOFC stack under different temperature and pressure values and its achievements were compared with several different latest methods to show the proposed method’s efficiency.

Hybrid model in machine learning–robust regression applied for sustainability agriculture and food security

<span lang="EN-US">A dataset containing 1924 observations used in this study to evaluate the effect of 435 different independent variables on one dependent variable. Big data has some issues such as irrelevant variables and outliers. Therefore, this study focused on analysing and comparing the impact of three different variable selection based on machine learning techniques, including random forest (RF), support vector machines (SVM), and Boosting. Further, the M robust regression was applied to address the outliers using M–bi square, M–Hampel, and M–Huber. Random forest and M-Hampel results revealed the significant comparing from the other methods such as mean absolute error (MAE) 175.33995, mean square error (MSE) 31.8608, mean average percentage error (MAPE) 9.16091, sum of square error (SSE) 89270.45, R–square 0.829511, and R–square adjusted 0.82670. Also, these techniques indicated that the 8 selection criteria were lower than the other techniques including Akaike information criterion (AIC) 47.25915, generalized cross validation (GCV) 47.27169, hannan-quinn (HQ) 47.60351, RICE (47.2845), SCHWARZ 51.7099, sigma square (SGMASQ) 46.50605, SHIBATA 47.23489, and final prediction error (FPE) 47.25929. Therefore, the study recommended that the best random forest and M-Hampel models are helpful to show the minimum issues and efficient validation for analysing and comparing big data.</span>

Discrete-Time System Conditional Optimization Based on Takagi–Sugeno Fuzzy Model Using the Full Transfer Function

The study proposes a novel method for synthesis of a discrete-time parallel distributed compensation (PDC) controller for the nonlinear discrete-time Takagi–Sugeno (TS) fuzzy plant model. For each of the fuzzy plant model linear subsystems, a local linear first order proportional-sum (PS) controller is designed. The algebraic technique is used in two-dimensional parameter space, utilizing the characteristic polynomial of the row nondegenerate full transfer function matrix. Each system’s relative stability is accomplished in relation to the selected damping coefficient. The supplementary criterion is the minimal value of the performance index in the form of the sum of squared errors (SSE). However, unlike the traditional technique, output error is impacted by all simultaneous actions on the system: nonzero inputs and nonzero initial conditions. The full transfer function matrix of the system allows for the treatment of simultaneous actions of the input vector and unknown unpredictable initial conditions. In order to show the improvement caused by the application of a new optimization method that considers nonzero initial conditions, a comparison of PDC controllers designed under zero and nonzero initial conditions is given, where the system in both cases starts from the same nonzero initial conditions, which is often the case in practice. The simulation and experimental results on a DC servo motor are shown to demonstrate the suggested method efficiency.

Effects of cutting and drying method (vacuum freezing, catalytic infrared, and hot air drying) on rehydration kinetics and physicochemical characteristics of ginger (Zingiber officinale Roscoe).

The purpose of this study was to discuss the effects of cutting methods (transverse cutting [TC] and longitudinal cutting [LC]) and drying methods (vacuum freeze-drying [FD], hot air drying [HD], catalytic infrared drying [CID]) on rehydration kinetics and physical and chemical characteristics of rehydrated ginger. The research results showed that the rehydration rate and equilibrium moisture content increased with an increase in temperature. LC samples had a higher rehydration rate, while TC samples showed higher equilibrium moisture. Peleg model can fit the rehydration curve of the sample well. The highest coefficient of determination (R2 ) was 0.99, while the sum of squares error and lowest chi-square (χ2 ) was close to zero. Compared with fresh samples, the rehydrated ginger slices had lower gingerol content, total phenol content (TPC), total flavonoid content (TFC), and higher antioxidant activity. The different cutting methods had no significant effect on the physical and chemical properties of rehydrated ginger. In conclusion, TC-CID rehydrated products have better retention of gingerol, TPC, TFC, and antioxidant properties, which was similar to the principal component analysis. PRACTICAL APPLICATION: The results of this study show that transverse cutting combined with catalytic infrared drying is a unique processing technology. Due to the short xylem of transverse cutting ginger, the xylem diameter can be restored during rehydration, the balanced water content was high, and the quality of dried ginger can be restored to the greatest extent. This makes food processors competitive in the operation process and provides better services to consumers.

Hybrid model to predict the effect of complex media changes in mammalian cell cultures

This work presents a modelling approach to account for the contribution of minor elements in cell culture media for mammalian cell cultures. The effect of minor elements is captured through an empirical PLS (Partial Least Squares) based correction that is incorporated into a dynamic mechanistic model composed of mass balances of major components in the media: amino acids, main by-products, biomass and product. The combination of the empirical correction based on PLS and the mechanistic model results in a hybrid model that was calibrated and validated with industrial experimental data. The goal is to develop a comprehensive model that can be used in the future to optimize batch, fed-batch and perfusion operations with respect to the media formulation. Based on the application of t-test to the sum of square errors (SSE) of the models it is shown that the re-calibrated hybrid model accounting for minor components interactions performed better predictions as compared to mechanistic or hybrid models that do not account for the minor components. Furthermore, the hybrid model is shown to remove dynamic auto-correlation error which is another indicator of reduced model error.

Developing hybrid ELM-ALO, ELM-LSO and ELM-SOA models for predicting advance rate of TBM

Accurate prediction of TBM performance is very important for efficient completion of TBM construction tunnel project. This paper aims to predict the advance rate (AR) of tunnel boring machine (TBM) using three hybrid models by combining three swarm intelligence optimization algorithm (Ant Lion Optimizer (ALO), Loin swarm optimization (LSO) and Seagull optimization algorithm (SOA)) and the Extreme learning machine (ELM) model, namely ELM-ALO, ELM-LSO and ELM-SOA model respectively. The dataset consists of 1, 286 samples from the Pahang Selangor Raw Water Transfer (PSRWT) tunnel project in Malaysia, and containing six parameters (rock quality designation (RQD), uniaxial compressive strength (UCS), rock mass rating (RMR), Brazilian tensile strength (BTS), thrust force per cutter (TFC) and revolution per minutes (RPM)) from rock mass and machines. In order to evaluate the prediction performance of different hybrid models, the root mean square error (RMSE), the mean absolute error (MAE), the mean square error (MSE), the determination coefficient (R2), the sum of square error (SSE), and the variance accounted for (VAF) were adopted as the performance indicators. The results show that ELM-LSO is the best model to predict AR. Sensitivity analysis shows the importance of all considerations to AR. TFC, RPM and RMR are the three most important parameters. But this is not absolute, more parameters need to be taken into account in AR prediction. Meanwhile, the ELM-LSO model proposed in this paper can be used as a new method to predict AR.