nan Tulus

Real-time detection with AdaBoost-svm combination in various face orientation

Most of the research has used algorithm AdaBoost-SVM for face detection. However, to our knowledge so far there is no research has been facing detection on real-time data with various orientations using the combination of AdaBoost and Support Vector Machine (SVM). Characteristics of complex and diverse face variations and real-time data in various orientations, and with a very complex application will slow down the performance of the face detection system this becomes a challenge in this research. Face orientation performed on the detection system, that is 900, 450, 00, -450, and -900. This combination method is expected to be an effective and efficient solution in various face orientations. The results showed that the highest average detection rate is on the face detection oriented 00 and the lowest detection rate is in the face orientation 900.

Attribute Weighting Based K-Nearest Neighbor Using Gain Ratio

K- Nearest Neighbor (KNN) is a good classifier, but from several studies, the result performance accuracy of KNN still lower than other methods. One of the causes of the low accuracy produced, because each attribute has the same effect on the classification process, while some less relevant characteristics lead to miss-classification of the class assignment for new data. In this research, we proposed Attribute Weighting Based K-Nearest Neighbor Using Gain Ratio as a parameter to see the correlation between each attribute in the data and the Gain Ratio also will be used as the basis for weighting each attribute of the dataset. The accuracy of results is compared to the accuracy acquired from the original KNN method using 10-fold Cross-Validation with several datasets from the UCI Machine Learning repository and KEEL-Dataset Repository, such as abalone, glass identification, haberman, hayes-roth and water quality status. Based on the result of the test, the proposed method was able to increase the classification accuracy of KNN, where the highest difference of accuracy obtained hayes-roth dataset is worth 12.73%, and the lowest difference of accuracy obtained in the abalone dataset of 0.07%. The average result of the accuracy of all dataset increases the accuracy by 5.33%.

Shear rate analysis of water dynamic in the continuous stirred tank

Analysis of mixture in a continuous stirred tank reactor (CSTR) is an important part in some process of biogas production. This paper is a preliminary study of fluid dynamic phenomenon in a continuous stirred tank numerically. The tank is designed in the form of cylindrical tank equipped with a stirrer. In this study, it is considered that the tank is filled with water. Stirring is done with a stirring speed of 10rpm, 15rpm, 20rpm, and 25rpm. Mathematical modeling of stirred tank is derived. The model is calculated by using the finite element method that are calculated using CFD software. The result shows that the shear rate is high on the front end portion of the stirrer. The maximum shear rate tend to a stable behaviour after the stirring time of 2 second. The relation between the speed and the maximum shear rate is in the form of linear equation.

Computational Analysis of Sedimentation Process in the Water Treatment Plant

This study aims to determine how the distribution of sludge concentration and velocity of water flow in the water treatment plant in equilibrium state. The problems are solved by implementing the finite element method to a momentum transport equation which is a basic differential equation that is used for liquid-solid mixtures with high solid concentrations. In the finite element method, the flow field is broken down into a set of smaller fluid elements. The domain is considered as a container in the space of three-dimensional (3D). The sludge concentration distribution as well as the water flow velocity distribution in the inlet, central and outlet are different. The results of numerical computation are similar compared to the measurement results.

Data envelopment analysis with upper bound on output to measure efficiency performance of departments in Malaikulsaleh University

The higher education system in Indonesia can be considered not only as an important source of developing knowledge in the country, but also could create positive living conditions for the country. Therefore it is not surprising that enrollments in higher education continue to expand. However, the implication of this situation, the Indonesian government is necessarily to support more funds. In the interest of accountability, it is essential to measure the efficiency for this higher institution. Data envelopment analysis (DEA) is a method to evaluate the technical efficiency of production units which have multiple input and output. The higher learning institution considered in this paper is Malikussaleh University located in Lhokseumawe, a city in Aceh province of Indonesia. This paper develops a method to evaluate efficiency for all departments in Malikussaleh University using DEA with bounded output. Accordingly, we present some important differences in efficiency of those departments. Finally we discuss the effort should be done by these departments in order to become efficient.

Analysis Resilient Algorithm on Artificial Neural Network Backpropagation

Prediction required by decision makers to anticipate future planning. Artificial Neural Network (ANN) Backpropagation is one of method. This method however still has weakness, for long training time. This is a reason to improve a method to accelerate the training. One of Artificial Neural Network (ANN) Backpropagation method is a resilient method. Resilient method of changing weights and bias network with direct adaptation process of weighting based on local gradient information from every learning iteration. Predicting data result of Istanbul Stock Exchange training getting better. Mean Square Error (MSE) value is getting smaller and increasing accuracy.

Computational Analysis of Suspended Particles in the Irrigation Channel

Irrigation channel that is used for bringing water to land in order to make plants grow is one of important thing in tropical country, especially in Indonesia. It has been also a central feature of agriculture for over 5,000 years and is the method in which water is supplied to plants at regular intervals for agriculture. This paper is to analyse the sedimentation process in the irrigation channel in District Deli Serdang, Sumatera Utara Province. The analysis is based on the mixture model in turbulent flow. Computation using Finite Element Method is performed in the domain in two dimensional. The values of dispersed phase density parameter vary from 1100 kg/m3 to 1250 kg/m3. The results have shown that the structure of mixture velocity distribution and the dispersed phase volume fraction.

K-Means Algorithm Performance Analysis With Determining The Value Of Starting Centroid With Random And KD-Tree Method

Clustering methods that have high accuracy and time efficiency are necessary for the filtering process. One method that has been known and applied in clustering is K-Means Clustering. In its application, the determination of the begining value of the cluster center greatly affects the results of the K-Means algorithm. This research discusses the results of K-Means Clustering with starting centroid determination with a random and KD-Tree method. The initial determination of random centroid on the data set of 1000 student academic data to classify the potentially dropout has a sse value of 952972 for the quality variable and 232.48 for the GPA, whereas the initial centroid determination by KD-Tree has a sse value of 504302 for the quality variable and 214,37 for the GPA variable. The smaller sse values indicate that the result of K-Means Clustering with initial KD-Tree centroid selection have better accuracy than K-Means Clustering method with random initial centorid selection.

Modeling of Sedimentation Process in the Irrigation Channel

Irrigation has been a central feature of agriculture for over 5,000 years and is the method in which water is supplied to plants at regular intervals for agriculture. Channel irrigation allows irrigation over large areas, with large volumes of water. The content of the water in channel from the river generally contain a lot of material that can precipitate during the water flood the area of agriculture. This paper is to derive a mathematical model of sedimentation processes in the irrigation channel. The model is analysed using Finite Element Method with respect to the geometry of the channel in the district Galang, Sumatera Utara Province. From a computational point of view, results have shown the importance streamlines of the mixture velocity and the dispersed phase volume fraction.

Simple Technique of Projected Lagrange for a Class of Multi-Stage Stochastic Nonlinear Programs

This paper presents a techniq for solving multi-stage stochastic nonlinear programs. The techniq is based on projected lagrange approach which generates the search direction by solving parallelly a set of quadratic programming subproblems with size much less than the original problem at each iteration. Mathamatically, can be pointed out that Lagrange’s projection method can solve problem multi-stage stochastic nonlinear programs.