Search

The model is part of a learning structure that has a scope large. Inside there are approaches, strategies, methods, and techniques. One of an important aspect of a learning model is syntax, which is standard steps that must be taken in implementing the model. This syntax should be reflected in the steps of learning in particular detailed in the core learning activities. The results achieved in this activity are the teacher has the ability to develop scenarios or core steps active learning that uses certain learning models through the use of supporting media in teaching and learning activities

The term learning model is distinguished from the term learning strategy, method learning or learning procedure. The term learning model has broader meaning than a strategy, approach, method or procedure. Learning models are patterns of interaction between students, teachers, and material learning that includes strategies, approaches, methods and techniques learning. Elaborate that learning strategies are tactics or tips planned by the teacher related to the whole preparation of learning can be achieved effectively. While the approach is the way taken by the teacher in the implementation of learning so that the active ideas presented can be adapted to then be understood by students. There are two types of active learning, namely: a methodological approach and material approach. Methodological approach concerns the way students Adapting the active ideas presented into their cognitive structures that are in line in the way taken by the teacher in presenting learning materials the. Examples of methodological approaches are intuitive, analytic, synthetic, spiral, inductive, deductive, thematic, realistic and heuristic. The result of this research is the material approach able to present an active concept through other active concepts already owned by students. The example presents the concept of addition with using the number line or set approach.

In order to optimize the diagnosis of eye disease, the authors want to propose the combination of Support Vector Machine and K-Nearest Neighbor Algorithm to Optimize Diagnosis of Eye Disease. This is a combination method of SVM to get a better classification to diagnose the eye disease. The problem is how to get a better classification to diagnose eye disease. In this research, the hybrid of SVM-KNN is more accurate to classify the eye disease than SVM itself. The accuracy using the combination SVM-KNN algorithm is 94.67%.

Face detection plays an important role in various applications such as face recognition, object tracking and also computer-human interaction. An efficient face detection algorithm is needed to apply this. In this paper, Viola-Jones is used not only to detect faces, but also to determine the position of the sub-window which will be carried out in the detection process of Helmets. Bicubic Interpolation plays an important role in scaling and improving detection accuracy. Helmet detection is done by conducting a training process using Principal Component Analysis which is done after the face is detected successfully. The test results show that the accuracy of using the original image is at 92.537% for face detection and 78.125% for helmet detection. But in images that have gone through the stages of bicubic interpolation and histogram equalization, accuracy can reach 95.522% for face detection and 82.8125% for helmet detection.

The paper discussed how to increase the effectiveness of semi-supervised clustering algorithm by integrating active learning and semi-supervised clustering to guide the model. To solve this complexity problem of the clustering algorithm, this paper presented an active semi- supervised k-means clustering model based on silhouette coefficient by utilizing a pair-wise constraint clustering method in PCKmeans and actively selects valuable samples to establish constraints. Our method was based on silhouette coefficient. The model was iterated until the number of queries reaches a threshold or the clustering algorithm achieves an acceptable performance. The method optimized the semi-supervised k means by using Local Sample Density (LDS) sampling strategy in order to ensure the stability of the algorithm. Furthermore, a distance-based sampling method, which reduced the queries quantity as well as increase the number of constraint samples, was introduced to optimize the process of establishing pair-wise constraints. These two methods significantly promoted the effectiveness of clustering algorithm. The experimental results indicated that our model outperforms the compared models in MI and ARI with 5% and 6% boost than k-means, PCKMeans, Min-Max, and LDS models.

Patients in the intensive care unit require fast and efficient handling, including in-diagnosis service. The objectives of this study are to produce a computer-aided system so that it can help radiologists to classify the types of brain tumors suffered by patients quickly and accurately; to build applications that can determine the location of brain tumors from CT scan images; and to get the results of the analysis of the system design. The combination of the zoning algorithm with Learning Vector Quantization can increase the speed of computing and can classify normal and abnormal brains with an average accuracy of 85%.

Indonesia's growing area of cultivation and agriculture requires a monitoring system of growingvegetation on it. By using images captured from the top (orthophotos), the result was processedusing algorithms of digital image processing combined with machine learning in order to get theaccurate information of vegetation status. The long-term goal of this program is the establishment ofan independent business unit engaged in the field of orthophotos image sensing for the purposes ofutilization in agriculture, health, territorial mapping, mining, and industrial and governanceindustries requiring sensing results taken from the upper side of the object. For applicationdevelopment, agile methodology is used, while business-side planning use business model canvasand SWOT analysis. With the geospatial orthophotos, it is possible to identify which part of theplantation land is fertile for planted crops, means to grow perfectly. It is also possible furthermoreto identify less fertile in terms of growing but not perfect, and also part of plantation field that is notgrowing at all. This information can be easily known quickly with the use of UAV photos. Theresulting orthophotos image were processed using Matlab including classification of fertile,infertile, and dead palm oil plants by using Gray Level Co-Occurrence Matrix (GLCM) method.From the results of research conducted with 30 image samples, it was found that the accuracy of thesystem can be reached by using the features extracted from the matrix as parameters Contrast,Correlation, Energy, and Homogeneity.

The Naïve Bayes method is proven to have a high speed when applied to large datasets, but the Naïve Bayes method has weaknesses when selecting attributes because Naïve Bayes is a statistical classification method that is only based on the Bayes theorem so that it can only be used to predict the probability of the class membership of a class independently. Independent without being able to do the selection of attributes that have a high correlation and correlation between one attribute with other attributes so that it can affect the value of accuracy. Naïve Bayesian Weight has been able to provide better accuracy than conventional Naïve Bayesian. Where an increase in the highest accuracy value obtained from the Water Quality dataset is equal to 88.57% in the Weight Naïve Bayesian classification model, while the lowest accuracy value is obtained from the Haberman dataset which is 78.95% in the conventional Naïve Bayesian classification model. The increase in accuracy of the Weight Naïve Bayesian classification model in the Water Quality dataset is 2.9%. While the increase in accuracy value in the Haberman dataset is 1.8%. If done the average accuracy of each dataset using the Weight Naïve Bayesian classification model is 2.35%. Based on the testing that has been done on all test data, it can be said that the Weight Naïve Bayesian classification model can provide better accuracy values than those produced by the conventional Naïve Bayesian classification model.

There are many factors that can affect the quality of Refined Bleached Deodorized Palm Oil produced. Every step in RBDPO processing must be mastered very precisely in terms of process conditions such as temperature, flowrate, dose, pressure, etc. This condition can vary from one facility to another and therefore requires the company’s own specifications / rules to implement and integrate all production process facilities until the product is produced. The focus of the study on this particular task is the quality problems faced by companies in the Refinery section where research is carried out using data mining concepts to predict data logsheets that are written every 24 hours by refinery operators. The data can be used as a tool to predict the color quality of Refined Bleached Deodorized Palm Oil (RBPO). The use of Data Mining in this study is to facilitate operators in managing machine settings to achieve the quality required by the company directly. So that the Refinery section does not need to wait for the results of laboratory tests which require approximately 2 hours to find out the RBDPO quality results.

At the company found problems related to the length of the product assembly process. The assembly system can be optimized by eliminating, combining, or simplifying the way the product is assembled so that the time needed in the assembly process becomes more minimum. If this design improvement is also carried out on other products produced by Jayatech Palmindo company, it will have a significant impact on reducing assembly time and unit costs in the production process. The integration of the Quality Function Deployment, Design for Manufacture and Assembly methods is expected to provide the right solution to improve the design of the ripple mill product and other products at Jayatech Palmindo company so that assembly time can be further shortened, and minimal unit costs without changing the value from the company’s products.

Cryptography is the study of mathematical techniques related to information security aspects such as validity, data integrity, and data authentication. In this study, Variably Modified Permutation Composition (VMPC) algorithm is modified by adding complementary methods to the encryption and decryption process. Keys that are generated randomly will be optimized using Genetic Algorithm. The Variably Modified Permutation Composition (VMPC) algorithm is a symmetrical stream cipher algorithm similar to the RC4 cipher designed by Bartosz Zoltak. The Variably Modified Permutation Composition (VMPC) algorithm is an extension of the one-way function VMPC that was developed into a byte-based encryption algorithm. In its use the VMPC is generated by an 8-bit stream of 256 element permutations. The initial state of the permutation is calculated in VMPC Key Scheduling. The Genetic Algorithm produces a unique intermediate key for each algorithm run. The intermediary key is combined with the Ciphertext in the first level which produces the second level Ciphertext, up to the third level Ciphertext. Attackers will not be able to carry out attacks such as brute force, differential attacks or statistical attacks without having knowledge of the key. From the results of the tests carried out, the more characters that are encrypted and decrypted, the longer it will take. On testing the avalanche effect produces an average value of 51.25% for keys without optimization while 53.42% for keys optimized. The effect of key optimization using Genetic Algorithm has increased the value of the avalanche effect and has an effect on the results of changing bits in the ciphertext.

In digital world, data and information is very valuable and much targeted by unauthorized parties. One way to secure messages is cryptography. Cryptography itself is a branch of science in concealing messages. In further development a hybrid cryptosystem was formed which combines symmetrical and asymmetric cryptography, which in this paper uses VMPC and Multi-Power.. The RSA Multi-Power algorithm is an asymmetric algorithm that is excellent at message encryption but requires a long process time because it uses very complicated calculations. While VMPC has advantages in the process with fast time and relatively small size of ciphertext. Here we have analyzed the performance of various variants of RSA that have been hybridized with VMPC and given the results.

Naïve Bayes is a prediction method that contains a simple probabilistic that is based on the application of the Bayes theorem (Bayes rule) with the assumption that the dependence is strong. K-Nearest Neighbor (K-NN) is a group of instance-based learning, K-NN is also a lazy learning technique by searching groups of k objects in training data that are closest (similar) to objects on new data or testing data. Classification is a technique in Data mining to form a model from a predetermined data set. Data mining techniques are the choices that can be overcome in solving this problem. The results of the two different classification algorithms result in the discovery of better and more efficient algorithms for future use. It is recommended to use different datasets to analyze comparisons of naïve bayes and K-NN algorithms. the writer formulates the problem so that the research becomes more directed. The formulation of the problem in this study is to find the value of accuracy in the Naïve Bayes and KNN algorithms in classifying data.

According to the theft report received by Indonesian National Police in 2014, 9112 motorcycles were stolen, the number of motorcycle thefts decreased by 43.87% in 2015. And in 2016, motorcycle theft again increased by 1.23% from the previous year. Due to this problem, an alternative solution is needed to improve motorcycle security. One way to improve the security of the motorcycle is to modernize the motorcycle security system from conventional way to high-tech by utilizing the development of information technology (IT). In this study, we explored ATMega328 microcontroller on Arduino Promini board which is controlled using a smartphone with Android platform to build a motorcycle security device. Controls made through the smartphone to activate or to disconnect the electric motorcycle circuit through the relay. We conducted tests to measure the effectiveness and the time required by the device to be active based on different distances. The results of this test indicate that the device took a longer time if it is turned on from a longer distance. As for turning on or off a motorcycle, the device took 0.5 seconds at a minimum distance of 1 meter and took 1.5 seconds at a maximum distance of 15 (fifteen) meters. It is also found that to turn on a motorcycle engine, it took 0.5 seconds at a minimum distance of 1 (one) meter and 3 seconds at a maximum distance of 15 (fifteen) meters, and it took 0.5 seconds at a minimum distance of 1 (one) meter and 4 seconds at a maximum distance of 15 (fifteen) meters. The results obtained shows that the proposed method can be potential motorcycle security as an alternative solution.

The main concern of this paper is to decide the locations and allocations of facilities that impact not only the profitability of an organization but the fast ability to serve customers. Generally the location-routing problem is to minimize the overall cost by simultaneously selecting a subset of candidate facilities and constructing a set of delivery routes that satisfy some restrictions. In this paper we consider the periodic routing of vehicle to be used to distribute goods. Integer programming model is built to solve the problem. A feasible neighbourhood search is developed to solve the result model.

This research is about smooth support vector machine (SSVM) and Decision Tree in data mining. Many researchers conduct and develop methods to improve the accuracy and classification of data on good results. This research was conducted by conducting an experiment on STMIK Neumann Medan student data. In this study, it was concluded that Decision Tree performance is better than SSVM, Decision Tree gets very good results that promise to help find the best students to get scholarships. This study is better than SSVM. The training process has a difference of 11.04% and the testing process is 10.08% with each Accuracy.

The progress and success of the company can be seen from the consumer’s response to production from all aspects of each company’s activities and is a key success factor. In this case describes the problem of supply chain optimization from the perspective of providing logistics including a mathematical model of cost optimization for supply chains in the form of MILP (Mixed Integer Linear). Production, transportation and distribution costs are chosen as optimization criteria. Time, volume, capacity and mode of transportation are also taken into account. The model was developed based on supply chain management theory to achieve the lowest cost, responsive and to achieve common goals. The results state that product inventories, loading patterns, modes of transportation, and minimum order quantities significantly affect the total logistics costs. Shorter production processing time, and produce optimal solutions. However, the right limits must be carefully defined to get a viable solution.

In this study using a comparative analysis of SMART and SAW methods. The results of the SAW method calculation analysis have a faster processing time with a time of 0.40 s. While the SMART method calculation analysis has a longer processing time difference of 0.47 s. In this study the authors suggest using the SMART method. Where the process of calculating the SMART method has more varied results, because the criteria value between one candidate and another candidate influences each other. While the calculation of the SAW method results are less varied, because the criteria value between one candidate and another candidate does not affect each other. Weighting is done without an algorithm. In this study the authors suggest using the SMART method because there is a final value of

Dyslexia disorders commonly occur in children. Dyslexia is a difficulty in recognizing letters and numbers. Helpful tools are needed to detect and treat dyslexic children so that early anticipation can be taken. So that later this disorder will no longer be suffered by the child when he is an adult. For this reason, information technology-based learning media was created in this study with the aim of helping therapy for children with dyslexia. This study utilizes the hidden Markov method for speech recognition and multisensory methods for learning media. In this study learning is divided into three levels, namely learning to recognize numbers, learning to recognize letters, and learning to understand words. Each level uses a pattern that is generally difficult to accept children with dyslexia disorders. During the testing process, level one and level three efficiency has reached 80%, while for level two it is still worth 60%.

Software testing is a significant activity of the Software Development Life Cycle (SDLC) that can overcome possibility of error in every single development step. Software testing is most often used technique for verifying and validating the quality of software. Software testing that concern with the internal mechanism of a systems and mainly focus on control flow or data flow a program is called White box testing. White box testing is classified into static and structural testing. Type of white box testing that is used in this paper is structural testing. Path coverage and code complexity is a sub testing within the scope of structural testing. Path coverage split a program into a number of distinct paths. In this paper, structural graph and data flow graph is used to ease the tester to find path in a program by mapping out the program and software testing metrics is used to describe the effectiveness and quality of that processes that produce the software product. This paper did manual testing for genetic algorithm program, such as mapping the genetic algorithm program into the control flow graph, create test cases to provide some possibility inputs that can be handled by program, execute test cases, analyze, and calculate the software manual test process metrics.

Hydroponic farming system is an agricultural system that uses direct water as a nutrient without using soil as a planting medium. This system allows smallholder farmers to have the opportunity to develop their crop production with less capital. In addition, hydroponic planting has also been widely adapted by individuals as a personal hobby. Application of technology has penetrated various fields including agricultural fields. One of the technologies that can be applied in a hydroponic farming system is the sensor. Sensors are devices that used to convert a physical quantity into a quantity of electricity so that it can be analyse with a certain electrical circuit. In this study, the technology to be applied is wireless sensor technology applied in human life to help get information quickly and accurately. Sensors to be used in this study are pH sensors, conductivity sensors, temperature sensors and humidity. In addition to sensors, the study also involved Arduino technology. Arduino is a microcontroller board that is used to interact with the environment based on programs that have been made. The final results of the application testing show that the system success to display diagram in real-time in an environment from Arduino board to database and web server.

Generally, the scheduling process is done manually. However, this method has a low accuracy level, along with possibilities that a scheduled process collides with another scheduled process. When doing theory class and practicum timetable scheduling process, there are numerous problems, such as lecturer teaching schedule collision, schedule collision with another schedule, practicum lesson schedules that collides with theory class, and the number of classrooms available. In this research, genetic algorithm is implemented to perform theory class and practicum timetable scheduling process. The algorithm will be used to process the data containing lists of lecturers, courses, and class rooms, obtained from information technology department at University of Sumatera Utara. The result of scheduling process using genetic algorithm is the most optimal timetable that conforms to available time slots, class rooms, courses, and lecturer schedules.

This paper discusses the problem of project selection in the presence of two objective functions that maximize profit and minimize cost and the existence of some limitations is limited resources availability and time available so that there is need allocation of resources in each project. These resources are human resources, machine resources, raw material resources. This is treated as a consideration to not exceed the budget that has been determined. So that can be formulated mathematics for objective function (multi-objective) with boundaries that fulfilled. To assist the project selection process, a multi-objective combinatorial optimization approach is used to obtain an optimal solution for the selection of the right project. It then described a multi-objective method of genetic algorithm as one method of multi-objective combinatorial optimization approach to simplify the project selection process in a large scope.

Backpropagation is a good artificial neural network algorithm used to predict, one of which is to predict the rate of Consumer Price Index (CPI) based on the foodstuff sector. While conjugate gradient fletcher reeves is a suitable optimization method when juxtaposed with backpropagation method, because this method can shorten iteration without reducing the quality of training and testing result. Consumer Price Index (CPI) data that will be predicted to come from the Central Statistics Agency (BPS) Pematangsiantar. The results of this study will be expected to contribute to the government in making policies to improve economic growth. In this study, the data obtained will be processed by conducting training and testing with artificial neural network backpropagation by using parameter learning rate 0,01 and target error minimum that is 0.001-0,09. The training network is built with binary and bipolar sigmoid activation functions. After the results with backpropagation are obtained, it will then be optimized using the conjugate gradient fletcher reeves method by conducting the same training and testing based on 5 predefined network architectures. The result, the method used can increase the speed and accuracy result.

Back-propagation is one of the learning algorithms on artificial neural networks that have been widely used to solve various problems, such as pattern recognition, prediction and classification. The Back-propagation architecture will affect the outcome of learning processed. BFGS Quasi-Newton is one of the functions that can be used to change the weight of back-propagation. This research tested some back-propagation architectures using classical back-propagation and back-propagation with BFGS. There are 7 architectures that have been tested on glass dataset with various numbers of neurons, 6 architectures with 1 hidden layer and 1 architecture with 2 hidden layers. BP with BFGS improves the convergence of the learning process. The average improvement convergence is 98.34%. BP with BFGS is more optimal on architectures with smaller number of neurons with decreased epoch number is 94.37% with the increase of accuracy about 0.5%.