Muhammad Zarlis

The role of information and communication technology in developing smart education

The right to get a proper education for every citizen had been regulated by the government, but not all citizens have the same opportunity. This is due to the other factors in the nations infrastructure, Frontier, Outermost, and Disadvantaged (3T) which have not beenaccomodatedto access information and communication technology (ICT), and the ideal learning environment in order to pursue knowledge. This condition could be achieved by reforming higher education. Such reforms include the provision of educational services in the form of a flexible learner-oriented, and to change the curriculum with market based.These changes would include the provision of lecturers, professors, and professional teaching force. Another important effort is to update the quality of higher education with resource utilization. This paper proposes a new education business model to realize the Smart Education (SE), with an orientation on the proven skills and competitive.SE is the higher education system to optimize output (outcome) learning with combine individual learning and collaboration techniques based network system, informal practice learning and formal theory. UtilizingICT resources can improve the quality and access to higher education in supporting activities of higher education.This paper shows that ICT resources can support virtual connected with the use of shared resources, such as resource of information, learning resources, computing resources, and human resources.

A framework of training ANFIS using Chicken Swarm Optimization for solving classification problems

The result of training parameters described Adaptive Neuro-Fuzzy Inference System (ANFIS) performance. The speed and reliability of training effect depend on the training mechanism. There have been many methods used to train the parameters of ANFIS as using GD, metaheuristic techniques, and LSE. But there are still many methods developed to achieve efficiently. One of the proposed algorithm to improve the performance of ANFIS is Chicken swarm optimization (CSO) algorithm. The experimental results of training ANFIS network for classification problems show that ANFIS-CSO algorithm achieved better accuracy.

Smart City: Utilization of IT resources to encounter natural disaster

This study proposes a framework for the utilization of IT resources in the face of natural disasters with the concept of Smart City in urban areas, which often face the earthquake, particularly in the city of North Sumatra and Aceh. Smart City is a city that integrates social development, capital, civic participation, and transportation with the use of information technology to support the preservation of natural resources and improved quality of life. Changes in the climate and environment have an impact on the occurrence of natural disasters, which tend to increase in recent decades, thus providing socio-economic impacts for the community. This study suggests a new approach that combines the Geographic Information System (GIS) and Mobile IT-based Android in the form of Geospatial information to encounter disaster. Resources and IT Infrastructure in implementing the Smart Mobility with Mobile service can make urban areas as a Smart City. This study describes the urban growth using the Smart City concept and considers how a GIS and Mobile Systems can increase Disaster Management, which consists of Preparedness, mitigation, response, and recovery for recovery from natural disasters.

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.

Modification Of Learning Rate With Lvq Model Improvement In Learning Backpropagation

One type of artificial neural network is a backpropagation, This algorithm trained with the network architecture used during the training as well as providing the correct output to insert a similar but not the same with the architecture in use at training.The selection of appropriate parameters also affects the outcome, value of learning rate is one of the parameters which influence the process of training, Learning rate affects the speed of learning process on the network architecture.If the learning rate is set too large, then the algorithm will become unstable and otherwise the algorithm will converge in a very long period of time.So this study was made to determine the value of learning rate on the backpropagation algorithm. LVQ models of learning rate is one of the models used in the determination of the value of the learning rate of the algorithm LVQ.By modifying this LVQ model to be applied to the backpropagation algorithm. From the experimental results known to modify the learning rate LVQ models were applied to the backpropagation algorithm learning process becomes faster (epoch less).

Optimizing Robinson Operator with Ant Colony Optimization As a Digital Image Edge Detection Method

Edge detection serves to identify the boundaries of an object against a background of mutual overlap. One of the classic method for edge detection is operator Robinson. Operator Robinson produces a thin, not assertive and grey line edge. To overcome these deficiencies, the proposed improvements to edge detection method with the approach graph with Ant Colony Optimization algorithm. The repairs may be performed are thicken the edge and connect the edges cut off. Edge detection research aims to do optimization of operator Robinson with Ant Colony Optimization then compare the output and generated the inferred extent of Ant Colony Optimization can improve result of edge detection that has not been optimized and improve the accuracy of the results of Robinson edge detection. The parameters used in performance measurement of edge detection are morphology of the resulting edge line, MSE and PSNR. The result showed that Robinson and Ant Colony Optimization method produces images with a more assertive and thick edge. Ant Colony Optimization method is able to be used as a method for optimizing operator Robinson by improving the image result of Robinson detection average 16.77 % than classic Robinson result.

Analysis of Accuracy and Epoch on Back-propagation BFGS Quasi-Newton

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%.

Modification of Symmetric Cryptography with Combining Affine Chiper and Caesar Chiper which Dynamic Nature in Matrix of Chiper Transposition by Applying Flow Pattern in the Planting Rice

Classical cryptography is a way of disguising the news done by the people when there was no computer. The goal is to protect information by way of encoding. This paper describesa modification of classical algorithms to make cryptanalis difficult to steal undisclosed messages. There are three types of classical algorithms that are combined affine chiper, Caesar chiper and chiper transposition. Where for chiperteks affine chiper and Caesar chiper can be looped as much as the initial key, because the result can be varied as much as key value, then affine chiper and Caesar chiper in this case is dynamic. Then the results of the affine and Caesar will be combined in the transposition chiper matrix by applying the pattern of rice cultivation path and for chipertext retrieval by finally applying the pattern of rice planting path. And the final digit of the digit shown in the form of binary digits so that 5 characters can be changed to 80 digit bits are scrambled. Thus the cryptanalyst will be more difficult and takes a very long time to hack information that has been kept secret.

The Planning of Smart City to Mitigate the Impacts of Natural Disaster in North Sumatera

This article introduces the smart urban planning in the mitigation of natural disasters in urban areas in Indonesia especially North Sumatera. A smart city is a city-based social development, capital, citizen participation, transportation and information technology, natural resources and quality of life. Frequency and socio-economic impacts of natural disasters frequent in recent decades due to climate change and the environment. The approach used in this paper is a combination of Geographic Information System (GIS) and mobile IT in the form of geospatial information. Mobile services sector in which the city government is involved in the formation of smart cities. This article reviews the growth of smart cities and considers how a systems can improve mitigation and adaptation approaches to these risks and to recovery from the natural disasters.

A soft set approach for fast clustering attribute selection

Attribute-based data clustering has been proven as one of the efficient methods in data clustering. Set theory approaches for data clustering exist to handle attribute-based data clustering. The MDDS, a soft set based technique has proven its applicability in data clustering. However, in reviewing MDDS, where its calculations are based on comparing all constructed multi-soft sets, it still suffers from high computational time. This research presents a modification of the MDDS by generating an alternative technique to reduce its computational complexity. To provide alternative solutions from MDDS algorithm, we derive a new algorithm that can lesser response time. It is using theory of soft set by selecting and excluding the set having no effect domination on other sets. The experiments are implemented in MATLAB software thought to UCI benchmark datasets. The computation experiment illustrate that the time response can be speed up to 67.56 % by proposed algorithm compared with MDDS.