Articles
<![CDATA[Prediksi Suku Bunga Acuan (BI Rate) Menggunakan Metode Adaptive Neuro Fuzzy Inference System (ANFIS) ]]>
<![CDATA[Nur Adli Ari Darmawand]]>;
<![CDATA[Dian Eka Ratnawati]]>;
<![CDATA[Rizal Setya Perdana]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 1 (2018): Januari 2018 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (992.843 KB)
<![CDATA[BI Rate is the interest rate policy that reflects the monetary stance policy which set by Bank of Indonesia and announced to the public. BI Rate is used as the parameter of economic activity of a country. BI Rate will affect the turnover of bank financial flows, inflation, and currency movement. The ups and downs of BI Rate are highly important for investors and market participants to increase or decrease the amount of production and to increase or decrease existing investment. That's what makes the BI Rate prediction important. The predicted BI Rate is expected to help investors and market participants to determine long-term economic decisions. In this study used Adaptive Neuro Fuzzy Inference System method which is a combination of steepest descent and least square estimator (LSE) algorithm for training. Based on the test results, it produces the best RMSE value 0.0019165.The final result obtained is the predicted value of bi rate.]]>
<![CDATA[Rancang Bangun Aplikasi Deteksi Spam Twitter menggunakan Metode Naive Bayes dan KNN pada Perangkat Bergerak Android ]]>
<![CDATA[Faisal Aji Prayoga]]>;
<![CDATA[Aryo Pinandito]]>;
<![CDATA[Rizal Setya Perdana]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 2 (2018): Februari 2018 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1117.117 KB)
<![CDATA[Twitter currently is one of the leading social networks worldwide based on the amount of monthly active users after Facebook and Instagram. People uses Twitter mostly to find out more information about breaking news or keeping up with news in general by following trending topics. As Twitter become a source of news breaks contents in form of comments and replies to share the newest ideas. Therefore, several mobile applications that utilize Twitter API has been developed to provide a convenient way in providing trending topics to their user. Twitter trending topics offers an effective opportunity in marketing point of view for online marketers to promote their marketing contents. Spam contents in Twitter were found to be distracting and annoying for certain users, thus mobile application to deliver spam-free Twitter trending topics contents is needed. This research designs an Android application framework that allow developers to build their own implementation of spam detection classifier for Twitter contents as application library. This research implements two classification methods, i.e. Naive Bayes and K-Nearest Neighbor, to identify spam in Twitter trending topics. The Naive Bayes and K-Nearest Neighbor classification methods are able to detect spam and ham contents with 82% and 71% accuracy respectively.]]>
<![CDATA[Peramalan Kenaikan Indeks Harga Konsumen/Inflasi Kota Malang menggunakan Metode Support Vector Regression (SVR) dengan Chaotic Genetic Algorithm-Simulated Annealing (CGASA) ]]>
<![CDATA[Muhammad Maulana Solihin Hidayatullah]]>;
<![CDATA[Imam Cholissodin]]>;
<![CDATA[Rizal Setya Perdana]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 2 (2018): Februari 2018 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1337.38 KB)
<![CDATA[Inflation forecasting is complicated. Inflation rate calculated based on the rise in the consumer price index (CPI) is influenced by various factors ranging from volatile prices of various types of goods, rupiah exchange rate, world inflation rate, government policy, fluctuations in the supply of goods and demand. Hybridation algorithm of support vector regression (SVR) with chaotic sequences and genetic algorithms has been successfully applied to improve the accuracy of forecasting in various fields. But it has not been explored the usability of this algorithm in the field of market economy which is forecasting inflation. This journal will analyze the potential of hybridization algorithm that which is chaotic genetic algorithm-simulated annealing algorithm (CGASA) with SVR model to improve the performance of forecasting accuracy. With the chaotic sequence of chaotic sequences, it will be able to avoid premature local optimum and early convergention, especially with the simulated annealing algorithm that increases the search area of ​​the solution. The results of the forecasting test in this study show better accuracy than the previous research which has been studied is the combined ensemble method between autoregressive integrated moving average (ARIMA) and artificial neural network (ANN) algorithm.]]>
<![CDATA[Penerapan Sentimen Analisis Acara Televisi Pada Twitter Menggunakan Support Vector Machine dan Algoritma Genetika sebagai Metode Seleksi Fitur ]]>
<![CDATA[I Made Budi Surya Darma]]>;
<![CDATA[Rizal Setya Perdana]]>;
<![CDATA[Indriati Indriati]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 3 (2018): Maret 2018 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1037.703 KB)
<![CDATA[Rating is one approach method that can be used to find out about audience satisfaction of a TV show. In Indonesia, rating was calculated by using AGB Nielsen services. However, rating that AGB Nielsen produced was based on the people watching bahavior in 10 major cities in Indonesia. Therefore, rating in Indonesia requires another method to get the watching behavior of the whole people in Indonesia. Twitter, can be used to get Indonesia people watching behavior. Through the published tweets, it can be applied the process of extracting information by using classification techniques to get the opinions. One of the classification techniques that can be applied to text categorization is the Support Vector Machine (SVM) it`s suitable for multiple dimension data. By optimizing the features that will be used, it can provide optimal results with less features used. One of the feature selection methods that can be applied to SVM is the genetic algorithm (GA). System calculates the rating, based on positive and negative sentiments about the TV show and divided by the population of the tweet used. The rating comparison test that produced by AGB Nielsen and system shows an average error value of 0.562. In testing the accuracy before and after the feature selection method is applied, showed results with average error value 0.62%.]]>
<![CDATA[Pemodelan Sistem Pakar untuk Identifikasi Hama Penyakit Tanaman Tebu dengan Metode Dempster-Shafer ]]>
<![CDATA[Yusuf Nurcahyo]]>;
<![CDATA[Nurul Hidayat]]>;
<![CDATA[Rizal Setya Perdana]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 3 (2018): Maret 2018 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1054.056 KB)
<![CDATA[Every year, the demand for sugar continues to grow as consumption of the community grows and growth in the food and beverage sector. In 2014 the consumption of white crystal sugar (GKP) reaches 2.84 million tons, while in 2015, GKP consumption reached 2.98 million tons and will continue to increase every year. But now the productivity of sugar has decreased. The decline in productivity is caused by several things, one of which is the decrease in the level of sugar content or sugar content in sugarcane stalks. In addition to high rainfall and improper harvesting methods, other sugar cane inhibiting factors are pests and diseases of sugarcane. The limited number of experts and extension agents while in the field, as well as the lack of knowledge of farmers cause problems surrounding pests and diseases of this cane can not be solved immediately. Because of the limitations of these conditions, the authors make an expert system to facilitate the farmers in order to identify diseases and pests in sugar cane plants. This system makes the process of disease identification as well as the conclusion of the diagnosis calculated using the Dempster-shafer method by using fact-insert facts from the user. This expert system makes it easy to determine the type of disease that suits the symptoms. Testing is done by comparing the diagnosis of the system with the results of expert diagnosis using 30 test data consisting of 19 cases of pests and 11 cases of disease in sugarcane.]]>
<![CDATA[Implementasi Metode Backpropagation Untuk Klasifikasi Kenaikan Harga Minyak Kelapa Sawit ]]>
<![CDATA[Dwi Rahayu]]>;
<![CDATA[Randy Cahya Wihandika]]>;
<![CDATA[Rizal Setya Perdana]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 4 (2018): April 2018 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1109.234 KB)
<![CDATA[Palm oil is a plantation product that is the main export commodity of Indonesia. The increasing amount of processed materials that can be made by using palm oil makes the rise of oil palm demand. The main factor causing an increase in demand for palm oil is a relatively low price compared to its competitor prices such as soybean oil, sunflower seed oil, peanut oil, cotton oil and rapeseed oil. Price becomes an important factor to determine the selling point of the product. Prices also affect the producer's profit. The classification of the possibility of rising or falling prices of palm oil becomes a major consideration of a consumer to buy. This writing discusses the classification of palm oil prices using Backpropagation method. The Backpropagation method will model the coconut oil price data 5 months earlier to find the classification results in the 6th month. Classification results obtained have an accuracy of 69.57% with the number of hidden neurons as much as 50, the value of learning rate as big as 0.1 and the number of maximum iterations of 70,000.]]>
<![CDATA[Klasifikasi Penyimpangan Tumbuh Kembang Anak Menggunakan Metode Extreme Learning Machine (ELM) ]]>
<![CDATA[Makrina Christy Ariestyani]]>;
<![CDATA[Putra Pandu Adikara]]>;
<![CDATA[Rizal Setya Perdana]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 4 (2018): April 2018 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1307.34 KB)
<![CDATA[Growth and development of children at an early age affect the child's personal ability in the future. Every child is unique, so growth and growth are not the same. Slow growth and development are often considered normal. Deviation of late child growth is known to result in long-term and difficult to repair. Based on these problems, this research was conducted by using the Extreme Learning Machine (ELM) method for the classification of child growth deviations. ELM method consists of training process as system learning and testing to obtain the result of classification. The parameters test are test of ratio of training data and test data, testing the influence of number of hidden neurons over time, and comparative test of activation function. Accuracy calculation is done by using confusion matrix to know the accuracy of system work in each class. The result of parameter test shows that the ratio of training data and test data with ratio 70:30, the number of hidden neurons as many as 10 units, and the binary activation function is the parameter with the best accuracy value. The comparison of the result of the classification of child growth deviation with the help of psychologist shows that the system produces poor accuracy. This can be due to the small and unbalanced data used for the research.]]>
<![CDATA[Klasifikasi Penyakit Kulit Pada Manusia Menggunakan Metode Binary Decision Tree Support Vector Machine (BDTSVM) (Studi Kasus: Puskesmas Dinoyo Kota Malang) ]]>
<![CDATA[Dyan Dyanmita Putri]]>;
<![CDATA[Muhammad Tanzil Furqon]]>;
<![CDATA[Rizal Setya Perdana]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 5 (2018): Mei 2018 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1435.086 KB)
<![CDATA[The skin is an organ in the human body is very important because it lies on the outside of the body that serves to receive stimuli such as touch, pain and other influences from the outside. Skin disease is one of the most common diseases in tropical countries such as Indonesia. The lack of knowledge about the type of skin disease and do not know how to prevent it cause a person can get acute skin disease. So with the help of computer technology is expected to attack the skin of the human body can be detected early and it can minimize the occurrence of more dangerous diseases. This research aims to determine the classification of skin diseases in humans using the method of Binary Decision Tree Support Vector Machine (BDTSVM) Based on the test results obtained the best accuracy of 97.14% with SVM parameter test that is the value of λ (lambda) = 0,5, C (complexity) = 1, constant γ (gamma) = 0,01, and itermax = 10.]]>
<![CDATA[Prediksi Rating Pada Review Produk Kecantikan Menggunakan Metode Naive Bayes Dan Categorical Proportional Difference (CPD) ]]>
<![CDATA[Fathor Rosi]]>;
<![CDATA[Mochammad Ali Fauzi]]>;
<![CDATA[Rizal Setya Perdana]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 5 (2018): Mei 2018 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1452.418 KB)
<![CDATA[Beauty products at this time become a popular thing in various circles, especially among women. Almost all of them have beauty products and are included as a primary requirement to support their better performances. The existence of a product can not be separated from a comment or review of the consumer for the product. Of course with the review can help consumers to be more selective again in choosing a product. And from the production side can be helped to measure how far the quality of the products they produce. But from the production itself sometimes have difficulty in sorting and categorize the review, whether the product is good quality, good enough, not good, and so forth. In this study the assessment of a product based on the review given is rating. So it takes a rating prediction system to predict and determine the right rating based on the reviews given by the users of a product. To support the system built required methods to solve the problem, in this study researchers used the method of Naive Bayes and Categorical Proportional Difference. Naive Bayes is a method for classification whereas Categorical Proportional Difference is a feature selection to further optimize the results of classification. From the test results, obtained the best accuracy level when the use of features by 50% with an accuracy of 87%. These results are the best results of the results with other feature usage ratios of 25%, 75% and 100%. From these results CPD proven to make the selection of words that are considered relevant or irrelevant to do classification.]]>
<![CDATA[Pelatihan Multi-Layer Neural Network Menggunakan Algoritma Genetika untuk Memprediksi Harga Saham Esok Hari (T+1) ]]>
<![CDATA[Grady Davinsyah]]>;
<![CDATA[Wayan Firdaus Mahmudy]]>;
<![CDATA[Rizal Setya Perdana]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 6 (2018): Juni 2018 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1017.541 KB)
<![CDATA[Stock is one of investment instrument which is popular because of the high profit potential and risk. These profit potential and risk are caused by fluctuations of the stock price in the stock market. To minimalize the risk, a system which is able to predict closing price of the next day is required. The architecture which is used in this research is multi-layer neural network. This architecture is trained with 2 different training methods, which is backpropagation and genetic algorithm. Both of the methods aim to gain weights of all network's architecture. Backpropagation's parameters which obtained during the research are 4500 iteration and 0.7 learning rate. For genetic algorithm's parameters which obtained during the research are 2000 generations, population size of 200, crossover rate 0.1 and mutation rate 0.9. By using those parameters, average RMSE value which produced using backpropagation algorithm is 0.048006. Meanwhile when using genetic algorithm as a training method, average RMSE value which produced by the network is 0.065205. So in this research, average error value which is produced by using backpropagation training is smaller than using genetic algorithm training method.]]>
