Articles
<![CDATA[Prediksi Curah Hujan Menggunakan Evolving Fuzzy ]]>
<![CDATA[Bernadus Seno Aji]]>;
<![CDATA[Fhira Nhita]]>;
<![CDATA[Adiwijaya Adiwijaya]]>
<![CDATA[ Indonesia Symposium on Computing Indonesian Symposium on Computing 2014/Seminar Nasional Ilmu Komputasi Teknik Informatika (SNIKTI) ]]>
Publisher : <![CDATA[Indonesia Symposium on Computing ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[Meteorologi atau ilmu yang mempelajari tentang cuaca dan faktor-faktor yang mempengaruhinya dan salah satu faktor yang dipelajari adalah curah hujan.Pada kehidupan sehari-hari, seringkali kita menemuai prediksi curah hujan diberbagai media massa. Kebutuhan akan keadaan cuaca esok hari sangat dibutuhkan untuk menyusun berbagai rencana. Untuk masa lampau, perkiraan curah hujan sangat bergantung dengan bulannya, ada musim kemarau dan musim penghujan. Namun saat ini, curah hujan semakin sulit untuk diprediksi sehingga diperlukan model atau sistem yang dapat memprediksi curah hujan dengan akurat. Pada penelitian Penelitian ini dijelaskan tentang prediksi curah hujan menggunakan Evolving Fuzzy. Algoritma Genetika akan digunakan untuk mengoptimasi fungsi keanggotaan dan rule Fuzzy. Fuzzy yang telah dioptimasi digunakan untuk memprediksi curah hujan esok hari. Parameter input yang akan digunakan merupakan data parameter cuaca. Berdasarkan hasil pelatihan Fuzzy menggunakan Algoritma Genetika didapat parameter Fuzzy yang optimal dihasilkan dari Ukuran populasi 50, probabilitas crossover 0.7, probabilitas mutasi 0.1 serta jumlah individu yang dievaluasi sebanyak 10000 dengan akurasi pelatihan 66.09% dan akurasi pengujian 63.13%.]]>
<![CDATA[Klasterisasi Data Microarray Menggunakan Metode Clique Partitioning ]]>
<![CDATA[Lisa Marianah]]>;
<![CDATA[Fhira Nhita]]>;
<![CDATA[Adiwijaya Adiwijya]]>
<![CDATA[ Indonesia Symposium on Computing Indonesian Symposium on Computing 2014/Seminar Nasional Ilmu Komputasi Teknik Informatika (SNIKTI) ]]>
Publisher : <![CDATA[Indonesia Symposium on Computing ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[Microarray merupakan salah satu teknologi bioinformatika yang dapat mengetahui profil ekspresi gen secara paralel dalam jumlah dimensi yang besar. Microarray digunakan untuk membantu peneliti dalam melakukan diagnosis terhadap penyakit. Pada analisis penelitian, data Microarray yang memiliki jumlah dimensi yang besar akan sangat sulit untuk diteliti. Oleh karena itu dibutuhkan klasterisasi untuk memperoleh klaster sehingga dihasilkan informasi dari data tersebut. Metode yang digunakan adalah clique partition yang didasari oleh prosedur branch and bound dan DFS untuk menelusuri setiap titik dalam graf.Proses menemukan klaster diawali dengan mentransformasikan data Microarray ke dalam graf yang dibentuk menjadi matriks adjacency. Dalam penelitian Penelitian ini, penentuan korelasi ditentukan berdasarkan nilai threshold. Mencari klaster menggunakan clique partition berarti mencari maximal clique. Hasil yang diperoleh menunjukkan perubahan threshold mempengaruhi jumlah klaster yang diperoleh. Analisis hasil klaster untuk data Microarray yang digunakan menunjukkan bahwa pemilihan threshold yang lebih kecil memberikan nilai error SSE yang lebih kecil.]]>
<![CDATA[Perancangan Pengaturan Durasi Lampu Lalu Lintas Adaptif ]]>
<![CDATA[Rudericus Andika Pramudya]]>;
<![CDATA[Mahmud Imrona]]>;
<![CDATA[Fhira Nhita]]>
<![CDATA[ Indonesia Symposium on Computing Indonesia Symposium on Computing 2015 ]]>
Publisher : <![CDATA[Indonesia Symposium on Computing ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[Kemacetan lalu lintas adalah suatu permasalahan yang selalu dirasakan masyarakat pengguna jalan, terlebih lagi bagi masyarakat di kota-kota besar, seperti Bandung. Kemacetan lalu lintas berdampak buruk bagi siapapun. Kemacetan mengakibatkan kerugian yang besar bagi individu maupun kelompok tertentu. Maka dari itu dibutuhkan solusi untuk mengurangi kemacetan. Solusi yang ditawarkan adalah pendekatan perhitungan lama durasi waktu lampu lalu lintas yang efisien, sehingga dapat mengurangi kemacetan berlebihan yang terjadi dan arus kendaraan menjadi lancar. Pada penelitian ini dibuat usulan sistem pengendali lampu lalu lintas yang adaptif, sistem ini menggunakan jaringan syaraf tiruan recurrent neural network untuk memecahkan permasalahan yang bersifat tidak pasti. Rancangan jaringan syaraf tiruan dicari dengan algoritma genetika (AG) berdasarkan data yang diperoleh dari data di lapangan. Berdasarkan penelitian yang telah dilakukan, didapatkan arsitektur terbaik berupa bobot-bobot dan hubungan antar neuron. Akurasi tertinggi pada sistem yang dibandingkan dengan fix time menunjukkan hasil yang cukup baik yaitu 90,082% untuk pembelajaran dan 87,191% untuk pengujian pengaturan durasi waktu lampu hijau lalu lintas adaptif. Jaringan syaraf tiruan yang telah dioptimalkan dengan proses pencarian arsitektur terbaik oleh algoritma genetika mempunyai hasil uji kinerja sistem yang lebih baik dibandingkan dengan fix time. Â ]]>
<![CDATA[The Optimal High Performance Computing Infrastructure for Solving High Complexity Problem ]]>
<![CDATA[Yuliant Sibaroni]]>;
<![CDATA[Fitriyani Fitriyani]]>;
<![CDATA[Fhira Nhita]]>
<![CDATA[ TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 14, No 4: December 2016 ]]>
Publisher : <![CDATA[Universitas Ahmad Dahlan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.12928/telkomnika.v14i4.3586
<![CDATA[The high complexity of the problems today requires increasingly powerful hardware performance. Corresponding economic laws, the more reliable the performance of the hardware, it will be comparable to the higher price. Associated with the high-performance computing (HPC) infrastructures, there are three hardware architecture that can be used, i.e. Computer Cluster, Graphical Processing Unit (GPU), and Super Computer. The goal of this research is to determine the most optimal of HPC infrastructure to solve high complexity problem. For this reason, we chose Travelling Salesman Problem (TSP) as a case study and Genetic Algorithm as a method to solve TSP. Travelling Salesman Problem is belong often the case in real life and has a high computational complexity. While the Genetic Algorithm (GA) is belong a reliable algorithm to solve complex cases, but has the disadvantage that the time complexity level is very high. In some research related to HPC infrastructure comparison, the performance of multi-core CPU single node for data computation has not been done. Whereas the current development trend leads to the development of PCs with higher specifications like this. Based on the experiments results, we conclude that the use of GA is very effective to solve TSP. the use of multi-core single-node in parallel for solving high complexity problems as far as this is still better than the two other infrastructure but slightly below compare to multi-core single-node serially, while GPU deliver the worst performance compared to others infrastructure. The utilization of a super computer PC for data computation is still quite promising considering the ease of implementation, while the GPU utilization for the purposes of data computing is profitable if we only utilize GPU to support CPU for data computing.]]>
<![CDATA[IMPLEMENTASI ALGORITMA WEIGHTED MOVING AVERAGE PADA (FUZZY EAs) UNTUK PERAMALAN KALENDER MASA TANAM BERBASIS CURAH HUJAN ]]>
<![CDATA[Fhira Nhita]]>;
<![CDATA[Zahra Putri Agusta zahra]]>
<![CDATA[ Indonesia Journal on Computing (Indo-JC) Vol. 1 No. 1 (2016): March, 2016 ]]>
Publisher : <![CDATA[School of Computing, Telkom University ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.21108/INDOJC.2016.1.1.7
<![CDATA[Peramalan merupakan proses memperkirakan sesuatu secara sistematis berdasarkan keadaan atau fakta sebelumnya. Peramalan bisa dilakukan melalui serangkaian metode ilmiah atau dengan subjektif belaka. Soft computing (SC) merupakan salah satu metode ilmiah yang dapat digunakan untuk kasus peramalan atau prediksi, Soft Computing (SC) memiliki Algoritma dasar yakni Fuzzy System, Artificial Neural Network (ANN), dan Evolutionary Alghorithms (EAs). Pada Tugas akhir ini dilakukan penelitian mengenai peramalan kalender masa tanam tanaman jagung yang berbasis curah hujan di wilayah Soreang Kabupaten Bandung menggunakan salah satu jenis algoritma dasar Soft computing (SC) yakni Evolutionary Alghorithms (EAs). Data yang digunakan adalah data curah hujan wilayah Soreang Kabupaten Bandung selama 10 tahun terakhir (2006-2015), data ini akan melalui preprocessing terlebih dahulu dengan Weighted Moving Average (WMA). Pada representasi individu, EAs memiliki empat algoritma yang bisa digunakan, salah satunya Grammatical Evolution (GE) yang akan digunakan pada penelitian ini. Selanjutnya, dalam tugas akhir ini digunakan logika Fuzzy untuk pengoptimasian GE, dengan cara mendefinisikan beberapa parameter pada awal running , agar proses dapat berjalan dengan baik. Hasil akhir yang didapat menunjukkan bahwa logika Fuzzy membantu meningkatkan performansi Eas dan Fuzzy EAs menghasilkan performansi peramalan kalender masa tanam sebesar 76,93%. Hasil peramalan akan digunakan untuk pembuatan kalender masa tanam di Kabupaten Bandung selama 13 (tiga belas) bulan yang dimulai pada Oktober 2014 sampai Oktober 2015. ]]>
<![CDATA[Clustering of Earthquake Prone Areas in Indonesia Using K-Medoids Algorithm ]]>
<![CDATA[Fiona Ramadhani Senduk]]>;
<![CDATA[Indwiarti Indwiarti]]>;
<![CDATA[Fhira Nhita]]>
<![CDATA[ Indonesia Journal on Computing (Indo-JC) Vol. 4 No. 3 (2019): December, 2019 ]]>
Publisher : <![CDATA[School of Computing, Telkom University ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.34818/INDOJC.2019.4.3.359
<![CDATA[Located right above the ring of fire makes Indonesia prone to natural disasters, especially earthquakes. With the number of earthquakes that have occurred, disaster mitigation is very much needed. The use of data mining methods will certainly help in disaster mitigation. One method that can be used is clustering. The clustering algorithm used in this study is k-Medoids, and comparison with the k-means algorithm is also carried out. The data used are earthquake data from all regions in Indonesia during 2014-2018 that were recorded by the United State Geological Survey (USGS). The results obtained showed that k-medoids giving better silhouette results and computational time than k-means. For the k-medoids cluster results, the highest value of silhouette was 0.4574067 with k = 6. The analysis of each cluster is presented in this paper.Keywords: clustering,data mining, earthquake, k-medoid.]]>
<![CDATA[Comparative Study between Parallel K-Means and Parallel K-Medoids with Message Passing Interface (MPI) ]]>
<![CDATA[Fhira Nhita]]>
<![CDATA[ International Journal on Information and Communication Technology (IJoICT) Vol. 2 No. 2 (2016): December 2016 ]]>
Publisher : <![CDATA[School of Computing, Telkom University ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.21108/IJOICT.2016.22.86
<![CDATA[Data mining is a combination technology for analyze a useful information from dataset using some technique such as classification, clustering, and etc. Clustering is one of the most used data mining technique these day. K-Means and K-Medoids is one of clustering algorithms that mostly used because it’s easy implementation, efficient, and also present good results. Besides mining important information, the needs of time spent when mining data is also a concern in today era considering the real world applications produce huge volume of data. This research analyzed the result from K-Means and K-Medoids algorithm and time performance using High Performance Computing (HPC) Cluster to parallelize K-Means and K-Medoids algorithms and using Message Passing Interface (MPI) library. The results shown that K-Means algorithm gives smaller SSE than K-Medoids. And also parallel algorithm that used MPI gives faster computation time than sequential algorithm.]]>
<![CDATA[Weather Forecasting in Bandung Regency based on FP-Growth Algorithm ]]>
<![CDATA[Farida Nur Khasanah]]>;
<![CDATA[Fhira Nhita]]>
<![CDATA[ International Journal on Information and Communication Technology (IJoICT) Vol. 4 No. 2 (2018): December 2018 ]]>
Publisher : <![CDATA[School of Computing, Telkom University ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.21108/IJOICT.2018.42.203
<![CDATA[Weather change is one of the things that can affect people around the world in doing activities, including in Indonesia. The area of Indonesia, especially in Bandung regency has a high intensity of rainfall, compared with other regions. The people of Bandung Regency mostly have livelihoods in the fields of industry and agriculture, both of which are closely related to the effects of weather. Weather prediction is used for reference, so the future of society can prepare all possible weather before the move. One method of data mining used to predict weather is the association rule method. In this method there is Frequent Pattern Growth (FP-Growth) algorithm, this algorithm is used to determine the pattern of linkage between attribute weather with rainfall. The result of the FP-Growth algorithm is an association rule, the result of the algorithm rules is then used as reference for data entry in the classification process, where the process is done to get the forecast based on the rainfall category to obtain maximum accuracy. The highest performance result of FP-Growth from the result of rules based on its confidence value is 92%.]]>
<![CDATA[Price Prediction of Chili Commodities in Bandung Regency Using Bayesian Network ]]>
<![CDATA[Putri Nuvaisiyah]]>;
<![CDATA[Fhira Nhita]]>;
<![CDATA[Deni Saepudin]]>
<![CDATA[ International Journal on Information and Communication Technology (IJoICT) Vol. 4 No. 2 (2018): December 2018 ]]>
Publisher : <![CDATA[School of Computing, Telkom University ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.21108/IJOICT.2018.42.204
<![CDATA[Chili is one of the agricultural commodities consumed by Indonesian people. Market data in recent years show that chili prices tend to fluctuate as supply and demand changes. One of the impacts of chili price changes for farmers is the production cost is higher than the selling price. In addition to supply and demand changes, the weather is also indicated as a factor of price changes due to the weather being considered by farmers to grow chili. Price prediction is needed to determine the condition of chili prices in the future to help farmers in making decisions to plant at the right time. One method that can be used to make prediction is Data Mining classification method. In this paper, Bayesian network algorithm was used as Data Mining classification method to predict the price of chili commodity in Bandung Regency based on weather information and classified the price into economic class and not economic class. The result shows that the prediction model obtained by the Bayesian Network gives a system’s performance for precision and recall that is 1 and 0.94 respectively with average accuracy of 85.5% in classifying the price.]]>
<![CDATA[Implementation of Ensemble Method in Schizophrenia Identification Based on Microarray Data ]]>
<![CDATA[Diya Namira Purba]]>;
<![CDATA[Fhira Nhita]]>;
<![CDATA[Isman Kurniawan]]>
<![CDATA[ Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 6 No 1 (2022): Februari 2022 ]]>
Publisher : <![CDATA[Ikatan Ahli Informatika Indonesia (IAII) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (377.317 KB)
|
DOI: 10.29207/resti.v6i1.3788
<![CDATA[Schizophrenia is a chronic mental illness that leads the patient to hallucinations and delusions with a prevalence of 0.4% worldwide. The importance early detection of Schizophrenia is tracking the pre-syndrome of Schizophrenia during the active phase, and could reduce psychosis symptomatic. However, the method sometimes cannot detect the symptoms accurately. As an alternative, machine learning can be implemented on microarray data for early detection. This study aimed to implement three ensemble methods, i.e., Random Forest (RF), Adaptive Boosting (AdaBoost), and Extreme Gradient Boosting (XGBoost) to identify Schizophrenia. Hyperparameter tuning was performed to improve the performance of the models. Based on the results, we found that the model 6, which is developed by the XGBoost method, performs better than other models with the value of accuracy and F1-score are 0.87 and 0.87, respectively.]]>
