Articles
<![CDATA[Implementasi Sistem Pakar Diagnosa Penyakit Gigi dan Mulut Menggunakan Metode Hybrid Case-Based dan Rule-Based Reasoning ]]>
<![CDATA[Ade Romadhony]]>;
<![CDATA[Siti Saadah]]>
<![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[Kesehatan adalah poin terpenting dalam hidup kita. Terkadang kita lupa untuk menjaga tubuh kita, apalagi pada bagian-bagian tubuh yang terkecil seperti gigi dan mulut. Masyarakat di Indonesia khususnya cenderung untuk memeriksa gigi dan mulut ketika sudah mempunyai penyakit yang parah dan mengganggu aktivitas. Untuk itu, dibuatlah sebuah sistem pakar yang dapat mendeteksi penyakit gigi dan mulut. Pengertian dari sistem pakar adalah sebuah sistem yang bekerja seperti layaknya seorang ahli di bidangnya sehingga dapat membantu permasalahan yang ada dalam hidup. Sistem ini menggunakan metode Hybrid Rule Based-Case Based Reasoning di mana metode ini memiliki akurasi yang lebih baik dibandingkan metode yang berjalan sendiri. Rule Based-Case Based Reasoning akan mengolah gejala tersebut sehingga dapat dideteksi penyakit yang diderita pasien. Gejala tersebut juga diolah dengan Case Based Reasoning sehingga didapat penyebab dari penyakit tersebut. Solusi penyakit yang didapat dari Rule Based-Case Based Reasoning akan disaring dengan batasan Nilai Kesamaan (Similarity Value) yang ditentukan sehingga solusi yang ditampilkan adalah solusi yang mempunyai tingkat kemiripan yang besar. Adapun ketiga metode Nilai Kesamaan yang diterapkan disini adalah Jaccard Similarity, Hamming Similarity, dan Cosine Similarity. Dari hasil yang didapat, dengan menerapkan metode Hybrid Rule Based-Case Based Reasoning didapat akurasi lebih tinggi dibandingkan metode yang berjalan sendiri. Dari hasil juga didapat bahwa Cosine Similarity mempunyai hasil yang lebih baik dibandingkan kedua metode lainnya. Â ]]>
<![CDATA[Bioprospeksi ekstrak jahe gajah sebagai anti-crd: kajian aktivitas antibakteri terhadap Mycoplasma galliseptikum dan e. coli in vitro ]]>
<![CDATA[Min Rahminiwati]]>;
<![CDATA[Aulia Andi Mustika P.]]>;
<![CDATA[Siti Saadah]]>;
<![CDATA[. Andriyanto]]>;
<![CDATA[. Soeripto]]>;
<![CDATA[Unang P.]]>
<![CDATA[ Jurnal Ilmu Pertanian Indonesia Vol. 15 No. 1 (2010): Jurnal Ilmu Pertanian Indonesia ]]>
Publisher : <![CDATA[Institut Pertanian Bogor ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (971.752 KB)
<![CDATA[CRD is chronic respiratory disease in chicken caused by infection of Mycoplasma gallisepticum (M gallisepticum) and E. coli. Rio-prospective of jahe for controlling the disease was investigated through the study of antibacterial activity against M. gallisepticum of fresh ginger juice extract and fraction of hexan, ethyl acetate, methanol and water against M. gallisepticum and E. coli. The results showed that the juice of fresh ginger inhibited the growth of M. gallisepticum with the minimum inhibitory concentration that could inhibit the growth was 10 °/o. The fractions that effectively inhibited the growth of M. gal/isepticum are hexan fraction and water fraction with the smallest inhibition zone was found at concentration of at least 8 % and 10 % respectivelly.TLC examination results of hexan fraction showed a purple spot with Rf value of 0.9 and a dark blue spot with Rf value of 0.36. Based on Rf values and color reference, the first spot was suggested zingiberen and the second spot was gingerol. All fractions that were examined, did not show any inhibitory activity against thegrowth of E coli. Thus the extract of fresh ginger was only to be used to control the respiratory disease causedby M. gallisepticum but not coli.]]>
<![CDATA[Analysis of Random Forest, Multiple Regression, and Backpropagation Methods in Predicting Apartment Price Index in Indonesia ]]>
<![CDATA[I NYM Yoga Saputra]]>;
<![CDATA[Siti Saadah]]>;
<![CDATA[Prasti Eko Yunanto]]>
<![CDATA[ Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol 7, No 2 (2021): August ]]>
Publisher : <![CDATA[Universitas Ahmad Dahlan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.26555/jiteki.v7i2.20997
<![CDATA[This study focuses on predicting the apartment price index in Indonesia using property survey data from Bank Indonesia. In the era of the Covid-19 pandemic, accurately predicting the sale and purchase price of apartments is essential to minimize the impact of losses, thus making apartment prices attractive to predict. The machine learning approach used to predict the apartment price index are the Random Forest method, the Multiple Regression method, and the Backpropagation method. This study aims to determine which method is more effective in predicting small amounts of data accuracy. The data used is apartment price index data from 2012 to 2019 in the JABODEBEK area. The research will produce prediction accuracy that will determine the effectiveness of the application of the method. The Random Forest method with parameters n_estimators=100 and max_features=â€log2†produces an R2 accuracy of 0.977. The Multiple Regression method with a correlation between the selling price and rental price variables is 0.746, and the rental inflation variable is 0.042 produces an R2 accuracy of 0.559. The Backpropagation method with a 1000-4000-1 hidden scheme and 20000 iterations produces an R2 accuracy of 0.996. Therefore, the Backpropagation method is more suitable in this study compared to the other two methods. The Backpropagation method is suitable because it gets almost perfect accuracy, so this method will minimize losses in investing in buying and selling apartments in the Covid-19 pandemic era.]]>
<![CDATA[Blood Glucose Prediction Using Convolutional Long Short-Term Memory Algorithms ]]>
<![CDATA[Redy Indrawan]]>;
<![CDATA[Siti Saadah]]>;
<![CDATA[Prasti Eko Yunanto]]>
<![CDATA[ Khazanah Informatika Vol. 7 No. 2 October 2021 ]]>
Publisher : <![CDATA[Department of Informatics, Universitas Muhammadiyah Surakarta, Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.23917/khif.v7i2.14629
<![CDATA[Diabetes Mellitus is one of the preeminent causes of death to date. Effective procedures are necessary to prevent diabetes and avoid complications that may cause early death. A common approach is to control patient blood glucose, which necessitates a periodic measurement of blood glucose concentration. This study developed a blood glucose prediction system using a convolutional long short-term memory (Conv-LSTM) algorithm. Conv-LSTM is a variation of LSTM algorithms that are suitable for use in time series problems. Conv-LSTM overcomes the lack in the LSTM algorithm because the latter algorithm cannot access the content of previous memory cells when its output gate has closed. We tested the algorithm and varied the experiment to check the effect of the cross-validation ratio between 70:30 and 80:20. The study indicates that the cross-validation using a ratio of 70:30 data split is more stable compared to one with 80:20 data split. The best result shows a measure of 21.44 in RMSE and 8.73 in MAE. With the application of conv-LSTM using correct parameters and selected data split, our experiment attains accuracy comparable to the regular LSTM.]]>
<![CDATA[Prediksi Ketersediaan Energi Sumber Daya Mineral di Indonesia yang di Optimasi Menggunakan Algoritma Genetika ]]>
<![CDATA[Siti Saadah]]>;
<![CDATA[E Handayani]]>;
<![CDATA[Jondri -]]>
<![CDATA[ Indonesia Journal on Computing (Indo-JC) Vol. 1 No. 2 (2016): September, 2016 ]]>
Publisher : <![CDATA[School of Computing, Telkom University ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.21108/INDOJC.2016.1.2.27
<![CDATA[Energi dan Sumber Daya Mineral (ESDM) sebagai unsur yang merupakan kebutuhan utama pada suatu Negara membutuhkan kajian untuk memprediksi ketersediaannnya. Prediksi ini dilakukan menggunakan model autoregressive yang diimplementasikan pada data time series dan dioptimasi menggunakan Algoritma Genetika. Berdasarkan hasil observasi yang dilakukan untuk pencarian parameter algoritma genetika, diperoleh parameter terbaik yaitu ukuran populasi pada nilai 100 dan 200 sedangkan probabilitas pindah silang bernilai 0.8 dan probabilitas mutasi nilainya 0.1 dengan akurasi MAPE yang diperoleh di bawah 25%. Prediksi yang menghasilkan MAPE terbaik adalah prediksi yang menggunakan data latih sebesar 85% dan data uji sebesar 15%. Hasil akhir dari prediksi adalah adalah ketersediaan gas alam dan batubara termasuk ke dalam kategori tidak krisis, sedangkan ketersediaan minyak bumi mengalami krisis.Kata kunci: Prediksi, Algoritma Genetika, Energi, autoregressive, time series. ]]>
<![CDATA[MODEL INTERAKSI MANGSA PEMANGSA DENGAN FUNGSI RESPON RASIO DEPENDENT HOLLING TIPE II DAN PERILAKU ANTI PEMANGSA ]]>
<![CDATA[SITI SAADAH]]>;
<![CDATA[ABADI]]>
<![CDATA[ MATHunesa: Jurnal Ilmiah Matematika Vol 7 No 2 (2019) ]]>
Publisher : <![CDATA[Universitas Negeri Surabaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (679.454 KB)
<![CDATA[Interaksi antara mangsa pemangsa dalam bidang ekologi merupakan suatu topik menarik untuk dibahas. Namun untuk mengetahuinya tidak mudah, sehingga dibutuhkan model matematika untuk dapat memprediksi perilakunya. Interaksi mangsa pemangsa dengan fungsi respon rasio dependent Holling tipe II mengkaji bahwa populasi pemangsa tidak hanya bergantung pada keberadaan populasi mangsa, namun juga keberadaan populasi pemangsa itu sendiri. Artikel ini khusus membahas kontruksi model interaksi mangsa pemangsa menggunakan fungsi respon rasio dependent Holling tipe II dengan adanya perilaku anti pemangsa. Kata kunci: mangsa pemangsa, rasio dependent, anti pemangsa.]]>
<![CDATA[IMPLEMENTASI PEMODELAN SELF ASSESMENT DALAM PENILAIAN KINERJA KARYAWAN ]]>
<![CDATA[Siti Saadah]]>;
<![CDATA[Vip Paramarta]]>;
<![CDATA[Didin Saepudin]]>
<![CDATA[ TECHNO-SOCIO EKONOMIKA Vol 14, No 2 (2021): Jurnal Techno-Socio Ekonomika - Oktober ]]>
Publisher : <![CDATA[LPPM Universitas Sangga Buana ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.32897/techno.2021.14.2.604
<![CDATA[Universitas Sangga Buana telah memberlakukan penilaian kinerja karyawan dengan membagikan kertas kuesioner yang disebar dan diisi oleh atasan langsung, atasan khusus dan rekan sejawat. Pada prosesnya, kegiatan penyebaran kuesioner banyak menggunakan kertas serta memungkinkan akan terjadinya human error, pada pengumpulan lembar kuesioner yang telah diisi, terkadang tercecer atau hilang dan tidak terarsipkan dengan baik oleh petugas. Selanjutnya tahap penghitungan kueioner juga sangat memungkinkan terjadi kesalahan input data dan perhitungan. Kesalahan tersebut dapat mempengaruhi penilaian karyawan, sehingga diperlukan sebuah model penilaian karyawan berupa sistem informasi yang terintegrasi. Penelitian ini bertujuan untuk mengetahui dan menganalisis Model Penilaian Kinerja Karyawan Berbasis Daily Activities Report Sebagai Implementasi Self assesment pada Karyawan Universitas Sangga Buana YPKP Bandung dengan menggunakan pendekatan kualitatif dan jenis penelitian deskriptif. Hasilnya adalah model Penilaian Kinerja Karyawan Berbasis Daily Activities Report Sebagai Implementasi Self assesment pada Karyawan Universitas Sangga Buana YPKP Bandung bisa digunakan dan diimplementasikan sesuai dengan hasil wawancara dari beberapa informan dan hasil pengujian sistem dengan tim IT. Kata Kunci: Evaluasi Kinerja, Self assesment, Daily Activity Report. ]]>
<![CDATA[Implementation of Verification and Matching E-KTP with Faster R-CNN and ORB ]]>
<![CDATA[Muhammad Muttabi Hudaya]]>;
<![CDATA[Siti Saadah]]>;
<![CDATA[Hendy Irawan]]>
<![CDATA[ Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 5 No 4 (2021): Agustus 2021 ]]>
Publisher : <![CDATA[Ikatan Ahli Informatika Indonesia (IAII) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (936.392 KB)
|
DOI: 10.29207/resti.v5i4.3175
<![CDATA[needs a solid validation that has verification and matching uploaded images. To solve this problem, this paper implementing a detection model using Faster R-CNN and a matching method using ORB (Oriented FAST and Rotated BRIEF) and KNN-BFM (K-Nearest Neighbor Brute Force Matcher). The goal of the implementations is to reach both an 80% mark of accuracy and prove matching using ORB only can be a replaced OCR technique. The implementation accuracy results in the detection model reach mAP (Mean Average Precision) of 94%. But, the matching process only achieves an accuracy of 43,46%. The matching process using only image feature matching underperforms the previous OCR technique but improves processing time from 4510ms to 60m). Image matching accuracy has proven to increase by using a high-quality dan high quantity dataset, extracting features on the important area of EKTP card images.]]>
<![CDATA[ANALISIS PERGERAKAN RUPIAH DI PASAR UANG TERHADAP KINERJA KEUANGAN (RETURN ON ASSET DAN RETURN ON EQUITY) PT INDOFOOD SUKSES MAKMUR, TBK (TRIWULANAN) DARI TAHUN 2010-2016 ]]>
<![CDATA[Mario Adventino Hamboerh]]>;
<![CDATA[Siti Saadah]]>
<![CDATA[ Prosiding Working Papers Series In Management Vol 9 (2017) ]]>
Publisher : <![CDATA[Prosiding Working Papers Series In Management ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (559.989 KB)
<![CDATA[Multinational Companies always make sell and purchase transactions using foreign currency that has been agreed before. Stability foreign currency in transaction is what company expectations. Financial performance is one things can be affected because of the change in value of foreign currency. Return on Asset is a ratio looking at the company profit with total asset owned by the company. Return on Equity is a ratio looking the company profit with total equity / company’s capital in operational activities.One of the multinational company and located in Indonesia is PT Indofood Sukses Makmur, Tbk. This research aims to analyze the impact of exchange rate changes on financial performance of PT Indofood Sukses Makmur, Tbk. The method in this research with Error Correction Model (ECM) and uses time series data in E-views 9.0 software. Data obtained from www.bi.go.id, www.indofood.com, www.sahamok.com The result of this research with significant level ( = 5%), show that there is no significant on the exchange rate variable to Return on Asset (ROA) and Return on Equity (ROE) in 2010-2016. Finally, ROA and ROE PT Indofood Sukses Makmur, Tbk is not influenced by exchange rate movements.Keywords: Foreign Currency, Return on Asset, Return on Equity]]>
<![CDATA[Prediksi Harga Bitcoin Menggunakan Metode Random Forest : (Studi Kasus: Data Acak Pada Masa Pandemic Covid-19) ]]>
<![CDATA[Siti Saadah]]>;
<![CDATA[Haifa Salsabila]]>
<![CDATA[ Jurnal Komputer Terapan Vol. 7 No. 1 (2021): Jurnal Komputer Terapan ]]>
Publisher : <![CDATA[Politeknik Caltex Riau ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (439.575 KB)
|
DOI: 10.35143/jkt.v7i1.4618
<![CDATA[During this pandemic, virtual financial transactions increased sharply. Because the storage of assets and forms of buying and selling transformed using digital services. Bitcoin as one of the cryptocurrencies that is currently widely used and in demand by the people of the world, but there is no specialized financial institution responsible for bitcoin buying and selling transactions, requires a bitcoin price prediction system to know the status of the value of bitcoin. Referring to the ever-fluctuating characteristics of bitcoin data, the Random Forest Regression method is used to predict the price of bitcoin. This algorithm is one of the modeling that can produce good performance in terms of prediction. Using Random Forest Regression modeling, MAPE value was obtained by 1.50% with accuracy of 98.50%. That value is the value that produces the best performance among all bitcoin prediction attempts.]]>
