Claim Missing Document
Check
Articles

Found 40 Documents
Search

Implementation of Backpropagation Artificial Neural Networks to Predict Palm Oil Price Fresh Fruit Bunches Edi Ismanto; Noverta Effendi; Eka Pandu Cynthia
IJISTECH (International Journal of Information System and Technology) Vol 2, No 1 (2018): November
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/ijistech.v2i1.17

Abstract

Riau Province is one of the regions known for its plantation products, especially in the oil palm sector, so that Riau Province and regional districts focus on oil palm plants as the main commodity of plantations in Riau. Based on data from the Central Bureau of Statistics (BPS) of Riau Province, the annual production of oil palm plantations, especially smallholder plantations in Riau province has always increased. So is the demand for world CPO. But sometimes the selling price of oil palm fresh fruit bunches (FFB) for smallholder plantations always changes due to many influential factors. With the Artificial Neural Network approach, the Backpropagation algorithm we conduct training and testing of the time series variables that affect the data, namely data on the area of oil palm plantations in Riau Province; Total palm oil production in Riau Province; Palm Oil Productivity in Riau Province; Palm Oil Exports in Riau Province and Average World CPO Prices. Then price predictions will be made in the future. Based on the results of the training and testing, the best Artificial Neural Network (ANN) architecture model was obtained with 9 input layers, 5 hidden layers and 1 output layer. The output of RMSE 0000699 error value and accuracy percentage is 99.97% so that it can make price predictions according to the given target value.
Pengelompokan Diabetic Macular Edema Berbasis Citra Retina Mata Menggunakan Fuzzy Learning Vector Quantization (FLVQ) Sarbaini Sarbaini; Eka Pandu Cynthia; M Imam Arifandy
SITEKIN: Jurnal Sains, Teknologi dan Industri Vol 19, No 1 (2021): Desember 2021
Publisher : Fakultas Sains dan Teknologi Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/sitekin.v19i1.14907

Abstract

Diabetic Macula Edema (DME) merupakan komplikasi serius dari penyakit diabetes. DME diawali dengan terjadinya retinopati diabetik, yaitu gangguan pada retina mata. Stadium lanjut dari retinopati diabetic meruapakan jenis penyakit mata manusia yang disebut dengan Macula edema. Dimana pada kasus Macula Edema yang sebelumnya masih menggunakan kamera fendus, maka masih mempunyai kesulitan pada pengenalan keparahan penyakit Macula Edema. Didalam penelitian ini dilakukan pengklasifikasin keparah penyakit Macula Edema menggunakan metode ektrsaksi ciri Hue Saturation value dan Gray Level CoOccurrence dan metode Fuzzy Learning Vector Quantization (FLVQ) untuk pengklasifikasi. Dari 400 gambar citra retina mata akan dibagi sesuai rasio pengujian yaitu dengan rasio ,  dan . Yang akan terjadi akhir berasal perangkat lunak yg dibangun dari penelitian ini artinya berupa sosialisasi taraf keparahan penyakit Macula Edema yang diproses apakah berhasil dikenali atau tidak. Berdasarkan pengujian akurasi memakai metode confusion matrix, maka didapatkan akibat akurasi tertinggi yaitu 100%. Oleh karna itu, dapat disimpulkan bahwa metode ekstraksi ciri pada kasus mampu mengenali ciri dari penyakit Macula Edema berdasarkan Hard Exudate
Potensi Limbah Padat Kelapa Sawit Sebagai Sumber Energi Terbarukan Dalam Implementasi Indonesian Sustainability Palm Oil M Imam Arifandy; Eka Pandu Cynthia; Sarbaini sarbaini; Fitriani Muttakin; Nazaruddin Nazaruddin
SITEKIN: Jurnal Sains, Teknologi dan Industri Vol 19, No 1 (2021): Desember 2021
Publisher : Fakultas Sains dan Teknologi Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/sitekin.v19i1.14915

Abstract

In 2019 Indonesia became the largest producer of Crude Palm Oil / CPO in the world, with a total area of oil palm plantations reaching 14,456,611 hectares with Crude Palm Oil / CPO production reaching 47,120,247 tons. The CPO production process produces various kinds of waste, one of which is solid waste. If the waste is not managed properly, it will cause environmental problems. This study aims to calculate the potential for managing waste generated from palm oil mills, namely solid waste as a renewable energy source and the potential effect of palm oil solid waste on increasing the value of Net Energy Balance (NEB) and the value of Net Energy Ratio (NER). This study uses a quantitative approach by performing calculations using the Life Cycle Assessment (LCA) method which is used to calculate the balance of the solid waste produced by the palm oil mill, which is then converted into energy factor values from accountable literature sources. The calculation results show that for each processing of 1 ton of fresh fruit bunches (FFB) of oil palm, it produces 130 kg of fiber waste and 65 kg of kernel shell waste. The results show that if solid waste is applied as an alternative fuel to the boiler, it will be able to produce 13,182 MJ of energy. This renewable energy source can increase the value of NEB from 27,199 MJ to 40,378.01 MJ (48.45%) and increase NER from 3.19 to 4.01 or an increase of 25.7%.
PENINGKATAN JARINGAN JALAN DALAM KAWASAN KAMPUS DENGAN MENGGUNAKAN METODA SIMULASI ANTRIAN Syaifullah Syaifullah; Hasdi Radiles; M. Afdal M. Afdal; Eka Pandu Cynthia
Jurnal Ilmiah Rekayasa dan Manajemen Sistem Informasi Vol 5, No 1 (2019): Februari
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/rmsi.v5i1.7375

Abstract

Permasalahan kemacetan telah mulai mengganggu aktivitas civitas akademika di lingkungan UIN Suska Riau. Kajian yang komprehensif diperlukan untuk menjawab tantangan bagaimanakah meningkatkan kualitas jaringan jalan tersebut. Dengan menggunakan data survei, teori antrian kemudian digunakan untuk membangun model simulasi dalam memprediksi kondisi terkini dari kemacetan. Analisis dilakukan dengan menggunakan beberapa skenario untuk menguji usaha-usaha yang dapat dilakukan. Hasil simulasi menunjukkan bahwa usaha pelebaran jalan musti dilakukan, mengingat tingkat pertumbuhan populasi telah membuat trafik menjadi jenuh. Kejenuhan trafik ini terlihat dari waktu antrian dalam sistem telah melewati durasi rata-rata 5 menit. Selain itu, peningkatkan kualitas pengerasan jalan juga harus diperhatikan untuk mendapatkan kecepatan arus bebas 30 km/jam.
Random Forest Algorithm to Investigate the Case of Acute Coronary Syndrome Eka Pandu Cynthia; M. Afif Rizky A.; Alwis Nazir; Fadhilah Syafria
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 5 No 2 (2021): April 2021
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (677.337 KB) | DOI: 10.29207/resti.v5i2.3000

Abstract

This paper explains the use of the Random Forest Algorithm to investigate the Case of Acute Coronary Syndrome (ACS). The objectives of this study are to review the evaluation of the use of data science techniques and machine learning algorithms in creating a model that can classify whether or not cases of acute coronary syndrome occur. The research method used in this study refers to the IBM Foundational Methodology for Data Science, include: i) inventorying dataset about ACS, ii) preprocessing for the data into four sub-processes, i.e. requirements, collection, understanding, and preparation, iii) determination of RFA, i.e. the "n" of the tree which will form a forest and forming trees from the random forest that has been created, and iv) determination of the model evaluation and result in analysis based on Python programming language. Based on the experiments that the learning have been conducted using a random forest machine-learning algorithm with an n-estimator value of 100 and each tree's depth (max depth) with a value of 4, learning scenarios of 70:30, 80:20, and 90:10 on 444 cases of acute coronary syndrome data. The results show that the 70:30 scenario model has the best results, with an accuracy value of 83.45%, a precision value of 85%, and a recall value of 92.4%. Conclusions obtained from the experiment results were evaluated with various statistical metrics (accuracy, precision, and recall) in each learning scenario on 444 cases of acute coronary syndrome data with a cross-validation value of 10 fold.
Metode Fuzzy Time Series Cheng dalam Memprediksi Jumlah Wisatawan di Provinsi Sumatera Barat Eka Pandu Cynthia; Rahma wati
Jurnal Pendidikan Teknologi Informatika dan Sains Vol 1 No 1 (2019): Journal of Education Informatic Technology and Science (JeITS)
Publisher : Faculty of Teacher Training and Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (449.793 KB)

Abstract

West Sumatra Province is one of the provinces in Indonesia that is very rich in its natural beauty, making this area one of the popular tourist destinations for local and foreign tourists. The large number of tourists who come has a very good impact on the Province of West Sumatra, especially for the economic sector. Increased regional income and growing economic activity of the community is very much influenced by the presence of these tourists. In this study, the author uses one method to make predictions or forecasting, namely the Cheng Fuzzy Time Series method. The actual data used is the number of tourists from 2015 to 2017, and the process of predicting the number of tourists will be carried out for 2019 until 2021. From the results of calculations that have been done using this method, good performance conclusions are generated, in the range of MAPE 10% - 20%, which is an error value of 14.61%. With an absolute error value of 5.26 and the value of predictive accuracy is 85.39%.
Rancang Bangun e-Recruitment untuk Sekolah Kejuruan dengan Model Knowledge Centered Services (KCS) Edi Ismanto; Eka Pandu Cynthia
Jurnal Pendidikan Teknologi Informatika dan Sains Vol 1 No 1 (2019): Journal of Education Informatic Technology and Science (JeITS)
Publisher : Faculty of Teacher Training and Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (676.63 KB)

Abstract

Abstrak Sekolah menegah kejuruan (SMK) merupakan sekolah yang menyiapkan peserta didiknya agar trampil dan siap untuk bekerja,salah satu indikator keberhasilan dari sekolah kejuruan bahwa peserta didiknya harus banyak diserap atau dipakai dalam dunia industry ataupun perusahaan, untuk mencapai tujuan tersebut sekolah kejuruan harus membangun relasi dengan dunia industry ataupun perusahaan agar memudahkan lulusan dari peserta didiknya dalam mencari pekerjaan sesuai kompetensinya.Dengan pengembangan model e-recruitment ini merupakan salah satu upaya untuk mempermudah hubungan antara sekolah,perusahaan, dan lulusan peserta didiknya, dalam mendapatkan dan menyampaikan informasi lowongan pekerjaan yang dibutuhkan.Model e-recruitment ini dikembangkan dengan pendekatan Knowledge Centered Services (KCS) yang menekankan pengetahuan sebagai asset terpenting dengan sistemdua loop kontinyu, Loop Solve dan Loop Evolve sehingga meningkatkan sistem kerja dari pelayanan e-recruitment. Kata kunci:e-recruitment,knowledge centered services (KCS), Abstract Vocational high school (SMK) is a school that prepares students to be skilled and ready to work, one indicator of the success of vocational schools is that students must be absorbed or used in the world of industry or companies, to achieve this goal vocational schools must build relationships with the world of industry or companies to make it easier for graduates of their students to find work according to their competencies. By developing this e-recruitment model, it is one effort to facilitate the relationship between schools, companies, and graduates of students, in obtaining and delivering the required job information. This e-recruitment model was developed with the Knowledge Centered Services (KCS) approach which emphasizes knowledge as the most important asset with a continuous two-loop system, Loop Solve and Loop Evolve so as to improve the work system of e-recruitment services. Keywords:e-recruitment, knowledge centered services (KCS),
Penerapan Metode Elman Recurrent Neural Network (ERNN) Untuk Peramalan Penjualan Eka Pandu Cynthia; Novi Yanti; Yusra Yusra; Yelvi Fitriani; Muhammad Yusuf
Jurnal Pendidikan Teknologi Informatika dan Sains Vol 1 No 2 (2019): Journal of Education Informatic Technology and Science (JeITS)
Publisher : Faculty of Teacher Training and Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (847.155 KB)

Abstract

Penjualan adalah suatu aktivitas atau bisnis menjual suatu produk atau jasa. Pada penelitian ini, mengambil studi kasus pada sebuah perusahaan penjualan tempe (PT. HB) di Kota Pekanbaru yang menggunakan metode penjualan melalui agen atau sales. Permasalahan penjualan pada perusahaan ini adalah sering terjadinya returned product karena tidak laku, yang dapat menyebabkan kerugian yang cukup besar. Menggunakan Algoritma Elman Recurrent Neural Network (ERNN), penelitian ini melakukan prediksi penjualan tempe pada PT. HB. Data yang digunakan adalah data penjualan tempe harian periode Juli 2016 hingga September 2018 dengan parameter Jumlah Produksi, Harga, Jumlah Agen dan Jumlah Penjualan. Hasil yang diperoleh melalui percobaan beberapa skenario pelatihan dan pengujian implementasi algoritma pada kasus ini adalah akurasi tertinggi bernilai 96,92% pada arsitektur jaringan 3 input neuron layer, 3 neuron hidden layer, 1 output, pembagian data latih dan uji 70 : 30, nilai learning rate 0,9 dan maksimum epoch 900.
Algoritma Genetika untuk Menentukan Objek Wisata Berbasis Geographic Information System (GIS) Edi Ismanto; Rahmad Al Rian; Eka Pandu Cynthia
Jurnal Pendidikan Teknologi Informatika dan Sains Vol 1 No 2 (2019): Journal of Education Informatic Technology and Science (JeITS)
Publisher : Faculty of Teacher Training and Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1616.981 KB)

Abstract

Pariwisata merupakan salah satu sektor pembangunan yang mendapat perhatian pengembangan prioritas dari pemerintah. Sektor ini dinilai cukup berpotensi bagi pengembangan perekonomian rakyat serta mampu menghasilkan devisa bagi negara dari komoditi nonmigas. Kota Pekanbaru merupakan Ibukota Provinsi Riau yang keberadaanya sangat strategis, menjadi titik transit mancanegara karena berbatasan langsung dengan negara Malaysia dan Singapura. Kota Pekanbaru memiliki daya tarik sebagai daerah tujuan wisata belanja dan wisata kebudayaan melayu yang cukup terkenal bagi wisatawan lokal dan macanegara. Ketika melakukan kunjungan wisata, seorang wisatawan biasanya dihadapkan pada keterbatasan waktu dan banyaknya pilihan lokasi wisata yang akan dikunjungi. Sehingga wisatawan juga diharapkan mampu memperhitungkan jarak tempuh menuju setiap lokasi wisata tersebut. Memperhatikan hal tersebut, maka dirasakan perlu untuk melakukan pengembangan sebuah sistem informasi yang dapat membantu wisatawan dapat mengunjungi lokasi tujuan wisatanya dengan efektif. Penelitian ini menggunakan algoritma genetika yang menggabungkan secara acak berbagai pilihan solusi terbaik di dalam suatu populasi untuk mendapatkan generasi solusi terbaik, yaitu pada suatu kondisi dengan nilai fitness yang paling tinggi. Setiap generasi akan merepresentasikan perbaikan-perbaikan pada populasi awalnya. Proses tersebut dilakukan secara berulang sehingga dapat mensimulasikan proses evolusi yang semakin baik. Berdasarkan hasil pengujian dengan menggunakan 5 tempat objek wisata di Kota Pekanbaru, sebagai variabel kromosom (R01, R02, R03, R04 dan R05) dan 5 generasi yang dibangkitkan, menghasilkan nilai fitness terbaik sebesar 19.8 pada generasi ke 5.
Penerapan Fuzzy Inference System Mamdani Untuk Menentukan Jumlah Pembelian Obat (Studi Kasus: Garuda Sentra Medika) Rahmawati Rahmawati; Eka Pandu Cynthia; Intan Eria Elfi
ALGORITMA : JURNAL ILMU KOMPUTER DAN INFORMATIKA Vol 3, No 1 (2019): April 2019
Publisher : UIN Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (269.573 KB) | DOI: 10.30829/algoritma.v3i1.4437

Abstract

The availability of the right raw materials is closely related to the number of products to be produced. Therefore the prediction of production must be adjusted so that the stock order of raw materials can be calculated correctly. Inventory problems are problems that are always faced by decision makers in the field of inventory. Supplies are needed because basically the demand pattern is irregular. Inventories are carried out to ensure that there is certainty that when needed these products are available. The problem in inventory is the difficulty in determining the amount of inventory that must be provided in meeting the number of requests to consumers. The purpose of this study was to determine the amount of drug purchases at Garuda Sentra Medika with the Mamdani method fuzzy inference system based on inventory data and sales data. This study uses three variables, namely inventory, sales and purchases by having two inputs, namely inventory and sales and one output, namely purchase. The results of the application of the fuzzy inference system Mamdani method can help the company to determine the amount of drug purchases with a success rate of 99.35869%.Keywords: Drug Sales, Fuzzy Inference System, Inventory, Purchasing.