Claim Missing Document
Check
Articles

PERAMALAN POTENSI KEBAKARAN HUTAN DENGAN METODE DATA MINING Ermatita, Ermatita; Sukemi, Sukemi; Pratomo, Yudha
SEINASI-KESI Vol 1, No 1 (2018): Seinasi-Kesi 2018
Publisher : Fakultas Ilmu Komputer UPN Veteran Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (173.163 KB)

Abstract

Kebakaran hutan merupakan kejadian yang selalu berualang setiap tahun, terutama di Sumatera Selatan. Penanggulangan kebakaran hutan ini, terutama di lahan gambut, perlu dianalisis agar dapat diprediksi pola penyebaran kebakaran lahan gambut. Hal ini perlu dilakukan karena pemadaman kebakaran lahan gambut sulit dilakukan.Penelitian ini memproses data faktor-faktor yang memberikan potensi kebakaran hutan menerapkan data mining. Metode yang digunakan dalam penelitian ini . Hasil dari penelitian ini menunjukkan bahwa faktor-faktor penyebab dari kebakaran hutan yang diproses mempunyai potensi yang sama dalam menyebabkan kebakaran hutan.
Penerapan Knowledge Management System Berbasis Web Menggunakan Model Inukshuk dan Algoritma Levenshtein Octaria, Orissa; Ermatita, Ermatita; Sukemi, Sukemi
CSRID (Computer Science Research and Its Development Journal) Vol 11, No 2 (2019): CSRID JUNI 2019
Publisher : Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (264.369 KB) | DOI: 10.22303/csrid.11.2.2019.63-73

Abstract

Manajemen pengetahuan atau knowledge management (KM) merupakan hal yang penting untuk  menyimpan atau mengatur pengetahuan yang sejatinya sudah ada. Sulitnya mendapatkan pengetahuan yang sebenarnya sudah lama diketahui menjadi kendala tersendiri bagi penerus baru untuk melanjutkan suatu jabatan tertentu, dalam hal ini wadah yang diteliti adalah bebrapa perguruan tinggi swata kota Palembang. Dosen baru dapat mengetahui bagaimana sistem pengajaran dalam perguruan tinggi tersebut, dan banyak pengetahuan lain yang harus dipahami oleh dosen baru tersebut. Oleh karena itu maka akan di bangun KMS menggunakan Model Inukshuk untuk menjadi sarana untuk mengatur pengetahuan yang yang sudah ada, adapun algoritma pencarian yang digunakan adalah Algoritma Levenshtein. Hasil yang ada nantinya berupa KMS yang penting bagi perguruan tinggi swasta tersebut untuk meyimpan serta mengelola sebuah pengetahuan. KMS yang dibangun akan berbasis web guna memudahkan pengguna yang sekarang ini sudah banyak menggunakan jaringan internet.
Segmentation atrioventricular septal defect by using convolutional neural networks based on U-NET architecture Ade Iriani Sapitri; Siti Nurmaini; Sukemi Sukemi; M. Naufal Rachmatullah; Annisa Darmawahyuni
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 10, No 3: September 2021
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v10.i3.pp553-562

Abstract

Congenital heart disease often occurs, especially in infants and fetuses. Fetal image is one of the issues that can be related to the segmentation process. The fetal heart is an important indicator in the process of structural segmentation and functional assessment of congenital heart disease. This study is very challenging due to the fetal heart has a relatively unclear structural anatomical appearance, especially in the artifacts in ultrasound images. There are several types of congenital heart disease that often occurs namely in septal defects it consists of the atrial septal defect, ventricular septal defect, and atrioventricular septal defect. The process of identifying the standard of the heart, especially the fetus, can be identified with a 2D ultrasound video in the initial steps to diagnose congenital heart disease. The process of diagnosis of fetal heart standards can be seen from a variety of spaces, i.e., 4 chamber views. In this study, the standard semantic segmentation process of the fetal heart is abnormal and normal in terms of the perspective of 4 chamber views. The validation evaluation results obtained in this study amounted to 99.79% pixel accuracy, mean iou 96.10%, mean accuracy 97.82%, precision 96.41% recall 95.72% and F1 score 96.02%.
Pattern of E-marketplace Customer Shopping Behavior using Tabu Search and FP-Growth Algorithm Ayu Meida; Dian Palupi Rini; Sukemi Sukemi
Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Vol 7, No 4: December 2019
Publisher : IAES Indonesian Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52549/ijeei.v7i4.1362

Abstract

Pattern of customer shopping behavior can be known by analyzing market cart. This analysis is performed using Association Rule Mining (ARM) method in order to improve cross-sale. The weakness of ARM is if processed data is big data, it takes more time to process the data. To optimize the ARM, we perform merging algorithm with Improved Tabu Search (TS). The application of Improved TS algorithm as optimization algorithm for preprocessing datasets, data filtering, and sorting data closely related products on sales data can optimize the ARM processing. The method of Association Rule Mining (FP-Growth) to determine frequent K-itemset, Support value and Confidence value of data which is already sorted on TS is based on patterns which often appear in the dataset so it generates rules as reference of decision making for company. To measure the level of power of rule which has been formed, the Lift Ratio value was calculated. Based on the calculation of 97 rules produced, the lift ratio produces values > 1 of 82.54% and based on processing time, it produces the fastest data search in 1.66 seconds. When compared with previous research that uses the hybrid method, for data retrieval based on processing time, it produces the fastest data search within 12.3406 seconds, 150 seconds and 50 seconds. Previous studies have only compared the processing time of data searching without regard to validation / accuracy of data search. The test results in this study obtained more optimal results than when compared with the results of previous studies, namely in time efficiency and data mining in real time and more accurate data validation.  As a conclusion, the resulting rule can be used as a reference in understanding shopping behavior patterns customer on the E-Marketplace.
STUDI KETINGGIAN KOLAM RETENSI SIMPANG POLDA PALEMBANG UNTUK LANGKAH PENENTUAN KEBIJAKAN Sukemi -; Marlina Sylvia; samsuryadi samsuryadi; Hadipurnama Satria; Apriansyah Putra
Jurnal Informatika dan Rekayasa Elektronik Vol. 4 No. 1 (2021): JIRE April 2021
Publisher : LPPM STMIK Lombok

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36595/jire.v4i1.332

Abstract

Simpang Polda retention pond is an alternative flood control construction which is designed to temporarily hold exceeding water flow during rainfall in the vicinity of Simpang Polda, in order to avoid or reduce flood in the area. Retention ponds are prone to sedimentation due to garbage and other materials settling down in the bottom of the pond, which in turn causing reduction of total volume of water it can contain. To ensure that the pond has enough volume, depth measurements were done so that the pond can function as intended. Boat robots from previous research in 2019 and 2020 were utilized as the method to measure the depth of the retention pond. The boat robots mapped the depth of the whole pond area with the help of remote control and single beam sensor. Measurement result shows that the Simpang Polda retention pond has an average depth of 2.245 m. Based on this finding it is suggested that the local government water resource management agency (Dinas PUPR Dept. PSDA) to follow up with the appropriate sediment removal procedures to return the pond’s depth back to the original value when it was constructed
Electrospun nylon-6 nanofibers and their characteristics Ida Sriyanti; Meily P Agustini; Jaidan Jauhari; Sukemi Sukemi; Zainuddin Nawawi
Jurnal Ilmiah Pendidikan Fisika Al-Biruni Vol 9, No 1 (2020): Jurnal Ilmiah Pendidikan Fisika Al-Biruni
Publisher : Universitas Islam Negeri Raden Intan Lampung, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (645.62 KB) | DOI: 10.24042/jipfalbiruni.v9i1.5747

Abstract

The purposes of this research were to investigate the synthesized Nylon-6 nanofibers using electrospinning technique and their characteristics. The method used in this study was an experimental method with a quantitative approach. Nylon-6 nanofibers have been produced using the electrospinning method. This fiber was made with different concentrations, i.e. 20% w/w (FN1), 25% w/w (FN2), and 30% w/w (FN3). The SEM results show that the morphology of all nylon-6 nanofibers) forms perfect fibers without bead fiber. Increasing fiber concentration from 20% w/w to 30% w/w results in bigger morphology and fiber diameter. The dimensions of the FN1, FN2, and FN3 fibers are 1890 nm, 2350 nm, and 2420 nm, respectively. The results of FTIR analysis showed that the increase in the concentration of nylon-6 (b) and the electrospinning process caused a peak shift in the amide II group (CH2 bond), the carbonyl group and the CH2 stretching of the amide III group from small wave numbers to larger ones. The results of XRD characterization showed that the electrospinning process affected the changes in the XRD pattern of nylon-6 nanofiber (FN1, FN2, and FN3) in the state of semi crystal. Nylon-6 nanofibers can be used for applications in medicine, air filters, and electrode for capacitors
Priority based computation: "An Initial study result of paradigm shift on real time computation" Sukemi Sukemi; Riyanto Riyanto
Computer Engineering and Applications Journal Vol 6 No 1 (2017)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (762.871 KB) | DOI: 10.18495/comengapp.v6i1.198

Abstract

This research is purposed to increase computer function into a time driven to support real time system. This purposed would the processor can work according to determined time variable and can work optimally in a certained deadline. The first approachment to design some of processor that has a different bit space 64, 32, 16 and 8 bits. Each processor will be separated by selector/arbiter priority of a task. In addition, the design of the above processors are designed as a counter with varying levels of accuracy (variable precision computing). The selection is also done by using statistical control in the task are observed by the appearance of controller mounted on the front of the architecture bit space the second approach above. The last approach to ‘add’ certainty in the form of interval arithmetic precision cutting task that can be the upper bound and lower bound of the area (bounds). These four approachment can be structured orthogonally into a processor/several processors by introducing a new classifier that serves as a selector or a task arbiter. The results of the four approaches to prove that the processor is prepared by incorporating a variable bitspace adder selectors can provide optimality of 0.43%.
The Combination of Naive Bayes and Particle Swarm Optimization Methods of Student’s Graduation Prediction Evi Purnamasari; Dian Palupi Rini; Sukemi Sukemi
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol 5, No 2 (2019): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (625.875 KB) | DOI: 10.26555/jiteki.v5i2.15272

Abstract

This research conducted classification testing on the study case of student graduation prediction in a university. It aims to assist the university in maintaining academic development and in finding solutions for improving timely graduation. This study combined two methods, i.e., Naive Bayes and Particle Swarm Optimization, to produce a better level of accuracy. The Naive Bayes method is a statistical classification method used to predict a student's graduation in this study. That will be further enhanced using the Particle Swarm Optimization method to produce a better level of accuracy. There are 10 (ten) samples in this study randomly selected from the alumni data of UIGM students in 2011-2014. From the test results, this research resulted in an accuracy value of 90% from the Naive Bayes algorithm testing, after testing the Naive Bayes with Particle Swarm Optimization, which produced an accuracy value of 100%. The conclusion obtained from the results is the Naive Bayes method has a higher accuracy value if combined with Particle Swarm Optimization. Thus the university can more easily predict whether or not the students graduate on time for the upcoming graduation period. The results of this test prove that to predict student graduation using the Naive Bayes method with Particle Swarm Optimization is appropriate.
PENINGKATAN KECEPATAN PENDETEKSIAN CITRA GERAKAN MATA MENGGUNAKAN ALGORITMA GAUSSIAN FILTER Joko Purnomo; Sukemi Sukemi
Annual Research Seminar (ARS) Vol 5, No 1 (2019): ARS 2019
Publisher : Annual Research Seminar (ARS)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Gerakan mata yang cepat dan berubah-ubah, dapat diukur dengan menganalisa gerakan bola mata tersebut. Pengolahan hasil dari citra gerakan mata tersebut dapat dilaksanakan dengan cepat dan tingkat keakuratan tinggi dengan menggunakan proses komputasi. Melalui tahapan pengambilan gambar gerakan mata tersebut dilanjutkan dengan proses penyeleksian gambar sehingga gambar dapat atau siap di analisa. Proses penyeleksian dan analisa dilaksanakan dengan menggunakan proses komputasi cepat sehingga dihasilkan data yang yang yang akurat. Tahapan awal dari penelitian ini adalah pengolahan citra mata dengan menggunakan filterisasimatrix citra 5x5,7x7 dan 9x9 dengan proses gaussian filter untuk mendapatkan data citra yang akurat dan dengan proses komputasi yang lebih cepat.
Klasifikasi Tingkat Kematangan Buah Tomat Berdasarkan Fitur Warna Menggunakan K-Nearest Neighhbor Shinta Aprilisa; Sukemi Sukemi
Annual Research Seminar (ARS) Vol 5, No 1 (2019): ARS 2019
Publisher : Annual Research Seminar (ARS)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Pada proses klasifikasi buah tomat dengan cara manual yaitu dengan menggunakan mata manusia merupakan hal yang sangat sulit dilakukan. Hal ini dibuktikan dengan tidak konsisten serta bersifat subyektif sehingga menyebabkan tingkat akurasi yang rendah. Oleh karena itu, untuk meningkatkan tingkat akurasi serta mengurangi sifat subyektifitas mata manusia, maka penelitian ini mengusulkan sebuah algoritma yang dapat digunakan untukk mengklasifikasi tingkat kematangan buah tomat yaitu dengan K-Nearest Neighbor berdasarkan kepada warna kulit yang ada pada buah tersebut. Nilai k yang digunakan pada penenlitian ini yaitu 1, 3, 5, 7, dan 9 untuk menguji coba pencarian jarak Euclidean distance pada citra dengan ukuran 512x512 piksel. Penelitian yang dilakukan membuktikan bahwa dengan jarak Euclidean k=3 memiliki nilai prosentase 92%. Berdasarkan tingkat akurasi yang dimiliki, fitur warna k=3 menunjukkan nilai k terbaik pada klasifikasi tingkat kematangan buah tomat.