Claim Missing Document
Check
Articles

Found 31 Documents
Search

Peramalan Penjualan Mobil Menggunakan Jaringan Syaraf Tiruan dan Certainty Factor Fachrudin Pakaja; Agus Naba; Purwanto Purwanto
Jurnal EECCIS Vol 6, No 1 (2012)
Publisher : Fakultas Teknik, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (417.923 KB)

Abstract

Prediksi penjualan adalah salah satu cara untuk meningkatkan laba perusahaan, peramalan diperlukan untuk menyetarakan antara perbedaan waktu yang sekarang dan yang akan datang terhadap kebutuhan, Jaringan Syaraf Tiruan (JST) dapat mengaplikasikan dengan baik metode peramalan.Pendekatan peramalan kuantitatif dengan metode times series akan menentukan nilai data masukan dari sekumpulan data serial atau berkala dari transaksi pada suatu jangka waktu tertentu. Data dibagi menjadi data pelatihan, pengujian dan validasi. Proses peramalan menggunakan metode certainty factor (CFf) sebagai nilai pembanding pada bobot koreksi yang telah di latih dalam jaringan backpropagation untuk prediksi yang optimal. Simulasi program peramalan penjualan mobil honda tahun 2015 dengan variabel input data penjualan daerah 30,000 unit, penjualalan dealer 25.000, penjualan tunai 25.000, CF = 0.5 dan kredit 19.000 menghasilkan ramalan penjualan sebanyak 29579 unit dengan target error 4,205 %.Kata Kunci—Peramalan, Time series, Certainty Factor, JST, Backpropagation.
Penentuan Kapasitas dan Lokasi Optimal Penempatan Kapasitor Bank Pada Penyulang Rijali Ambon Menggunakan Sistem Fuzzy Hamles Leonardo Latupeirissa; Agus Naba; Erni Yudaningtyas
Jurnal EECCIS Vol 6, No 2 (2012)
Publisher : Fakultas Teknik, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (393.032 KB)

Abstract

Penelitian ini bertujuan untuk dan menentukan kapasitas dan lokasi optimal kapasitor pada penyulang Rijali kota Ambon menggunakan sistem fuzzy. Hasil penelitiannya sebagai berikut , pertama studi aliran daya pada penyulang Rijali, tegangan paling rendah terjadi pada bus 21 yakni 0.948 pu atau 18,96 kV.. Kedua, letak kapasitor yang optimal pada Bus 3 dengan sensitivitas bus 0,61 himpunan “tinggi”, Bus 5 dengan sensitivitas bus 0,60 himpunan “tinggi”, Bus 14 dengan sensitivitas bus 0,69 himpunan “tinggi” dan Bus 20 dengan sensitivitas bus 0,92 himpunan “sangat tinggi”. Ketiga, Berdasarkan hasil perhitungan rating kapasitor sebagai kompensasi, maka rating kapasitor yang terpasang sebesar 3 MVAR. Keempat, setelah kompensasi, profil tegangan pada semua node penyulang Rijali bertambah baik, untuk node 21 menjadi 0,960 pu atau 19,18 kV mengalami kenaikan sebesar 0,12 pu atau 1,2 %. Kelima, Besar rugi daya aktif terjadi penurunan sebesar 150,421 kW dari 821,943 kW menjadi 671,522 kW atau sebesar 18,3 %. Hasil pemasangan kapasitor pada jaringan distribusi primer penyulang Rijali kota Ambon, didapatkan jatuh tegangan sebesar ± 4%. Dengan membandingkan batas toleransi tegangan yang diijinkan yaitu ± 5 %, maka dapat diasumsikan tegangan telah dapat diperbaiki dan sesuai ketentuan.Kata Kunci—Kapasitas, Lokasi optimal, Kapasitor, dan Sistem Fuzzy.
Analisis Kinerja Jalan Raya Kota Malang Menggunakan Metode FCD (Floating Car Data) Mega Satya Ciptaningrum; Muhammad Aziz Muslim; Agus Naba
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 5 No 1: Februari 2016
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (356.651 KB)

Abstract

Congestion is one of the symptoms of inadequate road conditions and interaction between the traffic elements that affect the performance of the highway. Methods of measuring the performance of the highway have been reported in Manual Kapasitas Jalan Indonesia in 1997. Highway performance measurement parameters that can be used are speed and time delay. Floating Car Data (FCD) is a method to retrieve data such as speed and time delay quickly and efficiently. While Adaptive Neuro Fuzzy Inference System (ANFIS) can be used as a method of measuring the performance of the FCD method. In this study, the FCD method is applied to the segment of urban roads in the city of Malang by utilizing the GPS feature on a mobile device carried by the rider. The results of data recording by FCD are tested using ANFIS with two input parameters (speed and time delay) and one output (congestion level). Results of experiments using 70% training data and 30% test data are able to obtain maximum performance, with the lowest MSE is 0.43, while the calculated travel speed results of the FCD method compared with the base flow speed (based on MKJI) is 68.22% during spare time, and 43.96% during traffic jam.
Analysis the Effect of Physical Parameters on Groundwater Salinity in the KEK Mandalika Lombok Alfina Taurida Alaydrus; Adi Susilo; Suhayat Minardi; Agus Naba; Agus Wahid
Prisma Sains : Jurnal Pengkajian Ilmu dan Pembelajaran Matematika dan IPA IKIP Mataram Vol 9, No 2: December 2021
Publisher : IKIP Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1196.834 KB) | DOI: 10.33394/j-ps.v9i2.4437

Abstract

KEK Mandalika is located in a coastal area which is very vulnerable to changes in the quantity and quality of groundwater due to seawater intrusion. This study aims to detect the presence of aquifers (groundwater), seawater intrusion and analyze the effect of physical parameters to determine groundwater quality in the KEK Mandalika area. The physical parameters used are: resistivity, conductivity, Total Dissolved Solid (TDS) and salinity. The resistivity value was obtained using the geoelectric resistivity method with 10 lines using a dipole-dipole configuration, while the other parameters were obtained through 10 samples of well water which were located adjacent to the geoelectric line. Resistivity geoelectrical data processing using Res2Dinv software, Surfer13 software to observe the spread of each parameter and perform regression analysis to see the effect of resistivity, conductivity, TDS on salinity. The results obtained are geoelectric resistivity in the form of an aquifer layer around the KEK Mandalika at a depth of (2 – 12) meters with resistivity values ranging from (0 – 2257) Ωm. The results of groundwater samples are: conductivity with values ranging from (1.02 – 20) mS/cm, TDS with values ranging from (67.3 – 3070) mg/L and salinity with values ranging from (0.05 – 2.07) ppt. The effect of conductivity, TDS on salinity is directly proportional, while the effect of resistivity on salinity is inversely proportional. Most of the KEK Mandalika area is likely to experience seawater intrusion, especially in the Eastern region.
Segmentasi Radiografi Tangan Pasien Artritis Rematoid dengan Pendekatan Branches Filtering Andrijani Sumarahinsih; Handono Kalim; Yuyun Yueniwati; Agus Naba
JASIEK (Jurnal Aplikasi Sains, Informasi, Elektronika dan Komputer) Vol. 4 No. 2 (2022): Desember 2022
Publisher : Universitas Merdeka Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26905/jasiek.v4i2.8334

Abstract

This research is for the possibility of automating the assessment of hand radiographic joint damage in rheumatoid arthritis. The objective of this research is to design a segmentation algorithm to obtain the area which is the joint space object. This study has collected 46 radiographic images of the hands. Image preprocessing is performed using adaptive thresholds and the concept of morphological gradient, then segmentation is performed using branches filtering approach. Analysis based on accuracy, sensitivity and specificity compared with manual segmentation by experts. The results of segmentation research preceded by preprocessing produce better images with an accuracy of 96.413%, a sensitivity of 72.121% and a specificity of 97.891% in the highest percentage.
Optimasi Gerakan Heliks untuk Meningkatkan Performa Algoritme Alga pada Desain Pressure Vessel Hari Santoso; Muhammad Aziz Muslim; Agus Naba
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 5 No 3: Agustus 2016
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (888.819 KB)

Abstract

Artificial Algae Algorithm (AAA) is an optimization algorithm that takes advantage of the swarm and evolutionary models. AAA consists of three phases, which are helical movement, reproduction, and adaptation. Helical movement is a three-dimensional motion which is highly influential in the convergence rate and diversity of solutions. Optimization of helical movement aims to increase the rate of convergence by moving the algae to the best colony in the population. Best colony in population is the closest to the best light source (the target solution), so that the movement is called Best Light Movement (BLM). AAA with movement toward the best light source (AAA-BLM) is tested and implemented in the case of pressure vessel design optimization. The test results indicate that the execution time of AAA-BLM increases 1,103 times faster than AAA. The increase in speed is caused by the tournament selection of AAA which is performed before the helical movement, while the AAA-BLM is conducted if a solution after the movement is not better than previous one. In the best condition, AAA-BLM finds a solution 4,5921 times faster than AAA. In the worst condition, AAA-BLM get stuck in local optima due to helical movement is too focused on the global best which may not be the global optima.
Identification of CO2 , SO2 , and a Mixture of Both Gases Using Optical Imaging Combined with Convolutional Neural Network (CNN) Salamah, Umi; Sakti, Setyawan Purnomo; Naba, Agus; Soetedjo, Hariyadi
Science and Technology Indonesia Vol. 9 No. 2 (2024): April
Publisher : Research Center of Inorganic Materials and Coordination Complexes, FMIPA Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26554/sti.2024.9.2.371-379

Abstract

CO2 and SO2 gases are utilized in various industrial applications and are subjects of environmental research. However, these gases are considered toxic and pose dangers at certain concentrations. Therefore, it is crucial to monitor and control the exposure to these gases in the environment to prevent reaching hazardous levels that could endanger both humans and the environment. A non-contact detection and monitoring system is essential to minimize the adverse effects of direct gas exposure. In this research, a non-contact detection system for CO2, SO2, and mixed gases was developed using optical imaging analysis generated by infrared cameras. The images were captured using the FLIR Vue Pro-R infrared camera, with infrared absorbing gas sourced from a 50-watt tungsten lamp. Visual identification of these gases through optical imaging is challenging; however, this study successfully identified these gases using a Convolutional Neural Network (CNN). The CNN architecture used in this study is DenseNet (Densely Connected Convolutional Networks), comprising 169 convolution layers. The CNN model was trained and tested on experimental optical imaging data, categorized into three classes: CO2, SO2, and a mixture of gases. A total of 1030 optical imaging data points were utilized for training. Training was conducted using the AdamW optimization function over 28 epochs. The evaluation of results yielded accuracy, precision, recall, and F1-score metrics. The novelty of this study lies in the successful identification of CO2, SO2, and their mixture by the CNN model with an accuracy of 85%. Precision, recall, and F1-score values are all 0.85. These results indicate that the CNN model effectively distinguishes optical imaging of each gas (CO2, SO2, and their mixture) consistently and accurately. Consequently, it can be concluded that the CNN model performs well in distinguishing between these gases in optical imaging analysis.
Cost Optimization of Multi-Level Multi-Product Distribution Using An Adaptive Genetic Algorithm Sarwani, Mohammad Zoqi; Mahmudy, Wayan Firdaus; Naba, Agus
Journal of Information Technology and Computer Science Vol. 1 No. 2: November 2016
Publisher : Faculty of Computer Science (FILKOM) Brawijaya University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (561.249 KB) | DOI: 10.25126/jitecs.20161218

Abstract

Distribution is the challenging and interesting problem to be solved. Distribution problems have many facets to be resolved because it is too complex problems such as limited multi-level with one product, one-level and multi-product even desirable in terms of cost also has several different versions. In this study is proposed using an adaptive genetic algorithm that proved able to acquire efficient and promising result than the classical genetic algorithm. As the study and the extension of the previous study, this study applies adaptive genetic algorithm considering the problems of multi-level distribution and combination of various products. This study considers also the fixed cost and variable cost for each product for each level distributor. By using the adaptive genetic algorithm, the complexity of multi-level and multi-product distribution problems can be solved. Based on the cost, the adaptive genetic algorithm produces the lowest and surprising result compared to the existing algorithm
Sosialisasi Pemberdayaan Situs Geologi untuk Pengembangan Wisata Desa Purwodadi, Malang Susilo, Adi; Pamungkas, Mauludi Ariesto; Juwono, Alamsyah M.; Naba, Agus; Yudianto, Didik; Hasan, Muhammad Fathur Rouf
Mitra Akademia: Jurnal Pengabdian Masyarakat Vol 7 No 1 (2024): Mitra Akademia: Jurnal Pengabdian Masyarakat
Publisher : Pusat Penelitian dan Pengabdian kepada Masyarakat (P3M) Politeknik Negeri Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32722/mapnj.v7i1.6620

Abstract

Purwodadi Village is located in the southern part of Malang Regency with a karst area which presents a beautiful panorama of rock outcrops and forms a collection of geological sites, so this area has the potential to be developed as a geotourism. Optimizing the use of geological sites and digital technology in the tourism sector will bring extraordinary benefits. This service activity aims to socialize the empowerment of geological sites to support Purwodadi Tourism Village as a geotourism centre. This activity is in collaboration with the Purwodadi Village-Owned Enterprise "Dadi Mulyo" and the Purwodadi Village Government, who also participate in the activity. The socialization is carried out to provide an overview and demonstration of the empowerment of geological sites as well as efforts that can be made to introduce geological sites to the wider community, such as digitization through the website. While the geological survey aims to map the variety of geological sites owned by Purwodadi Village, which have the potential to attract visitors. The final target of this activity is to increase the number of tourist visitors in the hope of increasing income generating BUMDes and the local government.
DOSIMETRIC EVALUATION OF POST-MASTECTOMY THREE-DIMENSIONAL CONFORMAL RADIATION THERAPY (3DCRT) BREAST CANCER TREATMENT PLANS Herwiningsih, Sri; Naba, Agus; Rianto, Sugeng; Hentihu, Fatimah Kunti
Indonesian Physical Review Vol. 6 No. 3 (2023)
Publisher : Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/ipr.v6i3.240

Abstract

Breast cancer is the most diagnosed cancer in women globally. External beam radiotherapy is one method to treat breast cancer, which can be given to the patients after mastectomy. The changes in anatomy of breast tissues after mastectomy makes the radiotherapy treatment very challenging to ensure the prescribed dose delivered to the tumour target while the radiation to the surrounding critical organs is kept to be low. This study aims to evaluate the dosimetric parameters of radiotherapy treatment plans for breast cancer patients after mastectomy delivered using 3DCRT technique. The evaluation includes the target coverage to the PTV, defined as the volume of PTV receiving 95% of the prescribed dose and the volume of PTV receiving 107% of the prescribed dose. The min, max and mean dose to the PTV were also recorded. The dosimetric parameters to the OARs were Dmean and V20 to the lung, Dmean and V25 to the heart, Dmean to esophagus and Dmax to the spinal cord. The result shows that target coverage is fulfilled in most of the plans, however the host spot in the PTV also observed in the most of the plans. Dose to heart, left lung, esophagus and spinal cord are relatively low and below the constraint recommended by QUANTEC, however the V20 to the right lung exceeded the constraint in the most of the plans. The combination of photon and electron beam might be useful to reduce the excessive dose to the right lung.