Claim Missing Document
Check
Articles

Found 21 Documents
Search

REDIKSI KETERSEDIAAN STOK KAYU DENGAN METODE BACKPROPOGATION DAN JARINGAN KOHONEN (Studi Kasus Ud. Wahyu Nugroho Grabag Magelang) Yulfikar, Muhammad; Yudatama, Uky; Artha, Emilya Ully
Jurnal Komtika Vol 2 No 2 (2018)
Publisher : Universitas Muhammadiyah Magelang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (575.296 KB) | DOI: 10.31603/komtika.v2i2.2598

Abstract

Jaringan syaraf tiruan merupakan salah satu teknologi komputer dalam bidang kecerdasan buatan yang mampu memahami pola data yang rumit. Salah satu kemampuan teknologi JST adalah mampu memprediksi sebuah keluaran berdasarkan pola data pelatihan yang diberikan saat proses pembelajaran sistem. Pada penelitian ini, JST akan mencoba memprediksi persediaan stok kayu. Backpropagation merupakan algoritma pembelajaran terawasi yang dapat memperbaiki bobot pada masing-masing lapisan penghubung hingga diperoleh bobot terbaik dengan minimum error yang telah diberikan. Sedangkan Kohonen merupakan jaringan yang dipakai untuk membagi pola masukan kedalam beberapa kelompok (cluster). Aplikasi ini memiliki struktur jaringan yang terdiri dari 6 neuron masukan, 100 neuron pada lapisan tersembunyi, dan 1 dan 6 neuron pada lapisan keluaran. Jumlah keseluruhan data yakni 365 data, 250 data digunakan untuk data pelatihan, dan 115 digunakan untuk data pengujian. Mesin pemrediksi ini menggunakan iterasi maksimal sampai 100.000 epochs, konstanta pembelajaran 0.5, momentum 0.9, serta tingkat error minimum 0,001. Dengan variasi nilai dari komponen backpropagation dihasilkan prediksi sebesar kurang dari 150m3/bulan., Sedangkan dari bobot yang dihasilkan akan diprediksi dengan metode Kohonen dan menghasilkan prediksi pengeluaran stok kayu perbulan. Berdasarkan hasil pengujian terhadap 115 data pengujian, prosentase tingkat keakuratan sistem adalah 73,9 % . Pengurangan konstanta pembelajaran dan penambahan data pelatihan mungkin dapat meningkatkan keakuratan sistem dalam melakukan prediksi.
PANDUAN JALUR ANGKUTAN UMUM MENGGUNAKAN ALGORITMA FLOYD WARSHALL Fatmala, Fungki; Yudatama, Uky; Burhanuddin, Auliya
Jurnal Komtika (Komputasi dan Informatika) Vol 3 No 1 (2019)
Publisher : Universitas Muhammadiyah Magelang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (221.482 KB) | DOI: 10.31603/komtika.v3i1.3462

Abstract

Public transportation as one of the most easily found transportation for tourists to visit a tourist destination. There are 12 public transportation lines in Magelang. The large number of public transport lines caused problems for tourists to choose which lines of transportation to get in. The purpose of this research is to develop a guide for public transportation for tourist destination in Magelang usin Floyd Warshall Algorithm. Floyd Warshall's algorithm provides the shortest path recommendation by calculating all vertices, then calculating all possible routes from the initial location to the final destination to determine the total distance travelled on each route. After knowing the total distance on all routes, the system will display the shortest path as a recommendation. From the test results obtained that the system being built is feasible to be used and is able to find the shortest route for determining public transport lines in the city of Magelang Angkutan umum sebagai salah satu transportasi yang paling mudah ditemui untuk digunakan wisatawan dalam mengunjungi suatu objek wisata. Terdapat 12 jalur angkutan umum yang ada di Kota Magelang. Banyaknya jumlah jalur angkutan umum tersebut menjadikan permasalahan bagi wisatawan dalam memilih angkutan yang akan digunakan. Tujuan dari penelitian adalah membangun aplikasi panduan jalur angkutan umum untuk tempat wisata di Kota Magelang dengan menggunakan Algoritma Floyd Warshall. Algoritma Floyd Warshall memberikan rekomendasi jalur terpendek dengan melakukan perhitungan dari semua simpul, kemudian melakukan perhitungan pada semua kemungkinan rute dari lokasi awal sampai lokasi akhir untuk mengetahui total jarak yang dilalui pada masing-masing rute. Setelah diketahui total jarak pada semua rute sistem akan menampilkan jalur terpendek sebagai rekomendasi. Dari hasil pengujian diperoleh bahwa sistemyang telah dibangun layak digunakan dan mampu mencari rute terpendek untuk penentuan jalur angkutan umum di Kota Magelang
MEDIA KONSULTASI PENYAKIT KULIT PADA BALITA MENGGUNAKAN METODE CERTAINTY FACTOR Utari, Sudi; Yudatama, Uky; Pujiarto, Bambang
Jurnal Komtika (Komputasi dan Informatika) Vol 3 No 1 (2019)
Publisher : Universitas Muhammadiyah Magelang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (308.203 KB) | DOI: 10.31603/komtika.v3i1.3463

Abstract

The skin, which is the largest part  of the human body, is the body's first defense against bacterial and virus attacks. When the skin is exposed to the sun, dry weather, or bacteria, the reaction will spread to other parts of the body, and can even result in death if it is too late to be handled especially if the sufferers are children who are very vulnerable to disease. In this study an expert system was implemented to diagnose skin diseases in infants using the certainty factor method. certainty factor method is very suitable for expert systems that diagnose something that is uncertain. This system makes a diagnosis based on the symptoms felt by the user and then calculates certainty factors based on existing symptoms. Based on the test results by making comparisons between manual calculations and the one carried out by the system it is known that 90.22% of the diagnosis results get the same results so that the system is said to be suitable for use.  
Peningkatan Kualitas Media Pembelajaran Dengan Google Sites Pada Guru SMK 1 Windusari Magelang Hasani, Rofi Abul; Yudatama, Uky; Yudianto, Resa Arif; Sukmasetya, Pristi; Maimunah, Maimunah
Jurnal Pengabdian kepada Masyarakat UBJ Vol. 5 No. 2 (2022): June 2022
Publisher : Lembaga Penelitian Pengabdian kepada Masyarakat dan Publikasi Universitas Bhayangkara Jakarta Raya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31599/j3vvyy86

Abstract

Technology has changed the teaching and learning process in the world of education. The most visible change is the use of learning media in schools. The presence of digital media provides a variety of educational innovations, where rigid and monotonous conventional learning will be replaced by learning using digital media which is considered more practical, flexible, and not limited by space and time. One of the learning media is a website. Based on the results of interviews with teachers at SMK Negeri 1 Windusari, they said the importance of online learning media, especially when online learning demands. Therefore, in this PKM, the authors carry out google sites training activities to improve the ability of teachers of SMK Negeri 1 Windusari to create learning media. After training on making teaching media using google sites will help teachers in making interesting learning materials and conveying them to students. So that this activity will provide good benefits to teachers, students, and SMK N 1 Windusari, Magelang Regency. Many teachers were previously reluctant to use making websites because of difficulties. However, after this training, the teachers at SMK Negeri 1 Windusari began to be enthusiastic about making learning media using google sites. Because using google sites is quite easy for teachers to do.
Forecasting Optimalization in Spare Part Inventory Applications on XYZ Temanggung Outlet Ltd. Anwar, Tulkhah Mubasyir; Yudatama, Uky; Primadewi, Ardhin
Proceedings of Universitas Muhammadiyah Yogyakarta Graduate Conference Vol. 3 No. 2 (2024): Crafting Innovation for Global Benefit
Publisher : Universitas Muhammadiyah Yogyakarta

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

Abstract

XYZ Magelang Branch Ltd is a company engaged in the automotive sector, which supported by three outlets. The name of the outlet are Temanggung Outlet, Purworejo Outlet, and Kebumen Outlet. The Temanggung Outlet is one of the outlet with the highest number of services compared to the others. The impact of having the highest number of services is that the demand for spare parts is also the highest compared to the other outlets. To overcome the demand for spare parts at the Temanggung Outlet, an inventory application is needed to manage spare parts with the implementation of forecasting to determine the stock of spare parts for the upcoming period. In this research, the forecasting calculation is carried out by utilizing the historical calculation of the outgoing transaction data in the inventory application. The data obtained from the sales transaction report is in the form of spare parts sales with a data quantity of 30 items, selected from the top 30 spare parts sales. The calculation process using the Single Moving Average (SMA) forecasting is validated using Mean Absolute Deviation (MAD) and Mean Absolute Percentage Error (MAPE). In this research manuscript, SMA has MAPE error with range 0% up to 62.069% compared to the conventional method, which has range 16% up to 83%.
Metode Cosine Similarity pada Penilaian Essay Perkaderan Ikatan Mahasiswa Muhammadiyah Anggraini, Novi Kusuma; Yudatama, Uky; Maimunah, Maimunah
CESS (Journal of Computer Engineering, System and Science) Vol 9, No 1 (2024): January 2024
Publisher : Universitas Negeri Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24114/cess.v9i1.55475

Abstract

Perkaderan persyarikatan merupakan suatu program yang dilaksanakan oleh Muhammadiyah baik ditingkat pusat maupun bawahnya dan menjadi bagian inti dalam perjalanan organisasi Muhammadiyah. Perkaderan utama di Muhamamdiyah dibagi menjadi 2 (dua) yaitu Darul Arqam dan Baitul Arqam. Dalam pelaksanaannya juga terdapat evaluasi pembelajaran yaitu pre-test dan post-test. Pre-Test dilaksanakan sebelum materi disampaikan, sedangkan post-test dilaksanakan setelah materi disampaikan. Evaluasi ini berbentuk soal esai yang bersangkut pautan dengan materi yang akan diberikan. Jawaban peserta yang bervariasi dan waktu yang padat menjadi tantangan tersendiri untuk mengoreksinya, dan membutuhkan waktu yang lebih banyak lagi ditambah dengan harus memasukkan nilai ke sistem perkaderan secara manual. Penelitian ini menerapkan text mining dengan menggunakan metode cosine similarity untuk melakukan penilaian otomatis pada soal esai pre-test dan post-test. Hasil perhitungan pada soal pre-test mendapatkan hasil tertinggi dengan tingkat persamaan 77,46% oleh peserta 1 pada soal 4 dan peserta 2 pada soal 3, dan post-test dengan hasil tertinggi 100% oleh peserta 1 pada soal 4. Sedangkan untuk hasil 0,0 yang diperoleh beberapa peserta dikarenakan term antar kunci jawaban dan jawaban peserta tidak memiliki persamaan.
Prediksi Bahan Baku Kerupuk Rambak UMKM Tiga Berlian dengan Single Moving Average Sebastian, Devara Avila; Yudatama, Uky; Primadewi, Ardhin
Journal of Computer System and Informatics (JoSYC) Vol 5 No 4 (2024): August 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i4.5604

Abstract

The "Tiga Berlian" rambak cracker MSME is an MSME in the snack food sector located in Banyuwangi Bandongan Village which produces crackers made from cowhide. Rambak crackers are a superior product with total demand per month reaching 150 kg. Tiga Berlian UMKM has difficulty in predicting and calculating raw material supplies for the coming period so excess raw material stock often occurs, such as cowhide or buffalo as the main raw material that is wasted due to uncertain demand. Single Moving Average (SMA) is used as a prediction method for raw materials in Tiga Berlian. Calculations with several periods (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, and 11) will be tested for accuracy using MAD, MSE and MAPE. The 11 predictions made with Tiga Berlian raw material data for 12 months, the 11th-period calculation resulted in a MAD value of 2.56198, a MAPE value of 2.561983, and an MSE value of 72.20135 as the smallest and most relevant accuracy value.
Peramalan Stok Penjualan Sahabi Frozen Food dengan Weighted Moving Average Karim, Muhammad Abdul; Yudatama, Uky; Primadewi, Ardhin
Journal of Computer System and Informatics (JoSYC) Vol 5 No 4 (2024): August 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i4.5824

Abstract

Jajan Sahabi Frozen Food (Jajan Sahabi) is a small and medium-sized enterprise (SME) located in Secang, Magelang, offering various types of frozen foods such as burgers, meatballs, and fries from multiple brands. Currently, inventory tracking at Jajan Sahabi is still conducted manually using a logbook, while stock replenishment is carried out weekly based on the remaining inventory. This approach leads to stock imbalances, either resulting in overstock, which may cause losses, or understock, which could lead to customer dissatisfaction. Forecasting is employed as an alternative decision-making tool to predict product demand based on historical data over a certain period. This study analyzes meatball sales reports from January 2022 to December 2022 using the Weighted Moving Average (WMA) method. The accuracy of the forecasts was evaluated using Mean Absolute Deviation (MAD) and Mean Absolute Percentage Error (MAPE). The forecast results for January 2023 indicate that Meatball Ori is expected to sell 216.3 pieces with a MAD of 76.81 and a MAPE of 53.90%. Meatball Kanzler showed the best performance with a MAPE of 28.80% and a MAD of 28.53. In contrast, Meatball Ikan, Meatball Ikan TL, Meatball Fish dan Shrimp, Meatball Cheese Kanzler, and Meatball Wahid exhibited lower accuracy, with MAPE values ranging from 29.03% to 53.90%. These results suggest that the WMA method produces varying outcomes depending on the product, indicating that further adjustments may be necessary to enhance accuracy.
Fuzzy Time Series dan Algoritme Average Based Length untuk Prediksi Pekerja Migran Indonesia Solikhin, Solikhin; Yudatama, Uky
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 6 No 4: Agustus 2019
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (3634.511 KB) | DOI: 10.25126/jtiik.2019641177

Abstract

Perkembangan jumlah Pekerja Migran Indonesia (PMI) program Government to Government (G to G) Jepang bidang perawat (nurse) dan perawat orang berusia lanjut (care worker) mengalami naik turun dari tahun 2008 hingga 2018. Untuk dapat menganalisis jumlah PMI yang mengalami naik turun dengan mengukur perkembangan jumlah PMI saat ini dan memprediksikan kondisi tersebut pada masa mendatang, maka diperlukan model prediksi. Dalam penelitian ini diterapkan model fuzzy time series dengan menggunakan algoritme average-based length. Penentuan panjang interval yang efektif dapat mempengaruhi hasil prediksi yaitu dapat meningkatkan keakuratan yang tinggi dalam fuzzy time series. Hasil proses prediksi PMI program G to G Jepang tahun 2019 bidang nurse diperoleh 43.3, bidang care worker diperoleh 300 dan bidang keseluruhan diperoleh 325. Hasil uji kinerja prediksi PMI program G to G Jepang, menggunakan Mean Absolute Percentage Error (MAPE) adalah 24.27% untuk bidang nurse dengan nilai akurasi prediksi 20–50% termasuk dalam kriteria “wajar”, bidang care worker 11.29% dengan nilai akurasi prediksi 10–20% termasuk dalam kriteria “baik”, sedangkan untuk bidang keseluruhan diperoleh 8.41% dengan nilai akurasi prediksi MAPE <10% termasuk dalam kriteria “sangat baik”. Berdasarkan hasil prediksi tersebut dapat digunakan sebagai pendukung keputusan bagi manajemen dalam membuat kebijakan terkait persiapan, perencanaan, penjadwalan, penempatan, dan perlindungan terhadap para calon PMI pada masa mendatang. Dengan demikian dapat meningkatkan kualitas kinerja sumberdaya manusia dalam memberikan pelayanan terbaik terhadap para calon PMI program G to G Jepang.AbstractThe development of the number of Pekerja Migran Indonesia (PMI) Government to Government programs (G to G) in Japan in the field of nurses  and care workers experienced ups and downs from 2008 to 2018. To be able to analyze the number of PMIs experiencing ups and downs by measuring the development of the current number of PMIs and predicting these conditions in the future, a prediction model is needed. In this study fuzzy time series models are applied using an average-based length algorithm. Determining the length of an effective interval can influence the results of predictions, which can increase high accuracy in fuzzy time series. The results of the PMI program G to G Japan prediction process for 2019 in the nurse field were obtained 43.3, the care worker field was obtained 300 and the overall field was 325. The results of the G to G Japan PMI prediction performance test, using the Mean Absolute Percentage Error (MAPE) were 24.27% for nurse field with predictive accuracy value of 20–50% included in the criteria of "reasonable", the field of care worker 11.29% with a prediction accuracy value of 10-20% included in the criteria "good", while for the overall field obtained 8.41% with MAPE prediction accuracy value < 10% is included in the criteria of "very good". Based on the results of these predictions it can be used as a decision support for management in making policies related to preparation, planning, scheduling, placement, and protection of future PMI candidates. Thus it can improve the quality of the performance of human resources in providing the best service to prospective G-G Japan PMI programs.
Implementasi Simple Additive Weight pada Sistem Pendukung Keputusan Penerima Bantuan Stimulan Perumahan Swadaya Berbasis Web di Dinas Perumahan dan Kawasan Pemukiman Kota Magelang Pamungkas, Eko Joko; Yudatama, Uky; Artha, Emilya Ully
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 9 No 4: Agustus 2022
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2022944697

Abstract

Salah satu program pemerintah yang sedang berjalan yaitu program Bantuan Stimulan Perumahan Swadaya (BSPS) dengan targetnya adalah masyarakat berpenghasilan rendah dan memiliki rumah yang belum layak huni. Rumah Tidak Layak Huni yang selanjutnya disingkat RTLH adalah rumah yang tidak memenuhi persyaratan keselamatan bangunan, kecukupan minimum luas bangunan, dan kesehatan penghuni. Adapun kriteria yang harus dipenuhi untuk mendapatkan Bantuan Stimulan Perumahan Swadaya ini Kondisi Atap, Dinding, Pintu & Jendela, Lantai, Pondasi,Sanitasi, dan calon penerima harus merupakan warga negara Indonesia dan mempunyai sertifikat hak milik atas tanah rumah tersebut. Dalam menentukan Penerima Bantuan Stimulan Perumahan Swadaya Dinas Perumahan dan Kawasan Permukiman masih kurang efektif dalam penentuan penerima Bantuan Stimulan Perumahan Swadaya seperti banyaknya calon penerima Bantuan Stimulan Perumahan Swadaya sedangkan dana bantuan stimulan perumahan swadaya yang turun dari pusat hanya sedikit dari banyaknya calon penerima bantuan stimulan perumahan swadaya maka di perlukan perangkingan dari setiap kriteria-kriteria dari calon penerima bantuan yang ada. Selain itu data survey masih ditulis menggunakan kertas secara manual sehingga rawan untuk hilang ataupun rusak dan juga proses pemilihan Penerima Bantuan Selama ini belum terpublikasi. Metode Simple Additive Weighting digunakan untuk penentuan diterima/ tidak berdasarkan urutan rangking prioritas. Selain itu dengan menggunakan Aplikasi Web bertujuan untuk mempublikasi hasil penilaian Bantuan Stimulan Perumahan Swadaya di Dinas Perumahan dan Kawasan Permukiman. Dengan dibangunnya sistem ini dapat mempermudah Surveyor dalam proses penginputan data penduduk dan penginputan data nilai sehingga membantu dalam proses pemilihan Penerima Bantuan Stimulan Perumahan Swadaya. Sistem yang telah dibuat ini dapat membantu dalam pemilihan Penerima Bantuan Stimulan Perumahan Swadaya karena selain  memberikan hasil perhitungan perankingan tetapi juga menampilkan grafik visualisasi sehingga mempermudah dan mempercepat dalam pengambilan keputusan. AbstractOne of the ongoing government programs is Bantuan Stimulan Perumahan Swadaya (BSPS) program with the target being people who have low income and have houses that are not yet suitable for habitation. Unfit for habitation, hereinafter abbreviated as RTLH, is a house that does not meet the requirements for building safety, minimum adequacy of building area, and occupant health. The criteria that must be met to get this Self-Help Housing Stimulant Assistance are Conditions of Roof, Walls, Doors & Windows, Floor, Foundation, Sanitation, and prospective recipients must be Indonesian citizens and have a certificate of title to the land of the house. In determining Recipients of Bantuan Stimulan Perumahan Swadaya Dinas Perumahan dan Kawasan Permukiman is still ineffective in determining recipients of Bantuan Stimulan Perumahan Swadaya such as the number of prospective recipients of Bantuan Stimulan Perumahan Swadaya while the funds for Bantuan Stimulan Perumahan Swadaya that have come down from the center are only a few of the many potential recipients of Bantuan Stimulan Perumahan Swadaya. then it is necessary to rank each of the criteria of the existing beneficiary candidates. In addition, the survey data is still written using paper manually so it is prone to loss or damage and the process of selecting aid recipients has not been published. The Simple Additive Weighting method is used to determine whether it is accepted or not based on the priority ranking order. In addition, using the Web application aims to publish the results of the assessment of Bantuan Stimulan Perumahan Swadaya in Dinas Perumahan dan Kawasan Permukiman. With the construction of this system, it can facilitate Surveyors in the process of inputting population data and inputting value data to assist in the selection process of Penerima Bantuan Stimulan Perumahan Swadaya. The system that has been created can assist in the selection of Self-help Housing Stimulant Assistance Recipients because, in addition to providing ranking results, it also displays visualization graphs to simplify and speed up decision making.