Claim Missing Document
Check
Articles

Found 20 Documents
Search

PENERAPAN ALGORITMA C4.5 DALAM MENGENALI POLA PERKEMBANGAN PEKERJAAN PROYEK Laila, Rahmah; Hendra, Syaiful; Azhar, Ryfial; Anwar, Asriani; Ngemba, Hajra Rasmita
ScientiCO : Computer Science and Informatics Journal Vol 3, No 2 (2020): Scientico : November
Publisher : Fakultas Teknik, Universitas Tadulako

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

Abstract

PLN UPP KITRING Central Sulawesi has duties and responsibilities in the process of supervising the construction period until the completion of the contract mass. In this monitoring process, managers find it very difficult to know the progress of the project due to the absence of media to facilitate reporting and monitoring of system developments to find out follow-up to the system. If this problem is allowed to continue, the project work cannot be completed on time and incurs a considerable cost loss. Through this research, it is hoped that it can help solve project monitoring problems by identifying patterns of project development that will be useful for managers in making decisions related to project performance. The development of this research uses the waterfall method and the system testing uses a black-box testing. The results of this study are based on testing and design analysis of the C4.5 Algorithm Application in Recognizing Project Work Development Patterns to Know the Win/Lose Target Results of the Case Study Project at PT PLN (PERSERO) UPP KITRING Central Sulawesi, it can be concluded that the system is able to recognize patterns project development by utilizing the C4.5 algorithm and the system can implement the C4.5 algorithm in recognizing project development patterns.
RANCANG BANGUN SISTEM PENDUKUNG KEPUTUSAN LELANG MENGGUNAKAN METODE SIMPLE MULTY ATTRIBUTE RATING TECHNIQUE (SMART) Hendra, Syaiful; Azhar, Ryfial; Risaldi Pata’Dungan, Adi; Ngemba, Hajra Rasmita; Laila, Rahmah
ScientiCO : Computer Science and Informatics Journal Vol 4, No 2 (2021): Scientico : November
Publisher : Fakultas Teknik, Universitas Tadulako

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

Abstract

Auction is a process that starts from the moment someone is about to sell an item until a price agreement is reached or until the auction is stopped, so that the item is not auctioned or sold. In the auction evaluation section, there is a problem, namely when there are many assessment documents for the goods to be auctioned, making the assessment hampered because they are still using the manual method, by assessing one by one document of the goods to be auctioned and then the results of the assessment are compared with other data items to determine which ones are eligible for auction, so that requires a longer process to determine the items eligible for auction. This study uses the SMART method for its decision support system method. This study using 15 criteria in determining decisions. The result of this research is that the decision support system designed or built is successful in selecting auction-worthy vehicles, by implementing the SMART method and running well. Determination of eligibility for auction vehicles must meet predetermined criteria, there are 15 criteria in the assessment of auction vehicles. System testing is carried out by comparing manual calculations with calculations using the system resulting in a 100% accuracy percentage of the 61 test data entered into the system.
Integrasi Density-Based Clustering dan HMRF-EM Pada Ruang Warna HSI untuk Segmentasi Citra IkanTuna Ryfial Azhar; Agus Zainal Arifin; Wijayanti Nurul Khotimah
Inspiration: Jurnal Teknologi Informasi dan Komunikasi Vol 6, No 1 (2016): Jurnal Inspiration Volume 6 Issue 1
Publisher : STMIK AKBA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35585/inspir.v6i1.89

Abstract

Segematasi citra adalah tahapan yang penting dalam proses segmentasi citra ikan tuna. Namun, pada umumnya terdapat beberapa kendala yang sering dihadapi dalam proses segmentasi citra ikan seperti pencahayaan yang tidak seimbang, adanya noise, dan ketidakakuratan tepi objek yang dihasilkan setelah proses segmentasi. Pada penelitian ini diusulkan sebuah metode segmentasi citra ikan tuna baru dengan mengintegrasikan metode Density-Based Clustering (DBSCAN), Hidden Markov Random Field (HMRF), dan algoritma expectation-maximization (EM) pada ruang warna HSI. Metode ini terdiri dari tiga tahapan utama. Tahap Pertama ialah konversi ruang warna HSI. Tahap kedua ialah segmentasi menggunakan pengklasteran DBSCAN. Tahap terakhir ialah perbaikan tepi objek hasil segmentasi menggunakan HMRF-. Hasil uji coba menunjukkan bahwa metode yang diusulkan pada penelitian ini mencapai akurasi segmentasi sebesar 98%.
PEMBOBOTAN KATA BERDASARKAN KLASTER PADA OPTIMISASI COVERAGE, DIVERSITY DAN COHERENCE UNTUK PERINGKASAN MULTI DOKUMEN Ryfial Azhar; Muhammad Machmud; Hanif Affandi Hartanto; Agus Zainal Arifin; Diana Purwitasari
Jurnal Ilmiah Teknologi Infomasi Terapan Vol. 2 No. 3 (2016)
Publisher : Universitas Widyatama

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (394.174 KB) | DOI: 10.33197/jitter.vol2.iss3.2016.105

Abstract

[Id]Peringkasan yang baik dapat diperoleh dengan coverage, diversity dan coherence yang optimal. Namun, terkadang sub-sub topik yang terkandug dalam dokumen tidak terekstrak dengan baik, sehingga keterwakilan setiap sub-sub topik tersebut tidak ada dalam hasil peringkasan dokumen. Pada paper ini diusulkan metode baru pembobotan kata berdasarkan klaster pada optimisasi coverage, diversity dan coherence untuk peringkasan multi-dokumen. Metode optimasi yang digunakan ialah self-adaptive differential evolution (SaDE) dengan penambahan pembobotan kata berdasarkan hasil dari pembentukan cluster dengan metode Similarity Based Histogram Clustering (SHC). Metode SHC digunakan untuk mengklaster kalimat sehingga setiap sub-topik pada dokumen bisa terwakili dalam hasil peringkasan. Metode SaDE digunakan untuk mencari solusi hasil ringkasan yang memiliki tingkat coverage, diversity, dan coherence paling tinggi. Uji coba dilakukan pada 15 topik dataset Text Analysis Conference (TAC) 2008. Hasil uji coba menunjukkan bahwa metode yang diusulkan dapat menghasilkan ringkasan skor ROUGE-1 sebesar 0.6704, ROUGE-2 sebesar 0.2051, ROUGE-L sebesar 0.6271 dan ROUGE-SU sebesar 0.3951.Kata kunci : peringkasan multi dokumen, similarity based histogram clustering, coverage, diversity, coherence[En]Good summary can be obtained with optimizing coverage, diversity, and coherence. Nevertheless, sometime sub-topics wich is contained in the document is not extracted well, so that the representation of each sub-topic is appear in docment summarizarion result. In this paper, we propose new of term weighting based on? cluster in optimizing coverage, diversity, and coherence for multi-document summarization. Optimization method which is used is self-adaptive differential evolution (SaDE) with additional term weighting based on clustering result with Similarity Based Histogram Clustering (SHC). SHC is used to cluster sentence so that every sub-topic in the document can be represented in summarization result. SaDE is used to search summarization result solution which has high coverage, diversity, and coherence level. Experiment is done on 15 topics in Text Analysis Conference (TAC) 2008 dataset. Experimental results show that this proposed method can produce summarization score? ROUGE-1 0.6704, ROUGE-2 0.2051, ROUGE-L 0.6271 and ROUGE-SU 0.3951.Keywords: multy-document summarization, similarity based histogram clustering, coverage, diversity, coherence.
Perancangan Sistem Virtual Tour (Si VIRAL) Tempat Wisata Alam di Kota Palu Berbasis Cloud Computing Chairunnisa Ar Lamasitudju; Miftah Miftah; Septiano A Pratama; Ryfial Azhar
Innovative: Journal Of Social Science Research Vol. 3 No. 4 (2023): Innovative: Journal Of Social Science Research
Publisher : Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/innovative.v3i4.4562

Abstract

Beberapa Indikator Teknologi Informasi yang terkomputerisasi menurut Muslihudin dan Oktafianto (2016:41) yaitu dimana terdapat hardware, software, data, prosedur, dan manusia. Adapun penjelasan lain mengenai indikator teknologi informasi menurut Muslihudin dan Oktafianto (2016:41) adalah sebagai berikut: (1). Hardware yaitu terdiri dari komponen input, proses, output dan jaringan; (2). Software yaitu terdiri dari komponen operasi, utilitas dan aplikasi; (3). Data mencakup struktur data, keamanan dan integritas data; (4). Prosedur seperti dokumentasi, prosedur sistem, buku petunjuk operasi dan teknis; (5). Manusia yaitu pihak yang terlibat dalam penggunaan sistem informasi. Menurut Fatma, Y., Hayami,dkk (2019) Penerapan Virtual Tour tidak hanya digunakan di lingkungan kapus tetapi disektor pariwisata juga. Salah satunya penerapan pada promosi pariwisata di Provinsi Riau dengan menerapkan Virtual Tour berbasis VR yang membantu wisatawan serta masyarakat memberikan informasi tentang lokasi tempat wisata dan dapat meningkatkan potensi pariwisata di propinsi Riau khususnya Kota Pekanbaru. Ada berbagai macam strategi promosi daerah yang dilakukan mulai dari pembuatan brosur, pembuatan media sosial, serta pembuatan video singkat mengenai daerah tersebut. Tetapi sampai saat ini belum ada yang mengembangkan sebuah promosi daerah dalam hal tempat wisata khusunya di kota Palu dalam bentuk virtual tour sehingga memberikan kesan unik dalam berwisata. Minim budget serta mendapat banyak informasi terkait tempat wisata yang dituju. Berdasarkan alasan diatas maka peneliti melalui usulan ini mengajukan judul penelitian yaitu: Perancangan Sistem Virtual Tour (Si VIRAL) Tempat Wisata Alam di Kota Palu Berbasis Cloud Computing.
Comparison of Machine Learning Algorithms for Predicting Stunting Prevalence in Indonesia Pratama, Moh. Asry Eka; Hendra, Syaiful; Ngemba, Hajra Rasmita; Nur, Rosmala; Azhar, Ryfial; Laila, Rahmah
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol 13, No 2 (2024): JULY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v13i2.2097

Abstract

Stunting is a serious public health problem, especially among under-fives, which can cause serious short- and long-term impacts. Efforts to tackle stunting in Indonesia involve national strategies and development priorities. Therefore, this study aims to compare the performance of machine learning regression algorithms in predicting stunting prevalence in Indonesia. The data collected is secondary data. The data collection was done carefully, taking explicit details regarding the source, scope, extent, and analysis of the dataset, and using a careful sampling methodology. The model evaluation results show that the Random Forest Regression algorithm has the best performance, with a success rate of 90.537%. The application of this model to the new dataset shows that East Nusa Tenggara province has the highest percentage of stunting at 31.85%, while Bali has the lowest percentage at 12.07%. Visualization of the dashboard using Tableau provides a clear picture of the distribution of stunting in Indonesia. In conclusion, this research contributes to the development of science, especially in the field of machine learning and public health, and provides policy recommendations for tackling stunting in Indonesia.
Aplikasi Antrian Pasien Pada Dokter Praktek Umum Menggunakan Metode FIFO (First In First Out) Berbasis Android Hardianti, Hardianti; Hendra, Syaiful; Kasim, Anita Ahmad; Azhar, Ryfial; Angreni, Dwi Shinta; Ngemba, Hajra Rasmita
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol 12, No 1 (2023): MARET
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v12i1.1478

Abstract

Currently, there are so many services in Indonesia. One of the services in the health sector is the practice of general practitioners. Services that occur at the practice of general practitioners, namely dr. Zaki Mubarak and dr. Subhan Habibi, located in Palu, often has complaints because it is still ineffective where getting these services is still done manually by means of patients coming in person and taking a queue based on the order of seats then one by one they will be served. This causes patient discomfort in waiting. To make it easier for patients who want to seek treatment, a system is needed, with this; an Android-based patient queuing application for general practice doctors was made. The application of the method used in building the system is the FIFO queuing method where patients who register earlier get medical services first. Then the average waiting time is calculated where the results obtained will be used as an estimate of the waiting time for the next patient. The application development method in this research used the prototype method and application testing uses the black box testing method. The results of this research are the application of patient queues for general practice doctors based on Android which is built to be able to take queues anywhere and anytime and obtain some information including doctor’s practice schedules, queue numbers, running queues, and estimated waiting times so that patients can estimate arrival time without having to wait long. Based on system testing with black box, the results show that the functional system is running well. Based on the average waiting time calculation, from the 60 queue data tested, the result is that the distance between queue 1 and the order is around 5 minutes.
IMPLEMENTASI ALGORITMA RC4 PADA SISTEM INFORMASI KOPERASI VIRTUAL BAWASLU PROVINSI SULAWESI TENGAH VIRTUAL BAWASLU Ngemba, Hajra Rasmita; Ulhaq, Muhammad Naufal Daffa; Hendra, Syaiful; Azhar, Ryfial; Alamsyah, Alamsyah; Laila, Rahma
PROSISKO: Jurnal Pengembangan Riset dan Observasi Sistem Komputer Vol. 11 No. 1 (2024): Prosisko Vol. 11 No. 1 Maret 2024
Publisher : Pogram Studi Sistem Komputer Universitas Serang Raya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30656/prosisko.v11i1.8182

Abstract

Koperasi merupakan hal yang penting bagi kemajuan ekonomi Indonesia yang berlandaskan kekeluargaan dan gotong royong. Perkembangan teknologi berupa internet dapat digunakan untuk mempermudah operasional koperasi, dan keamanan data di dalamnya tetap terjaga. Penelitian ini bertujuan untuk meningkatkan kualitas koperasi Bawaslu khususnya di Sulawesi Tengah, dan mempermudah menghubungkan koperasi dengan mitra serta bertujuan untuk mengamankan suatu transaksi yang dilakukan oleh karyawan dengan mitra nantinya tanpa adanya keamanan saat melakukan transaksi maka sangat berbahaya karena pihak-pihak lain yang tidak bertanggung jawab akan memanfaatkan celah keamanan tersebut sehingga dapat merugikan karyawan nantinya. Oleh karena itu penelitian ini menggunakan metode kriptografi dengan menggunakan algoritma RC4. Algoritma RC4 digunakan untuk enkripsi barcode pada saat melakukan transaksi. Jika id dari barcode telah diamankan, maka kecil kemungkinan pihak lain yang tidak bertanggung jawab dapat menggunakan barcode tersebut. Algoritma ini digunakan karena efektif, mudah diimplementasikan, dan ringan. Pengembangan sistem menggunakan bahasa pemrograman PHP dengan menggunakan framework Laravel. Pengujian sistem menggunakan Blackbox dan juga metode BIG-O. Hasil penelitian berdasarkan pengujian bahwa aplikasi dengan menggunakan Algoritma RC4 berjalan dengan baik karena proses enkripsi berhasil
KLASIFIKASI JENIS KAYU BERDASARKAN CITRA SERAT KAYU MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK Dwimanhendra, Muhammad Rifaldi; Syahrullah, Syahrullah; Joefrie, Yuri Yudhaswana; Angreni, Dwi Shinta; Azhar, Ryfial; Nugraha, Deny Wiria; rezandy Lapatta, Nouval; Najar, Abdul Mahatir
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 10, No 1 (2025)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v10i1.5726

Abstract

Kayu merupakan sumber daya alam yang sangat penting bagi industri mebel atau furnitur. Pemilihan jenis kayu yang tepat sangat krusial dalam industri mebel untuk menentukan kualitas hasil produksi. Pemilihan kayu secara manual memiliki risiko kesalahan yang dapat berdampak negatif pada kualitas akhir produk mebel. Oleh karena itu, diperlukan penerapan teknologi untuk meminimalkan kesalahan pemilihan jenis kayu dan meningkatkan efisiensi proses produksi. Penelitian ini bertujuan membangun model klasifikasi jenis kayu (nantu, palapi, dan uru) berbasis Convolutional Neural Network (CNN) menggunakan citra serat kayu. Dataset terdiri dari 1.584 citra yang dibagi menjadi 80% data pelatihan dan 20% data pengujian. Arsitektur model CNN terdiri dari 4 lapisan konvolusi, 4 lapisan pooling, dan 2 lapisan fully-connected. Hasil pelatihan mencapai akurasi 97,06%, sedangkan hasil pengujian dan evaluasi menggunakan matriks konfusi mencapai akurasi 95,56%. Penelitian ini membuktikan bahwa CNN dapat digunakan secara efektif untuk klasifikasi jenis kayu dengan tingkat akurasi yang tinggi, sehingga dapat membantu meningkatkan efisiensi proses produksi mebel.
Implementasi Face Recognition Pada Aplikasi Absensi Berbasis Android Menggunakan Algoritma Haversine Siddiq Assegaf, Djafar; Azhar, Ryfial; Pusadan, Yazdi; Anggun Pratama, Septiano; AR. Lamasitudju, Charunnisa
The Indonesian Journal of Computer Science Vol. 13 No. 6 (2024): The Indonesian Journal of Computer Science (IJCS)
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v13i6.4494

Abstract

Android-Based Attendance Application, Face Recognation, Haversine Algorithm, Management System. The attendance system is a method for managing employee presence, which contributes to productivity and accountability. This study aims to implement an Android-based attendance application that utilizes face recognition technology and the Haversine algorithm to enhance the accuracy and efficiency of the attendance process. Face recognition is applied to automatically verify user identity and reduce the risk of fraud in the attendance process. The system integrates the Haversine algorithm and face recognition, where the Haversine algorithm is used to calculate the distance between the employee's location and the office, ensuring that attendance can only be recorded within a predetermined radius. The results indicate that this system is effective in determining employee attendance status with high accuracy, recording employees within a radius of ≤ 30 meters as present. Additionally, the use of face recognition technology accelerates the attendance process and improves accountability. These findings open opportunities for further research in integrating technology into human resource management and are expected to enhance transparency and efficiency in managing employee attendance across various sectors.