Garuda - Garba Rujukan Digital

Prediction of Rainfall Intensity as Early Warning Information on Potential Landslides using Fuzzy Logic (Case Study West Lampung Regency) Daniel Rinaldi; Rahman Indra Kesuma; M. Yafi Fahmi; Winda Yulita; Mugi Praseptiawan; Aidil Afriansyah
IJISTECH (International Journal of Information System and Technology) Vol 5, No 4 (2021): December
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/ijistech.v5i4.163

Landslides always happened in West Lampung Regency yearly, which makes early warning information of landslides is needed. There are many factors which can cause landslide, one of the important factors is rainfall intensity, which can be predicted. The prediction of rainfall intensity can be obtained by using fuzzy logic. The fuzzy logic used in this research is Mamdani, and this research show the similar result for most data which means that fuzzy logic might not be suitable to be used to forecast the rainfall if the obtained data has lots of missing values.

The Use of Edge Coloring Concept for Solving The Time Schedule Problem at Senior High School (Case Study at SMAN 9 Bandarlampung) Rahman Indra Kesuma; . Wamiliana; Machudor Yusman
International Conference on Engineering and Technology Development (ICETD) 2012: 1st ICETD 2012
Publisher : Bandar Lampung University (UBL)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (785.764 KB)

Nowadays, the computer’s technology is growing so fast and affects the human’s life. With computer, people can do something easier, faster, more efficient, and so on. At SMAN Bandarlampung, the time schedule for teaching process is still done manually. One person is in charge of doing and making the time schedule so that all the lessons, time, classrooms, and days are supposed to be fixed and suitable for every teacher. However, this is not easy to be done, because there are some factors also that must be considered, for example: teacher who also put in structural position such as headmaster or vice headmasters. Besides, under Indonesian’s regulations, the teacher whose certificate to educate must teach at least a certain hour per week. Therefore, in order to handle this condition, we design and develop a system so that the problem can be solved easily. We use the concept of edge coloring to match the schedule. The data are divided into three sets: the set of active time, the set of classes and classroom, and the set of teachers’ obligation (which include : the data of teachers and their subjects/lessons, and how many time/hours needed to teach for every teacher. The system developed is running well and we will be discussed in the paper.

Penerapan Content-Boosted Collaborative Filtering untuk Meningkatkan Kemampuan Sistem Rekomendasi Penyedia Jasa Acara Pernikahan Rahman Indra Kesuma; Amirul Iqbal
Jurnal Ilmiah FIFO Vol 12, No 1 (2020)
Publisher : Fakultas Ilmu Komputer

AbstractThe changes in lifestyle of the global society in the era of digital world development have made the smartphone technology penetration to rise continually. This condition can increase business opportunities, especially e-commerce activities that utilize technology and the internet in terms of promotions and transactions. The efficiency and effectiveness is an interesting focus that is discussed in this issue. For example, in services or products searching for a wedding where many customers still feel difficult and need a long time to find the desired things. The existence of a recommendation system also has not been able to help, especially for users who are newly registered to the system. This is because most of them will provide recommendations based on a history of user activity. Therefore, this study applies the content-boosted collaborative filtering (CBCF) method to improve the ability of the recommendation system in providing recommendations for weddings, especially for a new user. The obtained results are then compared with two commonly used methods, content-based recommendations (CB) and collaborative filtering (CF). Based on the experimental results, it can be concluded that CBCF can maintain the quality of good recommendations for long registered users with an accuracy of 84% and also can provide recommendations for new users with an accuracy of 54% which is cannot be solved by CB or CF methods.Key Word: digital businesses, wedding vendors/organizers, recommendation system, content-boosted collaborative filtering AbstrakPerubahan pola kehidupan masyarakat global pada era perkembangan dunia digital membuat penetrasi dari teknologi telepon pintar terus menaik. Kondisi ini dapat meningkatkan kesempatan bisnis khususnya kegiatan jual beli yang memanfaatkan teknologi dan internet dalam hal promosi dan transaksi. Efisiensi dan efektifitas proses menjadi fokus yang terus menarik dibahas dalam hal ini. Sebagai contoh, pada pencarian layanan atau produk untuk pernikahan yang mana banyak pelanggan masih merasakan kesulitan dan membutuhkan waktu yang lama untuk mencari sesuatu yang diinginkannya. Keberadaan sistem rekomendasi juga belum bisa membantu terlebih bagi pengguna yang baru terdaftar pada sistem. Hal ini dikarenakan kebanyakan sistem akan memberikan rekomendasi berdasarkan rekam jejak aktifitas pengguna. Maka itu, pada penelitian ini diusulkan penerapan metode content-boosted collaborative filtering (CBCF) untuk meningkatkan kemampuan sistem rekomendasi dalam pemberian rekomendasi untuk acara pernikahan, khususnya pada pengguna baru. Hasil yang diperoleh selanjutnya dibandingkan dengan dua metode yang umum digunakan yaitu content based recommendation (CB) dan collaborative filtering (CF). Berdasarkan hasil penelitian yang diperoleh, dapat disimpulkan bahwa CBCF dapat mempertahankan kualitas pemberian rekomendasi yang baik untuk pengguna lama dengan akurasi sebesar 84% serta mampu memberikan rekomendasi untuk pengguna baru dengan akurasi 54% yang mana kondisi ini tidak bisa diselesaikan oleh metode CB ataupun CF.Kata Kunci: bisnis digital, penyedia jasa acara pernikahan, sistem rekomendasi, content-boosted collaborative filtering

Automatic Gate for Body Temperature Check and Masks Wearing Compliance Using an Embedded System and Deep Learning Rahman Indra Kesuma; Rivaldo Fernandes; Martin Clinton Tosima Manullang
Khazanah Informatika Vol. 8 No. 1 April 2022
Publisher : Department of Informatics, Universitas Muhammadiyah Surakarta, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23917/khif.v8i1.15205

A new coronavirus variant known as n-Cov has emerged with a fast transmission rate. The World Health Organization (WHO) has declared the related disease or COVID-19 as a global pandemic that requires special handling. Many parties have shown efforts to reduce virus transmission by implementing health protocols and adapting a new normal lifestyle. Implementation of the health protocol creates new problems, especially in the health check at the main entrance. The officers in charge of measuring body temperature are at risk of getting infected by COVID. Such a measurement is prone to errors. This study proposed a solution to build an automatic gate system that worked based on the new normal health protocol. The system utilizes the MLX90614 contactless temperature sensor to probe body temperature. It applies deep learning implementing the Convolutional Neural Network (CNN) algorithm with the MobileNetV2 architecture as a determinant of the conditions of wearing face masks. The system is equipped with an IoT-based remote controller to control the gate. Experimental results prove that the system works well. Temperature measurement takes a response time of 20 seconds for each user with 99% accuracy for the sensor and masks classification model.

Combination of Ant Colony Optimization with Local Triangular Kernel Clustering for Vehicle Routing Problem with Time Windows Aina Musdholifah; Rahman Indra Kesuma
Indonesian Journal of Electrical Engineering and Computer Science Vol 16, No 2: November 2015
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v16.i2.pp355-362

VRP is a common problem that occurred in logistics, including determination a route of products from the source to the destination. VRPTW is variation of VRP that use routing concepts in the serving process at the certain time interval. Recently, many methods are used to solve this optimization problem, for example ACO. LTKC-ACO was developed to improve the ACO solutions that apply LTKC to obtain a number of classes that are considered as the candidate list in ACO. Local Search is also used to avoid ACO getting stuck in the local optimum. In this study, two types of LTKC-ACO are developed that’s related to time windows parameter usage in clustering. The experimental result of 56 Solomon’s datasets showed that LTKC-ACO can improve the ACO solutions on 73,21% of datasets and can out performed then the other methods, especially on the datasets that have longer scheduling of service time.

Prediction of Rainfall Intensity as Early Warning Information on Potential Landslides using Fuzzy Logic (Case Study West Lampung Regency) Daniel Rinaldi; Rahman Indra Kesuma; M. Yafi Fahmi; Winda Yulita; Mugi Praseptiawan; Aidil Afriansyah
IJISTECH (International Journal of Information System and Technology) Vol 5, No 4 (2021): December
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Landslides always happened in West Lampung Regency yearly, which makes early warning information of landslides is needed. There are many factors which can cause landslide, one of the important factors is rainfall intensity, which can be predicted. The prediction of rainfall intensity can be obtained by using fuzzy logic. The fuzzy logic used in this research is Mamdani, and this research show the similar result for most data which means that fuzzy logic might not be suitable to be used to forecast the rainfall if the obtained data has lots of missing values.

Sistem Peringatan Dini untuk Pemborosan Penggunaan Listrik pada Masyarakat Provinsi Lampung dengan Menggunakan Model Analisis Regresi Linier dan SMS Gateway Rahman Indra Kesuma; Mahardika Yoga Darmawan; Hafiz Budi Firmansyah
Electrician : Jurnal Rekayasa dan Teknologi Elektro Vol. 13 No. 1 (2019)
Publisher : Department of Electrical Engineering, Faculty of Engineering, Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/elc.v13n1.2085

Intisari — Saat ini masyarakat Indonesia cenderung sering melakukan pemborosan pada penggunaan listrik. Di sisi lain energi listrik di Indonesia mayoritas dihasilkan dari pembangkit listrik tenaga uap, yang membutuhkan bahan bakar dari sumber daya alam yang tidak dapat diperbaharui. Sehingga tingginya permintaan dan kejadian pemborosan dalam penggunaan listrik dapat meningkatkan konsumsi sumber daya alam serta polusi udara. Maka dari itu, dalam penelitian ini diusulkan sebuah solusi melalui sistem peringatan dini yang dapat menumbuhkan kesadaran masyarakat untuk melakukan penghematan dalam penggunaan listrik. Sistem ini membutuhkan data masukan berupa jumlah pemakaian listrik dalam 6 bulan terakhir, yang selanjutnya akan dibentuk pola penggunaan listrik dari setiap pengguna menggunakan analisis regresi linier. Selanjutnya dari pola yang diperoleh, diambil informasi pemakaian listrik perhari untuk dijadikan ambang batas pada pemberian peringatan pemborosan yang diprediksi akan terjadi. Sedangkan untuk penyebaran informasi ke pengguna tentang prediksi pemborosan, sistem ini menggunakan fasilitas SMS Gateway. Hasil penelitian ini adalah sistem yang dapat memberikan peringatan kepada pengguna jika penggunaan listriknya sudah melebihi ambang batas tertentu.Kata kunci — Sistem peringatan dini, pemborosan penggunaan listrik, analisis regresi linier, sms gateway. Abstract — Nowadays almost Indonesian people get inefficient management on the electricity usage. While, Indonesia is still use steam power plant to produce the electricity power, which require fuel from non-renewable natural resouces. So the highness of demand and the occurrence of inefficiency from the electricity usage may increase the consumption of natural resource and the air pollution. Therefore, a solution through an early warning system are proposed in this study, that would increase awareness of the people to use the electricity power become more efficient. This system require the data of electricity usage from each customers in the last 6 months, that will be generated the electricity usage trend from each customers using linear regression analysis. Furthermore from the trend data obtained, the daily electricity usage information will be taken to use as a threshold for giving the inefficiency warnings from electricity usage that will occur from the available prediction. Moreover, in this study also use SMS Gateway for send the information of inefficiency electricity usage prediction automatically to each customers. Finally, the experimental result from this study is the system that can provide a warning to customers if their electricity usage run over the certain thresholds.Keywords— Early warning system, inefficient of electricity usage, linear regression analysis, sms gateway.

Performasi Deteksi Jumlah Manusia Menggunakan YOLOv8 Nike Dwi Grevika Drantantiyas; Winda Yulita; Naufal Taufiq Ridwan; Uri Arta Ramadhani; Rahman Indra Kesuma; Arkham Zahri Rakhman; Radhinka Bagaskara; Afit Miranto; Zunanik Mufidah
JASIEK (Jurnal Aplikasi Sains, Informasi, Elektronika dan Komputer) Vol 5, No 2 (2023): Desember
Publisher : Universitas Merdeka Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26905/jasiek.v5i2.11605

Pengembangan deteksi kepala sudah meningkat dengan adanya peningkatan algoritma kecerdasan buatan. Peningkatan ini dapat pula dengan penambahan tugas yaitu menghitung jumlah orang dengan mendeteksi jumlah kepala. Tujuan penelitian ini adalah menentukan performansi model sistem penghitung jumlah kepala dengan menggunakan algoritma Yolov8. Penelitian ini hanya berfokus membuat model deteksi jumlah orang. Jumlah dataset yang dirancang berjumlah 2390 gambar yang diperoleh dari dataset Roboflow, dengan pemisahan data sebesar 70:20:10 untuk masing-masing, data latih; data uji ; data validasi. Besar Epoch pada pelatihan model yang digunakan adalah 50. Algoritma deteksi jumlah kepala meggunakan YOLOv8. Nilai yang diukur adalah performasi dari model data training, nilai confusion matrix dan nilai evaluasi dari confusion matrix. Nilai evaluasi yang akan dihitung adalah nilai presisi, nilai akurasi, recall dan f1-score. Diperoleh hasil pengujian nilai akurasi sebesar 87,56 %, nilai presisi 83,74%, nilai recall 100% dan nilai F1-score 91,15%. Kurva presisi memberikan nilai tertinggi 1 pada tingkat kepercayaan 0,857, recall bernilai 0,8 pada tingkat kepercayaan 0, f1 0,716 pada kepercayaan 0,36 dan presisi-recall 0,771 pada 0,5 mAP. Berdasarkan nilai ini, model sudah cukup mendeteksi jumlah kepala.

Title

Found 8 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 8 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 8 Documents
Search