Claim Missing Document
Check
Articles

Indonesian license plate recognition with improved horizontal-vertical edge projection Ida Nurhaida; Imam Nududdin; Desi Ramayanti
Indonesian Journal of Electrical Engineering and Computer Science Vol 21, No 2: February 2021
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v21.i2.pp811-821

Abstract

License plate recognition (LPR) is one of the classical problems in the field of object recognition. Its application is very crucial in the automation of transportation system since it helps to recognise a vehicle identity, which information is stored in the license plate. LPR usually consists of three major phases: pre-processing, license plate localisation, optical character recognition (OCR). Despite being classical, its implementation faced with much more complicated problems in the real scenario. This paper proposed an improved LPR algorithm based on modified horizontal-vertical edge Projection. The method uses for detecting and localising the region of interest. It is done using the horizontal and vertical projection of the image. Related works proved that the modified horizontal-vertical edge projection is the simplest method to be implemented, yet very effective against Indonesian license plate. However, its performance gets reduced when specular reflection occurs in the sample image. Therefore, morphological operations are utilised in the pre-processing phase to reduce such effects while preserving the needed information. Eighty sample images which captured using various camera configurations were used in this research. Based on the experimental results, our proposed algorithm shows an improvement compared with the previous study and successfully detect 71 license plates in 80 image samples which results in 88.75% accuracy.
Implementasi Model Arsitektur VGG16 dan MobileNetV2 Untuk Klasifikasi Citra Kupu-Kupu Desi Ramayanti; Sri Dianing Asri; Lionie Lionie
JSAI (Journal Scientific and Applied Informatics) Vol 5 No 3 (2022): November 2022
Publisher : Fakultas Teknik Universitas Muhammadiyah Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36085/jsai.v5i3.2864

Abstract

Untuk mengurangi populasi kupu-kupu, perlu adanya strategi untuk memantau jumlah dan spesies yang ada pada masing-masing ekosistem. Peran teknologi dapat membantu dalam proses ini, misalnya pengembangan sistem e-Butterfly untuk mengumpulkan gambar spesies kupu-kupu dari berbagai wilayah sehingga dapat diketahui jenis spesies yang masih ada dan letak wilayah hidupnya. Identifikasi spesies kupu-kupu dapat dilakukan dan dibantu oleh komputer dengan serangkaian proses lebih spesifik pada cabang ilmu machine learning dan image processing. Tujuan dari penelitian ini adalah untuk mengetahui kinerja (performance) dari model model arsitektur VGG16 dan MobileNetV2 untuk klasifikasi citra gambar kupu-kupu berdasarkan hasil ekstraksi fitur pada citra gambar tersebut. Dataset penelitian berisi 4955 gambar yang kemudian diberi label 50 butterfly species dengan ukuran 224 X 224 X 3. Akurasi terbaik diperoleh MobileNetV2 tanpa fine-tuning yaitu mencapai presentase 96%, dilanjutkan dengan VGG16 dengan fine-tuning, MobileNetV2 dengan fine-tuning, dan akurasi testing paling kecil diperoleh VGG16 tanpa fine-tuning. Untuk nilai precision, recall, F1-Score, dan Cohens Kappa lebih tinggi diperoleh model MobileNetV2 tanpa fine tuning, hal ini menunjukkan bahwa MobileNetV2 tanpa fine tuning lebih imbang dalam akurasi tiap kelasnya.
METODE PROFILE MATCHING UNTUK PENENTUAN AMBALAN TERGIAT PADA GERAKAN PRAMUKA KECAMATAN JATISAMPURNA BEKASI Muhamad Sony Pratama; Sri Dianing Asri; Desi Ramayanti; Sri Andriati Asri; Widyadi Setiawan
Jurnal Teknoinfo Vol 17, No 1 (2023): Vol 17, No 1 (2023): JANUARI
Publisher : Universitas Teknokrat Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33365/jti.v17i1.2373

Abstract

DKR Jatisampurna Bekasi is a Group of Scout Members in the Jatisampurna area who are responsible for scouting management. Every year DKR Jatisampurna will choose the Most Active Ambalan in the Jatisampurna area. This study intends to get DKR Jatisampurna's active ambalan using Profile Matching. The Profile Matching method is used to compare individual/school competencies into competencies as the best shelves so that differences in competence (Gap Value) can be identified. The smaller the Gap Value generated, the greater the weighted score, which means that there is a greater opportunity for individuals/schools to become the best Troops in Jatisampurna district. The criteria provided by DKR Jatisampurna include the criteria of 35% Activeness, 35% Organizational, and 35% Non-Organizational. The three criteria are further divided into core and secondary factors, with the provisions of DKR Jatisampurna 50% core factor and 50% secondary for Activeness criteria, 60% core factor and 40% secondary for Organizational aspects, and 40% core factor and 60% secondary for non-organizational criteria. The end result of the profile matching process is the ranking of the shelves that can be used as the best shelves. Ranking is determined from the total value of the assessment sorted from the largest value to the smallest, where the alternative with the largest total value is selected as the final result. The profile matching method for determining the most active ambalan at DKR Jatisampurna Bekasi has worked well, with the highest score of 4.376875 for SMKN 14.
Finding Nearest Mosque Using Haversine Formula on Android Platform Indah Setyorini; Desi Ramayanti
JOIN (Jurnal Online Informatika) Vol 4 No 1 (2019)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v4i1.267

Abstract

Prayer is the second pillar of Islam and it is emphasized after the two sentences of syahadat. It has been said that it’s as perfect and as good as worship. Prayer is one of the obligations for Muslims and must be done both for Mukimin and Musafir. The virtue of prayer in the mosque is the same as the value of 20 degrees of reward compared to prayer elsewhere. With the traffic jam phenomenon that is increasing due to heavy traffic. For someone who is traveling home in the afternoon before maghrib, some people are always confused to do Maghrib prayer because of the lack of information about the nearest mosque. The problem can be solved by finding the shortest path is a problem to find the minimum route from the starting point to the destination point with the shortest route. This research was made to design an application that provides direction to the nearest mosque in the area of Larangan, Tangerang city. In the making of this system to find the shortest path can be solved using the haversine formula and using the java programming language, where java is used to build applications while the database used is the MySQL database and the use of Google Maps API in determining the route.
Sistem Informasi Edukasi Sampah Dan Transaksi Keuangan Usaha Pengepul Berkah Barang Bekas Tri Damayanti; Desi Ramayanti
INFORMATION MANAGEMENT FOR EDUCATORS AND PROFESSIONALS : Journal of Information Management Vol 8 No 1 (2023): INFORMATION MANAGEMENT FOR EDUCATORS AND PROFESSIONALS (AGUSTUS 2023)
Publisher : Penelitian dan Pengabdian Masyarakat Universitas Bina Insani

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51211/imbi.v8i1.2507

Abstract

Sistem informasi edukasi sampah dan transaksi keuangan pada usaha pengepul berkah barang bekas merupakan solusi untuk meningkatkan efisiensi dan pengelolaan transaksi jual beli barang bekas. Penelitian ini menggunakan metode waterfall dalam tahapan analisis, perancangan, dan implementasi sistem. Tahap analisis dilakukan untuk mengidentifikasi kebutuhan pengguna dan pemangku kepentingan, serta menganalisis proses bisnis manual yang saat ini digunakan pada transaksi jual beli. Berdasarkan analisis tersebut, sistem informasi yang mencakup fitur registrasi dan login, transaksi pembelian dan penjualan dengan cetak kwitansi, serta fitur laporan transaksi dirancang untuk memudahkan proses bisnis. Implementasi sistem dilakukan setelah tahapan analisis dan perancangan selesai. Pengujian black box dilakukan untuk memastikan fungsi-fungsi sistem berjalan sesuai harapan. Hasil implementasi menunjukkan bahwa sistem informasi dapat berjalan dengan baik dan memberikan kemudahan dalam bertransaksi. Halaman beranda website, informasi edukasi, harga barang bekas, dan kontak lokasi menjadi tampilan awal saat membuka website. Pengguna dapat melakukan transaksi pembelian dan penjualan dengan mudah, serta mencetak kwitansi atau mengunggah kwitansi sesuai kebutuhan. Sistem informasi ini juga memberikan edukasi mengenai pengelolaan sampah dan pentingnya daur ulang. Dengan demikian, usaha pengepul berkah barang bekas dapat meningkatkan efisiensi operasional dan memberikan dampak positif terhadap lingkungan. Untuk pengembangan lebih lanjut, perlu dilakukan pengembangan fitur-fitur baru berdasarkan umpan balik pengguna. Dengan langkah-langkah tersebut, diharapkan sistem informasi ini dapat terus berkembang dan memberikan manfaat yang lebih besar bagi pengguna dan lingkungan sekitarnya.
Sistem Keamanan Perumahan Menggunakan Face Recognition Desi Ramayanti; Yuwan Jumaryadi; Daim Muhammad Gufron; Dio Dava Ramadha
TIN: Terapan Informatika Nusantara Vol 3 No 12 (2023): May 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/tin.v3i12.4145

Abstract

The residential environment system is a system that can be used to assist security officers and neighborhood residents to carry out environmental monitoring of crimes both coming from outside the environment and from the environment itself. This residential security system application uses the face recognition method carried out by residential security. The security system is an important point, which makes it the most important goal of researchers. Data collection methods used such as, observation, observation and literature study. The results of this study are to create a security system application using android-based facial recognition. The conclusion of this research is that this residential security system application is designed with simple systems and features to make it easier for users or users, with the Face Recognition method it makes it easier for security guards to carry out security for people who come out of housing, and the security system application is an application designed to help community and security officers so as not to lose the motorized vehicles of residential residents
Implementasi Metode Waterfall dalam Pengembangan Sistem Point of Sales dan e-Commerce Desi Ramayanti; Yuwan Jumaryadi; Aris Sunandar; Kolidi Kolidi
TIN: Terapan Informatika Nusantara Vol 4 No 2 (2023): July 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/tin.v4i2.4208

Abstract

Along with the development of technology, Micro, Small and Medium Enterprises need to adapt to technology in order to compete and also expand the market reach of selling their products. As for Micro, Small and Medium Enterprises, which still use manual methods in marketing their products, it is an obstacle in developing their business in the current digitalization era because of the difficulty in carrying out promotions and marketing. In today's digital era, E-Commerce applications are a solution for MSMEs to increase efficiency and effectiveness in their business. In developing the system carried out using the waterfall methodology. The waterfall methodology consists of communication, planning, modeling, construction, and implementation. Meanwhile, application design modeling uses Hyper Text Markup Language, Cascading Style Sheets, and Semantic UI to create an attractive appearance and is easy for users to use, and the Angular Framework which uses Typescript as its programming language and Firebase as a database. After the system is developed, it will be tested using black box testing. The system developed is able to provide easy access via the internet network, as well as increase the efficiency and effectiveness of product promotion and marketing processes and make it easier for store owners to view product sales report data
ANALISIS DAN PENINGKATAN KUALITAS LAYANAN PADA JARINGAN KOMPUTER NIRKABEL BADAN PENGHUBUNG LAMPUNG DALAM MENDUKUNG TUGAS PEMERINTAHAN: Bahasa Indonesia Desi Ramayanti; Syarifudin
JSAI (Journal Scientific and Applied Informatics) Vol 7 No 1 (2024): Januari
Publisher : Fakultas Teknik Universitas Muhammadiyah Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36085/jsai.v7i1.5529

Abstract

This study aims to evaluate the quality of internet network in Badan Penghubung Lampung using the TIPHON standard. The assessment is conducted by measuring several network performance parameters, including bandwidth, throughput, delay, and packet loss. The measurements are carried out for four days during office hours using the Axence Nettools 5 and speedtest.net applications. The collected data is then analyzed to obtain the average values for each parameter. The measurement results indicate that the overall quality of the internet network in Badan Penghubung Lampung is classified as very good. The average throughput value is 1,636 Kbps, which exceeds the TIPHON standard. The delay parameter has an average of 40.17 ms, which also meets the TIPHON standard. Meanwhile, the packet loss has an average of 2.75%, which is well below the maximum limit set by the TIPHON standard. However, this study also shows that the throughput value can be influenced by varying weather conditions, with the lowest data transfer speed occurring on the last day of the study. Therefore, for a more comprehensive evaluation of network quality, it is recommended to consider other parameters such as jitter, reliability, and availability.
Analisis Kualitas Jaringan Internet di Gedung Guntur: Studi Kasus pada Tenant Call Center PT Jasnita Telekomindo Thoriq Zibaltar; Desi Ramayanti
JSAI (Journal Scientific and Applied Informatics) Vol 6 No 3 (2023): November
Publisher : Fakultas Teknik Universitas Muhammadiyah Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36085/jsai.v6i3.5531

Abstract

This research aims to measure the quality of the internet network in Gedung Guntur, which is owned by PT Jasnita Telekomindo and houses a call center tenant. The staff of the call center have complained about the slow internet connection when inputting reports in the CRM system and making phone calls to customers. Therefore, this research is conducted to measure network parameters, such as throughput, delay, and packet loss, by implementing Quality of Service (QoS) on voice and CRM data. The measurement is performed using Axence Net Tools 5 software. The results of the testing show that the bandwidth parameter has a value of 3.086 Kbps, throughput has a value of 1.918 Kbps, delay has a value of 1 ms, and packet loss has a value of 0%. If these test results are compared with the TIPHON standard, the parameters achieve an index of 4, indicating excellent network quality. This research provides a clearer understanding of the quality of the internet network in Gedung Guntur and indicates that the network meets the TIPHON standard. The results of this research can be used as a basis for identifying necessary improvement or enhancement measures to improve the service quality in Gedung Guntur.
Model Extreme Gradient Boosting Berbasis Term Frequency (TFXGBoost) Untuk Klasifikasi Laporan Pengaduan Masyarakat Vina Ayumi; Desi Ramayanti; Handrie Noprisson; Yuwan Jumaryadi; Umniy Salamah
JSAI (Journal Scientific and Applied Informatics) Vol 6 No 1 (2023): Januari
Publisher : Fakultas Teknik Universitas Muhammadiyah Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36085/jsai.v6i1.6089

Abstract

Various algorithms and machine learning techniques are being applied to improve the efficiency and effectiveness of the process of automatically classifying complaint reports from the public in Indonesia. One machine learning algorithm that has recently gained benchmarks in the state of the art of various problems in machine learning is eXtreme Gradient Boosting (XGBoost). This study aims to develop an extreme gradient boosting model based on term frequency (TFXGBoost) to predict whether a text is classified as a complaint or not a complaint based on the data studied. Based on the experimental results, TFXGBoost achieved 92.79% accuracy with eta / learning rate hyperparameters of 0.5, gamma of 0, and max_depth of 3 and the computation time required to adjust the hyperparameters was 13870.012468 seconds.
Co-Authors Abdillah, Aditya Nur Abdul Wahab Nashir Ade Dwi Putra Amiroh Amiroh, Amiroh Anita Ratnasari Anrie Suryaningrat Anrie Suryaningrat Apriani, Ari Aprianto, Aditya Dwi Ardianto, Darmawan Aris Sunandar Armita Athennia Asyifah, Nurul Ayumi, Vina Badru Salam Bathin, Muhammad Sholeh Bias Yulisa Geni Borneo Satria Pratama C Achmad Fahrudin Christian Hovel Simanjuntak Cofely, Chinoble Daim Muhammad Gufron Dariato, Eri Dianing Asri, Sri Diky Firdaus Dio Dava Ramadha Dion Sakti, Arman Elvaresia, Meysiel Faishal, Imam Ibnu Frianto, Dody Gatsu, Puspita Glen Maxi Taberima Glen Maxie Taberima Hadi, Solihul Hariyanto Aditya Ramadhan Hutapea, Natalia Ida Nurhaida Imam Nududdin Indah Setyorini Jalaludin, Jalaludin Juliansyah, Yahya Maulana Jumaryadi, Yuwan Kartika, amalia Kolidi Kolidi Komarudin Komarudin Komarudin Lionie Lionie M.Rizky Alfariz Maula Thoman Sihotang Maulana, Ivan Mohammad Bakhriansyah Muhamad Sony Pratama Muhammad Hanafi MUHAMMAD RIZAL Mulya, Imam Mustofa, Achmmad N Narsih Nelly Al Audhah Noprisson, Handrie Nur Ani Panji Pratama Kurniawan Priyanto, Mei Rendy Purnama, Giri Ramadhan, Hariyanto Aditya Robby Cahyadi Rony, Zahara Tussoleha S Saniah Sabar Rudiarto Salamah, Umniy Samuel Aras Michael Saputra, M Julius Saputra, Vega Sarwati Rahayu SEPTIANITA Setyorini, Indah Shadiqi , Muhammad Abdan Shintya Dewi, Marysca Sri Andriati Asri Sri Dianing Asri Suryaningrat, Anrie Susanto, Dwi Andrian Syarifudin Thoriq Zibaltar Tri Damayanti Wawan Gunawan Weni Indri Yanti Widyadi Setiawan Y. Erning Indrastuti YOHANA TRI UTAMI, YOHANA TRI yulisa geni, bias Zoelkarnain, Izaak