Claim Missing Document
Check
Articles

Found 4 Documents
Search

A HYBRID RECOGNITION METHOD THROUGH VIDEO SURVEILLANCE USING COMBINED HARRIS-EDGE Indrabulan, Tantri
Patria Artha Technological Journal Vol 2, No 1 (2018): Patria Artha Technological Journal
Publisher : Department of Electrical Engineering, University of Patria Artha

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (7.612 KB) | DOI: 10.1234/patjou.v2i1.131

Abstract

This paper discuss Intelligent Transportation System (ITS) which is incorporated with computer vision techniques in recognition of vehicles for typical fast growth cities in development countries. Two algorithm are combined i.e. Harris and Edge Prewitt to increase accuration of vehicles’ detection. Verification is conducted using Support Vector Machine (SVM) and Histograms of Oriented Gradiens (HOG) as its descriptor. Six pieces of experimental videos from a wide variety of road conditions are used for processing. It shows that  percentage average for sensitivity is 75.73%, specificity 90.1% precision 56.0% and with accuration of 77.73%.
Rancang Bangun Smart Robot Omni Wheel sebagai Permainan Edukatif dan Interaktif bagi Balita Muhammad Nur; Tantri Indrabulan
PROtek : Jurnal Ilmiah Teknik Elektro Vol 8, No 1 (2021): PROtek : Jurnal Ilmiah Teknik Elektro
Publisher : Program Studi Teknik Elektro Universitas Khairun

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33387/protk.v8i1.2520

Abstract

The purpose of this research is to produce a smart robot prototype that is able to attract toddlers' attention so that they can respond in the form of motor movements. The making of smart robots will be adjusted to the needs of toddler stimulation in the form of movement interactions approaching or away from objects so that toddlers are triggered to chase or avoid the robot. Educational games that are designed appropriately for toddlers can improve their motor development. This can occur due to stimulating activities from educational games that can stimulate the toddler's brain. Smart robots are one of the educational game technology products that apply the concept of the industrial revolution 4.0. The smart robot prototype design will use the Arduino Mega microcontroller. The microcontroller input is obtained from a proximity sensor that is implanted in the robot's body. The essence of the smart robot in this study is a dynamic and very flexible robot movement caused by the use of the omni wheel as a driving wheel.
Algoritma Interest Point dalam segmentasi citra objek kendaraan Tantri Indrabulan; Irwan Syarif
PROtek : Jurnal Ilmiah Teknik Elektro Vol 7, No 1 (2020): PRotek : Jurnal Ilmiah Teknik Elektro
Publisher : Program Studi Teknik Elektro Universitas Khairun

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33387/protk.v7i1.1353

Abstract

Penelitian ini mengumpulkan data berupa gambar dan video yang berisi objek kendaraan di lalu lintas. Data tersebut kemudian akan diproses menggunakan  algoritma pengolahan citra dan dikombinasikan dengan algoritma kecerdasan buatan. Penelitian ini akan difokuskan pada pengolahan citra berbasis algoritma hibrid Interest Point jenis Harris yang dapat mengoptimasi segmentasi citra objek. Proses tersebut dilakukan sebab segmentasi citra objek merupakan faktor utama yang mempengaruhi hasil dari sistem. Pada akhirnya sistem akan dirancang untuk menghasilkan informasi baru sesuai dengan alur sistem yang didasarkan pada kebutuhan, antara lain: pengenalan kendaraan, pengklasifikasian kendaraan, perhitungan jumlah kendaraan, dan pergerakan kendaraan.
KLASIFIKASI SAMPAH PLASTIK BERDASARKAN KEPAKARAN AHLI MENGGUNAKAN METODE K-NEAREST NEIGHBOR Tantri Indrabulan; Herlina Herlina
Ainet : Jurnal Informatika Vol 4, No 1 (2022): Maret (2022)
Publisher : Universitas Muhammadiyah Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26618/ainet.v4i1.9136

Abstract

Bank Sampah yang ada di Kabupaten Polewali Mandar merupakan salah satu solusi dalam penanganan masalah sampah. Namun dalam prosesnya, terkhusus pada sampah plastik, Bank Sampah tersebut belum mampu membedakan berbagai jenis plastik yang sebenarnya memiliki variasi nilai jual. Oleh karena itu diterapkan kepakaran ahli ke dalam sebuah sistem yang mampu mengklasifikasi sampah plastik berdasarkan jenis karakteristik plastik yang diinput. Adapun metode yang diadaptasi ke dalam sistem ialah metode K-Nearest Neighbour (KNN). Untuk mengetahui kinerja sistem, pengujian dilakukan melalui 3 metode yaitu metode Cross Tabulation, Classification Metrics, dan Cross Validation. Dari hasil pengujian diperoleh tingkat akurasi KNN terhadap data testing sebesar 88%