Articles
Pengembangan Convolutional Neural Network untuk Klasifikasi Ketersediaan Ruang Parkir
Sayuti Rahman;
Haida Dafitri
Explorer Vol 2 No 1 (2022): Januari 2022
Publisher : Forum Kerjasama Pendidikan Tinggi
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (357.099 KB)
|
DOI: 10.47065/explorer.v2i1.148
Information on the availability of parking spaces is needed for drivers. Drivers walking around looking for parking spaces have negative impacts, including traffic jams, waste of fuel, increasing pollution and even causing driver panic. Classification of parking spaces properly and quickly becomes a solution to present information on the availability of parking spaces. Based on the technology used, parking space classification usually uses sensors or computer vision. However, computer vision is lower in cost usage because a single camera can classify multiple parking spaces simultaneously. Convolutional Neural Network (CNN) is a popular method in dealing with vision problems. mAlexnet is one of the CNN architectures that has succeeded in classifying parking spaces well, but its accuracy still needs to be improved. A better architecture of mAlexnet needs to be made to improve classification accuracy and speed. In this study, we designed a CNN architecture named ParkingNet. Based on testing using sub-dataset camera B from the CNRPark dataset, ParkingNet is better than mAlexnet, both in terms of accuracy, the number of parameters, and FLOPs. ParkingNet managed to outperform mAlexnet's accuracy by 0.68%. Although not significant, ParkingNet is faster in classification due to the smaller number of parameters and FLOPs. The number of ParkingNet parameters is 4/5 mAlexnet parameters and the number of ParkingNet FLOPs is 2/5 mAlexnet. ParkingNet can be implemented in a smart parking system to classify parking spaces with lower computational costs.
Pelatihan Pembuatan Vidio Menggunakan Adobe Premier dan Adobe Affter Effects di SMK Telkom Sandhy Shandy Putra
Fera Damayanti;
Munjiat Setiani Asih;
Sayuti Rahman
Prioritas: Jurnal Pengabdian Kepada Masyarakat Vol 2 No 02 (2020): EDISI SEPTEMBER 2020
Publisher : Universitas Harapan Medan
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35447/prioritas.v2i02.251
Sekolah Menengah Kejuruan Telkom Sandhy Putra Medan adalah salah satu sekolah SMK dalam bidang Telekomunikasi dan Teknik Informatika yang didirikan pada tahun 1992. SMK Telkom Sandhy Putra beralamat di jalan Jamin Ginting KM. 11,1 No.9 C Kwala Bekala, Medan Johor Simpang Selayang Kecamatan Medan Tuntungan Kota Medan Sumatera Utara. Perkembangan internet juga sangat dirasakan oleh siswa-siswi SMK Telkom Medan. Rata-rata siswa dan siswi menggunakan internet untuk mencari materi pelajaran, bermain sosial media ataupun bermain game. Di tahun 2019 Youtube telah mencatat rekor terbaru dengan jumlah pengunjung terbanyak setiap bulannya dan jumlah ini akan terus meningkat setiap tahunnya. Tidak dipungkiri menjadi Youtuber merupakan pekerjaan yang dicita-citakan setiap anak remaja zaman sekarang, karena penghasilan Youtuber yang besar. Salah satu skill yang harus dimiliki Youtuber adalah keahlian dalam mengedit video. Yang menjadi kebanyakan masalah yang ada adalah kurangnya kepahaman menggunakan software editing video. Dalam pengeditan video sebenarnya dapat menggunakan software Adobe Premier dan Adobe After Effect yang dikembangkan oleh adobe system. Adobe Premier dan Adobe After Effect dapat membantu siswa- siswi SMK Telkom Medan yang ingin membuat video yang menarik dengan mudah.
Model Efektif Pembelajaran Daring di Masa Pandemi
Risko Liza;
Sayuti Rahman;
Arnes Sembiring;
Tengku Mhd Diansyah;
Haida Dafitri
Prioritas: Jurnal Pengabdian Kepada Masyarakat Vol 3 No 01 (2021): EDISI MARET 2021
Publisher : Universitas Harapan Medan
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35447/prioritas.v3i01.371
Meningkatnya jumlah pasien covid-19 di dunia, khususnya di Indonesia, menyebabkan perubahan kebijakan di Indonsia. Pandemi covid-19 juga menyebabkan sistem belajar mengajar di Indonesia berubah dari luring menjadi daring. Di perguruan tinggi, perubahan ini menimbulkan beberapa kendala dalam melakukan adaptasi baik dari dosen maupun perserta didik yakni mahasiswa. Untuk itu perlu ada pelatihan dan pembelajaran serta diskusi mengenai problematika ini. Sehingga tercapai tujuan belajar mengajar yang semestinya. Fakultas Syariah dan Hukum UINSU mengundang tim pengabdian masyarakat dari Prodi Teknik Informatika UNHAR sebagai narasumber serta memberi solusi dalam kegiatan belajar dimasa pandemi. Kami dari tim pengabdian masyarakat menyajikan solusi diantaranya tentang komunikasi yang baik melalui media ajar, meninjau keaktifan mahasiswa serta memberi pemahaman dalam penggunaan aplikasi yang disediakan oleh Google seperti Classroom, email, youtube, Drive, Meet daln lain sebagainya susai perkembangan dalam diskusi
Analisis Klasifikasi Mobil Pada Gardu Tol Otomatis (GTO) Menggunakan Convolutional Neural Network (CNN)
Sayuti Rahman;
Adinda Titania;
Arnes Sembiring;
Mufida Khairani;
Yessi Fitri Annisah Lubis
Explorer Vol 2 No 2 (2022): July 2022
Publisher : Forum Kerjasama Pendidikan Tinggi
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47065/explorer.v2i2.286
The concept of a smart city is the most important issue in the development aspect of big cities in the world. Where the city must promise a more comfortable, organized, healthy and efficient life. Smart transportation is part of a smart city that is useful for improving better urban planning. Smart transportation also applies to toll roads, such as automating toll road retribution payments. Automatic Toll Gate (GTO) in Indonesia still uses sensors. However, sensors often misclassify trailers. In addition, the use of sensors also requires additional costs in installation and maintenance. Currently, every toll gate is equipped with cameras for various purposes. By utilizing the camera for vehicle type classification, the cost of the GTO will be reduced. For this reason, utilizing a digital camera with computer vision for vehicle type classification is the solution. Convolutional Neural Networks (CNN) is the most popular technique today in solving computer vision problems. Exploit the existing CNN by replacing the last fully connected output according to the number of vehicle classes. The test results show that mobilenet V2 is better in the classification of vehicle types, the best accuracy is Alexnet 93.81% and Mobilenet 96.19%. Computer vision by utilizing CNN is expected to replace the use of sensors so that implementation costs are cheaper.
Aplikasi untuk Menghitung Estimasi Biaya Pembuatan Pagar Besi dengan Cepat
Sayuti Rahman;
Suriati Suriati;
Risko Liza;
Arnes Sembiring;
Muhammad Zen
Prioritas: Jurnal Pengabdian Kepada Masyarakat Vol 4 No 02 (2022): EDISI SEPTEMBER 2022
Publisher : Universitas Harapan Medan
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35447/prioritas.v4i02.603
Kurangnya lowongan pekerjaan memberi dampak negatif bagi masyarakat Indonesia. Seorang dengan keahlian dan pendidikan rendah akan tersisih dari persaingan untuk mendapatkan pekerjaan yang layak. Tidak sedikit dari mereka mengambil jalan pintas untuk memenuhi kebutuhan hidup. Hal ini mengakibatkan terjadinya pencurian, begal dan sejenisnya. Dampak negatif ini sangat mempengaruhi kehidupan masyarakat dengan berkurangnya rasa aman, terutama di rumah. Demi menjaga keamanan linkungan, masyarakat bahu membahu mengadakan perangkat keamanan seperti satpam dan CCTV. Namun itu belum cukup untuk menghilangkan rasa tidak aman di masyarakat. Banyak masyarakat menambah pagar pada rumah mereka agar merasa lebih aman, sekaligus memberi keindahan. Kebutuhan masyarakat dan pengusaha untuk menghitung estimasi biaya pembuatan pagar sangat dibutuhkan. Oleh karena itu, kami bekerjasama dengan pengusaha untuk membuat form hitung cepat biaya pembutan pagar menggunakan MS Excel. Berdasarkan model dan aplikasi yang dibuat, masyarakat dan pengusaha dapat menghitung estimasi harga dengan cepat dan tepat. Aplikasi ini juga mudah digunakan dan bisa dibuka pada perangkat smart phone.
Rancang Bangun Prototype Sistem Keamanan Rumah Dan Monitoring Peralatan Listrik Dengan Sms Gateway Dan Validasi Telepon
Fiqi Arfian;
Ade Zulkarnain Hasibuan;
sayuti rahman
SNASTIKOM Vol. 1 No. 01 (2022): SEMINAR NASIONAL TEKNOLOGI INFORMASI & KOMUNIKASI (SNASTIKOM) 2022
Publisher : Unit Pengelola Jurnal Universitas Harapan Medan
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (575.589 KB)
Advanced technology has many benefits for its users. One way to protect the home by utilizing home securitysystem technology. Fire and theft are major problems that must be considered in home security. Several factorsfor the occurrence of fires and theft in the house are due to the negligence of the owner of the house itself and thedelay in handling and prevention. Incidents like this can result in material losses and even fatalities. Therefore,the purpose of this research is to create a tool that can monitor security and home electrical equipment at anytime by using Arduino as a medium of information that will be sent via short SMS messages and phone calls. Thisdevice can also control home electrical appliances remotely automatically with SMS commands. The test resultsshow that this system can provide accurate information to homeowners and can monitor security and homeelectrical equipment.
Pengamanan Kendaraan Roda Dua Berbasis IoT Menggunakan Aplikasi Telegram
Muhammad Rizky Irwansyah;
sayuti rahman;
Arnes Sembiring
SNASTIKOM Vol. 1 No. 01 (2022): SEMINAR NASIONAL TEKNOLOGI INFORMASI & KOMUNIKASI (SNASTIKOM) 2022
Publisher : Unit Pengelola Jurnal Universitas Harapan Medan
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
In today's modern era, two-wheeled vehicles have become a basic necessity. Almost all people use two-wheeledvehicles for their daily needs. It is easy to use and relatively inexpensive to maintain, which is why many peopleuse it. Along with the increase in the number of two-wheeled vehicles, the crime of theft of two-wheeled vehiclesis also increasing. Therefore we need additional security that is better and more sophisticated on the two-wheeledvehicle itself. One of the technological developments for securing two-wheeled vehicles can now be doneautomatically using Wemos D1 and can be accessed using an Android device, namely telegram. Internet of Things(IoT) is one of the technologies that can be applied to help fulfill the security system. IoT is needed to designsecurity devices on two-wheeled vehicles, by using the telegram application to turn on two-wheeled vehiclesaccording to orders from the owner. LM2596 stepdown is required to lower the motor battery (battery) voltage tosystem voltage. Two-wheeled vehicles that have been installed with this tool can later be turned on or off via thetelegram application and can only be operated by the owner.
Chroma Key untuk Mengubah Warna Pakaian dengan HSV dan Morfologi pada Citra Digital
Sayuti Rahman;
M F Verri Anggriawan;
Rosyidah Siregar;
Siti Sundari;
Kharunnisa Kharunnisa;
Muhammad Zen
JURIKOM (Jurnal Riset Komputer) Vol 9, No 6 (2022): Desember 2022
Publisher : STMIK Budi Darma
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30865/jurikom.v9i6.5164
Currently, Indonesia is still under the influence of the COVID-19 virus. Indonesian people buy necessities of life on the online market. Clothing is a daily necessity that people often buy online. This has an impact on increasing online clothing sales, but not all clothes are according to the tastes of buyers. Therefore we need an application that is used to speed up changing the color of clothes according to the needs of buyers. The chroma key application that is used to change the color of the clothing image uses the HSV and morphology classification methods. Edge detection and median filters are used to improve the quality of color shift results with HSV. This application is built using MatLab 2015a programming. The test results show that the HSV classification method is better at changing the color of the clothing image than the morphological method. The HSV classification method was successful in changing the color of clothes well with a 100% success rate. While the morphological method succeeded in changing the color of the clothes with a success rate of 60%.
Sistem Pendukung Keputusan Pemilihan Siswa Study Tour Menggunakan Metode TOPSIS
Muhammad Zen;
Supiyandi Supiyandi;
Chairul Rizal;
Sayuti Rahman;
Irwan Irwan
JURIKOM (Jurnal Riset Komputer) Vol 9, No 6 (2022): Desember 2022
Publisher : STMIK Budi Darma
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30865/jurikom.v9i6.5152
Study tour activities are as a means of learning while recreation for teachers, students and course administrators. This recreational trip while studying is held every year and requires good preparation. For students who wish to take part in the study tour, a selection stage is carried out. In this study, the selection used a decision support system using the TOPSIS method (Technique For Others Reference by Similarity to Ideal Solution). This method consists of several steps that are easy to implement. In this method, there is no special calculation for weights. The weight is determined based on the analysis of all parties involved in developing the system. This system is expected to be able to select students properly through the attributes used, namely achievement, health, files and budget capabilities. Some assessments are carried out by interviews conducted by the course admin. The data is then processed as input to a decision support system. The system was developed using the PHP programming language and MySQL database. Some of the features or menus contained in it are home, alternative data, ratings, rankings and weights. These features are designed so that the system is easy to use. This research resulted in a selection system that makes it easier for administrators to determine students who take part in the study tour. Decision support systems simplify student data collection and topsis method calculations. The value of each criterion can be calculated quickly by the system. The weight used can be changed through the system. Recommendations for students to take part in the study tour can be seen in the ranking menu in the system in order. The system can be used annually in selecting study tour students
Identifikasi Kematangan Buah Menggunakan Metode Gray Level Co-occurence Matrix pada Citra Digital
Arnes Sembiring;
Sayuti Rahman;
Mufida Khairani;
Ilham Faisal;
Sri Eka Riyani Harahap;
Muhammad Zen
JURIKOM (Jurnal Riset Komputer) Vol 9, No 6 (2022): Desember 2022
Publisher : STMIK Budi Darma
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30865/jurikom.v9i6.5163
In the current era of information technology, the use of images is widely applied in various aspects of life. Some of the uses of image processing include the fields of military, medicine, education, agriculture and so on. One example of the use of image processing that will be discussed in this study is in the agricultural sector. Farmers can take advantage of technology in selecting fruit with the appropriate maturity level. In terms of selecting fruit based on the level of maturity, some fruit farmers still use the conventional method or with the human sense of sight, namely the eye. Therefore, this study was conducted for preliminary research that can change the conventional method into system that uses technology that makes a computerized way of identifying fruit maturity levels. The system that will be used to identify fruit maturity uses the Gray Level Co-occurance Matrix method on digital images and Euclidean Distance as a classification method. This application is built using MatLab 2019a programming. The test results show that the Gray Level Co-occurance Matrix and Euclidean Distance methods can be used to identify the ripeness of guava, oranges, bananas, papayas and mangoes into three categories, namely raw, unripe and ripe. The Gray Level Co-occurance Matrix and Euclidean Distance classification methods succeeded in identifying fruit maturity with an overall success rate of 87%.