Article Per Year (5 Year)
p-Index From 2021 - 2026
0.882
P-Index
This Author published in this journals
All Journal JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH) JPM: JURNAL PENGABDIAN MASYARAKAT EXPLORER
Haida Dafitri
Universitas Harapan Medan, Medan
Aerospace Engineering Humanities Astronomy Computer Science & IT Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Environmental Science Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Materials Science & Nanotechnology Medicine & Pharmacology Public Health Social Sciences Transportation Other

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
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

Abstract

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.
Pemanfaatan Augmented Reality Sebagai Media Pengenalan Atribut TNI Angkatan Darat Berbasis Android Rachmat Edy; Haida Dafitri; Septiana Dewi Andriana
Journal of Information System Research (JOSH) Vol 4 No 1 (2022): October 2022
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (618.973 KB) | DOI: 10.47065/josh.v4i1.2391

Abstract

Augmented Reality is an activity that combines the appearance of virtual and real objects (objects) in real life and at that time will also display 3D objects that we want to see in real time. The process of combining virtual and real objects using technology that continues to develop rapidly in the world of design, interactivity is aimed at the input devices needed to support the goals to be achieved. Augmented reality technology at the Indonesian Army Attributes application is an application that uses the Markerless method with the Pattern Matching technique to display augmented reality 3D objects at the Indonesian Army Attributes. This application system can help users, especially prospective students (cassis) to make it easier for prospective students (casis) to achieve their goals of becoming an Indonesian Army Soldier, starting from the recruitment level and selection of units on duty. This technology can guide users to directly view 3D Indonesian Army Attributes objects without having to browse, not to mention network constraints when accessed, which takes longer. This application system is based on Android and can be accessed and used offline.
Pemanfaatan Produksi Pakan Mandiri untuk Meningkatkan Efisiensi Usaha Budidaya Ikan Nurjamiyah Nurjamiyah; Haida Dafitri; Zaharuddin Zaharuddin; Kalvin Chiuluto; Sumi Khairani; Lisa Adriana
JPM: Jurnal Pengabdian Masyarakat Vol. 7 No. 1 (2026): July 2026
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/jpm.v7i1.3262

Abstract

Feed costs are the largest component in fish farming businesses, accounting for more than 60% of total production costs. This condition is also experienced by fish farmer groups in Patumbak Village, Deli Serdang Regency, which still depend on commercial feed, resulting in high operational costs and reduced profits. On the other hand, the area has local resources that can be utilized as alternative feed ingredients, one of which is chicken feather waste, which contains a high protein content. However, the limited knowledge and skills of the partners in producing self-made feed have become the main obstacle to utilizing this potential. This community service program aimed to improve the knowledge and skills of fish farmer groups in producing self-made feed based on chicken feather waste to enhance the efficiency of fish farming businesses. The partner of this activity was a fish farmer group managed by Mr. Denianto in Patumbak Village, Deli Serdang Regency. The implementation methods included socialization, self-made feed production training, feed production practice, mentoring, and evaluation. The results showed an improvement in participants’ knowledge and skills regarding feed formulation and self-made feed production. The partners were able to utilize chicken feather waste as an alternative feed ingredient, thereby reducing their dependence on commercial feed. Furthermore, the program had a positive impact on production cost efficiency, strengthened group collaboration, and encouraged more environmentally friendly utilization of livestock waste. This program is expected to support the sustainability of fish farming businesses and improve the welfare of fish farming communities in Deli Serdang Regency.
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 | DOI: 10.47065/explorer.v2i1.148

Abstract

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.
Co-Authors Kalvin Chiuluto Lisa Adriana Muhammad Farhan Syahaf Nasution Nurjamiyah, Nurjamiyah Rachmat Edy Rahman, Sayuti Septiana Dewi Andriana, Septiana Dewi Sumi Khairani Zaharuddin Zaharuddin