Claim Missing Document
Check
Articles

Found 24 Documents
Search

PERANCANGAN DAN IMPLEMENTASI JARINGAN RADIUS DI PUSKESMAS BANJIT Deni; Firmansyah, Firmansyah
CONTEN : Computer and Network Technology Vol. 3 No. 2 (2023): Desember 2023
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/conten.v3i2.2730

Abstract

Along with the development of technological advances nowadays, it is very useful for us in looking for information that is fast, precise and accurate in everyday life, especially in helping us complete our work. With the existence of a computerized system, it is hoped that it can help us with all the work that is difficult to do. becomes easy to do in order to get better results than before, Banjit Community Health Center. It requires a lot of overhaul of the network structure that supports and provides satisfactory services for community health center internet users. For this reason, the author wrote this thesis regarding internet network design, currently the Banjit Community Health Center is still using repeaters to spread the internet network throughout the community health center area and using WPA/WPA2 security so that the internet network at several points of the Community Health Center is less stable and feels slow for some users, by using The network design proposed by the author can improve the quality of the internet network at the Banjit Community Health Center.
PERBANDINGAN ALGORITMA SUPPORT VECTOR MACHINE DAN RANDOM FOREST UNTUK ANALISIS SENTIMEN ISU IJAZAH PALSU JOKO WIDODO DI MEDIA SOSIAL X Deni; Musthofa, Roki Fatih; Herfiana, Hanum Surya; Sari, Betha Nurina
Jurnal TIMES Vol 14 No 2 (2025): Jurnal TIMES
Publisher : STMIK TIME

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Media sosial, khususnya X, telah menjadi ruang diskusi publik yang aktif dalam membahas berbagai isu sosial dan politik. Salah satu isu yang menimbulkan banyak perdebatan adalah dugaan ijazah palsu milik Presiden Joko Widodo. Penelitian ini bertujuan untuk menganalisis sentimen pengguna X terhadap isu tersebut serta membandingkan performa dua algoritma klasifikasi, yaitu Support Vector Machine (SVM) dan Random Forest. Proses analisis diawali dengan pengumpulan data menggunakan teknik scraping, diikuti tahap pra-pemrosesan, pelabelan data secara manual, ekstraksi fitur menggunakan TF-IDF, serta penyeimbangan data dengan SMOTE untuk mengatasi ketidakseimbangan label. Dari total 1.783 komentar yang terkumpul, ditemukan 1.661 komentar negatif dan 122 komentar positif. Setelah diterapkan SMOTE, distribusi data menjadi seimbang dengan total 3.322 data. Hasil pengujian pada beberapa skenario menunjukkan bahwa algoritma SVM mencapai akurasi tertinggi sebesar 100%, sementara Random Forest juga memberikan performa sangat baik dengan akurasi mencapai 99,24%. Temuan ini menunjukkan bahwa SVM lebih unggul dalam mengklasifikasikan sentimen teks pada isu sensitif di media sosial, khususnya ketika data telah melalui proses penyeimbangan menggunakan SMOTE.
UJI CITA RASA KOPI LOKAL ROBUSTA (Coffea canephone) FERMENTASI GUNUNG SINDORO, GUNUNG SUMBING, DAN ROWO SENENG Deni; Widata, Sri; Arnanto, Driska
Journal of Industrial Engineering & Technology Innovation Vol. 3 No. 2 (2025): Journal of Industrial Engineering & Technology
Publisher : LENVARI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61105/jieti.v3i2.337

Abstract

The research aims to determine the results of the taste test of local robusta coffee fermented from Mount Sindoro, Mount Sumbing, and Rowo Seneng. This research was conducted from 19 September to 31 October 2024, to carry out organoleptic tests. This research was carried out in the Integrated Laboratory of Bachelorwiyata Tamansiswa University, Yogyakarta. This research method uses a factorial Complete Randomized Block Design (RAKL), where the first factor is the origin of the Robusta Coffee (Mount Sindoro, Mount Sumbing, and Rowo Seneng) and the second factor is the fermentation time (2 weeks, 3 weeks and 4 weeks). Organoleptic data were analyzed using analysis of variance (ANOVA), while Robusta coffee was evaluated through a hedonic sensory test using a hedonic scale from 1 (not liked) to 5 (very liked). The results of the research show that there is a difference in gamification (Pr < 0.01) between the origin of Robusta coffee and the length of fermentation of Robusta coffee and organoleptics which show a significant difference, namely the taste and texture are not significantly different, with this number showing that there is a high level. Origin of Robusta coffee and fermentation time with organoleptic tests which show the interaction of aroma and color by showing the highest numbers. In conclusion, there is no interaction between the origin of the robusta coffee location and the fermentation time on taste and texture, whereas there is an interaction between the origin of the robusta coffee and the fermentation time on the aroma and color.
Penentuan Pencemaran Air Menggunakan Metode Self Organizing Maps (SOM) Deni; Midyanti, Dwi Marisa; Hidayati, Rahmi
The Indonesian Journal of Computer Science Vol. 11 No. 1 (2022): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v11i1.3036

Abstract

Water pollution is the entry of a component or substance into water, which causes water quality to decrease. The decrease in water quality causes the water to be unfit and affects the community's health. Therefore, an application for determining the water quality level building using the SOM algorithm with several data input parameters: Fluoride, Hardness, and Nitrite. These parameters use for data clustering in determining clean and polluted water. The SOM algorithm arranges SOM neurons based on the data input values ​​in a SOM cluster. For testing the SOM method on 114 data, the Silhouette Coefficient value was used to find the best number of clusters. Silhouette Coefficient will evaluate clustering the proximity of the distance between data. The test was carried out 27 times with variations of the experiment with the learning rate starting from 0.1 to 0.9 and the number of clusters from 2 to 4 to get the best Silhouette Coefficient value. The result of clustering the best silhouette coefficient value obtained is 0.7276473444141 with 3 clusters and the learning rate of 0.2.