Claim Missing Document
Check
Articles

Found 24 Documents
Search

Pelatihan Internet Of Things (IoT) Untuk Meningkatkan Kompetensi Digital Siswa Di Smk Negeri Jorlang Hataran Perangin Angin, Despaleri; Gultom, Togar Timoteus; Sitanggang, Delima; Yennimar, Yennimar; Prabowo, Agung; Siregar, Saut Dohot; Ridwan, Achmad; Ginting, Riski Titian; HS, Christnatalis; Manday, Dhanny Rukmana
Jurnal Pengabdian kepada Masyarakat Politeknik Negeri Batam Vol. 7 No. 1 (2025): Jurnal Pengabdian kepada Masyarakat Politeknik Negeri Batam
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/abdimaspolibatam.v7i1.10114

Abstract

The purpose of this community service activity is to enhance digital competency skills at SMK Negeri I Jorlang Hataran. The method used in the implementation of this activity is training through the delivery of materials, practical training on the assembly and programming of IoT devices, and a question-and-answer session. The participants of this activity consist of 37 students from the 11th grade RPL (Software Engineering) major. The instruments used in this activity include participant feedback and activity documentation. The results of the implementation show that the participants' responses to the basic computer training were overall in the good category. The percentage of student responses reached 98.20%, which falls into the very good category.
Comparison of K Nearest Neighbor Algorithm with Apriori Algorithm to Analyze Lifestyle Patterns in Hypertensive Patients Steven, Steven; Wijaya, Ricky; Yawin, Helbert; Siregar, Saut Dohot
Jurnal Indonesia Sosial Teknologi Vol. 5 No. 6 (2024): Jurnal Indonesia Sosial Teknologi
Publisher : Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59141/jist.v5i6.1134

Abstract

Hypertension is one of the most influential cardiovascular diseases that can lead to organ disorders such as heart dysfunction or stroke and hypertension is often discovered by chance. This disease can interfere with the work of other organs if left untreated, especially the heart and kidneys. Not paying attention to diet, exercise, stress, smoking, and drinking alcohol can all be causes of increased risk of hypertension. To predict people with hypertension and find out the comparison of behavior and lifestyle patterns with hypertension patients using a priori algorithm in the case study of Sei Semayang Health Center. So the results of rapidminer use the apriori algorithm to analyze the Comparison of K the nearest Neighbor Algorithm with the apriori Algorithm to Analyze Lifestyle Patterns in Hypertensive Patients the results obtained is U1 which means there are people with hypertension aged 25-38 years who have more hypertension and the results are H2 which means that people have but do not control to the doctor with a pattern style such as consuming alcohol, Smoking, and lack of exercise, sugar consumption, consumption of saturated fat and foods that contain a lot of salt and rarely consume vegetables or fruits and foods containing MSG then more and more people who have hypertension with an unhealthy lifestyle.
Implementation of the YOLO Method for Detection of Human Emotions Based on Facial Mimics Felison, Thomas; firtan, Erwin conery; Steven, Steven; Chandra, Willyam; Siregar, Saut Dohot
Jurnal Indonesia Sosial Teknologi Vol. 5 No. 10 (2024): Jurnal Indonesia Sosial Teknologi
Publisher : Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59141/jist.v5i10.1196

Abstract

Emotion detection through facial expression recognition plays an important role in everyday life, such as how to respond correctly to emotional expressions in social interactions, so that you can establish and build verbal or nonverbal communication with other people and so on. Facial expressions are facial changes in response to a person's emotional state, intentions, or social communication. Face detection is the first step that must be taken in facial analysis, including facial expression recognition. There are many methods that can be used to carry out the face detection process, such as the YOLO method. This YOLO method reframes object detection as a single regression problem, directly from image pixels to bounding box coordinates and class probabilities. By using the YOLO method, the process only needs to look once at the input image, to predict what objects are in the image and where those objects are. Based on the results of the tests carried out, the YOLO method can be used to detect human facial expressions with a success rate of 80%, with neutral, surprise and disgust facial expressions having a good level of accuracy and fear facial expressions having a poor accuracy level. The YOLO method is able to detect facial expressions of humans who wear accessories such as glasses.
Rancang Bangun IoT Otomatis Berbasis Sensor PIR untuk Menghemat Energi Listrik pada saat Ruangan Kosong Okman Tampubolon, Juan Renhard; Ramadan, Wahyu; Buulolo, Julianus; Purba, Piona Pricilia; Siregar, Saut Dohot
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 6 No. 4 (2025): Juni 2025
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v6i4.8805

Abstract

Pemakaian listrik yang tidak efisien, terutama dari lampu yang menyala di ruangan kosong, menyumbang sekitar 30% pemborosan energi di sektor rumah tangga, perkantoran, dan industri menurut Kementerian Energi dan Sumber Daya Mineral Indonesia. Penelitian ini merancang sistem otomatisasi lampu berbasis Internet of Things (IoT) menggunakan sensor PIR (Passive Infrared) dan mikrokontroler Arduino untuk mendeteksi keberadaan manusia. Sistem ini akan mengaktifkan atau mematikan lampu secara otomatis berdasarkan aktivitas di dalam ruangan, sehingga mampu menghemat konsumsi energi listrik. Studi dilakukan di ruang kelas dan laboratorium Universitas Prima Indonesia dengan menganalisis pola penggunaan energi. Hasil pengujian menunjukkan bahwa sistem mampu merespons gerakan dalam ±2 detik, mengurangi konsumsi energi hingga 30–50% tergantung kondisi ruangan. Penelitian ini juga mengisi celah dari studi sebelumnya yang belum mengintegrasikan pemantauan real-time dan fitur override manual. Dengan penggunaan sensor PIR yang lebih akurat dibandingkan sensor cahaya (LDR), sistem ini mendukung efisiensi energi yang lebih adaptif dan berkelanjutan. Rancang bangun ini berpotensi diterapkan luas dalam lingkungan akademik maupun industri.