Claim Missing Document
Check
Articles

Found 8 Documents
Search

OPTIMALISASI DETEKSI TEPI DENGAN METODE SEGMENTASI CITRA Hotma Pangaribuan
Journal Information System Development Vol 4, No 1 (2019): Journal Information System Development (ISD)
Publisher : UNIVERSITAS PELITA HARAPAN

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

Abstract

Segmentasi citra sebagai bagian dari proses pengolahan citra, adalah kegiatan untuk membagi citra menjadi beberapa bagian atau region, yang bertujuan untuk mengisolasi atau menemukan suatu obyek di dalam citra. Beberapa pertumbuhan kemajuan teknologi baru membuka peluang bagi pengembangan lebih lanjut dalam bidang ini. Saat ini pengolahan citra mempunyai peranan yang sangat penting dalam berbagai bidang kehidupan. Segmentasi adalah proses pemisahan objek dengan latar belakangnya. Saat ini telah banyak dilakukan penelitian tentang segmentasi.Deteksi tepi merupakan suatu proses pencarian informasi tepi dari sebuah gambar. Deteksi tepi memiliki tujuan antara lain digunakan untuk menandai bagian yang menjadi detail dari sebuah gambar Ada banyak metode dalam melakukan segmentasi salah satunya adalah level-set menggunakan metode roberts, prewit sobel dan frei chan. Histogram citra digunakan untuk mengetahui intensitas dan kontras suatu citra, timing run digunakan untuk mengetahui lamanya suatu proses citra, dan SNR (Signal to Noise Ratio) yang digunakan untuk mengetahui kualitas citra. Pengujian dilakukan dengan melakukan uji coba terhadap Objek citra dan selanjutnya dilakukan analisis citra.Metode Sobel dan Prewitt memiliki proses komputasi yang lebih lebih sedikit jika dibandingkan. Secara umum algoritma segmentasi citra didasarkan pada satu dari dua property nilai intensitas yaitu mendeteksi diskontinuitas atau mendeteksi similaritas. Dari hasil penelitian ini didapat kesimpulan sebagai berikut:metode segmentasi yang paling tajam hasilnya yaitu menggunakan Operator Freichen, karena dari sudut pandang horizontal dan sudut pandang Vertikal sama sama menghasilkan hasil yang bagus, Dari hasil pembahasan untuk jenis operator yang paling baik adalah operator Robert, Hasil deteksi pada operator sobel lebih bagus atau tegas dibandingkan dengan operator Robert dan prewitt. Operator Sobel lebih sensitif terhadap tepi diagonal daripada tepi vertikal dan horizontal  Hal ini berbeda dengan operator Prewitt, yang lebih sensitif terhadap tepi vertikal dan horizontal.
OPTIMALISASI KUALITAS CITRA DIGITAL DENGAN METODE KETETANGGAAN PIKSEL: Ketetanggaan Piksel Hotma Pangaribuan
JURNAL ILMIAH INFORMATIKA Vol 7 No 01 (2019): Jurnal Ilmiah Informatika (JIF)
Publisher : Teknik Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1006.21 KB) | DOI: 10.33884/jif.v7i01.864

Abstract

This study aims to improve the image or image by eliminating noise in the color image that is converted to gray images with a number of pixel intensities of 0 to 255 using the pixel neighboring method. Pixel neighbor types used in the test include boundary filters, uniform filters and median filters. While noise added to the original image is salt noise and pepper and gaussian with a value of p = 0.01. From the results of this study, it can be seen how much interference can be corrected by using a type of neighboring pixel filter, with the amount of improvement including reducing noise, softening noise and eliminating noise. From the results of the tests carried out with the help of the octave 3.4.3 program, it can be seen that the boundary filter aims to prevent pixels whose intensity outside the intensity of neighboring pixels with white spots on the image can be removed. However, if you pay close attention, the operation also blurs the image, while in the equalization filter the processing effect with the alignment filter. Compared to the limit filter, the processing of the uniform filter does not eliminate white spots on the image of the car, but only slightly disguises the image, while in median filter The results show that noise can be removed, but the details on the image are retained. However, this is of course obtained with the added computational burden of "sorting".
RANCANG BANGUN INTRUSION DETECTION SYSTEM (IDS) MENGGUNAKAN SNORT (STUDI KASUS PT PLN BATAM) Sunarsan Sitohang; Hotma Pangaribuan
JURSIMA (Jurnal Sistem Informasi dan Manajemen) Vol 11 No 1 (2023): Volume 11 Nomor 1 2023
Publisher : INSTITUT TEKNOLOGI DAN BISNIS INDOBARU NASIONAL

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47024/js.v11i1.571

Abstract

Security is an important aspect in building a network. The use and utilization of information technology for PT PLN Batam has become an important component for the daily activities of employees in improving company performance. This research was conducted to assist network administrators in monitoring traffic and supervising suspicious activities at PT PLN Batam. For monitoring of suspicious activities at PT PLN Batam, the intruder detection system that the author uses is Snort which runs on the Linux Operating System, namely Debian, because Snort is open source and can detect attack patterns in accordance with existing rules. The author uses Snort which is assisted by the Snorby interface to make it easier for a network administrator in terms of monitoring. Log or Alert results from Snort are presented in the form of a Graphical User Interface (GUI) using the Snorby application as a monitoring system in the form of Line Charts and Pie Charts. Snort can also display Logs or Alerts based on the severity level which is divided into 3 colors, namely High severity in red which is categorized as a dangerous attack, Medium severity in yellow which is categorized as an attack with a moderate level, and Low severity in green which is categorized as an attack that is not dangerous or weak. In general, Snort only works as a detector and is unable to withstand attacks. It is hoped that in the future Snort can be developed which is able to prevent attacks automatically.
Perancangan Sistem Kendali Rumah Pintar Berbasis Arduino Sitompul, Artaulima; Hotma Pangaribuan
Computer Science and Industrial Engineering Vol 10 No 2 (2024): Comasie
Publisher : LPPM Universitas Putera Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33884/comasiejournal.v10i2.8477

Abstract

The house can act as a place to shelter, rest, gather with family. However, there are times when homeowners often feel worried because they cannot monitor their house thoroughly, especially if it has been abandoned for a long time. Therefore, we need a control device that operates automatically or manually to monitor the condition of the house and can control it remotely. Arduino-Based Smart Home Control". The design of an Arduino-based smart control system that operates automatically or manually with users able to monitor and control remotely using an Android smartphone. The smart home system being built consists of three parts, namely input, processing and output. Process The input consists of PIR, LDR and DHT 11 sensors, then the data from these three sensors is collected by Arduino Mega to be processed into instructions for controlling lights, fan, and buzzers via a 4-channels relay module. The NodeMCU is tasked with sending and reading and controlling lights, fans, and buzzer. Android-based smartphones, the data is read in database storage which is used to display the results of sensor data readings in real time and send data based on controls in the application menu carried out by the user.
PERANCANGAN SISTEM PENGUKUR PH AIR SUMUR MASYARAKAT KELURAHAN TANJUNG SENGKUANG KOTA BATAM MENGGUNAKAN ARDUINO UNO Febrianto, Rizki Amin; Hotma Pangaribuan
Computer Science and Industrial Engineering Vol 10 No 4 (2024): Comasie
Publisher : LPPM Universitas Putera Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33884/comasiejournal.v10i4.8585

Abstract

The growth of technology and industry is growing rapidly in several Indonesian provinces, especially in Tanjung Sengkuang urban village of Batam City, where many factories are established around residential areas. Well water is the main source of water for the local community. However, the quality of the well water has not been accurately measured so that people do not know whether the water is safe to use. The designed water pH measuring system consists of a pH sensor as input, then the measurement results from the sensor will be sent through Arduino Uno to be displayed on the LCD, on the other hand, Arduino Uno also sends data from the measurement results to NodeMCU to be sent to the database, after which users can see the results of the water pH measurement through smart devices, anywhere and anytime. It is hoped that with this well water pH measuring system, people can monitor the quality of well water used and can immediately take appropriate action if problems are found in the quality of the water.
DETEKSI KALORI PADA CITRA MAKANAN DENGAN ALGORITMA SINGLE SHOT MULTIBOX DETECTOR Fifin ayu puspitasari; Hotma Pangaribuan
Computer Science and Industrial Engineering Vol 12 No 2 (2025): Comasie Vol 12 No 2
Publisher : LPPM Universitas Putera Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33884/comasiejournal.v12i2.9714

Abstract

The increasing prevalence of non-communicable diseases such as obesity and diabetes mellitus has become a major public health concern in Indonesia. Uncontrolled food consumption is one of the primary contributing factors to these issues. Therefore, a system is needed to help individuals monitor their calorie intake more effectively. This study aims to develop a food calorie detection system using the Single Shot Multibox Detector (SSD) method. The model is applied to identify and classify food objects with high accuracy. Calorie estimation is performed based on predefined fixed portion rules. The results indicate that the developed system can recognize various types of food in real-time with optimal performance. The implementation of this system is expected to raise public awareness of healthy eating habits and support efforts to prevent non-communicable diseases in Indonesia.
RANCANG BANGUN ALAT AUTO FEEDER HEWAN PELIHARAN BERBASIS ARDUINO Eko, Eko Giri Pratama; Hotma Pangaribuan
Computer Science and Industrial Engineering Vol 12 No 3 (2025): Comasie Vol 12 No 3
Publisher : LPPM Universitas Putera Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33884/comasiejournal.v12i3.9801

Abstract

Ensuring proper and regular feeding is an important aspect of maintaining the health and well-being of pets. However, pet owners sometimes face challenges in consistently providing food to their pets, especially when they are busy with work or other activities. To address this issue, an automated feeding system can be an effective solution. This abstract highlights the implementation of an automated pet feeding system using Arduino Uno, a popular open-source microcontroller board. The system is designed to dispense the appropriate amount of food at scheduled times, ensuring that pets receive their meals on time. The Arduino Uno acts as the brain of the system, controlling various components such as a motorized food dispenser, a digital display for programming and monitoring, and sensors for detecting the presence of pets and food levels. By utilizing a programmable microcontroller, the system can be easily customized to accommodate specific feeding requirements and pet schedules. Overall, the automated pet feeding system using Arduino Uno offers a practical and reliable solution for pet owners who struggle to maintain consistent feeding routines. By utilizing technology such as Arduino Uno, pet owners can ensure that their pets receive proper nutrition, even in their absence.
PERANCANGAN SISTEM ABSENSI BERBASIS MONITORING MENGGUNAKAN TEKNOLOGI FACE RECOGNITION Kho, Gafery; Hotma Pangaribuan
Computer Science and Industrial Engineering Vol 13 No 4 (2025): Comasie Vol 13 No 4
Publisher : LPPM Universitas Putera Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33884/comasiejournal.v13i4.10580

Abstract

Employee attendance is a crucial factor in determining company performance and productivity. Therefore, an accurate and efficient attendance system is needed to ensure compliance with working hours. This study aims to design a monitoring-based attendance system using Face Recognition technology at PT. Global Benua Bajatama. The technology is used to automatically detect and recognize employee faces. The research method applied is qualitative, involving system design using Unified Modeling Language (UML), database design, and testing the accuracy of facial detection as well as analyzing the system’s effectiveness. The results show that the face detection accuracy ranges from 80% to 95% under optimal conditions. These conditions include employees not wearing facial accessories such as masks, sunglasses, or safety helmets, and maintaining a face-to-camera distance of about 40–50 cm. Under these circumstances, the system can detect and recognize faces quickly and accurately, producing attendance data that meets the required specifications. The implementation of this system improves the efficiency of the attendance process and reduces the potential for errors compared to manual attendance recording.