Journal of Telecommunication Network (Jurnal Jaringan Telekomunikasi)

New Employee Admission Decision Support System at Bangraden Foods using The Web-based Fuzzy Tsukamoto Method

Handy Widianto Prabowo — 2024-03-30

Currently, Bangraden Foods is having problems picking new employees by offering numerous criteria to identify the applicant's abilities and personality, the results are typically recorded and must be compared to make judgments, which takes a long time for the company. In this case, the researcher used the Tsukamoto fuzzy method to develop a decision support system because it is simple, flexible, data-tolerant, faster, and better suited for input from humans rather than robots. Based on black box testing, the web system performance results run 100% smoothly for all existing functions. Testing data on 5 new employee candidates obtained a system value difference of 0.001-0.02 with 100% data accuracy, and the system recognized the graduation of two prospective workers with a decision of 'pass' since it reached an average score of 75, according to HRD, and three candidates 'did not qualify' due to below-average grades. In addition to testing service quality, throughput of 16Kb/s is classed as 'bad', packet loss of 0.273594% as 'very good', and delay of 293ms as 'good'. As a result, Bangraden Foods management may use the system to make data processing quicker and provide advice for decisions on recruiting new personnel based on the company's needs.

Elephas-SAM : segmentation performance of Sumatran Elephant in captivity with segment anything model

Fortuno Ery Faqih — 2024-03-29

Surabaya Zoo is one of the conservation institutions in Surabaya, which has Sumatran elephants as a collection of endemic Indonesian animals. The Indonesian government protects this animal because of its endangered status. Having CCTV cameras installed in captivity helped us to create Elephas-SAM by utilizing Segment Anything Model (SAM) technology as the initial foundation for developing a system for monitoring animals in captivity with artificial intelligence (AI). Our investigations differ from past research in that we utilize 60 exclusive images obtained from CCTV footage in an elephant enclosure at Surabaya Zoo over a 30-day period instead of using publicly available datasets. The image set was partitioned into 30 instances taken under low-light settings (01:00 WIB) and 30 instances taken under high-light conditions (15:00 WIB). We perform the evaluation of SAM's prediction scores using the SAM-Point Prompt and SAM-Box Prompt techniques. It was found that, on average, the segmentation prediction scores for 30 low-light images are higher when the SAM-Point prompt is used (0.941) instead of the SAM-Box prompt (0.939), which is only a 0.002 difference. For a set of 30 vivid images, the SAM-Point Prompt produces a higher average score (0.989) than the SAM-Box Prompt (0.968), indicating a difference of 0.021. The results emphasize the effectiveness of using a SAM-Point prompt instead of a SAM-Box question to accurately forecast segmentation scores for items of Sumatran elephants under different illumination situations.

Painting Security System using TensorFlow Based Object Detection Method

MUHAMMAD YOGA AKBAR PRASETYA — 2024-03-30

Painting is an art form that should be preserved. Raden Saleh, Affandi, Hendra Gunawan, and Nyoman Gunarsa's paintings are among those of outstanding artistic worth. The existence of paintings may be jeopardized if the painting protection system is poor. Several well-known examples of art theft include the theft of Affandi's paintings in 1973 and Raden Saleh's paintings in 2007. Apart from famous paintings, personal paintings, which are equally expensive, are frequently stolen. This, of course, concerns the general public, particularly private art collectors with minimal security. Based on these problems, specific management is needed through the "SI LUKAS" Painting Security System. Using the TensorFlow-Based Object Detection Method, a system innovation that can continuously monitor the whereabouts of artworks and send notifications via Telegram, can be accessed from anywhere and at any time using TensorFlow. Based on evaluating the system's delay in reading items at a distance, it is discovered that the system can detect all objects, specifically hands and paintings, within a distance of 50cm to 550cm, however the latency varies. The average accuracy of object detection from various angles was found to be 89.6% for hand objects and 96.4% for painting objects, placing them in the very high category. In other words, the SI LUKAS system is implementable.

Design and Development of Augmented Reality Applications in Computer Network Topology Animation

Gaguk Suprianto — 2024-03-29

Technology can be applied in the development of teaching materials to enable students to explore material outside the classroom. One of the relevant technologies is Augmented Reality (AR), which allows the appearance of three-dimensional objects in the real world. One of the courses that has significance in the realm of information and communication technology is computer networks. However, this course faces several obstacles in implementing the teaching and learning process, including high equipment costs and expensive maintenance requirements. In addition, the teaching methods currently used still tend to be monotonous. Given these factors, the objective of this study is to incorporate Augmented Reality technology into the teaching of computer network courses. An Augmented Reality application has been developed and tested using the black box method. This approach has the advantage of assessing software quality, ensuring that the software meets desired expectations Test results on mobile devices state that the application developed can be installed on two mobile devices with different specifications. The marker test was also declared successful up to a distance of 100 cm. All buttons and features in the application run smoothly and function well. The application designed and developed possesses the potential for use in additional courses necessitating object visualization. In addition, the developed application supports users with special needs because there are audio features in each material. For future research, it may be considered to use a markless-based method because it is more flexible and does not require markers.