Lalitya Nindita Sahenda
Politeknik Negeri Jember

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

Red Dragon Fruit (Hylocereus costaricensis) Ripeness Color Classification by Naïve Bayes Algorithm Zilvanhisna Emka Fitri; Mega Silvia; Abdul Madjid; Arizal Mujibtamala Nanda Imron; Lalitya Nindita Sahenda
TEKNOLOGI DITERAPKAN DAN JURNAL SAINS KOMPUTER Vol 5 No 1 (2022): June
Publisher : Universitas Nahdlatul Ulama Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33086/atcsj.v5i1.3690

Abstract

Dragon fruit is a unique fruit that is popular in Indonesia. besides having a sweet taste, this fruit also contains fiber, vitamins and minerals that are good for health. Dinas Pertanian Kabupaten Banyuwangi noted that the total dragon fruit production was 906,511.61 tons and the total productivity was 261.14 Kw/Ha in 2018. This shows that Kabupaten Banyuwangi is one of the largest producers of red dragon fruit in East Java Province. One of the problems in determining the quality of dragon fruit is choosing the harvest time, considering that dragon fruit is a non-climatic fruit. Non-climateric fruit is when we harvest fruit in its raw state, the fruit will never become ripe, so determining the harvest time for dragon fruit is very important. The determination made by paying discoloration and sizes of dragon fruit that is considered less effective. To overcome this, a system was created that was able to determine the level of dragon fruit maturity automatically by utilizing digital image processing techniques and intelligent systems. The parameters used are color features and GLCM texture features using angles 0°, 45°, 90° and 135° These features are parameters in the classification process using the Naïve Bayes method. Naïve bayes is able to classify the level of maturity of red dragon fruit (Hylocereus costaricensis) with an accuracy rate of 87.37%.
PENINGKATAN KUALITAS LAYANAN INTERNET SEKOLAH DENGAN METODE POLICY BASED ROUTE (PBR) DI SMK PP NEGERI 1 TEGALAMPEL BONDOWOSO Lalitya Nindita Sahenda; Prayugo Ardi Wibowo; Pramuditha Shinta Dewi Puspitasari
Batara Wisnu : Indonesian Journal of Community Services Vol. 4 No. 1 (2024): Batara Wisnu | Januari - April 2024
Publisher : Gapenas Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53363/bw.v4i1.242

Abstract

Nowadays, internet connectivity is very important in various aspects. All sectors of life require an internet connection, for example in the communications, economic, social and educational sectors.  The massive development of internet connections has had a positive impact on various sectors. including the education sector. Before the massive development of the internet, education in schools was carried out manually, for example the teacher would explain on the blackboard. But with the development of the internet, learning media is built by utilizing the internet. Students can also easily find the learning materials they need on the internet. Not only teachers and students, other entities in the school, namely administrative staff, also need a reliable internet network to make it easier to report school activities, for example attendance, finances, personnel, etc. All of these activities require a reliable and fast internet connection at school. Unfortunately, for partners, the internet is still slow and often disconnects, so it is necessary to add a new internet service provider (ISP) to support the previous ISP. Apart from that, it is also necessary to rejuvenate internet devices, as well as network management so that the 2 connected ISPs can be used optimally and optimally. Network management is by implementing the Policy Based Route (PBR) method. This method allows the load to be adjusted to be balanced across the 2 ISPs used. So as to avoid overload/overload on the school network. The availability of reliable and fast internet is an effort to improve the quality of school internet services which can support teaching and learning activities optimally
Implementing K-Nearest Neighbor to Classify Wild Plant Leaf as a Medicinal Plants Zilvanhisna Emka Fitri; Lalitya Nindita Sahenda; Sulton Mubarok; Abdul Madjid; Arizal Mujibtamala Nanda Imron
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 23 No. 1 (2023)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v23i1.2220

Abstract

in leaf shape. Therefore, this study aimed to create a system to help increase public knowledge about wild plant leaves that also function as medicinal plants by the KNN method. Leaves of wild plants, namely Rumput Minjangan, Sambung Rambat, Rambusa, Brotowali, and Zehneria japonica, are also medicinal plants in comparison. Image processing techniques used were preprocessing, image segmentation, and morphological feature extraction. Preprocessing consists of scaling and splitting the RGB components and using an RGB component decomposition process to find the color component that best describes the leaf shape and generate the blue component image. The segmentation process used a thresholding technique with a gray threshold value (T) of less than 150, which best separates objects and backgrounds. Some morphological feature extraction used are area, perimeter, metric, eccentricity, and aspect ratio. Based on the results of this research, the KNN method with variations in K values, namely 13, 15, and 17, obtained a system accuracy of 94.44% with a total of 90% training data and 10% test data. This comparison also affected the increase in system accuracy.