Article Per Year (5 Year)
p-Index From 2021 - 2026
0.659
P-Index
This Author published in this journals
All Journal Indonesian Journal of Information System Jurnal Restikom : Riset Teknik Informatika dan Komputer Prosiding Seminar Nasional Sisfotek (Sistem Informasi dan Teknologi Informasi) Journal of Information Technology and its Utilization
Debby Paseru
Universitas Katolik De La Salle Manado
Computer Science & IT Engineering

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
Comparative Analysis of Classification Methods of KNN and Naïve Bayes to Determine Stress Level of Junior High School Students Yohanes Christopher Tapidingan; Debby Paseru
Indonesian Journal of Information Systems Vol. 2 No. 2 (2020): February 2020
Publisher : Program Studi Sistem Informasi Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/ijis.v2i2.3035

Abstract

Stress is generally defined as a state where someone is mentally disturbed as the response to the adversity that he/she experiences. Junior High School students usually are not aware of the stress that they encounter. This research aims to compare two classification methods of KNN and Naïve Bayes to determine stress level. The data of this research were gathered from 254 respondents from Catholic Junior High School of Don Bosco Bitung. The tests of k-cross validation and percentage split from the data showed that Naïve Bayes method excelled KNN method. With k=3, KNN accuracy reached 86.61% at the highest and Naïve Bayes reached 87.40%. Meanwhile, based on percentage split test, the average of Naïve Bayes accuracy was higher than KNN with percentage of 88.31%. Moreover, for the precision and recall, Naïve Bayes was higher than KNN with 88.30% and 87.40% seen from the k-cross validation.
Implementasi Metode Vector Space Model pada Search Engine Perpustakaan Stevanus Salmon; Debby Paseru; Vivie Kumenap
Prosiding SISFOTEK Vol 4 No 1 (2020): Vol 4 No 1 (2020): SISFOTEK 2020
Publisher : Ikatan Ahli Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (604.398 KB)

Abstract

Dinas Perpustakaan dan Kearsipan Daerah Provinsi Sulawesi Utara is a library owned by the provincial government of Sulawesi Utara (Sulut), which provides various sources of information needed by the community such as books or reference documents. Other. This library provides various facilities and services that can be used by the community of Sulut such as searching, reading and borrowing books. Libraries are required to be able to improve their services especially in book Search or documents. The book search process in a library that requires visitors to visit each of the booksets will take a long time. In addition, visitors should also first find the fields or topics of the searched book by visiting the Bookcloset section that corresponds to the field or topic. The lack of information available about books or documents in the library will prevent visitors from finding the information they need. Therefore the library requires a system to simplify the process of searching the book. A book search system that uses the search process by matching keywords and data to the database, will only display the title of the book exactly as the keyword entered on the search form. If the user forgets the details of the title of the book to be searched, it is very difficult to search the book title because the system is unable to display the corresponding title of the book or is relevant to the book title entered on the search form. To be able to display the information or title of the book related or relevant to the title of the book to be searched, will be created a search system of books that use an information retrieval system or the information Retrieval (IR). Information Retrieval (IR) or an info-back system is one way to easily rediscover the information on documents contained in a system. Search engine or search engine is a device that can facilitate the user to obtain information by displaying the search results according to the information that is sought by the user. On this final task will be built search engine libraries that can make it easier for users to rediscover relevant books according to the data sought. This final task applies a Vector Space Model (VSM) method that is one of several methods that can be used in building the System Information Retrieval (IR). The result of this final task is a search engine library by implementing a VSM method that provides the document search feature and provides a complete document or book information in the library. In addition, testing of the application uses recall and precision which results in a value of 1 which shows that the system can find the relevant documents according to the relevant documents in the collection.
Perbandingan Metode Forward Chaining dan Backward Chaining Dalam Mendiagnosis Perkembangan Anak Usia Dini Sofyana Ibrahim; Debby Paseru; Vivie Deyby Kumenap
Prosiding SISFOTEK Vol 5 No 1 (2021): SISFOTEK V 2021
Publisher : Ikatan Ahli Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (514.484 KB)

Abstract

Development in humans occurs from birth to adulthood, therefore parents have a very important role in paying attention to the development of children. The survey conducted by the author shows that not all parents will see a doctor to check their child's growth and development because they are busy working and will only go to the doctor when their child is in an unhealthy condition. From the survey data in the form of questionnaires collected, some parents also do not know what symptoms affect their child's growth and development. If a child has a developmental disorder and parents rarely consult to find out how high the level of the disorder is, it will worsen the growth and development of the child so that the number of developmental disorders in children will increase. Based on the problems above, an Early Childhood Development Expert System application was built using the Forward Chaining Method and the Backward Chaining Method, the reason for using both methods is to be different from previous research and the search process can be more varied. The forward chaining method looks for disorders based on the symptoms selected by the user. The backward chaining method is used to determine the level of disorders that occur in children based on the symptoms and disorders selected by the user. The application is built using the PHP programming language and the Unified Modeling Language (UML) modeling tool. The results of the implementation of this scientific work are able to produce an early childhood development expert system application that can detect symptoms or disorders using the Forward Chaining and Backward Chaining methods. This application is ready and suitable for users to detect symptoms or disorders.
Comparison of Vector Space Model and BM25F Methods in Book Search Debby Paseru; Reynaldi Kuera; Stevanus Salmon
Jurnal RESTIKOM : Riset Teknik Informatika dan Komputer Vol 5 No 3 (2023): Desember
Publisher : Program Studi Teknik Informatika Universitas Nusa Putra

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52005/restikom.v5i3.264

Abstract

Pencarian sebuah buku di perpustakaan dapat dilakukan secara mudah jika kita sudah mengetahui judul buku, pengarang, bidang ilmu atau pun penerbit dari buku tersebut sebagai kata kunci. Tanpa kata kunci, pencarian buku akan sulit dilakukan karena pencarian akan membutuhkan waktu dan kita akan mencari buku tersebut di antara ratusan bahkan ribuan buku yang ada meskipun sudah ada katalog atau basis data. Basis data buku yang ada di perpustakaan merupakan gudang data dan untuk memanfaatkan gudang data tersebut, maka dapat digunakan proses temu balik informasi atau information retrieval (IR). Proses temu balik informasi merupakan suatu cara untuk menemukan kembali informasi pada dokumen atau basis data. Terdapat beberapa metode dalam IR ini, seperti inverted index, boolean retrieval, tokenization, stemming and lemmatization, dictionaries, wildcard queries, BM25F dan vector space model (VSM). Penelitian ini telah membandingkan metode vector space model dan BM25F untuk mencari waktu akses tercepat dalam pencarian buku. Data yang digunakan dalam penelitian ini merupakan data semu sebanyak 50 buku. Pengujian dilakukan sebanyak 20 kali terhadap 10 kata kunci yang berbeda dari 50 data buku yang ada. Berdasarkan pengujian yang telah dilakukan, metode Vector Space Model memiliki waktu pencarian yang lebih cepat dibandingkan dengan metode BM25F. Metode VSM menghasilkan rata-rata waktu pencarian 0,002 detik, sedangkan rata-rata waktu pencarian metode BM25F adalah 6,308 detik. Perbedaan waktu yang cukup besar dikarenakan metode MB25F mengharuskan pencarian kata kunci berdasarkan kategori yang ditentukan dulu, sedangkan metode VSM melakukan pencarian langsung kata kunci tanpa penentuan kategori.
Geographical Information System for Mapping Flood-Prone Areas in Manado City Using the K-Means Clustering Method Aurelia Koagouw; Debby Paseru; Indah Kairupan
Journal of Information Technology and Its Utilization Vol 7 No 1 (2024): June 2024
Publisher : Sekolah Tinggi Multi Media

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56873/jitu.7.1.5403

Abstract

Floods are natural events or phenomena that can cause environmental damage, loss of property, psychological effects, and death or casualties. One way to control flooding non-structurally is by mapping areas that are prone to flooding. This study builds a geographic-based information system to map flood-prone areas in Manado City using the K-Means Clustering algorithm. The main objective of this research is to identify and map areas with a high risk of flooding using spatial data. Slope, land cover type, soil type, water discharge (discharge), and rainfall are independent variables that will be used and processed using the K-Means Clustering algorithm. There are four clusters in the mapping results of flood-prone areas, namely: high vulnerability, medium vulnerability, low vulnerability, and not vulnerable. By using the K-Means method, the results obtained are Paal Dua and Wenang sub-districts are high-vulnerability groups, followed by Mapanget, Tuminting, and Singkil subdistricts with medium vulnerability groups. Tikala District is the only area with low vulnerability. Meanwhile, Bunaken, Sario, Wanea, and Malayayang sub-districts are areas that are not potentially prone to flooding.
Co-Authors Aurelia Koagouw Indah Kairupan Kumenap, Vivie Deyby Reynaldi Kuera Sofyana Ibrahim Stevanus Salmon Vivie Kumenap Yohanes Christopher Tapidingan