Article Per Year (5 Year)
p-Index From 2021 - 2026
1.665
P-Index
This Author published in this journals
All Journal CogITo Smart Journal JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH) Servitium Smart Journal
Semmy Wellem Taju
Fakultas Ilmu Komputer, Universitas Klabat
Computer Science & IT Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering

Published : 11 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 7 Documents
Search
Journal : CogITo Smart Journal

 1 
Bioinformatics Tools for Data Processing and Prediction of Protein Function Green Arther Sandag; Semmy Wellem Taju
CogITo Smart Journal Vol 4, No 2 (2018): CogITo Smart Journal
Publisher : Fakultas Ilmu Komputer, Universitas Klabat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (698.713 KB) | DOI: 10.31154/cogito.v4i2.137.305-315

Abstract

Bioinformatika semakin populer karena kemampuannya untuk menganalisis dan memproses data biologis dengan cepat dan efektif. Bagian penting dari bioinformatika adalah untuk mengidentifikasi fungsi dan karakteristik protein dengan membangun metode prediksi menggunakan algoritma pembelajaran mesin. Ini termasuk bagaimana pembelajaran mesin dapat digunakan untuk menganalisis dan mengklasifikasikan fungsi protein yang cocok untuk digunakan sebagai deteksi penyakit, merancang perawatan medis yang tepat untuk pasien, dan mengembangkan obat untuk beberapa penyakit. Permintaan untuk pembuatan predictive tools dalam menentukan model protein-ligand dan fungsi protein meningkat untuk mempromosikan penelitian biologi dalam lingkungan desain obat yang inovatif. Namun, dibutuhkan banyak waktu dan upaya untuk mengembangkan alat prediksi yang dapat diterapkan pada protein. Dalam penelitian ini kami mengembangkan tools bioinformatika yang dapat secara otomatis mengembalikan data protein dalam bentuk komposisi asam amino (AAC), komposisi pasangan dipeptida (DPC), dan matriks penentuan spesifikasi posisi (PSSM). Data protein, telah kita ambil dari database uniprot yang berisi file fasta. Penelitian ini, kami membuat alat untuk memfasilitasi ilmuwan dalam memproses atau menganalisis data protein dan juga dapat memprediksi fungsi protein menggunakan algoritma pembelajaran mesin seperti Neural Network dan Random Forest. Kata Kunci—Bionformatika, AAC, DPC, PSSM
Bahasa Indonesia Bahasa Inggris Elshadai Gracia Carolina Rampengan Rampengan; Semmy Wellem Taju; Venisa Tewu
CogITo Smart Journal Vol. 9 No. 1 (2023): Cogito Smart Journal
Publisher : Fakultas Ilmu Komputer, Universitas Klabat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31154/cogito.v9i1.469.181-192

Abstract

Klabat University provides residential facilities for students, better known as a dormitory. Information services regarding dormitories and reservation rooms at Klabat University are still managed manually between the dormitory and students. Some problems occur when students want to find information and/or reserve a room at the same time. From the problems that have been observed, researchers have designed a Chatbot to facilitate the students to find for information as well as reserve dormitory rooms. The development method used in this research is the prototyping model. To design a chatbot by implementing two-way communication, researchers implemented Natural Language Processing technique with a Machine Learning approach. The result of this research is a new Chatbot widget as a virtual assistant for information services and reservation rooms in the dormitory at Klabat University
Sistem Analisis Sentimen Ulasan Aplikasi Belanja Online Menggunakan Metode Ensemble Learning Debby Erce Sondakh, S.Kom, M.T, Ph.D; Semmy W. Taju; Michelle G. Tene; Arwin E. T. Pangaila
CogITo Smart Journal Vol. 9 No. 2 (2023): Cogito Smart Journal
Publisher : Fakultas Ilmu Komputer, Universitas Klabat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31154/cogito.v9i2.525.280-291

Abstract

Terdapat pertumbuhan jumlah dan prevalensi belanja online. Teknologi belanja online memungkinkan pembeli memberikan umpan balik pasca pembelian (komentar dan ulasan) mengenai aplikasi itu sendiri dan aspek-aspek lain dari produk. Umpan balik ini dapat bermanfaat bagi pelanggan dan bisnis. Namun demikian, menyortir, mengkategorikan, dan membaca begitu banyak ulasan secara manual membutuhkan waktu. Analisis sentimen dapat menyelidiki perilaku, pendapat, dan emosi pelanggan melalui komentar/ulasan teks. Pada penelitian ini, Sistem Analisis Sentimen dikembangkan untuk membantu menentukan sentimen dari setiap ulasan dengan menampilkan visualisasi yang menarik dari hasil analisis melalui diagram lingkaran, frekuensi kemunculan kata, dan persentase probabilitas setiap kelas sentimen-positif, netral, dan negatif. Sistem Analisis Sentimen menggunakan model pengklasifikasi ensemble learning dengan algoritma SVM, KNN, dan Random Forest. Ensemble learning menghasilkan hasil yang lebih tepat daripada algoritma tunggal. Ensemble learning menghasilkan model classifier dengan performa yang lebih baik, dengan indikator akurasi 81.8% precision 83%, recall 82%, F1-score 82%.
Sistem Pencarian dan Rekomendasi Tukang Bangunan Menggunakan Mobile-Based dan GPS Marchel Thimoty Tombeng; Semmy Taju; Ferrell Sanger; Reynaldo Daingah
CogITo Smart Journal Vol. 9 No. 2 (2023): Cogito Smart Journal
Publisher : Fakultas Ilmu Komputer, Universitas Klabat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31154/cogito.v9i2.566.304-316

Abstract

In the current digital era, information technology-based applications are rapidly evolving and becoming increasingly essential in everyday life. One type of application that is gaining popularity among the public is recommendation applications, especially those for finding handyworkers. Airmadidi is one of the cities in Indonesia with many boarding houses offering various facilities and prices. However, for newcomers seeking handyworkers in the city, finding the right one for their needs can be a challenging and exhausting task. Therefore, there is a need for a recommendation and handyworker search application system that can assist seekers in addressing issues in their boarding houses or homes according to their specific requirements. This application system will gather information about available handyworkers in Airmadidi and provide recommendations based on users' preferences and needs.The aim of this research is to design a recommendation and handyworker search application in Airmadidi using an appropriate software development method supported by the latest technology. This application system is expected to help users easily and efficiently find handyworkers that match their needs. The research methodology employed in this writing includes interviews, literature reviews, and system design using the SDLC (Software Development Life Cycle) method with a spiral model. The stages of the spiral model With the existence of this recommendation and handyworker search application system, searching for handyworkers in Airmadidi is expected to become easier, more efficient, and effective for seekers. Additionally, this research can serve as a reference for similar studies in other areas.
Implementing QR code and Geolocation Technologies for the Student Attendance System Semmy Wellem Taju; Yonatan Putra Mamahit; Jeremy Andrew Pongantung
CogITo Smart Journal Vol. 10 No. 1 (2024): Cogito Smart Journal
Publisher : Fakultas Ilmu Komputer, Universitas Klabat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31154/cogito.v10i1.636.642-653

Abstract

Attendance is one of the important factors in supporting lecture activities that can be used to see how well the performance of student attendance in class. Traditional attendance systems used in various educational institutions often cause problems. This research aims to develop an innovative and efficient student attendance system to help the process of taking attendance by utilizing QR-Code and geo-location technologies at Klabat University. The research method employed for this development is the Prototyping Model, which involves iterative development and refinement processes. The system is designed as a web-based application and a mobile application, developed using PHP as the programming language, MySQL as the database management system, Bootstrap 5 as the CSS and JavaScript framework for creating responsive websites, Apache as the web server and Ubuntu 22.04 as the operating system for the server. QR-Code technology is proposed as a medium for recording and verifying student attendance, while Geo-Location technology is used to verify the presence of students in the right lecture venue. The results of this research are expected to make a positive contribution to Klabat University in terms of recording student attendance.
Research Project Topic Recommender System Using Generative Language Model Debby Erce Sondakh, S.Kom, M.T, Ph.D; Semmy Wellem Taju; Jian Kezia Tesalonica Yuune; Anjelita Ferensca Kaminang; Syalom Gabriela Wagey
CogITo Smart Journal Vol. 10 No. 1 (2024): Cogito Smart Journal
Publisher : Fakultas Ilmu Komputer, Universitas Klabat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31154/cogito.v10i1.678.654-666

Abstract

Education has become a driver of a person's continuous innovation to improve their quality. Currently, the use of artificial intelligence determines progress in education. In this research, artificial intelligence technology was applied to develop a web-based recommendation system to help students at the Faculty of Computer Science, Klabat University, choose appropriate research topics for their final assignments. To provide personalized and contextually relevant suggestions, the recommendation system leverages deep learning and generative language models, specifically GPT-3. The Rapid Application Development process model is employed to develop the system. Its key components include semantic search, rapid engineering, and an advanced vector database for effective data management and retrieval. The functions provided by the system include user account registration, login, input of major subject grades and research preferences, and personalized recommendation results. Some additional features such as profile management, previous recommendation history, and password reset options are also provided. All these functions have been tested using the black box method.
MRI Image Analysis for Alzheimer’s Disease Detection Using Transfer Learning: VGGNet vs. EfficientNet Sandag, Green Arther; Djamal, Eleonora; Tangka, George Morris William; Taju, Semmy Wellem
CogITo Smart Journal Vol. 10 No. 2 (2024): Cogito Smart Journal
Publisher : Fakultas Ilmu Komputer, Universitas Klabat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31154/cogito.v10i2.836.580-592

Abstract

This study focuses on developing an effective Alzheimer's disease (AD) classification model using MRI images and transfer learning. This research targets individuals aged 65 and above who are affected by the predominant form of dementia and utilizes an Alzheimer's Disease MRI Image dataset from Kaggle. Model selection involved options like EfficientNetB1, B3, B5, B7, VGG16, and VGG19. Two scenarios with distinct batch sizes (10 and 20) were explored in the model creation process. Evaluation, using a confusion matrix, determined that the EfficientNetB5 model yielded the highest accuracy at 99.22%, surpassing other models such as EfficientNetB1, B3, B7, VGG16, and VGG19. Notably, this research highlights the superior performance of EfficientNet over VGGNet in transfer learning for analyzing Alzheimer's disease MRI images. The study concludes with the implementation of a simple web system for testing model outcomes. Overall, the investigation underscores the efficacy of Convolutional Neural Network (CNN) modeling in Alzheimer's disease analysis and identifies EfficientNetB5 as the optimal model for accurate classification.
Co-Authors Anjelita Ferensca Kaminang Arwin E. T. Pangaila Djamal, Eleonora Elshadai Gracia Carolina Rampengan Rampengan Ferrell Sanger Frans, Rycko Giovann Leon George Morris William Tangka Green Arther Sandag Jeremy Andrew Pongantung Jian Kezia Tesalonica Yuune Jimmy H Moedjahedy Marchel Thimoty Tombeng Masengi, Julio Joseph Victor Michelle G. Tene Reymon Rotikan Reynaldo Daingah Rolly Junius Lontaan Sondakh, Debby Erce Stenly Ibrahim Adam Stenly Richard Pungus Syalom Gabriela Wagey Venisa Tewu Yonatan Putra Mamahit