Claim Missing Document
Check
Articles

Found 13 Documents
Search

Pendeteksi Kemiripan Dokumen (PKD) Menggunakan POSI (Percentage OF Similarity) Dengan Algoritma Genetika Sihombing, Poltak
Prosiding SNATIKA Vol 01 (2011) Vol 1
Publisher : Prosiding SNATIKA Vol 01 (2011)

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

Abstract

Dalam paper ini, penulis mengembangkan suatu formula POSI (Persentage Of Similarity) dengan Algortima Genetika (Genetic Algorithm, GA) untuk menemukan nilai kemiripan dokumen yang diperoleh dari suatu database. Kemiripan ini didasakan pada jumlah keyword (katakunci) yang ditemukan dan berkompetisi menggunakan GA. Sebagai data testing penulis menggunakan database dari koleksi jurnal, paper dan proceeding dari  BATAN (Badan Tenaga Atom Nasional) ditambah beberapa tesis (skripsi) mahasiswa sebagai benchmark data-set. Penulis memodifikasi keyword dari koleksi dokumen tersebut menjadi bentuk  kromosom dengan  maksud untuk mendapatkan nilai kemiripan yang paling optimum untuk diseleksi berdasarkan  fitness kromosom.  Penulis mengembangkan sebuah prototype mesin pencari dokumen yang disebut sebagai Pendeteksi Kemiripan Dokumen (PKD). PKD ini dapat dimanfaatkan untuk berbagai jenis database sesuai dengan keperluan yang dibutuhkan. Kata Kunci: database, optimasi, kemiripan, POSI, GA
Weighting Comparative Analysis Using Fuzzy Logic and Rank Order Centroid (ROC) in the Simple Additive Weighting (SAW) Method Ghazali, Alfin; Sihombing, Poltak; Zarlis, Muhammad
International Journal of Natural Science and Engineering Vol 5, No 2 (2021): July
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (307.467 KB) | DOI: 10.23887/ijnse.v5i2.37847

Abstract

The Covid-19 outbreak has changed the learning system in Indonesia into distance learning, better known as online learning. In determining student learning outcomes on student learning satisfaction with distance learning during the Covid-19 pandemic, a study was carried out using the Simple Additive Weighting (SAW) method. This study aims to determine student learning outcomes during the Covid-19 pandemic. The type of research used in this research is applied research, in which this research is directed to obtain information that can be used to solve problems. The method used is Simple Additive Weighting (SAW) by comparing the results of the decision of the SAW method between the weighting based on the Fuzzy Logic method and the weighting based on the ROC method. The subjects involved in this study were 36 students of Vocational High School (SMK). Data collection in the study was carried out using direct observation, interviews, and questionnaires. The criteria contained in the questionnaire are factors that affect the process of student learning outcomes on learning satisfaction during the Covid-19 pandemic. The criteria used are device ownership, accessibility, ease of obtaining materials, method accuracy, monitoring ability, interactivity, and independent learning. From the seven criteria, the priority scale is determined. The results showed that the analysis of the search for weight scores using the Simple Additive Weighting (SAW) method using Fuzzy Logic and Simple Additive Weighting (SAW) using the Rank Order Centroid (ROC) method resulted in different sub-criteria weighting scores, so it can be said that the combination of SAW- ROC provides a more accurate and more selective selection of the number of students.
Pelatihan Penggunaan Aplikasi Penjualan Hewan Ternak Yg Ada Di Kampung Kunyit Desa Tumpatan Nibung Untuk Peningkatan Pendapatan Ekonomi Nurahmadi, Fauzan; Sihombing, Poltak
Jurnal Masyarakat Indonesia (Jumas) Vol. 3 No. 01 (2024): Jurnal Masyarakat Indonesia (Jumas)
Publisher : Cattleya Darmaya Fortuna

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54209/jumas.v3i01.85

Abstract

This article aims to delve into the impact of training on the utilization of livestock sales applications on the local economy of Kampung Kunyit. The significance of incorporating technology into livestock marketing not only broadens perspectives but also enhances the skills and knowledge of the local community. This article discusses effective and applicable training methods. The piece explores the effective integration of technological advancements, specifically the utilization of a livestock sales application, as a catalyst for economic empowerment. Through a detailed examination, the training methods outlined in the article not only aim to increase digital literacy but also foster a deeper connection between the community and the evolving landscape of agricultural commerce. By steering away from commonplace language, the author successfully communicates complex concepts with precision, ensuring that the content resonates with a diverse audience. The narrative weaves through the challenges faced by rural communities in adapting to technological shifts, providing insights into the innovative strategies employed during the training sessions.
Combination of Ant Colony Tabu Search Algorithm with Firefly Tabu Search Algorithm (ACTS-FATS) in Solving the Traveling Salesman Problem (TSP) Harahap, Siti Sarah; Sihombing, Poltak; Zarlis, Muhammad
Sinkron : jurnal dan penelitian teknik informatika Vol. 7 No. 1 (2023): Articles Research Volume 7 Issue 1, 2023
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v8i1.12016

Abstract

Traveling Salesman Problem (TSP) is a classic combinatorial optimization problem, one of the optimization problems that can be applied to various activities such as finding the shortest path. The optimization problem in TSP is the most widely discussed and has become the standard for testing computational algorithms. TSP is a good object to test optimization performance. With scientific developments in the field of informatics, many researchers have optimized the application of algorithms to solve the Traveling Salesman Problem (TSP). In this study, researchers used a combination of Ant Colony Tabu Search – Firefly Algorithm Tabu Search (ACTS-FATS). The combination is doneto overcome Premature Convergence (trapped local optimum) which is a shortcoming of the ant colony algorithm, get the best running time by looking at the process of each point movement with the ant colony and firefly methods. After testing, getting the best running time results of 27.79%, and getting an accuracy rate of 17%.
Smart agriculture model in detecting oil palm plantation diseases using a convolution neural network Gunawan, Gunawan; Zarlis, Muhammad; Sihombing, Poltak; Sutarman, Sutarman
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 13, No 3: September 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v13.i3.pp3164-3171

Abstract

Planning models for sustainable crop care in the context of smart agriculture are complex issues as they involve many factors such as productivity, quality, growth sustainability, workforce use, and information technology use. In this study, we will create an optimized model using a convolution neural network (CNN) that can classify and monitor plant diseases. Part of the plant care system is to be aware of plant diseases and to be able to deal with them immediately. This study aims to acquire a new smart farming model for integrated crop care. The results of this research are findings in the form of a CNN model for classifying plant diseases detected from the leaves of the plants studied in oil palm. Testing using Google Colab obtains 100% accuracy and 99% accuracy using a teachable machine. The contributions of this paper create a new model in the field of informatics, especially in the field of intelligent agriculture based on information technology.
Development of the fuzzy grid partition methods in generating fuzzy rules for the classification of data set Marbun, Murni; Sitompul, Opim Salim; Nababan, Erna Budhiarti; Sihombing, Poltak
Bulletin of Electrical Engineering and Informatics Vol 13, No 3: June 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v13i3.5378

Abstract

The main weakness of complex and sizeable fuzzy rule systems is the complexity of data interpretation in terms of classification. Classification interpretation can be affected by reducing rules and removing important rules for several reasons. Based on the results of experiments using the fuzzy grid partition (FGP) approach for high-dimensional data, the difficulty in generating many fuzzy rules still increases exponentially as the number of characteristics increases. The solution to this problem is a hybrid method that combines the advantages of the rough set method and the FGP method, which is called the fuzzy grid partition rough set (FGPRS) method. In the Irish data, the rough set approach reduces the number of characteristics and objects so that data with excessive values can be minimized, and the fuzzy rules produced using the FGP method are more concise. The number of fuzzy rules produced using the FGPRS method at K=2 is 50%; at K=K+1, it is reduced by 66.7% and at K=2 K, it is reduced by 75%. Based on the findings of the data collection classification test, the FGPRS method has a classification accuracy rate of 83.33%, and all data can be classified.
Deep learning approaches for analyzing and controlling rumor spread in social networks using graph neural networks Manurung, Jonson; Sihombing, Poltak; Andri Budiman, Mohammad; Sawaluddin, Sawaluddin
Bulletin of Electrical Engineering and Informatics Vol 14, No 1: February 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v14i1.8143

Abstract

The pervasive influence of social networks on information dissemination necessitates robust strategies for understanding and mitigating the spread of rumors within these interconnected ecosystems. This research endeavors to address this imperative through the application of a graph neural network (GNN) model, designed to capture intricate relationships among users and content in social networks. The study integrates user-level attributes, content characteristics, and network structures to develop a comprehensive model capable of predicting the likelihood of rumor propagation. The proposed model is situated within a broader conceptual framework that incorporates sociological theories on information diffusion, user behavior, and network dynamics. The results of this research offer insights into the interpretability of the GNN model’s predictions and lay the groundwork for future investigations. The iterative refinement of the model, consideration of ethical implications, and comparison against traditional machine learning baselines emerge as crucial steps in advancing the understanding and application of deep learning methodologies for rumor control in social networks. By embracing the complexities of real-world scenarios and adhering to ethical standards, this research strives to contribute to the development of proactive tools for rumor management, fostering resilient and trustworthy online information ecosystems.
Target image validation modeling using deep neural network algorithm Mubarakah, Naemah; Sihombing, Poltak; Efendi, Syahril; Fahmi, Fahmi
International Journal of Electrical and Computer Engineering (IJECE) Vol 15, No 2: April 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v15i2.pp2042-2054

Abstract

Research on image validation models is an interesting topic. The application of deep learning (DL) for object detection has been demonstrated to effectively and efficiently address the challenges in this field. Deep neural networks (DNN) are deep learning algorithms capable of handling large datasets and effectively solving complex problems due to their robust learning capacity. Despite their ability to address complex problems, DNN encounter challenges related to the necessity for intricate architectures and a large number of hidden layers. The objective of this research is to identify the most effective model for achieving optimal performance in image validation. This study investigates target image validation using DNN algorithms, examining architectures with 3, 4, 5, and 6 hidden layers. This study also evaluates the performance of image validation across various activation functions, batch sizes, and numbers of neurons. The results of the study show that the best performance for image validation is achieved using the Leaky-ReLU and Sigmoid activation functions, with a batch size of 64, and an architecture consisting of 3 hidden layers with neuron sizes of 256, 128, and 64. This model is capable of providing real-time target image validation with an accuracy of up to 94.31%.
Analisis Random Forest Menggunakan Principal Component Analysis Pada Data Berdimensi Tinggi Diba, Farah; Lydia, Maya Silvi; Sihombing, Poltak
The Indonesian Journal of Computer Science Vol. 12 No. 4 (2023): The Indonesian Journal of Computer Science (IJCS)
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v12i4.3329

Abstract

Data yang memiliki dimensi tinggi membutuhkan metode machine learning yang mampu bekerja lebih cepat dan efektif dalam proses klasifikasi. Salah satu algoritma yang mampu menangani data kompleks adalah Random Forest. Random Forest bekerja dengan membangun beberapa decision tree secara random sebagai acuan feature selection. Namun, data berdimensi tinggi membutuhkan ruang penyimpanan yang lebih besar sehingga mengakibatkan lamanya proses komputasi. Oleh karena itu, Principal Component Analysis merupakan salah satu metode reduksi dimensi dalam merepresentasikan data berdimensi tinggi. PCA akan membentuk beberapa Principal Component yang mengandung informasi penting dari data asli. Dataset yang digunakan pada penelitian ini bersumber dari kaggle repository terdiri atas 26 atribut dan 129880 intances. Hasil dari penelitian ini RF dengan dengan n_estimators = 7 setelah direduksi PCA memiliki akurasi terbaik yaitu 90,13% pada data water quality.. Hal ini membuktikan bahwa PCA mampu mereduksi dimensi dengan membentuk pohon n_estimators sebanyak 7.
Weighting Comparative Analysis Using Fuzzy Logic and Rank Order Centroid (ROC) in the Simple Additive Weighting (SAW) Method Ghazali, Alfin; Sihombing, Poltak; Zarlis, Muhammad
International Journal of Natural Science and Engineering Vol. 5 No. 2 (2021): July
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (307.467 KB) | DOI: 10.23887/ijnse.v5i2.37847

Abstract

The Covid-19 outbreak has changed the learning system in Indonesia into distance learning, better known as online learning. In determining student learning outcomes on student learning satisfaction with distance learning during the Covid-19 pandemic, a study was carried out using the Simple Additive Weighting (SAW) method. This study aims to determine student learning outcomes during the Covid-19 pandemic. The type of research used in this research is applied research, in which this research is directed to obtain information that can be used to solve problems. The method used is Simple Additive Weighting (SAW) by comparing the results of the decision of the SAW method between the weighting based on the Fuzzy Logic method and the weighting based on the ROC method. The subjects involved in this study were 36 students of Vocational High School (SMK). Data collection in the study was carried out using direct observation, interviews, and questionnaires. The criteria contained in the questionnaire are factors that affect the process of student learning outcomes on learning satisfaction during the Covid-19 pandemic. The criteria used are device ownership, accessibility, ease of obtaining materials, method accuracy, monitoring ability, interactivity, and independent learning. From the seven criteria, the priority scale is determined. The results showed that the analysis of the search for weight scores using the Simple Additive Weighting (SAW) method using Fuzzy Logic and Simple Additive Weighting (SAW) using the Rank Order Centroid (ROC) method resulted in different sub-criteria weighting scores, so it can be said that the combination of SAW- ROC provides a more accurate and more selective selection of the number of students.