Claim Missing Document
Check
Articles

Found 11 Documents
Search

THERMAL IMAGING DETEKSI KERUSAKAN DAUN PADA TANAMAN CABE Lubis, Adyanata
Riau Journal Of Computer Science Vol. 6 No. 1 (2020): Riau Journal of Computer Science
Publisher : Riau Journal Of Computer Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (397.713 KB)

Abstract

This study aims to implement pest detection using a camera so that it can see the point of leaf damage by pests in chili plants, the method used is thermal imaging technic, from observations and trials on chili plants there is image data from the detection period, the data is analyzed using thermal images so that it can spread the damage to pests of chili plants
IDENTIFICATION AND DIAGNOSIS EXPERT SYSTEM DESIGN FOR OIL PLANT DISEASE USING FORWARD CHAINING Iskandar; Lubis, Adyanata; Prasiwinigrum, Elyandri; Maulana, Sabda
RJOCS (Riau Journal of Computer Science) Vol. 7 No. 2 (2021): RJOCS (Riau Journal of Computer Science)
Publisher : Fakultas Ilmu Komputer, Universitas Pasir Pengaraian

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30606/rjocs.v7i2.1835

Abstract

This research was conducted to create an expert system expert system that can identify and diagnose major diseases of oil palm trees with chaining forward method. The system is designed to analyze a disease that can strike at the nursery stage, the plants in the field, both at thestage of immature plantations (TBM) and crop yield (TM). The result of this research is a learning system to provide knowledge regarding the disease of oil crops by utilizing a computer.
Analisa Visualisasi Data Penjualan dan Tingkat Kepuasan Penjualan Menggunakan Platform Lookerstudio Arfandi, Zirhan; Yanto, Budi; Sabri, Khairul; Aini, Yulfita; Lubis, Adyanata
RJOCS (Riau Journal of Computer Science) Vol. 10 No. 1 (2024): RJOCS (Riau Journal of Computer Science)
Publisher : Fakultas Ilmu Komputer, Universitas Pasir Pengaraian

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30606/rjocs.v10i1.2402

Abstract

Data management in projects is an important activity in a company because over time the company develops more and more versatile data it has. Growing and highly complex business and supply of goods on a large scale makes data processing difficult. In the current situation, data processing starting from exporting, filtering data, analyzing and visualizing data is still done using Excel files which takes quite a long time, so that management decision making is still not optimal. . The purpose of this research is to provide users with important information and data in real time to speed up the decision-making process. Therefore, the data must be analyzed using the exploratory data analysis (EDA) method. EDA is carried out starting from understanding business objects, with revenue/sales as one of the metrics used to see the company's performance profile and the correlation of other variables. target knife The results of this study indicate that monthly sales comparisons, sales comparisons for each product and composition have the lowest sales generation and customer satisfaction, so that they can be used as material for management evaluation and EDA results can be seen in data visualization applications
Implementasi Deep Learning dengan Convolutional Neural Network untuk Pendeteksian Hama pada Sawi Hijau Menggunakan Google Colab Ulfi, Meitra; Nurliani; Nurafidah, Annisa; Saudah; Lubis, Adyanata
RJOCS (Riau Journal of Computer Science) Vol. 10 No. 2 (2024): RJOCS (Riau Journal of Computer Science)
Publisher : Fakultas Ilmu Komputer, Universitas Pasir Pengaraian

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30606/rjocs.v10i2.2854

Abstract

Penelitian ini mengkaji penerapan metode Convolutional Neural Network (CNN) untuk mengidentifikasi penyakit hama pada daun sawi hijau berdasarkan gambar berwarna, dengan tujuan utama mengembangkan model yang mampu mendeteksi berbagai jenis penyakit hama dengan akurasi tinggi guna membantu petani dalam mengelola penyakit pada tanaman sawi hijau secara lebih efektif. Google Colab digunakan sebagai platform pemrosesan karena menyediakan lingkungan komputasi yang kuat dengan akses gratis ke GPU, sehingga mempercepat pelatihan model. Dataset yang digunakan dalam penelitian ini diperoleh dari platform Kaggle, yang menyediakan 100 gambar sampel untuk pelatihan dan 50 gambar untuk validasi yang terbagi dalam dua kelas: sehat dan terinfeksi hama. Validasi dilakukan untuk menguji kemampuan model dalam memprediksi data baru yang belum pernah dilihat sebelumnya, dan model CNN dibangun menggunakan berbagai pustaka seperti TensorFlow, Keras, NumPy, Pandas, Matplotlib, dan scikit-learn. Hasil penelitian menunjukkan bahwa model CNN yang dikembangkan mampu mencapai akurasi sebesar 99% pada pengujian menggunakan 10 epoch. Dengan hasil ini, diharapkan sistem yang diusulkan dapat digunakan sebagai alat bantu yang efektif bagi petani dalam mengidentifikasi penyakit hama pada daun sawi hijau, sehingga dapat meningkatkan hasil dan kualitas produksi tanaman sawi hijau
Implementation of PageRank Algorithm for Visualization and Weighting of Keyword Networks in Scientific Papers Lubis, Adyanata; Prasiwiningrum, Elyandri
Journal of Applied Data Sciences Vol 4, No 4: DECEMBER 2023
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v4i4.138

Abstract

Papers are written works that contain thoughts about a particular problem or topic that are written systematically accompanied by logical analysis. Scientific papers are often found on the internet or in libraries for various titles of scientific papers, citations or references can be found in every scientific paper and can be obtained easily, but to display all citations in scientific papers in the form of visualization cannot be done easily. Visualizing the citation network of scientific papers in the form of a graph, with nodes representing research papers and edges representing the relationship between researchers' scientific papers and other scientific papers based on scientific paper citations. This research uses the pagerank algorithm to create a keyword network that has a high relationship and potential relevance in a data library. This research is the first research in using the pagerank algorithm and testing its accuracy by comparing with KNN and linear clustering. The presentation displays the citation of scientific papers based on the size of the node by showing the number of citations of the scientific paper. It can be concluded that all processes in the system have run according to design, and functionally the visualization system and weighting of the scientific paper citation network are in accordance with the design. The results obtained from 51 articles, this algorithm produces a visual user interest of 81.60%, compared to the accuracy of the data suitability produced by the linear clustering and KNN algorithms in the form of 71.22% and 61.34%, helping to facilitate the search for scientific papers in large quantities.
Creating Interactive Learning Media On The Adobe Animate 2021 Application As A Means Of Learning Graphic Design At SMA Negeri 3 Tambusai Utara Wahyudi, Sri; Efendi; Amelia Chandra, Detri; Lubis, Adyanata
Journal of ICT Applications System Vol 1 No 2 (2022): Journal of ICT Aplications and System
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (279.761 KB) | DOI: 10.56313/jictas.v1i2.194

Abstract

The development of learning media that is able to contain various types of text, graphics, audio and video can help in a learning, one of which is learning media with introduction material to Adobe Photoshop CS3 based on Adobe Animate 2021. This study aims to develop a learning media introduction to Adobe Photoshop CS3 based on Adobe Animate, The development model used in this study is the ADDIE model. The purpose of the study was to Create Interactive Learning Media introduction to Adobe Photoshop CS3 in the subject of Graphic Design produces interactive learning media products that are in accordance with basic competencies, material on the introduction of Adobe Photoshop CS3 which is equipped with video tutorials. So that interactive learning media introduction to Adobe Photoshop CS3 based on Adobe Animatecan be used as a good teaching aid in the learning process at school
Consumen Laptop Service Notification System In Android-Based Family Computer Shops Iskandar; Alvin, Muhammad; Hayadi, B. Herawan; Lubis, Adyanata
Journal of ICT Applications System Vol 1 No 2 (2022): Journal of ICT Aplications and System
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (328.394 KB) | DOI: 10.56313/jictas.v1i2.200

Abstract

Currently the Family Computer store already has 3 branches and for sales matters it implements an offline and online system. But at this time the store still uses an offline system in terms of service matters such as: Warranty Claims, Service, and Current Status Checks.For this reason, research was carried out which aims to create a program to provide services online so that users when there are problems can provide easier access.This research was made after passing observations and interviews from local parties. Making this program uses the Android Studio application to create an Android application where almost everyone has an Android cellphone, and uses the Firebase Cloud Messagging feature from Google to provide service access to users so that users can monitor and get the latest information from the program without having to come to the store. or notify the admin at the store
Leveraging K-Nearest Neighbors with SMOTE and Boosting Techniques for Data Imbalance and Accuracy Improvement Lubis, Adyanata; Irawan, Yuda; Junadhi, Junadhi; Defit, Sarjon
Journal of Applied Data Sciences Vol 5, No 4: DECEMBER 2024
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v5i4.343

Abstract

This research addresses the issue of low accuracy in sentiment analysis on Israeli products on social media, initially achieving only 64% using the K-NN algorithm. Given the ongoing Israeli-Palestinian conflict, which has garnered widespread international attention and strong opinions, understanding public sentiment towards Israeli products is crucial. To improve accuracy, the study employs SMOTE to handle data imbalance and combines K-NN with boosting algorithms like AdaBoost and XGBoost, which were selected for their effectiveness in improving model performance on imbalanced and complex datasets. AdaBoost was chosen for its ability to enhance model accuracy by focusing on misclassified instances, while XGBoost was selected for its efficiency and robustness in handling large datasets with multiple features. The research process includes data pre-processing (cleaning, normalization, tokenization, stopwords removal, and stemming), labeling using a Lexicon-Based approach, and feature extraction with CountVectorizer and TF-IDF. SMOTE was applied to oversample the minority class to match the number of instances in the majority class, ensuring balanced representation before model training. A total of 1,145 datasets were divided into training and testing data with a ratio of 70:30. Results demonstrate that SMOTE increased K-NN accuracy to 77%. Interestingly, combining K-NN with AdaBoost after SMOTE achieved 72% accuracy, which, although lower than the 77% achieved with SMOTE alone, was higher than the 68% accuracy without SMOTE. This discrepancy can be attributed to the added complexity introduced by AdaBoost, which may not synergize as effectively with SMOTE as XGBoost does, particularly in this dataset's context. In contrast, K-NN with XGBoost after SMOTE reached the highest accuracy of 88%, demonstrating a more effective combination. Boosting without SMOTE resulted in lower accuracies: 68% for KNN+AdaBoost and 64% for KNN+XGBoost. The combination of K-NN with SMOTE and XGBoost significantly improves model accuracy and reliability for sentiment analysis on social media.
Using Artificial Neural Networks and the Kohonen Method, an Image Pattern Recognition System for Khat Art Types Rasna, Rasna; Lubis, Adyanata; Suryadi, Dikky; Bani, Alexius Ulan; Nugroho, Fifto
International Journal of Engineering, Science and Information Technology Vol 5, No 2 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i2.851

Abstract

Arabic letter writing is known as khat art. Khat is classified into many categories and can be identified into three types: Khat Naskhi, Khat Qufi, and Khat Farisi, per the rules established in the art of Khat. Arabic letters, the subjects of khat art, evolved following the region where it first appeared. As a result, the Qufi style, for instance, marked the start of the evolution of Khat in the tenth century. Previously somewhat rigid, Khat became more fluid and beautiful, although it remained angular. Subsequently, the art of Sulus, Naskhi, Raiham, Riqa, and Tauqi evolved and exhibited the form of Khat, cursive (italic)—artificial neural network-based khat art type recognition by selecting the Kohonen
Penerapan Metode Forward Chaining Pada Sakit Gusi Handayani, Meli; Hayadi, B.Herawan; Lubis, Adyanata
Journal of ICT Applications System Vol 1 No 1 (2022): Journal of ICT Aplications and System
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (290.79 KB) | DOI: 10.56313/jictas.v1i1.128

Abstract

Sampai saat ini, perkembangan teknologi informasi telah merambah ke berbagai sektor termasuk di sektor kesehatan yang mampu membantu dalam mendiagnosa penyakit melalui gejala yang diberikan serta dapat memberikan solusi penanganan penyakit. Salah satu penyakit yang dapat dilakukan diagnosa dengan adanya perkembangan teknologi komputer adalah penyakit gusi. Penyakit gusi adalah penyakit infeksi yang menyerang pada jaringan di sekitar gigi. Kondisi ini merupakan penyebab utama dari gigi yang lepas pada orang dewasa. Perawatan gigi merupakan salah satu usaha penjagaan untuk mencegah kerusakan gigi dan penyakit gusi. Penyakit gusi dapat menyerang siapa saja baik menyerang bayi, balita, remaja bahkan menyerang orang dewasa. Menurut jurnal penelitian dari Mubasyiroh, dan Andayasari (2017:141) berpendapat bahwa Penyakit gigi dapat berupa kerusakan gigi (karies) dan penyakit gusi. Penyakit gigi dan mulut (termasuk karies dan penyakit periodontal) merupakan masalah yang cukup tinggi yang dikeluhkan oleh masyarakat. Adapun cabang ilmu komputer yang dapat melakukan diagnosa untuk mengetahui penyakit gusi adalah sistem pakar.Berdasarkan hasil pembahasan diatas, maka didapatkan jawaban B1, B2, B3 sampai dengan B9 gejala penyakit berdasarkan pilihan pertanyaan yang dipilih, itu menandakan, bahwa sistem pakar dengan metode forward chaining dapat mengatasi penyakit gusi dengan tingkat kepercayaan 89%