Lubis, Ahmadi Irmansyah
Unknown Affiliation

Published : 6 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 6 Documents
Search

The Application of Convolutional Neural Networks in Floristic Recognition Legito; Nuraini, Rini; Judijanto, Loso; Lubis, Ahmadi Irmansyah
International Journal Software Engineering and Computer Science (IJSECS) Vol. 3 No. 3 (2023): DECEMBER 2023
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v3i3.1827

Abstract

In the dynamic field of computer vision, this research explores the application of Convolutional Neural Networks (CNNs) for the complex task of floristic recognition, a critical aspect of botanical and ecological studies. Addressing the challenges posed by the vast diversity and subtle morphological differences among plants, our study leverages CNNs for an efficient and accurate plant identification method. Distinguished by a comprehensive dataset encompassing a wide range of plant species and employing a state-of-the-art CNN model, our research significantly advances the methodology of flower recognition. This paper highlights the CNN model's sophisticated feature extraction and image analysis capabilities, demonstrating its superior performance in classifying a diverse range of flora compared to traditional methods and other machine learning techniques like Support Vector Machines (SVM) and decision trees. Our approach emphasizes practical applications in areas such as agriculture, ecology, and conservation, and offers a powerful tool for rapid and efficient plant identification, crucial in biodiversity studies. The research contributes to the fields of botany, ecology, and environmental conservation, underscoring the transformative potential of CNNs in floristic recognition. It also outlines the future direction for enhancing the model's efficiency, including developing more computationally efficient architectures and expanding training datasets.
Penerapan Neural Network Dalam Klasifikasi Citra Permainan Batu Kertas Gunting dengan Probabilistic Neural Network Siregar, Siti Julianita; Lubis, Ahmadi Irmansyah; Ginting, Erika Fahmi
Building of Informatics, Technology and Science (BITS) Vol 3 No 3 (2021): December 2021
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (552.519 KB) | DOI: 10.47065/bits.v3i3.1143

Abstract

In this research, an image classification model was developed to distinguish hand objects pointing at rock, paper, and scissors using one of the popular image classification methods, namely the Probabilistic Neural Network. Probabilistic Neural Network is a method in an artificial neural network that is used to classify a category based on the results of calculating the distance between the density function and the probability. PNN has 4 stages of processing, namely Input Layer, Pattern Layer, Summation Layer, and Output Layer. Tests in the study were carried out with a total of 60 testing data from three object classes from the dataset. Then the results of the classification of Batu, Scissors, and Paper hand images using the application of the PNN algorithm in this research test obtained an average accuracy value of 90%
Application of Certainty Factor Method in Intelligent System for Diagnosis of Periodontal Disease in Cigarette AddictsApplication of Certainty Factor Method in Intelligent System for Diagnosis of Periodontal Disease in Cigarette Addicts Lubis, Ahmadi Irmansyah; Gaol, Nur Yanti Lumban
Sinkron : jurnal dan penelitian teknik informatika Vol. 6 No. 4 (2022): Article Research: Volume 6 Number 4, October 2022
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v7i4.11695

Abstract

This study discusses the design of an Android-based innovative application that is useful in the early diagnosis of periodontal disease in cigarette addicts. The problem which is the main topic of discussion in this study is the health issue of organs that are often ignored by humans, namely the teeth and mouth. Then one of the types of dental and oral diseases that many people often complain about is the periodontal disease which also gets less attention in Indonesian society. And one of the causes of this periodontal disease is caused by smoking habits. So to facilitate the identification in knowing the periodontal symptoms caused by the cigarette, a system that can identify the early symptoms of periodontal disease is needed. The technology proposed to build the system applies expert system technology with Certainty Factor. In building an android-based innovative application to diagnose periodontal disease, there are cigarette addicts in this study with the Research & Development research method to produce an output that can be right on target by the expected target. In addition, interviews and direct observation techniques were also carried out with experts or experts in the field of dental and oral diseases to collect the required data on the needs of the system to be built.
Forward Selection Attribute Reduction Technique for Optimizing Naïve Bayes Performance in Sperm Fertility Prediction Lubis, Ahmadi Irmansyah; Chandra, Rudy
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.v8i1.11967

Abstract

The problem of infertility between husband and wife is an important issue that destroys family harmony, and many people still consider infertility or infertility a female problem. However, about 7% of men of childbearing age suffer from infertility. The biggest factor causing male infertility is sperm quality problems. Sperm analysis can be the best predictor of male fertility potential. Machine learning and data mining techniques can be used to automate disease diagnosis. This study aims to obtain a regular form classification model from sperm sample data of 100 volunteers. This classification model can be used to predict male fertility levels into 2 classes, namely normal and alter (decreased fertility). This study uses a fertility dataset obtained from the UCI Machine Learning Repository. Before the data mining process, data preprocessing is required. The classification process is carried out using Naive Bayes and attribute reduction techniques using forward selection to see the increase in the accuracy of Naive Bayes performance. The Naive Bayes test without attribute reduction has an accuracy of 85%, while attribute reduction with forward selection has an accuracy of 88% in predicting sperm fertility. Therefore, by using forward selection with Naive Bayes to reduce attributes in this study, this study was able to increase accuracy by 3% and can be used to help predict sperm fertility
Analysis of docker container Implementation in SIEM infrastructure Ardi, Noper; Lubis, Ahmadi Irmansyah; Ikhwan Ash Shafa Arrafi
Journal of Applied Informatics and Computing Vol. 9 No. 3 (2025): June 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i3.9476

Abstract

It is known that configuring system information and event management (SIEM) infrastructure using conventional virtualization still provides essential functions. However, if a problem occurs such as a configuration error during the staging process or application service failure, the recovery process from the error requires quite a long time. This research aims to explore and analyze the implementation of container technology in the SIEM Infrastructure using the Wazuh platform. The analysis focuses on a Docker-based architecture running Wazuh's core components: the wazuh-indexer, wazuh-manager, and wazuh-dashboard, each in its own container. This approach is evaluated to see how containerization affects SIEM effectiveness and efficiency, particularly in resource utilization and fault recovery. Performance testing carried out on systems using Docker Containers shows lower Memory and CPU usage compared to Conventional Virtualization. The results demonstrate that Docker not only enhances resource efficiency but also improves system resilience, directly impacting SIEM operational functionality.
Aircraft Image Classification on a Small-Scale Dataset using MobileNetV2 with Grad-CAM as Explainable AI Lestari, Susi; Dzulfiqar, Mohamad Alif; Lubis, Ahmadi Irmansyah; Nova, Muhammad Andi; Zaimah, Zaimah; Mulyadi, Mulyadi
Journal of Applied Informatics and Computing Vol. 9 No. 5 (2025): October 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i5.10546

Abstract

This study explores aircraft image classification using MobileNetV2 combined with Gradient-weighted Class Activation Mapping (Grad-CAM) for model interpretability. A dataset of 1,500 balanced images—helicopters, propeller aircraft, and jets—was split into training, validation, and testing sets with data augmentation to reduce overfitting. Transfer learning with pre-trained MobileNetV2 achieved an accuracy of 87.56%, with macro-average precision and recall of 85.76% and 87.69%. Grad-CAM visualizations confirmed that correct predictions relied on distinctive features such as rotor blades, propellers, and engines, while misclassifications often stemmed from background distractions or less discriminative areas. These findings demonstrate the potential of lightweight architectures for small-scale datasets and highlight the value of Explainable AI in validating deep learning models. The study provides a practical reference for educational contexts and offers directions for future work with larger datasets.