Claim Missing Document
Check
Articles

Found 14 Documents
Search

Komparasi Algoritma Support Vector Machine Dan Naive Bayes Pada Klasifikasi Ras Kucing Jaka Kusuma; Abwabul Jinan; Muhammad Zulkarnain Lubis; Rubianto Rubianto; Rika Rosnelly
Generic Vol 14 No 1 (2022): Vol 14, No 1 (2022)
Publisher : Fakultas Ilmu Komputer, Universitas Sriwijaya

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

Abstract

Salah satu hewan peliharaan yang paling populer ialah kucing. Kucing dipilih menjadi hewan peliharaan manusia karena tingkahnya sangat lucu. Kucing memiliki variasi ras yang sangat banyak. Terdapat 315 ras kucing pada seluruh dunia yang mana setiap ras kucing mempunyai ciri-ciri tertentu, akibat banyaknya terjadi perkawinan silang antara kucing kampung dan kucing ras dalam penentuan ras kucing menjadi lebih sulit. Seiring perkembangan zaman yang begitu cepat, perkembangan teknologi informasi pengenalan objek citra menjadi subjek yang sangat menarik dan tentunya berkaitan erat dengan data informasi. Maka peneliti akan melakukan komparasi antara algoritma Support Vector Machine (SVM) dan Naive Bayes (NB) pada klasifikasi citra ras kucing dengan memanfaatkan model Deep Learning SqueezeNet sebagai proses ekstraksi fitur pada citra. Dari hasil penelitian ini akan membuktikan secara empiris perbedaan antara accuracy, precision dan recall dari setiap algoritma. Hasil yang diperoleh menunjukan bahwa, dalam hal klasifikasi yang terbaik yaitu algoritma Support Vector Machine (SVM) dengan nilai accuracy 88.4%, precision 88.5% dan recall 88.4% sedangkan yang terendah adalah algoritma Naive Bayes (NB) dengan nilai accuracy 79.5%, precision 79.9% dan recall 79.5%.
RANCANG BANGUN APLIKASI RAMBU-RAMBU LALU LINTAS DALAM BENTUK POP QUIS BERBASIS ANDROID Abwabul Jinan; Frans Ikorasaki
IT (INFORMATIC TECHNIQUE) JOURNAL Vol 8, No 2 (2020): IT JOURNAL OKTOBER 2020
Publisher : Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/it.8.2.2020.184-198

Abstract

Saat ini perkembangan Tren Teknologi Informasi terus meningkat dengan cepat termasuk aspek pendidikan. Tidak terkecuali aspek pendidikan pada anak. Pendidikan bervariasi dan kreatif tapi yang masih mengandung unsur pendidikan cenderung dipilih oleh mereka. Hal ini dibuktikan dari sejumlah besar aplikasi atau game dengan unsur-unsur pendidikan di Android. Selama ini masih banyak yang tidak mengerti arti dari rambu-rambu lalu lintas sehingga perlu untuk mengetahui dan memahami pengertian rambu-rambu lalu lintas tersebut. Banyaknya terjadi pelangaran rambu lalu lintas di jalan raya karena minimnya pemahaman tentang peraturan dan arti dari rambu-rambu lalu lintas tersebut. Seperti seringnya terjadi menerobos lampu lalu lintas, salah parkir, salah berhenti, dan sebagainya, maka perlunya pemahaman tentang rambu-rambu lalu lintas terutama untuk anak-anak. Dengan adanya aplikasi rambu-rambu berbasis Android. Sangat berguna untuk anak-anak maupun masyarakat pada umumnya dalam proses belajar dan memahami arti dari rambu-rambu lalu lintas.
Bulldog Breed Classification Using VGG-19 and Ensemble Learning Abwabul Jinan; Zakarias Situmorang; Rika Rosnelly
Proceeding of International Conference on Information Science and Technology Innovation (ICoSTEC) Vol. 2 No. 1 (2023): Proceeding of International Conference on Information Science and Technology In
Publisher : Universitas Respati Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35842/icostec.v2i1.29

Abstract

In image classification, the C4.5, Adaboost, and Gradient Boosting algorithms need another method to extract the image's features in the classification process. This research employs transfer learning with the VGG-19 network for the image's features extraction and transfers the result as a dataset to classify image-based Bulldog breeds. As the classifier to classify the extracted features from the VGG 16 model, we employ three ensemble learning algorithms, namely C4.5, AdaBoost, and Gradient Boost. The training data classification results of the American, English, and French bulldog breeds show that, with a 20-fold cross-validation evaluation, the Gradient Boosting algorithm performs the best, with an accuracy value of 0.958, a precision value of 0.958 and recall value of 0.933. And show the highest accuracy (0.933), precision (0.938), and recall (0.933) in the testing data classification. While in the testing data classification, the Gradient Boosting algorithm scores an accuracy value of 0.933, a precision value of 0.938, and a recall value of 0.933
Comparing Neural Networks, Support Vector Machines, and Naïve Bayes Algorhythms for Classifying Banana Types Abwabul Jinan; Manutur Siregar; Vicky Rolanda; Dede Fika Suryani; Abdul Muis
Journal of Computer Networks, Architecture and High Performance Computing Vol. 6 No. 1 (2024): Article Research Volume 6 Issue 1, January 2024
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/cnahpc.v6i1.3381

Abstract

One of the most significant fruits for human consumption is the banana. Fruit consumption not only promotes health but also lowers the risk of heart disease, stroke, digestive issues, hypertension, some cancers, cataracts in the eyes, skin ailments, cholesterol reduction, and, perhaps most importantly, boosts immunity.The study included secondary data, which is information gathered from online resources like Kaggle. Ten categories of bananas will be identified from the 531 total varieties of bananas used as a train dataset: Ambon bananas, Stone bananas, Cavendish bananas, Kepok bananas, Mas bananas, Red bananas, plantains, Milk bananas, Horn bananas, and Varigata bananas. The development of information technology for image object recognition has become a very intriguing topic along with the rapid advancement of society, and it is undoubtedly directly tied to information data. In order to examine Naive Bayes, Support Vector Machine, and Neural Network techniques for classifying banana types, researchers will use the SqueezeNet Deep Learning model to extract features from photos. The study's findings will provide empirical evidence for the distinctions between each algorithm's accuracy, recall, and precision. Based on the collected results, the Neural Network (NN) method is the best in terms of classification, with accuracy of 72.3%, precision of 72.1%, and recall of 72.3%.
Disguising Text Using Caesar Cipher, Reverse Cipher and Least Significant Bit (LSB) Algorithms in Video Siregar, Manutur; Jinan, Abwabul; Muhammad Raja Gunung, Tar
Journal of Computer Networks, Architecture and High Performance Computing Vol. 6 No. 3 (2024): Articles Research Volume 6 Issue 3, July 2024
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/cnahpc.v6i3.4217

Abstract

In communication, there is a process of transferring information from the sender to the recipient. The information sent must be the same as the information received. If there are differences, it means that there has been a data change process carried out by irresponsible parties. One technique for changing the content of information is man in the middle. The data changer will receive information from the sender, then change it and forward it to the recipient, so that the changed information appears to have come from the sender.To protect information, this can be done by utilizing the science of cryptography and steganography which aims to protect information by changing it to another form or by inserting the information into other media. In this research, to protect information the Caesar Cipher Algorithm is used, this algorithm will change the letters in plaintext to another letter (ciphertext) by using an alphabetical shift according to the number in the form of the key used, namely > 1 and < 26, then the Reverse Cipher algorithm is carried out, namely changing the position of the letters of the plaintext from the first order to the last order and so on. The encrypted information will then be inserted into a video using the Steganography Algorithm, namely Least Significant Bit (LSB). Before being inserted, the video will first be converted into several image frames, then in one frame the information will be inserted. This can be done because the frame is a collection of RGB arrays which have values 0-255 or 0 and 1. So the insertion is done in bit form. Frames containing information will then be converted back into a video.On the receiving side, the video will be converted into a frame, next is the process of retrieving the information that was previously inserted. The information that has been taken is then reversed in order and then shifted using the Caesar chipper algorithm according to the key used by the sender, then the first letter of each word is changed to capital, so that the information sent is the same as that received. The implication of this research is that it is a way to combine cryptography with steganography as an information security technique.
Implementasi Metode Case-Based Reasoning (CBR) dalam Sistem Pakar untuk Mendapatkan Diagnosis Anxiety Disorders Gunung, Tar Muhammad Raja; Lubis, Siti Sahara; Siregar, Manutur; Simanjuntak, Peter Jaya Negara; Jinan, Abwabul
Jurnal Teknologi Terpadu Vol 10 No 2 (2024): Desember, 2024
Publisher : LPPM STT Terpadu Nurul Fikri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54914/jtt.v10i2.1480

Abstract

This research aims to develop an expert system based on the case-based reasoning method for diagnosing anxiety disorders. Anxiety Disorder is a mental health disorder that is often experienced by the public but is often not detected correctly. The case-based reasoning method was chosen because of its ability to utilise previous cases to solve new problems that have similarities. Case-based reasoning uses four main stages: retrieval, reuse, revise, and retain. The case-based reasoning method is implemented using case data obtained from psychology clinics and interviews with mental health experts. Testing the case-based reasoning method shows a high level of accuracy in diagnosing various types of Anxiety Disorders, such as Generalised Anxiety Disorder, Panic Disorder, and Specific Phobias. The results of this study show that the case-based reasoning method can be an effective tool in helping mental health professionals diagnose Anxiety Disorders more quickly and accurately. After searching using the symptoms obtained, the percentage of each type of disease is the percentage of Generalised Anxiety Disorder 35.7%, the percentage of Panic Disorder 30.7%, and the percentage of Specific Phobias 65%.
Penerapan Algoritma Sorting dalam Penentuan Pekerja Pada Aplikasi Cari Kerja Oleh dan Untuk Warga Satu Kelurahan Dataran Tinggi Binjai Siregar, Manutur Pandapotan; Jinan, Abwabul; Siagian, Akbar Idaman Prince Peter S.
METHOMIKA: Jurnal Manajemen Informatika & Komputerisasi Akuntansi Vol. 8 No. 2 (2024): METHOMIKA: Jurnal Manajemen Informatika & Komputersisasi Akuntansi
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/jmika.Vol8No2.pp294-300

Abstract

The current job search process often involves posting an announcement on paper or a banner on a notice board, or in front of the company’s location. Another common method is through job search applications, such as JobStreet and others. The first method has a drawback because people may not know when the job posting is published. Meanwhile, with the second method, many people hesitate to use these applications as they feel their skills may not be sufficient. To address these issues, an Android or web-based job search application is proposed to facilitate job sharing and job seeking within a nearby area, specifically within a single subdistrict. This application is targeted at individuals with a high school education level or lower, and the jobs shared are typically daily work requiring minimal skills, such as construction work, electrical repairs, gardening, cleaning, and similar tasks. A sorting algorithm will be implemented to help select the nearest and most suitable candidate for each job. To access the application, users must first register, enabling employers to post jobs and workers to find suitable positions.
Comparing Neural Networks, Support Vector Machines, and Naïve Bayes Algorhythms for Classifying Banana Types Jinan, Abwabul; Siregar, Manutur; Rolanda, Vicky; Suryani, Dede Fika; Muis, Abdul
Journal of Computer Networks, Architecture and High Performance Computing Vol. 6 No. 1 (2024): Article Research Volume 6 Issue 1, January 2024
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/cnahpc.v6i1.3381

Abstract

One of the most significant fruits for human consumption is the banana. Fruit consumption not only promotes health but also lowers the risk of heart disease, stroke, digestive issues, hypertension, some cancers, cataracts in the eyes, skin ailments, cholesterol reduction, and, perhaps most importantly, boosts immunity.The study included secondary data, which is information gathered from online resources like Kaggle. Ten categories of bananas will be identified from the 531 total varieties of bananas used as a train dataset: Ambon bananas, Stone bananas, Cavendish bananas, Kepok bananas, Mas bananas, Red bananas, plantains, Milk bananas, Horn bananas, and Varigata bananas. The development of information technology for image object recognition has become a very intriguing topic along with the rapid advancement of society, and it is undoubtedly directly tied to information data. In order to examine Naive Bayes, Support Vector Machine, and Neural Network techniques for classifying banana types, researchers will use the SqueezeNet Deep Learning model to extract features from photos. The study's findings will provide empirical evidence for the distinctions between each algorithm's accuracy, recall, and precision. Based on the collected results, the Neural Network (NN) method is the best in terms of classification, with accuracy of 72.3%, precision of 72.1%, and recall of 72.3%.
Desain dan Rancang Bangun Sistem E-Learning Menggunakan Framework Laravel Berbasis WEB Jinan, Abwabul; Siregar, Manutur Pandapotan; Suryani, Dede Fika; Rolanda, Vicky; Muis, Abdul
ROUTERS: Jurnal Sistem dan Teknologi Informasi Vol. 3 No. 2, Juli 2025 (In Progress)
Publisher : Program Studi Teknologi Rekayasa Internet, Politeknik Negeri Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25181/rt.v3i2.4182

Abstract

The design and development of a web-based E-Learning system using the Laravel framework aims to provide an effective and structured digital learning solution. This system is developed to address the limitations of face-to-face learning time in traditional classrooms and to leverage technological advancements in order to enhance educational quality. Utilizing Laravel as the primary development framework, the system is built with PHP, HTML, CSS, and JavaScript technologies, and MySQL as the database engine. The E-Learning platform features core functionalities such as instructional material management, class administration, structured user accounts (admin, teacher, and student roles), as well as support for material download and task submission. Testing results indicate that the system performs effectively and supports flexible and efficient teaching and learning processes. It is expected that this system will serve as a reliable and sustainable learning medium to support technology-based academic activities.
Penerapan Decision Tree Algoritma C4.5 Dalam Penentuan Izin Pembongkaran Muatan Kapal Kusuma, Jaka; Jinan, Abwabul; Situmorang, Zakarias
MEANS (Media Informasi Analisa dan Sistem) Volume 7 Nomor 1
Publisher : LPPM UNIKA Santo Thomas Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (595.022 KB) | DOI: 10.54367/means.v7i1.1632

Abstract

Along with the increasing number of bulk cargoes that are dismantled every year at belawan port and for the creation of services in accordance with expectations, it is necessary to develop services in support of indonesia's logistics improvement readiness, especially in terms of demolition. Utilization of machine learning using the C4.5 algorithm can make it easier to conduct selection and classification of the feasibility of ships that get permission for demolition activities. The use of the C4.5 algorithm will produce a decision tree that can equalize the results of data mining, so that the information obtained from the data will be easier to identify in testing methods using the Orange Data Mining tool. The results obtained by the C4.5 algorithm in the form of a decision tree with an accuracy value of 84%, 90% precision and 84% recall.