Claim Missing Document
Check
Articles

Found 14 Documents
Search

Convolutional Neural Network and Support Vector Machine in Classification of Flower Images Ari Peryanto; Anton Yudhana; Rusydi Umar
Khazanah Informatika Vol. 8 No. 1 April 2022
Publisher : Department of Informatics, Universitas Muhammadiyah Surakarta, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23917/khif.v8i1.15531

Abstract

Flowers are among the raw materials in many industries including the pharmaceuticals and cosmetics. Manual classification of flowers requires expert judgment of a botanist and can be time consuming and inconsistent. The ability to classify flowers using computers and technology is the right solution to solve this problem. There are two algorithms that are popular in image classification, namely Convolutional Neural Network (CNN) and Support Vector Machine (SVM). CNN is one of deep neural network classification algorithms while SVM is one of machine learning algorithm. This research was an effort to determine the best performer of the two methods in flower image classification. Our observation suggests that CNN outperform SVM in flower image classification. CNN gives an accuracy of 91.6%, precision of 91.6%, recall of 91.6% and F1 Score of 91.6%.
Rancang Bangun Klasifikasi Citra Dengan Teknologi Deep Learning Berbasis Metode Convolutional Neural Network Ari Peryanto; Anton Yudhana; Rusydi Umar
FORMAT Vol 8, No 2 (2019)
Publisher : Universitas Mercu Buana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/format.2019.v8.i2.007

Abstract

Dengan berkembang pesatnya teknologi saat ini, mengakibatkan Deep Learning menjadi salah satu metode machine learning yang sangat diminati. Teknologi GPU Acceleration menjadi salah satu sebab dari pesatnya perkembangan Deep Learning. Deep learning sangat cocok digunakan untuk memecahkan permasalahan klasik dalam Computer Vision, yaitu dalam pengklasifikasian citra. Salah satu metode dalam deep  learning yang  sering digunakan dalam pengolah  citra  adalah  Convolutional Neural Network dan merupakan pengembangan dari Multi Layer Perceptron. Pada penelitian ini pengimplementasian  metode ini dilakukan  menggunakan library  keras dengan bahasa pemrograman phyton.  Pada  proses  training  menggunakan  Convolutional  Neural  Network,  dilakukan  setting  jumlah epoch dan memperbesar ukuran data training untuk meningkatkan akurasi dalam pengklasifikasian citra. Ukuran yang digunakan adalah 32x32, 64x64 dan 128x128. Proses training dengan jumlah epoch 40 dan ukuran 32x32 didapat nilai akurasi tertinggi yang mencapai 98,02% dan rata-rata akurasi tertinggi yaitu 97,56 %, serta  akurasi sistem sebesar 96,64%.
Klasifikasi Citra Menggunakan Convolutional Neural Network dan K Fold Cross Validation Ari Peryanto; Anton Yudhana; Rusydi Umar
Journal of Applied Informatics and Computing Vol 4 No 1 (2020): Juli 2020
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1169.96 KB) | DOI: 10.30871/jaic.v4i1.2017

Abstract

Image classification is a fairly easy task for humans, but for machines it is something that is very complex and is a major problem in the field of Computer Vision which has long been sought for a solution. There are many algorithms used for image classification, one of which is Convolutional Neural Network, which is the development of Multi Layer Perceptron (MLP) and is one of the algorithms of Deep Learning. This method has the most significant results in image recognition, because this method tries to imitate the image recognition system in the human visual cortex, so it has the ability to process image information. In this research the implementation of this method is done by using the Keras library with the Python programming language. The results showed the percentage of accuracy with K = 5 cross-validation obtained the highest level of accuracy of 80.36% and the highest average accuracy of 76.49%, and system accuracy of 72.02%. For the lowest accuracy obtained in the 4th and 5th testing with an accuracy value of 66.07%. The system that has been made has also been able to predict with the highest average prediction of 60.31%, and the highest prediction value of 65.47%.
Pengembangan Sistem Informasi Penunjang Pelayanan Hotel (Studi Kasus: Hotel XYZ) Umar, Rusydi; Nugrahantoro, Achmad; Periyanto, Ari; Nugroho, Aji; Kharismajati, Gema; Susanto, Dwi
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 4, No 2 (2020): EDISI SEPTEMBER
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v4i2.216

Abstract

The hotel is a building that provides lodging services, restaurants, and other services that provide commercial for visitors. The use of hotel services that are still manual will be handled on the effectiveness of excellent service in hotel management. Computer technology support can be a solution in optimizing administrative activities, improving information, and making decisions. Hotel XYZ as one that still uses a manual transaction system. Then it is necessary to integrate data for each transaction using an interconnected database. Steps in the development of information systems need to be considered in improving the services of each hotel. The technique by collecting data to produce literature studies is an appropriate step to analyze the old system while developing the expected system. The results will be made on the design of the system for the database so that they are interconnected and the interface is easily understood by the user so that it facilitates the process of system implementation. After doing research, the black box test with a value of 100% with the results as expected is done. Comparison of the old system can be made by Microsoft Excel with interconnected databases presenting reports in printed form. It can meet the level of user satisfaction with a value of 95.3% of the results of the questionnaire from the five respondents involved.
Edukasi Bijak Kelola Sampah untuk Masa Depan Berkelanjutan Aditya, Anggie Yudistira; Susanto, Dwi; Peryanto, Ari; Widodo, Yuwono Fitri
Jurnal Pengabdian Masyarakat Bangsa Vol. 2 No. 12 (2025): Februari
Publisher : Amirul Bangun Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59837/jpmba.v2i12.2022

Abstract

Sampah menjadi isu global yang mendesak, terutama di negara berkembang seperti Indonesia, yang menghasilkan 68,5 juta ton sampah pada tahun 2021. Di wilayah Joho, Jambidan, Bantul, pengelolaan sampah masih menjadi tantangan akibat rendahnya kesadaran masyarakat, terbatasnya fasilitas pengelolaan, serta kebiasaan membakar sampah yang mencemari lingkungan. Untuk mengatasi permasalahan tersebut, dilakukan edukasi dan sosialisasi pengelolaan sampah berkelanjutan bertujuan meningkatkan pengetahuan, mengubah perilaku, dan mendorong partisipasi aktif masyarakat. Metode yang digunakan meliputi wawancara, penyebaran kuesioner, dan pemberian materi sosialisasi. Hasil wawancara menunjukkan bahwa 50% masyarakat tidak mengetahui metode pengelolaan sampah yang benar, sementara kuesioner mengungkapkan jenis dan pola pembuangan sampah serta tingkat pengetahuan masyarakat. Materi penyuluhan disampaikan pada 20 Januari 2025 berhasil meningkatkan pemahaman masyarakat terkait pemilahan sampah organik dan anorganik, teknik pengomposan sederhana, dan pentingnya daur ulang. Tingkat pengetahuan masyarakat meningkat dari 50% tidak mengetahui menjadi 20%, dengan 40% mengetahui dan 40% sangat mengetahui pengelolaan sampah. Kegiatan ini menunjukkan bahwa edukasi dan pendekatan partisipatif efektif dalam meningkatkan kesadaran masyarakat terhadap pengelolaan sampah yang ramah lingkungan. Keterlibatan aktif masyarakat melalui tanya jawab dan praktik langsung mencerminkan kesiapan mereka untuk mengimplementasikan perubahan perilaku. Kesimpulannya, kegiatan ini memberikan kontribusi signifikan dalam menciptakan kesadaran dan tindakan nyata menuju lingkungan yang lebih bersih, sehat, dan berkelanjutan.
Classification of Skin Disease Images Using K-Nearest Neighbour (KNN) Ari Peryanto; Susanto, Dwi; Jihad, Bagus Hayatul
Journal of Advanced Health Informatics Research Vol. 2 No. 3 (2024)
Publisher : Peneliti Teknologi Teknik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59247/jahir.v2i3.300

Abstract

The skin is the outermost part of the human body that is often exposed to the environment, so it is easy to experience disease disorders. Some of the skin diseases that are often contracted in humans are ulcers, herpes, and warts. Untreated skin diseases will be very annoying because of the sensation of itching so it can cause irritation and inflammation. The ability to classify skin diseases using technology is one solution. This study uses the K-Nearest Neighbour (KNN) method to detect images of skin diseases. KNN is one of the machine learning methods with a calculation method based on the proximity of k. KNN was chosen because it is fast and has high-accuracy results. The results of the research that has been carried out have obtained results of accuracy of 63%, precision of 63%, recall of 63%, and F1 Score of 63%. From the results of the study, it can be concluded that disease detection using KNN has been successfully applied and can be used in classification.
Klasifikasi Citra Bekicot Menggunakan Algoritma Support Vector Machine Peryanto, Ari; Hakim, Lukmanul; Nugrahantoro, Achmad
Jurnal IT UHB Vol 6 No 2 (2025): Jurnal Ilmu Komputer dan Teknologi
Publisher : Universitas Harapan Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35960/ikomti.v6i2.1790

Abstract

Snails are one of the animals that are widely found in Indonesia, but they are often considered pests and are not used optimally. In fact, there are several types of snails that have high economic value and can be exported, especially to countries such as France that use snails as restaurant cuisine. On a small scale, the process of classifying local and imported snails can be done manually however, if there are a lot of them, an automated system is needed to help the classification process become faster and more accurate. This study proposes a classification method based on Support Vector Machine (SVM) to distinguish local and imported snails. SVM is used as a classification model because of its ability to handle high-dimensional data and complex patterns. The results of the study showed an accuracy of 54%, so it can be an effective solution in the process of sorting snails on a large scale.
Digitalisasi Sistem Keuangan dan Informasi Berbasis Android di RT 05 Karangsari, Sendangtirto, Berbah, Sleman Peryanto, Ari; Susanto, Dwi; Widodo, Yuwono Fitri; Aditya, Anggie Yudistira
Jurnal Pengabdian Masyarakat - PIMAS Vol. 4 No. 1 (2025): Februari
Publisher : LPPM Universitas Harapan Bangsa Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35960/pimas.v4i1.1796

Abstract

Some issues in the neighborhood RT (community association) do not arise without reason. So far, the RT management has not received adequate attention from the local government. The challenges faced by RT administrators in carrying out their duties often conflict with their personal responsibilities as heads of families who need to earn a living, so services to the community can only be provided in the evening or on holidays. The community financial application is designed to address issues in monitoring payment of contributions, difficulties in the contribution collection process, and the management of data that is still done manually, often leading to errors in payment records. With this community financial application, the author hopes that it can make it easier for residents to make contribution payments in a practical and efficient manner, provide monthly financial reports, and remind residents who have not paid through two notifications each month. This application also allows residents to get to know each other through the block menu and helps the administrators in lightening their tasks as well as monitoring the recording and data collection of community contributions.
KLASIFIKASI CITRA BUNGA MENGGUNAKAN METODE SUPPORT VECTOR MACHINE DAN GRAY LEVEL CO-OCCURRENCE MATRIX Peryanto, Ari; Susanto, Dwi; Widodo, Yuwono Fitri
Jurnal Informatika Vol 9, No 2 (2025): JIKA (Jurnal Informatika)
Publisher : University of Muhammadiyah Tangerang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31000/jika.v9i2.13151

Abstract

Flowers are an important raw material in the pharmaceutical and cosmetic industries. However, manual flower classification requires special skills, is time-consuming, and is prone to inconsistency. This study proposes the use of Machine Learning (ML) technology, especially the Support Vector Machine (SVM) method, to automate the flower classification process. The Gray Level Co-occurrence Matrix (GLCM) is a method used in extracting visual features of flowers and will obtain parameters such as contrast, correlation, energy, and homogeneity. The research stages include data collection, image preprocessing, feature extraction, classification model creation, and model performance evaluation using a confusion matrix. The results show that the classification model built is able to achieve an optimal accuracy of 78.3%. This approach shows great potential in improving the efficiency and consistency of automatic flower classification.
Meninjau Peranan Text Mining sebagai Alat Strategis dalam Industri Kreatif melalui Sajian Webinar Hakim, Lukmanul; Peryanto, Ari; Susanto, Dwi; Fitri Widodo, Yuwono
Jurnal Pengabdian Masyarakat - PIMAS Vol. 4 No. 3 (2025): Agustus
Publisher : LPPM Universitas Harapan Bangsa Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35960/pimas.v4i3.1868

Abstract

The growth of unstructured data has been triggering a big data explosion. About 90 percent of the current unstructured data has not been fully analyzed so that cannot be used for valuable new information. Text mining can process text data to be extracted into new knowledge, identify significant patterns, and find hidden correlations. The use of text mining can be applied to various themes such as encouraging creativity in industry, society, and researchers by focusing on exploration versus exploitation strategies in crowdsourcing contests by utilizing data from proposals to make close and distance classifications between proposals, analyze sentiment tone on product launch announcements or creative economy programs and make correlations with sales data or public interest in a post-launch program, performing software lifecycle management by leveraging new ideas from users/customers such as Google reviews to create clusters of topics discussed in the comment section, and combining a topic-search approach and language style that can make a successful Kickstarter campaign. In this article, the author discusses the definition, process, application, and integration of text mining in the context of encouraging the creative industry to innovate further.