Article Per Year (5 Year)
p-Index From 2019 - 2024
2.808
P-Index
This Author published in this journals
All Journal Sinkron : Jurnal dan Penelitian Teknik Informatika JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Jurnal Mantik Penusa Jurnal Mantik Jusikom: Jurnal Sistem Informasi Ilmu Komputer INFOKUM Jurnal Sistem Informasi dan Teknologi Jaringan (SISFOTEKJAR) DISTANCE: Journal of Data Science, Technology, and Computer Science
Insidini Fawwaz
Universitas Prima Indonesia
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Engineering Languange, Linguistic, Communication & Media

Published : 19 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 19 Documents
Search

 1   2 
IMPLEMENTASI RESTORASI CITRA MENGGUNAKAN ALGORITMA INTERPOLASI RADIAL BASIS FUNCTIONS Devin Teheri; Denny Wijaya; Juvendi Juvendi; Steven Lunoto; Insidini Fawwaz
Jurnal Mantik Penusa Vol. 3 No. 1.1 (19): Manajemen dan Ilmu Komputer
Publisher : Lembaga Penelitian dan Pengabdian (LPPM) STMIK Pelita Nusantara Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (373.321 KB)

Abstract

Citra sering mengalami penurunan kualitas citra, misalnya karena mengandung cacat atau derau (noise). Noise pada citra ada berbagai jenis, salah satunya adalah noise dengan bintik putih yang tersebar dalam suatu citra (Salt and pepper). Untuk meningkatkan kembali kualitas citra yang memliki noise, maka diperlukan perbaikan citra atau restorasi citra. Restorasi citra adalah proses perbaikan atau pengembalian citra yang mengalami degradasi ataupun noise. Namun, proses penghilangan noise ini terkadang justru menyamarkan citra asli dan menyebabkan turunnya kualitas citra hasil. Salah satu teknik yang dapat diterapkan adalah algoritma interpolasi radial basis functions. Algoritma interpolasi radial basis function adalah suatu algoritma yang digunakan untuk memperbaiki kerusakan gambar dengan cara interpolasi gambar. Algoritma ini biasanya digunakan untuk memulihkan bagian-bagian yang hilang dan sebagainya.Teknik ini mencakup pengisian area yang hilang atau modifikasi bagian yang rusak pada piksel citra. Dari hasil pengujian, restorasi citra dengan algoritma interpolasi radial basis functions dapat memperbaiki citra yang memiliki noise (derau) menjadi citra yang lebih bagus kualitasnya. Hal ini terlihat dari nilai MSE dan PSNR yang diperoleh. Metode Interpolasi Radial Basis Functions dapat digunakan untuk melakukan proses restorasi citra digital dengan waktu eksekusi yang relatif cepat untuk ukuran citra yang lebih kecil.
IMAGE ENHANCEMENT KOMBINASI METODE FUZZY FILTERING DENGAN METODE GAUSSIAN FILTERING Tawarta Wiranata Gultom; Lisandra Veronica Tambunan; Jeckson Febryanto Sianipar; Gian Nugraha; Rian Surya M. Ilham; Insidini Fawwaz
Jurnal Mantik Penusa Vol. 3 No. 1.1 (19): Manajemen dan Ilmu Komputer
Publisher : Lembaga Penelitian dan Pengabdian (LPPM) STMIK Pelita Nusantara Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1059.518 KB)

Abstract

Citra adalah salah satu komponen dalam multimedia yang berperan penting karena mengandung informasi dalam bentuk visual. Penyampaian informasi dengan citra terkadang tidak diikuti oleh kualitas citra yang ada. Seringkali ada gangguan pada citra yang ditemukan, seperti dalam bentuk bintik-bintik yang mungkin disebabkan oleh gambar yang tidak baik, baik pembesaran (zoom) saat mengambil gambar, kontras dan pencahayaan yang tidak cocok saat mengambil gambar dan sebagainya. Fuzzy filter dapat digunakan untuk mengurangi derau pada citra digital dan menghasilkan nilai MSE yang rendah. Penelitian terdahulu menyimpulkan bahwa dengan menggunakan fuzzy filter, derau tidak hanya berkurang namun citra juga akan menjadi lebih jelas. Metode lain yang memiliki kegunaan yang sama dengan fuzzy filter, yaitu Gaussian filter. Gaussian filter merupakan metode yang baik untuk mengurangi derau pada citra digital. Pernyataan ini didukung peneliti lain yang mengatakan bahwa Gaussian filter menghasilkan sebuah gambar yang memiliki kualitas yang lebih baik dibandingkan dengan citra sebelum filter diaplikasikan. Oleh karena itu, penelitian ini bertujuan untuk menganalisis kombinasi dari kedua metode tersebut, yaitu fuzzy filter dan Gaussian  filter untuk pengurangan noise pada citra. Untuk menguji kelayakan metode yang diusulkan maka dalam penelitian ini dilakukan perbandingan hasil output citra antara metode yang diusulkan dengan metode lain yaitu Wiener Filter. Metode yang diusulkan menghasilkan efek pada citra yang cenderung blur namun dapat mereduksi noise pada citra. Kualitas citra juga mengalami peningkatan. Hal ini dapat dilihat dari nilai MSE dan RMSE yang dihasilkan lebih kecil sedangkan untuk nilai PSNR nya lebih besar dibandingkan dengan hasil Wiener  Filter.
Comparative Analysis Of Chaotic Cat MAP And Fibonacci Image Scrambling Methods To Secure Digital Image: Comparative Analysis Of Chaotic Cat MAP And Fibonacci Image Scrambling Methods To Secure Digital Image Hendra Hendra; Johanus Kurniawan; Insidini Fawwaz
Jurnal Mantik Vol. 3 No. 4 (2020): February: Manajemen, Teknologi Informatika dan Komunikasi (Mantik)
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (768.727 KB)

Abstract

In the process of communication through the internet network, security is an important issue that needs serious attention. This is because the process of sending and communicating data through the internet has the possibility to be intercepted by other parties. This also applies to image data. Therefore, data to be sent via the internet must be secured first. However, the application of several cryptographic methods and several methods of randomization of images requires a relatively long time. To solve the problems encountered, the Image Scrambling Generalized Fibonacci And Chaotic Cat Map algorithm can be applied. The work process of the algorithm will start from the process of selecting the input image and charging the key value that will be used. After that, the process continues with the process of randomizing the image, so that it will produce a randomized image. The resulting image can be reconstructed again by applying an anti-scrambling algorithm. This process requires the same key to be used at the scrambling stage. The resulting application can randomize the original image by filling in the randomization key value. The resulting image can be reconstructed again using the same key. In addition, the application will also produce detailed reports of calculations performed during the scrambling and anti-scrambling processes for each of these methods.
Analysis of T-Code Compression Methods to Increase Capacity of SSCE Method Marzuki Leo; Charles Halim; Iola Iola; Jeremy Valtino; Insidini Fawwaz
Jurnal Mantik Vol. 4 No. 3 (2020): November: Manajemen, Teknologi Informatika dan Komunikasi (Mantik)
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mantik.Vol4.2020.978.pp1678-1689

Abstract

The process of hiding classified information can take advantage of the steganography method. However, media such as images, audio or video is not efficient, due to the large size of the media, making text media a great solution for hiding confidential information. In 2011, a new steganographic method was introduced that uses special code generation based on the use of unlimited articles or on conjunctions with nouns that are not specific or specific to English. A new code representation method Secret Steganography Code for Embedding (SSCE) was also used to increase security. However, there is a problem with the application of this text steganography method, namely that the secret message has not been compressed, where if the cover text is smaller than the secret message, the secret message cannot be inserted into the cover text. To solve this problem, a text compression method can be applied. One of the compression methods that can be applied is the T-Code text compression method. The T-Code method uses the concept of iterative code construction and self-synchronization to compress and decompress text. From the testing process, information was obtained that every change of letter or word in the position where the secret message bit is attached will cause the secret message that is extracted to become chaotic and the T-Code compression method can increase the capacity of the cover document by 10.61%.
Linear Kernel and Polynomial Analysis in Recognizing Tuberculosis Image Using HOG Feature Extraction Ira Farenda Sudirman; Winda Hartati Giawa; Intan Permatasari Sarumaha; Sukurman Ndraha; Insidini Fawwaz
Jurnal Mantik Vol. 4 No. 3 (2020): November: Manajemen, Teknologi Informatika dan Komunikasi (Mantik)
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mantik.Vol4.2020.980.pp1695-1700

Abstract

Tuberculosis (TB) is an airborne disease caused by mycobacterium tuberculosis (MTB) which usually attacks the lungs which can cause severe coughing, fever and chest pain. The recognition of TB negative and positive TB x-ray image patterns in this study uses HOG feature extraction and the SVM method as a classification method by adding linear and polynomial kernel functions to the SVM method. This is because even though it is very good at solving classification problems, SVM can only be used on linear data, so that in order to be used on non-linear data, SVM must be modified using kernel functions. The results showed that the linear kernel was better at classifying the x-ray image of TB with an average accuracy of 79.50% while the polynomial kernel was 77.50%.
IMPROVEMENT OF DIGITAL IMAGE USING A COMBINATION OF ALPHA TRIMMED MEAN FILTER AND ARITHMETIC MEAN FILTER Insidini Fawwaz; N P Dharshinni; Irfan Hindrawan
INFOKUM Vol. 10 No. 02 (2022): Juni, Data Mining, Image Processing, and artificial intelligence
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (944.539 KB)

Abstract

The development of technology at this time causes the provision of information to increase through social media. Many social media users convey information by including digital images. Digital images are very important in conveying the accuracy of information. However, digital images often experience various disturbances, such as decreased pixel quality, less sharpness, blurring, and the appearance of noise in the image. Noise contained in the image causes a decrease in image quality. Image degradation can be caused by uneven light intensity and can also be caused by dirt adhering to the camera lens. There are various types of noise found in digital images, including Salt And Pepper Noise, Speckle Noise, and Rayleigh Noise. There are many filtering methods that can improve digital images from noise interference. Some of them are the Mean Filter method, Geometric Mean Filter, Harmonic Mean Filter, Arithmetic Mean Filter, Median Filter, Midpoint filter, Alpha Trimmed Mean Filter and so on. Based on the research conducted, the combination of the Alpha Trimmed Mean Filter and Arithmetic Mean Filter methods can reduce Salt and Pepper noise, Speckle noise and Rayleigh noise better than the Alpha Trimmed Mean Filter and Arithmetic Mean Filter methods based on the MSE, RMSE and PSNR parameters.
WEBSITE-BASED LIBRARY DATA PROCESSING DESIGN Insidini Fawwaz; Erwin Conery Firtan; Steven -; Helbert Yawin
Jurnal Sistem Informasi dan Ilmu Komputer Prima(JUSIKOM PRIMA) Vol. 7 No. 1 (2023): Jurnal Sistem Informasi dan Ilmu Komputer Prima (JUSIKOM Prima)
Publisher : Fakultas Teknologi dan Ilmu Komputer Universitas Prima Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34012/jurnalsisteminformasidanilmukomputer.v7i1.4029

Abstract

The main problem Indonesia faces, especially in education in the era of globalization, is the low quality of human resources. One of the efforts to improve the quality of human resources is to increase interest in reading and the habit of reading. From this fact, the library is expected to be the center of activities to develop interest in reading and reading habits. Libraries have a great responsibility to increase and generate interest in reading. Library data management is one of the essential activities in running a library. Librarians must be able to process and manage book data efficiently and effectively to avoid losing library property. This study uses PHP to create a website design to assist librarians in processing and storing data about existing books. This study designs a library data processing system that contains library book loans, such as recording books, transactions, and student data collection in the library. The results of this website design can facilitate library staff in organizing and tracking library management quickly and efficiently. Keywords: Digital Library, Library Website, Electronic Journal
Implementation of Transfer Learning in CNN for Classification of Nut Type Insidini Fawwaz; Jimmy Deardo Sagala; Reivaldo Kevin Febriawan Sijabat; Novita Marissa Maringga
Sinkron : jurnal dan penelitian teknik informatika Vol. 8 No. 4 (2023): Article Research Volume 8 Issue 4, October 2023
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v8i4.12784

Abstract

Nut has a high nutritional value and is widely used as an ingredient in cooking and snacks. Nut is included in the group of grains and has many types. Each type of nut has different nutritional content. Some types of nuts can also cause allergies or negative reactions in certain people, so it is important to identify the type of nut to be consumed. There are many types of nut that are different from each other, but some of them are similar. This makes it difficult to distinguish between the types of nuts, so there is a need for technology that can accurately identify nut types. Transfer Learning method is used to utilize trained models and applied to nut type classification. The two CNN models used are Inception V3 and Xception. The dataset consists of 11 types of nuts consisting of 1,320 data. The data is divided into 60% for training data and 40% for validation data. Preprocessing is done to ensure the image size is consistent and clarify the focus on the data image to be tested. The training results show that the Xception model is superior to Inception V3, with an accuracy of 86.36% on the validation data, while Inception V3 only reached 74.05%. Xception is able to predict nut types more precisely.
The Optimization of CNN Algorithm Using Transfer Learning for Marine Fauna Classification Insidini Fawwaz; Yennimar Yennimar; N P Dharsinni; Bayu Angga Wijaya
Sinkron : jurnal dan penelitian teknik informatika Vol. 8 No. 4 (2023): Article Research Volume 8 Issue 4, October 2023
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v8i4.12893

Abstract

Marine fauna are all types of organisms that live in the marine environment. Marine fauna is also an important part of the marine ecosystem that has an important role in maintaining environmental balance. However, the survival of marine fauna is threatened due to activities carried out by humans, such as pollution, overfishing, industrial waste disposal into marine waters, plastic pollution and so on. Therefore, efforts are needed to monitor and protect marine fauna so that marine ecosystems can remain stable. One way to monitor marine fauna is by using classification technology. One of the technologies that can be used in marine fauna classification technology is Convolutional Neural Network (CNN). CNN is one of the classification methods that can be used to classify objects in images with a high level of accuracy. The CNN architecture models used are MobileNet, Xception, and VGG19. Furthermore, the method used to improve the performance of the CNN algorithm is the Transfer Learning method. The test results show that the MobileNet architecture model produces the highest accuracy value of 91.94% compared to Xception and VGG19 which only get an accuracy value of 87.64% and 88.42%. This shows that the MobileNet model has a more optimal performance in classifying marine fauna.
Co-Authors Agus Winarta Andre Tarigan Azmi, Fadhillah Bayu Angga Wijaya Charles Halim Denny Wijaya Devin Teheri Erwin Conery Firtan Fadhillah Azmi FADHILLAH AZMI Gian Nugraha Helbert Yawin Hendra Hendra Intan Permatasari Sarumaha Iola Iola Ira Farenda Sudirman Irfan Hindrawan Jeckson Febryanto Sianipar Jeremy Valtino Jimmy Deardo Sagala Johanus Kurniawan Juvendi Juvendi Lisandra Veronica Tambunan Marzuki Leo Muhathir Muhathir Muhathir, Muhathir N P Dharshinni N P Dharsinni Novita Marissa Maringga Reivaldo Kevin Febriawan Sijabat Rian Surya M. Ilham Rina Anugrahwaty Steven - Steven Lunoto Sukurman Ndraha Tawarta Wiranata Gultom Winarta, Agus Winda Hartati Giawa Yennimar Yennimar