Christy Atika Sari - Academia.edu (original) (raw)

Papers by Christy Atika Sari

Research paper thumbnail of Secure Text Encryption for Iot Communication Using Affine Cipher and Diffie-Hellman Key Distribution on Arduino ATMEGA2560 Iot Devices

Jurnal Teknik Informatika, Aug 20, 2023

Research paper thumbnail of The Involvement of Local Binary Pattern to Improve the Accuracy of Multi Support Vector-Based Javanese Handwriting Character Recognition

JAIS (Journal of Applied Intelligent System), Jul 30, 2023

Research paper thumbnail of Komparasi Watermarking Dengan Lifting Wavelet Transform Dan Disctere Wavelet Transform

Jurnal Mnemonic, Feb 27, 2024

Privasi dan security merupakan hal yang sangat penting untuk dijaga pada era teknologi seperti se... more Privasi dan security merupakan hal yang sangat penting untuk dijaga pada era teknologi seperti sekarang. Cara untuk menjaga privasi dapat dilakukan dengan menggunakan pengamanan pada data. Data perlu dijaga karena didalam data tersebut terdapat informasi pribadi dan sangat bahaya apabila sampai disalahgunakan oleh pihak yang tidak bertanggung jawab. Watermarking merupakan proses yang dilakukan untuk melakukan pengamanan data dengan cara menyisipkan citra watermark ke dalam citra host atau utama. Tujuan dilakukannya watermarking yaitu untuk melakukan pengamanan pada citra. Pada penelitian ini akan dilakukan proses watermarking dengan menggunakan algoritma Lifting Wavelet Transform (LWT) dan Disctere Wavelet Transform (DWT). Tujuan dilakukannya penelitian ini yaitu untuk melakukan komparasi dari proses watermarking yang dimana nantinya dapat dilihat proses watermarking mana yang lebih baik untuk digunakan. Data yang digunakan pada penelitian ini yaitu citra host menggunakan citra Lena dan Baboon yang memiliki ukuran 512*512 pixel dan citra watermark dengan ukuran 64*64 pixel. Hasil yang didapatkan dari penelitian ini yaitu setelah dilakukan proses pengujian, dengan menggunakan citra lena, pada algoritma LWT mendapatkan nilai PSNR sebesar 47.5513 dB dan pada algoritma DWT mendapatkan PSNR sebesar 42.2207 dB.

Research paper thumbnail of Comparative Study of Machine Learning Algorithms for Performing Ham or Spam Classification in SMS

Scientific Journal of Informatics/Scientific journal of informatics, Feb 29, 2024

Research paper thumbnail of Otomatisasi Sistem Kontrol Tumbuh Kembang Toga (Tanaman Obat Keluarga) Berbasis Fuzzy C-Means

SEMNAS RISTEK (Seminar Nasional Riset dan Inovasi Teknologi), Jan 31, 2024

Tanaman TOGA adalah tanaman obat keluarga yang memiliki peran penting dalam pengobatan tradisiona... more Tanaman TOGA adalah tanaman obat keluarga yang memiliki peran penting dalam pengobatan tradisional. Dalam beberapa tahun terakhir, terjadi permasalahan serius terkait dengan pertumbuhan dan pemeliharaan tanaman TOGA, yang disebabkan oleh perubahan iklim, urbanisasi, dan kurangnya pengetahuan dalam budidaya tanaman ini. Untuk mengatasi tantangan ini, penelitian mengenai pengembangan Prototype Hidroponik Cerdas dilakukan. Prototype ini mengadopsi teknologi canggih yang memungkinkan pemantauan dan pengendalian otomatis terhadap semua aspek yang memengaruhi pertumbuhan tanaman, termasuk suhu, kelembaban udara, intensitas cahaya, pH larutan nutrisi, dan kadar oksigen dalam air. Dengan demikian, sistem ini mampu meningkatkan konsistensi, kecepatan pertumbuhan, dan kualitas tanaman TOGA, yang pada gilirannya mendukung ketersediaan sumber daya TOGA yang berkualitas tinggi bagi masyarakat serta berkontribusi pada pelestarian lingkungan yang lebih baik secara keseluruhan.

Research paper thumbnail of Performa Convolutional Neural Network Dalam Deep Layers RESNET-50 Untuk Klasifikasi Mri Tumor Otak

SEMNAS RISTEK (Seminar Nasional Riset dan Inovasi Teknologi), Jan 31, 2024

Research paper thumbnail of Klasifikasi Terumbu Karang Menggunakan CNN Mobilenet

SEMNAS RISTEK (Seminar Nasional Riset dan Inovasi Teknologi), Jan 31, 2024

Research paper thumbnail of Optimasi Invisible Watermarking Metode DCT Berbasis SVD Pada Citra Berwarna

SEMNAS RISTEK (Seminar Nasional Riset dan Inovasi Teknologi), Jan 31, 2024

Research paper thumbnail of Imperceptible and Robust Encryption: Salsa20 Stream Cipher for Colour Image Data

Research paper thumbnail of Text and Image Encryption Using Symmetric Cryptography Ron Rivest Cipher 2 (RC2)

In the current context, ensuring the secure transmission of data over the internet has become a c... more In the current context, ensuring the secure transmission of data over the internet has become a critical concern, with information technology playing a fundamental role. As society advances into the digital information age, the importance of network security issues continues to increase. Therefore, the need for cryptographic technology has emerged to overcome these challenges. Cryptography includes symmetric and asymmetric cryptography. An example of symmetric cryptography is the RC2 algorithm. RC2 is a symmetric encryption algorithm that uses a single key to encrypt and decrypt data. The ciphertext is then concealed within an image using the Stepic technique. The RC2 encryption method also utilizes symmetric encryption, ensuring the security of the encryption process while maintaining efficient encryption and decryption speeds. The result of this research is that the average percentage of MSE is 0.00%, and for PSNR and AVA are 70.85% and 34.93%. However, the AVA value is quite unstable because the average value is below 40%. Meanwhile, image encryption results in the longer the text that needs to be hidden in the image, the higher the UACI percentage. This is inversely proportional to the NPCR, the longer the text that needs to be hidden in the image, the lower the NPCR percentage. The average results obtained for UACI and NPCR values are 41.46% dan 98.13%.

Research paper thumbnail of Pneumonia Prediction Using Convolutional Neural Network

Research paper thumbnail of Crypto-Stegano Color Image Based on Rivest Cipher 4 (RC4) and Least Significant Bit (LSB)

JAIS (Journal of Applied Intelligent System), Jul 30, 2023

Research paper thumbnail of Ambon Banana Maturity Classification Based On Convolutional Neural Network (CNN)

Sinkron : jurnal dan penelitian teknik informatika, Sep 30, 2023

Research paper thumbnail of Autentikasi Citra RGB Menggunakan Kombinasi Fungsi Hash MD5 Dan Rsa

Proses autentikasi pada citra sangatlah penting dalam proses berbagi gambar agar tidak terjadi pe... more Proses autentikasi pada citra sangatlah penting dalam proses berbagi gambar agar tidak terjadi pemalsuan gambar saat dikirim melalui internet. Proses autentikasi dapat dilakukan dengan memberi identitas unik kepada tiap citra. MD5 merupakan salah satu algoritma yang sering digunakan dalam proses pembentukan identitas unik yang biasa disebut message digest. Untuk melindungi identitas unik ini agar tidak dimanipulasi oleh pihak lain, penulis menggabungkannya dengan RSA untuk memberikan keamanan tambahan. RSA merupakan salah satu public crypto system yang kuat oleh karena sulitnya memfaktorkan bilangan yang besar. Pada penelitian ini, pengujian gabungan metode yang diusulkan dilakukan dengan membandingan hasil message digest tiap citra sebelum dan sesudah mengalami proses filtering dan noising serta menggunakan perhitungan SSIM untuk mengetahui tingkat kemiripan citra. Dari hasil pengujian didapatkan bahwa gabungan MD5 dan RSA memiliki sensitivitas yang tinggi terhadap perubahan kecil....

Research paper thumbnail of Web Desa Wonosuko, Kemiri, Purworejo untuk Informasi Desa dan Peningkatan Pelayanan Masyarakat pada Masa Pandemi Covid-19

Journal of Interconnection Networks, Sep 20, 2021

Research paper thumbnail of Peningkatan Model Pembelajaran Pengenalan Binatang Melalui Video Animasi

Abdimasku, Jun 15, 2020

Pada makalah ini, telah dipaparkan mengenai cara pemebelajaran bagi anak usia dini. Terdpaat du a... more Pada makalah ini, telah dipaparkan mengenai cara pemebelajaran bagi anak usia dini. Terdpaat du acara pembelajaran dalam ranah visual, yaitu pembelajaran visual statis dan dinamis. Mitra pengabdian, dalam hal ini Guru TK PGRI 08 Purowyoso dan siswa anak usia 4-6 tahun sejumlah 45 orang, telah diobservasi dan terbukti bahwa hasil permbelajaran menggunakan video animasi memudahkan guru dalam mengajar, memudahkan siswa dalam belajar, menambah motivasi bekajar, siswa menjadi lebih aktif bertanya dan berani untuk menjelaskan apa yang mereka lihat dalam video tersebut. Dalam pengabdian yang telah dilakukan, digunakan materi pemebelajaran berupa video animasi yang diperkenalkan menggunakan laptop dan handphone serta buku animasi statis. Video dapat menjadi asisten dari guru dalam mengajar dan mempermudah penguasaan pemelajaran aktif bagi siswa.

Research paper thumbnail of Performance Analysis of LSB Image Steganography Combined with Blowfish-RC4 Encryption in Various File Extensions

Sending and exchanging important data through the internet is prone to be stolen by unauthorized ... more Sending and exchanging important data through the internet is prone to be stolen by unauthorized parties. The number of confidential data theft cases make the need for data security important. Steganography and cryptography can be used as tools to protect the security and confidentiality of confidential data. Steganography as a tool to hide confidential data while cryptography as a tool to randomize confidential data. The combination of the Least Significant Bit (LSB)- Blowfish and Rivest Code 4 (RC4) is proposed because it can provide layered protection on confidential data. The secret data is encrypted using the Blowfish algorithm and encrypted again using the RC4 algorithm before it is pinned on the LSB media cover in the form of images. The performance analysis of the combination of LSB and Blowfish-RC4 was carried out on various image sizes with messages that had various types of file extensions. The stego image was compared to determine the level of its imperceptibility with the cover image through Mean Square Error (MSE) test, Peak Signal to Noise Ratio (PSNR) test also histogram analysis from both of that images. Based on experiments showed good PSNR results with an average above 56dB. Meanwhile, the performance of cryptographic algorithms tested through entropy tests proved to be very good because it approached perfect values.

Research paper thumbnail of A Survey: Effect of the Number of GLCM Features on Classification Accuracy of Lasem Batik Images using K-Nearest Neighbor

2018 International Seminar on Research of Information Technology and Intelligent Systems (ISRITI), Nov 1, 2018

Lasem batik is one of traditional Indonesian’s famous batik that has high artistic and economic v... more Lasem batik is one of traditional Indonesian’s famous batik that has high artistic and economic value. Lasem batik can be classified into several different motifs. This study aims to analyze the number of gray level co-occurrence matrix (GLCM) features during the process of classification of Lasem batik image with K-Nearest Neighbor (KNN). KNN has advantages in overcoming probability density, able to consolidate calculations based on the number of neighbors specified, and can perform calculations with limited parameters. Feature extraction is one of the important steps before performing image classification. GLCM is one of the extraction features of a very popular texture. There are five GLCM features that are widely used, namely contrast, homogeneity, energy, correlation, and entropy. This research classifies five kinds of the famous motif of batik Lasem. The training and testing process compare the use of four and five GLCM features for each of the three experiments with different amounts of data. The test results show that the use of four and five types of GLCM features get the same accuracy in each experiment. It can be concluded that with KNN enough to use four kinds of features to speed up the calculation of the classification.

Research paper thumbnail of Landsat Image Classification Based on K-Nearest Neighbor

Research paper thumbnail of Javanese Character Recognition Based on K-Nearest Neighbor and Linear Binary Pattern Features

Kinetik : game technology, information system, computer network, computing, electronics, and control, Sep 29, 2022

Javanese script (Hanacaraka) is one of the cultures owned by Indonesia. Javanese script is found ... more Javanese script (Hanacaraka) is one of the cultures owned by Indonesia. Javanese script is found in temples, inscriptions, cultural and prehistoric sites, ancient Javanese manuscripts, Gulden series banknotes, street signage, and palace documents. Javanese script has a form with an article, and the use of reading above the script is a factor that affects the character detection process. Punctuation marks, clothing, Swara script, vowels, and consonants are parts of the script that are often found in Javanetest scripts. Preserving Javanese script in the digital era, of course, must use technology that can support the digitization of Javanese script through the script detection process. The concept of script image is the image of Javanese script in ancient manuscripts. The process of character detection using certain techniques can be carried out to extract characters so that they can be read. Detection of Javanese characters can be found by finding a testing image. Here, we had been used 10 words images consisting of 3 to 5 syllables with the vowel aiu. Dataset process by Linear Binary Pattern (LBP) feature extraction, which is used to characterize images and describe image textures locally. LBP has been used in r=4 and preprocessing is also done by thresholding with d=0.3. This process can be done using the K-Nearest Neighbor algorithm. In 10 datasets of Javanese script words, an average accuracy value of 90.5% was obtained. The accuracy value of 100% is the highest and 50% is the lowest.

Research paper thumbnail of Secure Text Encryption for Iot Communication Using Affine Cipher and Diffie-Hellman Key Distribution on Arduino ATMEGA2560 Iot Devices

Jurnal Teknik Informatika, Aug 20, 2023

Research paper thumbnail of The Involvement of Local Binary Pattern to Improve the Accuracy of Multi Support Vector-Based Javanese Handwriting Character Recognition

JAIS (Journal of Applied Intelligent System), Jul 30, 2023

Research paper thumbnail of Komparasi Watermarking Dengan Lifting Wavelet Transform Dan Disctere Wavelet Transform

Jurnal Mnemonic, Feb 27, 2024

Privasi dan security merupakan hal yang sangat penting untuk dijaga pada era teknologi seperti se... more Privasi dan security merupakan hal yang sangat penting untuk dijaga pada era teknologi seperti sekarang. Cara untuk menjaga privasi dapat dilakukan dengan menggunakan pengamanan pada data. Data perlu dijaga karena didalam data tersebut terdapat informasi pribadi dan sangat bahaya apabila sampai disalahgunakan oleh pihak yang tidak bertanggung jawab. Watermarking merupakan proses yang dilakukan untuk melakukan pengamanan data dengan cara menyisipkan citra watermark ke dalam citra host atau utama. Tujuan dilakukannya watermarking yaitu untuk melakukan pengamanan pada citra. Pada penelitian ini akan dilakukan proses watermarking dengan menggunakan algoritma Lifting Wavelet Transform (LWT) dan Disctere Wavelet Transform (DWT). Tujuan dilakukannya penelitian ini yaitu untuk melakukan komparasi dari proses watermarking yang dimana nantinya dapat dilihat proses watermarking mana yang lebih baik untuk digunakan. Data yang digunakan pada penelitian ini yaitu citra host menggunakan citra Lena dan Baboon yang memiliki ukuran 512*512 pixel dan citra watermark dengan ukuran 64*64 pixel. Hasil yang didapatkan dari penelitian ini yaitu setelah dilakukan proses pengujian, dengan menggunakan citra lena, pada algoritma LWT mendapatkan nilai PSNR sebesar 47.5513 dB dan pada algoritma DWT mendapatkan PSNR sebesar 42.2207 dB.

Research paper thumbnail of Comparative Study of Machine Learning Algorithms for Performing Ham or Spam Classification in SMS

Scientific Journal of Informatics/Scientific journal of informatics, Feb 29, 2024

Research paper thumbnail of Otomatisasi Sistem Kontrol Tumbuh Kembang Toga (Tanaman Obat Keluarga) Berbasis Fuzzy C-Means

SEMNAS RISTEK (Seminar Nasional Riset dan Inovasi Teknologi), Jan 31, 2024

Tanaman TOGA adalah tanaman obat keluarga yang memiliki peran penting dalam pengobatan tradisiona... more Tanaman TOGA adalah tanaman obat keluarga yang memiliki peran penting dalam pengobatan tradisional. Dalam beberapa tahun terakhir, terjadi permasalahan serius terkait dengan pertumbuhan dan pemeliharaan tanaman TOGA, yang disebabkan oleh perubahan iklim, urbanisasi, dan kurangnya pengetahuan dalam budidaya tanaman ini. Untuk mengatasi tantangan ini, penelitian mengenai pengembangan Prototype Hidroponik Cerdas dilakukan. Prototype ini mengadopsi teknologi canggih yang memungkinkan pemantauan dan pengendalian otomatis terhadap semua aspek yang memengaruhi pertumbuhan tanaman, termasuk suhu, kelembaban udara, intensitas cahaya, pH larutan nutrisi, dan kadar oksigen dalam air. Dengan demikian, sistem ini mampu meningkatkan konsistensi, kecepatan pertumbuhan, dan kualitas tanaman TOGA, yang pada gilirannya mendukung ketersediaan sumber daya TOGA yang berkualitas tinggi bagi masyarakat serta berkontribusi pada pelestarian lingkungan yang lebih baik secara keseluruhan.

Research paper thumbnail of Performa Convolutional Neural Network Dalam Deep Layers RESNET-50 Untuk Klasifikasi Mri Tumor Otak

SEMNAS RISTEK (Seminar Nasional Riset dan Inovasi Teknologi), Jan 31, 2024

Research paper thumbnail of Klasifikasi Terumbu Karang Menggunakan CNN Mobilenet

SEMNAS RISTEK (Seminar Nasional Riset dan Inovasi Teknologi), Jan 31, 2024

Research paper thumbnail of Optimasi Invisible Watermarking Metode DCT Berbasis SVD Pada Citra Berwarna

SEMNAS RISTEK (Seminar Nasional Riset dan Inovasi Teknologi), Jan 31, 2024

Research paper thumbnail of Imperceptible and Robust Encryption: Salsa20 Stream Cipher for Colour Image Data

Research paper thumbnail of Text and Image Encryption Using Symmetric Cryptography Ron Rivest Cipher 2 (RC2)

In the current context, ensuring the secure transmission of data over the internet has become a c... more In the current context, ensuring the secure transmission of data over the internet has become a critical concern, with information technology playing a fundamental role. As society advances into the digital information age, the importance of network security issues continues to increase. Therefore, the need for cryptographic technology has emerged to overcome these challenges. Cryptography includes symmetric and asymmetric cryptography. An example of symmetric cryptography is the RC2 algorithm. RC2 is a symmetric encryption algorithm that uses a single key to encrypt and decrypt data. The ciphertext is then concealed within an image using the Stepic technique. The RC2 encryption method also utilizes symmetric encryption, ensuring the security of the encryption process while maintaining efficient encryption and decryption speeds. The result of this research is that the average percentage of MSE is 0.00%, and for PSNR and AVA are 70.85% and 34.93%. However, the AVA value is quite unstable because the average value is below 40%. Meanwhile, image encryption results in the longer the text that needs to be hidden in the image, the higher the UACI percentage. This is inversely proportional to the NPCR, the longer the text that needs to be hidden in the image, the lower the NPCR percentage. The average results obtained for UACI and NPCR values are 41.46% dan 98.13%.

Research paper thumbnail of Pneumonia Prediction Using Convolutional Neural Network

Research paper thumbnail of Crypto-Stegano Color Image Based on Rivest Cipher 4 (RC4) and Least Significant Bit (LSB)

JAIS (Journal of Applied Intelligent System), Jul 30, 2023

Research paper thumbnail of Ambon Banana Maturity Classification Based On Convolutional Neural Network (CNN)

Sinkron : jurnal dan penelitian teknik informatika, Sep 30, 2023

Research paper thumbnail of Autentikasi Citra RGB Menggunakan Kombinasi Fungsi Hash MD5 Dan Rsa

Proses autentikasi pada citra sangatlah penting dalam proses berbagi gambar agar tidak terjadi pe... more Proses autentikasi pada citra sangatlah penting dalam proses berbagi gambar agar tidak terjadi pemalsuan gambar saat dikirim melalui internet. Proses autentikasi dapat dilakukan dengan memberi identitas unik kepada tiap citra. MD5 merupakan salah satu algoritma yang sering digunakan dalam proses pembentukan identitas unik yang biasa disebut message digest. Untuk melindungi identitas unik ini agar tidak dimanipulasi oleh pihak lain, penulis menggabungkannya dengan RSA untuk memberikan keamanan tambahan. RSA merupakan salah satu public crypto system yang kuat oleh karena sulitnya memfaktorkan bilangan yang besar. Pada penelitian ini, pengujian gabungan metode yang diusulkan dilakukan dengan membandingan hasil message digest tiap citra sebelum dan sesudah mengalami proses filtering dan noising serta menggunakan perhitungan SSIM untuk mengetahui tingkat kemiripan citra. Dari hasil pengujian didapatkan bahwa gabungan MD5 dan RSA memiliki sensitivitas yang tinggi terhadap perubahan kecil....

Research paper thumbnail of Web Desa Wonosuko, Kemiri, Purworejo untuk Informasi Desa dan Peningkatan Pelayanan Masyarakat pada Masa Pandemi Covid-19

Journal of Interconnection Networks, Sep 20, 2021

Research paper thumbnail of Peningkatan Model Pembelajaran Pengenalan Binatang Melalui Video Animasi

Abdimasku, Jun 15, 2020

Pada makalah ini, telah dipaparkan mengenai cara pemebelajaran bagi anak usia dini. Terdpaat du a... more Pada makalah ini, telah dipaparkan mengenai cara pemebelajaran bagi anak usia dini. Terdpaat du acara pembelajaran dalam ranah visual, yaitu pembelajaran visual statis dan dinamis. Mitra pengabdian, dalam hal ini Guru TK PGRI 08 Purowyoso dan siswa anak usia 4-6 tahun sejumlah 45 orang, telah diobservasi dan terbukti bahwa hasil permbelajaran menggunakan video animasi memudahkan guru dalam mengajar, memudahkan siswa dalam belajar, menambah motivasi bekajar, siswa menjadi lebih aktif bertanya dan berani untuk menjelaskan apa yang mereka lihat dalam video tersebut. Dalam pengabdian yang telah dilakukan, digunakan materi pemebelajaran berupa video animasi yang diperkenalkan menggunakan laptop dan handphone serta buku animasi statis. Video dapat menjadi asisten dari guru dalam mengajar dan mempermudah penguasaan pemelajaran aktif bagi siswa.

Research paper thumbnail of Performance Analysis of LSB Image Steganography Combined with Blowfish-RC4 Encryption in Various File Extensions

Sending and exchanging important data through the internet is prone to be stolen by unauthorized ... more Sending and exchanging important data through the internet is prone to be stolen by unauthorized parties. The number of confidential data theft cases make the need for data security important. Steganography and cryptography can be used as tools to protect the security and confidentiality of confidential data. Steganography as a tool to hide confidential data while cryptography as a tool to randomize confidential data. The combination of the Least Significant Bit (LSB)- Blowfish and Rivest Code 4 (RC4) is proposed because it can provide layered protection on confidential data. The secret data is encrypted using the Blowfish algorithm and encrypted again using the RC4 algorithm before it is pinned on the LSB media cover in the form of images. The performance analysis of the combination of LSB and Blowfish-RC4 was carried out on various image sizes with messages that had various types of file extensions. The stego image was compared to determine the level of its imperceptibility with the cover image through Mean Square Error (MSE) test, Peak Signal to Noise Ratio (PSNR) test also histogram analysis from both of that images. Based on experiments showed good PSNR results with an average above 56dB. Meanwhile, the performance of cryptographic algorithms tested through entropy tests proved to be very good because it approached perfect values.

Research paper thumbnail of A Survey: Effect of the Number of GLCM Features on Classification Accuracy of Lasem Batik Images using K-Nearest Neighbor

2018 International Seminar on Research of Information Technology and Intelligent Systems (ISRITI), Nov 1, 2018

Lasem batik is one of traditional Indonesian’s famous batik that has high artistic and economic v... more Lasem batik is one of traditional Indonesian’s famous batik that has high artistic and economic value. Lasem batik can be classified into several different motifs. This study aims to analyze the number of gray level co-occurrence matrix (GLCM) features during the process of classification of Lasem batik image with K-Nearest Neighbor (KNN). KNN has advantages in overcoming probability density, able to consolidate calculations based on the number of neighbors specified, and can perform calculations with limited parameters. Feature extraction is one of the important steps before performing image classification. GLCM is one of the extraction features of a very popular texture. There are five GLCM features that are widely used, namely contrast, homogeneity, energy, correlation, and entropy. This research classifies five kinds of the famous motif of batik Lasem. The training and testing process compare the use of four and five GLCM features for each of the three experiments with different amounts of data. The test results show that the use of four and five types of GLCM features get the same accuracy in each experiment. It can be concluded that with KNN enough to use four kinds of features to speed up the calculation of the classification.

Research paper thumbnail of Landsat Image Classification Based on K-Nearest Neighbor

Research paper thumbnail of Javanese Character Recognition Based on K-Nearest Neighbor and Linear Binary Pattern Features

Kinetik : game technology, information system, computer network, computing, electronics, and control, Sep 29, 2022

Javanese script (Hanacaraka) is one of the cultures owned by Indonesia. Javanese script is found ... more Javanese script (Hanacaraka) is one of the cultures owned by Indonesia. Javanese script is found in temples, inscriptions, cultural and prehistoric sites, ancient Javanese manuscripts, Gulden series banknotes, street signage, and palace documents. Javanese script has a form with an article, and the use of reading above the script is a factor that affects the character detection process. Punctuation marks, clothing, Swara script, vowels, and consonants are parts of the script that are often found in Javanetest scripts. Preserving Javanese script in the digital era, of course, must use technology that can support the digitization of Javanese script through the script detection process. The concept of script image is the image of Javanese script in ancient manuscripts. The process of character detection using certain techniques can be carried out to extract characters so that they can be read. Detection of Javanese characters can be found by finding a testing image. Here, we had been used 10 words images consisting of 3 to 5 syllables with the vowel aiu. Dataset process by Linear Binary Pattern (LBP) feature extraction, which is used to characterize images and describe image textures locally. LBP has been used in r=4 and preprocessing is also done by thresholding with d=0.3. This process can be done using the K-Nearest Neighbor algorithm. In 10 datasets of Javanese script words, an average accuracy value of 90.5% was obtained. The accuracy value of 100% is the highest and 50% is the lowest.