Papers by didi DIDI ROSIYADI
Jasa layananan telemedis memanfaatkan kemajuan teknologi informasi untuk pertukaran informasi dan... more Jasa layananan telemedis memanfaatkan kemajuan teknologi informasi untuk pertukaran informasi dan pelayanan kesehatan tanpa memperhatikan batas tempat dan waktu. Data medis yang dapat dikirim, ditu- kar, dan distribusikan untuk memenuhi layanan telemedis harus diikuti dengan sistem keamanan karena kejahatan pencurian data identitas medis semakin meningkat dan membahayakan. Data pasien yang ber- sifat pribadi dan rahasia dapat dijaga dengan skema watermarking dengan cara menyisipkan rekam medis pasien pada citra medis digitalnya. Hal ini dapat menjamin kerahasiaan dan keamanan pengiriman data serta menjaga integritas dan hak milik citra medis digitalnya. Pada penelitian ini diusulkan skema water- marking menggunakan penggabungan metode DWT-DCT serta optimasi dengan GA untuk mencapai nilai robustness dan imperceptibility yang lebih baik. Parameter yang dioptimasi adalah subband DWT, subband DCT, dan scale factor penyisipan. Skema watermarking yang diusulkan dibandingkan dengan skema w...
International Journal of Advances in Intelligent Informatics
The k-means is a clustering algorithm that is often and easy to use. This algorithm is susceptibl... more The k-means is a clustering algorithm that is often and easy to use. This algorithm is susceptible to randomly chosen centroid points so that it cannot produce optimal results. This research aimed to improve the k-means algorithm’s performance by applying a proposed algorithm called point center. The proposed algorithm overcame the random centroid value in k-means and then applied it to predict software defects modules’ errors. The point center algorithm was proposed to determine the initial centroid value for the k-means algorithm optimization. Then, the selection of X and Y variables determined the cluster center members. The ten datasets were used to perform the testing, of which nine datasets were used for predicting software defects. The proposed center point algorithm showed the lowest errors. It also improved the k-means algorithm’s performance by an average of 12.82% cluster errors in the software compared to the centroid value obtained randomly on the simple k-means algorit...
Jurnal Techno Nusa Mandiri
Data Mining is a series of processes to explore added value in the form of unknown information ma... more Data Mining is a series of processes to explore added value in the form of unknown information manually from the database. In the world of data mining education can be used to obtain information about student performance. In this study the researchers took research samples from class XI (eleven) students at SMAN 3 Ambon by classifying student performance based on thirteen attributes, namely: age, sex, school organization, extracurricular activities, pocket money, duration of study at home, duration of social media, online game duration, attendance, illness, permits, semester 1 and semester 2 grades. Using the KDD (Knowledge Discovery Database) method and classification algorithm that will be used, namely, decision tree, Naïve Bayes and K-Nearest Neighbor. And then do the test using k-fold cross validation.
Jurnal Informatika
Persaingan dalam menarik minat orang tua siswa untuk menyekolahkan anak mereka ke sekolah swasta ... more Persaingan dalam menarik minat orang tua siswa untuk menyekolahkan anak mereka ke sekolah swasta memang sangat tinggi. Sekolah swasta harus bekerja keras dalam hal mendapatkan siswa yang akan melanjutkan pendidikannya ke tingkat selanjutnya. Sekolah hendaknya harus memiliki nilai tambah yang lebih di mata orang tua siswa. Dari ketiga algoritma yang digunakan, terdapat nilai accuracy tertinggi sebesar 86,50% dihasilkan dari algoritma Naïve Bayes. Dalam artian, tingkat prediksi untuk sekolah SMP Cenderawasih mendapatkan jumlah siswa yang didapatkan dari kuesioner sangat memungkinkan orang tua mendaftarkan anaknya kesekolah ini. Dapat dilihat dari beberapa faktor yang dijadikan sebagai atribut dalam daftar kuesioner. Dengan algoritma Naïve Bayes, atribut yang paling tinggi sebagai faktor penentu orang tua mendaftarkan anaknya adalah atribut umur, yaitu yang berumur 31 sampai 50 tahun, kemudian atribut faktor karena tidak masuk negeri, atribut transport menggunakan motor, kemudian atri...
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
The use of Learning Management System (LMS) applications made by Google with name Google Classroo... more The use of Learning Management System (LMS) applications made by Google with name Google Classroom since 2015 in junior and senior high schools in Bekasi City helps the learning process become easier. However, its use can have positive and negative effects on students. Google Class Sentiment by integrating N-grams, Information Gain, Particle Swarm Optimization, and Naïve Bayes Classifiers that have never been done by researchers before. From the experiments carried out, N-gram can increase the accuracy of 6.7% and AUC 4%, while using PSO can increase the Accuracy of 9.9% and AUC of 10.4%.
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Increasingly sophisticated technology brings various conveniences both in transportation, informa... more Increasingly sophisticated technology brings various conveniences both in transportation, information, education to the convenience of transactions in shopping, such as the development of E-wallet can now be easily done using a smartphone. From a number of e-wallet products, researchers took a case study, which is OVO product, which is currently being discussed by many groups, especially in the capital of Jakarta today. Customers or clients who are not satisfied with the services or products offered by a company will usually write their complaints on social media or reviews on Google play. However, monitoring and organizing opinions from the public is also not easy. For this reason, we need a special method or technique that is able to categorize these reviews automatically, whether positive or negative. The algorithm used in this study is Naive Bayes Classifier (NB), with the optimization of the use of Particle Swarm Optimization Feature Selection (FS). The results of cross validat...
Jurnal Pilar Nusa Mandiri
Analysis of the odd even-numbered sentiment systems in Bekasi toll using the Naïve Bayes Algorith... more Analysis of the odd even-numbered sentiment systems in Bekasi toll using the Naïve Bayes Algorithm, is a process of understanding, extracting, and processing textual data automatically from social media. The purpose of this study was to determine the level of accuracy, recall and precision of opinion mining generated using the Naïve Bayes algorithm to provide information community sentiment towards the effectiveness of the odd system of Bekasi tiolls on social media. The research method used in this study was to do text mining in comments-comments regarding posts regarding even odd oddities on Bekasi toll on Twitter, Instagram, Youtube and Facebook. The steps taken are starting from preprocessing, transformation, datamining and evaluation, followed by information gaon feature selection, select by weight and applying NB Algorithm model. The results obtained from the study using the NB model are obtained Confusion Matrix result, namely accuracy of 79,55%, Precision of 80,51%, and Sens...
Jurnal Pilar Nusa Mandiri
Penelitian ini adalah tentang pengklasifikasian berita yang mengoptimalisasi dengan kombinasi ant... more Penelitian ini adalah tentang pengklasifikasian berita yang mengoptimalisasi dengan kombinasi antar algoritma. Tentang dataset yang digunakan diambil pada situs pemberitaan online. Algoritma yang digunakan adalah algoritma Naive Bayes Classifier, dan Random Forest dengan pembobotan seleksi fitur Information Gain. Dataset yang digunakan terdapat 615 dataset dengan 3 katagori atau tema berita. Dalam permodelan terdapat 6 model skenario sebagai pembanding untuk menentukan skenario mana yang mendapatkan nilai terbaik, berdasarkan hasil penelitian ini nilai terbaik didapatkan oleh model Remove Useless Attributes, Naive bayes Classifier-Multinomial, dan Random Forest-Feature Selection Information gain. Hasil evaluasi yang didapatkan adalah nilai accuracy 85.67%, nilai recall 85.67%, dan nilai precision 86.23
2014 8th International Conference on Telecommunication Systems Services and Applications, Oct 1, 2014
Di Indonesia ZIS dikelola oleh suatu badan resmi yang bernama BAZIS Pengelolaan ZIS pada mulanya ... more Di Indonesia ZIS dikelola oleh suatu badan resmi yang bernama BAZIS Pengelolaan ZIS pada mulanya dilakukan secara manual mengingat jumlah muzaki dan mustahik yang ada saat itu relatif sebanding dengan kemampuan pengelola BAZIS. Pada saat ini sistem manual hanya dapat dilakukan untuk tingkat RT/RW sedangkan pengelolaan selanjutnya memerlukan sistem komputerisasi pengumpulan dan penyerahan ZIS karena jumlah mustahik dan muzaki semakin bertambah dan kebutuhan penanganan mutasi pengelolaan ZIS di tingkat DKM dan tingkat di atasnya memerlukan ketelitian dan kecermatan dalam pengelolaan ZIS yang akhirnya menghasilkan laporan zis secara cepat, tepat dan akurat. Metodologi penelitian yang digunakan dalam penelitian ini adalah observasi, wawancara, studi literatur dan metode siklus hidup klasik untuk. Hasil akhir penelitian adalah membuat suatu rancangan program pengumpulan dan penyerahan ZIS secara terpadu mulai dari tingkat DKM sampai dengan tingkat Kabupaten. Dengan sistem ini diharapkan pengawasan dan pengendalian pengelolaan ZIS dapat lebih baik serta mudah diakses oleh semua pihak yang berkepentingan sehingga penyimpangan-penyimpangan yang terjadi dapat dikurangi atau ditanggulangi. Sebagai tahap selanjutnya adalah dilakukan implementasi dengan langkah-langkah menentukan bahasa pemrograman yang digunakan, tes dan modifikasi, dan evaluasi sistem yang telah dibuat.
International Journal of Computer Theory and Engineering, 2012
The comparison between the hybrid watermarking using genetic algorithm and the pure hybrid DCT-SV... more The comparison between the hybrid watermarking using genetic algorithm and the pure hybrid DCT-SVD (Discrete Cosine Transform-Singular Value Decomposition) is presented.
Multimedia Tools and Applications, 2013
ABSTRACT This paper proposes an adaptive watermarking scheme for e-government document images. Th... more ABSTRACT This paper proposes an adaptive watermarking scheme for e-government document images. The adaptive scheme combines the discrete cosine transform (DCT) and the singular value decomposition (SVD) using luminance masking. As a core of masking model in the human visual system (HVS), luminance masking is implemented to improve noise sensitivity. Genetic algorithm (GA), subsequently, is employed for the optimization of the scaling factor of the masking. Involving a number of steps, the scheme proposed through this study begins by calculating the mask of the host image using luminance masking. It is then continued by transforming the mask on each area into all frequencies domain. The watermark image, following this, is embedded by modifying the singular values of DCT-transformed host image with singular values of mask coefficient of host image and the control parameter of DCT-transformed watermark image using Genetic Algorithm (GA). The use of both the singular values and the control parameter respectively, in this case, is not only to improve the sensitivity of the watermark performance but also to avoid the false positive problem. The watermark image, afterwards, is extracted from the distorted images. The experiment results show the improved adaptive performance of the proposed scheme is in resistant to several types of attacks in comparison with the previous schemes; the adaptive performance refers to the adaptive parameter of the luminance masking functioned to improve the performance or robustness of an image from any attacks.
Journal of Visual Communication and Image Representation, 2013
ABSTRACT An efficient blind copyright protection for e-government document images is proposed thr... more ABSTRACT An efficient blind copyright protection for e-government document images is proposed through a combination of the discrete cosine transform (DCT) and the singular value decomposition (SVD) based on genetic algorithm (GA). This combination could lead the watermarked image to be resistant to various attacks as well as to improve its performance, security and robustness. DCT, in this case, is applied to the entire image and mapped by a zigzag manner to four areas from the lowest to the highest frequencies. SVD, meanwhile, is applied in each area and then the singular value of DCT-transformed host image, subsequently, is modified in each area with the quantizing value using GA to increase the visual quality and the robustness. The host image is not needed in the watermark extraction and it is more useful than non-blind one in real-world applications. Experiment results demonstrate that the proposed method outperforms other existing methods under several types of attacks.
Uploads
Papers by didi DIDI ROSIYADI