<p><em>Convolutional Neural Network</em> (CNN) adalah salah satu metode <em>multilayer perceptron</em> yang dapat melakukan klasifikasi aplikasi lebih dari dua kelas. Penelitian ini mengklasifikasikan aplikasi ke dalam tiga kelas, yaitu kelas aplikasi tidak berbahaya, mengandung <em>malware</em> kurang berbahaya, dan mengandung <em>malware</em> berbahaya. Dataset yang digunakan pada penelitian ini terdiri dari <em>dataset</em> Androsec dan Koodous dengan total data 37289 aplikasi. <em>Dataset</em> mengandung aplikasi <em>undetected</em> (tidak mengandung <em>malware</em>) dan <em>detected</em> (mengandung <em>malware</em>). Data <em>detected</em> perlu dikelompokkan dengan algoritme <em>k-means </em>sehingga menghasilkan kelompok aplikasi kurang berbahaya dan berbahaya berdasarkan tingkat kemiripan fitur <em>permission</em> yang dimiliki aplikasi. Kerangka kerja meliputi <em>dataset preprocessing, learning and classification algorithm using CNN</em>, dan <em>check APK to Model</em>. Tingkat akurasi terbaik yang didapat pada penelitian ini adalah 92,23% dan dapat mengklasifikasikan ke dalam kelas tidak berbahaya, kurang berbahaya, dan berbahaya.</p><p> </p><p><em><strong>Abstract</strong></em></p><p class="Judul2"><em>Convolutional Neural Network (CNN) is a multilayer perceptron method which able to classify apps more than two classes. This paper describes classification into three classes such as benign/no malware, less harmful, and harmful application. In this research, we use and construct dataset from Androsec and Koodous with total 37289 apps. Dataset consists of undetected (no malware) and detected (consists of malware). Detected files need to clustered with k-means algorithm to clasify apps into less harmful and harmful </em><em>based on apps permission similarity.</em><em> The framework includes dataset preprocessing, learning and classification algorithm using CNN, and check APK to Model. In this research, we get the best accuracy 92,23% and able to classify apps into three classes benign, less harmful, and harmful.</em><em></em></p><p><em><strong><br /></strong></em></p>

AbstrakDigital audio watermarking dibutuhkan untuk memberi perlindungan dari pembajakan musik secara ilegal dan pemberian hak cipta/kepemilikan. Penelitian ini menjelaskan perpaduan metode audio watermarking dimana informasi berupa hak cipta disisipkan ke dalam sinyal audio. Perpaduan dari metode DWT (Discrete Wavelet Transfrom) dan SVD (Singular Value Decomposition) digunakan untuk menyisipkan dan mengekstrak watermark dari sinyal audio. Informasi atau watermark tersebut dapat berupa gambar hitam putih (biner) atau huruf-huruf karakter ASCII. Pada penelitian ini sebuah gambar dijadikan sebagai watermark dengan berbagai variasi ukuran piksel seperti 10×10, 30×30, 40×40 dan 50×50 piksel. Hasil dari penyisipan watermark yang berukuran 30×30 piksel menghasilkan imperceptibility yang baik dengan nilai rata-rata diantara 43 sampai dengan 50 dB. Hasil eksperimen yang telah dilakukan juga menunjukkan bahwa kombinasi dari kedua metode tahan (robustness) terhadap beberapa serangan seperti amplify, resampling dan invert. AbstractDigital audio watermarking is needed as a protection against online music piracy and copyright issues. This paper describes an audio watermarking combination method where the copyright information is imperceptibly added into the audio signal. The combination of discrete wavelet transform (DWT) and singular value decomposition (SVD) is used to embed and extract the watermark from the audio signal. The copyright information or watermark could be a binary logo or some unique binary patterns. In this paper, a watermarked image is divided into four different capacities of dimension such as 10×10, 30×30, 40×40 and 50×50 pixels. The results of the watermarked image are imperceptibly added into the audio signal and image with 30×30 pixel dimension has the best mean result ranged from 43 to 50 dB. The experiment result also shows that the combination of DWT and SVD is robust against different attacks such as amplify, resampling and invert.

No abstract

By utilizing current technological developments, an android application was developed for the TB Silalahi Center Balige Museum with the application of Gamification concepts and Augmented Reality (AR) technology with marker-based methods. The gamification approach was used to provide challenges and rewards since they can encourage someone to accomplish a task, in this case, to find artifact items and information contained in artifact. The utilization of 3D object with a QR Code marker on the artifact also enables the combination of the virtual world and the real world. This application was developed to improve the experience of visitors who come to the Museum, where visitors can carry out activities by playing games and interacting with objects in the museum. The final result of the project is a application with the integration of gamification and storytelling and AR technology. This application was evaluated with the usability testing and user satisfaction reaches 72,23% meaning the application can be used and can well perform its functions.

No abstract