No abstract

Data mining melakukan proses ekstraksi pengetahuan yang diperoleh dari sekumpulan data dalam jumlah besar. Penelitian ini bertujuan untuk menerapkan dan melakukan analisis kinerja algoritma data mining untuk memprediksi konsumsi alkohol dan menganalisis faktor-faktor yang terkait pada siswa tingkat menengah. Adapun tahapan yang dilakukan ialah pra-proses data, seleksi fitur, klasifikasi, dan evaluasi model. Pada tahap praproses, beberapa fitur diubah menjadi bentuk yang sesuai untuk memudahkan proses klasifikasi. Selanjutnya, algoritma Gain Ratio dan Feature Correlation-Based Filter (FCBF) digunakan untuk memilih fitur-fitur yang relevan dan penting untuk digunakan dalam tahapan klasifikasi. Decision Tree C5.0, Support Vector Machine (SVM), K-Nearest Neighbor (KNN), dan Naive Bayes (NB) dieksekusi pada kelompok fitur yang terpilih. Akurasi model yang dibangun dievaluasi menggunakan 10-fold Cross-Validation (CV). Hasil penelitian menunjukkan bahwa model klasifikasi yang dibangun menggunakan Naïve Bayes memiliki nilai akurasi tertinggi dengan menggunakan 5 fitur terbaik dari Gain Ratio. Selain itu, penggunaan metode pemilihan fitur mampu meningkatkan performa dari seluruh klasifier secara umum. Pengujian lebih lanjut pada data yang sama maupun berbeda perlu dilakukan untuk mendapatkan gambaran lebih mendalam mengenai kinerja algoritma-algoritma yang digunakan.

Urban swarming transportation (UST) is a type of road transportation where multiple types of vehicles such as cars, buses, trucks, motorcycles, and bicycles, as well as pedestrians are allowed and mixed together on the roads. Predicting the traffic jam speed under UST is very different and difficult from the single road network traffic prediction which has been commonly studied in the intelligent traffic system (ITS) research. In this research, the road network wide (RNW) traffic prediction which predicts traffic jam speeds of multiple roads at once by utilizing citizens’ mobile GPS sensor records is proposed to better predict traffic jam under UST. In order to conduct the RNW traffic prediction, a specific data preprocessing is needed to convert traffic data into an image representing spatial-temporal relationships among RNW. In addition, a revised capsule network (CapsNet), named OCapsNet, which utilizes nonlinearity functions in the first two convolution layers and the modified dynamic routing to optimize the performance of CapsNet, is proposed. The experiments were conducted using real-world urban road traffic data of Jakarta to evaluate the performance. The results show that OCapsNet has better performance than Convolution Neural Network (CNN) and original CapsNet with better accuracy and precision.

An image resulting from a low-resolution (LR) camera on the mobile phone has lower quality than a high-resolution(HR) camera on a DSLR. Meanwhile, the HR camera is pricing if compared with the LR camera. How to achieve a single-image quality on LR camera likewise on HR camera becomes essential research in the past years. Addressing this issue can be done by upscaling a single LR image. Recently, the super-resolution generative adversarial network (SRGAN) model is one of the state-of-the-art super-resolution(SR)models employed on single-image SR. However, implementing a deep learning model like SRGAN on a mobile device is challenging in computation power and resources. This study aims to develop a smaller and lower resources model while preserving single-image SR quality on mobile devices. To meet these objectives, we convert, quantize, and compress the SRGAN model on Snapdragon Neural Processing Engine (SNPE) as an example. We then validate the SRGAN on the DIV2K dataset on which improves the model performances. Besides, we conduct experiments on GPU, DSP environment. The experimental result confirmed that SNPE-SRGAN capable of achieves not only HR images’ quality but also low latency by 0.06 second and smaller model by 1.7 Mb size running on DSP. Also, the SRGAN-DLC-Quantized running on GPU has a smaller size by 1.7 Mb and lower latency by 1.151 seconds compared with Non-quantized SRGAN-TensorFlow by 9.1 Mb and 1.608 seconds latency.