| KIKI FERAWATI | D, 中間発表 | ソーシャル・コンピューティング | 荒牧 英治, 安本 慶一, 若宮 翔子, 矢田 竣太郎 |
|
Title: COVID-19 Discussion in Social Media: Cross Country Comparison
Abstract: Twitter, as one of the most popular media, has been widely utilized as a source for research. This study focused on cross-country comparison of topics related to COVID-19 between countries in Twitter. Some parts of COVID-19 discussions can be found a lot in tweets, such as vaccination as a measure to end the pandemic and related policies. We first discussed about monitoring mentions of COVID-19 vaccine, Pfizer and Moderna, and its side effects in Japan and Indonesia as two countries. Aside from vaccine, some policies were also interesting to investigate. One of the policies generating a lot of discussions were the usage of mask for COVID-19 prevention. We investigated the mask-related discussions in United States and Japan, two countries with a different cultural background and pandemic policies. We created annotation guidelines for the Japanese and English tweets, and then plan to classify the tweets for discussion and comparison between countries. language of the presentation: English | |||
| FAN YOUMEI | M, 2回目発表 | ソフトウェア工学 | 松本 健一, 安本 慶一, 石尾 隆, 畑 秀明, Raula Gaikovina Kula |
|
Title: An Empirical Study of The Impact of Twitter on GitHub Sponsors
Abstract: Sustaining open source software (OSS) ecosystems is a multifaceted and challenging endeavour. In our study, we delve into the critical aspects of financial support. GitHub's introduction of GitHub Sponsors has provided a platform for developers to seek financial support for their OSS projects. This study examines the influence of Twitter discussions on GitHub profiles and their subsequent impact on the number of GitHub sponsors. By uncovering the effectiveness of utilising Twitter as an advertising platform, this research sheds light on how developers can leverage social media to promote their projects and attract more sponsors. Language of the presentation: English | |||
| 北村 圭輝 | M, 2回目発表 | 情報セキュリティ工学 | 林 優一, 岡田 実, 安本 慶一, 藤本 大介, Kim Youngwoo |
|
title: Deep Learning-Based Side-Channel Analysis Considering Noise and Transfer Functions in the Measurement Process
abstract: Deep learning-based side-channel analysis (DLSCA) enables model-free evaluations against cryptographic modules. Traditional DLSCA has primarily focused on generating learning models suitable for classifying side-channel waveforms measured during the attack phase to improve their portability. However, preemptively predicting the characteristics of the side-channel waveforms measured during an attack for use in training is realistically challenging. In this research, we propose a novel approach that enhances the transferability of learning models by adopting a perspective contrary to traditional studies. We introduce a preprocessing step that transforms the side-channel waveforms acquired during the attack phase to a state possessing identical characteristics to the side-channel waveforms used during training before their input into the learning model. language of the presentation: Japanese | |||
| WANG ZAOSHI | M, 2回目発表 | ネットワークシステム学 | 岡田 実, 林 優一, 東野 武史, DUONG Quang Thang, CHEN Na |
|
title: Deep Learning-Based Variable Scaling Beam Training for mmWave Massive MIMO System
abstract: Improving the accuracy of beam training while reducing the training overhead and the influence of noise has become an important issue for massive multiple-input multiple-output (MIMO) millimeter-wave (mmWave) communication systems. We propose a deep learning-based variable scaling neural network for beam training in massive MIMO mmWave communication system. The model predicts the orientation of narrow beams by learning the characteristics of wide beams, achieving high accuracy and low training overhead. language of the presentation: English | |||