| 西 陽太 | M, 2回目発表 | ソフトウェア工学 | 松本 健一, | 中島 康彦, | 石尾 隆, | Kula Raula Gaikovina | ||
|
title: Support for grading program assignments using data flow
abstract: Due to the popularity of CS, the number of people learning programming is increasing. In recent years, the number of students taking introductory programming classes at MOOCs has increased significantly, and programming has become a compulsory subject at high schools in Japan, so there is a need for many human resources who can provide appropriate feedback on the programming assignments. However, there is a shortage of human resources who can teach programming, and instructors who are not specialized in CS are currently working on it. Therefore, the grading work for program assignments is becoming more intense, and there is a need for a system that can reduce the workload of scoring and provide information that can be used as hints for appropriate feedback. In this study, we propose a method to automatically link variables in programs written by students to variables in sample programs written by instructors. The method identifies the corresponding variables using similarity between possible data flow paths in source code of the sample and the submitted program. The linked variables enable instructors to understand the student programs whose variables are linked to concepts in their sample programs. language of the presentation: Japanese | ||||||||
| TSOGBAATAR ENKHTUR | D, 中間発表 | サイバーレジリエンス構成学 | 門林 雄基, | 中島 康彦, | 妙中 雄三, | Doudou Fall, | 宮本 大輔（客員）, | Monowar Bhuyan (Umea U.) |
|
title: Applying Deep Learning Approaches to IoT Cyberattacks Detection
abstract: Internet of Things (IoT) devices are inherently vulnerable due to insecure design, implementation, and configuration. Aggressive behavior change, due to increased attacker’s sophistication, and the heterogeneity of the data in IoT have proven that securing IoT devices trigger multiple challenges. It includes complex and dynamic attack detection, data imbalance, data heterogeneity, real-time response, and prediction capability. Most researchers are not focusing on the class imbalance, dynamic attack detection, and data heterogeneity problems together in Software-Defined Networking (SDN) enabled IoT anomaly detection. Thus, to address these challenging tasks, we propose DeL-IoT, a deep ensemble learning framework for IoT anomaly detection and prediction using SDN, having three primary modules including anomaly detection, intelligent flow management, and device status forecasting. The DeL-IoT employs deep and stacked autoencoders to extract handy features for stacking into an ensemble learning model. This framework yields efficient detection of anomalies, managing flows dynamically, and forecast both short and long-term device status for early action. We validate the proposed DeL-IoT framework with testbed and benchmark datasets. We demonstrate that in even a 1% imbalanced dataset, the performance of our proposed method, deep feature extraction with a deep ensemble learning model, is around 3% better than the single model. The extensive experimental results show that our models have a better and more reliable performance than the competing models showcased in the relevant related work. language of the presentation:English | ||||||||