卒業生 別宮君の論文がElsevier Pervasive and Mobile Computingに採択・公開されました。修士2年時の研究です。
Highlights:
・We introduce DynamicECM, an object detection approach for false positive suppression.
・DynamicECM optimizes the trade-off between inference time and detection performance.
・Our method maintains stable and accurate inference in various road environments.
Bekku, H., Kume, T., Tsuge, A., & Nakazawa, J. (2024). A stable and efficient dynamic ensemble method for pothole detection. Pervasive and Mobile Computing, 104, 101973.
道路の損傷調査を効率的に行うため、ゴミ収集車のダッシュカメラ映像を利用した物体検出モデルを適用する方法が提案されています。著者が以前の研究で提案したECM(Ensemble of Classification Mechanisms)は、誤検出を抑制する効果がありましたが、推論速度と検出性能の両立に課題がありました。
この問題を解決するために、DynamicECM(Dynamic Ensemble of Classification Mechanisms)を新たに提案しました。本手法は、必要に応じてECMを選択的に使用することで、安定した推論と最小限の誤検出抑制を実現します。
学部3年 大崎君の研究「Dynamic Fixed-point Values in eBPF: a Case for Fully In-kernel Anomaly Detection」が国際会議 The 19th Asian Internet Engineering Conference (AINTEC 2024) にacceptされました．
Abstract:
eBPF and XDP are promising technologies that are capable of accelerating packet processing inside the Linux kernel. Despite these benefits, eBPF is constrained by a number of rigorous restrictions that are imposed to protect the kernel. One such restriction is the lack of support for floating-point values, which was introduced to achieve faster execution and avoid non-deterministic behavior. However, this has become a significant obstacle to expanding the functionality of eBPF programs with advanced algorithms. In this paper, we propose dynamic fixed-point as a solution to overcome this challenge within the restrictions of eBPF. Dynamic fixed-point values are an expansion from traditional fixed-point values, with the bit allocation adjusted dynamically. Benefit of dynamic fixed-point is that the accuracy of calculations are improved, which is one of the critical shortcomings of fixed-point. To demonstrate the effectiveness of our approach, we have designed and implemented a prototype of an entropy-based traffic anomaly detection framework and have reported on its performance and the detection accuracy. Our prototype, which employs dynamic fixed-point, has achieved an 18% improvement in throughput while also matching the detection accuracy of a similar system that employs floating-point values in user space.
Osaki, A., Poisson, M., Makino, S., Shiiba, R., Fukuda, K., Okoshi, T., & Nakazawa, J. (2024, August). Dynamic Fixed-point Values in eBPF: a Case for Fully In-kernel Anomaly Detection. In Proceedings of the Asian Internet Engineering Conference 2024 (pp. 46-54).
2024年6月3日(月)~7日(金)に，東京・虎ノ門ヒルズで開催されたThe 22nd ACM International Conference on Mobile Systems, Applications, and Services (ACM MobiSys 2024) で，本研究室から12本の論文をposter/demo sessionで発表しました．
大越 匡 准教授はJeongGil Ko Associate Professor（韓国・延世大学校）とGeneral Co-Chair，陳 寅 特任准教授はVice General Chair，中澤 仁 教授はSponsorship Chairs，佐々木 航 特任助教はRegistration Chair，D2 黄君はStudent Volunteer Chairsを務めました．
併設開催されたA3 Foresight Workshopでは，特任助教 佐々木君が「Adaptive Information Presentation Methods Based on Estimated Internal States」というタイトルで口頭発表を行いました
【採択】修士1年 富澤君の研究が国際会議 ACM The Web Conference 2024 Short Papers Sessionにacceptされました – ‘ FaST: Accelerating Web Front-end Data Binding with Compiler and Visible Anchor’
Abstract:
Data binding in web front-end development has made a significant contribution to removing complexity from development and simplifying programming. However, data binding has caused a degradation of website performance at the cost of reducing the burden on programmers. In this paper, we propose Visible Anchor to solve the performance degradation caused by data binding. We develop a compiler called FaST that implements the method. Then, We compared the rendering time among websites built by existing methods and FaST compiler. The evaluation result revealed that the websites built by FaST compiler are at minimum 2.9 times faster to be rendered than the ones built by the existing methods. FaST made a significant contribution to improving the performance of web front-end data binding. Consequently, data binding with FaST can be a better choice for web front-end development.
Tomizawa, T., Makino, S., Kume, T., Hamanaka, S., Okoshi, T., & Nakazawa, J. (2024, May). FaST: Accelerating Web Front-end Data Binding with Compiler and Visible Anchor. In Companion Proceedings of the ACM on Web Conference 2024 (pp. 754-757).
During Sept. 20~23, 2023, the 6th workshop, entitled 2023 International Joint Workshop on Intelligent IoT Key Technology, was held in Nanjing city, China. This is the first time members from the China, Japan and Korea could gather on-site for face-to-face communication. We have 5 keynotes and 10 oral presentation sessions. The topics ranges from wireless sensing and communication to IoT and smart home applications. From our team, we sent 13 attendees and two students, Wenhao Huang and Taiga Kume presented their work on machine learning driven sensing technology. In addition to the academic events, we also learned a lot about Nanjing city’s history and culture. A very great trip! See you next time, Nanjing.
