| KONAN N'DJABLI CEDRIC ANGE | 1551126: M, 2回目発表 | ユビキタスコンピューティングシステム | 安本 慶一,池田 和司,荒川 豊,諏訪 博彦,藤本 まなと |
|
title: Automatic curation system for personal photos based on emotion
abstract: For our photos, taken during some events, we sometimes needs to make a short video to keep an easily consultable memory. Then a problem quickly appears : How to choose the best Background music? During this presentation i will present a system that is able to analyse the emotion in the photo provided, and recommend the Best Background music according to the main emotion detected. We used machine learning technics to devellop a model that is able to evaluate which emotion a certain BGM conveys. language of the presentation: English | |||
| 荒川 周造 | 1551005: M, 2回目発表 | ユビキタスコンピューティングシステム | 安本 慶一,池田 和司,荒川 豊,諏訪 博彦,藤本 まなと |
|
title: Rent estimation system of real estate properties for the restaurant based on the tacit knowledge
abstract: At present, the rent of real estate properties for the restaurant is determined based on the tacit knowledge, that is, intuition and experience gained by experienced salesmen. This business custom, however, has the following problems: there is no evidence to the rent decided; and there is no effective means to transfer the knowledge and experience from the experienced salesman to fresh one. In this presentation, we propose a new rent estimation model which solves the above problems, and construct a rent estimation system based on the model. Moreover we discuss the specific challenges in building the proposed system, are (1) acquisition and indexing of the tacit knowledge and (2) construction of a rent estimation model. language of the presentation: Japanese | |||
| 浅山 和宣 | 1551003: M, 2回目発表 | 数理情報学 | 池田 和司,安本 慶一,久保 孝富 |
|
title: Modeling of Lane Changing Intention by Using Surrounding Vehicle
abstract: Advanced Driver Assistance Systems (ADAS) can help drivers to improve traffic flow and avoid accidents. And an autonomous car system can be main transportation system in future. These are the next generation driving system. For realization of these systems, modeling of driving behavior and extracting characteristics of the road is important. In particular, predicting lane changing intension in advance can prevent accidents in situation that other vehicle is reaching. There are several researches about prediction of lane changing, but none focus on surrounding vehicles. In our study, we tried making predicting model for lane changing from surrounding vehecles information of real driving data on highway. Language of the presentation: Japanese | |||
| OJETUNDE BABATUNDE SEGUN | 1561030: D, 中間発表 | モバイルコンピューティング | 伊藤 実,安本 慶一,柴田 直樹,Gao Juntao |
|
title: Consideration on Monitoring Scheme to Secure Link State Routing against Byzantine Attacks
abstract: Secure communication is essential in most applications where timely delivery of information is required, such as battlefield and disaster management applications. Most existing protocols adopt cryptography based approach, trust based approach (reputation of nodes) and incentive based approach to detect and prevent attacks in such applications. However, such protocols are still subjected to drawbacks like expensive overheads, difficulty in maintaining secure key and session management, unsecured routes against Byzantine attacks and so on. Therefore, we introduce a monitoring scheme to secure packets route in link state routing protocol against Byzantine attacks. Specifically, each node creates an event-driven monitoring block which is used to record all activities of an intermediate node when receiving and forwarding packets. Our schemes provide mutual monitoring in which nodes in the network can validate the monitoring blocks of other nodes and report malicious activities. Also, our scheme uses a statistical method to predict the probability that a node is not benign. The proposed scheme provides protection against colluding attacks and other Byzantine attacks. language of the presentation: English | |||