Forecasting time-series data is useful in many fields, such as stock price predicting system, autonomous driving system, weather forecast, etc. Many existing forecasting models tend to work well when forecasting short-sequence time series. However, when working with long sequence time series, the performance suffers significantly. Recently, there has been more intense research in this direction, and Informer is currently the most efficient predicting model. Informer's main drawback is that it does not allow for incremental learning. In this paper, we propose a Fast Informer called Finformer, which addresses the above bottleneck by reducing the training/predicting time of Informer. Finformer can efficiently compute the positional/temporal/value embedding and Query/Key/Value of the self-attention incrementally. Theoretically, Finformer can improve the speed of both training and predicting over the state-of-the-art model Informer. Extensive experiments show that Finformer is about 26% faster than Informer for both short and long sequence time series prediction. In addition, Finformer is about 20% faster than InTrans for the general Conv1d, which is one of our previous works and is the predecessor of Finformer.

抄録全体を表示

In a previous paper, we proposed a rescue support system for victims buried in an earthquake disaster by constructing an ad-hoc network using home-server based smart homes. However, this system has the following two problems: i) it cannot ensure sufficient density of home servers to realize adequate WLAN coverage, ii) the system does not consider areas in which home servers cannot be used such as parks and factories, for example. In this paper, we propose a new method using a delay tolerant network (DTN) technique. In this method, rescuers (such as rescue teams) with mobile devices relay information between disconnected networks by walking around during rescue activities. For a performance evaluation, we performed simulation experiments using a map of Abeno-ku, Osaka. From our results, we show that the proposed method increases the information acquisition rate, and that the network can be maintained. We also quantitatively show the penetration rate of smart homes needed for our system. In addition, we show that the rescue request system is more effective than other systems, and the method with the mobile device relay is better than without this method.

抄録全体を表示

従来の移動通信システムとは異なり，インフラを使用しない移動通信ネットワークとしてマルチホップ無線ネットワークがある．マルチホップ無線ネットワークでは送信元ノードと宛先ノードの間の連結なマルチホップ無線経路で通信を行う．それを更に柔軟にしたものとして，移動ノード間の直接無線通信と移動ノードの移動により情報を空間的に拡散し情報を伝えるというエピデミック通信や，直接無線通信を特定領域だけで許可することにより無秩序な情報拡散を防ぎながら特定の領域の不特定のノードに情報を伝えるという情報フローティングがある．これらのように，移動体同士の情報交換と移動により情報を伝えることができるという性質を生かした手法が注目されている．本論文ではエピデミック通信，情報フローティングとその安全・安心への応用について，安全・安心への応用における移動ノードの特徴的な移動との関係に着目しながら解説する．また，情報フローティングによる情報配信がノードの行動変化を促し，この行動変化により情報フローティング自体も影響を受けること等に着目して，新たな観点から行われている情報フローティングの研究について解説する．

抄録全体を表示