This study investigated the waveform representation for audio signal classification. Recently, many studies on audio waveform classification such as acoustic event detection and music genre classification have been published. Most studies on audio waveform classification have proposed the use of a deep learning (neural network) framework. Generally, a frequency analysis method such as Fourier transform is applied to extract the frequency or spectral information from the input audio waveform before inputting the raw audio waveform into the neural network. In contrast to these previous studies, in this paper, we propose a novel waveform representation method, in which audio waveforms are represented as a bit sequence, for audio classification. In our experiment, we compare the proposed bit representation waveform, which is directly given to a neural network, to other representations of audio waveforms such as a raw audio waveform and a power spectrum with two classification tasks: one is an acoustic event classification task and the other is a sound/music classification task. The experimental results showed that the bit representation waveform achieved the best classification performance for both the tasks.

Since the radio wave is rapidly attenuated in the seawater, the radio wave communication has not been applied to the underwater communication. However, the radio wave communication in the seawater can be realized by placing a dielectric material as a propagation path between watertight cases which contain a transmitter and/or a receiver. This radio wave communication method in the seawater is proposed by authors. The proposed method is only used for a short distance communication because the attenuation of a dielectric material is still large compared with the air. In order to apply the proposed method to underwater systems, the extension of the communication distance is desired. The major factor of the attenuation is considered the radio wave propagation into seawater from the propagation path. It is known that the radio wave cannot penetrate a metal foil or a wire netting. Therefore, the attenuation of the radio wave can be decreased by covering the propagation path with the metal foil or the wire netting. In this paper, the communication property is analyzed how the communication range can be extended by covering the propagation path in the metal foil or the wire netting.

Recently, the radio wave communication method in the sea water has been developed by authors. The radio wave communication can be realized by attaching the dielectric material as the propagation channel between intercommunication systems in watertight cases equipped on the underwater vehicle. This method provides the high speed and the large volume data communication compared with the acoustic wave communication in the sea water. In this paper, the characteristic analysis of propagation channels of the radio wave communication in the sea water is discussed. The field intensity depending upon the form and the contact area of the propagation channel are investigated experimentally.

Researches of sensor networks collecting patients' data with computerized triage tags, called Triage network are developed. In Triage networks, network topology changes frequently. Because some sensors have mobility and each sensor participates in Triage networks and secedes from them with frequency. As a result, route to a sink fails and power consumption increases by increase of the number of re-searching routes and the number of packets transmissions and receptions. In this paper, we propose an energy efficient data collection method by two types routes selection in Triage networks. In our method, to consider mobility and topology changes, two types routes, Electric power efficient route and Stable route, are used depending on mobility existence. Electric power efficient route is used where sensors with short participating time work as relay sensors positively. Stable route is used where sensors which don't secede easily and links don't fail easily work as relay sensors positively. We evaluate our proposed method using computer simulations and show its effectiveness.

In traditional image composition methods for cutting out a source object from a source image and pasting it onto a target image, users have to segment a foreground object in a target image when they want to partially hide a source object behind it. While recent image editing tools greatly facilitate segmentation operations, it can be tedious to segment each object if users try to place a source object in various positions in a target image before obtaining a satisfying composition. We propose a method which allows users to drag a source object and slip it behind a target object as shown in Fig. 1, so that users can move a source object around without manually segmenting each part of a target image.

Manipulative operations of rheological objects can be found in many industrial fields such as food industry and medical product industry. Automatic operations of rheological objects are eagerly required in these fields. In this paper, we realize a vision-based automatic forming of rheological objects using deformation transition graphs. First, we develop a forming machine of rheological objects with multi-degrees of freedom. Next, we analyze the forming processes of rheological objects. Then we introduce a deformation transition graph so that the forming processes can be described in a systematic manner. Finally, we propose a forming control method of a rheological object based on the deformation transition graph.