The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
We present Bautext, a new minimally supervised approach for automatically extracting ratable aspects from customer reviews and classifying them to some previously defined categories. Bautext requires a small amount of seed words as supervised data and uses a bootstrapping mechanism o progressively collect new member for each category. Learning new category members and the category-specific terms for...
The present paper introduces a new approach to the construction of a sequence set with a zero-correlation zone (ZCZ). This sequence set is referred to as a zero-correlation zone sequence set. The proposed sequence construction can generate an optimal ZCZ sequence set, the member size of which reaches the theoretical bound. The proposed sequence construction generates a ZCZ sequence set from a perfect...
This study focuses on the issue of how kanji learners mentally ??deconstruct?? a kanji as they view it and how they may update this visual deconstruction over time as they learn kanji. The research problem deals with the question of whether or not an innovative kanji learning approach, the ??learner's visualization (LV) Approach??, assists learners in significantly updating their personal kanji deconstruction...
Recently, more and more Chinese students begin to learn Japanese as their second language, for the close connections between Japanese and their mother language. However, it turns out that Chinese students feel difficult to learn Japanese, especially Katakana words. They have to listen to the words repeatedly, and it is hard for them to recognize their special sounds and to distinguish the length of...
Learning and recognition of object velocity sequences using a hierarchical network similar in structure to the mammalian neocortex is proposed. Space and time invariant representations of velocity sequences are captured in an unsupervised manner. Recognition of similar sequences are achieved by allowing some variance in the learned velocity vectors.
This paper proposes a framework for predicting whether a driving behavior that a driver is going to execute is usual or not in that situation for the purpose of preventing accidents caused by human error. The framework is applied to unusual right-turn driving behavior prediction at an intersection and the effectiveness is confirmed with an experiment on a driving simulator.
In this paper, we discuss an obstacle to training in SpikeProp, which is a type of supervised learning algorithms for spiking neural networks. In the original publication of SpikeProp, weights with mixed signs are suspected to cause failures of training. We pointed out the cause of it through some experiments. Weights with mixed signs make the dynamics of the unit's activity twisted, and the twisted...
With the spread of small wireless devices, mobile mesh networks (MMN) will be constructed in the near future by interconnecting such devices. However, it is difficult to reliably deliver data over the moving nodes in an MMN due to the instability of the wireless medium and the movement itself of mobile nodes. Although an existing method, MORE, improves the efficiency of data delivery in fixed wireless...
The present paper describes an approach to the construction of a sensor network using a messaging network. A messaging network is an overlay network with a set of content-aware message handling capabilities. The use of a messaging network can reduce the complexity and maintenance burden of integrated sensor information systems. Message mediation (a function of the messaging network) enables interoperation...
The present paper describes a mashup and an approach by which to integrate a sensor network using a messaging network. A messaging network is an overlay network that has a rich set of message handling capabilities. The use of a messaging network enables the complexity and maintenance burden of the integrated sensor information systems to be reduced. Mashup refers to the use of different data or services...
This paper presents a method for gathering Japanese Web documents which contain personal opinions. Our method is available as a pre-processing of applications for mining various opinions. In order to find personal documents on the Web, we focus on four kinds of subjective expressions: (1) negative meaning expressions, (2) final particles, (3) interjections, and (4) specific symbols such as face marks...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.