Iwate, Japan

Iwate Prefectural University is a public university located in Takizawa, Iwate, Japan, founded in 1998. Wikipedia.

Time filter

Source Type

Zhou L.,Macau University of Science and Technology | Fujita H.,Iwate Prefectural University
Information Sciences | Year: 2017

Ensemble strategy is important to develop a decomposition and ensemble method for multi-class classification problems. Most existing ensemble strategies use predetermined and heuristic decision rules. In this work, we build up the decision rules by optimizing decision directed acyclic graph (ODDAG) with classical and fuzzy decision trees to ensemble the posterior probabilities of binary classifiers from one-vs-one (OVO) or one-vs-all (OVA) decomposition strategies for multi-class classification problems. Four widely used extensible algorithms and ten decomposition and ensemble methods incorporating four binary classifiers (BCs) have been tested on 25 data sets. The empirical results show that the methods based on ensemble strategies using ODDAG are among the top methods that achieve the best performance in terms of two different measures. © 2017 Elsevier Inc.

Bista B.B.,Iwate Prefectural University
Proceedings - 2016 10th International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing, IMIS 2016 | Year: 2016

Wireless Delay Tolerant Networks (DTNs) are designed for intermittently connected wireless nodes to communicate with each other. In a DTN, messages are copied, stored and forwarded to other nodes when connection is established between nodes. Various routing protocols are designed to improve message delivery probability in networks but a very few of them consider energy constraint of nodes. In this paper we propose an Energy Aware Epidemic (EAEpidemic) routing protocol for DTNs. We extensively simulated our proposal and have shown that our proposed protocol performs better than the original Epidemic routing protocol in terms of energy consumption, message delivery probability and overhead ratio. © 2016 IEEE.

Chakraborty G.,Iwate Prefectural University
2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings | Year: 2016

We collect environmental information through our sensory organs, perceive them suitably to execute the task in hand. Examples of such tasks are abundant, like driving, operating machines, playing games, hunting, or mushroom picking on mountains. While executing such tasks, there is a marked difference in efficiency and accuracy between an expert and a novice. An expert is attentive to only what is important, still makes fewer errors. She is tacitly aware when or where to focus attention. The operation is efficient because an expert has less information to process, and do not attend to what is irrelevant. An expert correctly perceives from sensory information when to be alert, and therefore she is efficient. At times, the expert is able to explicitly describe her knowledge in a set of rules, but not always. It is not uncommon that the expert herself is unaware how the right decision is taken, and can not express his expertise in explicit rules. This is tacit knowledge acquired through long experience, and lack of which makes a novice ponder to accomplish the task correctly. What is perceived by an expert is different from that of a novice, though the available information through vision, audio and other senses are the same. We can design efficient machines, if the expert's selective attention and perception could be learned and incorporated in machine learning. The motivation of this work is to propose a framework to design machines which will be able to learn the tacit knowledge of an expert. When something important is perceived (like an alarming situation warranting immediate action), it is reflected in bio-signals like increased pulse rate or decrease in GSR. These bio-signals are used as cues to collect labeled data for supervised learning of the tacit knowledge. The system will be efficient by avoiding irrelevant information. © 2016 IEEE.

Dai Y.,Iwate Prefectural University
2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings | Year: 2016

In order to improve the reliability of the status perception, this paper defines a metric QoSTD to measure the quality of the subjectively labelled training data used with K-means clustering. On the basis of QoSTD, we propose a method that utilizes a support vector support (SVM) model to predict the specified states of an individual's status. We also present a way to determine a threshold for QoSTD so that it rejects states that cannot be predicted with sufficient certainty. A high positive correlation between the QoSTD and the quality of the perception of the status is verified by experimental results with predictions based on traditional Chinese medicine (TCM) Zhengs. © 2016 IEEE.

Prima O.D.A.,Iwate Prefectural University | Yoshida T.,Tohoku University
Geomorphology | Year: 2010

We used a digital elevation model (DEM) of Iwate Volcano, Japan to calculate slope and topographic openness for every geological unit in that area. Further, we conducted principal component analysis (PCA) and stepwise discriminant analysis (SDA) to evaluate statistical differences in the morphometric parameters of the geological units. We categorized the geological units according to their ages and their formation processes. The categorization based on formation processes was as follows: lava-flow/lava, central cone/stratocone, air fall deposit, pyroclastic flow deposit, volcanic fan deposit, and debris avalanche deposit. PCA allowed us to select geological units suitable for analysis, while SDA was used to select some morphometric parameters, which could explain the differences in the formation processes and ages of the geological units. We found that the formation processes correspond well to mean slope, and that the geological ages that control the degree of surface dissection correspond well to the standard deviations of slope and negative topographic openness. © 2009 Elsevier B.V.

Sasaki Y.,Iwate Prefectural University | Shibata Y.,Iwate Prefectural University
Proceedings - 26th IEEE International Conference on Advanced Information Networking and Applications Workshops, WAINA 2012 | Year: 2012

Each local government provides a sharing system of disaster area information and safety information at a disaster. However, when a large-disaster occurs, disaster information system may not be available in the situation that a communication infrastructure was destroyed. In this study, we propose the disaster information system that is usually changes two kind of reporting methods at time and a disaster. In addition, the information dispatch from a stricken area at the time of disaster is enabled in the proposed system. That is because mobile server relays the data that occurred from disaster information system. © 2012 IEEE.

Akimoto T.,Iwate Prefectural University | Ogata T.,Iwate Prefectural University
Proceedings of the 11th IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2012 | Year: 2012

This paper proposes the comprehensive architecture of an integrated narrative generation system to discuss main two methods which are the foundations for integrating a variety of modules or elements and show a preliminary version utilizing our existing programs directly for seeing the picture of the integrated system. After we propose the macro structure of the proposed integrated system, we describe two fundamental methods to generate narrative structures and controlling the execution. And we show a pilot or preliminary version for the system developed by a kind of "bricolage" of existing programs corresponding to each module in the narrative generation process. Last, we discuss some issues for building the next version of the integrated narrative generation system. Moreover, this architecture is also differentiated from other many systems and approaches in the interdisciplinary concept of AI and narratology. © 2012 IEEE.

Oishi K.,Iwate Prefectural University | Ogata T.,Iwate Prefectural University
NLP-KE 2011 - Proceedings of the 7th International Conference on Natural Language Processing and Knowledge Engineering | Year: 2011

This paper describes the structure and function of conceptual dictionary positioning in our integrated narrative generation system architecture. It provides knowledge of verb concepts and noun concepts associated with an event concept that is a basic constitutional unit in narrative. This dictionary is developing now with the integrated narrative generation system. In this paper, we report the current developmental process to consider future expansion and plan. Current version of verb concept dictionary has 5337 case frames and modified 300 constraints, and noun concept dictionary contains 142168 noun concepts including 5770 intermediate concepts. After we explain the structure, we introduce the role and function in narrative generation process using two application systems. © 2011 IEEE.

Akimoto T.,Iwate Prefectural University | Ogata T.,Iwate Prefectural University
NLP-KE 2011 - Proceedings of the 7th International Conference on Natural Language Processing and Knowledge Engineering | Year: 2011

A goal of this research is to integrate various elements of narrative generation and develop an "integrated narrative generation system". Previously, we have been developing various prototyping elements under top-down designing. And we connected several elements in a pilot version of integrated narrative generation system. In this paper, first, we introduce elements and a pilot integrated system. And we consider on the expansion of the system mainly framework of narrative structural techniques and generation control mechanism. © 2011 IEEE.

Chakraborty B.,Iwate Prefectural University | Chakraborty G.,Iwate Prefectural University
Proceedings - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013 | Year: 2013

Feature selection or dimensionality reduction is an important task for any pattern recognition, data mining or machine learning problem. For selection of the optimal subset of relevant features, two steps are needed. In the first step a measure is designed for the evaluation of a candidate feature subset and in the second step, search through the feature space is done for selecting the optimal one. Existing feature selection methodologies use combinations of various evaluation measures and search strategies for selecting optimal feature subset. Though a large number of effective methodologies are already developed, none of them is perfect. Research is still going on to find better algorithm with lesser computational cost. In this work a fuzzy consistency based evaluation measure has been proposed. Consequently a feature selection algorithm using the proposed fuzzy consistency measure with particle swarm optimization, an evolutionary computational technique widely used for optimization problems, is developed for selecting optimal feature subset. Simple simulation experiments with bench mark data sets have been done and the simulation results provide evidence that the proposed algorithm might be a good candidate for selecting optimal feature subset. © 2013 IEEE.

Loading Iwate Prefectural University collaborators
Loading Iwate Prefectural University collaborators