The development of business failure prediction system to prevent the significant loss of social costs caused by the companies' unexpected bankruptcy is a popular investigation issue. Because of the constraint on t...
详细信息
To appropriately assist mobile robot teleoperation within a shared autonomy system for remote task executions, this paper reports a novel approach to recognize the contextual task the human operator performs, by emplo...
详细信息
To appropriately assist mobile robot teleoperation within a shared autonomy system for remote task executions, this paper reports a novel approach to recognize the contextual task the human operator performs, by employing Sparse Online Gaussian Process to learn and classify human motion patterns executing various task types from demonstrations, due to its superior introspective capability over other state-of-art classification methods, such as Support Vector Machine (SVM), which is probably the most widely used approach on this topic to date. Our approach is evaluated on real data and shown to outperform current methods both in classification accuracy and uncertainty estimation regarding the predictive class labels, while maintaining sparsity to scale with large datasets.
The development of business failure prediction system to prevent the significant loss of social costs caused by the companies' unexpected bankruptcy is a popular investigation issue. Because of the constraint on t...
详细信息
The development of business failure prediction system to prevent the significant loss of social costs caused by the companies' unexpected bankruptcy is a popular investigation issue. Because of the constraint on the statistic assumptions, the forecasting models established by traditional statistic methods have some limits in its identity. Therefore, in recent years various algorithms imitating of biological behavior have been proposed for improving the accuracy of forecasting models. In this paper, a new artificial bee colony (ABC) based clustering algorithm has been proposed for replacing with previous clustering method to group forecast value by homogeneous. Furthermore, the rough set theory has been utilized to deal with the uncertain data and provide the decision rules and classification results. In the simulation test, the data of listed companies in Taiwan between 1977 to 2011 years have been sampled. Finally, there are 57 companies with bankruptcy crisis have been sifted to verify the effectiveness of the proposed methods. The simulation results indicate that the accuracy of developed business distress early-warning model is much better than that of other methods, especially in the last year of crisis occurrence.
In the present paper, we propose a simplified variant of the conditional gradient method for the network equilibrium problem. This modification uses an inexact solution to the auxiliary direction finding problem. Prel...
详细信息
ISBN:
(数字)9781538694688
ISBN:
(纸本)9781538694695
In the present paper, we propose a simplified variant of the conditional gradient method for the network equilibrium problem. This modification uses an inexact solution to the auxiliary direction finding problem. Preliminary numeric tests show the efficiency of this approach in comparison with the ordinary conditional gradient method.
Understanding the reasons for customer churn provides added value in terms of retaining existing customers, as customer attrition leads to revenue loss for companies and incurs marketing costs for acquiring new custom...
详细信息
作者:
Takebayashi, YMemberSenior Research Engineer
3rd Communications System Lab. Research & Development Center Toshiba Corporation Kawasaki Japan 210 Received his B.E. degree in 1974 from Dept. Electrical Eng.
Keio Univ. and his Ph.D. degree in 1980 from Tohoku Univ. He affiliated in 1980 with Toshiba Corp. He is engaged in research on speech recognition and intelligent interface. Presently Chief Researcher 3rd Comm. System Lab. in R&D Center. Visiting Researcher 1985–1987 MIT Media Lab. Head of 5th Lab. 1992–1993 Jap. Electr. Dictionary Lab. Paper Award 1992 Nat. Conv. Soc. Artif. Intel. Tech. Dev. Award 1993 Acost. Soc. Jap. He is a member of Inf. Proc. Soc. Acoust. Soc. Jap.and Soc. Artif. Intel.
This paper considers the user-centered spontaneous speech dialogue system TOSBURG-II (Task-oriented dialogue system based on speech understanding and response generation), and discusses the design from the viewpoint o...
详细信息
This paper considers the user-centered spontaneous speech dialogue system TOSBURG-II (Task-oriented dialogue system based on speech understanding and response generation), and discusses the design from the viewpoint of media tech.ology and a multimodal interface. The authors have developed element tech.iques, including spontaneous speech understanding, user-center dialogue control, multimodal response generation and speech response cancelling, all based on the noise-immune word-spotting and keywords. The concept is that ''no constraint is imposed on the user.'' By integrating these tech.iques, the realtime speech dialogue system for an unspecified user is developed. The speech dialogue data acquisition/ evaluation system is constructed on the real system. The system can record real speech data as well as the intermediate result of processing in the dialogue system, such as keyword spotting, Speech understanding and dialogue processing: The system can also be utilized in the construction of the speech dialogue corpus and the. evaluation/improvement of the human factor aspect, in addition to,the evaluation of the system performance. As a result of trial use and evaluation experiment for the real system for unspecified users, it is verified that spontaneous speech understanding based on the interruption function by the user and the multimodal response and keywords, is useful in improving the naturalness of the dialogue and robustness.
作者:
OOHORI, TNAGAO, NWATANABE, KMemberFaculty of Engineering
Hokkaido Institute of Technology Sapporo Japan 006 Takafumi Oohori graduated in 1973 from the Dept. Electrical Eng.
Fac. Eng. Hokkaido Univ. where he received a Dr. of Eng. degree (Electrical Eng.) in 1978. He was a Lecturer in 1978 an Assoc. Prof. in 1981 and a Prof. in 1993 in the Dept. of Electrical Eng. Fac. Eng. Hokkaido Inst. of Tech. He is engaged in research on system engineering and neural networks. He is a member of IEEJ and Inf. Proc. Soc. Japan. Nonmember
The distributed representation-type three-layered perceptron with backpropagation has such problems as the local minimum long learning time, and ambiguity in internal representation. As a method to cope with those pro...
详细信息
The distributed representation-type three-layered perceptron with backpropagation has such problems as the local minimum long learning time, and ambiguity in internal representation. As a method to cope with those problems, this paper proposes the four-layered perceptron, together with the learning algorithm, where a hidden layer is added, so that each discrete sample point can perfectly be represented by the corresponding output of the upper hidden layer. First, the learning algorithm of the perceptron is applied successively to the sample points, and the learning is executed so that the input sample points are separated perfectly by the piecewise sets of hyperplanes. In this mechanism, the output matrix of the lower hidder layer output is nonsingular. Consequently, the following four-layered perceptron can be constructed, where the output matrix of the upper hidden layer is an identity matrix, and any discrete value can be produced as the output from the output layer by adjusting the network coefficients. Computational experiments are made for the realization of the three-valued logic function, which is a learning problem on the two-dimensional plane, as well as the pattern recognition problem by the representative sample points. As a result, it is shown that the learning converges in less than 1/100 computation time, compared to the three-layered perceptron with the backpropagation.
Understanding the reasons for customer churn provides added value in terms of retaining existing customers, as customer attrition leads to revenue loss for companies and incurs marketing costs for acquiring new custom...
Understanding the reasons for customer churn provides added value in terms of retaining existing customers, as customer attrition leads to revenue loss for companies and incurs marketing costs for acquiring new customers. In this study, the 6-month historical data of a Pay-TV company operating in Turkey was used, and due to the imbalanced nature of the dataset on a label basis, the oversampling method was applied. During the model development phase, various artificial learning algorithms (Random Forest, Logistic Regression, KNearest Neighbors, Decision Tree, AdaBoost, XGBoost, Extra Tree Classifier) were utilized, and their performances were compared. Based on the evaluation of success criteria for each model, it was observed that the tree-based Random Forest, Extra Tree Classifier and XGBoost achieved the highest performance for this dataset.
暂无评论