The study on speech recognition and understanding has been done for many years. In this paper, we propose a fully-connected hidden layer between the input and state nodes and the output. Besides that, we also investig...
详细信息
ISBN:
(纸本)0780385934
The study on speech recognition and understanding has been done for many years. In this paper, we propose a fully-connected hidden layer between the input and state nodes and the output. Besides that, we also investigate and show that this hidden layer makes the learning of complex classification tasks more efficient. We also investigate difference between LPCC and MFCC in feature extraction process. The aim of the study was to observe the difference of Arabic's alphabet like "alif" until "ya". The purpose of this research is to upgrade the people's knowledge and understanding on Arabic's alphabet or word by using Fully-Connected Recurrent Neural Network (FCRNN) and Backpropagation through Time (BPTT) learning algorithm. 6 speakers (a mixture of male and female) are trained in quiet environment. Neural Network is well-known as a technique that has the ability to classified nonlinear problem. Today, lots of researches have been done in applying Neural Network towards the solution of speech recognition [1] such as Arabic. The Arabic language offers a number of challenges for speech recognition [2]. Even though positive results have been obtained from the continuous study, research on minimizing the error rate is still gaining lots of attention. This research utilizes Recurrent Neural Network, one of Neural Network technique to observe the difference of alphabet "alif" until "ya".
The fetal heart rate is indispensable for monitoring the health of unborn cattle fetuses. To monitor the fetal heart rate, a method employing independent component analysis (ICA) to extract the fetal electrocardiogram...
详细信息
The fetal heart rate is indispensable for monitoring the health of unborn cattle fetuses. To monitor the fetal heart rate, a method employing independent component analysis (ICA) to extract the fetal electrocardiogram (fECG) from potentials measured on the maternal body surface and composed of a mixture of the maternal ECG (mECG), fECG, baseline drift and noise is described. A mixing of the raw data was simplified using a linear time-invariant model. To separate the fECG from the mECG, baseline drift, and noise, an ICA strategy was applied, using a hyperbolic tangent as the contrast function and treating mutual information with the minimization principle to find the optimum demixing matrix to derive the fECG from the measured signals. After the feasibility of this method was shown on simulated signals obtained by randomly mixing pure fECG, pure mECG, low frequency sinusoidal drift and noise, real signals from three cloned pregnant Holstein cows with 157, 177 and 224-day gestation periods were used to verify the separation method. The results show that the fECG, mECG, low-frequency sinusoidal drift and noise can be clearly segregated in simulations, and that the fECG, mECG, baseline drift and noise can be successfully derived from real signals. The ICA approach has great potential in effectively detecting the fECG from maternal body surface potentials.
We present an approach to embedding a formal method into Rational Unified Process (RUP). The purposes are: (a) to unify different views of UML. (b) to enhance UML with the formal method to improve the quality of softw...
详细信息
The problem this paper addresses is that an architecture formed of software components can contain composition errors (introduced, for instance, as a result of the choice of a framework's parameters). The title &q...
详细信息
ISBN:
(纸本)0889864276
The problem this paper addresses is that an architecture formed of software components can contain composition errors (introduced, for instance, as a result of the choice of a framework's parameters). The title "Erroneous architecture is a relative concept" is to emphasize that whether a composition error occurs in an architecture depends on the way the architecture is used in its environment. An important issue is finding a way to possibly statically verify that, for a given setup containing the architecture, no composition errors can occur in any run. The contribution of the paper is bringing an evidence that this can be done by employing behavior protocols and their consent operator.
An architecture design of the intelligent agent for speech recognition and translation is presented in this paper. The design involves the agent architecture and the method of the agent is used. The architecture desig...
详细信息
An architecture design of the intelligent agent for speech recognition and translation is presented in this paper. The design involves the agent architecture and the method of the agent is used. The architecture design shows the relationship between the intelligent agent and speech recognition also translation. The intelligent agent for speech recognition is called S-AGENT and T-AGENT for translation. The purpose of the S-AGENT is to facilitate for transmitting the speech data via Internet or network. The S-AGENT is acting as a data transmit control to ensure the transmitted speech data is securely delivered. The task of the T-AGENT is different from the S-AGENT. The T-AGENT is acting as information retrieval. It processes the output from the speech recognition and translates the output based on its information memory database. If the information cannot be found on its memory, it searches the information required from the database dictionary provided. At the same time, it learns the information and saves the information to its memory for the future purpose.
Final year, group (capstone) projects in computing disciplines are often expected to fill multiple roles: in addition to allowing students to learn important domain-specific knowledge, they should reinforce computing ...
详细信息
Final year, group (capstone) projects in computing disciplines are often expected to fill multiple roles: in addition to allowing students to learn important domain-specific knowledge, they should reinforce computing and softwareengineering concepts and provide for the acquisition of transferable skills. For motivational and pedagogical reasons, it is clearly preferable that such projects respond to real needs, be those in research or industry. We describe two student projects based on a large repository of usage data and integrated into a course in Professional Computing. These projects fulfilled the objectives outlined above and were closely linked to the research of the first author. We suggest that similar projects based on large databases may offer a transferable paradigm for others to follow. Finally, we outline some important elements for a successful group project based on a large database. Copyright 2004 ACM.
＜正＞ Recently the Mathematical Programming community showed a renewed interest in Hilbert’s Positivstellensatz. The reason for this is that global optimization of polynomials in R[x1,..., xn] is NP-hard, while the ...
＜正＞ Recently the Mathematical Programming community showed a renewed interest in Hilbert’s Positivstellensatz. The reason for this is that global optimization of polynomials in R[x1,..., xn] is NP-hard, while the question whether a polynomial can be written as a sum of squares has tractable aspects. This is due to the fact that Semidefinite Programming can be used to decide in polynomial time （up to a prescribed precision） whether a polynomial can be rewritten as a sum of squares of linear combinations of monomials coming from a specified set. We investigate this approach in the context of Satisfiability. We are interested in the question whether the Satisfiability area can provide examples of polynomials which are non-negative but not sums of squares but also examine the potential of the theory for providing tests for unsatisfiability and providing MAXSAT upper bounds. We compare the SOS （Sums Of Squares） approach with existing upper bound techniques （for the MAX-2-SAT case） of Goemans and Williamson [6] and Feige and Goemans [5], which are based on Semidefinite Programming as well. We advocate that the SOS approach gives more accurate upper bounds at comparable computational costs.
This paper describes the application of a novel reinforcement learning to the difficult real world problem of elevator dispatching. We propose a new algorithm combing Q-learning and residual gradient to solve this pro...
详细信息
ISBN:
(纸本)4907764227
This paper describes the application of a novel reinforcement learning to the difficult real world problem of elevator dispatching. We propose a new algorithm combing Q-learning and residual gradient to solve this problem and obtain the results which are better than other traditional elevator control algorithms.
暂无评论