• ETRI Journal
• /
• v.40 no.5
• /
• pp.643-652
• /
• 2018

Dysarthria is a degenerative disorder of the central nervous system that affects the control of articulation and pitch; therefore, it affects the uniqueness of sound produced by the speaker. Hence, dysarthric speaker recognition is a challenging task. In this paper, a feature-extraction method based on deep belief networks is presented for the task of identifying a speaker suffering from dysarthria. The effectiveness of the proposed method is demonstrated and compared with well-known Mel-frequency cepstral coefficient features. For classification purposes, the use of a multi-layer perceptron neural network is proposed with two structures. Our evaluations using the universal access speech database produced promising results and outperformed other baseline methods. In addition, speaker identification under both text-dependent and text-independent conditions are explored. The highest accuracy achieved using the proposed system is 97.3%.

• Proceedings of the ESK Conference
• /
• 1993.10a
• /
• pp.21-30
• /
• 1993

This paper describes the development of a simulation model of nuclear power plant operators including cognitive aspects by using a network modeling soft ware, Micro-SAINT (System Analysis of Integrated Networks of Tasks) for the analysis of operator performance. Network model description based on Micro-SAINT includes tasks, resources, precedence relations among tasks, flow of information and PSFs (Performance Shaping Factors) on task performance. We have tried to evaluate the performance with several performance measures such as the number of tasks allocated, relative time presure among operators within a shift, for the selected test accident scenarior; small-break LOCA (Loss of Coolant Accident) in a PWR (Pressurized Water Reactor) type nuclear power plant.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.29B no.10
• /
• pp.37-45
• /
• 1992

For a precise manipulator control in the presence of environmental uncertainties, it has long been recognized that the robot should be controlled in a task-referenced space. In this respect, an effective visual servo control system for robot manipulators based on neural networks is proposed. In the proposed control system, a Backpropagation neural network is used first to learn the mapping relationship between the robot's joint space and the video image space. However, in the real control loop, this network is not used in itself, but its first and second derivatives are used to generate servo commands for the robot. Second, and Adaline neural network is used to identify the approximately linear dynamics of the robot and also to generate the proper joint torque commands. Computer simulation has been performed demonstrating the proposed method's superior performance. Futrhermore, the proposed scheme can be effectively utilized in a robot skill acquisition system where the robot can be taught by watching a human behavioral task.

• The Journal of the Korea Contents Association
• /
• v.5 no.1
• /
• pp.109-116
• /
• 2005

This paper is to develop the prototype of a decision making for loan granting system at banks and to evaluate the effectiveness of it. The prototype is called at FENET-LG in this paper. The decision to grant a loan is an unstructured and vagueness task because it is required a tremendous amount of data and many complex relationships among them. Evaluating these many data and relationships is a difficult task even for most experienced decision maker of bank. Therefore, where complex judgement is required, the decision maker of bank may benefit from the use of fuzzy expert network to support the evaluation of ability to pay back. Given the characteristics of decision maker of banking facilities judgement task about ability to pay back, the prototype system named FENET-LG is constructed by integration of fuzzy expert system and neural network. The FENET-LG takes advantage of both the deductive approach of fuzzy expert system and the inductive approach of a neural network to provide a decision aid designed to support and facilitate the process of conducting a judgement of ability to pay back.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.1
• /
• pp.107-112
• /
• 2020

We analyze the flow aggregate (FA) based network delay guarantee framework, with generalized minimal interleaved regulator (IR) initially suggested by IEEE 802.1 time sensitive network (TSN) task group (TG). The framework has multiple networks with minimal IRs attached at their output ports for suppressing the burst cascades, with FAs within a network for alleviating the scheduling complexity. We analyze the framework with various topology and parameter sets with the conclusion that the FA-based framework with low complexity can yield better performance than the integrated services (IntServ) system with high complexity, especially with large network size and large FA size.

• Journal of the Korean Society for information Management
• /
• v.30 no.2
• /
• pp.83-99
• /
• 2013

The purpose of this study was to analyze ILL data in Gyeonggi province so that it could make a further analysis on current inter-regional network of book collection in ILL. In details, this study sought to analyze inter-regional network of ILL book collection among public libraries in Gyeonggi province to examine how a collection of books could be exchanged among those libraries, and analyze possible applications of task-based data in ILL. As a result, this study could verify that the further implementation of ILL across more detailed areas than current regions for the benefit of efficient ILL, if possible, would contribute to streamlining ILL practices.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.16 no.4
• /
• pp.87-92
• /
• 2007

The full automation welding has not yet been achieved partly because the mathematical model for the process parameters of a given welding task is not fully understood and quantified. Several mathematical models to control welding quality, productivity, microstructure and weld properties in arc welding processes have been studied. However, it is not an easy task to apply them to the various practical situations because the relationship between the process parameters and the bead geometry is non-linear and also they are usually dependent on the specific experimental results. Practically, it is difficult, but important to know how to establish a mathematical model that can predict the result of the actual welding process and how to select the optimum welding condition under a certain constraint. In this paper, an attempt has been made to develop an neural network model to predict the weld top-bead height as a function of key process parameters in the welding. and to compare the developed models using three different training algorithms in order to select an adequate neural network model for prediction of top-bead height.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2004.10a
• /
• pp.170-174
• /
• 2004

Despite the widespread use in the various manufacturing industries, the full automation of the robotic CO$_2$ welding has not yet been achieved partly because the mathematical model for the process parameters of a given welding task is not fully understood and quantified. Several mathematical models to control welding quality, productivity, microstructure and weld properties in arc welding processes have been studied. However, it is not an easy task to apply them to the various practical situations because the relationship between the process parameters and the bead geometry is non-linear and also they are usually dependent on the specific experimental results. Practically, it is difficult, but important to know how to establish a mathematical model that can predict the result of the actual welding process and how to select the optimum welding condition under a certain constraint. In this paper, an attempt has been made to develop an Radial basis function network model to predict the weld top-bead width as a function of key process parameters in the robotic CO$_2$ welding. and to compare the developed model and a simple neural network model using two different training algorithms in order to verify performance. of the developed model.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.337-351
• /
• 2021

Automatically recognizing facial expressions in video sequences is a challenging task because there is little direct correlation between facial features and subjective emotions in video. To overcome the problem, a video facial expression recognition method using spatiotemporal recurrent neural network and feature fusion is proposed. Firstly, the video is preprocessed. Then, the double-layer cascade structure is used to detect a face in a video image. In addition, two deep convolutional neural networks are used to extract the time-domain and airspace facial features in the video. The spatial convolutional neural network is used to extract the spatial information features from each frame of the static expression images in the video. The temporal convolutional neural network is used to extract the dynamic information features from the optical flow information from multiple frames of expression images in the video. A multiplication fusion is performed with the spatiotemporal features learned by the two deep convolutional neural networks. Finally, the fused features are input to the support vector machine to realize the facial expression classification task. The experimental results on cNTERFACE, RML, and AFEW6.0 datasets show that the recognition rates obtained by the proposed method are as high as 88.67%, 70.32%, and 63.84%, respectively. Comparative experiments show that the proposed method obtains higher recognition accuracy than other recently reported methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.4
• /
• pp.1275-1292
• /
• 2021

As a fine-grained classification problem, aspect-level sentiment classification predicts the sentiment polarity for different aspects in context. To address this issue, researchers have widely used attention mechanisms to abstract the relationship between context and aspects. Still, it is difficult to effectively obtain a more profound semantic representation, and the strong correlation between local context features and the aspect-based sentiment is rarely considered. In this paper, a hybrid attention capsule network for aspect-level sentiment classification (ABASCap) was proposed. In this model, the multi-head self-attention was improved, and a context mask mechanism based on adjustable context window was proposed, so as to effectively obtain the internal association between aspects and context. Moreover, the dynamic routing algorithm and activation function in capsule network were optimized to meet the task requirements. Finally, sufficient experiments were conducted on three benchmark datasets in different domains. Compared with other baseline models, ABASCap achieved better classification results, and outperformed the state-of-the-art methods in this task after incorporating pre-training BERT.