Search

To perform a home service task through cooperation with a human in a real environment, a robot needs to deal with the environmental changes and accordingly plan appropriate behavior sequence. For this purpose, in this paper, we propose an adaptive task planner which is based on memory and reasoning. A robot perceives user behaviors and objects using an RGB-depth and thermal sensor. The robot stores a temporal sequence of behaviors for performing a task in its episodic memory that is realized by a sequence to sequence network. When the user command is given, the episodic memory is used to retrieve the behavior sequence to carry out the command. On the other hand, when the robot perceives user behaviors, the robot postpones its behavior till his/her behavior is stopped. Once stopped, the episodic memory retrieves the behavior sequence to conduct a task that the user has intended. A task scheduler schedules the behavior sequence from the memory and sends it to an internal simulator. The internal simulator confirms the behavior sequence to be executable and then if executable, it sends the next executable behavior to the execution module. If a behavior fails in the internal simulation test, fast forward planner generates an alternative behavior sequence to resolve the failed behavior problem. The effectiveness and applicability of the proposed planner is demonstrated by a wheel-based humanoid robot.

Online sequential extreme learning machine (OS-ELM) is an online learning algorithm training single-hidden layer feedforward neural networks (SLFNs), which can learn data one-by-one or chunk-by-chunk with fixed or varying data size. Due to its characteristics of online sequential learning, OS-ELM is popularly used to solve time-series prediction problem, such as stock forecast, weather forecast, passenger count forecast, etc. OS-ELM, however, has two fatal drawbacks: Its input weights cannot be adjusted and it cannot be applied to learn recurrent neural network (RNN). Therefore we propose a modified version of OS-ELM, called online recurrent extreme learning machine (OR-ELM), which is able to adjust input weights and can be applied to learn RNN, by applying ELM-auto-encoder and a normalization method called layer normalization (LN). Proposed method is used to solve a time-series prediction problem on NewYork City passenger count dataset, and the results show that R-ELM outperforms OS-ELM and other online-sequential learning algorithms such as hierarchical temporal memory (HTM) and online long short-term memory (online LSTM).

We propose a novel method for the demosaicing of event-based images that offers substantial performance improvement of far-distance gesture recognition based on deep Convolutional Neural Network. Unlike the conventional demosaicing technique using the spatial color interpolation of Bayer patterns, our new approach utilizes spatiotemporal correlation between pixel arrays, whereby timestamps of high-resolution pixels are efficiently generated in real-time from the event data. In this paper, we describe this new method and evaluate its performance with a hand motion recognition task.

For the last few decades, lead-based(PbO-) glass-frits have been used in Ag electrode paste for screen printing metallization on Si-solar cell because of strong contact formation with a low cost. However, due to the electric insulation of oxide glass (OG), even though a great deal of effort has been made to improve the contact resistance between Ag grid and Si-emitter by adding nano-sized fillers, such as nano-Ag or ZnO, etc., there is a huge limitation which could not be easily overcome with an intrinsic electrical insulation property of OG. Therefore, we suggest that the total replacement of OG with metallic glass(MG), which is a conductive, is a new approach to overcome the limitation of electrical properties of Ag electrode paste. In this research, Al-based metallic glass(Al-MG) has been selected with the advantages of high oxidation resistance, low Tg (glass transition temperature) and high solubility in Ag. The contact resistance and specific resistivity of Ag/Al-MG electrode are achieved 0.5mΩcm2 and 2.9 μΩcm, respectively, which are comparable to those of electroplating electrode. The performance of Ag/Al-MG electrode is also proved in i-BC (inter-digitated back contact) cell of which conversion efficiency showed above 20.3%. We will discuss about the mechanism of Al-MG electrode contact formations, including a wetting behavior of Al-MG and the reaction steps between Al-MG and Ag during the firing processing.

Early detection of breast tumor is critical in determining the best possible treatment approach. Due to its superiority compared with mammography in its possibility to detect lesions in dense breast tissue, ultrasound imaging has become an important modality in breast tumor detection and classification. This paper discusses the novel Fourier-based shape feature extraction techniques that provide enhanced classification accuracy for breast tumor in the computer-aided B-mode ultrasound diagnosis system. To demonstrate the effectiveness of the proposed method, experiments were performed using 4,107 ultrasound images with 2,508 malignancy cases. Experimental results show that the breast tumor classification accuracy of the proposed technique was 15.8%, 5.43%, 17.32%, and 13.86% higher than the previous shape features such as number of protuberances, number of depressions, lobulation index, and dissimilarity, respectively.

Text recognition in natural color images is not successful with the naive application of general OCR (Optical character recognition) because the numerous visual environments and luminance in the real world scene. This problem can be solved by adopting various brightness/contrast adjustments and texture analysis to create a binary image very similar to printed text. But such a solution can have a shortcoming; increased execution time. We propose an English text detection method that parallelizes processing jobs to utilize a multi-core processor effectively in order to improve text recognition accuracy and minimize execution time overhead.

Multiprocessor-system-on-a-chips (MPSoCs) are being increasingly employed to solve a diverse spectrum of problems from both high-end and low-end computing. Multimedia streaming applications can get great performance from them, but developing MPSoC software that guarantees real-time requirements is very difficult. In this paper, we present an architecture of real-time media framework that can provide both easy of programming and real-time guarantee to multimedia applications. In addition, programming model and mechanism for real-time guarantee are briefly explained. Issues in developing media framework on asymmetric MPSoC hardware further presented, which we are going to apply in our media framework implementation.