Soyeon Kim

In this study, the ideal cycles with finite heat capacity rates is investigated theoretically to maximize power generation using a sequential Carnot cycle model. Although the Carnot efficiency is important, it is limited to evaluating only in terms of heat source/sink temperatures. For the actual heat engine, maximization of power generation is more important than cycle thermal efficiency when utilizing low-grade heat sources such as a waste heat. In this study, power generation optimization is

Moving target detection is an important technique in visual surveillance systems. If a camera is freely moving, it becomes more difficult to detect a moving target, especially in the environment of a wide-range background. To compensate for the global motion of a wide-range background, a disparity-based adaptive multi-homography method is proposed. The proposed method comprises four steps: 1) feature point extraction; 2) generation of adaptive multi-homography matrices using motion grouping; 3)

A low power real-time visual object tracking (VOT) processor using the siamese network (SiamNet) is proposed for mobile devices. Two key features enable a real-time VOT with low power consumption on mobile devices. First, correlation-based spatial early stopping (CSES) is proposed to reduce the computational workload. CSES reduces ~56.8% of the overall computation of the SiamNet by gradually eliminating the background. Second, the dual mode reuse core (DMRC) is proposed for supporting both the c

Generative adversarial networks (GANs) consist of multiple deep neural networks cooperating and competing with each other. Due to their complex architectures and large feature map sizes, training GANs requires a huge amount of computations. Moreover, instance normalization (IN) layers in GANs dramatically increase the external memory access (EMA). However, retraining GANs with user-specific data is critical on mobile devices because the pre-trained model outputs distorted images under user-speci

This letter demonstrates hidden Markov model (HMM), multilayer perceptron (MLP), and time-delay recursive neural network (TDRNN) architectures for the purpose of recognizing pitch accents given observation of the F0 and energy trajectories. At an insertion error rate of 25%, the deletion error rates of the MLP, TDRNN, and HMM are 13.2%, 7.9%, and 32.7%, respectively, despite the fact that both MLP and TDRNN have 70% fewer trainable parameters than the HMM. Error analysis suggests that low-pitch

We propose a new object motion histogram for content-based indexing of MPEG video data. Video data are segmented into shots. Then object motions are extracted and clustered after removing background motion. We adopted polar coordinates to describe the clustered object motion. An object motion histogram in a shot (OMHS) is defined and obtained on the proposed polar division technique. The first moment of object motion is utilized as a descriptor of object motion.

A new neural network approach is presented for the global placement of macrocells. This algorithm is based on a learning algorithm for neural networks proposed by T. Kohonen (1988), called the self-organization principle, which has the property of topology-preserving mapping. Due to this property, topologically close circuit modules are located closely in the target placement region. Compared to earlier work on standard cell circuits, finite sizes of modules are considered during the self-organi

The advent of deep learning technologies gives satellite imagery analysis birth to unprecedented achievements to various tasks. Especially, change detection is one of the attentive fields regarding to remote sensing as a unique task to compare the paired images. While a great amount of works deals with change detection in pixel level to generate change map, its labelling cost to train the model in data driven manner is extremely high in that it should be annotated in pixel level as well and it i

A lot of companies have essentially exploited Database Management System (DBMS) to process huge amounts of data due to emerging of the information industry. Database administrators need the information of workload in order to maintain high performance DBMS. However, it has been hard to identify workload due to being diversified and complicated of database application. Therefore, the method which can automatically identify workload is required in these environments. In this paper, we propose PCA-

Due to the emergence of new application programs and the fast growth of Internet users, Internet routers are required to provide the quality of services according to the class of input packets, which is identified by wire-speed packet classification. For a pre-defined rule set, by performing multi-dimensional search using various header fields of an input packet, packet classification determines the highest priority rule matching to the input packet. Efficient packet classification algorithms ha