• The Journal of the Acoustical Society of Korea
• /
• v.42 no.5
• /
• pp.395-401
• /
• 2023

Sound Event Detection (SED) aims to identify not only sound category but also time interval for target sounds in an audio waveform. It is a critical technique in field of acoustic surveillance system and monitoring system. Recently, various models have introduced through Detection and Classification of Acoustic Scenes and Events (DCASE) Task 4. This paper explored how to design optimal parameters of DenseNet based model, which has led to outstanding performance in other recognition system. In experiment, DenseRNN as an SED model consists of DensNet-BC and bi-directional Gated Recurrent Units (GRU). This model is trained with Mean teacher model. With an event-based f-score, evaluation is performed depending on parameters, related to model architecture as well as model training, under the assessment protocol of DCASE task4. Experimental result shows that the performance goes up and has been saturated to near the best. Also, DenseRNN would be trained more effectively without dropout technique.

• Journal of Broadcast Engineering
• /
• v.24 no.4
• /
• pp.633-642
• /
• 2019

Recently, the convolution neural network (CNN) model at a single image super-resolution (SISR) have been very successful. The residual learning method can improve training stability and network performance in CNN. In this paper, we propose a SISR using recursive residual network architecture by introducing dense skip connections for learning nonlinear mapping from low-resolution input image to high-resolution target image. The proposed SISR method adopts a method of the recursive residual learning to mitigate the difficulty of the deep network training and remove unnecessary modules for easier to optimize in CNN layers because of the concise and compact recursive network via dense skip connection method. The proposed method not only alleviates the vanishing-gradient problem of a very deep network, but also get the outstanding performance with low complexity of neural network, which allows the neural network to perform training, thereby exhibiting improved performance of SISR method.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.38 no.6
• /
• pp.412-419
• /
• 2001

In accordance with the PON(passive optical network) could be setup, effective connections with light sources, optical detectors, and optical fibers are the best sensitive points to represent the efficiency of network. Therefore, in this paper we designed and fabricated optical transceiver connection chip that was consisted of channel waveguide, Y-branch, and CWDM on the 2" BK7 glass substrate. This chip can be used for 1.31/1.55${\mu}{\textrm}{m}$ CWDM network and 1.55${\mu}{\textrm}{m}$ region dense WDM network.work.

• Journal of Korea Multimedia Society
• /
• v.23 no.12
• /
• pp.1540-1551
• /
• 2020

Aiming at the problem that the existing human behavior recognition algorithm cannot fully utilize the multi-level spatio-temporal information of the network, a human behavior recognition algorithm based on a dense three-dimensional residual network is proposed. First, the proposed algorithm uses a dense block of three-dimensional residuals as the basic module of the network. The module extracts the hierarchical features of human behavior through densely connected convolutional layers; Secondly, the local feature aggregation adaptive method is used to learn the local dense features of human behavior; Then, the residual connection module is applied to promote the flow of feature information and reduced the difficulty of training; Finally, the multi-layer local feature extraction of the network is realized by cascading multiple three-dimensional residual dense blocks, and use the global feature aggregation adaptive method to learn the features of all network layers to realize human behavior recognition. A large number of experimental results on benchmark datasets KTH show that the recognition rate (top-l accuracy) of the proposed algorithm reaches 93.52%. Compared with the three-dimensional convolutional neural network (C3D) algorithm, it has improved by 3.93 percentage points. The proposed algorithm framework has good robustness and transfer learning ability, and can effectively handle a variety of video behavior recognition tasks.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.6 s.38
• /
• pp.209-218
• /
• 2005

In this paper, we present an Active Optical Network(AON) . The AON uses the Dense Wavelength Division Multiplexing(DWDM) from optical communication access network of ring type, and will be able to provide the smoothly service in the Bandwidth on Demand by using DWDM. It supports the connection of the multiple wavelength and the Sub-Carrier from the optical gigabit ethernet switch. The Wavelength Add Drop Multiplexer(WADM) extracts a specific wavelength, and composes a node of the ring network. The specific wavelength becomes demultiplexing in the Sub-Carrier and it is distributed in the user The active connection of optical gigabit ethernet switch where the distribution of access network is started and access terminal connection equipment is possible. By the BoD from the AON it compares the buffer size which changes, and it analyzes. Also the Time delay of bit compares with the throughput of server The limit of amount of time is decided. Consequently it will be able to realize the dynamic use protocol and an efficient algorithm of the network.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.6
• /
• pp.2480-2496
• /
• 2020

Considering that high-dose X-ray radiation during CT scans may bring potential risks to patients, in the medical imaging industry there has been increasing emphasis on low-dose CT. Due to complex statistical characteristics of noise found in low-dose CT images, many traditional methods are difficult to preserve structural details effectively while suppressing noise and artifacts. Inspired by the deep learning techniques, we propose a densely connected residual network (DCRN) for low-dose CT image noise cancelation, which combines the ideas of dense connection with residual learning. On one hand, dense connection maximizes information flow between layers in the network, which is beneficial to maintain structural details when denoising images. On the other hand, residual learning paired with batch normalization would allow for decreased training speed and better noise reduction performance in images. The experiments are performed on the 100 CT images selected from a public medical dataset-TCIA(The Cancer Imaging Archive). Compared with the other three competitive denoising algorithms, both subjective visual effect and objective evaluation indexes which include PSNR, RMSE, MAE and SSIM show that the proposed network can improve LDCT images quality more effectively while maintaining a low computational cost. In the objective evaluation indexes, the highest PSNR 33.67, RMSE 5.659, MAE 1.965 and SSIM 0.9434 are achieved by the proposed method. Especially for RMSE, compare with the best performing algorithm in the comparison algorithms, the proposed network increases it by 7 percentage points.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.1061-1070
• /
• 2021

In this manuscript, we tried to improve the performance of the FC-DenseNet by applying an attention gate for the classification of cropping areas. The attention gate module could facilitate the learning of a deep learning model and improve the performance of the model by injecting of spatial/spectral weights to each feature map. Crop classification was performed in the onion and garlic regions using a proposed deep learning model in which an attention gate was added to the skip connection part of FC-DenseNet. Training data was produced using various PlanetScope satellite imagery, and preprocessing was applied to minimize the problem of imbalanced training dataset. As a result of the crop classification, it was verified that the proposed deep learning model can more effectively classify the onion and garlic regions than existing FC-DenseNet algorithm.

• International Journal of Computer Science & Network Security
• /
• v.21 no.11
• /
• pp.17-22
• /
• 2021

Recently, image super-resolution techniques used in convolutional neural networks (CNN) have led to remarkable performance in the research area of digital image processing applications and computer vision tasks. Convolutional layers stacked on top of each other can design a more complex network architecture, but they also use more memory in terms of the number of parameters and introduce the vanishing gradient problem during training. Furthermore, earlier approaches of single image super-resolution used interpolation technique as a pre-processing stage to upscale the low-resolution image into HR image. The design of these approaches is simple, but not effective and insert the newer unwanted pixels (noises) in the reconstructed HR image. In this paper, authors are propose a novel single image super-resolution architecture based on synchronized depthwise separable convolution with Dense Skip Connection Block (DSCB). In addition, unlike existing SR methods that only rely on single path, but our proposed method used the synchronizes path for generating the SISR image. Extensive quantitative and qualitative experiments show that our method (SDCN) achieves promising improvements than other state-of-the-art methods.

• ETRI Journal
• /
• v.29 no.2
• /
• pp.162-168
• /
• 2007

A new scheme for bi-directional HDTV/Gigabit Ethernet/CATV transmission over a hybrid dense-wavelength-division-multiplexing passive optical network (DWDM-PON) is proposed and demonstrated. It is based on injection-locked vertical-cavity surface-emitting lasers and distributed-feedback laser diodes as transmitters. Services with 129 HDTV channels, a 1.25 Gbps Gigabit Ethernet connection, and 77 CATV channels are successfully demonstrated over 40 km single-mode fiber links. Good performance of bit error rate, carrier-to-noise ratio, composite second order, and composite triple beat is achieved in our proposed bidirectional DWDM-PON.

• Journal of The Korean Astronomical Society
• /
• v.37 no.4
• /
• pp.223-224
• /
• 2004

The Tycho supernova remnant (SNR), as one of the few historical SNRs, has been widely studied in various wavebands and previous observations have shown evidence that Tycho is interacting with a dense ambient medium toward the northeast direction, In this paper, we report our high-resolution (16') $^{12}CO$ observation of the remnant using the Nobeyama 45m radio telescope. The Nobeyama data shows that a large molecular cloud surrounds the SNR along the northeastern boundary. We suggest that the Tycho SNR and the molecular cloud are both located in the Perseus arm and that the dense medium interacting with the SNR is possibly the molecular cloud. We also discuss the possible connection between the molecular cloud and the Balmer-dominated optical filaments, and suggest that the preshock gas may be accelerated within the cosmic ray and/or fast neutral precursor.