• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.3 no.2
• /
• pp.313-319
• /
• 1999

We devise the 3 models of Multilayered Recurrent Prediction Neural Network(MLRPNN), which are obtained by modifying the Multilayered Perceptron(MLP) with 4 layers. We experimentally study the speech recognition performance of 3 models by a comparative method, according to the variation of the prediction order, the number of neurons in two hidden layers, initial values of connecting weights and transfer function, respectively. By the experiment, the recognition performance of each MLRPNN is better than that of MLP. At the model that returns the output of the upper hidden layer to the lower hidden layer, the recognition performance shows the best value. All MLRPNNs, which have 10 or 15 neurons in the upper and lower hidden layer and is predicted by 3rd or 4th order, show the improved speech recognition rate. On learning, these MLRPNNs have a better recognition rate when we set the initial weights between -0.5 and 0.5, and use the unipolar sigmoid transfer function in the lower hidden layer.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.5C
• /
• pp.683-691
• /
• 2004

To transmit MPEG-2 video on an errorneous channel, a number of error control techniques are needed. Especially, error concealment techniques which can be implemented on receivers independent of transmitters are essential to obtain good video quality. In this paper, prediction of motion vector and an adaptive boundary matching algorithm are presented for temporal error concealment. Before the complex BMA, we perform error concealment by a motion vector prediction using neighboring motion vectors. If the candidate of error concealment is not satisfied, search range and reliable boundary pixels are selected by the temporal activity or motion vectors and a damaged macroblock is concealed by applying an adaptive BMA. This error concealment technique reduces the complexity and maintains a PSNR gain of 0.3∼0.7㏈ compared to conventional BMA.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.1
• /
• pp.56-63
• /
• 2009

Nowdays, Most of Internet Contents delivered as a compressed file. It gives many advantages like deduction of communication bandwidth and transmission time etc. In case of JPEG Compression, Quantization is the most important procedure which accomplish the compression. In general signal processing, Quantization is the process which converts continuous analog signal to discrete digital signal. As you known already, Quantization over JPEG compression is to reduce magnitude of pixel value in spatial domain or coefficient in frequency domain. A lot of Data Hiding algorithms also developed to applicable for those compressed files. In this paper, we are going to unveil the influence of quantization table which used in the process of JPEG compression. Even thought most of algorithm modify frequency coefficients with considering image quality, they are ignoring the influence of quantization factor corresponding with the modified frequency coefficient. If existing algorithm adapt this result, they can easily evaluate their performances.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.8A
• /
• pp.702-711
• /
• 2011

This paper proposes a HAG(Hidden-Node-Aware Grouping) algorithm for IEEE 802.15.4 networks to enhance the performance by eliminating collisions resulted from the hidden node problem without adopting the RTS/CTS packet exchanges. To solve the hidden node problem, the HAG algorithm organizes nodes into disjoint transmission groups by dynamically allocating hidden nodes into separate groups which take turns in a round robin way for their transmission. For dynamic group adjustment, it periodically evaluates the presence of hidden nodes based on subordinate nodes' receipt reports. To accurately measure its behavior, this paper also builds an analytical model to estimate its throughput fluctuation over various network topologies. The mathematical model along with simulation results confirmed that the HAG technique gracefully degraded the throughput of IEEE 802.15.4 networks whereas the standard IEEE 802.15.4 networks suffer severe throughput fallout as hidden nodes become populated.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.9C
• /
• pp.712-719
• /
• 2008

Temporal error concealment indicates the algorithm that restores the lost video data using temporal correlation between previous frame and current frame with lost data. It can be categorized into the methods of block-based and pixel-based concealment. The proposed method in this paper is for pixel-based temporal error concealment using affine transform. It outperforms especially when the object or background in lost block has geometric transform which can be modeled using affine transform, that is, rotation, magnification, reduction, etc. Furthermore, in order to maintain good performance even though one or more motion vector represents the motion of different objects, we defines a cost function. According to cost from the cost function, the proposed method adopts affine error concealment adaptively. Simulation results show that the proposed method yields better performance up to 1.9 dB than the method embedded in reference software of H.264/AVC.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.8A
• /
• pp.786-795
• /
• 2002

In this paper, we present a histogram and moment-based vidoe scencd change detection technique using hierarchical Hidden Markov Models(HMMs). The proposed method extracts histograms from a low-frequency subband and moments of edge components from high-frequency subbands of wavelet transformed images. Then each HMM is trained by using histogram difference and directional moment difference, respectively, extracted from manually labeled video. The video segmentation process consists of two steps. A histogram-based HMM is first used to segment the input video sequence into three categories: shot, cut, gradual scene changes. In the second stage, a moment-based HMM is used to further segment the gradual changes into a fade and a dissolve. The experimental results show that the proposed technique is more effective in partitioning video frames than the previous threshold-based methods.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.6
• /
• pp.1-8
• /
• 2021

The performance of hidden camera cameras is improving day by day due to miniaturization and advanced technology integration according to the speed of technological development of smartphones. As this external networking computing environment is advanced and diversified, exposure to hidden cameras in addition to general safety cameras is also increasing. On the other hand, the technology for detecting and preventing hidden cameras is not keeping up with the development and speed of these hidden cameras. Therefore, in this study, the heat of the hidden camera was detected using infrared thermal detection technology based on general image and thermal image synthesis technology, and the reflectance of each wavelength according to the difference in ambient temperature was analyzed to reduce the false positive rate.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.1
• /
• pp.45-50
• /
• 2023

Roblox, the world's No. 1 metaverse platform, has more than 3 billion subscription accounts and more than 150 millionmonthly active users (MAU). Despite such high interest in metaverse, existing studies on analyzing the risk of cyberattacks and security in the metaverse environment is insufficient. Therefore, in this paper, we propose a new steganography-basedcovert communication method in Roblox. In our proposed method, a secret message is hidden into an image by using a function provided in the Roblox Experience environment and then the image is automatically stored in the RobloxExperience participants' devices (PC or Smartphone) so that a malicious software can extract the hidden message fromthe image. By our experiments in the Roblox metaverse environment, we validated our proposed method works and thus want to inform our proposed method can be used in various cyberattacks and crimes such as the spread of secret commands, the establishment of a steganography botnet, and the mass distribution of malicious malware in metaverse platforms.

• Journal of KIISE:Computer Systems and Theory
• /
• v.29 no.5
• /
• pp.299-306
• /
• 2002

Partially blind signature scheme is used in applications such as electronic cash and electronic voting where the privacy of the signature requester is important. This paper proposes an RSA-based enhanced partially blind signature scheme minimizing the amount of computation of the signature requester. The signature requester needs computation in blinding the message to the signer and in generating the final signature using the intermediate signature generated by the signer. Since the proposed scheme enables the signature requester to get the final signature just by using modular additions and multiplications, it decreases computation of the signature requester considerably. So, the proposed partially blind signature scheme is adequate for devices such as mobile device, smart-card, and electronic purse that have relatively low computing power.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.16 no.2
• /
• pp.113-119
• /
• 2006

Image steganography is a secret communication method used to transmit secret messages that have been embedded into an image. To accommodate a secret message in a digital image, the original cover image is modified by the embedding algorithm. As a result, a stego image is obtained. The sender hides the secret message in a cover image that has no meaning, and then transmits the stego image to the receiver. In this paper, we propose a steganographic method based on spatial domain to embed a secret message using a difference value of two consecutive pixels and a secret quantization range. Especially, we use the modular operation for increasing of insertion information. Through experiments, we have shown that the proposed method has much mon payload capacity, average 60 percent, than some existing methods by using modular operation.