• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.6
• /
• pp.2612-2633
• /
• 2020

Due to the explosive growth of multimedia speech data, how to protect the privacy of speech data and how to efficiently retrieve speech data have become a hot spot for researchers in recent years. In this paper, we proposed an encrypted speech retrieval scheme based on long short-term memory (LSTM) neural network and deep hashing. This scheme not only achieves efficient retrieval of massive speech in cloud environment, but also effectively avoids the risk of sensitive information leakage. Firstly, a novel speech encryption algorithm based on 4D quadratic autonomous hyperchaotic system is proposed to realize the privacy and security of speech data in the cloud. Secondly, the integrated LSTM network model and deep hashing algorithm are used to extract high-level features of speech data. It is used to solve the high dimensional and temporality problems of speech data, and increase the retrieval efficiency and retrieval accuracy of the proposed scheme. Finally, the normalized Hamming distance algorithm is used to achieve matching. Compared with the existing algorithms, the proposed scheme has good discrimination and robustness and it has high recall, precision and retrieval efficiency under various content preserving operations. Meanwhile, the proposed speech encryption algorithm has high key space and can effectively resist exhaustive attacks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.12
• /
• pp.4934-4949
• /
• 2015

The unstable characteristic values of communication signals along with the varying SNR (Signal Noise Ratio) environment make it difficult to identify the modulations of signals. Most of relevant literature revolves around signal recognition under stable SNR, and not applicable for signal recognition at varying SNR. To solve the problem, this research developed a novel communication signal recognition algorithm based on Holder coefficient and cloud theory. In this algorithm, the two-dimensional (2D) Holder coefficient characteristics of communication signals were firstly calculated, and then according to the distribution characteristics of Holder coefficient under varying SNR environment, the digital characteristics of cloud model such as expectation, entropy, and hyper entropy are calculated to constitute the three-dimensional (3D) digital cloud characteristics of Holder coefficient value, which aims to improve the recognition rate of the communication signals. Compared with traditional algorithms, the developed algorithm can describe the signals' features more accurately under varying SNR environment. The results from the numerical simulation show that the developed 3D feature extraction algorithm based on Holder coefficient cloud features performs better anti-noise ability, and the classifier based on interval gray relation theory can achieve a recognition rate up to 84.0%, even when the SNR varies from -17dB to -12dB.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.11
• /
• pp.1022-1028
• /
• 2013

It is well knowns that based on the CSP (Common Spatial Pattern) algorithm, the linear projection of an EEG (Electroencephalography) signal can be made to spaces that optimize the discriminant between two patterns. Sharing disadvantages from linear time invariant systems, CSP suffers from the non-stationary nature of EEGs causing the performance of the classification in a BCI (Brain-Computer Interface) system to drop significantly when comparing the training data and test data. The author has suggested a simple idea based on the parallel model of CSP filters to improve the performance of BCI systems. The model was tested with a simple CSP algorithm (without any elaborate regularizing methods) and a perceptron learning algorithm as a classifier to determine the improvement of the system. The simulation showed that the parallel model could improve classification performance by over 10% compared to conventional CSP methods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.10
• /
• pp.2409-2416
• /
• 2014

In this paper, an automatic recognition algorithm for linearly modulated signals like PSK, QAM under noncoherent asynchronous condition is proposed. Frequency, phase, and amplitude characteristics of digitally modulated signals are changed periodically. By using this characteristics, cyclic moments and higher order cumulants based features are utilized for the modulation recognition. Hierarchial decision tree method is used for high speed signal processing and totally 4 feature extraction parameters are used for modulation recognition. In the condition where the symbol number is 4,096, the recognition accuracy of the proposed algorithm is more than 95% at SNR 15dB. Also the proposed algorithm is effective to classify the signal which has carrier frequency and phase offset.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.10
• /
• pp.185-198
• /
• 2021

With the development of Internet technology, because traditional recommendation algorithms cannot learn the in-depth characteristics of users or items, this paper proposed a recommendation algorithm based on the AMITI(attention mechanism and improved TF-IDF) to solve this problem. By introducing the two-layer attention mechanism into the CNN, the feature extraction ability of the CNN is improved, and different preference weights are assigned to item features, recommendations that are more in line with user preferences are achieved. When recommending items to target users, the scoring data and item type data are combined with TF-IDF to complete the grouping of the recommendation results. In this paper, the experimental results on the MovieLens-1M data set show that the AMITI algorithm improves the accuracy of recommendation to a certain extent and enhances the orderliness and selectivity of presentation methods.

• Journal of Software Assessment and Valuation
• /
• v.16 no.2
• /
• pp.63-68
• /
• 2020

This paper proposes a face authentication system based on deep learning framework. The proposed system is consisted of face region detection and feature extraction using deep learning algorithm, and performed the face authentication using joint-bayesian matrix learning algorithm. The performance of proposed paper is evaluated by various face database , and the face image of one person consists of 2 images. The face authentication algorithm was performed by measuring similarity by applying 2048 dimension characteristic and combined Bayesian algorithm through Deep Neural network and calculating the same error rate that failed face certification. The result of proposed paper shows that the proposed system using deep learning and joint bayesian algorithms showed the equal error rate of 1.2%, and have a good performance compared to previous approach.

• Journal of information and communication convergence engineering
• /
• v.22 no.2
• /
• pp.145-152
• /
• 2024

Closed quotient (CQ) represents the time ratio for which the vocal folds remain in contact during voice production. Because analyzing CQ values serves as an important reference point in vocal training for professional singers, these values have been measured mechanically or electrically by either inverse filtering of airflows captured by a circumferentially vented mask or post-processing of electroglottography waveforms. In this study, we introduced a novel algorithm to predict the CQ values only from audio signals. This has eliminated the need for mechanical or electrical measurement techniques. Our algorithm is based on a gated recurrent unit (GRU)-type neural network. To enhance the efficiency, we pre-processed an audio signal using the pitch feature extraction algorithm. Then, GRU-type neural networks were employed to extract the features. This was followed by a dense layer for the final prediction. The Results section reports the mean square error between the predicted and real CQ. It shows the capability of the proposed algorithm to predict CQ values.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.26 no.5
• /
• pp.30-42
• /
• 2022

Due to the increase in construction of tunnels, the burdens of maintenance works for tunnel structures have been increasing in Korea. In addition, the increase of traffic volume and aging of materials also threatens the safety of tunnel facilities, therefore, maintenance costs are expected to increase significantly in the future. Accordingly, automated condition assessment technologies like image-based tunnel scanning system for inspection and diagnosis of tunnel facilities have been proposed. For image-based tunnel scanning system, it is key to create a planar image through stitching of multiple images captured by tunnel scanning system. In this study, performance of feature-based stitching algorithms suitable for stitching tunnel scanning images was evaluated. In order to find a suitable algorithm SIFT, ORB, and BRISK are compared. The performance of the proposed algorithm was determined by the number of feature extraction, calculation speed, accuracy of feature matching, and image stitching result. As for stitching performance, SIFT algorithm was the best in all parts of tunnel image. ORB and BRISK also showed satisfactory performance and short calculation time. SIFT can be used to generate precise planar images. ORB and BRISK also showed satisfactory stitching results, confirming the possibility of being used when real-time stitching is required.

• Journal of KIISE:Computer Systems and Theory
• /
• v.32 no.10
• /
• pp.520-529
• /
• 2005

A feature-based 3D modeling algorithm is presented in this paper. Since conventional methods use depth-based techniques, they need much time for the image matching to extract depth information. Even feature-based methods have less computation load than that of depth-based ones, the calculation of modeling error about whole pixels within a triangle is needed in feature-based algorithms. It also increase the computation time. Therefore, the proposed algorithm consists of three phases, which are an initial 3D model generation, model evaluation, and model refinement phases, in order to acquire an efficient 3D model. Intensity gradients and incremental Delaunay triangulation are used in the Initial model generation. In this phase, a morphological edge operator is adopted for a fast edge filtering, and the incremental Delaunay triangulation is modified to decrease the computation time by avoiding the calculation errors of whole pixels and selecting a vertex at the near of the centroid within the previous triangle. After the model generation, sparse vertices are matched, then the faces are evaluated with the size, approximation error, and disparity fluctuation of the face in evaluation stage. Thereafter, the faces which have a large error are selectively refined into smaller faces. Experimental results showed that the proposed algorithm could acquire an adaptive model with less modeling errors for both smooth and abrupt areas and could remarkably reduce the model acquisition time.

• Korean Journal of Remote Sensing
• /
• v.24 no.2
• /
• pp.117-124
• /
• 2008

This paper introduces a novel approach for automated mapping of a map feature that is vinyl green house in high spatial resolution imagery Some map features have their unique spatial patterns. These patterns are normally detected in high spatial resolution remotely sensed data by human recognition system. When spatial patterns can be applied to map feature identification, it will improve image classification accuracy and will be contributed a lot to feature identification. In this study, an automated feature identification approach using spatial aucorrelation is developed, specifically for the vinyl green house that has distinctive spatial pattern in its array. The algorithm aimed to develop the method without any human intervention such as digitizing. The method can investigate the characteristics of repeated spatial pattern of vinyl green house. The repeated spatial pattern comes from the orderly array of vinyl green house. For this, object-based approaches are essential because the pattern is recognized when the shapes that are consists of the groups of pixels are involved. The experimental result shows very effective vinyl house extraction. The targeted three vinyl green houses were exactly identified in the IKONOS image for a part of Jeju area.