• International Journal of Computer Science & Network Security
• /
• v.23 no.3
• /
• pp.161-168
• /
• 2023

It is a common practice to use a password in order to restrict access to information, or in a general sense, to assets. Right selection of the password is necessary for protecting the assets more effectively. Password finding/cracking try outs are performed for deciding which level of protection do used or prospective passwords offer, and password cracking algorithms are generated. These algorithms are becoming more intelligent and succeed in finding more number of passwords in less tries and in a shorter duration. In this study, the performances of possible password finding algorithms are measured, and a hybrid algorithm based on the performances of different password cracking algorithms is generated, and it is demonstrated that the performance of the hybrid algorithm is superior to the base algorithms.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.4
• /
• pp.103-111
• /
• 2004

The method of speaker normalization has been known as the successful method for improving the accuracy of speech recognition at speaker independent speech recognition system. A frequency warping approach is widely used method based on maximum likelihood for speaker normalization. This paper propose a new power spectrum warping approach to making improvement of speaker normalization better than a frequency warping. Th power spectrum warping uses Mel-frequency cepstrum analysis(MFCC) and is a simple mechanism to performing speaker normalization by modifying the power spectrum of Mel filter bank in MFCC. Also, this paper propose the hybrid VTN combined the Power spectrum warping and a frequency warping. Experiment of this paper did a comparative analysis about the recognition performance of the SKKU PBW DB applied each speaker normalization approach on baseline system. The experiment results have shown that a frequency warping is 2.06%, the power spectrum is 3.06%, and hybrid VTN is 4.07% word error rate reduction as of word recognition performance of baseline system.

• Korean Journal of Cognitive Science
• /
• v.7 no.4
• /
• pp.141-162
• /
• 1996

• Journal of Korea Society of Industrial Information Systems
• /
• v.9 no.1
• /
• pp.17-23
• /
• 2004

This paper proposes to determine word senses in Korean language processing by corpus-based ontology learning. Our approach is a hybrid method. First, we apply the previously-secured dictionary information to select the correct senses of some ambiguous words with high precision, and then use the ontology to disambiguate the remaining ambiguous words. The mutual information between concepts in the ontology was calculated before using the ontology as knowledge for disambiguating word senses. If mutual information is regarded as a weight between ontology concepts, the ontology can be treated as a graph with weighted edges, and then we locate the least weighted path from one concept to the other concept. In our practical machine translation system, our word sense disambiguation method achieved a 9％ improvement over methods which do not use ontology for Korean translation.

• Journal of Korean Library and Information Science Society
• /
• v.34 no.3
• /
• pp.211-229
• /
• 2003

In this paper, we have focused that the number of word in the web document affects definite clustering performance. Our experimental results have clearly shown the relationship between the amounts of word and its impact on clustering performance. We also have presented an algorithm that can be supplemented of the contrast portion through co-links frequency of web documents. Testing bench of this research is 1,449 web documents included on 'Natural science' category among the Naver Directory. We have clustered these objects by term-based clustering, link-based clustering, and hybrid clustering method, and compared the output results with originally allocated category of Naver directory.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.7
• /
• pp.674-679
• /
• 2009

This paper proposes a method of player event retrieval using combination of two functions: detection of player name in speech information and detection of sound event from audio information in golf videos. The system consists of indexing module and retrieval module. At the indexing time audio segmentation and noise reduction are applied to audio stream demultiplexed from the golf videos. The noise-reduced speech is then fed into speech recognizer, which outputs spoken descriptors. The player name and sound event are indexed by the spoken descriptors. At search time, text query is converted into phoneme sequences. The lists of each query term are retrieved through a description matcher to identify full and partial phrase hits. For the retrieval of the player name, this paper compares the results of word-based, phoneme-based, and hybrid approach.

• Journal of the Korean Society of Mechanical Technology
• /
• v.13 no.4
• /
• pp.165-168
• /
• 2011

In this paper, the hybrid tube expander unit for fin and tube type heat exchanger are developed by means of enlarging and inserting the smooth tube with a small diameter to a finned tube having larger diameter. In other word, the tube expander tool that is easy to attach and remove from tube is developed. The hybrid tube expander unit developed in this study can move easily and enlarge the tube without fixing at tube sheet. Also, this unit has a function removing scales inside tube by replacing a tube expander ball.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.9
• /
• pp.4408-4428
• /
• 2019

Due to the rapid advancement in smart phones, numerous new specifications are developed for variety of applications ranging from health monitoring to navigations and tracking. The word indoor navigation means location identification, however, where GPS signals are not available, accurate indoor localization is a challenging task due to variation in the received signals which directly affect distance estimation process. This paper proposes a hybrid approach which integrates fingerprinting based K-Nearest Neighbors (K-NN) and lateration based MinMax position estimation technique. The novel idea behind this hybrid approach is to use Euclidian distance formulation for distance estimates instead of indoor radio channel modeling which is used to convert the received signal to distance estimates. Due to unpredictable behavior of the received signal, modeling indoor environment for distance estimates is a challenging task which ultimately results in distance estimation error and hence affects position estimation process. Our proposed idea is indoor position estimation technique using Bluetooth enabled smart phones which is independent of the radio channels. Experimental results conclude that, our proposed hybrid approach performs better in terms of mean error compared to Trilateration, MinMax, K-NN, and existing Hybrid approach.

• The KIPS Transactions:PartB
• /
• v.9B no.4
• /
• pp.445-452
• /
• 2002

In Korean-English mixed documents, translated technical words are usually used with the attached full words or original words enclosed with parenthesis. In this paper, a collective method is presented to recognize and extract the translation phrases with using a base translation dictionary. In order to process the unregistered title words and translation words in the dictionary, a phonetic similarity matching method, a translation partial matching method, and a compound word matching method are newly proposed. The experiment result of each method was measured in F-measure(the alpha is set to 0.4) ; exact matching of dictionary terms as a baseline method showed 23.8%, the hybrid method of translation partial matching and phonetic similarity matching 75.9%, and the compound word matching method including the hybrid method 77.3%, which is 3.25 times better than the baseline method.

• Journal of KIISE
• /
• v.44 no.12
• /
• pp.1290-1295
• /
• 2017

Document classification, a task of classifying the category of each document based on text, is one of the fundamental areas for natural language processing. Document classification may be used in various fields such as topic classification and sentiment classification. Neural network models for document classification can be divided into two categories: word-level models and character-level models that treat words and characters as basic units respectively. In this study, we propose a neural network model that combines character-level and word-level models to improve performance of document classification. The proposed model extracts the feature vector of each word by combining information obtained from a word embedding matrix and information encoded by a character-level neural network. Based on feature vectors of words, the model classifies documents with a hierarchical structure wherein recurrent neural networks with attention mechanisms are used for both the word and the sentence levels. Experiments on real life datasets demonstrate effectiveness of our proposed model.