• Journal of Information Processing Systems
• /
• v.9 no.1
• /
• pp.117-140
• /
• 2013

Hindi is the most widely spoken language in India, with more than 300 million speakers. As there is no separation between the characters of texts written in Hindi as there is in English, the Optical Character Recognition (OCR) systems developed for the Hindi language carry a very poor recognition rate. In this paper we propose an OCR for printed Hindi text in Devanagari script, using Artificial Neural Network (ANN), which improves its efficiency. One of the major reasons for the poor recognition rate is error in character segmentation. The presence of touching characters in the scanned documents further complicates the segmentation process, creating a major problem when designing an effective character segmentation technique. Preprocessing, character segmentation, feature extraction, and finally, classification and recognition are the major steps which are followed by a general OCR. The preprocessing tasks considered in the paper are conversion of gray scaled images to binary images, image rectification, and segmentation of the document's textual contents into paragraphs, lines, words, and then at the level of basic symbols. The basic symbols, obtained as the fundamental unit from the segmentation process, are recognized by the neural classifier. In this work, three feature extraction techniques-: histogram of projection based on mean distance, histogram of projection based on pixel value, and vertical zero crossing, have been used to improve the rate of recognition. These feature extraction techniques are powerful enough to extract features of even distorted characters/symbols. For development of the neural classifier, a back-propagation neural network with two hidden layers is used. The classifier is trained and tested for printed Hindi texts. A performance of approximately 90% correct recognition rate is achieved.

• Journal of the Korean Geographical Society
• /
• v.50 no.2
• /
• pp.203-216
• /
• 2015

This paper examined the changes of urban system through the network and the flow pattern reflected in daily movement in Korea. Because daily movement reflects trip pattern, urban system formed by inter-city linkages can be recognized in terms of living sphere. While population movements between cities have the number of linkage systems of city network and the number of traffic regions composed of the origin and destination has increased respectively. Nevertheless, spatial extent of Capital region and Busan region has been expanded. In Gangwon-do in which Seoul-oriented high-speed transportation network has developed, separation of living sphere between Yeongdong area and the Soyanggang cultural region formed around Chuncheon was intensified. Living sphere that includes Daejeon and the surrounding cities has been expanded to the southern Gyeonggi-do. The existing living sphere formed in Jeollanam-do was fragmented into the east and west around Mokpo and Suncheon due to the weakened centrality of Gwangju. Living spheres formed by spatial interaction were consistent with regional administrative boundary. Considering the increased interaction between Seoul and its surrounding cities, the development of global city-region centered on Seoul is expected.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.3
• /
• pp.493-499
• /
• 2015

In Korea mobile phone subscribers exceeded 1 million people in 1995, and ten million people in 1998. Prevalence of the mobile phone increased dramatically over 110% compared to the population. Almost every family members including children uses more than one mobile terminal. Mobile phone is obviously more necessary good than washer, vacuum cleaner and passenger car. Our daily life are conveniently positioned with mobile communication, but communication related costs including the price of the device and service charges become a big burden on the household. But the government does not seem to do the right role at the right time to prevent the market failure to maximize consumer welfare and social welfare through supporting fair competition. This principal-agent problem issues of mobile communication policies will be understood in perspective of public choice against joint use of the mobile communication network, number portability, separation of phone distribution and phone service, network neutrality, mobile phone subsidy since the early 1990s when mobile phone service was introduced in Korea.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.6
• /
• pp.1320-1326
• /
• 2011

National institutions on the importance of information security is being recognized, information security laws are being discussed in Congress 3.4 DDoS incident and Nonghyup hacking, etc. However, National Assembly Secretariat when the results of the Information Security Consulting has been assessed very low 61.2 points, evaluation of hardware and software in secure areas were vulnerable. This paper, the legislative support agencies National Assembly and National Assembly Secretariat on the network and computer systems, and managerial, technical and physical security elements are analyzed for the status. And network should have the legislative support agencies and system for the physical network separation, DDoS attack response, Virus attack response, hacking attacks response, and Cyber Emergency Response Team/Coordination Center for Cyber infringing design and research through the confidentiality, integrity, availability, access control, authentication and security analysis is based on the evaluation criteria. Through this study, the legislative support agencies to strengthen the security of data and security laws enacted to provide the basis for.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.747-749
• /
• 2017

To protect financial services against danger of financial accidents and customer information leakage caused by malware, injection attack and so on, Financial Services Commission announced "Financial Networks Security Enhancement Comprehensive Plan", which suggests the guideline of protecting customer information and providing secure financial services by separating network topology and then makes the financial company use network partitioning system. In consequence of this policy, financial companies respectively chose between the physical partitioning mechanism or the logical partitioning mechanism according to their IT environment. This paper suggests an efficient infrastructure configuration plan for making the logical network partition, by comparison of a construction of traditional general equipment and an integrated HCI(Hyper Converged Infrastructure) through 'Hyper Converged' which is one of virualization techniques for developing currently, and the case study of the integrated HCI method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.4
• /
• pp.991-998
• /
• 2010

In realization of wireless home network system using speech recognition in indoor voice recognition environment, background noise and reverberation are two main causes of digression in voice recognition system. In this study, the home network system resistant to reverberation and background noise using voice section detection method based on spectral entropy in indoor recognition environment is to be realized. Spectral subtraction can reduce the effect of reverberation and remove noise independent from voice signal by eliminating signal distorted by reverberation in spectrum. For effective spectral subtraction, the correct separation of voice section and silent section should be accompanied and for this, improvement of performance needs to be done, applying to voice section detection method based on entropy. In this study, experimental and indoor environment testing is carried out to figure out command recognition rate in indoor recognition environment. The test result shows that command recognition rate improved in static environment and reverberant room condition, using voice section detection method based on spectral entropy.

• Membrane Journal
• /
• v.28 no.3
• /
• pp.214-219
• /
• 2018

In the present study, superflux nickel capillary supports for gas and vapor separation membranes were prepared by a combined process of NIPS and sintering. Nickel capillary precursors were prepared by NIPS process from PSf-Ni-DMAC-PEG400 dope solution and was sintered at various temperatures in $H_2$ atmosphere to reliably produce Ni capillary support. The optimized Ni capillary support has an outer and inner diameters of 722 and $550{\mu}m$, and its thickness was $94{\mu}m$. It has 3-dimensional pore channel network and its porosity and mean pore diameter was 26% and $4{\mu}m$, respectively. Also, its mechanical strength was tested in tensile mode: its fracture load was 2.84 kgf and the fracture elongation was 13%. Finally, its single gas permeance was measured: He, $N_2$, $O_2$, and $CO_2$ permeance was 432,327, 281,119, 264,259, and 193,143 GPU, respectively. The superflux behavior could be explained from viscous flow through the macropores having a diameter of $4{\mu}m$ and narrow thickness. It could be concluded that the superflux behavior of the Ni capillary support was from the 3-D pore channel network and the small thickness.

• Journal of Internet Computing and Services
• /
• v.24 no.2
• /
• pp.11-18
• /
• 2023

Recently, in the field of Speech Emotion Recognition (SER), many studies have been conducted to improve accuracy using voice features and modeling. In addition to modeling studies to improve the accuracy of existing voice emotion recognition, various studies using voice features are being conducted. This paper, voice files are separated by time interval in a time series method, focusing on the fact that voice emotions are related to time flow. After voice file separation, we propose a model for classifying emotions of speech data by extracting speech features Mel, Chroma, zero-crossing rate (ZCR), root mean square (RMS), and mel-frequency cepstrum coefficients (MFCC) and applying them to a recurrent neural network model used for sequential data processing. As proposed method, voice features were extracted from all files using 'librosa' library and applied to neural network models. The experimental method compared and analyzed the performance of models of recurrent neural network (RNN), long short-term memory (LSTM) and gated recurrent unit (GRU) using the Interactive emotional dyadic motion capture Interactive Emotional Dyadic Motion Capture (IEMOCAP) english dataset.

• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.85-90
• /
• 2022

In modern conditions of the development of public relations, there is a continuous development of technologies. This not only reflects the convenience of service users, and new technology but also contributes to the emergence of new disputes to protect the rights of stakeholders. Therefore, it is urgent to study the distinctions between the jurisdiction of commercial, civil and administrative courts in resolving IT disputes. The work aims to study the peculiarities of delimitation of the jurisdiction of commercial, civil, and administrative courts through the prism of IT measurement. The research methodology consists of such methods as a historical, comparative-legal, formal-logical, empirical, method of analogy, method of synthesis, method of analysis, and systematic method. Examining the specifics of delimiting the jurisdiction of commercial, civil, and administrative courts through the IT dimension, it was concluded that there is a problem in determining the jurisdiction of the court. In addition, the judicial practice on this issue is quite variable, which negatively affects the predictability of technology in resolving potential disputes. In this regard, the criterion models for distinguishing between commercial, administrative, and civil proceedings according to the legal classification of the parties, as well as the nature of the claim are identified. This separation will contribute to a more accurate application of legal norms and methods of application of administrative norms and reduce the number of cases of improper proceedings.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.3
• /
• pp.978-983
• /
• 2010

Acoustic target classification in wireless sensor network is important research at environmental surveillance, invasion surveillance, multiple target separation. General sensor node signal processing methods concentrated on received signal energy based target detection and received raw signal compression. The former is not suited to target classification because of almost every target information are lost except target energy. The latter bring down life-time of sensor node owing to high computational complexity and transmission energy. In this paper, we introduce an feature extraction algorithm for acoustic target classification in wireless sensor network which has time and frequency information. The proposed method extracts time information and de-noised target classification information using wavelet decomposition step. This method reduces communication energy by 28% of original signal and computational complexity.