• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.365-370
• /
• 2023

This paper aims to compare the performance of speech data classification into two groups, adult and elderly, based on the acoustic and linguistic characteristics that change due to aging, such as changes in respiratory patterns, phonation, pitch, frequency, and language expression ability. For acoustic features we used attributes related to the frequency, amplitude, and spectrum of speech voices. As for linguistic features, we extracted hidden state vector representations containing contextual information from the transcription of speech utterances using KoBERT, a Korean pre-trained language model that has shown excellent performance in natural language processing tasks. The classification performance of each model trained based on acoustic and linguistic features was evaluated, and the F1 scores of each model for the two classes, adult and elderly, were examined after address the class imbalance problem by down-sampling. The experimental results showed that using linguistic features provided better performance for classifying adult and elderly than using acoustic features, and even when the class proportions were equal, the classification performance for adult was higher than that for elderly.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.4
• /
• pp.9-21
• /
• 2024

Deep learning has been developing rapidly in recent years, with many researchers working to utilize large language models in various domains. However, there are practical difficulties that developing and utilizing language models require massive data and high-performance computing resources. Therefore, in-context learning, which utilizes prompts to learn efficiently, has been introduced, but there needs to be clear criteria for effective prompts for learning. In this study, we propose a methodology for enhancing prompt-based learning performance by improving the PET technique, which is one of the contextual learning methods, to select PVPs that are similar to the context of existing data. To evaluate the performance of the proposed methodology, we conducted experiments with 30,100 restaurant review datasets collected from Yelp, an online business review platform. We found that the proposed methodology outperforms traditional PET in all aspects of accuracy, stability, and learning efficiency.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.9
• /
• pp.453-459
• /
• 2024

Recent advances in generative AI technologies using natural language processing have critically impacted text, image, and video production. Despite these innovations, we still need to improve the consistency and reusability of AI-generated outputs. These issues are critical in cartoon creation, where the inability to consistently replicate characters and specific objects can degrade the work's quality. We propose an integrated adaption of language analysis-based requirement engineering and cartoon engineering to solve this. The proposed method applies the linguistic frameworks of Chomsky and Fillmore to analyze natural language and utilizes UML sequence models for generating consistent 3D representations of object interactions. It systematically interprets the creator's intentions from textual inputs, ensuring that each character or object, once conceptualized, is accurately replicated across various panels and episodes to preserve visual and contextual integrity. This technique enhances the accuracy and consistency of character portrayals in animated contexts, aligning closely with the initial specifications. Consequently, this method holds potential applicability in other domains requiring the translation of complex textual descriptions into visual representations.

• Journal of Intelligence and Information Systems
• /
• v.18 no.1
• /
• pp.1-21
• /
• 2012

In recent years, mobile phone has experienced an extremely fast evolution. It is equipped with high-quality color displays, high resolution cameras, and real-time accelerated 3D graphics. In addition, some other features are includes GPS sensor and Digital Compass, etc. This evolution advent significantly helps the application developers to use the power of smart-phones, to create a rich environment that offers a wide range of services and exciting possibilities. To date mobile AR in outdoor research there are many popular location-based AR services, such Layar and Wikitude. These systems have big limitation the AR contents hardly overlaid on the real target. Another research is context-based AR services using image recognition and tracking. The AR contents are precisely overlaid on the real target. But the real-time performance is restricted by the retrieval time and hardly implement in large scale area. In our work, we exploit to combine advantages of location-based AR with context-based AR. The system can easily find out surrounding landmarks first and then do the recognition and tracking with them. The proposed system mainly consists of two major parts-landmark browsing module and annotation module. In landmark browsing module, user can view an augmented virtual information (information media), such as text, picture and video on their smart-phone viewfinder, when they pointing out their smart-phone to a certain building or landmark. For this, landmark recognition technique is applied in this work. SURF point-based features are used in the matching process due to their robustness. To ensure the image retrieval and matching processes is fast enough for real time tracking, we exploit the contextual device (GPS and digital compass) information. This is necessary to select the nearest and pointed orientation landmarks from the database. The queried image is only matched with this selected data. Therefore, the speed for matching will be significantly increased. Secondly is the annotation module. Instead of viewing only the augmented information media, user can create virtual annotation based on linked data. Having to know a full knowledge about the landmark, are not necessary required. They can simply look for the appropriate topic by searching it with a keyword in linked data. With this, it helps the system to find out target URI in order to generate correct AR contents. On the other hand, in order to recognize target landmarks, images of selected building or landmark are captured from different angle and distance. This procedure looks like a similar processing of building a connection between the real building and the virtual information existed in the Linked Open Data. In our experiments, search range in the database is reduced by clustering images into groups according to their coordinates. A Grid-base clustering method and user location information are used to restrict the retrieval range. Comparing the existed research using cluster and GPS information the retrieval time is around 70~80ms. Experiment results show our approach the retrieval time reduces to around 18~20ms in average. Therefore the totally processing time is reduced from 490~540ms to 438~480ms. The performance improvement will be more obvious when the database growing. It demonstrates the proposed system is efficient and robust in many cases.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.12
• /
• pp.3874-3884
• /
• 2000

An information retrieval system has to retrieve all and only documents which are relevant to a user query, even if index terms and query terms are not matched exactly. However, term mismatches between index terms and qucry terms have been a serious obstacle to the enhancement of retrieval performance. In this paper, we discuss automatic term normalization between words in text corpora and their application to a Korean information retrieval system. We perform two types of term normalizations to alleviate semantic term mismatches: equivalence class and co-occurrence cluster. First, transliterations, spelling errors, and synonyms are normalized into equivalence classes bv using contextual similarity. Second, context-based terms are normalized by using a combination of mutual information and word context to establish word similarities. Next, unsupervised clustering is done by using K-means algorithm and co-occurrence clusters are identified. In this paper, these normalized term products are used in the query expansion to alleviate semantic tem1 mismatches. In other words, we utilize two kinds of tcrm normalizations, equivalence class and co-occurrence cluster, to expand user's queries with new tcrms, in an attempt to make user's queries more comprehensive (adding transliterations) or more specific (adding spc'Cializationsl. For query expansion, we employ two complementary methods: term suggestion and term relevance feedback. The experimental results show that our proposed system can alleviatl' semantic term mismatches and can also provide the appropriate similarity measurements. As a result, we know that our system can improve the rctrieval efficiency of the information retrieval system.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.05a
• /
• pp.278-280
• /
• 2012

We are propose the position of the node context-awareness information and the validity of the head node in the path according to the clustering how to elect one of the energy efficiency ECOPS (Energy Conserving Optimal path Schedule) algorithm. Existing LEACH algorithm to elect the head node when the node's energy probability distribution function based on the management of the head node is optional cycle. However, in this case, the distance of the relay node status information including context-awareness parameters does not reflect. These factors are not suitable for the relay node or nodes are included in the probability distribution, if the head node selects occurs. In particular, to solve the problems from the LEACH-based hierarchical clustering algorithms, this study defines location with the status context information and the residual energy factor in choosing topology of the structure adjacent nodes. ECOPS algorithm that contextual information is contributed for head node selection in topology protocols. The proposed ECOPS algorithm has the head node replacement situations from the candidate head node in the optimal path and efficient energy conservation that is the path of the member nodes. The new head node election show as the entire node lifetime and network management technique improving the network lifetime and efficient management the simulation results.

• Korean journal of communication and information
• /
• v.58
• /
• pp.7-30
• /
• 2012

The advent of Social Journalism coincided with the rise of social media to create and deliver news information; as a type of civic journalism, social journalism may be characterized as a new form of information gathering and news reporting which is fed by citizens creating news information through their use social networking services (SNSs). The current study analyzed a Facebook page called, to determine how this page was utilized during the onset of the citizen movement for the Egyptian democratic revolution to produce news, to facilitate interaction among the public and to deliver the news under the form of networked journalism. Each post uploaded onto the Facebook page from January 27 till February 2, 2011 was coded in its category, content and the contextual frame of the news. The results of the study showed that during the first week, straight news rather than those with opinions was produced most frequently. The research findings of the current study suggest that in a society of political turmoil, such as in Egypt and other Arabic countries, when the institutionalized media are controlled severely by the government or other forces, SNSs can perform journalistic media roles which create and distribute news information representing facts and reality, and simultaneously facilitate the public's interactions on social and political issues.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.5
• /
• pp.903-913
• /
• 2015

The Korea Agency of Education, Promotion and Information Service in Food, Agriculture, Forestry and Fisheries launched a public data portal service in January 2015. The service provides customized information for consumers through an agri-food recommendation system built-in portal service. The recommendation system has fallowing characteristics. First, the system can increase recommendation accuracy by using a wide variety of agri-food related data, including SNS opinion mining, consumer's purchase data, climate data, and wholesale price data. Second, the system uses segmentation method based on consumer's lifestyle and megatrends factors to overcome the cold start problem. Third, the system recommends agri-foods to users reflecting various preference contextual factors by using recommendation algorithm, dirichlet-multinomial distribution. In addition, the system provides diverse information related to recommended agri-foods to increase interest in agri-food of service users.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.1
• /
• pp.225-232
• /
• 2013

In this paper, we introduce a method that can be used to select the position of head node for context-awareness information. The validity of the head node optimal location is saving the energy in the path according to the clustering. It is important how to elect one of the relay node for energy efficiency routing. Existing LEACH algorithm to elect the head node when the node's energy probability distribution function based on the management of the head node is optional cycle. However, in this case, the distance of the relay node status information including context-awareness parameters does not reflect. These factors are not suitable for the relay node or nodes are included in the probability distribution during the head node selects occurs. In particular, to solve the problems from the LEACH-based hierarchical clustering algorithms, this study defines location with the status context information and the residual energy factor in choosing topology of the structure adjacent nodes. The proposed ECOPS (Energy Conserving Optimal path Schedule) algorithm that contextual information is contributed for head node selection in topology protocols. This proposed algorithm has the head node replacement situations from the candidate head node in the optimal path and efficient energy conservation that is the path of the member nodes. The new head node election technique show improving the entire node lifetime and network in management the network from simulation results.

• Journal of Technology Innovation
• /
• v.32 no.2
• /
• pp.23-58
• /
• 2024

Despite the important roles of institutions and their collaboration in producing knowledge for innovation, the lack of accurate methods for identifying such knowledge-producing institutions has restricted empirical research on the role of institutions in innovation. This study explores methods to enhance the accuracy of identifying institutions involved in innovation process. To this end, we propose ways to improve accuracy in both aspects of information - data and algorithms - using bibliographic information in the digital health field. Specifically, in the data processing stage before applying algorithms, we address contextual inaccuracies of bibliographic information; in the algorithm application stage, we propose methods to improve the ambiguity of institution names (IND). When compared with the PKG dataset, which is publicly available datasets based on the same bibliographic information, our methods doubled the number of cases available for subsequent analysis. We also discovered that the contribution of Korean institutions in the digital health field is either underestimated or overestimated. The method presented in this study is expected to contribute to empirically researching the role of knowledge-producing institutions in innovation process and ecosystem.