• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.301-307
• /
• 2024

This study introduces a novel cascade fusion architecture aimed at enhancing thermal images across various scale conditions. The processing of thermal images at multiple scales has been challenging due to the limitations of existing methods that are designed for specific scales. To overcome these limitations, this paper proposes a unified framework that utilizes cascade feature fusion to effectively learn multi-scale representations. Confidence maps from different image scales are fused in a cascaded manner, enabling scale-invariant learning. The architecture comprises end-to-end trained convolutional neural networks to enhance image quality by reinforcing mutual scale dependencies. Experimental results indicate that the proposed technique outperforms existing methods in multi-scale thermal image enhancement. Performance evaluation results are provided, demonstrating consistent improvements in image quality metrics. The cascade fusion design facilitates robust generalization across scales and efficient learning of cross-scale representations.

• Journal of Korean Society of Rural Planning
• /
• v.30 no.2
• /
• pp.1-11
• /
• 2024

Farmland transaction prices are affected by various factors such as politics, society, and the economy. The purpose of this study is to identify multiple factors that affect the farmland transaction price due to changes in the actual transaction price of farmland by farmland unit from 2016 to 2020. There are several previous studies analyzed the determinants of farmland transaction prices by considering spatial dependency. However, in the case of land transactions where the time and space of the transaction affect simultaneously, if only spatial dependence is considered, there is a limitation in that it cannot reflect spatial dependence that occurs over time. In order to solve these limitations, To address these limitations, this study builds a spatio-temporal autoregressive model that simultaneously considers spatial and temporal dependencies using farmland transactions in Jinju City as an example. As a result of the analysis, it was confirmed that there was significant spatio-temporal dependence in farmland transactions within the previous 30 days. This means that if the previous farmland transaction was carried out at a high price, it has a spatio-temporal spillover effect that indirectly affects the increase in the price of other nearby farmland transactions. The study also found that various location attributes and socioeconomic attributes have a significant impact on farmland transaction prices. The spatio-temporal autoregressive model of farmland prices constructed in this study can be used to improve the prediction accuracy of farmland prices in the farmland transaction market in the future, and it is expected to be useful in drawing policy implications for stabilizing farmland prices

• The Journal of Small Business Innovation
• /
• v.19 no.4
• /
• pp.1-17
• /
• 2016

The purpose of this study is to suggest an efficient way for ventures to achieve innovation performance through R&D cooperative arrangements. Achieving innovation is one of the critical factors for the survival of ventures. Unlike established firms, ventures often do not have the specialized assets necessary to take technological developments to the product and market stages. Young and resource-constrained firms can achieve innovation by finding and accessing to the complementary resources from R&D cooperation. In the current business environment, many firms are likely to engage in multiple simultaneous R&D cooperations with different partners. Recent research stream addresses the importance of efficient cooperation management from the holistic portfolio perspective. Since maintaining the multiple cooperative relations require substantial amount of time and effort, managing cooperative relationships play a more important role to resource-constrained firms. In order to find an efficient composition of R&D cooperative partners, we mainly focus on the diversity of partner type and dependence level in partnership. We analyze the data on Korean manufacturing ventures collected in the Korean Innovation Survey (KIS) which was conducted by the Science and Technology Policy Institute (STEPI). The KIS questionnaire assesses the existence of cooperative relationships with different types of partners respectively. The types of cooperating partners are affiliated companies, suppliers, clients & customers, competitors or other firms in the same industry, consulting firms, universities, and research institutes. We confirm that ventures obtain relatively higher benefits from R&D cooperation compared with established firms in terms of innovation performance. The results show that a moderate level of diversity in cooperative partner type composition increases innovation. Moreover, diversity of cooperation dependency among the partners enhances innovation performance. Likewise, concentrating on the quality aspects of cooperative composition, such as diversity of partners and degree of dependencies, this study offers some implications for ventures in managing partners from an integrative perspective.

• Journal of Intelligence and Information Systems
• /
• v.21 no.1
• /
• pp.1-13
• /
• 2015

As opinion mining in big data applications has been highlighted, a lot of research on unstructured data has made. Lots of social media on the Internet generate unstructured or semi-structured data every second and they are often made by natural or human languages we use in daily life. Many words in human languages have multiple meanings or senses. In this result, it is very difficult for computers to extract useful information from these datasets. Traditional web search engines are usually based on keyword search, resulting in incorrect search results which are far from users' intentions. Even though a lot of progress in enhancing the performance of search engines has made over the last years in order to provide users with appropriate results, there is still so much to improve it. Word sense disambiguation can play a very important role in dealing with natural language processing and is considered as one of the most difficult problems in this area. Major approaches to word sense disambiguation can be classified as knowledge-base, supervised corpus-based, and unsupervised corpus-based approaches. This paper presents a method which automatically generates a corpus for word sense disambiguation by taking advantage of examples in existing dictionaries and avoids expensive sense tagging processes. It experiments the effectiveness of the method based on Naïve Bayes Model, which is one of supervised learning algorithms, by using Korean standard unabridged dictionary and Sejong Corpus. Korean standard unabridged dictionary has approximately 57,000 sentences. Sejong Corpus has about 790,000 sentences tagged with part-of-speech and senses all together. For the experiment of this study, Korean standard unabridged dictionary and Sejong Corpus were experimented as a combination and separate entities using cross validation. Only nouns, target subjects in word sense disambiguation, were selected. 93,522 word senses among 265,655 nouns and 56,914 sentences from related proverbs and examples were additionally combined in the corpus. Sejong Corpus was easily merged with Korean standard unabridged dictionary because Sejong Corpus was tagged based on sense indices defined by Korean standard unabridged dictionary. Sense vectors were formed after the merged corpus was created. Terms used in creating sense vectors were added in the named entity dictionary of Korean morphological analyzer. By using the extended named entity dictionary, term vectors were extracted from the input sentences and then term vectors for the sentences were created. Given the extracted term vector and the sense vector model made during the pre-processing stage, the sense-tagged terms were determined by the vector space model based word sense disambiguation. In addition, this study shows the effectiveness of merged corpus from examples in Korean standard unabridged dictionary and Sejong Corpus. The experiment shows the better results in precision and recall are found with the merged corpus. This study suggests it can practically enhance the performance of internet search engines and help us to understand more accurate meaning of a sentence in natural language processing pertinent to search engines, opinion mining, and text mining. Naïve Bayes classifier used in this study represents a supervised learning algorithm and uses Bayes theorem. Naïve Bayes classifier has an assumption that all senses are independent. Even though the assumption of Naïve Bayes classifier is not realistic and ignores the correlation between attributes, Naïve Bayes classifier is widely used because of its simplicity and in practice it is known to be very effective in many applications such as text classification and medical diagnosis. However, further research need to be carried out to consider all possible combinations and/or partial combinations of all senses in a sentence. Also, the effectiveness of word sense disambiguation may be improved if rhetorical structures or morphological dependencies between words are analyzed through syntactic analysis.