• Journal of Internet Computing and Services
• /
• v.24 no.4
• /
• pp.127-135
• /
• 2023

This research paper explores the application of FinBERT, a variational BERT-based model pre-trained on financial domain, for sentiment analysis in the financial domain while focusing on the process of identifying suitable training data and hyperparameters. Our goal is to offer a comprehensive guide on effectively utilizing the FinBERT model for accurate sentiment analysis by employing various datasets and fine-tuning hyperparameters. We outline the architecture and workflow of the proposed approach for fine-tuning the FinBERT model in this study, emphasizing the performance of various datasets and hyperparameters for sentiment analysis tasks. Additionally, we verify the reliability of GPT-3 as a suitable annotator by using it for sentiment labeling tasks. Our results show that the fine-tuned FinBERT model excels across a range of datasets and that the optimal combination is a learning rate of 5e-5 and a batch size of 64, which perform consistently well across all datasets. Furthermore, based on the significant performance improvement of the FinBERT model with our Twitter data in general domain compared to our news data in general domain, we also express uncertainty about the model being further pre-trained only on financial news data. We simplify the complex process of determining the optimal approach to the FinBERT model and provide guidelines for selecting additional training datasets and hyperparameters within the fine-tuning process of financial sentiment analysis models.

• Journal of the Korean Wood Science and Technology
• /
• v.46 no.2
• /
• pp.202-210
• /
• 2018

This study was carried out to quantify degree of contribution of harvested wood product (HWP) on mitigation of climate change by valuation of public benefits, environmentally and economically. The potential carbon dioxide emission reduction of HWP was estimated by accounting carbon storage effect and substitution effect. Based on 2014 statistics of Korea Forest Service, domestic HWPs were sorted by two categories, such as wood products produced domestically from domestic and imported roundwood. The wood products were divided into seven items; sawnwood, plywood, particle board, fiberboard (MDF), paper (including pulp), biomass (wood pellet) and other products. The carbon stock of wood products and substitution effects during manufacturing process was evaluated by items. Based on the relevant carbon emission factor and life cycle analysis, the amount of carbon dioxide emission per unit volume on HWP was quantified. The amounts of carbon stock of HWP produced from domestic and from imported roundwood were 3.8 million $tCO_{2eq}$., and 2.6 million $tCO_{2eq}$., respectively. Also, each reduction of carbon emission by substitution effect of HWP produced from domestic and imported roundwood was 3.1 million $tCO_{2eq}$. and 2.1 million $tCO_{2eq}$., respectively. The results of this study, the amount of carbon emission reduction of HWP, can be effectively used as a basic data for promotion of wood utilization to revise and establish new wood utilization promotion policy such as 'forest carbon offset scheme', and 'carbon storage labeling system of HWP'.

• Korean Journal of Veterinary Research
• /
• v.43 no.3
• /
• pp.317-322
• /
• 2003

TrkA is an essential component of the high affinity NGF receptor necessary to the mediate biological effects of the neurotrophins NGF. Here we report on the expression of TrkA in the olfactory bulb and basal nucleus of Mongolian gerbil brain during the postnatal development. The expressions of TrkA were identified in a immunohistochemical method. Higher levels of TrkA immunoreactivity were detected in septum than that in olfactory bulb and caudate putamen (CPu). But TrkA was not observed before postnatal days (PND6) in olfactory bulb and PND9 in CPu. No TrkA-positive cell was detectable in the olfactory fiber layer. Several regions, such as olfactory bulb and CPu, showed weak labeling. These data show that expression of TrkA is developmentally regulated during postnatal Mongolian gerbil brain development and suggest that high affinity neurotrophinreceptors mediate a transient response to neurotrophins in many regions during the brain ontogeny.

• Journal of Korean Neurosurgical Society
• /
• v.50 no.6
• /
• pp.481-485
• /
• 2011

Objective : The purpose of this study is to investigate serial changes of hypoxia-inducible factor $1{\alpha}$ (HIF-$1{\alpha}$), as a key regulator of hypoxic ischemia, and apoptosis of hippocampus induced by bilateral carotid arteries occlusion (BCAO) in rats. Methods : Adult male Wistar rats were subjected to the permanent BCAO. The time points studied were 1, 2, 4, 8, and 12 weeks after occlusions, with n=6 animals subjected to BCAO, and n=2 to sham operation at each time point, and brains were fixed by intracardiac perfusion fixation with 4% neutral-buffered praraformaldehyde for brain section preparation. Immunohistochemistry (IHC), western blot and terminal uridine deoxynucleotidyl transferase dUTP nick end labeling (TUNEL) assay were performed to evaluate HIF-$1{\alpha}$ expression and apoptosis. Results : In IHC and western blot, HIF-$1{\alpha}$ levels were found to reach the peak at the 2nd week in the hippocampus, while apoptotic neurons, in TUNEL assay, were maximal at the 4th week in the hippocampus, especially in the cornu ammonis 1 (CA1) region. HIF-$1{\alpha}$ levels and apoptosis were found to fluctuate during the time course. Conclusion : This study showed that BCAO induces acute ischemic responses for about 4 weeks then chronic ischemia in the hippocampus. These in vivo data are the first to show the temporal sequence of apoptosis and HIF-$1{\alpha}$ expression.

• The KIPS Transactions:PartD
• /
• v.13D no.1 s.104
• /
• pp.125-132
• /
• 2006

The existing recognition system of license plates cannot get the satisfactory result in noise environments. The purpose of this paper is to propose an algorithm that can recognize the region of license plates accurately in a noise environment. The algorithm is formulated by reorganizing the U- and V-channels of YUV color space as YUV is insensitive to light and carries less data than RGB color information. The region of license plates has been extracted by the geometric characteristics, sizes, and places of labeling images. The proposed algorithm was found to improve the process of extracting the region of license plates in various noise environments.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.11
• /
• pp.789-794
• /
• 2013

A vehicle tracking system makes it possible to induce the vehicle movement path for avoiding traffic congestion and to prevent traffic accidents in advance by recognizing traffic flow, monitoring vehicles, and detecting road accidents. To track the vehicles effectively, those which appear in a sequence of video frames need to identified by extracting the features of each object in the frames. Next, the identical vehicles over the continuous frames need to be recognized through the matching among the objects' feature values. In this paper, we identify objects by binarizing the difference image between a target and a referential image, and the labelling technique. As feature values, we use the center coordinate of the minimum bounding rectangle(MBR) of the identified object and the averages of 1D FFT(fast Fourier transform) coefficients with respect to the horizontal and vertical direction of the MBR. A vehicle is tracked in such a way that the pair of objects that have the highest similarity among objects in two continuous images are regarded as an identical object. The experimental result shows that the proposed method outperforms the existing methods that use geometrical features in tracking accuracy.

• Journal of the Korean Society of Food Culture
• /
• v.15 no.4
• /
• pp.269-277
• /
• 2000

A survey was conducted to examine the knowledge and acceptance of food irradiation in order to provide baseline data required in the development of food irradiation education programs for college students. 150 students majoring in food and nutrition or food technology in the Chungnam National University were chosen for a survey. The results are as follows. First, college students' knowledge about food irradiation is scanty. Knowledge assessment showed that 56% of the participants had previously heard of food irradiation. 68% of the respondents thought that radioactivity remains in food after irradiation and 25.3% of them were not sure whether radioactivity remains in food after irradiation or not. Only half of the respondents thought that nutrient loss due to irradiation is equal to or lower than that due to cooking or freezing. Second, approximately 56% of the respondents showed that food irradiation is somewhat or strongly needed for meat or fish; whereas, over 60% of them showed that food irradiation is not needed for grain, vegetable and fruit. Almost 40% of the respondents were seriously concerned about irradiation of vegetables and fruits; whereas, they showed less concern about spice irradiation. More than half of the respondents were not willing to use irradiated food in all the six food groups. Third, the correlation analysis showed that the need of food irradiation is negatively correlated with concerning about the irradiated fish and fruits, but positively correlated with willingness to use irradiated food in all the five food groups, except in spices. Concern about the irradiated food is negatively correlated with willingness to use irradiated food from all the six food groups. Fourth, almost all the respondents (over 90%) agreed that the irradiated food labeling is required as well as the development of proper methods to identify irradiated foods.

• KIISE Transactions on Computing Practices
• /
• v.23 no.5
• /
• pp.316-321
• /
• 2017

We analyze the online Hangul handwriting recognition problem (HHR) and present solutions based on recurrent neural networks. The solutions are organized according to the three kinds of sequence labeling problem - sequence classifications, segment classification, and temporal classification, with additional consideration of the structural constitution of Hangul characters. We present a stacked gated recurrent unit (GRU) based model as the natural HHR solution in the sequence classification level. The proposed model shows 86.2% accuracy for recognizing 2350 Hangul characters and 98.2% accuracy for recognizing the six types of Hangul characters. We show that the type recognizing model successfully follows the type change as strokes are sequentially written. These results show the potential for RNN models to learn high-level structural information from sequential data.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.3
• /
• pp.64-72
• /
• 1997

In this paper, study and experiments are performed for finding recognition unit fit which can be used in large vocabulary recognition system. Specifically, a phoneme that is currently used as recognition unit and a syllable in which Korean is well characterized are selected. From comparisons of recognition experiments, the study is performed whether a syllable can be considered as recognition unit of Korean recognition system. For report of an objective result of the comparison experiment, we collected speech data of a male speaker and processed them by hand-segmentation for phoneme boundary and labeling to construct speech database. And for training and recognition based on HMM, we used HTK (HMM Tool Kit) 2.0 of commercial tool from Entropic Co. to experiment in same condition. We applied two HMM model topologies, 3 emitting state of 5 state and 6 emitting state of 8 state, in Continuous HMM on training of each recognition unit. We also used 3 sets of PBW (Phonetically Balanced Words) and 1 set of POW(Phonetically Optimized Words) for training and another 1 set of PBW for recognition, that is "Speaker Dependent Medium Vocabulary Size Recognition." Experiments result reports that recognition rate is 95.65% in phoneme unit, 94.41% in syllable unit and decoding time of recognition in syllable unit is faster by 25% than in phoneme.

• Environmental Analysis Health and Toxicology
• /
• v.25 no.2
• /
• pp.131-143
• /
• 2010

We performed the tests of acute and subchronic inhalation toxicity of methyl formate, which has limited toxicological data in spite of its widespread use and enhanced hazard consequent on its high volatility. The median lethal concentration ($LC_{50}$) was evaluated to be above 5,000ppm(12.27 mg/L). In the test with subchronic inhalation, there are no deaths, but with reduction of body weight, food intake, organ weight by exposure to 400 (0.98 mg/L) and 1,600 (3.92 mg/L) ppm, dose-dependently. There were statistical differences in some hematological and blood biochemical parameters as compared to control (e.g. neutrophile and lymphocyte in the 1,600 ppm group, calcium and A/G in 1,600 ppm group). Methyl formate under the exposure of 1,600 ppm showed the respiratory findings with nasal, it was confirmed that the chemical has respiratory hazard with 1,600 ppm inhalation exposure, induces nasal epithelial atrophy, olfactory cell degeneration/regeneration and the contraction of olfactory cells, etc. According to the notification with Ministry of Labor (No. 2009-68) for classification, labeling and MSDS of chemicals, it is suggested for methyl formate to be classified as category 4 in acute (10.0$4\leq20.0$ mg/L), category 2 (0.2$\leq$1.0 mg/L/6h, 90 days) in specific target organ-repeated exposure.