• Journal of the Korea Society of Computer and Information
• /
• v.29 no.9
• /
• pp.79-87
• /
• 2024

This study aims to improve communication for people with hearing impairments by developing artificial intelligence models that recognize and classify emotions from voice data. To achieve this, we utilized three major AI models: CNN-Transformer, HuBERT-Transformer, and Wav2Vec 2.0, to analyze users' voices in real-time and classify their emotions. To effectively extract features from voice data, we applied transformation techniques such as Mel-Frequency Cepstral Coefficient (MFCC), aiming to accurately capture the complex characteristics and subtle changes in emotions within the voice. Experimental results showed that the HuBERT-Transformer model demonstrated the highest accuracy, proving the effectiveness of combining pre-trained models and complex learning structures in the field of voice-based emotion recognition. This research presents the potential for advancements in emotion recognition technology using voice data and seeks new ways to improve communication and interaction for individuals with hearing impairments, marking its significance.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.97-117
• /
• 2020

Product evaluation criteria is an indicator describing attributes or values of products, which enable users or manufacturers measure and understand the products. When companies analyze their products or compare them with competitors, appropriate criteria must be selected for objective evaluation. The criteria should show the features of products that consumers considered when they purchased, used and evaluated the products. However, current evaluation criteria do not reflect different consumers' opinion from product to product. Previous studies tried to used online reviews from e-commerce sites that reflect consumer opinions to extract the features and topics of products and use them as evaluation criteria. However, there is still a limit that they produce irrelevant criteria to products due to extracted or improper words are not refined. To overcome this limitation, this research suggests LDA-k-NN model which extracts possible criteria words from online reviews by using LDA and refines them with k-nearest neighbor. Proposed approach starts with preparation phase, which is constructed with 6 steps. At first, it collects review data from e-commerce websites. Most e-commerce websites classify their selling items by high-level, middle-level, and low-level categories. Review data for preparation phase are gathered from each middle-level category and collapsed later, which is to present single high-level category. Next, nouns, adjectives, adverbs, and verbs are extracted from reviews by getting part of speech information using morpheme analysis module. After preprocessing, words per each topic from review are shown with LDA and only nouns in topic words are chosen as potential words for criteria. Then, words are tagged based on possibility of criteria for each middle-level category. Next, every tagged word is vectorized by pre-trained word embedding model. Finally, k-nearest neighbor case-based approach is used to classify each word with tags. After setting up preparation phase, criteria extraction phase is conducted with low-level categories. This phase starts with crawling reviews in the corresponding low-level category. Same preprocessing as preparation phase is conducted using morpheme analysis module and LDA. Possible criteria words are extracted by getting nouns from the data and vectorized by pre-trained word embedding model. Finally, evaluation criteria are extracted by refining possible criteria words using k-nearest neighbor approach and reference proportion of each word in the words set. To evaluate the performance of the proposed model, an experiment was conducted with review on '11st', one of the biggest e-commerce companies in Korea. Review data were from 'Electronics/Digital' section, one of high-level categories in 11st. For performance evaluation of suggested model, three other models were used for comparing with the suggested model; actual criteria of 11st, a model that extracts nouns by morpheme analysis module and refines them according to word frequency, and a model that extracts nouns from LDA topics and refines them by word frequency. The performance evaluation was set to predict evaluation criteria of 10 low-level categories with the suggested model and 3 models above. Criteria words extracted from each model were combined into a single words set and it was used for survey questionnaires. In the survey, respondents chose every item they consider as appropriate criteria for each category. Each model got its score when chosen words were extracted from that model. The suggested model had higher scores than other models in 8 out of 10 low-level categories. By conducting paired t-tests on scores of each model, we confirmed that the suggested model shows better performance in 26 tests out of 30. In addition, the suggested model was the best model in terms of accuracy. This research proposes evaluation criteria extracting method that combines topic extraction using LDA and refinement with k-nearest neighbor approach. This method overcomes the limits of previous dictionary-based models and frequency-based refinement models. This study can contribute to improve review analysis for deriving business insights in e-commerce market.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.1135-1147
• /
• 2021

In order to geometrically correct high-resolution satellite imagery, the sensor modeling process that restores the geometric relationship between the satellite sensor and the ground surface at the image acquisition time is required. In general, high-resolution satellites provide RPC (Rational Polynomial Coefficient) information, but the vendor-provided RPC includes geometric distortion caused by the position and orientation of the satellite sensor. GCP (Ground Control Point) is generally used to correct the RPC errors. The representative method of acquiring GCP is field survey to obtain accurate ground coordinates. However, it is difficult to find the GCP in the satellite image due to the quality of the image, land cover change, relief displacement, etc. By using image maps acquired from various sensors as reference data, it is possible to automate the collection of GCP through the image matching algorithm. In this study, the RPC of KOMPSAT-3A satellite image was corrected through the extracted matching point using the UAV (Unmanned Aerial Vehichle) imagery. We propose a pre-porocessing method for the extraction of matching points between the UAV imagery and KOMPSAT-3A satellite image. To this end, the characteristics of matching points extracted by independently applying the SURF (Speeded-Up Robust Features) and the phase correlation, which are representative feature-based matching method and area-based matching method, respectively, were compared. The RPC adjustment parameters were calculated using the matching points extracted through each algorithm. In order to verify the performance and usability of the proposed method, it was compared with the GCP-based RPC correction result. The GCP-based method showed an improvement of correction accuracy by 2.14 pixels for the sample and 5.43 pixelsfor the line compared to the vendor-provided RPC. In the proposed method using SURF and phase correlation methods, the accuracy of sample was improved by 0.83 pixels and 1.49 pixels, and that of line wasimproved by 4.81 pixels and 5.19 pixels, respectively, compared to the vendor-provided RPC. Through the experimental results, the proposed method using the UAV imagery presented the possibility as an alternative to the GCP-based method for the RPC correction.

• Journal of KIISE:Software and Applications
• /
• v.28 no.2
• /
• pp.179-191
• /
• 2001

Comparison shopping is a merchant brokering process that finds the best price for the desired product from several Web-based online stores. To get a scalable comparison shopper, we need an agent that automatically constructs a simple information extraction procedure, called a wrapper, for each semi-structured store. Automatic construction of wrappers for HTML-based Web stores is difficult because HTML only defines how information is to be displayed, not what it means, and different stores employ different ways of manipulating customer queries and different presentation formats for displaying product descriptions. Wrapper induction has been suggested as a promising strategy for overcoming this heterogeneity. However, previous scalable comparison-shoppers such as ShopBot rely on a strong bias in the product descriptions, and as a result, many stores that do not confirm to this bias were unable to be recognized. This paper proposes a more scalable comparison-shopping agent named MORPHEUS. MORPHEUS presents a simple but robust inductive learning algorithm that antomatically constructs wrappers. The main idea of the proposed algorithm is to recognize the position and the structure of a product description unit by finding the most frequent pattern from the sequence of logical line information in output HTML pages. MORPHEUS successfully constructs correct wtappers for most stores by weakening a bias assumed in previous systems. It also tolerates some noises that might be present in production descriptions such as missing attributes. MORPHEUS generates the wrappers rapidly by excluding the pre-processing phase of removing redundant fragments in a page such as a header, a tailer, and advertisements. Eventually, MORPHEUS provides a framework from which a customized comparison-shopping agent can be organized for a user by facilitating the dynamic addition of new stores.

• The korean journal of orthodontics
• /
• v.36 no.5
• /
• pp.369-379
• /
• 2006

Objective: The purpose of this study was to find changes in the occlusal plane related to different vertical facial patterns and suggest treatment goals and conduct possible treatment mechanisms. Methods: 60 adult patients (28 males, 32 females) who had been diagnosed as Class 1 skeletal malocclusion and treated without extraction were selected. Patients were divided into three groups; short face type (group 1), average face type (group 2) and long face type (group 3), using the data on normal occlusion of Korean adults. Results: The results were achieved by analyzing cephalometric tracings of each group at pre-treatment, end-treatment and post-treatment (about 1 year recall check). The inclination of the occlusion plane tends to gradually increase as the face becomes longer In group 1, COP-X, FOP-X, L6/L1, MP-L6 were significantly decreased, and L1-FOP was significantly increased during the retention period (T3-T2). Group 2 showed no significant change, In group 3, FOP-X was significantly increased during the retention period (T3-T2). During the retention period, FOP-X showed significant change among each group, especially between group 1 and group 3. Conclusion: These results suggest that changes of occlusal plane inclination according to facial vertical pattern need to be considered during the retention period for intrusion, extrusion, and incisor overbite.

• Journal of Broadcast Engineering
• /
• v.22 no.6
• /
• pp.713-723
• /
• 2017

Since the panoramic image can overcome the limitation of the viewing angle of the camera and have a wide field of view, it has been studied effectively in the fields of computer vision and stereo camera. In order to generate a panoramic image, stitching images taken by a plurality of general cameras instead of using a wide-angle camera, which is distorted, is widely used because it can reduce image distortion. The image stitching technique creates descriptors of feature points extracted from multiple images, compares the similarities of feature points, and links them together into one image. Each feature point has several hundreds of dimensions of information, and data processing time increases as more images are stitched. In particular, when a panorama is generated on the basis of an image photographed by a plurality of unspecified cameras with respect to an object, the extraction processing time of the overlapping feature points for similar images becomes longer. In this paper, we propose a preprocessing process to efficiently process stitching based on an image obtained from a number of unspecified cameras for one object or environment. In this way, the data processing time can be reduced by pre-grouping images based on camera sensor information and reducing the number of images to be stitched at one time. Later, stitching is done hierarchically to create one large panorama. Through the grouping preprocessing proposed in this paper, we confirmed that the stitching time for a large number of images is greatly reduced by experimental results.

• Proceedings of the Korean Society of Near Infrared Spectroscopy Conference
• /
• 2001.06a
• /
• pp.1520-1520
• /
• 2001

Food adulteration is a serious consumer fraud and a potentially dangerous practice. Regulatory authorities and food processors require a rapid, non-destructive test to accurately confirm authenticity in a range of food products and raw materials. Olive oil is prime target for adulteration either on the basis of the processing treatments used for its extraction (extra virgin vs virgin vs ordinary oil) or its geographical origin (e.g. Greek vs Italian vs Spanish). As part of an investigation into this problem, some preliminary work focused on the ability of near infrared spectroscopy to discriminate between virgin olive oils from separate regions of the Mediterranean i. e. Crete and the Peloponese. A total of 46 oils were collected: 18 originated in Crete and 28 in the Peloponese. Oils were stored in a temperature-controlled room at 2$0^{\circ}C$ prior to spectral collection at room temperature (15-18$^{\circ}C$). Samples (approximately 0.5$m\ell$) were placed in the centre of the quartz window in a camlock reflectance cell; the gold-plated baking plate was then gently placed into the cell against the glass so as to minimize the formation of air bubbles. The rear of the camlock cell was then screwed into place producing a sample thickness of 0.5mm. Spectra were recorded between 400 and 2498nm at 2nm intervals on a NIR Systems 6500 scanning monochromator. Spectral collection took place over 2-3 days. Data were analysed using both WINISI and The Unscrambler software to investigate the possibility of discriminating between the oils from Crete and the Peloponese. A number of data pre-treatments were used and discriminant models were developed using discriminant PLS (WINISI & Unscrambler) and SIMCA (Unscrambler). Despite the small number of samples involved, a satisfactory discrimination between these two oil types was achieved. Graphical examination of principal component scores for each oil type also holds out the possibility of separating oils from either Crete and the Peloponese on the basis of districts within each region. These preliminary data suggest the potential of near infrared spectroscopy to act as a screening technique for the confirmation of geographic origin of extra virgin olive oils. The sample presentation strategy adopted uses only small volumes of material and produces high quality spectra.

• The korean journal of orthodontics
• /
• v.32 no.3 s.92
• /
• pp.165-174
• /
• 2002

The purpose of this study was to compare on masse retraction of six anterior teeth with separate canine retraction in the amount of the anchorage loss and the retraction of the anterior teeth. The subjects consisted of 30 adult female patients with Angle Class 1 malocclusions who were treated by .022' straight wire appliance with 4 first permolar extraction. They were composed of two groups. Group 1 consisted of 15 subjects, whose six anterior teeth were retracted by on masse retraction. Group 2 consisted of 15 subjects, whose canines were retracted separately. Pre-treatment and post-treatment lateral cephalometric radiographs were analyzed. All data were processed statistically with independent samples t-test, and the conclusions were as follows. 1. There was no significant difference in the amount of the anchorage loss between two groups(p>0.05). 2. There was no significant difference in the amount of the retraction of the anterior teeth between two groups(p>0.05). 3. There was a significant difference in the amount of the inclinational change of the upper incisors between two groups. It was greater in Group 2. 4. There was a significant difference in the vertical positional change of the upper incisal edges between two groups. The upper incisal edges in Group 2 were more extruded than Group 1 by about 1mm. 5. There was no significant difference in the vertical positional change of the root apex of the upper incisors between two groups(p>0.05). And there was no significant difference in the vertical positional change of the upper molar(p>0.05).

• Journal of the Korean Association of Geographic Information Studies
• /
• v.11 no.3
• /
• pp.13-22
• /
• 2008

The objective of this study is to evaluate the applicability of extracted PRMS input parameters by KGIS-Hydrology over Yongdam-Dam watershed. KGIS-Hydrology is a system for automatic extraction and analysis of watershed characteristic data. Input parameters of PRMS were generated from GIS data (DEM, soil, forest type, etc.) using KGIS-Hydrology. Multi-temporal meteorological data from Jangsu station of KMA (Korea Meteorological Administration) were used for all simulation periods. Input parameters of PRMS were optimized using observed runoff data of Yongdam-Dam station (1966-2001) and validated using observed runoff data of Yongdam-Dam station (2002-2006, Yongdam-Dam watershed). The results showed that the simulated flows were much closed to the observed flows of Yongdam-Dam (2002-2006) and Donghyang (2001-2004) station by 0.49~0.83 and 0.57~0.75 model efficiencies, respectively.

• Culinary science and hospitality research
• /
• v.15 no.3
• /
• pp.271-283
• /
• 2009

The purpose of this study is to make analyses on the importance and performance of the foodservice management, foodservice service, and the courses related to coffee in the colleges providing a coffee related curriculum, in order to determine which courses are required in the education programs for employees needed by the coffee restaurants as the employers' viewpoint. The analysis methods were frequency analysis, T-test and IPA analysis. The result are as followings. First, the performance was lower than the importance when it comes to importance and performance with the coffee related courses recognized by the staff in the coffee restaurants, particularly with a big gap in the theory of cost control and coffee theory. Second, in the IPA analysis of the importance and performance of the curriculum, quadrant - I as a weak item includes the cost control, foodservice marketing, and coffee theory courses. Quadrant - II includes the foodservice, coffee extraction practice, Espresso, Caffe Latte and Cappuccio, and Latte Art courses. Pertaining to the quadrant - III are those courses lack of the necessity, including the foodservice management, foodservice franchise, practical English in service, and coffee roasting. Quadrant - IV contains those course of less importance but of higher performance such as the practicum work experience. As part of limitations of study, specialties of staffs working for coffee franchise shops were not reflected due to lacking in pre-conducted studies and the samples couldn't be recognized to represent all coffee franchise shops since the sampling districts were restricted only to Seoul metropolitan area.