• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.171-176
• /
• 2023

This study is about a speech recognition error correction system designed to detect and correct speech recognition errors before natural language processing to increase the success rate of intent analysis in natural language processing with optimal efficiency in various service domains. An encoder is constructed to embedded the correct speech token and one or more error speech tokens corresponding to the correct speech token so that they are all located in a dense vector space for each correct token with similar vector values. One or more utterance tokens within a preset Manhattan distance based on the correct utterance token in the dense vector space for each embedded correct utterance token are detected through an error detector, and the correct answer closest to the detected error utterance token is based on the Manhattan distance. Errors are corrected by extracting the utterance token as the correct answer.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1505-1514
• /
• 2022

Image matching is a crucial preprocessing step for effective utilization of multi-temporal and multi-sensor very high resolution (VHR) satellite images. Deep learning (DL) method which is attracting widespread interest has proven to be an efficient approach to measure the similarity between image pairs in quick and accurate manner by extracting complex and detailed features from satellite images. However, Image matching of VHR satellite images remains challenging due to limitations of DL models in which the results are depending on the quantity and quality of training dataset, as well as the difficulty of creating training dataset with VHR satellite images. Therefore, this study examines the feasibility of DL-based method in matching pair extraction which is the most time-consuming process during image registration. This paper also aims to analyze factors that affect the accuracy based on the configuration of training dataset, when developing training dataset from existing multi-sensor VHR image database with bias for DL-based image matching. For this purpose, the generated training dataset were composed of correct matching pairs and incorrect matching pairs by assigning true and false labels to image pairs extracted using a grid-based Scale Invariant Feature Transform (SIFT) algorithm for a total of 12 multi-temporal and multi-sensor VHR images. The Siamese convolutional neural network (SCNN), proposed for matching pair extraction on constructed training dataset, proceeds with model learning and measures similarities by passing two images in parallel to the two identical convolutional neural network structures. The results from this study confirm that data acquired from VHR satellite image database can be used as DL training dataset and indicate the potential to improve efficiency of the matching process by appropriate configuration of multi-sensor images. DL-based image matching techniques using multi-sensor VHR satellite images are expected to replace existing manual-based feature extraction methods based on its stable performance, thus further develop into an integrated DL-based image registration framework.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.6 no.5
• /
• pp.211-221
• /
• 1998

Thermal behavior on the cylinder block of a 4-cylinder, 4-stroke 2.0L SOHC gasoline engine was numerically and experimentally analyzed. The numerical calculation was performed using the finite element method. The cylinder block was modelled as a three dimensional finite element by considering its geometry. The physical domain was devided into hexahedron elements. 16 thermocouples were installed at points of 2mm inside from cylinder wall near top ring of piston in cylinder block, which points have suffered major thermal loads and suggested as proper measurement points for engine design by industrial engineers. Under full load and 9$0^{\circ}C$ coolant temperature condition, temperature behavior of cylinder block according to engine speed were analyzed. The results showed that temperature rose gradually to conform to a function of 2nd~4th order of engine speed at intake side, exhaust and siamese side, respectively. As engine load was changed from 100 to 50% by 25% step, temperature curve also conformed to 2nd~7th order function of engine speed. Temperature differences by load condition were similar among 100, 75% and 50%. Under full load and coolant temperature of 11$0^{\circ}C$, temperature behavior were also analyzed and the result also showed conformance to 2n d~7th order function of engine speed. Temperature curve was transferred in parallel upwards corresponding coolant temperature rise.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.9 no.3
• /
• pp.42-50
• /
• 2001

In this paper, the effects of scale formation in engine water jacket upon the thermal durability of engine itself and its component parts were studied. To understand the effect of quality of water, a full load engine endurance test for 50 hours was carried out with not-treated underground water. The followings were found through the tested engine inspection after the endurance test; 1-2 mm thick scale formation in the engine water jacket, valve seat wear, piston top land scuffing, piston pin stick, and cylinder bore scuffing in siamese area. In order to understand the causes of above test results, the heat rejection rate to coolant, the metal surface temperature of combustion chamber, and the oil and exhaust gas temperatures were measured and analyzed. The scale formed in the engine water jacket played a role as thermal insulator. The scale formed in the engine reduced the heat rejection rate to coolant and it caused to increase the metal surface temperature. The reduced heat rejection rate to coolant increased the heat rejection rate to oil and exhaust gas and increased the oil and exhaust gas temperature. Also, the reasons of valve seat wear, piston top land scuffing and cylinder bore scuffing, and piston pin stick quantitatively analyzed in this paper.

• Journal of Veterinary Clinics
• /
• v.25 no.4
• /
• pp.286-288
• /
• 2008

A 8-year-old intact female Siamese cat with chronic vomiting was referred to the Veterinary Teaching Hospital of Chungnam National University. The cat was diagnosed as lymphocytic-plasmacytic enteritis by complete blood count, blood chemistry, radiography, ultrasonography and histopathologic examination following small intestine biopsy. The cat show good prognosis to date after continuous hypoallergenic diet providing and low-dose prednisolone therapy.

• Asian-Australasian Journal of Animal Sciences
• /
• v.7 no.2
• /
• pp.175-178
• /
• 1994

A study was conducted at Ijok, Malaysia, to determine the relationship of testicular measurements with libido and semen quality in tropical and imported temperate breeds of sheep. Ten rams each of Malin (M), Siamese Longtail (L), Cross of Merino with Border Leicester (C), Dorset (D) and Suffolk (S) were used for the study. Libido, semen volume and semen quality were recorded monthly for a year together with testicular length, width and circumference. The results showed that there were breed differences in volume and quality of semen where the tropical breeds had better semen compared to the temperate breeds. There was positive and significant correlation between testicle length and semen volume in all the breeds. Testicular length was found to be positively and significantly correlated with motility and sperm concentration in the tropical breeds (L and M). The relationship between libido and testicle measurements in the tropical breeds was not significant (p<0.05). There was variable relationship between the testicular measurements and libido in the temperate breeds where the relationship was significant and negative in breeds C and D and highly significant and positive in S. It was evident that the long testicles influenced the quality of the semen whereas testicles with greater circumference influenced the libido of the rams.

• The Journal of Korea Robotics Society
• /
• v.16 no.4
• /
• pp.299-305
• /
• 2021

In this study, the task of robotic tidy-up is to clean the current environment up exactly like a target image. To perform a tidy-up task using a robot, it is necessary to estimate the pose of various objects and to classify the objects. Pose estimation requires the CAD model of an object, but these models of most objects in daily life are not available. Therefore, this study proposes an algorithm that uses point cloud and PCA to estimate the pose of objects without the help of CAD models in cluttered environments. In addition, objects are usually detected using a deep learning-based object detection. However, this method has a limitation in that only the learned objects can be recognized, and it may take a long time to learn. This study proposes an image matching based on few-shot learning and Siamese network. It was shown from experiments that the proposed method can be effectively applied to the robotic tidy-up system, which showed a success rate of 85% in the tidy-up task.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.3
• /
• pp.670-684
• /
• 2024

3D Cross-Modal Retrieval (3DCMR) is a task that retrieves 3D objects regardless of modalities, such as images, meshes, and point clouds. One of the most prominent methods used for 3DCMR is the Cross-Modal Center Loss Function (CLF) which applies the conventional center loss strategy for 3D cross-modal search and retrieval. Since CLF is based on center loss, the center features in CLF are also susceptible to subtle changes in hyperparameters and external inferences. For instance, performance degradation is observed when the batch size is too small. Furthermore, the Mean Squared Error (MSE) used in CLF is unable to adapt to changes in batch size and is vulnerable to data variations that occur during actual inference due to the use of simple Euclidean distance between multi-modal features. To address the problems that arise from small batch training, we propose a Noisy Center Loss (NCL) method to estimate the optimal center features. In addition, we apply the simple Siamese representation learning method (SimSiam) during optimal center feature estimation to compare projected features, making the proposed method robust to changes in batch size and variations in data. As a result, the proposed approach demonstrates improved performance in ModelNet40 dataset compared to the conventional methods.

• Journal of Intelligence and Information Systems
• /
• v.26 no.3
• /
• pp.109-125
• /
• 2020

The Ministry of National Defense is pushing for the Defense Acquisition Program to build strong defense capabilities, and it spends more than 10 trillion won annually on defense improvement. As the Defense Acquisition Program is directly related to the security of the nation as well as the lives and property of the people, it must be carried out very transparently and efficiently by experts. However, the excessive diversification of laws and regulations related to the Defense Acquisition Program has made it challenging for many working-level officials to carry out the Defense Acquisition Program smoothly. It is even known that many people realize that there are related regulations that they were unaware of until they push ahead with their work. In addition, the statutory statements related to the Defense Acquisition Program have the tendency to cause serious issues even if only a single expression is wrong within the sentence. Despite this, efforts to establish a sentence comparison system to correct this issue in real time have been minimal. Therefore, this paper tries to propose a "Comparison System between the Statement of Military Reports and Related Laws" implementation plan that uses the Siamese Network-based artificial neural network, a model in the field of natural language processing (NLP), to observe the similarity between sentences that are likely to appear in the Defense Acquisition Program related documents and those from related statutory provisions to determine and classify the risk of illegality and to make users aware of the consequences. Various artificial neural network models (Bi-LSTM, Self-Attention, D_Bi-LSTM) were studied using 3,442 pairs of "Original Sentence"(described in actual statutes) and "Edited Sentence"(edited sentences derived from "Original Sentence"). Among many Defense Acquisition Program related statutes, DEFENSE ACQUISITION PROGRAM ACT, ENFORCEMENT RULE OF THE DEFENSE ACQUISITION PROGRAM ACT, and ENFORCEMENT DECREE OF THE DEFENSE ACQUISITION PROGRAM ACT were selected. Furthermore, "Original Sentence" has the 83 provisions that actually appear in the Act. "Original Sentence" has the main 83 clauses most accessible to working-level officials in their work. "Edited Sentence" is comprised of 30 to 50 similar sentences that are likely to appear modified in the county report for each clause("Original Sentence"). During the creation of the edited sentences, the original sentences were modified using 12 certain rules, and these sentences were produced in proportion to the number of such rules, as it was the case for the original sentences. After conducting 1 : 1 sentence similarity performance evaluation experiments, it was possible to classify each "Edited Sentence" as legal or illegal with considerable accuracy. In addition, the "Edited Sentence" dataset used to train the neural network models contains a variety of actual statutory statements("Original Sentence"), which are characterized by the 12 rules. On the other hand, the models are not able to effectively classify other sentences, which appear in actual military reports, when only the "Original Sentence" and "Edited Sentence" dataset have been fed to them. The dataset is not ample enough for the model to recognize other incoming new sentences. Hence, the performance of the model was reassessed by writing an additional 120 new sentences that have better resemblance to those in the actual military report and still have association with the original sentences. Thereafter, we were able to check that the models' performances surpassed a certain level even when they were trained merely with "Original Sentence" and "Edited Sentence" data. If sufficient model learning is achieved through the improvement and expansion of the full set of learning data with the addition of the actual report appearance sentences, the models will be able to better classify other sentences coming from military reports as legal or illegal. Based on the experimental results, this study confirms the possibility and value of building "Real-Time Automated Comparison System Between Military Documents and Related Laws". The research conducted in this experiment can verify which specific clause, of several that appear in related law clause is most similar to the sentence that appears in the Defense Acquisition Program-related military reports. This helps determine whether the contents in the military report sentences are at the risk of illegality when they are compared with those in the law clauses.

• Journal of Veterinary Clinics
• /
• v.31 no.4
• /
• pp.298-302
• /
• 2014

An 8-year-old castrated male domestic shorthair cat (Case 1) and 3-year-old castrated male Siamese cat (Case 2) was presented with acute paresis of the hindlimbs, constant open-mouth breathing, and hemoptysis. Heart murmur (Case 1) and gallop sound (Case 2) was ausculated on the left heart base. Radiographs revealed alveolar infiltration of the caudodorsal lung lobes with aerophagea in Case 1 and prominent cardiomegaly in Case 2. Marked concentric hypertrophy of the ventricular septum and free wall, and left atrial enlargement was detected through echocardiography in both cats. Based on the examinations including echocardiography, those cats were diagnosed as hypertropic cardiomyopathy. Abdominal ultrasound revealed echogenic material in the aortic trifurcation region, aortic thromboembolism (ATE). Although prognosis of those animals was guarded, interventional therapeutic approach through direct endovascular thrombolytic therapy was attempted. ATE was visualized through angiography; however dissolving the embolus using interventional thrombolytic approach was not successful due to the extensive thrombus.