• Journal of Gastric Cancer
• /
• v.15 no.4
• /
• pp.262-269
• /
• 2015

Purpose: Intraabdominal abscess is one of the most common reasons for re-hospitalization after gastrectomy. This study aimed to develop a model for estimating the probability of intraabdominal abscesses that can be used during the postoperative period. Materials and Methods: We retrospectively reviewed the clinicopathological data of 1,564 patients who underwent gastrectomy for gastric cancer between 2010 and 2012. Twenty-six related markers were analyzed, and multivariate logistic regression analysis was used to develop the probability estimation model for intraabdominal abscess. Internal validation using a bootstrap approach was employed to correct for bias, and the model was then validated using an independent dataset comprising of patients who underwent gastrectomy between January 2008 and March 2010. Discrimination and calibration abilities were checked in both datasets. Results: The incidence of intraabdominal abscess in the development set was 7.80% (122/1,564). The surgical approach, operating time, pathologic N classification, body temperature, white blood cell count, C-reactive protein level, glucose level, and change in the hemoglobin level were significant predictors of intraabdominal abscess in the multivariate analysis. The probability estimation model that was developed on the basis of these results showed good discrimination and calibration abilities (concordance index=0.828, Hosmer-Lemeshow chi-statistic P=0.274). Finally, we combined both datasets to produce a nomogram that estimates the probability of intraabdominal abscess. Conclusions: This nomogram can be useful for identifying patients at a high risk of intraabdominal abscess. Patients at a high risk may benefit from further evaluation or treatment before discharge.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.40 no.2
• /
• pp.92-98
• /
• 2017

Data clustering determines a group of patterns using similarity measure in a dataset and is one of the most important and difficult technique in data mining. Clustering can be formally considered as a particular kind of NP-hard grouping problem. K-means algorithm which is popular and efficient, is sensitive for initialization and has the possibility to be stuck in local optimum because of hill climbing clustering method. This method is also not computationally feasible in practice, especially for large datasets and large number of clusters. Therefore, we need a robust and efficient clustering algorithm to find the global optimum (not local optimum) especially when much data is collected from many IoT (Internet of Things) devices in these days. The objective of this paper is to propose new Hybrid Simulated Annealing (HSA) which is combined simulated annealing with K-means for non-hierarchical clustering of big data. Simulated annealing (SA) is useful for diversified search in large search space and K-means is useful for converged search in predetermined search space. Our proposed method can balance the intensification and diversification to find the global optimal solution in big data clustering. The performance of HSA is validated using Iris, Wine, Glass, and Vowel UCI machine learning repository datasets comparing to previous studies by experiment and analysis. Our proposed KSAK (K-means+SA+K-means) and SAK (SA+K-means) are better than KSA(K-means+SA), SA, and K-means in our simulations. Our method has significantly improved accuracy and efficiency to find the global optimal data clustering solution for complex, real time, and costly data mining process.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.7
• /
• pp.1749-1756
• /
• 2014

Knowledge about protein subcellular localization provides important information about protein function. This paper improves a label power-set multi-label classification for the accurate prediction of subcellular localization of proteins which simultaneously exist at multiple subcellular locations. Among multi-label classification methods, label power-set method can effectively model the correlation between subcellular locations of proteins performing certain biological function. With constrained optimization, this paper calculates combination weights which are used in the linear combination representation of a multi-label by other multi-labels. Using these weights, the prediction probabilities of multi-labels are combined to give final prediction results. Experimental results on human protein dataset show that the proposed method achieves higher performance than other prediction methods for protein subcellular localization. This shows that the proposed method can successfully enrich the prediction probability of multi-labels by exploiting the overlapping information between multi-labels.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.2
• /
• pp.739-748
• /
• 2014

In this paper, we propose pyramid appearance and global structure action descriptors on both RGB and depth motion history images and a model-free method for human action recognition. In proposed algorithm, we firstly construct motion history image for both RGB and depth channels, at the same time, depth information is employed to filter RGB information, after that, different action descriptors are extracted from depth and RGB MHIs to represent these actions, and then multimodality information collaborative representation and recognition model, in which multi-modality information are put into object function naturally, and information fusion and action recognition also be done together, is proposed to classify human actions. To demonstrate the superiority of the proposed method, we evaluate it on MSR Action3D and DHA datasets, the well-known dataset for human action recognition. Large scale experiment shows our descriptors are robust, stable and efficient, when comparing with the-state-of-the-art algorithms, the performances of our descriptors are better than that of them, further, the performance of combined descriptors is much better than just using sole descriptor. What is more, our proposed model outperforms the state-of-the-art methods on both MSR Action3D and DHA datasets.

• Biomolecules & Therapeutics
• /
• v.17 no.2
• /
• pp.181-187
• /
• 2009

Carnitine is known to be involved in lipid metabolism and affects body composition as well as energy metabolism of the whole body. Improvement of obesity by L-carnitine supplement suggests that obesity can be related with the abnormality of carnitine metabolism and therefore, plasma carnitine level in normal and obesity groups was investigated. For the characterization of plasma carnitine level in obese people, 60 plasma samples collected from Korean women subjects were analyzed using LC/MS and plasma fatty acid level was also determined using GC/MS. Additionally, several clinical chemical parameters including fasting glucose, cholesterol, AST, and ALT level were measured. All the data obtained were combined and pattern recognition analysis was carried out with the dataset. Obese group showed a different metabolic pattern compared with normal group. Plasma acylcarnitine level of the obese group was found to be $11.7{\mu}g/ml$, which was higher than that of normal group ($8.0{\mu}g/ml$). Statistically significant differences in plasma fatty acid level were not observed between the two groups. Other clinical parameters for the obese group were within normal ranges but AST and ALT levels were slightly elevated compared to normal group. The obese group showed elevated plasma acylcarnitine level.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.467-467
• /
• 2015

Sustainable water resource management requires the assessment of hydrological variability in response to climate fluctuations and anthropogenic activities. Determining quantitative estimates of water balance and total basin discharge are of utmost importance to understand the variations within a basin. Hard-to-reach areas with few infrastructures, coupled with lengthy administrative procedures makes in-situ data collection and water management processes very difficult and unreliable. In this study, the hydrological behavior of Lake Chad whose extent, extreme climatic and environmental conditions make it difficult to collect field observations was examined. During a 10 year period [January 2003 to December 2013], dataset from space-borne and global hydrological models observations were analyzed. Terrestial water storage (TWS) data retrieved from Gravity Recovery and Climate Experiment (GRACE), lake level variations from Satellite altimetry, water fluxes and soil moisture from Global Land Data Assimilation System (GLDAS) were used for this study. Furthermore, we combined altimetry lake volume with TWS over the lake drainage basin to estimate groundwater and soil moisture variations. This will be validated with groundwater estimates from WaterGAP Global Hydrology Model (WGHM) outputs. TWS showed similar variation patterns Lake water level as expected. The TWS in the basin area is governed by the lake's surface water. As expected, rainfall from GLDAS precedes GRACE TWS with a phase lag of about 1 month. Estimates of groundwater and soil moisture content volume changes derived by combining altimetric Lake Volume with TWS over the drainage basin are ongoing. Results obtained shall be compared with WaterGap Hydrology Model (WGHM) groundwater estimate outputs.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.2049-2068
• /
• 2021

AI combined with NLP techniques has promoted the use of Virtual Assistants and have made people rely on them for many diverse uses. Conversational Agents are the most promising technique that assists computer users through their operation. An important challenge in developing Conversational Agents globally is transferring the groundbreaking expertise obtained in English to other languages. AI is making it possible to transfer this learning. There is a dire need to develop systems that understand secular languages. One such difficult language is Hindi, which is the fourth most spoken language in the world. Semantic similarity is an important part of Natural Language Processing, which involves applications such as ontology learning and information extraction, for developing conversational agents. Most of the research is concentrated on English and other European languages. This paper presents a Corpus-based word semantic similarity measure for Hindi. An experiment involving the translation of the English benchmark dataset to Hindi is performed, investigating the incorporation of the corpus, with human and machine similarity ratings. A significant correlation to the human intuition and the algorithm ratings has been calculated for analyzing the accuracy of the proposed similarity measures. The method can be adapted in various applications of word semantic similarity or module for any other language.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.3
• /
• pp.381-388
• /
• 2022

In instance segmentation, Mask-RCNN is mostly used as a base model. Increasing the performance of Mask-RCNN is meaningful because it affects the performance of the derived model. Mask-RCNN has a transform module for unifying size of input images. In this paper, to improve the Mask-RCNN, we apply deep-learning-based ASSR to the resizing part in the transform module and inject calculated scale information into the model using IM(Integration Module). The proposed IM improves instance segmentation performance by 2.5 AP higher than Mask-RCNN in the COCO dataset, and in the periment for optimizing the IM location, the best performance was shown when it was located in the 'Top' before FPN and backbone were combined. Therefore, the proposed method can improve the performance of models using Mask-RCNN as a base model.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.10
• /
• pp.437-446
• /
• 2022

Text classification task from Natural Language Processing (NLP) combined with state-of-the-art (SOTA) Machine Learning (ML) and Deep Learning (DL) algorithms as the core engine is widely used to detect and classify voice phishing call transcripts. While numerous studies on the classification of voice phishing call transcripts are being conducted and demonstrated good performances, with the increase of non-face-to-face financial transactions, there is still the need for improvement using the latest NLP technologies. This paper conducts a benchmarking of Korean voice phishing detection performances of the pre-trained Korean language model KoBERT, against multiple other SOTA algorithms based on the classification of related transcripts from the labeled Korean voice phishing dataset called KorCCVi. The results of the experiments reveal that the classification accuracy on a test set of the KoBERT model outperforms the performances of all other models with an accuracy score of 99.60%.

• Smart Media Journal
• /
• v.11 no.2
• /
• pp.63-69
• /
• 2022

As the use of various IoT devices increases, the importance of IoT platforms is also rising. Recently, artificial intelligence technology is being combined with IoT devices, and research applying a neuromorphic architecture to IoT devices with low power is also increasing. In this paper, an application scenario is proposed based on NA-IDE (Neuromorphic Architecture-based autonomous IoT application integrated development environment) with IoT devices and FPGA devices in a GUI format. The proposed scenario connects a camera module to an IoT device, collects MNIST dataset images online, recognizes the collected images through a neuromorphic board, and displays the recognition results through a device module connected to other IoT devices. If the neuromorphic architecture is applied to many IoT devices and used for various application services, the autonomous IoT application integrated development environment based on the neuromorphic architecture is expected to emerge as a core technology leading the 4th industrial revolution.