• 한국컴퓨터정보학회논문지
• /
• 제14권11호
• /
• pp.1-12
• /
• 2009

집단따돌림(모빙: Mobbing, 이하 '모빙')은 사회 전반에 걸쳐 빠르게 확산되고 있으며 군 조직도 예외가 될 수 없다. 군 조직에서의 모빙 현상은 성인사회 따돌림의 형태인 심리적 배제뿐만 아니라 때로는 심리적, 신체적 괴롭힘까지 나타나기 때문에 자살이나 난동 같은 심각한 군기 사고로 이어지기도 한다. 특히 군 조직에서는 집단 따돌림 예방을 위한 여러 가지 제도 및 관리방안의 시행에도 불구하고 그 피해자가 계속 발생하므로 문제 해결을 위한 어떤 제도와 관리방안을 마련하는 것 보다 그 희생 대상자와 잠정적 희생 대상자를 파악하는 것이 보다 효율적이라는 것을 말해준다. 따라서 본 논문에서는 이러한 문제 해결을 위해 모빙 현상에 관련된 7개의 요소(Factor)와 그 하위에 포함된 50개의 속성 (Attribute)들을 선정한다. 이후 자체 개발한 Gunwoo's 소셜 네트워크 서비스를 이용하여 나와 커뮤니티를 형성한 그룹들에 대해 연관성 유무에 따라 관계가 있으면 '1', 관계가 없으면 '0'으로 표현하여 지수화 한다. 그리고 나와 사용자들 간의 유사도 산정을 위해 유사도 함수(Dice 계수)를 적용한다. 다음으로 SPSS 클레멘타인의 인공신경망(ANN: Artificial Neural Network) 알고리즘을 통해 7개 요소들에 대한 최적의 가중치를 산출하고, 이 값들의 총합으로 Mobbing Value(이하 '모빙 지수')를 산정하기 위한 알고리즘을 제안한다. 이 알고리즘은 현재의 모빙 희생자와 잠정적인 희생자를 파악하여 희생자 관리 개선에 도움이 될 것이다.

• Korean Journal of Radiology
• /
• 제21권1호
• /
• pp.88-100
• /
• 2020

Objective: We aimed to develop and validate a deep learning system for fully automated segmentation of abdominal muscle and fat areas on computed tomography (CT) images. Materials and Methods: A fully convolutional network-based segmentation system was developed using a training dataset of 883 CT scans from 467 subjects. Axial CT images obtained at the inferior endplate level of the 3rd lumbar vertebra were used for the analysis. Manually drawn segmentation maps of the skeletal muscle, visceral fat, and subcutaneous fat were created to serve as ground truth data. The performance of the fully convolutional network-based segmentation system was evaluated using the Dice similarity coefficient and cross-sectional area error, for both a separate internal validation dataset (426 CT scans from 308 subjects) and an external validation dataset (171 CT scans from 171 subjects from two outside hospitals). Results: The mean Dice similarity coefficients for muscle, subcutaneous fat, and visceral fat were high for both the internal (0.96, 0.97, and 0.97, respectively) and external (0.97, 0.97, and 0.97, respectively) validation datasets, while the mean cross-sectional area errors for muscle, subcutaneous fat, and visceral fat were low for both internal (2.1%, 3.8%, and 1.8%, respectively) and external (2.7%, 4.6%, and 2.3%, respectively) validation datasets. Conclusion: The fully convolutional network-based segmentation system exhibited high performance and accuracy in the automatic segmentation of abdominal muscle and fat on CT images.

• Asia pacific journal of information systems
• /
• 제18권1호
• /
• pp.79-96
• /
• 2008

One of the roles of the Semantic Web services is to execute dynamic intra-organizational services including the integration and interoperation of business processes. Since different organizations design their processes differently, the retrieval of similar semantic business processes is necessary in order to support inter-organizational collaborations. Most approaches for finding services that have certain features and support certain business processes have relied on some type of logical reasoning and exact matching. This paper presents our approach of using imprecise matching for expanding results from an exact matching engine to query the OWL(Web Ontology Language) MIT Process Handbook. MIT Process Handbook is an electronic repository of best-practice business processes. The Handbook is intended to help people: (1) redesigning organizational processes, (2) inventing new processes, and (3) sharing ideas about organizational practices. In order to use the MIT Process Handbook for process retrieval experiments, we had to export it into an OWL-based format. We model the Process Handbook meta-model in OWL and export the processes in the Handbook as instances of the meta-model. Next, we need to find a sizable number of queries and their corresponding correct answers in the Process Handbook. Many previous studies devised artificial dataset composed of randomly generated numbers without real meaning and used subjective ratings for correct answers and similarity values between processes. To generate a semantic-preserving test data set, we create 20 variants for each target process that are syntactically different but semantically equivalent using mutation operators. These variants represent the correct answers of the target process. We devise diverse similarity algorithms based on values of process attributes and structures of business processes. We use simple similarity algorithms for text retrieval such as TF-IDF and Levenshtein edit distance to devise our approaches, and utilize tree edit distance measure because semantic processes are appeared to have a graph structure. Also, we design similarity algorithms considering similarity of process structure such as part process, goal, and exception. Since we can identify relationships between semantic process and its subcomponents, this information can be utilized for calculating similarities between processes. Dice's coefficient and Jaccard similarity measures are utilized to calculate portion of overlaps between processes in diverse ways. We perform retrieval experiments to compare the performance of the devised similarity algorithms. We measure the retrieval performance in terms of precision, recall and F measure? the harmonic mean of precision and recall. The tree edit distance shows the poorest performance in terms of all measures. TF-IDF and the method incorporating TF-IDF measure and Levenshtein edit distance show better performances than other devised methods. These two measures are focused on similarity between name and descriptions of process. In addition, we calculate rank correlation coefficient, Kendall's tau b, between the number of process mutations and ranking of similarity values among the mutation sets. In this experiment, similarity measures based on process structure, such as Dice's, Jaccard, and derivatives of these measures, show greater coefficient than measures based on values of process attributes. However, the Lev-TFIDF-JaccardAll measure considering process structure and attributes' values together shows reasonably better performances in these two experiments. For retrieving semantic process, we can think that it's better to consider diverse aspects of process similarity such as process structure and values of process attributes. We generate semantic process data and its dataset for retrieval experiment from MIT Process Handbook repository. We suggest imprecise query algorithms that expand retrieval results from exact matching engine such as SPARQL, and compare the retrieval performances of the similarity algorithms. For the limitations and future work, we need to perform experiments with other dataset from other domain. And, since there are many similarity values from diverse measures, we may find better ways to identify relevant processes by applying these values simultaneously.

• 대한간호학회지
• /
• 제36권7호
• /
• pp.1204-1214
• /
• 2006

Purpose: This retrospective study was done to evaluate the status of nosocomial urinary tract infections and to determine the risk factors and transmission route of causal IRPA through molecular epidemiology. Method: Two hundred ninety-nine of 423 patients admitted to the internal medicine and surgery ICU at a university hospital incity B had a positiveurine culture. Twelve of the 299 patients who had a urinary tract infection had IRPA strains. The data was collected from November 1, 2004 to January 31, 2005. The following results were obtained after the data was analyzed using percentile and UPGMA. Result: The rate of nosocomial urinary tract infections in the ICU was 10.8%. Therewere 16.8 cases of infection based on the period of hospitalization. There were 16.9 cases of infection based on the use of a foley catheter. The rate of nosocomial urinary tract infection in the ICU and urinary tract infections related to IRPA were higher in patients with the following characteristics: men, old age, admission through the emergency room, longer than seven days admission, severity of admitting causes, disturbance of consciousness, hydration less than 300cc in 24hours, a long course of antibiotics, a long period of foley catheterization and perineal care. Most of the microorganisms that caused the urinary tract infection were gram negative bacilli, among which P. aeruginosa was found in 70 patients (18.5%) and IRPA in 12 (4.0%). Among the 12 IRPA strains that were tested with PFGE, eight showed a dice coefficient higher than 80%, suggesting a genetic relationship. They were related with the period of hospitalization in the same ICU. These patients all received direct care for a urinary tract infection. Conclusion: Through these results, IRPA can be consideredas a contributing factors to urinary tract infections thus, active preventative measures are needed by the medical staff.

• Journal of Microbiology and Biotechnology
• /
• 제17권11호
• /
• pp.1772-1781
• /
• 2007

Activated sludge was sequentially adapted to benzene, toluene, and o-xylene (BTX) to study the effects on the change of microbial community. Sludge adapted to BTX separately degraded each by various rates in the following order; toluene>o-xylene>benzene. Degradation rates were increased after exposure to repeated spikes of substrates. Eleven different kinds of sludge were prepared by the combination of BTX sequential adaptations. Clustering analyses (Jaccard, Dice, Pearson, and cosine product coefficient and dimensional analysis of MDS and PCA for DGGE patterns) revealed that acclimated sludge had different features from nonacclimated sludge and could be grouped together according to their prior treatment. Benzene- and xylene-adapted sludge communities showed similar profiles. The sludge profile was affected from the point of the final adaptation substrate regardless of the adaptation sequence followed. In the sludge adapted to 50 ppm toluene, Nitrosomonas sp. and bacterium were dominant, but these bands were not dominant in benzene and benzene after toluene adaptations. Instead, Flexibacter sp. was dominant in these cultures. Dechloromonas sp. was dominant in the culture adapted to 50 ppm benzene. Thauera sp. was the main band in the sludge adapted to 50 ppm xylene, but became vaguer as the xylene concentration was increased. Rather, Flexibacter sp. dominated in the sludge adapted to 100 ppm xylene, although not in the culture adapted to 250 ppm xylene. Two bacterial species dominated in the sludge adapted to 250 ppm xylene, and they also existed in the sludge adapted to 250 ppm xylene after toluene and benzene.

• 한국멀티미디어학회논문지
• /
• 제16권12호
• /
• pp.1376-1384
• /
• 2013

본 논문에서는 산업용 CT 볼륨데이터에서 템플릿 매칭을 통하여 제품의 이물질을 자동 검출하는 기법을 제안한다. 제안방법은 다음과 같은 세 단계로 이루어진다. 첫째, 다운 샘플링 데이터에서 잡음제거 후 제품을 배경과 분리하고, 영상의 평균값 및 표준편차를 이용하여 초기 이물질 후보를 추출한 후, K-평균 클러스터링을 이용하여 이물질 후보를 추출한다. 둘째, 템플릿 매칭을 이용하여 제품과 유사도가 다른 이물질을 검출한다. 이 때, 검출하고자 하는 이물질의 크기에 따라 밝기값평균차이(SSD)와 조인트 엔트로피를 이용한 유사도 평가를 통하여 이물질을 검출한다. 셋째, 원 볼륨데이터에서 이물질 검출률을 개선하기 위하여 여과기법으로 제품의 이물질을 최종 검출한다. 본 제안 방법의 결과를 평가하기 위해 산업용 CT 볼륨데이터와 시뮬레이션 데이터를 사용하여 육안평가, 정확성 평가와 수행시간 측정을 수행하였다. 정확성 평가를 위하여 기존 밝기값 기반 검출 기법을 비교방법으로 사용하고, 다이스 계수 유사도를 측정하였다.

• Investigative Magnetic Resonance Imaging
• /
• 제24권3호
• /
• pp.123-131
• /
• 2020

Purpose: Joint label fusion (JLF) is a popular multi-atlas-based segmentation algorithm, which compensates for dependent errors that may exist between atlases. However, in order to get good segmentation results, it is very important to set the several free parameters of the algorithm to optimal values. In this study, we first investigate the feasibility of a JLF algorithm for prostate segmentation in MR images, and then suggest the optimal set of parameters for the automatic prostate segmentation by validating the results of each parameter combination. Materials and Methods: We acquired T2-weighted prostate MR images from 20 normal heathy volunteers and did a series of cross validations for every set of parameters of JLF. In each case, the atlases were rigidly registered for the target image. Then, we calculated their voting weights for label fusion from each combination of JLF's parameters (r_pxy, r_pz, r_sxy, r_sz, β). We evaluated the segmentation performances by five validation metrics of the Prostate MR Image Segmentation challenge. Results: As the number of voxels participating in the voting weight calculation and the number of referenced atlases is increased, the overall segmentation performance is gradually improved. The JLF algorithm showed the best results for dice similarity coefficient, 0.8495 ± 0.0392; relative volume difference, 15.2353 ± 17.2350; absolute relative volume difference, 18.8710 ± 13.1546; 95% Hausdorff distance, 7.2366 ± 1.8502; and average boundary distance, 2.2107 ± 0.4972; in parameters of r_pxy = 10, r_pz = 1, r_sxy = 3, r_sz = 1, and β = 3. Conclusion: The evaluated results showed the feasibility of the JLF algorithm for automatic segmentation of prostate MRI. This empirical analysis of segmentation results by label fusion allows for the appropriate setting of parameters.

• 대한의용생체공학회:의공학회지
• /
• 제41권5호
• /
• pp.195-202
• /
• 2020

Needle detection in ultrasound images is sometimes difficult due to obstruction of fat tissues. Accurate needle detection using continuous ultrasound (CUS) images is a vital stage of treatment planning for tissue biopsy and brachytherapy. The main goal of the study is classified into two categories. First, new detection model, i.e. D-Attention Unet, is developed by combining the context information of 3D medical data and CUS images. Second, the D-Attention Unet model was compared with other models to verify its usefulness for needle detection in continuous ultrasound images. The continuous needle images taken with ultrasonic waves were converted into still images for dataset to evaluate the performance of the D-Attention Unet. The dataset was used for training and testing. Based on the results, the proposed D-Attention Unet model showed the better performance than other 3 models (Unet, D-Unet and Attention Unet), with Dice Similarity Coefficient (DSC), Recall and Precision at 71.9%, 70.6% and 73.7%, respectively. In conclusion, the D-Attention Unet model provides accurate needle detection for US-guided biopsy or brachytherapy, facilitating the clinical workflow. Especially, this kind of research is enthusiastically being performed on how to add image processing techniques to learning techniques. Thus, the proposed method is applied in this manner, it will be more effective technique than before.

• 한국수산과학회지
• /
• 제36권6호
• /
• pp.654-660
• /
• 2003

To evaluate the biological diversity of fish pathogenic streptococci, 35 strains isolated from diseased olive flounder (Paralichtys olivaceus), were analyzed using a random amplified polymorphic DNA (RAPD) technique with the oligonucleotide commercial primer 6 (Amersham Biosciences). Api 20 Strep test, drug resistance and artificial infection were carried out for further characterization of the isolates. RAPD fingerprints showed similar pattern in 25 strains (about $71.4\%$ of 35 isolates) and these strains were designed as RA group 1. Similarities greater than $44\%$ were obtained when the Dice coefficient was applied among the isolates of RA 1. On the other hand, the reference Streptococcus iniae showed a similar RAPD profile to the isolates with similarity levels of $40-93.3\%.$ Rh I was suggested to be the dominant group isolated from olive flounder suffering from streptococcosis. However, the isolates of Rh 1 group were not classified into the same species by the Api 20 Strep identification system. There was no peculiarity in drug resistance patterns of Rh I group isolates against 7 antibacterial agents. However, only 3 of 25 isolates $(0.12\%)$ showed oxytetracycline (OTC) resistance and OTC might be a useful chemotherapeutic agent in controlling the streptococcosis by strains of RA I group in olive flounder. Fish injected intraperitoneally with $10^5$ CFU of an isolate of Rh I and RA III group showed $60\%\;and\;50\%$ accumulative mortality for 20 days, respectively ($20\%$ in control or Rh II). However luther comparative studies about differences in virulence between isolates are needed.

• International Journal of Industrial Entomology and Biomaterials
• /
• 제29권2호
• /
• pp.169-178
• /
• 2014

In this study, we investigated genetic diversity of 22 microsporidian isolates infecting tropical tasar silkworm, Antheraea mylitta collected from various geographical forest locations in the state of Jharkhand, India, using polymerase chain reaction (PCR)-based marker assay: random amplified polymorphic DNA (RAPD). A type species, NIK-1s_mys was used as control for comparison. The shape of mature microsporidians was found to be oval to elongate, measuring 3.80 to $5.10{\mu}m$ in length and 2.56 to $3.30{\mu}m$ in width. Of the 20 RAPD primers screened, 16 primers generated reproducible profiles with 298 polymorphic fragments displaying high degree of polymorphism (97%). A total of 14 RAPD primers produced 45 unique putative genetic markers, which were used to differentiate the microsporidians. Calculation of genetic distance coefficients based on dice coefficient method and clustering with un-weighted pair group method using arithmetic average (UPGMA) analysis was conducted to unravel the genetic diversity of microsporidians infecting tasar silkworm. The similarity coefficients varied from 0.059 to 0.980. UPGMA analysis generated a dendrogram with four microsporidian groups, which appear to be different from each other as well as from NIK-1s_mys. Two-dimensional distribution based on Euclidean distance matrix also revealed considerable variability among different microsporidians identified from the tasar silkworms. Clustering of few microsporidian isolates was in accordance with the geographic origin. The results indicate that the RAPD profiles and specific/unique genetic markers can be used for differentiating as well as to identify different microsporidians with considerable accuracy.