• The Journal of the Acoustical Society of Korea
• /
• 제25권2E호
• /
• pp.74-78
• /
• 2006

This paper proposes an effective method for classifying emotions of the music from its acoustical signals. Two feature sets, timbre and tempo, are directly extracted from the modified discrete cosine transform coefficients (MDCT), which are the output of partial MP3 (MPEG 1 Layer 3) decoder. Our tempo feature extraction method is based on the long-term modulation spectrum analysis. In order to effectively combine these two feature sets with different time resolution in an integrated system, a classifier with two layers based on AdaBoost algorithm is used. In the first layer the MDCT-driven timbre features are employed. By adding the MDCT-driven tempo feature in the second layer, the classification precision is improved dramatically.

• Food Science and Biotechnology
• /
• 제17권1호
• /
• pp.95-101
• /
• 2008

Some biological activities of Beauveria bassiana were studied to elucidate pharmacological function of B. bassiana-infected larva of the silkworm. The mycelium consisted mainly of carbohydrate (65.8%), followed by protein (15.9%) and fat (8.3%). Glucose (68.8%), mannose (7.1%), and galactose (6.1%) were major components in carbohydrates. Ten amino acids including glutamine, threonine, valine, aspartic acid, alanine, leucine, serine, glycine, arginine, and isoleucine were found in protein as major amino acids. Various extracts were prepared from the freeze-dried mycelium of B. bassiana by systemic extraction and their biological activities were investigated. Among tested fractions, the hot-water extract (HW) contributed significantly to the anti-coagulant activity, anti-complementary activity, and stimulation of intestinal immune system. The methanol extract (ME) increased acetylcholinesterase (AChE) inhibition activity and reactive oxygen species (ROS) scavenging activity.

• 생명과학회지
• /
• 제20권6호
• /
• pp.922-928
• /
• 2010

한방 생약재로부터 안전하면서도 신규의 항혈전제를 개발하기 위해, 현재 국내에서 유통되고 있는 국내 및 국외산 한방 생약재 33종을 대상으로 40종의 에탄올 추출물을 조제하고, 이들의 thrombin time (TT), prothrombin time (PT), activated partial thromboplastin time (aPTT)을 평가하였다. 생약재중 중국산은 28종으로 대부분이 국외산이었으며, 부위별로는 종자 및 뿌리 부위가 19종을 차지하였다. 평균 수분함량은 $6.85{\pm}2.26%$, 평균 추출율은 $5.27{\pm}4.25%$를 나타내었다. 조제된 시료의 TT평가 결과, 사인(중국), 고본, 팔각향, 계지, 당삼, 계혈등, 행인, 오배자, 괄루근 및 포황에서 우수한 트롬빈 저해활성을 확인하였으며, 다양한 농도에서 평가 결과 계혈등, 행인, 팔각향, 계지, 오배자 추출물 순으로 트롬빈 저해능이 강력함을 확인하였다. PT 평가 결과 오배자, 계혈등, 행인에서, aPTT 평가결과 오배자 및 계혈등에서 우수한 항혈전능을 확인하였다. 한편 추출물의 인간적혈구 용혈활성을 평가한 결과, 계혈등, 팔각향, 계지, 오배자 추출물은 $500\;{\mu}g/ml$ 농도에서도 용혈활성이 없음을 확인하여 이들 4종을 최종 선정하였다. 본 연구결과는 이미 대량생산이 확립된 한방생약제로부터 우수한 항혈전제 개발이 가능함을 제시하고 있으며, 트롬빈 및 혈장 응고 인자에 대한 특이 저해제 개발이 가능함을 제시하고 있다.

• 전자공학회논문지B
• /
• 제32B권11호
• /
• pp.1445-1454
• /
• 1995

In this study, we have developed a prototype of the automatic defects detection system for capsule inspection using the computer vision techniques. The subjects for inspection are empty hard capsules of various sizes which are made of gelatine. To inspect both sides of a capsule, 2-stage recognition is performed. Features we have used are various lengths of a capsule, area, linearity, symmetricity, head curvature and so on. Decision making is performed based on average value which is computed from 20 good capsules in training and permission bounds in factories. Most of time-consuming process for feature extraction is computed by hardware to meet the inspection speed of more than 20 capsules/sec. The main logic for control and arithmetic computation is implemented using EPLD for the sake of easy change of design and reduction in time for developement. As a result of experiment, defects on size or contour of binary images are detected over 95%. Because of dead zone in imaging system, detection ratio of defects on surface, such as bad joint, chip, speck, etc, is lower than the former case. In this case, detection ratio is 50-85%. Defects such as collet pinch and mashed cap/body seldom appear in binary image, and detection ratio is very low. So we have to process the gray-level image directly in partial region.

• International Journal of Computer Science & Network Security
• /
• 제22권10호
• /
• pp.171-176
• /
• 2022

A dramatic rise in the number of people dying from heart disease has prompted efforts to find a way to identify it sooner using efficient approaches. A variety of variables contribute to the condition and even hereditary factors. The current estimate approaches use an automated diagnostic system that fails to attain a high level of accuracy because it includes irrelevant dataset information. This paper presents an effective neural network with convolutional layers for classifying clinical data that is highly class-imbalanced. Traditional approaches rely on massive amounts of data rather than precise predictions. Data must be picked carefully in order to achieve an earlier prediction process. It's a setback for analysis if the data obtained is just partially complete. However, feature extraction is a major challenge in classification and prediction since increased data increases the training time of traditional machine learning classifiers. The work integrates the CNN-MDRP classifier (convolutional neural network (CNN)-based efficient multimodal disease risk prediction with TANFIS (tuned adaptive neuro-fuzzy inference system) for earlier accurate prediction. Perform data cleaning by transforming partial data to informative data from the dataset in this project. The recommended TANFIS tuning parameters are then improved using a Laplace Gaussian mutation-based grasshopper and moth flame optimization approach (LGM²G). The proposed approach yields a prediction accuracy of 98.40 percent when compared to current algorithms.

• 한국지하수토양환경학회지:지하수토양환경
• /
• 제15권1호
• /
• pp.9-18
• /
• 2010

In this study, Solid-phase micro-extraction (SPME) with Gas Chromatograph using Flame Ionization Detector (GC/FID) was studied as a possible alternative to liquid-liquid extraction for the analysis of Methyl tert-butyl ether (MTBE) and Tertiary-butyl ether (TBA) in water and an optimization condition of trace analysis of MTBE and TBA using the design of experiment (DOE) was described. The aim of our research was to apply experimental design methodology in the optimization condition of trace analysis of fuel oxygenated compounds in soil-phase microextraction with GC/FID. The reactions of SPME were mathematically described as a function of parameters of Temp ($X_1$), Volume ($X_2$), Time ($X_3$) and Salt ($X_4$) being modeled by the use of the partial factorial designs, which was used for fitting 2nd order response surface models and was alternative to central composite designs. The model predicted agreed with the experimentally observed result ($Y_1$(MTBE, $R^2$ = 0.96, $Y_2$ (TBA, $R^2$ = 0.98)). The estimated ridge of the expected maximum responses and optimal conditions for MTBE and TBA were 278.13 and (Temp ($X_1$) = $48.40^{\circ}C$, Volume ($X_2$) = 73.04 mL, Time ($X_3$) = 11.51 min and Salt ($X_4$) = 12,50 mg/L), and 127.89 and (Temp ($X_1$) = $52.12^{\circ}C$, Volume ($X_2$) = 88.88mL, Time ($X_3$) = 65.40 min and Salt ($X_4$) = 12,50 mg/L), respectively.

• 한국정보통신학회논문지
• /
• 제14권11호
• /
• pp.2485-2490
• /
• 2010

본 논문에서는, 수면을 이루는 침실의 수면 환경 데이터를 채취하고 얻은 조건 데이터들과 수면 사이의 관계를 분석하였다. 이것을 기초로, 모의실험 모델을 추출하여 개인별 최적의 수면 환경을 제공하도록 한다. 시스템의 실험은 온/습도 센서와 조도 센서로 구성된 H-MOTE2420 센서를 이용하였다. 수면 중 뒤척임의 추출을 위하여 비디오에서 움직임을 추출하는 차영상 방법을 이용하였다. 또한, 수면에 영향을 끼칠만한 가중치의 정보로 피로한 정도, 음주의 정도, 공복의 정도 등의 정보를 입력 받는다. 실험 결과 최적의 수면환경을 추출할 수 있었다. 향후, 수면의 특수한 상황뿐만 아니라 식사나 출근과 같은 유기적인 생활환경의 한 부분에도 상황에 따른 적절한 실내 환경 변화를 제공해 주어서 좀더 쾌적한 일상생활을 영위할 수 있도록 도움을 주도록 개선하려 할 것이다.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 1999년도 가을 학술발표회 논문집
• /
• pp.405-414
• /
• 1999

The auger and screw piles have known an important evolution during the last decade. Besides the large success of augercast (CFA) piling systems, new systems have been developed combining, to a variable extent, the classical extraction auger with especially designed displacement tools in order to develop screw piles with partial or total lateral soil displacement. These last developments cover the whole range of lateral soil displacement and are more difficult than ever to compare. The authors present the latest evolutions in auger piling systems and compare them with respect to penetration performances, bearing capacities and amount of spoil generated. A special focus is given to a new efficient system: the OMEGA(H) pile in use in Korea since 1997. The results of the Hongcheon site are presented where this R system was applied for a new investment of the Korean National Housing Corporation (KNHC). This first important experience, with the execution of some 1,500 Omega piles with diameter 410 mm, is presented. The piles were installed through loose silty sands down to very dense sands and layers of gravel. The results of full-scale load tests are analysed and show the conformity with requirements of the clients.

• International Journal of Computer Science & Network Security
• /
• 제21권8호
• /
• pp.288-296
• /
• 2021

Automated face recognition in a runtime environment is gaining more and more important in the fields of surveillance and urban security. This is a difficult task keeping in mind the constantly volatile image landscape with varying features and attributes. For a system to be beneficial in industrial settings, it is pertinent that its efficiency isn't compromised when running on roads, intersections, and busy streets. However, recognition in such uncontrolled circumstances is a major problem in real-life applications. In this paper, the main problem of face recognition in which full face is not visible (Occlusion). This is a common occurrence as any person can change his features by wearing a scarf, sunglass or by merely growing a mustache or beard. Such types of discrepancies in facial appearance are frequently stumbled upon in an uncontrolled circumstance and possibly will be a reason to the security systems which are based upon face recognition. These types of variations are very common in a real-life environment. It has been analyzed that it has been studied less in literature but now researchers have a major focus on this type of variation. Existing state-of-the-art techniques suffer from several limitations. Most significant amongst them are low level of usability and poor response time in case of any calamity. In this paper, an improved face recognition system is developed to solve the problem of occlusion known as FRS-OCC. To build the FRS-OCC system, the color and texture features are used and then an incremental learning algorithm (Learn++) to select more informative features. Afterward, the trained stack-based autoencoder (SAE) deep learning algorithm is used to recognize a human face. Overall, the FRS-OCC system is used to introduce such algorithms which enhance the response time to guarantee a benchmark quality of service in any situation. To test and evaluate the performance of the proposed FRS-OCC system, the AR face dataset is utilized. On average, the FRS-OCC system is outperformed and achieved SE of 98.82%, SP of 98.49%, AC of 98.76% and AUC of 0.9995 compared to other state-of-the-art methods. The obtained results indicate that the FRS-OCC system can be used in any surveillance application.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권3호
• /
• pp.1086-1103
• /
• 2020

The automatic identification and classification of image-based weld defects is a difficult task due to the complex texture of the X-ray images of the weld defect. Several depth learning methods for automatically identifying welds were proposed and tested. In this work, four different depth convolutional neural networks were evaluated and compared on the 1631 image set. The concavity, undercut, bar defects, circular defects, unfused defects and incomplete penetration in the weld image 6 different types of defects are classified. Another contribution of this paper is to train a CNN model "RayNet" for the dataset from scratch. In the experiment part, the parameters of convolution operation are compared and analyzed, in which the experimental part performs a comparative analysis of various parameters in the convolution operation, compares the size of the input image, gives the classification results for each defect, and finally shows the partial feature map during feature extraction with the classification accuracy reaching 96.5%, which is 6.6% higher than the classification accuracy of other existing fine-tuned models, and even improves the classification accuracy compared with the traditional image processing methods, and also proves that the model trained from scratch also has a good performance on small-scale data sets. Our proposed method can assist the evaluators in classifying pipeline welding defects.