• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권2호
• /
• pp.742-762
• /
• 2015

In this study, we propose a distance metric learning approach called discriminant metric learning (DML) for face verification, which addresses a binary-class problem for classifying whether or not two input images are of the same subject. The critical issue for solving this problem is determining the method to be used for measuring the distance between two images. Among various methods, the large margin nearest neighbor (LMNN) method is a state-of-the-art algorithm. However, to compensate the LMNN's entangled data distribution due to high levels of appearance variations in unconstrained environments, DML's goal is to penalize violations of the negative pair distance relationship, i.e., the images with different labels, while being integrated with LMNN to model the distance relation between positive pairs, i.e., the images with the same label. The likelihoods of the input images, estimated using DML and LMNN metrics, are then weighted and combined for further analysis. Additionally, rather than using the k-nearest neighbor (k-NN) classification mechanism, we propose a verification mechanism that measures the correlation of the class label distribution of neighbors to reduce the false negative rate of positive pairs. From the experimental results, we see that DML can modify the relation of negative pairs in the original LMNN space and compensate for LMNN's performance on faces with large variances, such as pose and expression.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1997년도 추계학술대회 학술발표 논문집
• /
• pp.143-153
• /
• 1997

At the on-line control method FLC(Fuzzy Logic Controller) is stronger to the disturbance than a classical controller and its overshoot of the initialized value is excellent. The fuzzy controller can do a proper control, though it doesn't know the mathematical model of the system or the parameter value. But to make the control rule of the fuzzy controller through an expert's experiance has a changes of the control system, the control rule is fixed, it can't adjust to the environment changes of the control system, the controller output value has a minute error and it can't convergence correctly to the desired value[1][2]. There are many ways to eliminate the minute error[3][4][5], but in this paper suggests EP-FNNIC(Fuzzy Neurla Network Intelligence Controller) intelligence controller which combines FLC with NN(Neural Network) and EP(Evolution Programming). The output characteristics of EP-FNNIC controller will be compared and analyzed with FLC. It will be showed that this EP-FN IC controller converge correctly to the desirable value without any error. The convergence speed, overshoot, rising time, error of steady state of controller of these two kinds also will be compared.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 1998년도 가을 학술발표논문집 Vol.25 No.2 (2)
• /
• pp.384-386
• /
• 1998

The use of hand gesture provides an attractive alternative to cumbersome interface devices for human-computer interaction(HCI). Many methods hand gesture recognition using visual analysis have been proposed such as syntactical analysis, neural network(NN), Hidden Markov Model(HMM) and so on. In our research, a HMMs is proposed for alphabetical hand gesture recognition. In the preprocessing stage, the proposed approach consists of three different procedures for hand localization, hand tracking and gesture spotting. The hand location procedure detects the candidated regions on the basis of skin-color and motion in an image by using a color histogram matching and time-varying edge difference techniques. The hand tracking algorithm finds the centroid of a moving hand region, connect those centroids, and thus, produces a trajectory. The spotting a feature database, the proposed approach use the mesh feature code for codebook of HMM. In our experiments, 1300 alphabetical and 1300 untrained gestures are used for training and testing, respectively. Those experimental results demonstrate that the proposed approach yields a higher and satisfying recognition rate for the images with different sizes, shapes and skew angles.

• Advances in Traditional Medicine
• /
• 제3권1호
• /
• pp.21-28
• /
• 2003

The pharmacological effects of an Ayurvedic diuretic drug 'Treenoponchomul' (TPM) was investigated in animal model. The pharmacological actions of the test drug along with that of the components thereof, on the Central Nervous System (CNS) were studied. The drug under study TPM showed little effect on the CNS, the same can not be said about the components. The most prominent CNS depressant effect was observed with Saccharum officinarum Linn. (EE) in that it lowered the spontaneous motor activity as well the exploratory -behavior of the animals. An exploration retarding effect of moderate degree, was evident with Imperata cylindrica Beauv. (UU), and Phragmites maxima Blatter & McCann (NN). Although the test drug did not alter the normal locomotor and/ or exploratory behavior of the treated animals, it did significantly (p<0.01) lower the locomotion of the amphetamine induced hyperactive animals. TPM along with its components (especially Desmostachya bipinnata Stapf. Root, KU), significantly reduced the gastro-intestinal motility of the treated animals (p<0.01). The test drug and its components lowered the body weight of the treated animals, on being administered chronically (30 days), with EE being the only exception.

• Journal of Magnetics
• /
• 제22권1호
• /
• pp.34-42
• /
• 2017

Material defects in the Steam Generator Tubes (SGT) of sodium cooled fast breeder reactor (PFBR) can lead to leakage of water into sodium. The water and sodium reaction will lead to major accidents. Therefore, the examination of steam generator tubes for the early detection of defects is an important requirement for safety and economic considerations. In this work, the Magnetic Flux Leakage (MFL) based Non Destructive Testing (NDT) technique is used to perform the defect detection process. The rectangular notch defects on the outer surface of steam generator tubes are modeled using COMSOL multiphysics 4.3a software. The obtained MFL images are de-noised to improve the integrity of flaw related information. Grey Level Co-occurrence Matrix (GLCM) features are extracted from MFL images and taken as input parameter to train the neural network. A comparative study on characterization have been carried out using feed-forward back propagation (FFBP) and cascade-forward back propagation (CFBP) algorithms. The results of both algorithms are evaluated with Mean Square Error (MSE) as a prediction performance measure. The average percentage error for length, depth and width are also computed. The result shows that the feed-forward back propagation network model performs better in characterizing the defects.

• Journal of Information Processing Systems
• /
• 제15권3호
• /
• pp.682-693
• /
• 2019

The traditional classification methods mostly assume that the data for class distribution is balanced, while imbalanced data is widely found in the real world. So it is important to solve the problem of classification with imbalanced data. In Mahalanobis-Taguchi system (MTS) algorithm, data classification model is constructed with the reference space and measurement reference scale which is come from a single normal group, and thus it is suitable to handle the imbalanced data problem. In this paper, an improved method of MTS-CBPSO is constructed by introducing the chaotic mapping and binary particle swarm optimization algorithm instead of orthogonal array and signal-to-noise ratio (SNR) to select the valid variables, in which G-means, F-measure, dimensionality reduction are regarded as the classification optimization target. This proposed method is also applied to the financial distress prediction of Chinese listed companies. Compared with the traditional MTS and the common classification methods such as SVM, C4.5, k-NN, it is showed that the MTS-CBPSO method has better result of prediction accuracy and dimensionality reduction.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2019년도 제60차 하계학술대회논문집 27권2호
• /
• pp.157-158
• /
• 2019

발전소 관리의 단기 전력 수요에 대한 정확한 예측은 전력 시스템의 안전하고 효율적인 작동을 보장하는데 필수적이다. 따라서 본 연구는 가우스 커널 함수 네트워크 (GKFNs)의 심층 구조를 이용하여 일일 최대 전력 수요를 예측하는 새로운 방법을 제시한다. 제안 된 GKFN의 깊이 구조는 표준 GKFN에 비해 예측 정확도를 향상시킨다. 한국의 일일 최대 전력 수요를 예측하기위한 시뮬레이션은 제안 된 예측 모델이 GKFN 모델, k-NN 및 SVR과 같은 다른 예측 모델에 비해 예측 성능에 이점이 있음을 보여준다. GKFN의 제안된 심층 구조는 시계열 예측 및 회귀 문제의 다양한 문제에 적용될 수 있다.

• International Journal of Computer Science & Network Security
• /
• 제21권1호
• /
• pp.40-48
• /
• 2021

Content-Based Image Retrieval (CBIR) system plays a vital role to retrieve the relevant images as per the user perception from the huge database is a challenging task. Images are represented is to employ a combination of low-level features as per their visual content to form a feature vector. To reduce the search time of a large database while retrieving images, a novel image retrieval technique based on feature dimensionality reduction is being proposed with the exploit of metaheuristic optimization techniques based on Genetic Algorithm (GA), Extended Binary Cuckoo Search (EBCS) and Whale Optimization Algorithm (WOA). Each image in the database is indexed using a feature vector comprising of fuzzified based color histogram descriptor for color and Median binary pattern were derived in the color space from HSI for texture feature variants respectively. Finally, results are being compared in terms of Precision, Recall, F-measure, Accuracy, and error rate with benchmark classification algorithms (Linear discriminant analysis, CatBoost, Extra Trees, Random Forest, Naive Bayes, light gradient boosting, Extreme gradient boosting, k-NN, and Ridge) to validate the efficiency of the proposed approach. Finally, a ranking of the techniques using TOPSIS has been considered choosing the best feature selection technique based on different model parameters.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권5호
• /
• pp.1708-1727
• /
• 2021

In the advent of the twenty-first century, human beings began to closely interact with technology. Today, technology is developing, and as a result, the world wide web (www) has a very important place on the Internet and the significant task is fulfilled by Web services. A lot of Web services are available on the Internet and, therefore, it is difficult to find matching Web services among the available Web services. The recommendation systems can help in fixing this problem. In this paper, our observation was based on the recommended method such as the collaborative filtering (CF) technique which faces some failure from the data sparsity and the cold-start problems. To overcome these problems, we first applied an ontology-based clustering and then the k-nearest neighbor (KNN) algorithm for each separate cluster group that effectively increased the data density using the past user interests. Then, user ratings were predicted based on the model-based approach, such as singular value decomposition (SVD) and the predictions used for the recommendation. The evaluation results showed that our proposed approach has a less prediction error rate with high accuracy after analyzing the existing recommendation methods.

• International Journal of Computer Science & Network Security
• /
• 제21권11호
• /
• pp.1-10
• /
• 2021

Cyberbullying has become a severe issue and brought a powerful impact on the cyber world. Due to the low cost and fast spreading of news, social media has become a tool that helps spread insult, offensive, and hate messages or opinions in a community. Detecting cyberbullying from social media is an intriguing research topic because it is vital for law enforcement agencies to witness how social media broadcast hate messages. Twitter is one of the famous social media and a platform for users to tell stories, give views, express feelings, and even spread news, whether true or false. Hence, it becomes an excellent resource for sentiment analysis. This paper aims to detect cyberbully threats based on Naïve Bayes, support vector machine (SVM), and k-nearest neighbour (k-NN) classifier model. Sentiment analysis will be applied based on people's opinions on social media and distribute polarity to them as positive, neutral, or negative. The accuracy for each classifier will be evaluated.