Earticle

In this paper, it is aim to implement a wheelchair monitoring system that provides users with customized medical services easily in everyday life, together with mobility guarantee, which is the most basic requirement of the elderly and disabled persons with physical disabilities. The case-based intelligent wheelchair monitoring system proposed in this study is based on a case-based k-NN algorithm, which implements a system for constructing and inferring examples of various biometric and environmental information of wheelchair users as a knowledge database and a monitoring interface for wheelchair users. In order to confirm the usefulness of the case-based k-NN algorithm, the SVM algorithm showed an average accuracy of 84.2% and the average accuracy of the proposed case-based k-NN algorithm was 86.2% And showed higher performance in terms of accuracy. The system implemented in this paper has the advantage of measuring biometric information and data communication regardless of time and place and it can provide customized service of wheelchair user through user friendly interface.

Cybersecurity has become a key component of national strategy in recent years. Traditional cybersecurity technology such as network traffic-based intrusion detection and threatening intelligence sensing are designed to focus on the traffic features of network, which are no doubt effective defense technologies. However, these methods required decent amount of domain knowledge and massive training data, which brought a significant barrier for cybersecurity research. In this work, we propose a novel residual autoencoder and support vector machine combined approach (RAE-SVM) for webpage tamper-resistant detection using high-level webpage image features. This method, inspired by the Chinese proverb "mend the fold after the sheep have been stolen." The web crawler technology is used for website screenshot within limited domain names, and input them into autoencoder architecture and SVM for feature extraction and invaded webpage detection. This method combines the advantages of deep residual network, convolutional autoencoder and SVM, and the interdisciplinary intersection between cybersecurity and high-level image features. The experimental results demonstrate that the proposed method achieves an accuracy of 95%, significantly higher than other models, which proves the validity of the proposed method.

The present research article focused on the factual findings of the potential usage of the combinational Feed-Forward Back Propagation Neural Network as a judgment making for lung cancer. In this context, Support Vector Machine is integrated with Feed-Forward Back Propagation Neural Network to create a hybrid algorithm that further helps in reducing the computation complexity of the classification. A set of 500 images are utilized in which 75% data is used for the training purpose and the rest 25% is used to achieve the classification. In the view of forgoing, a three-block mechanism is proposed for the classification in which the first block preprocesses the dataset, the second block extracts the features via the SURF technique followed by the optimization using Genetic Algorithm and the terminal block is for the classification via FFBPNN. The hybrid classification algorithm is named as Kernel Attribute Selected Classifier and the overall classification accuracy of the proposed algorithm is 98.08%. Herein, the objective of the study is to enhance the classification accuracy by applying a hybrid classification algorithm.

For any pattern matching based algorithm in WLAN environment, the characteristics of signal to noise ratio(SNR) to multiple access points(APs) are utilized to establish database in the training phase, and in the estimation phase, the actual two dimensional coordinates of mobile unit(MU) are estimated based on the comparison between the new recorded SNR and fingerprints stored in database. The system that uses the artificial neural network(ANN) falls in a local minima when it learns many nonlinear data, and its classification accuracy ratio becomes low. To make up for this risk, the SVM/ANN hybrid algorithm is proposed in this paper. The proposed algorithm is the method that ANN learns selectively after clustering the SNR data by SVM, then more improved performance estimation can be obtained than using ANN only and The proposed algorithm can make the higher classification accuracy by decreasing the nonlinearity of the massive data during the training procedure. Experimental results indicate that the proposed SVM/ANN hybrid algorithm generally outperforms ANN algorithm.

본 연구의 목적은 한국의료패널 2012년 자료를 이 용하여 고지혈증 유병에 영향을 미치는 변수를 확인 하고 이를 예측하는 분류모형을 개발하는데 있다. 분류모형에 투입되는 변수 선정을 위해 로지스틱 회 귀분석, 의사결정트리 c4.5, 유전자 알고리즘을 각 각 적용하여 선정하였다. 고지혈증 유병을 예측하기 위해 SVM과 meta learning 알고리즘을 이용하였다. 먼저 SVM의 경우 변수를 6개만 투입하였을 때 정확도가 가장 높았으 며, meta learning의 경우 메타분류기를 SVM으로 하 여 변수 6개를 투입한 경우가 가장 높았다. 본 연구는 기존 연구에서 많이 다루지 않은 고지 혈증을 예측하는 모형을 개발했다는 점과 여러 변수 기법을 적용하여 모델 정확도를 기여하였다. 그러나 메타러닝 성과가 크게 향상되지 않은 점은 본 연구 의 한계이자 추후 관련 연구에서 보완되어야 할 부분이다.

본 논문에서는 사용자의 EEG(Electroencephalogram)신호를 측정하여 SVM(Support Vector Machine) 알 고리즘을 이용하여 EEG 신호룰 분류하고 신호의 정확도를 측정하였다. 사용자의 EEG 신호를 측정하기 위해 남·여를 구분하여 실험을 진행하였으며, EEG 신호 측정은 단채널 EEG 디바이스를 이용하였다. EEG 디바이스를 이용하여 사용 자의 EEG 신호를 측정한 결과는 R을 이용하여 분석하였다. 또한 SVM의 분류 성능이 최고가 되는 특정 벡터의 조합을 적용시켜 EEG 측정 실험 데이터를 80:20(훈련 데이터: 테스트 데이터) 비율로 예측해 본 결과 인식률 93.2% 의 예측 정확도를 보였다. 본 논문에서는 사용자의 EEG 신호를 약 93.2% 정도로 인식할 수 있었으며, SVM 알고리즘의 간단한 선형 분류만으로 수행이 가능하다는 점은 EEG 신호를 이용하여 생체인증에 다양하게 활용될 수 있음을 제시하였다.

In this paper, we measured the user's EEG signal and classified the EEG signal using the Support Vector Machine algorithm and measured the accuracy of the signal. An experiment was conducted to measure the user's EEG signals by separating men and women, and a single channel EEG device was used for EEG signal measurements. The results of measuring users' EEG signals using EEG devices were analyzed using R. In addition, data in the study was predicted using a 80:20 ratio between training data and test data by applying a combination of specific vectors with the highest classifying performance of the SVM, and thus the predicted accuracy of 93.2% of the recognition rate. This paper suggested that the user's EEG signal could be recognized at about 93.2 percent, and that it can be performed only by simple linear classification of the SVM algorithm, which can be used variously for biometrics using EEG signals.

Recently, due to the aging of workers and the weakening of the labor base in the automobile industry, research on quality inspection methods through ICT(Information and Communication Technology) convergence is being actively conducted. A lot of research has already been done on the development of an automated system for quality inspection in the manufacturing process using image processing. However, there is a limit to detecting defects occurring in the automotive sunroof sealer application process, which is the subject of this study, only by image processing using a general camera. To solve this problem, this paper proposes a system construction method that collects image information using a infrared thermal imaging camera for the sunroof sealer application process and detects possible product defects based on the SVM(Support Vector Machine) algorithm. The proposed system construction method was actually tested and applied to auto parts makers equipped with the sunroof sealer application process, and as a result, the superiority, reliability, and field applicability of the proposed method were proven.

도로의 결빙, 적설, 젖음 등 기상상황 및 표면 상태에 의한 안전사고 발생은 지속적으로 발생하고 있는 상황이다. 이 는 운전자 본인의 부주의 및 안전 운전의식 부족 등 개인의 역량에 기인하는 부문도 있지만, 도로관리 주체(정부 및 공 공 등)의 도로 상태 정보제공 미흡으로 인한 경우도 있어 이와 관련된 연구의 필요성이 대두되고 있는 추세이다. 본 연 구는 카메라(Stereo camera)의 영상 정보를 수집하여, 편광계수 및 웨이블릿 변환(Wavelet transform) 등을 통해 기존의 단 일 차원 분류알고리즘과 달리 다차원 분석이 가능한 SVM 분류기법을 활용하여 노면상태 판별 알고리즘을 개발하였으 며, 실제 도로상에서 4개의 상태(마른노면, 젖은노면, 적설노면, 결빙노면)에 대한 검지 인식 성공률을 실험 및 분석하였 다.

Road's accidents caused by Ice, snow, Wet of roads surface conditions and weather conditions situations that are constantly occurring. That is, driver's negligence and safe driving ability of individuals due to lack of awareness, and Road management main agent(the government and the public, etc.) due to road conditions, if there is insufficient information. So Related research needs is a trend that is required. In this study, gather Camera(Stereo camera)'s image data, and analysis polarization coefficients and wavelet transform. And unlike traditional single-dimensional classification algorithms as multi-dimensional analysis by using SVM classification techniques, develop an algorithm to determine road conditions. Four on the road conditions (dry, wet, snow, ice) recognition success rate for the detection and analysis of experiments.

It cannot avoid the noise interference in image processing, whether it is image generation, or image transmission, among them, the most typical noise is salt and pepper noise and Gaussian noise. The salt and pepper noise will cause the image showing the random distribution of noise points, thus greatly reduce the image quality. The Gaussian noise affects the input, collection and output of the image processing. Gaussian noise will make the image blurred. Therefore, the image de-noising plays a very important role in image processing. It has direct influence on image segmentation, feature extraction and image recognition. As is known to all, the support vector machine has the advantages of solving the problem of nonlinear, high dimension and local minimum points. In this article, we use this advantage to propose an image de-noising method which is based on it. The method uses support vector regression to construct the filter for image de-noising. The feature extraction and training samples are designed to suppress different types of noise. Firstly, we use the noise pixel as the center of the 5*5 window, and generate the input vector of SVM from row to column. Secondly, we set the output of the support vector filter as an image that is not contaminated by noise. At this point, we get the training samples of SVM filter. In addition, the parameter selection of support vector machine has a great influence on the result of image de-noising. Therefore, the particle swarm optimization algorithm is proposed in this article to optimize the parameters of SVM. Finally, we adding the simulated salt and pepper noise and Gaussian noise in the original Lena image, and using several methods to carry out the de-noising experiment. From the experimental results we can see that the de-noising effect of filtering algorithm of this paper is very good for the two kinds of noise. It can effectively remove the noise, and better maintain the details and the color of the image.

In recent years, cloud computing is becoming popular in the field of information, however, the development of cloud computing have to face the problem of cloud security. Intrusion Deletion System (IDS) is one of the possible solutions to the problem of cloud security, but the correct rate of general application of the IDS is not very satisfactory, for this purpose we propose a density-based binary Support Vector Machine (SVM) method (D-BSVM). Its main idea is based on the density of each class in the data set, and gets a binary sequence of training, according to this sequence obtained binary SVM training model to predict the behavior of the system. Further, the method for calculating the density is the paralleled, thereby improving efficiency of overall system. Finally, we present experimental results, and by contrast our approach can improve the accuracy and detection rate of IDS.

In Recent years the way we analyze the breast cancer has changed dramatically. Breast cancer is the most common and complex disease diagnosed among women. There are several subtypes of breast cancer and many options are there for the treatment. The most important is to educate the patients. As the research continues to expand, the understanding of the disease and its current treatments types, the researchers are constantly being updated with new researching techniques. Breast cancer survival rates have been increased with the use of new advanced treatments, largely due to the factors such as earlier detection, a new personalized approach to treatment and a better understanding of the disease. Many machine learning classification models have been adopted and modified to diagnose the breast cancer disease. In order to enhance the performance of classification model, our research proposes a model using A Hybrid Modified K-Means Clustering with Modified SVM (Support Vector Machine) Machine learning algorithm to create a new method which can highly improve the performance and prediction. The proposed Machine Learning model is to improve the performance of machine learning classifier. The Proposed Model rectifies the irregularity in the dataset and they can create a new high quality dataset with high accuracy performance and prediction. The recognized datasets Wisconsin Diagnostic Breast Cancer (WDBC) Dataset have been used to perform our research. Using the Wisconsin Diagnostic Breast Cancer (WDBC) Dataset, We have created our Model that can help to diagnose the patients and predict the probability of the breast cancer. A few machine learning classifiers will be explored in this research and compared with our Proposed Model “A Hybrid Modified K-Means with Modified SVM Machine Learning Algorithm to Enhance the Cancer Prediction” to implement and evaluated. Our research results show that our Proposed Model has a significant performance compared to other previous research and with high accuracy level of 99% which will enhance the Cancer Prediction.

This paper puts forward text filtering system based on SVM algorithm regarding to the problem that bad and sensitive information of user tag that may exist in the collaborative geographic information plotting system. Then further improvement has been made towards the TF-IDF for feature extraction and thus achieved the function that automatically blocks the bad and sensitive information marked by users.

This paper proposes an effective ensemble classifier, named PCAenSVM, which consists of ten weak Support Vector Machine classifiers based on different Principal Component Analysis thresholds. Those ten base Support Vector Machine classifiers are made up to fulfill classification tasks using Majority Voting strategy. Experiments are made on four UCI data sets and a data set from the Uppsala University to evaluate the performances of PCAenSVM. The results of PCAenSVM are compared with that of LibSVM and EnsembleSVM. Experimental results show that PCAenSVM has better classification accuracy than other two algorithms. Moreover, PCAenSVM has the same confidence level with the LibSVM, and its confidences of accuracy and sensitivity on those five data sets outperform that of the EnsembleSVM.

According to the merits and shortcomings of the traditional gridsearch algorithm in parameters optimization of support vector machine (SVM), an improved grid search algorithm is proposed. Dichotomous search algorithm is used to reduce target searching range. First, searching range is determined roughly, and a set of parameters are obtained. Then fine search is applied in reduction the range for searching, and searching the optimum parameters.Three kinds of famous tumor gene data set are used in the comparison experiments to validate the classification accuracy of principal component analysis (PCA)-SVM and kernel principal component analysis (KPCA)-SVM. Experiment results and data analysis shows that, comparing with traditional gridsearch algorithm, the proposed method has higher classification accuracy and less search time.

Because the properties of data are becoming more and more complex, the traditional data classification is difficult to realize the data classification according to the complexity characteristic of the data. Support vector machine is a machine learning method with the good generalization ability and prediction accuracy. So an improved ant colony optimization(ACO) algorithm is introduced into the support vector machine(SVM) model in order to propose a new data classification(ERURACO-SVM) method. In the ERURACO-SVM method, the pheromone evaporation rate strategy and pheromone updating rule are introduced into the ACO algorithm to improve the optimization performance of the ACO algorithm, and then the parallelism, global optimization ability, positive feedback mechanism and strong robustness of the improved ACO algorithm is used to find the optimal combination of parameters of the SVM model in order to improve the learning performance and generalization ability of the SVM model and establish the optimal data classification model. Finally, the experimental data from the UCI machine learning database are selected to validate the classification correctness of the ERURACO-SVM method. The experiment results show that the improved ACO(ERURACO) algorithm has better optimization performance for parameters selection of the SVM model and the ERURACO-SVM method has higher classification accuracy and better generalization ability.

Due to the problem of low imaging accuracy and slow imaging speed when applying SVM image reconstruction algorithm in ECT system to dealing with a large amount of sample data set, the method of combining feature dimension reduction with SVM algorithm is proposed. This method classifies the sample data by using the way of clustering and extracts the feature parameter, finds out the connection between each sample and the feature, and deals the sample data with dimension reduction, thus finally getting the high-quality training sample. Then it trains the simplified sample data by applying SVM algorithm and obtains decision function, then the decision function is used to predict and image. The experimental results of image reconstruction show that this method greatly reduces the running time and improves the accuracy of imaging compared to using the SVM algorithm alone.

The performance of video automatic classification algorithm depends largely on the extraction of video features and selection of classification algorithm. From the perspective of video contents and video style type, the paper presents a new feature representation scheme, i.e. MPEG-7 visual description sub-combination model, a new method based on support vector machine (SVM) to solve problems with existing algorithms, by analyzing visual differences between five types of videos. Also we improve the classifier decision scheme and then propose the secondary prediction mechanism based on SVM 1-1 approach, improving the accuracy of SVM multi-classification method. The experimental results indicate that the proposed method manifests differences of different videos about feature selection, enhances the discrimination ability of videos pending for classification and increases the effectiveness of SVM multi-video classification.

In the process of ventricular premature beat (PVC) and normal sinus rhythm (NSR) identification base on electrocardiogram (ECG), there exists problems like negative effect from ECG rhythm and low recognition rate. This paper proposes the electrocardiogram PVC classification algorithm based on support vector machine (SVM) and wavelet algorithm. The algorithm uses the wavelet transform to analyze ECG beating model, which is not influenced by the change of ECG waveform. The two feature sets respectively compose of statistical parameters of the wavelet coefficients and the selected wavelet coefficients. PVC and NSR are analyzed by using SVM. The experimental results show that this method improves the recognition rate of ECG.

As more and more insight into the human brain, EEG is not only for application, processing and analysis of EEG in science and engineering field, it will also be very important in the physical, psychological and pathological studies in humans. The EEG brain - machine interface technologies to achieve the human brain and the computer or other human interface devices to communicate and control, it can provide a special kind of information exchange and live entertainment, is also disabled and a new way of control. In this paper, the collection of information preprocessing electroencephalogram (EEG) signals is proposed wavelet packet transform feature extraction method, using SVM classifier, classification based on the operation mode to achieve recognition of the EEG signal. For different individuals turn, the next turn, show fist, fist four kinds of hand motion recognition experiments show that the average recognition rate of over 80%, significantly better than the other methods to identify results.