Analysis of Robust Soft Learning Vector Quantization and an application to Facial Expression Recognition

Efficient approximations of robust soft learning vector quantization for non-vectorial data

Robust soft learning vector quantization (RSLVQ) constitutes a probabilistic extension of learning vector quantization (LVQ) based on a labeled Gaussian mixture model of the data. Training optimizes the likelihood ratio of the model and recovers a variant similar to LVQ2.1 in the limit of small bandwidth. Recently, RSLVQ has been extended to a kernel version, thus opening the way towards more general data structures characterized in terms of a Gram matrix only. While leading to state of the art results, this extension has the drawback that models are no longer sparse, and quadratic training complexity is encountered. In this contribution, we investigate two approximation schemes which lead to sparse models: k-approximations of the prototypes and the Nystrom approximation of the Gram matrix. We investigate the behavior of these approximations in a couple of benchmarks.

For the pattern classification problems the neuro-pattern recognition which is the pattern recognition based on the neural network approach has been paid an attention since it can classify various patterns like human beings. In this paper, we adopt the learning vector quantization (LVQ) method to classify the various kinds of money. The reasons to use the LVQ are that it can process the unsupervised classification and treat many input data with small computational burdens. We will construct the LVQ network to classify the Italian liras. Compared with a conventional pattern matching technique, which has been adopted as a classification method, the proposed method has shown excellent classification results.

A bill money classification has become automated and it is important that the classifier has higher accuracy. Generally, the accuracy of classification is represented as the recognition rate of sample data. However, when classifying bill money, we must evaluate the accuracy more strictly. For pattern recognition a neural network (NN) is studied and its ability is highly estimated. Among NNs a competitive NN has a simple structure and can be analyzed by the relation between the inputs and the outputs more easily than a layered NN based on the backpropagation method. Because of this, we use a competitive NN for bill money classification and use the learning vector quantization (LVQ) method for training the NN. We propose a reliability criterion based on a probability distribution for the classification by the LVQ method. Then we classify US dollars by the LVQ and apply the reliability criterion to the classification. We show that the proposed method of bill money classification has higher accuracy.

The Research aimst to compare backpropagation and Learning Vector Quantization (LVQ) methods in exploring the potential of new students at STMIK PalComTech. Comparisons in this study involve four input variables used which consist of four basic subjects of informatics engineering and information systems (math, basic programming, computer networks and management bases) which then make informatics techniques and information systems as outputs, to get the accuracy level high in this study, the researchers used several variations of parameters which eventually produced the best accuracy of the two methods. From 120 data tested using variations in test data and training data which are then processed using variations in the learning rate parameters and epochs. From the test results obtained the level of accuracy of pattern recognition in the backpropagation method is 99.17% with a learning rate variation of 0.1 and epoch 100, the learning vector quantization method has an accuracy rate of 96.67% with a variation of learning rate 1 and epoch 20 From the results of the comparison the Backpropagation method is superior in terms of accuracy so that it becomes the right method to use in exploring the potential of new students at STMIK PalComTech.

The face is one of the media to identify someone, a human face has a very high level of variability. Many methods have been introduced by researchers and scientists in recognizing one's face, one of the methods introduced is the Feature Extraction of Gray Level Co-Occurrence Matrix (GLCM) and Learning Vector Quantization (LVQ). GLCM feature extraction is used for data extraction/learning process whereas a data analysis process (face recognition, cropping and storing data) the LVQ method is used for the data training process where the data that has been processed in GLCM feature extraction which still has large dimensions are processed to be smaller dimensions. So this test uses data of 190 photos and gets a match of 90%, the authors conclude that the GLCM feature extraction and LVQ method can very well recognize faces contained in the database.

PurposeFacial expression provides abundant information for social interaction, and the analysis and utilization of facial expression data are playing a huge driving role in all areas of society. Facial expression data can reflect people's mental state. In health care, the analysis and processing of facial expression data can promote the improvement of people's health. This paper introduces several important public facial expression databases and describes the process of facial expression recognition. The standard facial expression database FER2013 and CK+ were used as the main training samples. At the same time, the facial expression image data of 16 Chinese children were collected as supplementary samples. With the help of VGG19 and Resnet18 algorithm models of deep convolution neural network, this paper studies and develops an information system for the diagnosis of autism by facial expression data.Design/methodology/approachThe facial expression data of the training samples are based on the standard expression database FER2013 and CK+. FER2013 and CK+ databases are a common facial expression data set, which is suitable for the research of facial expression recognition. On the basis of FER2013 and CK+ facial expression database, this paper uses the machine learning model support vector machine (SVM) and deep convolution neural network model CNN, VGG19 and Resnet18 to complete the facial expression recognition.FindingsIn this study, ten normal children and ten autistic patients were recruited to test the accuracy of the information system and the diagnostic effect of autism. After testing, the accuracy rate of facial expression recognition is 81.4 percent. This information system can easily identify autistic children. The feasibility of recognizing autism through facial expression is verified.Research limitations/implicationsThe CK+ facial expression database contains some adult facial expression images. In order to improve the accuracy of facial expression recognition for children, more facial expression data of children will be collected as training samples. Therefore, the recognition rate of the information system will be further improved.Originality/valueThis research uses facial expression data and the latest artificial intelligence technology, which is advanced in technology. The diagnostic accuracy of autism is higher than that of traditional systems, so this study is innovative. Research topics come from the actual needs of doctors, and the contents and methods of research have been discussed with doctors many times. The system can diagnose autism as early as possible, promote the early treatment and rehabilitation of patients, and then reduce the economic and mental burden of patients. Therefore, this information system has good social benefits and application value.

Research on the Identification of Stroke with MRI Imagery Using the Learning Vector Quantization (LVQ) Method Based on Texture Features has been carried out. This study aims to determine the program's best parameters and the highest accuracy level of the stroke identification program. This research was conducted at Haji Sukolilo Hospital - Surabaya by obtaining 57 images of stroke patients and 15 images of regular patients. The study used the intelligence of stroke, tumor, and standard images to determine each category's image characteristics. After knowing the differences in each class, the next process is digital image processing, followed by feature extraction used is the Gray-Level Co-occurrence matrix (GLCM) with four parameters: contrast, correlation, diversity, and homogeneity. These four parameters are the best input parameters with an intelligence rate of 0.100 with a decrease in intelligence rate of 0.100, so the best accuracy value for training is 74.97%, and test data is 78.60%. Regarding the program's ability to correctly identify 11 data from 14 data tested, the program is feasible to be used as a second opinion.

Deaths of people with breast diseases have reached 40% and are increasing every year. Breast Disease arises from wounds in breast tissue is breast cancer. Wounds of breast can be seen and discriminated the type of wound using Electrical Impedance Spectroscopy(EIS). The results of this EIS data can be used as an initial diagnosis before the doctor carries out treatment. This research tried to classify the types of wounds from breast tissue by using the Learning Vector Quantization (LVQ) method with the Genetic Algorithm (GA) to find out whether the solution provides the expected optimum results. The dataset we used for this study was very small which did not represent the existing class, with 106 data for 6 classes. The results of the comparison between LVQ and GA-LVQ obtained LVQ added by GA has higher accuracy values than LVQ with 73% accuracy and compared to LVQ, GA increased accuracy by ± 50%.

The use of soft computing to classification of some weeds based on video processing

As a social being, humans must do a variety of activities ranging from waking up in the morning to going back to sleep at night. Of the many activities, this research wants to find out how many activities humans do, for example how many times people walk, lie down, and so on in a day. To find out the number of these activities, this study uses Learning Vector Quantization (LVQ) method for recognizing human activities. This study uses 561 features from 1000 data to be used for the training process and 500 data to be used in the testing process. Data with a large number of features can affect the length of the calculation process. Because LVQ uses features as input data, we need a method that can reduce the number of features. One method that can be used is the Particle Swarm Optimization (PSO) method. The training process is carried out using the PSO selection feature with the parameters of the number of particles 30, maximum iterations 30, the value of ω 0.3, Φp of 0.3 and Φg of 0.8. From the training process, gBest and LVQ parameters are obtained with a value of α 0.1, a reduction of α (dec α) 0.5, minimum α 0,0000001 and a maximum of epoch or iteration 5 with a final accuracy of 17%.

The problem of children nutrition isi still a problem in various regions in Indonesia. Poor or poor nutrition of children is influenced by several factors, namely insufficient food intake and infectious diseases. Undernutrition or poor nutrition can be known from the nutritional status assessment obtained from classifying the nutrional status of children. Classification is a part of data mining that is often used to classify data based on certain data or variables. This study aims to compare the classification of the nutritional status of children using data mining with the learning vector quantization (LVQ) and backpropagation methods. Test were carried out using a comparasion ratio of training and testing data, namely 75% and 25%. From the research results, LVQ is superior with an accuracy of 95.12% and backpropagation of 80.49%.

Palm oil is a very important commodity besides oil and gas which also has a fairly good export value. The palm oil produced must be supported by the quality standards set by SNI. The level of maturity when harvesting oil palm fruit greatly influences the quality of Crude Palm Oil (CPO) production, which is crude palm oil that has a reddish color obtained from extraction or from the pressing process of oil palm fruit flesh. In fact, in the field of oil palm fruit harvest, there are still many oil palm fruit that are not ripe enough and can even be said to be still raw, entering the CPO production process. Determination of the maturity level of oil palm fruit is generally determined based on the amount of loose fruit and color, so handling the harvest of oil palm fruit is an important activity in improving the quality of CPO. It is necessary to build a system capable of managing and processing palm fruit images to measure the maturity level of the palm fruit to be produced. To obtain the right level of accuracy, this research uses the Learning Vector Quantization (LVQ) method. LVQ is a method for conducting supervised competitive layer learning. From the results of trials conducted, it is proven that the system can measure very ripe oil palm fruit with HSV values (0.052209; 0.896021; 0.791114).

A new Sensor Validity Monitoring, Verification, and Accommodation (SVMVA) technique based on an artificial neural network is developed for a self-repairing Flight Control System (FCS). For the proposed system, the Learning Vector Quantization (LVQ) method is employed as the on-line, real time learning, monitoring, and estimation tool. In order to conduct a feasibility study, we applied the developed algorithm to a flight vehicle simulator. The simulation results show that the proposed SVMVA with LVQ can instantly detect the failure of physical sensors and accommodate them for more than 30 minutes. By employing this type of analytical sensor redundancy, a flight vehicle can save power, weight, and space, which are required for installing redundant physical sensors.

Facial Expression Recognition (FER) is a critical method for evaluating the emotional states of patients with mental disorders, playing a significant role in treatment monitoring. However, due to privacy constraints, facial expression data from patients with mental disorders is severely limited. Additionally, the more complex inter-class and intra-class similarities compared to healthy individuals make accurate recognition of facial expressions challenging. Therefore, we propose a Voluntary Facial Expression Mimicry (VFEM) experiment, which collected facial expression data from schizophrenia, depression, and anxiety. This experiment establishes the first dataset designed for facial expression recognition tasks exclusively composed of patients with mental disorders. Simultaneously, based on VFEM, we propose a Vision Transformer FER model tailored for Complex mental disorder patients (CmdVIT). CmdVIT integrates crucial facial expression features through both explicit and implicit mechanisms, including explicit visual center positional encoding and implicit sparse attention center loss function. These two key components enhance positional information and minimize the facial feature space distance between conventional attention and critical attention, effectively suppressing inter-class and intra-class similarities. In various FER tasks for different mental disorders in VFEM, CmdVIT achieves more competitive performance compared to contemporary benchmark models. Our works are available at https://github.com/yjy-97/CmdVIT.