• Journal of Intelligence and Information Systems
• /
• v.18 no.3
• /
• pp.185-202
• /
• 2012

.Since the value of information has been realized in the information society, the usage and collection of information has become important. A facial expression that contains thousands of information as an artistic painting can be described in thousands of words. Followed by the idea, there has recently been a number of attempts to provide customers and companies with an intelligent service, which enables the perception of human emotions through one's facial expressions. For example, MIT Media Lab, the leading organization in this research area, has developed the human emotion prediction model, and has applied their studies to the commercial business. In the academic area, a number of the conventional methods such as Multiple Regression Analysis (MRA) or Artificial Neural Networks (ANN) have been applied to predict human emotion in prior studies. However, MRA is generally criticized because of its low prediction accuracy. This is inevitable since MRA can only explain the linear relationship between the dependent variables and the independent variable. To mitigate the limitations of MRA, some studies like Jung and Kim (2012) have used ANN as the alternative, and they reported that ANN generated more accurate prediction than the statistical methods like MRA. However, it has also been criticized due to over fitting and the difficulty of the network design (e.g. setting the number of the layers and the number of the nodes in the hidden layers). Under this background, we propose a novel model using Support Vector Regression (SVR) in order to increase the prediction accuracy. SVR is an extensive version of Support Vector Machine (SVM) designated to solve the regression problems. The model produced by SVR only depends on a subset of the training data, because the cost function for building the model ignores any training data that is close (within a threshold ${\varepsilon}$) to the model prediction. Using SVR, we tried to build a model that can measure the level of arousal and valence from the facial features. To validate the usefulness of the proposed model, we collected the data of facial reactions when providing appropriate visual stimulating contents, and extracted the features from the data. Next, the steps of the preprocessing were taken to choose statistically significant variables. In total, 297 cases were used for the experiment. As the comparative models, we also applied MRA and ANN to the same data set. For SVR, we adopted '${\varepsilon}$-insensitive loss function', and 'grid search' technique to find the optimal values of the parameters like C, d, ${\sigma}^2$, and ${\varepsilon}$. In the case of ANN, we adopted a standard three-layer backpropagation network, which has a single hidden layer. The learning rate and momentum rate of ANN were set to 10%, and we used sigmoid function as the transfer function of hidden and output nodes. We performed the experiments repeatedly by varying the number of nodes in the hidden layer to n/2, n, 3n/2, and 2n, where n is the number of the input variables. The stopping condition for ANN was set to 50,000 learning events. And, we used MAE (Mean Absolute Error) as the measure for performance comparison. From the experiment, we found that SVR achieved the highest prediction accuracy for the hold-out data set compared to MRA and ANN. Regardless of the target variables (the level of arousal, or the level of positive / negative valence), SVR showed the best performance for the hold-out data set. ANN also outperformed MRA, however, it showed the considerably lower prediction accuracy than SVR for both target variables. The findings of our research are expected to be useful to the researchers or practitioners who are willing to build the models for recognizing human emotions.

• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.141-154
• /
• 2019

Rapid growth of internet technology and social media is progressing. Data mining technology has evolved to enable unstructured document representations in a variety of applications. Sentiment analysis is an important technology that can distinguish poor or high-quality content through text data of products, and it has proliferated during text mining. Sentiment analysis mainly analyzes people's opinions in text data by assigning predefined data categories as positive and negative. This has been studied in various directions in terms of accuracy from simple rule-based to dictionary-based approaches using predefined labels. In fact, sentiment analysis is one of the most active researches in natural language processing and is widely studied in text mining. When real online reviews aren't available for others, it's not only easy to openly collect information, but it also affects your business. In marketing, real-world information from customers is gathered on websites, not surveys. Depending on whether the website's posts are positive or negative, the customer response is reflected in the sales and tries to identify the information. However, many reviews on a website are not always good, and difficult to identify. The earlier studies in this research area used the reviews data of the Amazon.com shopping mal, but the research data used in the recent studies uses the data for stock market trends, blogs, news articles, weather forecasts, IMDB, and facebook etc. However, the lack of accuracy is recognized because sentiment calculations are changed according to the subject, paragraph, sentiment lexicon direction, and sentence strength. This study aims to classify the polarity analysis of sentiment analysis into positive and negative categories and increase the prediction accuracy of the polarity analysis using the pretrained IMDB review data set. First, the text classification algorithm related to sentiment analysis adopts the popular machine learning algorithms such as NB (naive bayes), SVM (support vector machines), XGboost, RF (random forests), and Gradient Boost as comparative models. Second, deep learning has demonstrated discriminative features that can extract complex features of data. Representative algorithms are CNN (convolution neural networks), RNN (recurrent neural networks), LSTM (long-short term memory). CNN can be used similarly to BoW when processing a sentence in vector format, but does not consider sequential data attributes. RNN can handle well in order because it takes into account the time information of the data, but there is a long-term dependency on memory. To solve the problem of long-term dependence, LSTM is used. For the comparison, CNN and LSTM were chosen as simple deep learning models. In addition to classical machine learning algorithms, CNN, LSTM, and the integrated models were analyzed. Although there are many parameters for the algorithms, we examined the relationship between numerical value and precision to find the optimal combination. And, we tried to figure out how the models work well for sentiment analysis and how these models work. This study proposes integrated CNN and LSTM algorithms to extract the positive and negative features of text analysis. The reasons for mixing these two algorithms are as follows. CNN can extract features for the classification automatically by applying convolution layer and massively parallel processing. LSTM is not capable of highly parallel processing. Like faucets, the LSTM has input, output, and forget gates that can be moved and controlled at a desired time. These gates have the advantage of placing memory blocks on hidden nodes. The memory block of the LSTM may not store all the data, but it can solve the CNN's long-term dependency problem. Furthermore, when LSTM is used in CNN's pooling layer, it has an end-to-end structure, so that spatial and temporal features can be designed simultaneously. In combination with CNN-LSTM, 90.33% accuracy was measured. This is slower than CNN, but faster than LSTM. The presented model was more accurate than other models. In addition, each word embedding layer can be improved when training the kernel step by step. CNN-LSTM can improve the weakness of each model, and there is an advantage of improving the learning by layer using the end-to-end structure of LSTM. Based on these reasons, this study tries to enhance the classification accuracy of movie reviews using the integrated CNN-LSTM model.

• Journal of the Korean association of regional geographers
• /
• v.3 no.2
• /
• pp.163-193
• /
• 1997

Medical services are a fundamental and essential service in all urban areas. The location and accessibility of medical service facilities and institutions are critical to the diagnosis, control and prevention of illness and disease. The purpose of this paper is to present the results of a study on the location of medical facilities in Kwangju and the utilization of these facilities by the inhabitants. The following information is a summary of the findings: (1) Korea, like many countries, is now witnessing an increase in the age of its population as a result of higher living standards and better medical services. Korea is also experiencing a rapid increase in health care costs. To ensure easy access to medical consultation, diagnosis and treatment by individuals, the hierarchical efficient location of medical facilities, low medical costs, equalized medical services, preventive medical care is important. (2) In Korea, the quality of medical services has improved significantly as evident by the increased number of medical facilities and medical personnel. However, there is still a need for not only quantitative improvements but also for a more equitable distribution of and location of medical services. (3) There are 503 medical facilities in Kwangju each with a need to service 2,556 people. This is below the national average of 1,498 inhabitants per facility. The higher locational quotient and satisfactory population per medical facility showed at the civic center. On the other hand, problem regions such as the traditional residential area in Buk-Gu, Moo-deung mountain area and the outer areas of west Kwangju still maintain rural characteristics. (4) In the study area there are 86 general medicine clinics which provide basic medical services. i. e. one clinic per every 14,949 residents. As a basic service, its higher locational quotient showed in the residential area. The lower population concentration per clinic was found in the civic center and in the former town center, Songjeong-dong. In recently build residential areas and in the civic center, the lack of general medicine clinics is not a serious medical services issue because of the surplus of medical specialists in Korea. People are inclined to seek a consultation with a specialist in specific fields rather than consult a general practitioner. As a result of this phenomenon, there are 81 internal medicine facilities. Of these, 32.1% provide services to people who are not referred by a primary care physician but who self-diagnose then choose a medical facility specializing in what they believe to be their health problem. Areas in the city, called dongs, without any internal facilities make up 50% of the total 101 dongs. (5) There are 78 surgical facilities within the area, and there is little difference at the locational appearance from internal medicine facilities. There are also 71 pediatric health clinics for people under 15 years of age in this area, represents one clinic per 5,063 people. On the quantitative aspect, this is a positive situation. Accessibility is the most important facility choice factor, so it should be evenly located in proportion to demander distribution. However, 61% of 102 dongs have no pediatric clinics because of the uneven location. (6) There are 43 obstetrical and gynecological clinics in Kwangju, and the number of residents being served per clinic is 15,063. These services need to be given regularly so it should increase the numbers. There are 37 ENT clinics in the study area with the lower concentration in Dong-gu (32.4%) making no locational differences by dong. There are 23 dermatology clinics with the largest concentration in Dong-Gu. There are 17 ophthalmic clinics concentrated in the residential area because of the primary function of this type of specialization. (7) The use of general medicine clinics, internal medicine clinics, pediatric clinics, ENT clinics by the inhabitants indicate a trend toward primary or routine medical services. Obstetrics and gynecology clinics are used on a regular basis. In choosing a general medicine clinic, internal medicine clinic, pediatric clinic, and a ENT clinic, accessibility is the key factor while choice of a general hospital, surgery clinic, or an obstetrics and gynecology clinic, thes faith and trust in the medical practitioner is the priority consideration. (8) I considered the efficient use of medical facilities in the aspect of locational and management and suggest the following: First, primary care facilities should be evenly distributed in every area. In Kwangju, the number of medical facilities is the lowest among the six largest cities in Korea. Moreover, they are concentrated in Dong-gu and in newly developed areas. The desired number of medical facilities should be within 30 minutes of each person's home. For regional development there is a need to develop a plan to balance, for example, taxes and funds supporting personnel, equipment and facilities. Secondly, medical services should be co-ordinated to ensure consistent, appropriate, quality services. Primary medical facilities should take charge of out-patient activities, and every effort should be made to standardize and equalize equipment and facility resources and to ensure ongoing development and training in the primary services field. A few specialty medical facilities and general hospitals should establish a priority service for incurable and terminally ill patients. (9) The management scheme for the inhabitants' efficient use of medical service is as follows: The first task is to efficiently manage medical facilities and related services. Higher quality of medical services can be accomplished within the rapidly changing medical environment. A network of social, administrative and medical organizations within an area should be established to promote information gathering and sharing strategies to better assist the community. Statistics and trends on the rate or occurrence of diseases, births, deaths, medical and environment conditions of the poor or estranged people should be maintained and monitored. The second task is to increase resources in the area of disease prevention and health promotion. Currently the focus is on the treatment and care of individuals with illness or disease. A strong emphasis should also be placed on promoting prevention of illness and injury within the community through not only public health offices but also via medical service facilities. Home medical care should be established and medical testing centers should be located as an ordinary service level. Also, reduced medical costs for the physically handicapped, cardiac patients, and mentally ill or handicapped patients should be considered.