• Proceedings of the Korea Society for Simulation Conference
• /
• 2001.10a
• /
• pp.321-324
• /
• 2001

The robot soccer simulation game is a dynamic multi-agent environment. In this paper we suggest a new reinforcement learning approach to each agent's dynamic positioning in such dynamic environment. Reinforcement Beaming is the machine learning in which an agent learns from indirect, delayed reward an optimal policy to choose sequences of actions that produce the greatest cumulative reward. Therefore the reinforcement loaming is different from supervised teaming in the sense that there is no presentation of input-output pairs as training examples. Furthermore, model-free reinforcement loaming algorithms like Q-learning do not require defining or loaming any models of the surrounding environment. Nevertheless it can learn the optimal policy if the agent can visit every state-action pair infinitely. However, the biggest problem of monolithic reinforcement learning is that its straightforward applications do not successfully scale up to more complex environments due to the intractable large space of states. In order to address this problem, we suggest Adaptive Mediation-based Modular Q-Learning(AMMQL) as an improvement of the existing Modular Q-Learning(MQL). While simple modular Q-learning combines the results from each learning module in a fixed way, AMMQL combines them in a more flexible way by assigning different weight to each module according to its contribution to rewards. Therefore in addition to resolving the problem of large state space effectively, AMMQL can show higher adaptability to environmental changes than pure MQL. This paper introduces the concept of AMMQL and presents details of its application into dynamic positioning of robot soccer agents.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.4
• /
• pp.19-27
• /
• 2022

In general, the performance of ML(Machine Learning) application is determined by various factors such as the type of ML model, the size of model (number of parameters), hyperparameters setting during the training, and training data. In particular, the recognition accuracy of ML may be deteriorated or experienced overfitting problem if the amount of dada used for training is insufficient. Existing studies focusing on image recognition have widely used open datasets for training and evaluating the proposed ML models. However, for specific applications where the sensor used, the target of recognition, and the recognition situation are different, it is necessary to build the dataset manually. In this case, the performance of ML largely depends on the quantity and quality of the data. In this paper, training data used for motion recognition application is augmented using the kernel density estimation algorithm which is a type of non-parametric estimation method. We then compare and analyze the recognition accuracy of a ML application by varying the number of original data, kernel types and augmentation rate used for data augmentation. Finally experimental results show that the recognition accuracy is improved by up to 14.31% when using the narrow bandwidth Tophat kernel.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.4
• /
• pp.159-164
• /
• 2023

Solar energy harvesting IoT devices prioritize maximizing the utilization of collected energy due to the periodic recharging nature of solar energy, rather than minimizing energy consumption. Meanwhile, research on edge AI, which performs machine learning near the data source instead of the cloud, is actively conducted for reasons such as data confidentiality and privacy, response time, and cost. One such research area involves performing various audio AI applications using audio data collected from multiple IoT devices in an IoT edge computing environment. However, in most studies, IoT devices only perform sensing data transmission to the edge server, and all processes, including data preprocessing, are performed on the edge server. In this case, it not only leads to overload issues on the edge server but also causes network congestion by transmitting unnecessary data for learning. On the other way, if data preprocessing is delegated to each IoT device to address this issue, it leads to another problem of increased blackout time due to energy shortages in the devices. In this paper, we aim to alleviate the problem of increased blackout time in devices while mitigating issues in server-centric edge AI environments by determining where the data preprocessed based on the energy state of each IoT device. In the proposed method, IoT devices only perform the preprocessing process, which includes sound discrimination and noise removal, and transmit to the server if there is more energy available than the energy threshold required for the basic operation of the device.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.4
• /
• pp.169-176
• /
• 2015

Recently smartphone market is rapidly growing and application market has also grown significantly. Mobile applications have been provided in various forms, such as education, game, SNS, weather and news. And It is distributed through a variety of distribution channels. Malicious applications deployed with malicious objectives are growing as well as applications that can be useful in everyday life well. In this study, Events from a malicious application that is provided by the normal application deployment and Android MalGenome Project through the open market were extracted and analyzed. And using the results, We create a model to determine whether the application is malicious. Finally, model was evaluated using a variety of statistical method.

• Journal of Internet Computing and Services
• /
• v.16 no.4
• /
• pp.39-50
• /
• 2015

In information retrieval process through search engine, some users want to retrieve several documents that are corresponding with specific time period situation. For example, if user wants to search a document that contains the situation before 'Japanese invasions of Korea era', he may use the keyword 'Japanese invasions of Korea' by using searching query. Then, search engine gives all of documents about 'Japanese invasions of Korea' disregarding time period in order. It makes user to do an additional work. In addition, a large percentage of cases which is related to historical documents have different time period between generation date of a document and record time of contents. If time period in document contents can be extracted, it may facilitate effective information for retrieval and various applications. Consequently, we pursue a research extracting time period of Joseon era's historical documents by using historic literature for Joseon era in order to deduct the time period corresponding with document content in this paper. We define historical objects based on historic literature that was collected from web and confirm a possibility of extracting time period of web document by machine learning techniques. In addition to the machine learning techniques, we propose and apply the similarity filtering based on the comparison between the historical objects. Finally, we'll evaluate the result of temporal indexing accuracy and improvement.

• ETRI Journal
• /
• v.32 no.5
• /
• pp.784-794
• /
• 2010

Automatic facial expression recognition has many potential applications in different areas of human computer interaction. However, they are not yet fully realized due to the lack of an effective facial feature descriptor. In this paper, we present a new appearance-based feature descriptor, the local directional pattern (LDP), to represent facial geometry and analyze its performance in expression recognition. An LDP feature is obtained by computing the edge response values in 8 directions at each pixel and encoding them into an 8 bit binary number using the relative strength of these edge responses. The LDP descriptor, a distribution of LDP codes within an image or image patch, is used to describe each expression image. The effectiveness of dimensionality reduction techniques, such as principal component analysis and AdaBoost, is also analyzed in terms of computational cost saving and classification accuracy. Two well-known machine learning methods, template matching and support vector machine, are used for classification using the Cohn-Kanade and Japanese female facial expression databases. Better classification accuracy shows the superiority of LDP descriptor against other appearance-based feature descriptors.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.21 no.6
• /
• pp.161-169
• /
• 2011

Recent intelligent video surveillance system asks for development of more advanced technology for analysis and recognition of video data. Especially, machine learning algorithm such as Support Vector Machine (SVM) is used in order to recognize objects in video. Because SVM training demands massive amount of computation, parallel processing technique is necessary to reduce the execution time effectively. In this paper, we propose a parallel processing method of SVM training with a multi-core processor. The results of parallel SVM on a 4-core processor show that our proposed method can reduce the execution time of the sequential training by a factor of 2.5.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.751-770
• /
• 2019

Action recognition is an essential task in computer vision due to the variety of prospective applications, such as security surveillance, machine learning, and human-computer interaction. The availability of more video data than ever before and the lofty performance of deep convolutional neural networks also make it essential for action recognition in video. Unfortunately, limited crafted video features and the scarcity of benchmark datasets make it challenging to address the multi-person action recognition task in video data. In this work, we propose a deep convolutional neural network-based Effective Hybrid Learning (EHL) framework for two-person interaction classification in video data. Our approach exploits a pre-trained network model (the VGG16 from the University of Oxford Visual Geometry Group) and extends the Faster R-CNN (region-based convolutional neural network a state-of-the-art detector for image classification). We broaden a semi-supervised learning method combined with an active learning method to improve overall performance. Numerous types of two-person interactions exist in the real world, which makes this a challenging task. In our experiment, we consider a limited number of actions, such as hugging, fighting, linking arms, talking, and kidnapping in two environment such simple and complex. We show that our trained model with an active semi-supervised learning architecture gradually improves the performance. In a simple environment using an Intelligent Technology Laboratory (ITLab) dataset from Inha University, performance increased to 95.6% accuracy, and in a complex environment, performance reached 81% accuracy. Our method reduces data-labeling time, compared to supervised learning methods, for the ITLab dataset. We also conduct extensive experiment on Human Action Recognition benchmarks such as UT-Interaction dataset, HMDB51 dataset and obtain better performance than state-of-the-art approaches.

• Journal of KIISE:Software and Applications
• /
• v.34 no.9
• /
• pp.804-816
• /
• 2007

Sample training data for machine learning often contain irrelevant information or redundant concept. It is also the case that the original data may include noise. If the information collected for constructing learning model is not reliable, it is difficult to obtain accurate information. So the system attempts to find relations or regulations between features and categories in the teaming phase. The feature selection is to remove irrelevant or redundant information before constructing teaming model. for improving its performance. Existing feature selection methods assume that the distribution of documents is balanced in terms of the number of documents for each class and the length of each document. In practice, however, it is difficult not only to prepare a set of documents with almost equal length, but also to define a number of classes with fixed number of document elements. In this paper, we propose a new feature selection method that considers the impurities among the words and unbalanced distribution of documents in categories. We could obtain feature candidates using the word impurity and eventually select the features through unbalanced distribution of documents. We demonstrate that our method performs better than other existing methods via some experiments.

• Journal of Advanced Navigation Technology
• /
• v.24 no.2
• /
• pp.155-162
• /
• 2020

Recently, with the development of computer vision and deep learning technology, research on human action recognition has been actively conducted for video analysis, video surveillance, interactive multimedia, and human machine interaction applications. Diverse techniques have been introduced for human action understanding and classification by many researchers using RGB image, depth image, skeleton and inertial data. However, skeleton-based action discrimination is still a challenging research topic for human machine-interaction. In this paper, we propose an end-to-end skeleton joints mapping of action for generating spatio-temporal image so-called dynamic image. Then, an efficient deep convolution neural network is devised to perform the classification among the action classes. We use publicly accessible UTD-MHAD skeleton dataset for evaluating the performance of the proposed method. As a result of the experiment, the proposed system shows better performance than the existing methods with high accuracy of 97.45%.