• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.85-110
• /
• 2018

A chatbot is an interactive assistant that utilizes many communication modes: voice, images, video, or text. It is an artificial intelligence-based application that responds to users' needs or solves problems during user-friendly conversation. However, the current version of the chatbot is focused on understanding and performing tasks requested by the user; its ability to generate personalized conversation suitable for relationship-building is limited. Recognizing the need to build a relationship and making suitable conversation is more important for social chatbots who require social skills similar to those of problem-solving chatbots like the intelligent personal assistant. The purpose of this study is to propose a text analysis method that evaluates relationships between chatbots and users based on content input by the user and adapted to the communication situation, enabling the chatbot to conduct suitable conversations. To evaluate the performance of this method, we examined learning and verified the results using actual SNS conversation records. The results of the analysis will aid in implementation of the social chatbot, as this method yields excellent results even when the private profile information of the user is excluded for privacy reasons.

• International Journal of Advanced Culture Technology
• /
• v.6 no.4
• /
• pp.275-283
• /
• 2018

Cancer show distinct pattern of gene expression when it is compared to normal. This difference results malignant characteristic of cancer. Many cancer drugs are targeting this difference so that it can selectively kill cancer cells. One of the recent demand for personalized treating cancer is retrieving normal tissue from a patient so that the gene expression difference between cancer and normal be assessed. However, in most clinical situation it is hard to retrieve normal tissue from a patient. This is because biopsy of normal tissues may cause damage to the organ function or a risk of infection or side effect what a patient to take. Thus, there is a challenge to estimate normal cell's gene expression where cancers are originated from without taking additional biopsy. In this paper, we propose in-silico based prediction of normal cell's gene expression from gene expression data of a tumor sample. We call this challenge as reverting the cancer into normal. We divided this challenge into two parts. The first part is making a generator that is able to fool a pretrained discriminator. Pretrained discriminator is from the training of public data (9,601 cancers, 7,240 normals) which shows 0.997 of accuracy to discriminate if a given gene expression pattern is cancer or normal. Deceiving this pretrained discriminator means our method is capable of generating very normal-like gene expression data. The second part of the challenge is to address whether generated normal is similar to true reverse form of the input cancer data. We used, cycle-consistent adversarial networks to approach our challenges, since this network is capable of translating one domain to the other while maintaining original domain's feature and at the same time adding the new domain's feature. We evaluated that, if we put cancer data into a cycle-consistent adversarial network, it could retain most of the information from the input (cancer) and at the same time change the data into normal. We also evaluated if this generated gene expression of normal tissue would be the biological reverse form of the gene expression of cancer used as an input.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.9
• /
• pp.1224-1230
• /
• 2020

Since the spread of smart phones, interest in wearable devices has increased and diversified, and is closely related to the lives of users, and has been used as a method for providing personalized services. In this paper, we propose a method to detect the user's behavior by applying information from a 3-axis acceleration sensor and a 3-axis gyro sensor embedded in a smartphone to a convolutional neural network. Human behavior differs according to the size and range of motion, starting and ending time, including the duration of the signal data constituting the motion. Therefore, there is a performance problem for accuracy when applied to a convolutional neural network as it is. Therefore, we proposed a Time-Division Feature Fusion Convolutional Neural Network (TDFFCNN) that learns the characteristics of the sensor data segmented over time. The proposed method outperformed other classifiers such as SVM, IBk, convolutional neural network, and long-term memory circulatory neural network.

• Journal of Broadcast Engineering
• /
• v.27 no.5
• /
• pp.738-750
• /
• 2022

In this study, we reviewed and discussed whether auditory stimuli with short length can evoke emotion-related neurological responses. The findings implicate that if personalized sound tracks are provided to XR users based on machine learning or probability network models, user experiences in XR environment can be enhanced. We also investigated that the arousal-relaxed factor evoked by short auditory sound can make distinct patterns in functional connectivity characterized from background EEG signals. We found that coherence in the right hemisphere increases in sound-evoked arousal state, and vice versa in relaxed state. Our findings can be practically utilized in developing XR sound bio-feedback system which can provide preference sound to users for highly immersive XR experiences.

• Journal of The Korean Association of Information Education
• /
• v.25 no.6
• /
• pp.927-934
• /
• 2021

AI(Artificial intelligence) is gradually taking up a large part of our lives, and the pace of AI development is accelerating. It is called ACT that develop students' computational thinking in the way artificial intelligence learns. Among ACTs, pattern recognition is an essential factor in efficiently solving problems. Pattern analysis is part of the pattern recognition process. In fact, Netflix's personalized movie recommendation service and what it named Covid-19 after repeated symptoms are all the results of pattern analysis. While the importance of ACT, including pattern recognition, is highlighted, software education for kindergarten and elementary school lower grades is much insufficient compared to foreign countries. Therefore, this study aims to design and develop textbooks for the development of artificial intelligence-based computational thinking through pattern analysis for kindergarten students.

• Smart Media Journal
• /
• v.12 no.4
• /
• pp.27-40
• /
• 2023

Many researchers have investigated ways to enhance recommender systems by integrating heterogeneous data to address the data sparsity problem. However, only a few studies have successfully integrated heterogeneous data using knowledge graph. Additionally, most of the knowledge graphs built in these studies only incorporate explicit relationships between entities and lack additional information. Therefore, we propose a method for expanding knowledge graphs by using deep learning to model latent relationships between heterogeneous data from multiple knowledge bases. Our extended knowledge graph enhances the quality of entity features and ultimately increases the accuracy of predicted user preferences. Experiments using real music data demonstrate that the expanded knowledge graph leads to an increase in recommendation accuracy when compared to the original knowledge graph.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.3
• /
• pp.469-475
• /
• 2022

To train the model of the deep learning-based single-speaker TTS system, a speech DB of tens of hours and a lot of training time are required. This is an inefficient method in terms of time and cost to train multi-speaker or personalized TTS models. The voice cloning method uses a speaker encoder model to make the TTS model of a new speaker. Through the trained speaker encoder model, a speaker embedding vector representing the timbre of the new speaker is created from the small speech data of the new speaker that is not used for training. In this paper, we propose a multi-speaker TTS system to which voice cloning is applied. The proposed TTS system consists of a speaker encoder, synthesizer and vocoder. The speaker encoder applies the d-vector technique used in the speaker recognition field. The timbre of the new speaker is expressed by adding the d-vector derived from the trained speaker encoder as an input to the synthesizer. It can be seen that the performance of the proposed TTS system is excellent from the experimental results derived by the MOS and timbre similarity listening tests.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.281-283
• /
• 2021

The representative companies mentioned in the recommendation service in the domestic OTT(Over-the-top media service) market are YouTube and Netflix. YouTube, through various methods, started personalized recommendations in earnest by introducing an algorithm to machine learning that records and uses users' viewing time from 2016. Netflix categorizes users by collecting information such as the user's selected video, viewing time zone, and video viewing device, and groups people with similar viewing patterns into the same group. It records and uses the information collected from the user and the tag information attached to the video. In this paper, we propose a method to improve video media recommendation by automatically generating metadata of video media that was written by hand.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.277-280
• /
• 2021

Recently as various contents are mass produced based on high accessibility, the media contents market is more active. Users want to find content that suits their taste, and each platform is competing for personalized recommendations for content. For an efficient recommendation system, high-quality metadata is required. Existing platforms take a method in which the user directly inputs the metadata of an image. This will waste time and money processing large amounts of data. In this paper, for media hyperpersonalization recommendation, keyframes are extracted based on the YCrCb color model of the video based on movie trailers, movie genres are distinguished through supervised learning of artificial intelligence and In the future, we would like to propose a utilization plan for generating metadata.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.4
• /
• pp.309-314
• /
• 2023

This study examines the development and limitations of current artificial intelligence (AI) music composition programs. AI music composition programs have progressed significantly owing to deep learning technology. However, they possess limitations pertaining to the creative aspects of music. In this study, we collect, compare, and analyze information on existing AI-based music composition programs and explore their technical orientation, musical concept, and drawbacks to delineate future directions for AI music composition programs. Furthermore, this study emphasizes the importance of developing AI music composition programs that create "personalized" music, aligning with the era of personalization. Ultimately, for AI-based composition programs, it is critical to extensively research how music, as an output, can touch the listeners and implement appropriate changes. By doing so, AI-based music composition programs are expected to form a new structure in and advance the music industry.