• 동의생리병리학회지
• /
• 제35권5호
• /
• pp.132-138
• /
• 2021

Artificial intelligence technology sheds light on new ways of innovating acupuncture research. As acupoint selection is specific to target diseases, each acupoint is generally believed to have a specific indication. However, the specificity of acupoint selection may be not always same with the specificity of acupoint indication. In this review, we propose that the specificity of acupoint indication can be inferred from clinical data using reverse inference. Using forward inference, the prescribed acupoints for each disease can be quantified for the specificity of acupoint selection. Using reverse inference, targeted diseases for each acupoint can be quantified for the specificity of acupoint indication. It is noteworthy that the selection of an acupoint for a particular disease does not imply the acupoint has specific indications for that disease. Electronic medical record includes various symptoms and chosen acupoint combinations. Data mining approach can be useful to reveal the complex relationships between diseases and acupoints from clinical data. Combining the clinical information and the bodily sensation map, the spatial patterns of acupoint indication can be further estimated. Interoperable medical data should be collected for medical knowledge discovery and clinical decision support system. In the era of artificial intelligence, machine learning can reveal the associations between diseases and prescribed acupoints from large scale clinical data warehouse.

• Journal of Information Processing Systems
• /
• 제19권6호
• /
• pp.803-816
• /
• 2023

Explainable artificial intelligence is a method that explains how a complex model (e.g., a deep neural network) yields its output from a given input. Recently, graph-type data have been widely used in various fields, and diverse graph neural networks (GNNs) have been developed for graph-type data. However, methods to explain the behavior of GNNs have not been studied much, and only a limited understanding of GNNs is currently available. Therefore, in this paper, we propose an explanation method for node classification using graph convolutional networks (GCNs), which is a representative type of GNN. The proposed method finds out which features of each node have the greatest influence on the classification of that node using GCN. The proposed method identifies influential features by backtracking the layers of the GCN from the output layer to the input layer using the gradients. The experimental results on both synthetic and real datasets demonstrate that the proposed explanation method accurately identifies the features of each node that have the greatest influence on its classification.

• Journal of Information Processing Systems
• /
• 제15권4호
• /
• pp.717-723
• /
• 2019

Smart systems and services aim to facilitate growing urban populations and their prospects of virtual-real social behaviors, gig economies, factory automation, knowledge-based workforce, integrated societies, modern living, among many more. To satisfy these objectives, smart systems and services must comprises of a complex set of features such as security, ease of use and user friendliness, manageability, scalability, adaptivity, intelligent behavior, and personalization. Recently, artificial intelligence (AI) is realized as a data-driven technology to provide an efficient knowledge representation, semantic modeling, and can support a cognitive behavior aspect of the system. In this paper, an integration of AI with the smart systems and services is presented to mitigate the existing challenges. Several novel researches work in terms of frameworks, architectures, paradigms, and algorithms are discussed to provide possible solutions against the existing challenges in the AI-based smart systems and services. Such novel research works involve efficient shape image retrieval, speech signal processing, dynamic thermal rating, advanced persistent threat tactics, user authentication, and so on.

• 한국정보교육학회:학술대회논문집
• /
• 한국정보교육학회 2021년도 학술논문집
• /
• pp.369-376
• /
• 2021

인공지능(AI) 기술의 발전에 따라 많은 분야에서 인공지능 활용 방안에 대한 논의가 활발하게 일어나고 있으며 교육 분야에서도 인공지능 인재 양성을 위한 각종 정책이 추진되고 있다. 본 연구에서는 인공지능 기술을 활용한 로봇 프로그래밍 프레임워크를 제안하고 이를 기반으로 머신러닝(Machine Learning) 분야에서 높은 빈도로 활용되는 파이썬(Python)과 교육 현장의 활용도가 높은 교육용 로봇을 활용하여 인공지능(AI) 교육 프로그램을 제안하였다. 국제자동차공학회(SAE)에서 제시하는 자율주행자동차 수준(0~5단계)을 4단계로 단순화하고 이를 기반으로 로봇에 부착된 카메라가 선(객체)을 인지(Perception)하고 검출(Object detection)하여 스스로 움직일 수 있는 라인 디텍터(Line Detector)를 만드는 것을 목표로 하였다. 개발된 프로그램은 단순히 특정 프로그래밍 언어를 활용하여 주어진 문제를 해결하는 정형화된 형태가 아니라 생활 속의 복잡하고 비구조화된 문제를 자기주도적으로 정의하고 인공지능(AI) 기술을 기반으로 해결하는 경험을 가지는데 그 의의가 있다.

• International Journal of Computer Science & Network Security
• /
• 제22권6호
• /
• pp.145-156
• /
• 2022

Children are the foundation and future of this society and understanding their impressions and behaviors is very important and the child's behavioral problems are a burden on the family and society as well as have a bad impact on the development of the child, and the early diagnosis of these problems helps to solve or mitigate them, and in this research project we aim to understand and know the behaviors of children, through artificial intelligence algorithms that helped solve many complex problems in an automated system, By using this technique to read and analyze the behaviors and feelings of the child by reading the features of the child's face, the movement of the child's body, the method of the child's session and nervous emotions, and by analyzing these factors we can predict the feelings and behaviors of children from grief, tension, happiness and anger as well as determine whether this child has the autism spectrum or not. The scarcity of studies and the privacy of data and its scarcity on these behaviors and feelings limited researchers in the process of analysis and training to the model presented in a set of images, videos and audio recordings that can be connected, this model results in understanding the feelings of children and their behaviors and helps doctors and specialists to understand and know these behaviors and feelings.

• 한국IT서비스학회지
• /
• 제15권4호
• /
• pp.85-95
• /
• 2016

Recently, deep learning and machine learning have attracted considerable attention and many supporting frameworks appeared. In artificial intelligence field, a large body of research is underway to apply the relevant knowledge for complex problem-solving, necessitating the application of various learning algorithms and training methods to artificial intelligence systems. In addition, there is a dearth of performance evaluation of decision making agents. The decision making agent that can find optimal solutions by using reinforcement learning methods designed through this research can collect raw pixel data observed from dynamic environments and make decisions by itself based on the data. The decision making agent uses convolutional neural networks to classify situations it confronts, and the data observed from the environment undergoes preprocessing before being used. This research represents how the convolutional neural networks and the decision making agent are configured, analyzes learning performance through a value-based algorithm and a policy-based algorithm : a Deep Q-Networks and a Policy Gradient, sets forth their differences and demonstrates how the convolutional neural networks affect entire learning performance when using pixel data. This research is expected to contribute to the improvement of artificial intelligence systems which can efficiently find optimal solutions by using features extracted from raw pixel data.

• Journal of Information Processing Systems
• /
• 제19권4호
• /
• pp.427-438
• /
• 2023

Plenty of works have indicated that single image super-resolution (SISR) models relying on synthetic datasets are difficult to be applied to real scene text image super-resolution (STISR) for its more complex degradation. The up-to-date dataset for realistic STISR is called TextZoom, while the current methods trained on this dataset have not considered the effect of multi-scale features of text images. In this paper, a multi-scale and attention fusion model for realistic STISR is proposed. The multi-scale learning mechanism is introduced to acquire sophisticated feature representations of text images; The spatial and channel attentions are introduced to capture the local information and inter-channel interaction information of text images; At last, this paper designs a multi-scale residual attention module by skillfully fusing multi-scale learning and attention mechanisms. The experiments on TextZoom demonstrate that the model proposed increases scene text recognition's (ASTER) average recognition accuracy by 1.2% compared to text super-resolution network.

• Journal of Information Processing Systems
• /
• 제15권4호
• /
• pp.865-889
• /
• 2019

The need for cyber resilience is increasingly important in our technology-dependent society where computing devices and data have been, and will continue to be, the target of cyber-attackers, particularly advanced persistent threat (APT) and nation-state/sponsored actors. APT and nation-state/sponsored actors tend to be more sophisticated, having access to significantly more resources and time to facilitate their attacks, which in most cases are not financially driven (unlike typical cyber-criminals). For example, such threat actors often utilize a broad range of attack vectors, cyber and/or physical, and constantly evolve their attack tactics. Thus, having up-to-date and detailed information of APT's tactics, techniques, and procedures (TTPs) facilitates the design of effective defense strategies as the focus of this paper. Specifically, we posit the importance of taxonomies in categorizing cyber-attacks. Note, however, that existing information about APT attack campaigns is fragmented across practitioner, government (including intelligence/classified), and academic publications, and existing taxonomies generally have a narrow scope (e.g., to a limited number of APT campaigns). Therefore, in this paper, we leverage the Cyber Kill Chain (CKC) model to "decompose" any complex attack and identify the relevant characteristics of such attacks. We then comprehensively analyze more than 40 APT campaigns disclosed before 2018 to build our taxonomy. Such taxonomy can facilitate incident response and cyber threat hunting by aiding in understanding of the potential attacks to organizations as well as which attacks may surface. In addition, the taxonomy can allow national security and intelligence agencies and businesses to share their analysis of ongoing, sensitive APT campaigns without the need to disclose detailed information about the campaigns. It can also notify future security policies and mitigation strategy formulation.

• 지능정보연구
• /
• 제2권2호
• /
• pp.43-54
• /
• 1996

Financial markets are operating 24 hours a day throughout the world and interrelated in increasingly complex ways. Telecommunications and computer networks tie together markets in the from of electronic entities. Financial practitioners are inundated with an ever larger stream of data, produced by the rise of sophisticated database technologies, on the rising number of market instruments. As conventional analytic techniques reach their limit in recognizing data patterns, financial firms and institutions find neural network techniques to solve this complex task. Neural networks have found an important niche in financial a, pp.ications. We a, pp.y neural networks to Standard and Poor's (S&P) 500 stock index futures trading to predict the futures marker behavior. The results through experiments with a commercial neural, network software do su, pp.rt future use of neural networks in S&P 500 stock index futures trading.

• 센서학회지
• /
• 제31권1호
• /
• pp.16-23
• /
• 2022

Cardiac disease is the most common cause of death worldwide. Therefore, detection and classification of electrocardiogram (ECG) signals are crucial to extend life expectancy. In this study, we aimed to implement an artificial intelligence signal recognition system in field programmable gate array (FPGA), which can recognize patterns of bio-signals such as ECG in edge devices that require batteries. Despite the increment in classification accuracy, deep learning models require exorbitant computational resources and power, which makes the mapping of deep neural networks slow and implementation on wearable devices challenging. To overcome these limitations, spiking neural networks (SNNs) have been applied. SNNs are biologically inspired, event-driven neural networks that compute and transfer information using discrete spikes, which require fewer operations and less complex hardware resources. Thus, they are more energy-efficient compared to other artificial neural networks algorithms.