• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.141-147
• /
• 2024

Recently, there has been growing interest in personalized services tailored to an individual's preferences. This has led to ongoing research aimed at recognizing and leveraging an individual's personality traits. Among various methods for personality assessment, the OCEAN model stands out as a prominent approach. In utilizing OCEAN for personality recognition, a multi modal artificial intelligence model that incorporates linguistic, paralinguistic, and non-linguistic information is often employed. This paper examines the impact of the margin value set for extracting facial areas from video data on the accuracy of a personality recognition model that uses facial expressions to determine OCEAN traits. The study employed personality recognition models based on 2D Patch Partition, R2plus1D, 3D Patch Partition, and Video Swin Transformer technologies. It was observed that setting the facial area extraction margin to 60 resulted in the highest 1-MAE performance, scoring at 0.9118. These findings indicate the importance of selecting an optimal margin value to maximize the efficiency of personality recognition models.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.3
• /
• pp.363-368
• /
• 2005

Artificial life is a science studying artificial systems that implement various behavioral characteristics of lives as an attempt of applying some features found in living creatures to artificial intelligent objects in virtual worlds. Attempts and researches are actively being made to apply human needs to games and express them through artificial life. Human needs and the expression of the needs are extremely diverse and complicated, so they cannot be modeled in a specific way. Thus this study modeled game AI object needs using AHP, which is a useful model in solving problems quantitatively through basic observation of human nature, analytic thinking, measuring, etc. In addition, the modeled game AI object needs were examined through the analysis of performance sensitivity and their applicability to actual games was assessed with example.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• pp.219-223
• /
• 2001

Within a mechanical system such as an automotive the number of standard machine parts is increasing, so that the parts selection becomes more important than ever before. Selection of appropriate bearings in the preliminary design phase of a machine is also important. In this paper, three decision-making approaches are compared to find out a model that is appropriate to bearing selection problem. An artificial neural network, which is trained with real design cases, is used to select a bearing mechanism at the first step. Then, the subtype of the bearing is selected by the weighting factor method. Finally, types of peripherals such as lubrication methods are determined by a rule-based expert system.

• ETRI Journal
• /
• v.46 no.5
• /
• pp.817-828
• /
• 2024

Owing to the widespread advancement of transformer-based artificial neural networks, artificial intelligence (AI) processors are now required to perform matrix-vector multiplication in addition to the conventional matrix-matrix multiplication. However, current AI processor architectures are optimized for general matrix-matrix multiplications (GEMMs), which causes significant throughput degradation when processing general matrix-vector multiplications (GEMVs). In this study, we proposed a port-folding GEMV (PF-GEMV) scheme employing multiformat and low-precision techniques while reusing an outer product-based processor optimized for conventional GEMM operations. This approach achieves 93.7% utilization in GEMV operations with an 8-bit format on an 8 × 8 processor, thus resulting in a 7.5 × increase in throughput compared with that of the original scheme. Furthermore, when applied to the matrix operation of the GPT-2 large model, an increase in speed by 7 × is achieved in single-batch inferences.

• Annual Conference of KIPS
• /
• 2024.05a
• /
• pp.692-695
• /
• 2024

With the recent advancements in artificial intelligence (AI), the performance of deep learning-based audio deepfake technology has significantly improved. This technology has been exploited for criminal activities, leading to various cases of victimization. To prevent such illicit outcomes, this paper proposes a deep learning-based audio deepfake detection model. In this study, we propose CoNSIST, an improved audio deepfake detection model, which incorporates three additional components into the graph-based end-to-end model AASIST: (i) Squeeze and Excitation, (ii) Positional Encoding, and (iii) Reformulated HS-GAL, This incorporation is expected to enable more effective feature extraction, elimination of unnecessary operations, and consideration of more diverse information, thereby improving the performance of the original AASIST. The results of multiple experiments indicate that CoNSIST has enhanced the performance of audio deepfake detection compared to existing models.

• Journal of The Korean Association For Science Education
• /
• v.44 no.2
• /
• pp.141-153
• /
• 2024

The 2022 revised science curriculum aims to develop the ability to solve scientific problems arising in daily life and society based on convergent thinking stimulated through participation in research activities using artificial intelligence (AI). Therefore, we developed a science-AI convergence education program that combines the science curriculum with artificial intelligence and employed it in convergence classes for high school students. The aim of the science-AI convergence class was for students to qualitatively understand the movement of a damped pendulum and build an AI model to predict the position of the pendulum using the block coding platform KNIME. Individual in-depth interviews were conducted to understand and interpret the learners' experiences. Based on Giorgi's phenomenological research methodology, we described the learners' learning processes and changes, challenges and limitations of the class. The students collected data and built the AI model. They expected to be able to predict the surrounding phenomena based on their experimental results and perceived the convergence class positively. On the other hand, they still perceived an with the unfamiliarity of platform, difficulty in understanding the principle of AI, and limitations of the teaching method that they had to follow, as well as limitations of the course content. Based on this, we discussed the strengths and limitations of the science-AI convergence class and made suggestions for science-AI convergence education. This study is expected to provide implications for developing science-AI convergence curricula and implementing them in the field.

• International Journal of Computer Science & Network Security
• /
• v.23 no.11
• /
• pp.99-109
• /
• 2023

The darknet is frequently referred to as the hub of illicit online activity. In order to keep track of real-time applications and activities taking place on Darknet, traffic on that network must be analysed. It is without a doubt important to recognise network traffic tied to an unused Internet address in order to spot and investigate malicious online activity. Any observed network traffic is the result of mis-configuration from faked source addresses and another methods that monitor the unused space address because there are no genuine devices or hosts in an unused address block. Digital systems can now detect and identify darknet activity on their own thanks to recent advances in artificial intelligence. In this paper, offer a generalised method for deep learning-based detection and classification of darknet traffic. Furthermore, analyse a cutting-edge complicated dataset that contains a lot of information about darknet traffic. Next, examine various feature selection strategies to choose a best attribute for detecting and classifying darknet traffic. For the purpose of identifying threats using network properties acquired from darknet traffic, devised a hybrid deep learning (DL) approach that combines Recurrent Neural Network (RNN) and Bidirectional LSTM (BiLSTM). This probing technique can tell malicious traffic from legitimate traffic. The results show that the suggested strategy works better than the existing ways by producing the highest level of accuracy for categorising darknet traffic using the Black widow optimization algorithm as a feature selection approach and RNN-BiLSTM as a recognition model.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.12 no.19
• /
• pp.57-65
• /
• 1989

This paper describes an artificial intelligence approach to machine diagnosis. Firstly, It considers how the knowledge could be organized and represented. Secondly, it considers which inference strategy could be chosen for contingent situations for the purpose of rationality, efficiency and user-friendliness. Finally, the prototype based on the suggested model is introduced briefly.

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.355-363
• /
• 2022

Korea is pursuing a plan to switch and expand energy sources with a focus on renewable energy with the goal of becoming carbon neutral by 2050. As the instability of energy supply increases due to the intermittent nature of renewable energy, accurate prediction of the amount of renewable energy generation is becoming more important. Therefore, the government has opened a small-scale power brokerage market and is implementing a system that pays settlements according to the accuracy of renewable energy prediction. In this paper, a prediction model was implemented using a statistical model and an artificial intelligence model for the prediction of solar power generation. In addition, the results of prediction accuracy were compared and analyzed, and the revenue from the settlement amount of the renewable energy generation forecasting system was estimated.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.6
• /
• pp.21-28
• /
• 2019

Recent years with the development of artificial intelligence and the success of the deep model, they have been deployed in all fields of computer vision. Action recognition, as an important branch of human perception and computer vision system research, has attracted more and more attention. Action recognition is a challenging task due to the special complexity of human movement, the same movement may exist between multiple individuals. The human action exists as a continuous image frame in the video, so action recognition requires more computational power than processing static images. And the simple use of the CNN network cannot achieve the desired results. Recently, the attention model has achieved good results in computer vision and natural language processing. In particular, for video action classification, after adding the attention model, it is more effective to focus on motion features and improve performance. It intuitively explains which part the model attends to when making a particular decision, which is very helpful in real applications. In this paper, we proposed a 3D dense convolutional network based on attention mechanism(ADD-Net), recognition of human motion behavior in the video.