• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.42 no.1
• /
• pp.1-11
• /
• 2005

Several Solid Freeform Fabrication Systems(SFFS) are commercialized in a few companies for rapid prototyping. However, they have many technical problems including the limitation of applicable materials. A new method of agile prototyping is required for the recent manufacturing environments of multi-item and small quantity production. The objectives of this paper include the development of a novel method of SFFS, the CAFL/sup VM/(Computer Aided Fabrication of Lamination for Various Material), and the manufacture of the various material samples for the certification of the proposed system and the creation of new application areas. For these objectives, the technologies for a highly accurate robot path control, the optimization of support structure, CAD modeling, adaptive slicing was implemented. However, there is an important problem with the conventional 2D lamination method. That is the inaccuracy of 3D model surface, which is caused by the stair-type surface generated in virtue of vertical 2D cutting. In this paper, We design the new control algorithm that guarantees the constant speed, precise positioning and tangential cutting on the 5DOF SFFS. We develop the tangential cutting algorithm to be controlled with constant speed and successfully implemented in the 5DOF CAFL/sup VM/ system developed in this paper. Finally, this paper confirms its high-performance through the experimental results from the application into CAFL/sup VM/ system.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.3
• /
• pp.304-315
• /
• 2001

In this paper, we peformed the real-time implementation of AMR(Adaptive Multi-Rate) speech coding algorithm which is adopted for IMT-2000 service using TMS320C6201, i.e., a Texas Instrument´s fixed-point DSP. With the ANSI C source code released from ETSI, optimization is performed to make it run in real-time with memory as small as possible using the C compiler and assembly language. Implemented AMR speech codec has the size of 32.06 kWords program memory, 9.75 kWords data RAM memory, and 19.89 kWords data ROM memory. And, The time required for processing one frame of 20 ms length speech data is about 4.38 ms, and it is short enough for real-time operation. It is verified that the decoded result of the implemented speech codec on the DSP is identical with the PC simulation result using ANSI C code for test sequences. Also, actual sound input/output test using microphone and speaker demonstrates its proper real-time operation without distortions or delays.

• Journal of Korea Water Resources Association
• /
• v.54 no.7
• /
• pp.475-484
• /
• 2021

The optimal design for water distribution system (WDS) is not only satisfying the minimum required water pressure of the nodes, but also minimizing pipe cost, etc. The number of designs of WDS increases exponentially due to the arrangement of various pipes. Various optimization algorithms were applied to propose an optimized design of WDS. In this study, Modified Hybrid Vision Correction Algorithm (MHVCA) with improved self-adapting parameter was applied to optimal design of WDS. The performance was improved by changing the Hybrid Rate (HR) of the existing Hybrid Vision Correction Algorithm (HVCA) to nonlinear HR. To verify the performance of the proposed MHVCA, it applied to mathematical problems consisting of 2 and 30 decision variables and constrained mathematical problems. In order to review the application results of MHVCA, it was compared with Harmony Search (HS), Improved Harmony Search (IHS), Vision Correction Algorithm (VCA) and HVCA. Finally, MHVCA was applied to the optimal design problem of WDS and the results were compared with other algorithms. MHVCA showed better results than other algorithms in mathematical problems and WDS problem. MHVCA will be able to show good results by applying to various water resource engineering problems as well as problems applied in this study.

• Journal of The Korean Association For Science Education
• /
• v.43 no.3
• /
• pp.307-319
• /
• 2023

This study aims to explain the key concepts and principles of text-based generative artificial intelligence (AI) that has been receiving increasing interest and utilization, focusing on its application in science education. It also highlights the potential and limitations of utilizing generative AI in science education, providing insights for its implementation and research aspects. Recent advancements in generative AI, predominantly based on transformer models consisting of encoders and decoders, have shown remarkable progress through optimization of reinforcement learning and reward models using human feedback, as well as understanding context. Particularly, it can perform various functions such as writing, summarizing, keyword extraction, evaluation, and feedback based on the ability to understand various user questions and intents. It also offers practical utility in diagnosing learners and structuring educational content based on provided examples by educators. However, it is necessary to examine the concerns regarding the limitations of generative AI, including the potential for conveying inaccurate facts or knowledge, bias resulting from overconfidence, and uncertainties regarding its impact on user attitudes or emotions. Moreover, the responses provided by generative AI are probabilistic based on response data from many individuals, which raises concerns about limiting insightful and innovative thinking that may offer different perspectives or ideas. In light of these considerations, this study provides practical suggestions for the positive utilization of AI in science education.

• Journal of the Korean Society of Radiology
• /
• v.17 no.5
• /
• pp.633-640
• /
• 2023

With the recent development of static and dynamic modulated brachytherapy methods in brachytherapy, which use radiation shielding to modulate the dose distribution to deliver the dose, the amount of parameters and data required for dose calculation in inverse treatment planning and treatment plan optimization algorithms suitable for new directional beam intensity modulated brachytherapy is increasing. Although intensity-modulated brachytherapy enables accurate dose delivery of radiation, the increased amount of parameters and data increases the elapsed time required for dose calculation. In this study, a GPU-based CUDA-accelerated dose calculation algorithm was constructed to reduce the increase in dose calculation elapsed time. The acceleration of the calculation process was achieved by parallelizing the calculation of the system matrix of the volume of interest and the dose calculation. The developed algorithms were all performed in the same computing environment with an Intel (3.7 GHz, 6-core) CPU and a single NVIDIA GTX 1080ti graphics card, and the dose calculation time was evaluated by measuring only the dose calculation time, excluding the additional time required for loading data from disk and preprocessing operations. The results showed that the accelerated algorithm reduced the dose calculation time by about 30 times compared to the CPU-only calculation. The accelerated dose calculation algorithm can be expected to speed up treatment planning when new treatment plans need to be created to account for daily variations in applicator movement, such as in adaptive radiotherapy, or when dose calculation needs to account for changing parameters, such as in dynamically modulated brachytherapy.

• Geophysics and Geophysical Exploration
• /
• v.27 no.2
• /
• pp.91-107
• /
• 2024

Single-channel seismic exploration has proven effective in delineating subsurface geological structures using small-scale survey systems. The seismic data acquired through zero- or near-offset methods directly capture subsurface features along the vertical axis, facilitating the construction of corresponding seismic sections. However, substantial noise in single-channel seismic data hampers precise interpretation because of the low signal-to-noise ratio. This study introduces a novel approach that integrate noise reduction and signal enhancement via matrix rank optimization to address this issue. Unlike conventional rank-reduction methods, which retain selected singular values to mitigate random noise, our method optimizes the entire singular value spectrum, thus effectively tackling both random and erratic noises commonly found in environments with low signal-to-noise ratio. Additionally, to enhance the horizontal continuity of seismic events and mitigate signal loss during noise reduction, we introduced an adaptive weighting factor computed from the eigenimage of the seismic section. To access the robustness of the proposed method, we conducted numerical experiments using single-channel Sparker seismic data from the Chukchi Plateau in the Arctic Ocean. The results demonstrated that the seismic sections had significantly improved signal-to-noise ratios and minimal signal loss. These advancements hold promise for enhancing single-channel and high-resolution seismic surveys and aiding in the identification of marine development and submarine geological hazards in domestic coastal areas.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.163-177
• /
• 2019

As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.