• International Journal of Computer Science & Network Security
• /
• v.24 no.5
• /
• pp.53-63
• /
• 2024

Alzheimer's disease is a brain disorder that worsens over time and affects millions of people around the world. It leads to a gradual deterioration in memory, thinking ability, and behavioral and social skills until the person loses his ability to adapt to society. Technological progress in medical imaging and the use of artificial intelligence, has provided the possibility of detecting Alzheimer's disease through medical images such as magnetic resonance imaging (MRI). However, Deep learning algorithms, especially convolutional neural networks (CNNs), have shown great success in analyzing medical images for disease diagnosis and classification. Where CNNs can recognize patterns and objects from images, which makes them ideally suited for this study. In this paper, we proposed to compare the performances of Alzheimer's disease detection by using two deep learning methods: You Only Look Once (YOLO), a CNN-enabled object recognition algorithm, and Visual Geometry Group (VGG16) which is a type of deep convolutional neural network primarily used for image classification. We will compare our results using these modern models Instead of using CNN only like the previous research. In addition, the results showed different levels of accuracy for the various versions of YOLO and the VGG16 model. YOLO v5 reached 56.4% accuracy at 50 epochs and 61.5% accuracy at 100 epochs. YOLO v8, which is for classification, reached 84% accuracy overall at 100 epochs. YOLO v9, which is for object detection overall accuracy of 84.6%. The VGG16 model reached 99% accuracy for training after 25 epochs but only 78% accuracy for testing. Hence, the best model overall is YOLO v9, with the highest overall accuracy of 86.1%.

• Science of Emotion and Sensibility
• /
• v.22 no.4
• /
• pp.31-44
• /
• 2019

This study intended to investigate the effects of the subtitle location on the decreased working memory abilities caused by aging. A junior group (average age: 26, SD: 3.06, N=27) and a senior group (average age: 61.69, SD=4.18, N=26) participated in this study and they all performed N-back tasks which measured the working memory ability of the participants and video subtitle recognition tasks that assessed the most effectively recognized subtitle locations in the video. The results of the N-back task revealed slower response times and low accuracy rates in the senior group in comparison to the junior group, suggesting lower working memory abilities in the senior group vis-à-vis the junior group. The deterioration of working memory due to aging also negatively influenced the 'left-bottom' subtitle location in the video subtitle recognition task and positively influenced the 'left-center' location of the screen. The deterioration of working memory ability did not affect other subtitle locations. By examining the positive or negative effects of the deterioration of working memory ability as a function of age on subtitle locations, the present study suggests that the selection of suitable subtitle locations taking into account the ages of video viewers would cause information to be more effectively displayed on screen.

• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1061-1069
• /
• 2021

Recently, the magnitude and frequency of extreme heavy rains and localized heavy rains have increased due to abnormal climate, which caused increased flood damage in river basin. As a result, the nonlinearity of the hydrological system of rivers or basins is increasing, and there is a limitation in that the lead time is insufficient to predict the water level using the existing physical-based hydrological model. This study predicted the water level at Ulsan (Taehwagyo) with a lead time of 0, 1, 2, 3, 6, 12 hours by applying deep learning techniques based on Deep Neural Network (DNN) and Long Short-Term Memory (LSTM) and evaluated the prediction accuracy. As a result, DNN model using the sliding window concept showed the highest accuracy with a correlation coefficient of 0.97 and RMSE of 0.82 m. If deep learning-based water level prediction using a DNN model is performed in the future, high prediction accuracy and sufficient lead time can be secured than water level prediction using existing physical-based hydrological models.

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.408-415
• /
• 2022

In this paper, we propose a 3D point cloud reconstruction technique from 2D images using efficient feature map extraction network. The originality of the method proposed in this paper is as follows. First, we use a new feature map extraction network that is about 27% efficient than existing techniques in terms of memory. The proposed network does not reduce the size to the middle of the deep learning network, so important information required for 3D point cloud reconstruction is not lost. We solved the memory increase problem caused by the non-reduced image size by reducing the number of channels and by efficiently configuring the deep learning network to be shallow. Second, by preserving the high-resolution features of the 2D image, the accuracy can be further improved than that of the conventional technique. The feature map extracted from the non-reduced image contains more detailed information than the existing method, which can further improve the reconstruction accuracy of the 3D point cloud. Third, we use a divergence loss that does not require shooting information. The fact that not only the 2D image but also the shooting angle is required for learning, the dataset must contain detailed information and it is a disadvantage that makes it difficult to construct the dataset. In this paper, the accuracy of the reconstruction of the 3D point cloud can be increased by increasing the diversity of information through randomness without additional shooting information. In order to objectively evaluate the performance of the proposed method, using the ShapeNet dataset and using the same method as in the comparative papers, the CD value of the method proposed in this paper is 5.87, the EMD value is 5.81, and the FLOPs value is 2.9G. It was calculated. On the other hand, the lower the CD and EMD values, the better the accuracy of the reconstructed 3D point cloud approaches the original. In addition, the lower the number of FLOPs, the less memory is required for the deep learning network. Therefore, the CD, EMD, and FLOPs performance evaluation results of the proposed method showed about 27% improvement in memory and 6.3% in terms of accuracy compared to the methods in other papers, demonstrating objective performance.

• Korean Journal of Cognitive Science
• /
• v.22 no.4
• /
• pp.365-384
• /
• 2011

A recent study of visual working memory(VWM) under a change detection paradigm proposed an idea that the comparison process of VWM representations against incoming perceptual inputs can be performed more rapidly than the process of forming durable memory representations into VWM. To test this hypothesis, we compared the size of interference effect caused by pattern-backward masks following after either the sample(sample-mask condition) or test items (test-mask condition). In Experiment 1, subjects performed a color change detection task for four colored-boxes, and pattern masks with mask-onset asynchronies(MSOA) of either 64ms or 150ms followed each item location either after the sample or after the test items. The change detection accuracy was both comparable in the sample-mask condition regardless of the MSOAs, whereas the accuracy in the trials with a MSOA of 150ms was substantially higher than the MSOA of 65ms in the test-masking condition. In Experiment 2, we manipulated setsizes to 1, 2, 3, 4 items and also MSOAs to 117ms, 234ms, 350ms, 484ms and compared the pattern of interference across a variety of setsize and MSOA conditions. The sample-mask condition yielded a pattern of masking interference which became more evident as the setsize increases and as the MSOA was shorter. However, this pattern of interference was less apparent in the test-mask condition. These results indicate that the comparison process between remembered items in VWM and perceptual inputs is less vulnerable to interference from pattern-backward masking than VWM consolidation is, and thus support for the recent idea that the comparison process in VWM can be performed very fast and accurately.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.16 no.10 s.101
• /
• pp.1010-1019
• /
• 2005

In this paper, we used neural network technique to model memory effects of RF power amplifier which is fed by two-tone input signals. The memory effects in power amplifier were identified by observing the unsymmetrical distribution of IMD(Inter-Modulation Distortion) measurements with the change of tone spacings and power levels. Different asymmetries of IMD were also found at different center frequencies. We applied TDNN technique to model LDMOS power amplifier based on two tone IMD data, and the accuracy was very high compared to other modeling methods such as the(memoryless) adaptive modeling method.

• Journal of Korean Society for Quality Management
• /
• v.47 no.3
• /
• pp.497-508
• /
• 2019

Purpose: The purpose of this study is to overcome limitations of conventional studies that to predict Baltic Dry Index (BDI). The study proposed applications of Artificial Neural Network (ANN) named Long Short-Term Memory (LSTM) to predict BDI. Methods: The BDI time-series prediction was carried out through eight variables related to the dry bulk market. The prediction was conducted in two steps. First, identifying the goodness of fitness for the BDI time-series of specific ANN models and determining the network structures to be used in the next step. While using ANN's generalization capability, the structures determined in the previous steps were used in the empirical prediction step, and the sliding-window method was applied to make a daily (one-day ahead) prediction. Results: At the empirical prediction step, it was possible to predict variable y(BDI time series) at point of time t by 8 variables (related to the dry bulk market) of x at point of time (t-1). LSTM, known to be good at learning over a long period of time, showed the best performance with higher predictive accuracy compared to Multi-Layer Perceptron (MLP) and Recurrent Neural Network (RNN). Conclusion: Applying this study to real business would require long-term predictions by applying more detailed forecasting techniques. I hope that the research can provide a point of reference in the dry bulk market, and furthermore in the decision-making and investment in the future of the shipping business as a whole.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.7
• /
• pp.2513-2530
• /
• 2021

With the fast development of information and communication technologies, video streaming services and applications are increasing rapidly. However, the network condition is volatile. In order to provide users with better quality of service, it is necessary to develop an accurate and low-complexity model for Quality of Experience (QoE) prediction of time-varying video. Memory effects refer to the psychological influence factor of historical experience, which can be taken into account to improve the accuracy of QoE evaluation. In this paper, we design subjective experiments to explore the impact of Short-Term Memory (STM) on QoE. The experimental results show that the user's real-time QoE is influenced by the duration of previous viewing experience and the expectations generated by STM. Furthermore, we propose analytical models to determine the relationship between intrinsic video quality, expectation and real-time QoE. The proposed models have better performance for real-time QoE prediction when the video is transmitted in a fluctuate network. The models are capable of providing more accurate guidance for improving the quality of video streaming services.

• Science of Emotion and Sensibility
• /
• v.25 no.2
• /
• pp.3-10
• /
• 2022

Memorability is an indicator of how well a stimulus can be remembered. Studies on memorability have shown that stimulus memorability cannot be explained by the perceptual and semantic properties of a stimulus, suggesting that memorability is an intrinsic property of a stimulus. Though real-world scenes almost always contain multiple objects, previous studies on memorability have mainly tested memory performance using a single stimulus. In the current study, we investigated how multiple stimuli with different levels of memorability interact with each other. Participants were asked to remember a high or low memorability target presented with a high or low memorability distractor in the encoding block. Participants' memory accuracy was measured by a sensitivity index in the testing block. Results showed that a high memorability target was easier to remember. However, the distractor memorability level did not modulate this target memorability effect. The current results support previous studies that showed a highly memorable stimulus does not automatically induce bottom-up attentional shifts.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1996.10a
• /
• pp.58-63
• /
• 1996

A study is drawn up its result's tables and graphs by measuring tools(outside micrometer cylinder gauge and dial caliper gauge) on the difference of diameter volumes from before-discharge and after-discharge under 52 Kind's experimental condition by cupper and graphite electrode of CNC EDM. The EDM is attached with A.V.R. and memory scope for keep up accuracy and the fixed table of work piece is used in order to eliminate the noise by the internal resistance of it and forcing to eradicate the discharge liquid. It is analyzed cutting conditions to compare its wave value and pulse time.(Ton Toff) through voltage and current for decreasing working error.