• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.7
• /
• pp.1726-1748
• /
• 2024

Trajectory planning is vital for autonomous systems like robotics and UAVs, as it determines optimal, safe paths considering physical limitations, environmental factors, and agent interactions. Recent advancements in trajectory planning and future location prediction stem from rapid progress in machine learning and optimization algorithms. In this paper, we proposed a novel framework for Spatial-temporal transformer-based feed-forward neural networks (STTFFNs). From the traffic flow local area point of view, skip-gram model is trained on trajectory data to generate embeddings that capture the high-level features of different trajectories. These embeddings can then be used as input to a transformer-based trajectory planning model, which can generate trajectories for new objects based on the embeddings of similar trajectories in the training data. In the next step, distant regions, we embedded feedforward network is responsible for generating the distant trajectories by taking as input a set of features that represent the object's current state and historical data. One advantage of using feedforward networks for distant trajectory planning is their ability to capture long-term dependencies in the data. In the final step of forecasting for future locations, the encoder and decoder are crucial parts of the proposed technique. Spatial destinations are encoded utilizing location-based social networks(LBSN) based on visiting semantic locations. The model has been specially trained to forecast future locations using precise longitude and latitude values. Following rigorous testing on two real-world datasets, Porto and Manhattan, it was discovered that the model outperformed a prediction accuracy of 8.7% previous state-of-the-art methods.

• Dementia and Neurocognitive Disorders
• /
• v.23 no.3
• /
• pp.146-160
• /
• 2024

Background and Purpose: The emotions of people at various stages of dementia need to be effectively utilized for prevention, early intervention, and care planning. With technology available for understanding and addressing the emotional needs of people, this study aims to develop speech emotion recognition (SER) technology to classify emotions for people at high risk of dementia. Methods: Speech samples from people at high risk of dementia were categorized into distinct emotions via human auditory assessment, the outcomes of which were annotated for guided deep-learning method. The architecture incorporated convolutional neural network, long short-term memory, attention layers, and Wav2Vec2, a novel feature extractor to develop automated speech-emotion recognition. Results: Twenty-seven kinds of Emotions were found in the speech of the participants. These emotions were grouped into 6 detailed emotions: happiness, interest, sadness, frustration, anger, and neutrality, and further into 3 basic emotions: positive, negative, and neutral. To improve algorithmic performance, multiple learning approaches were applied using different data sources-voice and text-and varying the number of emotions. Ultimately, a 2-stage algorithm-initial text-based classification followed by voice-based analysis-achieved the highest accuracy, reaching 70%. Conclusions: The diverse emotions identified in this study were attributed to the characteristics of the participants and the method of data collection. The speech of people at high risk of dementia to companion robots also explains the relatively low performance of the SER algorithm. Accordingly, this study suggests the systematic and comprehensive construction of a dataset from people with dementia.

• Journal of Internet Computing and Services
• /
• v.25 no.4
• /
• pp.7-21
• /
• 2024

There are various machine learning techniques such as Reinforcement Learning, Deep Learning, Neural Network Learning, and so on. In recent, Large Language Models (LLMs) are popularly used for Generative AI based on Reinforcement Learning. It makes decisions with the most optimal rewards through the fine tuning process in a particular situation. Unfortunately, LLMs can not provide any explanation for how they reach the goal because the training is based on learning of black-box AI. Reinforcement Learning as black-box AI is based on graph-evolving structure for deriving enhanced solution through adjustment by human feedback or reinforced data. In this research, for mutually exclusive decision-making, Mutually Exclusive Learning (MEL) is proposed to provide explanations of the chosen goals that are achieved by a decision on both ends with specified conditions. In MEL, decision-making process is based on the tree-based structure that can provide processes of pruning branches that are used as explanations of how to achieve the goals. The goal can be reached by trade-off among mutually exclusive alternatives according to the specific contextual conditions. Therefore, the tree-based structure is adopted to provide feasible solutions with the explanations based on the pruning branches. The sequence of pruning processes can be used to provide the explanations of the inferences and ways to reach the goals, as Explainable AI (XAI). The learning process is based on the pruning branches according to the multi-dimensional contextual conditions. To deep-dive the search, they are composed of time window to determine the temporal perspective, depth of phases for lookahead and decision criteria to prune branches. The goal depends on the policy of the pruning branches, which can be dynamically changed by configured situation with the specific multi-dimensional contextual conditions at a particular moment. The explanation is represented by the chosen episode among the decision alternatives according to configured situations. In this research, MEL adopts the tree-based learning model to provide explanation for the goal derived with specific conditions. Therefore, as an example of mutually exclusive problems, employment process is proposed to demonstrate the decision-making process of how to reach the goal and explanation by the pruning branches. Finally, further study is discussed to verify the effectiveness of MEL with experiments.

• Imaging Science in Dentistry
• /
• v.54 no.3
• /
• pp.257-263
• /
• 2024

Purpose: The purpose of this study was to classify mandibular molar furcation involvement (FI) in periapical radiographs using a deep learning algorithm. Materials and Methods: Full mouth series taken at East Carolina University School of Dental Medicine from 2011-2023 were screened. Diagnostic-quality mandibular premolar and molar periapical radiographs with healthy or FI mandibular molars were included. The radiographs were cropped into individual molar images, annotated as "healthy" or "FI," and divided into training, validation, and testing datasets. The images were preprocessed by PyTorch transformations. ResNet-18, a convolutional neural network model, was refined using the PyTorch deep learning framework for the specific imaging classification task. CrossEntropyLoss and the AdamW optimizer were employed for loss function training and optimizing the learning rate, respectively. The images were loaded by PyTorch DataLoader for efficiency. The performance of ResNet-18 algorithm was evaluated with multiple metrics, including training and validation losses, confusion matrix, accuracy, sensitivity, specificity, the receiver operating characteristic (ROC) curve, and the area under the ROC curve. Results: After adequate training, ResNet-18 classified healthy vs. FI molars in the testing set with an accuracy of 96.47%, indicating its suitability for image classification. Conclusion: The deep learning algorithm developed in this study was shown to be promising for classifying mandibular molar FI. It could serve as a valuable supplemental tool for detecting and managing periodontal diseases.

• Information Systems Review
• /
• v.26 no.2
• /
• pp.83-93
• /
• 2024

This study proposes a preprocessing methodology based on Dynamic Time Warping (DTW) and k-Nearest Neighbors (kNN) to effectively represent time series data for predicting the completion quality of electroplating baths. The proposed DTW-based kNN preprocessing approach was applied to various regression models and compared. The results demonstrated a performance improvement of up to 43% in maximum RMSE and 24% in MAE compared to traditional decision tree models. Notably, when integrated with neural network-based regression models, the performance improvements were pronounced. The combined structure of the proposed preprocessing method and regression models appears suitable for situations with long time series data and limited data samples, reducing the risk of overfitting and enabling reasonable predictions even with scarce data. However, as the number of data samples increases, the computational load of the DTW and kNN algorithms also increases, indicating a need for future research to improve computational efficiency.

• Steel and Composite Structures
• /
• v.52 no.6
• /
• pp.647-656
• /
• 2024

This paper discusses the study of concrete composite walls of algorithmic modeling, in which steel tubes are embedded. The load-bearing capacity of STHC composite walls increases with the increase of axial load coefficient, but its ductility decreases. The load-bearing capacity can be improved by increasing the strength of the steel pipes; however, the elasticity of STHC composite walls was found to be slightly reduced. As the shear stress coefficient increases, the load-bearing capacity of STHC composite walls decreases significantly, while the deformation resistance increases. By analyzing actual cases, we demonstrate the effectiveness of the research results in real situations and enhance the persuasiveness of the conclusions. The research results can provide a basis for future research, inspire more explorations on seismic design and construction, and further advance the development of this field. Emphasize the importance of research results, promote interdisciplinary cooperation in the fields of structural engineering, earthquake engineering, and materials science, and improve overall seismic resistance. The emphasis on these aspects will help highlight the practical impact of the research results, further strengthen the conclusions, and promote progress in the design and construction of earthquake-resistant structures. The goals of this work are access to adequate, safe and affordable housing and basic services, promotion of inclusive and sustainable urbanization and participation, implementation of sustainable and disaster-resilient architecture, sustainable planning and management of human settlements. Simulation results of linear and nonlinear structures show that this method can detect structural parameters and their changes due to damage and unknown disturbances. Therefore, it is believed that with the further development of fuzzy neural network artificial intelligence theory, this goal will be achieved in the near future.

• Journal of IKEEE
• /
• v.28 no.3
• /
• pp.352-359
• /
• 2024

This paper proposes a CNN-ViT hybrid model that automatically evaluates the aesthetic quality of images by combining local and global features. In this approach, CNN is used to extract local features such as color and object placement, while ViT is employed to analyze the aesthetic value of the image by reflecting global features. Color composition is derived by extracting the primary colors from the input image, creating a color palette, and then passing it through the CNN. The Rule of Thirds is quantified by calculating how closely objects in the image are positioned near the thirds intersection points. These values provide the model with critical information about the color balance and spatial harmony of the image. The model then analyzes the relationship between these factors to predict scores that align closely with human judgment. Experimental results on the AADB image database show that the proposed model achieved a Spearman's Rank Correlation Coefficient (SRCC) of 0.716, indicating more consistent rank predictions, and a Pearson Correlation Coefficient (LCC) of 0.72, which is 2~4% higher than existing models.

• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.9
• /
• pp.723-732
• /
• 2001

In this paper, the neurofuzzy controller of optically guided AGV is proposed to improve the path-tracking performance A differential steered AGV has front-side and rear-side optical sensors, which can identify the guiding path. Due to the discontinuity of measured data in optical sensors, optically guided AGVs break away easily from the guiding path and path-tracking performance is being degraded. Whenever the On/Off signals in the optical sensors are generated discontinuously, the motion errors can be measured and updated. After sensing, the variation of motion errors can be estimated continuously by the dead reckoning method according to left/right wheel angular velocity. We define the estimated contour error as the sum of the measured contour in the sensing error and the estimated variation of contour error after sensing. The neurofuzzy system consists of incorporating fuzzy controller and neural network. The center and width of fuzzy membership functions are adaptively adjusted by back-propagation learning to minimize th estimated contour error. The proposed control system can be compared with the traditional fuzzy control and decision system in their network structure and learning ability. The proposed control strategy is experience through simulated model to check the performance.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.8
• /
• pp.572-578
• /
• 2020

The stock market is affected by unexpected factors, such as politics, society, and natural disasters, as well as by corporate performance and economic conditions. In recent days, artificial intelligence has become popular, and many researchers have tried to conduct experiments with that. Our study proposes an experiment using not only stock-related data but also other various economic data. We acquired a year's worth of data on stock prices, the percentage of foreigners, interest rates, and exchange rates, and combined them in various ways. Thus, our input data became diversified, and we put the combined input data into a nonlinear autoregressive network with exogenous inputs (NARX) model. With the input data in the NARX model, we analyze and compare them to the original data. As a result, the model exhibits a root mean square error (RMSE) of 0.08 as being the most accurate when we set 10 neurons and two delays with a combination of stock prices and exchange rates from the U.S., China, Europe, and Japan. This study is meaningful in that the exchange rate has the greatest influence on stock prices, lowering the error from RMSE 0.589 when only closing data are used.

• Geophysics and Geophysical Exploration
• /
• v.23 no.3
• /
• pp.192-207
• /
• 2020

We acquire seismic data with regularly or irregularly missing traces, due to economic, environmental, and mechanical problems. Since these missing data adversely affect the results of seismic data processing and analysis, we need to reconstruct the missing data before subsequent processing. However, there are economic and temporal burdens to conducting further exploration and reconstructing missing parts. Many researchers have been studying interpolation methods to accurately reconstruct missing data. Recently, various machine learning technologies such as support vector regression, autoencoder, U-Net, ResNet, and generative adversarial network (GAN) have been applied in seismic data interpolation. In this study, by reviewing these studies, we found that not only neural network models, but also support vector regression models that have relatively simple structures can interpolate missing parts of seismic data effectively. We expect that future research can improve the interpolation performance of these machine learning models by using open-source field data, data augmentation, transfer learning, and regularization based on conventional interpolation technologies.