• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.290-297
• /
• 2024

We investigate the efficacy of ensemble learning methods, specifically the soft voting technique, for enhancing heart disease prediction accuracy. Our study uniquely combines Logistic Regression, SVM with RBF Kernel, and Random Forest models in a soft voting ensemble to improve predictive performance. We demonstrate that this approach outperforms individual models in diagnosing heart disease. Our research contributes to the field by applying a well-curated dataset with normalization and optimization techniques, conducting a comprehensive comparative analysis of different machine learning models, and showcasing the superior performance of the soft voting ensemble in medical diagnosis. This multifaceted approach allows us to provide a thorough evaluation of the soft voting ensemble's effectiveness in the context of heart disease prediction. We evaluate our models based on accuracy, precision, recall, F1 score, and Area Under the ROC Curve (AUC). Our results indicate that the soft voting ensemble technique achieves higher accuracy and robustness in heart disease prediction compared to individual classifiers. This study advances the application of machine learning in medical diagnostics, offering a novel approach to improve heart disease prediction. Our findings have significant implications for early detection and management of heart disease, potentially contributing to better patient outcomes and more efficient healthcare resource allocation.

• Geomechanics and Engineering
• /
• v.37 no.6
• /
• pp.539-554
• /
• 2024

This study explores development of prediction model for seismic site classification through the integration of machine learning techniques with horizontal-to-vertical spectral ratio (HVSR) methodologies. To improve model accuracy, the research employs outlier detection methods and, synthetic minority over-sampling technique (SMOTE) for data balance, and evaluates using seven machine learning models using seismic data from KiK-net. Notably, light gradient boosting method (LGBM), gradient boosting, and decision tree models exhibit improved performance when coupled with SMOTE, while Multiple linear regression (MLR) and Support vector machine (SVM) models show reduced efficacy. Outlier detection techniques significantly enhance accuracy, particularly for LGBM, gradient boosting, and voting boosting. The ensemble of LGBM with the isolation forest and SMOTE achieves the highest accuracy of 0.91, with LGBM and local outlier factor yielding the highest F1-score of 0.79. Consistently outperforming other models, LGBM proves most efficient for seismic site classification when supported by appropriate preprocessing procedures. These findings show the significance of outlier detection and data balancing for precise seismic soil classification prediction, offering insights and highlighting the potential of machine learning in optimizing site classification accuracy.

• Journal of Information Processing Systems
• /
• v.20 no.4
• /
• pp.558-573
• /
• 2024

Considering factors such as illumination, camera quality variations, and background-specific variations, identifying a face using a smartphone-based facial image capture application is challenging. Face Image Quality Assessment refers to the process of taking a face image as input and producing some form of "quality" estimate as an output. Typically, quality assessment techniques use deep learning methods to categorize images. The models used in deep learning are shown as black boxes. This raises the question of the trustworthiness of the models. Several explainability techniques have gained importance in building this trust. Explainability techniques provide visual evidence of the active regions within an image on which the deep learning model makes a prediction. Here, we developed a technique for reliable prediction of facial images before medical analysis and security operations. A combination of gradient-weighted class activation mapping and local interpretable model-agnostic explanations were used to explain the model. This approach has been implemented in the preselection of facial images for skin feature extraction, which is important in critical medical science applications. We demonstrate that the use of combined explanations provides better visual explanations for the model, where both the saliency map and perturbation-based explainability techniques verify predictions.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2009.10a
• /
• pp.684-685
• /
• 2009

• Korean Journal of Remote Sensing
• /
• v.7 no.1
• /
• pp.45-67
• /
• 1991

An overview is given on stochastic techniques with which remotely sensed data may be used together with ground measurements for purposes of state estimation and prediction. They can explicitly account for spatiotemporal differences in measurement characteristics between ground measurements and remotely sensed data, and are suitable for highly variant space or space-time processes, such as atmosperic processes, which may be viewed as (containing) a random process. For state estimation of static ststems, optimal linear estimation is described. As alternatives, various co-kriging estimation techniques are also described, including simple, ordinary, universal, lognormal, disjunctive, indicator, and Bayesian extersion to simple and lognormal. For illustrative purposes, very simple examples of optimal linear estimation and simple co-kriging are given. For state estimation and prediction of dynamic system, distributed-parameter kalman filter is described. Issues concerning actual implemention are given, and with application potential are described.

• Journal of Biosystems Engineering
• /
• v.38 no.3
• /
• pp.192-198
• /
• 2013

Purpose: Methods for non-destructive estimation of product quality have been reported in various industrial fields, but the application of ultrasonic techniques for the agricultural products of potatoes, pears, apples, watermelons, kiwis and tomatoes etc. have been rarely reported since the application of a contact-type ultrasonic transducer in agricultural products is very difficult. Therefore, this study sought to determine the firmness of apples using non-contact ultrasonic techniques. Methods: For this experiment, an ultrasonic experimental tester using a non-contact ultrasonic transducer was created, and a signal processing program was used to analyze the acquired ultrasonic reflected signal. Also, a universal testing machine was used to measure firmness parameters of the apples such as bioyield strength, a firmness factor, after the ultrasonic tests had been performed. Results: Six distance correction factors were calculated to obtain consistent values of ultrasonic properties regardless of the distance between the transducer and the surface of the subject. We developed prediction models of the bioyield strength using the distance correction factors. Conclusions: The optimum prediction model of the bioyield strength of apples using a non-contact ultrasonic technique was a multiple regression model ($R^2=0.9402$).

• IE interfaces
• /
• v.12 no.1
• /
• pp.158-165
• /
• 1999

One solution to the estimation of product reliability during the development phase is to measure reliability improvement over time and compare this improvement to previous product development progress. This paper presents the reliability growth theory and applies it to some subsystems of vehicles during their design, development and prototype testing. The data presented illustrates explicitly the prediction of the reliability growth in the product development cycle. The application of these techniques is a part of the product assurance function that plays an important role in product reliability improvement.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.523-523
• /
• 2000

We have developed a method to build time series prediction models by Genetic Programming (GP). Our proposed CP includes two new techniques. One is the parameter optimization algorithm, and the other is the new mutation operator. In this paper, the sunspot prediction experiment by our proposed CP was performed. The sunspot prediction is good benchmark, because many researchers have predicted them with various kinds of models. We make three experiments. The first is to compare our proposed method with the conventional methods. The second is to investigate about the relation between a model-building period and prediction precision. In the first and the second experiments, the long-term data of annual sunspots are used. The third is to try the prediction using monthly sunspots. The annual sunspots are a mean of the monthly sunspots. The behaviors of the monthly sunspot cycles in tile annual sunspot data become invisible. In the long-term data of the monthly sunspots, the behavior appears and is complicated. We estimate that the monthly sunspot prediction is more difficult than the annual sunspot prediction. The usefulness of our method in time series prediction is verified by these experiments.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.1
• /
• pp.30-45
• /
• 2024

This study introduces an effective method for predicting individual local tax delinquencies using prevalent machine learning and deep learning algorithms. The evaluation of credit risk holds great significance in the financial realm, impacting both companies and individuals. While credit risk prediction has been explored using statistical and machine learning techniques, their application to tax arrears prediction remains underexplored. We forecast individual local tax defaults in Republic of Korea using machine and deep learning algorithms, including convolutional neural networks (CNN), long short-term memory (LSTM), and sequence-to-sequence (seq2seq). Our model incorporates diverse credit and public information like loan history, delinquency records, credit card usage, and public taxation data, offering richer insights than prior studies. The results highlight the superior predictive accuracy of the CNN model. Anticipating local tax arrears more effectively could lead to efficient allocation of administrative resources. By leveraging advanced machine learning, this research offers a promising avenue for refining tax collection strategies and resource management.

• Transactions on Control, Automation and Systems Engineering
• /
• v.3 no.1
• /
• pp.10-14
• /
• 2001

We studied the use of time-related information, with and without prediction, to support human operators performing moni-toring and control tasks in the process. Based on monitoring and control techniques used for Project Management we developed a display design for the process industries. A simulated power plant was used to test the hypothesis that availability of predictions along with information on past trends can improve the performances of the human operator handling faults. Several designs of dis-plays were tested in the experiment in which human operators had to detect and handle two types of faults(local and systems wide) in the simulated electricity generation process. Analysis of the results revealed that temporal data, with and without prediction, signifi-cantly reduced response time. Our results encourage the integration of temporal information and prediction in displays used for the control processes to enhance the capabilities of the human operators. Based on the analysis we proposed some guidelines for the de-signer of the human interface of a process control system.