• Journal of Internet Computing and Services
• /
• v.2 no.1
• /
• pp.23-30
• /
• 2001

ILP processors require an accurate branch prediction scheme to achieve higher performance. Two-Level branch predictor has been known to achieve high prediction accuracy. But, when a branch accesses a PHT entry that was, previously updated by other branch, Two-level predictor may cause interferences. Negative interferences among all interferences have a negative effect on performance, since they can cause branch mispredictions. Agree predictor achieve high prediction accuracy by converting negative interferences to positive interferences by adding bias bits to BTB, but negative interferences may occur when bias bit is set incorrectly. This paper presents a new dynamic branch predictor which reduces negative interferences. In the proposed predictor, we attach hit bits to entries in BTB to change bias bit dynamically during the execution time, h a result the proposed scheme improve the accuracy of prediction by reducing negative Interferences effectively, To illustrate the effect of the proposed scheme, we evaluate the performance of this scheme using SPEC92int benchmarks, The results show that the proposed scheme can outperform traditional branch predictors.

• KIISE Transactions on Computing Practices
• /
• v.22 no.9
• /
• pp.455-460
• /
• 2016

Recently, with more severe types felonies such as robbery and sexual violence, the importance of crime prediction and prevention is emphasized. For accurate and prompt crime prediction and prevention, both a classification model of crime with high accuracy based on past criminal records and well-designed system interface are required. However previous studies on the analysis of crime factors have limitations in terms of accuracy due to the difficulty of data preprocessing. In addition, existing crime monitoring systems merely offer a vast amount of crime analysis results, thereby they fail to provide users with functions for more effective monitoring. In this paper, we propose a classification model for types of crime based on random-forest algorithms and system design factors for real-time crime prediction. From our experiments, we proved that our proposed classification model is superior to others that only use criminal records in terms of accuracy. Through the analysis of existing crime monitoring systems, we also designed and developed a system for real-time crime monitoring.

• Journal of Internet Computing and Services
• /
• v.17 no.2
• /
• pp.49-57
• /
• 2016

Ensemble classification involves combining multiple classifiers to obtain more accurate predictions than those obtained using individual models. Ensemble learning techniques are known to be very useful for improving prediction accuracy. Bagging is one of the most popular ensemble learning techniques. Bagging has been known to be successful in increasing the accuracy of prediction of the individual classifiers. Bagging draws bootstrap samples from the training sample, applies the classifier to each bootstrap sample, and then combines the predictions of these classifiers to get the final classification result. Bootstrap samples are simple random samples selected from the original training data, so not all bootstrap samples are equally informative, due to the randomness. In this study, we proposed a new method for improving the performance of the standard bagging ensemble by optimizing bootstrap samples. A genetic algorithm is used to optimize bootstrap samples of the ensemble for improving prediction accuracy of the ensemble model. The proposed model is applied to a bankruptcy prediction problem using a real dataset from Korean companies. The experimental results showed the effectiveness of the proposed model.

• Journal of KIISE:Computing Practices and Letters
• /
• v.12 no.5
• /
• pp.275-285
• /
• 2006

This paper proposes an efficient market mechanism-based resource transaction model for grid computing. This model predicts the next resource demand of users and suggests reasonable resource price for both of customers and resource providers. This model increases resource transactions between customers and resource providers and reduces the average of transaction response times from resource providers. For prediction accuracy improvement of resource demands and suggestion of reasonable resource price, this model introduces a statistics-based prediction model and a price decision model of microeconomics. For performance evaluating, this paper measures resource demand prediction accuracy rate of users, response time of resource transaction, the number of resource transactions, and resource utilization. With 87.45% of reliable prediction accuracy, this model works on the less 72.39% of response time than existing resource transaction models in a grid computing environment. The number of transactions and the resource utilization increase up to 162.56% and up to 230%, respectively.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.9
• /
• pp.1244-1253
• /
• 2021

In this paper, we propose a method for predicting in advance whether pedestrians will enter the hazardous area after the current time using the pedestrian trajectory prediction method and an efficient simplification method of the trajectory prediction network. In addition, we propose a method to apply KD(Knowledge Distillation) to a small network for real-time operation in an embedded environment. Using the correlation between predicted future paths and hazard zones, we determined whether to enter or not, and applied efficient KD when learning small networks to minimize performance degradation. Experimentally, it was confirmed that the model applied with the simplification method proposed improved the speed by 37.49% compared to the existing model, but led to a slight decrease in accuracy. As a result of learning a small network with an initial accuracy of 91.43% using KD, It was confirmed that it has improved accuracy of 94.76%.

• The Journal of the Korea Contents Association
• /
• v.19 no.1
• /
• pp.1-15
• /
• 2019

One of the biggest difficulties in the vocational training field is the dropout problem. A large number of students drop out during the training process, which hampers the waste of the state budget and the improvement of the youth employment rate. Previous studies have mainly analyzed the cause of dropouts. The purpose of this study is to propose a machine learning based model that predicts dropout in advance by using various information of learners. In particular, this study aimed to improve the accuracy of the prediction model by taking into consideration not only structured data but also unstructured data. Analysis of unstructured data was performed using Word2vec and Convolutional Neural Network(CNN), which are the most popular text analysis technologies. We could find that application of the proposed model to the actual data of a domestic vocational training institute improved the prediction accuracy by up to 20%. In addition, the support vector machine-based prediction model using both structured and unstructured data showed high prediction accuracy of the latter half of 90%.

• Journal of Korean Society of Water and Wastewater
• /
• v.35 no.1
• /
• pp.83-91
• /
• 2021

The increased turbidity in rivers during flood events has various effects on water environmental management, including drinking water supply systems. Thus, prediction of turbid water is essential for water environmental management. Recently, various advanced machine learning algorithms have been increasingly used in water environmental management. Ensemble machine learning algorithms such as random forest (RF) and gradient boosting decision tree (GBDT) are some of the most popular machine learning algorithms used for water environmental management, along with deep learning algorithms such as recurrent neural networks. In this study GBDT, an ensemble machine learning algorithm, and gated recurrent unit (GRU), a recurrent neural networks algorithm, are used for model development to predict turbidity in a river. The observation frequencies of input data used for the model were 2, 4, 8, 24, 48, 120 and 168 h. The root-mean-square error-observations standard deviation ratio (RSR) of GRU and GBDT ranges between 0.182~0.766 and 0.400~0.683, respectively. Both models show similar prediction accuracy with RSR of 0.682 for GRU and 0.683 for GBDT. The GRU shows better prediction accuracy when the observation frequency is relatively short (i.e., 2, 4, and 8 h) where GBDT shows better prediction accuracy when the observation frequency is relatively long (i.e. 48, 120, 160 h). The results suggest that the characteristics of input data should be considered to develop an appropriate model to predict turbidity.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.4
• /
• pp.771-780
• /
• 2024

In this study, we implemented a real-time pest detection and prediction system for a strawberry farm using a computer vision model based on the YOLOv5 architecture and an Isolation Forest Classifier. The model performance evaluation showed that the YOLOv5 model achieved a mean average precision (mAP 0.5) of 78.7%, an accuracy of 92.8%, a recall of 90.0%, and an F1-score of 76%, indicating high predictive performance. This system was designed to be applicable not only to strawberry farms but also to other crops and various environments. Based on data collected from a tomato farm, a new AI model was trained, resulting in a prediction accuracy of over 85% for major diseases such as late blight and yellow leaf curl virus. Compared to the previous model, this represented an improvement of more than 10% in prediction accuracy.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.2226-2229
• /
• 2003

A new method is presented to construct a classifier. This was accomplished by combining a generalized regression neural network (GRNN) and a genetic algorithm (GA). The classifier constructed in this way is referred to as a GA-GRNN. The GA played a role of controlling training factors simultaneously. In GA optimization, neuron spreads were represented in a chromosome. The proposed optimization method was applied to a data set, consisted of 4 different promoter sequences. The training and test data were composed of 115 and 58 sequence patterns, respectively. The range of neuron spreads was experimentally varied from 0.4 to 1.4 with an increment of 0.1. The GA-GRNN was compared to a conventional GRNN. The classifier performance was investigated in terms of the classification sensitivity and prediction accuracy. The GA-GRNN significantly improved the total classification sensitivity compared to the conventional GRNN. Also, the GA-GRNN demonstrated an improvement of about 10.1% in the total prediction accuracy. As a result, the proposed GA-GRNN illustrated improved classification sensitivity and prediction accuracy over the conventional GRNN.

• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.3
• /
• pp.183-192
• /
• 2017

k-nearest neighbor (K-NN) is a well-known classification algorithm, being feature space-based on nearest-neighbor training examples in machine learning. However, K-NN, as we know, is a lazy learning method. Therefore, if a K-NN-based system very much depends on a huge amount of history data to achieve an accurate prediction result for a particular task, it gradually faces a processing-time performance-degradation problem. We have noticed that many researchers usually contemplate only classification accuracy. But estimation speed also plays an essential role in real-time prediction systems. To compensate for this weakness, this paper proposes correlation coefficient-based clustering (CCC) aimed at upgrading the performance of K-NN by leveraging processing-time speed and plurality rule-based density (PRD) to improve estimation accuracy. For experiments, we used real datasets (on breast cancer, breast tissue, heart, and the iris) from the University of California, Irvine (UCI) machine learning repository. Moreover, real traffic data collected from Ojana Junction, Route 58, Okinawa, Japan, was also utilized to lay bare the efficiency of this method. By using these datasets, we proved better processing-time performance with the new approach by comparing it with classical K-NN. Besides, via experiments on real-world datasets, we compared the prediction accuracy of our approach with density peaks clustering based on K-NN and principal component analysis (DPC-KNN-PCA).