• ETRI Journal
• /
• v.42 no.6
• /
• pp.886-898
• /
• 2020

Unusual data patterns or outliers can be generated because of human errors, incorrect measurements, or malicious activities. Detecting outliers is a difficult task that requires complex ensembles. An ideal outlier detection ensemble should consider the strengths of individual base detectors while carefully combining their outputs to create a strong overall ensemble and achieve unbiased accuracy with minimal variance. Selecting and combining the outputs of dissimilar base learners is a challenging task. This paper proposes a model that utilizes heterogeneous base learners. It adaptively boosts the outcomes of preceding learners in the first phase by assigning weights and identifying high-performing learners based on their local domains, and then carefully fuses their outcomes in the second phase to improve overall accuracy. Experimental results from 10 benchmark datasets are used to train and test the proposed model. To investigate its accuracy in terms of separating outliers from inliers, the proposed model is tested and evaluated using accuracy metrics. The analyzed data are presented as crosstabs and percentages, followed by a descriptive method for synthesis and interpretation.

• International Journal of Advanced Culture Technology
• /
• v.11 no.1
• /
• pp.320-324
• /
• 2023

As urbanization accelerates and facilities that use energy increase, human life and property damage due to fire is increasing. Therefore, a fire monitoring system capable of quickly detecting a fire is required to reduce economic loss and human damage caused by a fire. In this study, we aim to develop an improved artificial intelligence model that can increase the accuracy of low fire alarms by mixing DeepSORT, which has strengths in object tracking, with the YOLOv5s model. In order to develop a fire detection model that is faster and more accurate than the existing artificial intelligence model, DeepSORT, a technology that complements and extends SORT as one of the most widely used frameworks for object tracking and YOLOv5s model, was selected and a mixed model was used and compared with the YOLOv5s model. As the final research result of this paper, the accuracy of YOLOv5s model was 96.3% and the number of frames per second was 30, and the YOLOv5s_DeepSORT mixed model was 0.9% higher in accuracy than YOLOv5s with an accuracy of 97.2% and number of frames per second: 30.

• 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.

• Imaging Science in Dentistry
• /
• v.33 no.2
• /
• pp.91-95
• /
• 2003

Purpose : To compare the diagnostic accuracy of proximal caries detection between Kodak Insight film and the Biomedisys CDX2000HQ digital (CCD) sensor. Materials and Methods: 156 proximal surfaces of extracted teeth, 78 of which had chemical artificial caries, were used in this study. Four observers interpreted the radiographs using a five-point confidence rating scale to record their diagnoses. The results were analyzed by receiver operating characteristic curves, ANOVA and Kappa values. Result: Analysis using receiver operating characteristic curves revealed the areas under each curve which indicated a diagnostic accuracy of 0.951 in Insight and 0.952 in CDX2000HQ digital sensor. ANOVA revealed no significant differences between the two images with respect to caries detection. Kappa values indicated that the mean intra-observer agreement was 0.85 and inter-observer agreement 0.71 in conventional radiography. In digital radiography, the mean intra-observer agreement was 0.84 and inter-observer agreement 0.72. Conclusion: The results suggest that no significant difference exists between the two modalities for artificial caries detection and that CDX2000HQ was as good as Insight film for this purpose.

• Journal of Information Processing Systems
• /
• v.11 no.4
• /
• pp.538-555
• /
• 2015

Event detection based on using features from a static grid can give poor results from the viewpoint of two main aspects: the position of the camera and the position of the event that is occurring in the scene. The former causes problems when training and test events are at different distances from the camera to the actual position of the event. The latter can be a source of problems when training events take place in any position in the scene, and the test events take place in a position different from the training events. Both issues degrade the accuracy of the static grid method. Therefore, this work proposes a method called a dynamic grid for event detection, which can tackle both aspects of the problem. In our experiment, we used the dynamic grid method to detect four types of event patterns: implosion, explosion, two-way, and one-way using a Multimedia Analysis and Discovery (MAD) pedestrian dataset. The experimental results show that the proposed method can detect the four types of event patterns with high accuracy. Additionally, the performance of the proposed method is better than the static grid method and the proposed method achieves higher accuracy than the previous method regarding the aforementioned aspects.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.893-903
• /
• 2022

Recently, computer vision (CV)-based safety monitoring (i.e., object detection) system has been widely researched in the construction industry. Sufficient and high-quality data collection is required to detect objects accurately. Such data collection is significant for detecting small objects or images from different camera angles. Although several previous studies proposed novel data augmentation and synthetic data generation approaches, it is still not thoroughly addressed (i.e., limited accuracy) in the dynamic construction work environment. In this study, we proposed a game engine-driven synthetic data generation model to enhance the accuracy of the CV-based object detection model, mainly targeting small objects. In the virtual 3D environment, we generated synthetic data to complement training images by altering the virtual camera angles. The main contribution of this paper is to confirm whether synthetic data generated in the game engine can improve the accuracy of the CV-based object detection model.

• International Journal of Computer Science & Network Security
• /
• v.23 no.7
• /
• pp.202-209
• /
• 2023

Android malware is now on the rise, because of the rising interest in the Android operating system. Machine learning models may be used to classify unknown Android malware utilizing characteristics gathered from the dynamic and static analysis of an Android applications. Anti-virus software simply searches for the signs of the virus instance in a specific programme to detect it while scanning. Anti-virus software that competes with it keeps these in large databases and examines each file for all existing virus and malware signatures. The proposed model aims to provide a machine learning method that depend on the malware detection method for Android inability to detect malware apps and improve phone users' security and privacy. This system tracks numerous permission-based characteristics and events collected from Android apps and analyses them using a classifier model to determine whether the program is good ware or malware. This method used the machine learning techniques KNN-SVM, DBN, and GRU in which help to find the accuracy which gives the different values like KNN gives 87.20 percents accuracy, SVM gives 91.40 accuracy, Naive Bayes gives 85.10 and DBN-GRU Gives 97.90. Furthermore, in this paper, we simply employ standard machine learning techniques; but, in future work, we will attempt to improve those machine learning algorithms in order to develop a better detection algorithm.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.30-33
• /
• 2023

The recent scholarly focus has been directed towards the expeditious and accurate detection of salient objects, a task that poses considerable challenges for resource-limited edge devices due to the high computational demands of existing models. To mitigate this issue, some contemporary research has favored inference speed at the expense of accuracy. In an effort to reconcile the intrinsic trade-off between accuracy and computational efficiency, we present novel model for salient object detection. Our model incorporate group-wise attentive module within the decoder of the encoder-decoder framework, with the aim of minimizing computational overhead while preserving detection accuracy. Additionally, the proposed architectural design employs attention mechanisms to generate boundary information and semantic features pertinent to the salient objects. Through various experimentation across five distinct datasets, we have empirically substantiated that our proposed models achieve performance metrics comparable to those of computationally intensive state-of-the-art models, yet with a marked reduction in computational complexity.

• Journal of Information Processing Systems
• /
• v.19 no.5
• /
• pp.688-701
• /
• 2023

The conventional methods of network intrusion detection system (NIDS) cannot measure the trend of intrusiondetection targets effectively, which lead to low detection accuracy. In this study, a NIDS method which based on a deep neural network in a big-data environment is proposed. Firstly, the entire framework of the NIDS model is constructed in two stages. Feature reduction and anomaly probability output are used at the core of the two stages. Subsequently, a convolutional neural network, which encompasses a down sampling layer and a characteristic extractor consist of a convolution layer, the correlation of inputs is realized by introducing bidirectional long short-term memory. Finally, after the convolution layer, a pooling layer is added to sample the required features according to different sampling rules, which promotes the overall performance of the NIDS model. The proposed NIDS method and three other methods are compared, and it is broken down under the conditions of the two databases through simulation experiments. The results demonstrate that the proposed model is superior to the other three methods of NIDS in two databases, in terms of precision, accuracy, F1- score, and recall, which are 91.64%, 93.35%, 92.25%, and 91.87%, respectively. The proposed algorithm is significant for improving the accuracy of NIDS.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_2
• /
• pp.975-988
• /
• 2020

Change detection is the process of identifying changes by observing the multi-temporal images at different times, and it is an important technique in remote sensing using satellite images. Among the change detection methods, the unsupervised change detection technique has the advantage of extracting rapidly the change area as a binary image. However, it is difficult to understand the changing pattern of land cover in binary images. This study used grid points generated from seamless digital map to evaluate the satellite image change detection results. The land cover change results were extracted using multi-temporal KOMPSAT-3A (K3A) data taken by Gimje Free Trade Zone and change detection algorithm used Spectral Angle Mapper (SAM). Change detection results were presented as binary images using the methods Otsu, Kittler, Kapur, and Tsai among the automated threshold selection algorithms. To consider the seasonal change of vegetation in the change detection process, we used the threshold of Differenced Normalized Difference Vegetation Index (dNDVI) through the probability density function. The experimental results showed the accuracy of the Otsu and Kapur was the highest at 58.16%, and the accuracy improved to 85.47% when the seasonal effects were removed through dNDVI. The algorithm generated based on this research is considered to be an effective method for accuracy assessment and identifying changes pattern when applied to unsupervised change detection.