• The Journal of the Acoustical Society of Korea
• /
• v.26 no.1E
• /
• pp.21-26
• /
• 2007

In this paper, we propose a modified Viterbi algorithm to compensate for endpoint detection error during the decoding phase of an isolated word recognition task. Since the conventional Viterbi algorithm explores only the search space whose boundaries are fixed to the endpoints of the segmented utterance by the endpoint detector, the recognition performance is highly dependent on the accuracy level of endpoint detection. Inaccurately segmented word boundaries lead directly to recognition error. In order to relax the degradation of recognition accuracy due to endpoint detection error, we describe an unconstrained search of word boundaries and present an algorithm to explore the search space with efficiency. The proposed algorithm was evaluated by performing a variety of simulated endpoint detection error cases on an isolated word recognition task. The proposed algorithm reduced the Word Error Rate (WER) considerably, from 84.4% to 10.6%, while consuming only a little more computation power.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.6
• /
• pp.1150-1158
• /
• 2010

In this paper, a new reliable portable activity monitoring device implemented with the buddhist-style bowing activity and walking step detection algorithm, is presented. In order to monitor the bowing and walking activities, miniaturized 3-axis accelerometer sensor with the sensitivity of 800 mV/g was used. After initial signal conditioning, vector magnitude of accelerometer signals was calculated. Syntactic peak detection method was used in order to feature points. All signal processing algorithms were implemented in ultra-low power microcontroller MSP430 with double precision floating point arithmetic. For evaluation, 19 young man($24.22\pm5.22$ yrs) and woman($22.28\pm2.72$ yrs) were involved. The accuracy of the proposed algorithms were 98.91 %($\pm0.011$) for walking step detection and 98.25 %($\pm0.023$) for buddhist-style bowing activity. Comparing to the commercialized pedometer accuracy, 87.1 %($\pm0.058$), the proposed walking step detection algorithms show more reliable accuracy.

• Korean Journal of Remote Sensing
• /
• v.33 no.1
• /
• pp.89-95
• /
• 2017

Ship detection in synthetic aperture radar(SAR)imagery has long been an active research topic and has many applications. In this paper,we propose an efficient method for detecting ships from SAR imagery using filtering. This method exploits ship masking using a median filter that considers maximum ship sizes and detects ships from the reference image, to which a Non-Local means (NL-means) filter is applied for speckle de-noising and a differential image created from the difference between the reference image and the median filtered image. As the pixels of the ship in the SAR imagery have sufficiently higher values than the surrounding sea, the ship detection process is composed primarily of filtering based on this characteristic. The performance test for this method is validated using KOMPSAT-5 (Korea Multi-Purpose Satellite-5) SAR imagery. According to the accuracy assessment, the overall accuracy of the region that does not include land is 76.79%, and user accuracy is 71.31%. It is demonstrated that the proposed detection method is suitable to detect ships in SAR imagery and enables us to detect ships more easily and efficiently.

• Current Optics and Photonics
• /
• v.4 no.3
• /
• pp.210-220
• /
• 2020

Aiming at the problem that the Local Sparse Difference Index algorithm has low accuracy and low efficiency when detecting target anomalies in a hyperspectral image, this paper proposes a Weighted Collaborative Representation and Sparse Difference-Based Hyperspectral Anomaly Detection algorithm, to improve detection accuracy for a hyperspectral image. First, the band subspace is divided according to the band correlation coefficient, which avoids the situation in which there are multiple solutions of the sparse coefficient vector caused by too many bands. Then, the appropriate double-window model is selected, and the background dictionary constructed and weighted according to Euclidean distance, which reduces the influence of mixing anomalous components of the background on the solution of the sparse coefficient vector. Finally, the sparse coefficient vector is solved by the collaborative representation method, and the sparse difference index is calculated to complete the anomaly detection. To prove the effectiveness, the proposed algorithm is compared with the RX, LRX, and LSD algorithms in simulating and analyzing two AVIRIS hyperspectral images. The results show that the proposed algorithm has higher accuracy and a lower false-alarm rate, and yields better results.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.245-265
• /
• 2022

In response to problems such as insufficient extraction information, low detection accuracy, and frequent misdetection in the field of Thangka image defects, this paper proposes a YOLOv5 prediction algorithm fused with the attention mechanism. Firstly, the Backbone network is used for feature extraction, and the attention mechanism is fused to represent different features, so that the network can fully extract the texture and semantic features of the defect area. The extracted features are then weighted and fused, so as to reduce the loss of information. Next, the weighted fused features are transferred to the Neck network, the semantic features and texture features of different layers are fused by FPN, and the defect target is located more accurately by PAN. In the detection network, the CIOU loss function is used to replace the GIOU loss function to locate the image defect area quickly and accurately, generate the bounding box, and predict the defect category. The results show that compared with the original network, YOLOv5-SE and YOLOv5-CBAM achieve an improvement of 8.95% and 12.87% in detection accuracy respectively. The improved networks can identify the location and category of defects more accurately, and greatly improve the accuracy of defect detection of Thangka images.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.2
• /
• pp.77-83
• /
• 2022

In this paper, the two-stage object detection approach is proposed to implement a deep learning-based label inspection system on edge computing environments. Since the label printed on the products during the production process contains important information related to the product, it is significantly to check the label information is correct. The proposed system uses the lightweight deep learning model that able to employ in the low-performance edge computing devices, and the two-stage object detection approach is applied to compensate for the low accuracy relatively. The proposed Two-Stage object detection approach consists of two object detection networks, Label Area Detection Network and Character Detection Network. Label Area Detection Network finds the label area in the product image, and Character Detection Network detects the words in the label area. Using this approach, we can detect characters precise even with a lightweight deep learning models. The SF-YOLO model applied in the proposed system is the YOLO-based lightweight object detection network designed for edge computing devices. This model showed up to 2 times faster processing time and a considerable improvement in accuracy, compared to other YOLO-based lightweight models such as YOLOv3-tiny and YOLOv4-tiny. Also since the amount of computation is low, it can be easily applied in edge computing environments.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.1
• /
• pp.41-49
• /
• 2022

This paper proposes a novel lane detection algorithm based on inverse perspective transformation and machine learning in lightweight embedded system. The inverse perspective transformation method is presented for obtaining a bird's-eye view of the scene from a perspective image to remove perspective effects. This method requires only the internal and external parameters of the camera without a homography matrix with 8 degrees of freedom (DoF) that maps the points in one image to the corresponding points in the other image. To improve the accuracy and speed of lane detection in complex road environments, machine learning algorithm that has passed the first classifier is used. Before using machine learning, we apply a meaningful first classifier to the lane detection to improve the detection speed. The first classifier is applied in the bird's-eye view image to determine lane regions. A lane region passed the first classifier is detected more accurately through machine learning. The system has been tested through the driving video of the vehicle in embedded system. The experimental results show that the proposed method works well in various road environments and meet the real-time requirements. As a result, its lane detection speed is about 3.85 times faster than edge-based lane detection, and its detection accuracy is better than edge-based lane detection.

• Journal of Information Processing Systems
• /
• v.19 no.1
• /
• pp.109-117
• /
• 2023

Defect detection is one of the key factors in fabric quality control. To improve the speed and accuracy of denim fabric defect detection, this paper proposes a defect detection algorithm based on cascading feature extraction architecture. Firstly, this paper extracts these weight parameters of the pre-trained VGG16 model on the large dataset ImageNet and uses its portability to train the defect detection classifier and the defect recognition classifier respectively. Secondly, retraining and adjusting partial weight parameters of the convolution layer were retrained and adjusted from of these two training models on the high-definition fabric defect dataset. The last step is merging these two models to get the defect detection algorithm based on cascading architecture. Then there are two comparative experiments between this improved defect detection algorithm and other feature extraction methods, such as VGG16, ResNet-50, and Xception. The results of experiments show that the defect detection accuracy of this defect detection algorithm can reach 94.3% and the speed is also increased by 1-3 percentage points.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.2
• /
• pp.494-510
• /
• 2024

Internet users are exposed to sophisticated cyberattacks that intrusion detection systems have difficulty detecting. Therefore, research is increasing on intrusion detection methods that use artificial intelligence technology for detecting novel cyberattacks. Unsupervised learning-based methods are being researched that learn only from normal data and detect abnormal behaviors by finding patterns. This study developed an anomaly-detection method based on unsupervised machines and deep learning for a network intrusion detection system (NIDS). We present a hybrid anomaly detection approach based on unsupervised learning techniques using the autoencoder (AE), Isolation Forest (IF), and Local Outlier Factor (LOF) algorithms. An oversampling approach that increased the detection rate was also examined. A hybrid approach that combined deep learning algorithms and traditional machine learning algorithms was highly effective in setting the thresholds for anomalies without subjective human judgment. It achieved precision and recall rates respectively of 88.2% and 92.8% when combining two AEs, IF, and LOF while using an oversampling approach to learn more unknown normal data improved the detection accuracy. This approach achieved precision and recall rates respectively of 88.2% and 94.6%, further improving the detection accuracy compared with the hybrid method. Therefore, in NIDS the proposed approach provides high reliability for detecting cyberattacks.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.44 no.1
• /
• pp.18-24
• /
• 2018

Objectives: Foreign bodies (FBs) account for 3.8% of all pathologies of the head and neck region, and approximately one third of them are missed on initial examination. Thus, FBs represent diagnostic challenges to maxillofacial surgeons, rendering it necessary to employ an appropriate imaging modality in suspected cases. Materials and Methods: In this cross-sectional study, five different materials, including wood, metal, glass, tooth and stone, were prepared in three sizes (0.5, 1, and 2 mm) and placed in three locations (soft tissue, air-filled space and bone surface) within a sheep's head (one day after death) and scanned by panoramic radiography, cone-beam computed tomography (CBCT), and ultrasonography (US) devices. The images were reviewed, and accuracy of the detection modalities was recorded. The data were analyzed statistically using the Kruskal-Wallis, Mann-Whitney U-test, Friedman, Wilcoxon signed-rank and kappa tests (P<0.05). Results: CBCT was more accurate in detection of FBs than panoramic radiography and US (P<0.001). Metal was the most visible FB in all of modalities. US was the most accurate technique for detecting wooden materials, and CBCT was the best modality for detecting all other materials, regardless of size or location (P<0.05). The detection accuracy of US was greater in soft tissue, while both CBCT and panoramic radiography had minimal accuracy in detection of FBs in soft tissue. Conclusion: CBCT was the most accurate detection modality for all the sizes, locations and compositions of FBs, except for the wooden materials. Therefore, we recommend CBCT as the gold standard of imaging for detecting FBs in the maxillofacial region.