• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.309-311
• /
• 2022

Oral cancer is a type of cancer that has a high possibility to be cured if it is threatened earlier. The convolutional neural network is very popular for being a good algorithm for image recognition. In this research, we try to compare 4 different architectures of the CNN algorithm: Convnet, VGG16, Inception V3, and Resnet. As we compared those 4 architectures we found that VGG16 and Resnet model has better performance with an 85.35% accuracy rate compared to the other 3 architectures. In the future, we are sure that image recognition can be more developed to identify oral cancer earlier.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.39 no.2
• /
• pp.176-181
• /
• 2002

In this paper, we consider the optimal control of detection threshold to minimize the conditional expectation of mean-square state estimation error for a probabilistic data association (PDA) filter. Earlier works on this problem involved the cumbersome graphical optimization algorithm or time-consuming numerical optimization algorithm. Using the numerical approximation of information reduction factor, we obtained the suboptimal detection threshold in a closed-form. This results are very useful for real- time implementation.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2006.11a
• /
• pp.165-168
• /
• 2006

Exponential smoothing methods do not adapt well to unexpected changes in underlying process. Over the past few decades a number of adaptive smoothing models have been proposed which allow for the continuous adjustment of the smoothing constant value in order to provide a much earlier detection of unexpected changes. However, most of previous studies presented ad hoc procedure of adaptive forecasting without any theoretical background. In this paper, we propose a detection-adaptation procedure applied to simple and Holt's linear method. We derive level and slope change detection statistics based on Bayesian statistical theory and present distribution of the statistics by simulation method. The proposed procedure is compared with previous adaptive forecasting models using simulated data and economic time series data.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.12
• /
• pp.1710-1715
• /
• 2014

In this paper, we propose a novel on-chip test logic for TSV fault detection in 3-dimensional integrated circuits. The proposed logic called OTT realizes the input signal delay-based TSV test method introduced earlier. OTT only includes one F/F, two MUXs, and some additional logic for signal delay. Thus, it requires small silicon area suitable for TSV testing. Both pre-bond and post-bond TSV tests are able to use OTT for short or open fault as well as small delay fault detection.

• Science of Emotion and Sensibility
• /
• v.8 no.1
• /
• pp.1-7
• /
• 2005

This paper reports several emotion detecting methods based on various attributes of human voice. These methods have been developed at our Engineering Systems Laboratory. It is noted that, in all of the proposed methods, only prosodic information in voice is used for emotion recognition and semantic information in voice is not used. Different types of neural networks(NNs) are used for detection depending on the type of voice parameters. Earlier approaches separately used linear prediction coefficients(LPCs) and time series data of pitch but they were combined in later studies. The proposed methods are explained first and then evaluation experiments of individual methods and their performances in emotion detection are presented and compared.

• Proceedings of the IEEK Conference
• /
• 2007.07a
• /
• pp.219-220
• /
• 2007

In this paper, we proposed image processing technique for automatic real time fire and smoke detection in tunnel environment. To avoid the large scale of damage of fire occurred in the tunnel, it is necessary to have a system to minimize and to discover the incident as fast as possible. The fire and smoke detection is different from the forest fire detection as there are elements such as car and tunnel lights and others that are different from the forest environment so that an indigenous algorithm has to be developed. The two algorithms proposed in this paper, are able to detect the exact position, at the earlier stage of incident.

• International Journal of Computer Science & Network Security
• /
• v.24 no.5
• /
• pp.129-134
• /
• 2024

Object Detection is an emerging technology in the field of Computer Vision and Image Processing that deals with detecting objects of a particular class in digital images. It has considered being one of the complicated and challenging tasks in computer vision. Earlier several machine learning-based approaches like SIFT (Scale-invariant feature transform) and HOG (Histogram of oriented gradients) are widely used to classify objects in an image. These approaches use the Support vector machine for classification. The biggest challenges with these approaches are that they are computationally intensive for use in real-time applications, and these methods do not work well with massive datasets. To overcome these challenges, we implemented a Deep Learning based approach Convolutional Neural Network (CNN) in this paper. The Proposed approach provides accurate results in detecting objects in an image by the area of object highlighted in a Bounding Box along with its accuracy.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.14
• /
• pp.5613-5618
• /
• 2015

Clinicians should looking for techniques that helps to early diagnosis of cancer, because early cancer detection is critical to increase survival and cost effectiveness of treatment, and as a result decrease mortality rate. Medical images are the most important tools to provide assistance. However, medical images have some limitations for optimal detection of some neoplasias, originating either from the imaging techniques themselves, or from human visual or intellectual capacity. Image processing techniques are allowing earlier detection of abnormalities and treatment monitoring. Because the time is a very important factor in cancer treatment, especially in cancers such as the lung and breast, imaging techniques are used to accelerate diagnosis more than with other cancers. In this paper, we outline experience in use of image processing techniques for lung and breast cancer diagnosis. Looking at the experience gained will help specialists to choose the appropriate technique for optimization of diagnosis through medical imaging.

• BMB Reports
• /
• v.41 no.10
• /
• pp.685-692
• /
• 2008

Colorectal cancer (CRC) is the third most common malignancy in the world. Because CRC develops slowly from removable precancerous lesions, detection of the disease at an early stage during regular health examinations can reduce both the incidence and mortality of the disease. Although sigmoidoscopy offers significant improvements in the detection rate of CRC, its diagnostic value is limited by its high costs and inconvenience. Therefore, there is a compelling need for the identification of noninvasive biomarkers that can enable earlier detection of CRC. Accordingly, many validation studies have been conducted to evaluate genetic, epigenetic or protein markers that can be detected in the stool or in serum. Currently, the fecal-occult blood test is the most widely used method of screening for CRC. However, advances in genomics and proteomics combined with developments in other relevant fields will lead to the discovery of novel non invasive biomarkers whose usefulness will be tested in larger validation studies. Here, non-invasive molecular biomarkers that are currently used in clinical settings and have the potential for use as CRC biomarkers are discussed.

• Journal of Biomedical Engineering Research
• /
• v.18 no.3
• /
• pp.315-323
• /
• 1997

Driving is a complex vigilance task that includes improper lookout, excessive speed and inattention. The primary objective of this research is to detect driver drowsiness so that the driver can be alerted to an impending traffic accident in performance. We developed the automatic detection and warning system during drowsy driving. A drowsiness detection system must be able to monitor driver status and detect the detrimental changes of a driver performance. Eyeblink has been found to be a reliable factor of drowsiness detection in earlier studies. As an additional parameter, we also considered the yawning which often occurs in a low vigilance state and predicts the drowsy state. We used a computer vision method to extract the eyeblink and yawning in the face image sequences. When the drowsy state was detected, the driver was refreshed by alarming device and menthol scent generator after deciding the warning level by fuzzy logic. For the evaluation of our system, we measured the physiological parameters such as EOG and EEG. The results indicated that it is possible to detect and alert the driver drowsiness temporarily or continuously by using our system.