• Journal of the Korea Society of Computer and Information
• /
• v.26 no.12
• /
• pp.77-84
• /
• 2021

In this paper, we propose a system that uses image data and beacon data to classify authorized and unauthorized perosn who are allowed to enter a group facility. The image data collected through the IP camera uses YOLOv4 to extract a person object, and collects beacon signal data (UUID, RSSI) through an application to compose a fingerprinting-based radio map. Beacon extracts user location data after CNN-LSTM-based learning in order to improve location accuracy by supplementing signal instability. As a result of this paper, it showed an accuracy of 93.47%. In the future, it can be expected to fusion with the access authentication process such as QR code that has been used due to the COVID-19, track people who haven't through the authentication process.

• Journal of Positioning, Navigation, and Timing
• /
• v.11 no.3
• /
• pp.217-227
• /
• 2022

In order to provide a location-based services regardless of indoor or outdoor space, it is important to provide position information of the terminal regardless of location. Among the wireless/mobile communication resources used for this purpose, Long Term Evolution (LTE) signal is a representative infrastructure that can overcome spatial limitations, but the positioning method based on the location of the base station has a disadvantage in that the accuracy is low. Therefore, a fingerprinting technique, which is a pattern recognition technology, has been widely used. The simplest yet widely applied algorithm among Fingerprint positioning technologies is k-Nearest Neighbors (kNN). However, in the kNN algorithm, it is difficult to find the optimal K value with the lowest positioning error for each location to be estimated, so it is generally fixed to an appropriate K value and used. Since the optimal K value cannot be applied to each estimated location, therefore, there is a problem in that the accuracy of the overall estimated location information is lowered. Considering this problem, this paper proposes a technique for adaptively varying the K value by using a Convolutional Neural Network (CNN) model among Artificial Neural Network (ANN) techniques. First, by using the signal information of the measured values obtained in the service area, an image is created according to the Physical Cell Identity (PCI) and Band combination, and an answer label for supervised learning is created. Then, the structure of the CNN is modeled to classify K values through the image information of the measurements. The performance of the proposed technique is verified based on actual data measured in the testbed. As a result, it can be seen that the proposed technique improves the positioning performance compared to using a fixed K value.

• Journal of the Institute of Convergence Signal Processing
• /
• v.10 no.1
• /
• pp.7-12
• /
• 2009

In this paper, we propose a directional feature extraction method for off-line handwritten numerals by using the morphological operations. Direction features are obtained from four directional line images, each of which contains horizontal, vertical, right-diagonal and left-diagonal lines in entire numeral lines. Conventional method for extracting directional features uses Kirsch masks which generate edge-shaped double line images for each direction, whereas our method uses directional erosion operations and generate single line images for each direction. To apply these directional erosion operations to the numeral image, preprocessing steps such as thinning and dilation are required, but resultant directional lines are more similar to numeral lines themselves. Our four [$4{\times}4$] directional features of a numeral are obtained from four directional line images through a zoning method. For obtaining the higher recognition rates of the handwrittern numerals, we use the multiple feature which is comprised of our proposed feature and the conventional features of a kirsch directional feature and a concavity feature. For recognition test with given features, we use a multi-layer perceptron neural network classifier which is trained with the back propagation algorithm. Through the experiments with the CENPARMI numeral database of Concordia University, we have achieved a recognition rate of 98.35%.

• Journal of Biomedical Engineering Research
• /
• v.25 no.5
• /
• pp.329-334
• /
• 2004

The electronic nose (E-nose) recently finds its applications in medical diagnosis, specifically on detection of diabetes, pulmonary or gastrointestinal problem, or infections by examining odors in the breath or tissues with its odor characterizing ability. The odor recognition performance of E-nose can be improved by manipulating the sensor array responses of vapors in time-profile forms. The different chemical interactions between the sensor materials and the volatile organic compounds (VOC's) leave unique marks in the signal profiles giving more information than collection of the conventional piecemal features, i.e., maximum sensitivity, signal slopes, rising time. In this study, to use them in vapor recognition task conveniently, a novel time-profile method was proposed, which is adopted from digital image pattern matching. The degrees of matching between 8 different vapors were evaluated by using the proposed method. The test vapors are measured by the silicon-based gas sensor array with 16 CB-polymer composites installed in membrane structure. The results by the proposed method showed clear discrimination of vapor species than by the conventional method.

• Journal of the Institute of Convergence Signal Processing
• /
• v.22 no.4
• /
• pp.149-155
• /
• 2021

In this study, we intend to develop a defective road surface object recognition model that automatically detects road surface defects that restrict the movement of the transportation handicapped using electric mobile devices with deep learning. For this purpose, road surface information was collected from the pedestrian and running routes where the electric mobility aid device is expected to move in five areas within the city of Busan. For data, images were collected by dividing the road surface and surroundings into objects constituting the surroundings. A series of recognition items such as the detection of breakage levels of sidewalk blocks were defined by classifying according to the degree of impeding the movement of the transportation handicapped in traffic from the collected data. A road surface object recognition deep learning model was implemented. In the final stage of the study, the performance verification process of a deep learning model that automatically detects defective road surface objects through model learning and validation after processing, refining, and annotation of image data separated and collected in units of objects through actual driving. proceeded.

• The Journal of the Acoustical Society of Korea
• /
• v.43 no.2
• /
• pp.225-233
• /
• 2024

Active sonar transmits sound waves to detect covertly maneuvering underwater objects and detects the signals reflected back from the target. However, in addition to the target's echo, the active sonar's received signal is mixed with seafloor, sea surface reverberation, biological noise, and other noise, making target recognition difficult. Conventional techniques for detecting signals above a threshold not only cause false detections or miss targets depending on the set threshold, but also have the problem of having to set an appropriate threshold for various underwater environments. To overcome this, research has been conducted on automatic calculation of threshold values through techniques such as Constant False Alarm Rate (CFAR) and application of advanced tracking filters and association techniques, but there are limitations in environments where a significant number of detections occur. As deep learning technology has recently developed, efforts have been made to apply it in the field of underwater target detection, but it is very difficult to acquire active sonar data for discriminator learning, so not only is the data rare, but there are only a very small number of targets and a relatively large number of non-targets. There are difficulties due to the imbalance of data. In this paper, the image of the energy distribution of the detection signal is used, and a classifier is learned in a way that takes into account the imbalance of the data to distinguish between targets and non-targets and added to the existing technique. Through the proposed technique, target misclassification was minimized and non-targets were eliminated, making target recognition easier for active sonar operators. And the effectiveness of the proposed technique was verified through sea experiment data obtained in the East Sea.

• Journal of Broadcast Engineering
• /
• v.23 no.3
• /
• pp.351-360
• /
• 2018

Human emotion recognition is a research topic that is receiving continuous attention in computer vision and artificial intelligence domains. This paper proposes a method for classifying human emotions through multiple neural networks based on multi-modal signals which consist of image, landmark, and audio in a wild environment. The proposed method has the following features. First, the learning performance of the image-based network is greatly improved by employing both multi-task learning and semi-supervised learning using the spatio-temporal characteristic of videos. Second, a model for converting 1-dimensional (1D) landmark information of face into two-dimensional (2D) images, is newly proposed, and a CNN-LSTM network based on the model is proposed for better emotion recognition. Third, based on an observation that audio signals are often very effective for specific emotions, we propose an audio deep learning mechanism robust to the specific emotions. Finally, so-called emotion adaptive fusion is applied to enable synergy of multiple networks. The proposed network improves emotion classification performance by appropriately integrating existing supervised learning and semi-supervised learning networks. In the fifth attempt on the given test set in the EmotiW2017 challenge, the proposed method achieved a classification accuracy of 57.12%.

• Journal of Korea Multimedia Society
• /
• v.15 no.11
• /
• pp.1305-1318
• /
• 2012

Image segmentation is one of the difficult research problems in machine vision and pattern recognition field. A commonly used segmentation method is the Otsu method. It is simpler and easier to implement but it fails if the histogram is unimodal or similar to unimodal. And if some target area is smaller than background object, then its histogram has the distribution close to unimodal. In this paper, we proposed an improved image segmentation method based on 1D Otsu method for a small target detection. To overcome drawbacks by unimodal histogram effect, we depressed the background histogram using a logarithm function. And to improve a signal to noise ratio, we used a local average value by the neighbor window for thresholding using 1D Otsu method. The experimental results show that our proposed algorithm performs better segmentation result than a traditional 1D Otsu method, and needs much less computational time than that of the 2D Otsu method.

• Journal of Korean Society for Geospatial Information Science
• /
• v.16 no.2
• /
• pp.87-95
• /
• 2008

Ladar (Laser Detection And Ranging, Lidar) is a sensor to acquire precise distances to the surfaces of target region using laser signals, which can be suitably applied to ATD (Automatic Target Detection) for guided missiles or aerial vehicles recently. It provides a range image in which each measured distance is expressed as the brightness of the corresponding pixel. Since the precise 3D models can be generated from the Ladar range image, more robust identification and recognition of the targets can be possible. If we simulate the data of Ladar sensor, we can efficiently use this simulator to design and develop Ladar sensors and systems and to develop the data processing algorithm. The purposes of this study are thus to simulate the signals of a Ladar sensor based on linear frequency modulation and to create range images from the simulated Ladar signals. We first simulated the laser signals of a Ladar using FM chirp modulator and then computed the distances from the sensor to a target using the FFT process of the simulated signals. Finally, we created the range image using the distances set.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2006.05a
• /
• pp.1001-1004
• /
• 2006

Many researches have been processed to reconstruct corrupted an image by noise in fields of signal processing such as image recognition and compute. vision, and AWGN(additive white gaussian noise) and impulse noise are representative. Impulse noise consists of fired-valued(salt & pepper) impulse noise and random-valued impulse noise, and non-linear filters such as SM(standard median) filters are used to remove this noise. But basic SM filters still generate many errors in edge regions of an image, and in order to overcome this problem a variety of methods have been researched. In this paper, we proposed an impulse noise removal algorithm which is superior to the edge preserving capacity. At this tine, after detecting a noise by using the noise detector, we applied a noise removal algorithm based on the min-max operation and compared the capacity with existing methods through simulation.