• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1835-1845
• /
• 2021

To accurately identify black ice and warn the drivers of information in advance so they can control speed and take preventive measures. In this paper, we propose a lightweight black ice detection network based on infrared road images. A black ice recognition network model based on CNN transfer learning has been developed. Additionally, to further improve the accuracy of black ice recognition, an enhanced lightweight network based on MobileNetV2 has been developed. To reduce the amount of calculation, linear bottlenecks and inverse residuals was used, and four bottleneck groups were used. At the same time, to improve the recognition rate of the model, each bottleneck group was connected to a 3×3 convolutional layer to enhance regional feature extraction and increase the number of feature maps. Finally, a black ice recognition experiment was performed on the constructed infrared road black ice dataset. The network model proposed in this paper had an accurate recognition rate of 99.07% for black ice.

• Journal of KIISE:Software and Applications
• /
• v.28 no.12
• /
• pp.947-954
• /
• 2001

In this paper, we propose a method for the recognition of various head gestures with automata technique applied to the sequence of facial pose states. Facial regions as detected by using the optimum facial color of I-component in YIQ model and the difference of images adaptively selected. And eye regions are extracted by using Sobel operator, projection, and the geometric location of eyes Hierarchical feature analysis is used to classify facial states, and automata technique is applied to the sequence of facial pose states to recognize 13 gestures: Gaze Upward, Downward, Left ward, Rightward, Forward, Backward Left Wink Right Wink Left Double Wink, Left Double Wink , Right Double Wink Yes, and No As an experimental result with total 1,488 frames acquired from 8 persons, it shows 99.3% extraction rate for facial regions, 95.3% extraction rate for eye regions 94.1% recognition rate for facial states and finally 99.3% recognition rate for head gestures. .

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.3
• /
• pp.267-275
• /
• 2019

Currently, due to the widespread use of a smartphone, QR codes allow users to access a variety of added services. However, the QR codes posted on curved surfaces tend to be non-uniformly illuminated and bring about the decline of recognition rate. So, in this paper, the block-adaptive binarization policy is adopted to find an optimal threshold appropriate for bimodal image like QR codes. For a large block, its histogram distribution is found to get an initial threshold and then the block is partitioned to reflect the local characteristics of small blocks. Also, morphological operation is applied to their neighboring boundary at the discontinuous at the QR code junction. This paper proposes an authentication method based on the color code, uniquely painted within QR code. Through a variety of practical experiments, it is shown that the proposed algorithm outperforms the conventional method in detecting QR code and also maintains good recognition rate up to 40 degrees on curved surfaces.

• Journal of Pharmacopuncture
• /
• v.25 no.1
• /
• pp.24-36
• /
• 2022

Objectives: This study is a comparative analysis of the satisfaction and recognition characteristics for traditional Korean medicine (TKM) in people with disabilities and the general population of Korea. Methods: Here, 5,000 subjects were categorized into two groups based on a disability rating using the data from the 2017 National Survey for the Usage of Korean Medicine. The relationships among the sociodemographic characteristics, TKM usage status, recognition of TKM usage, and recognition of the effectiveness of the TKM treatment were analyzed based on the disease. The response reliability was verified using the chi-square test analysis method. Results: Disabilities corresponded with low rates of high school or higher education (44%, 83.5%) and no jobs (56.9%, 33.5%), mostly the status of the low-income class with a monthly household income of < 1,500 USD (50.9%, 10.5%), poor health conditions (55.2%, 9.8%), high chronic disease prevalence rate (69.0%, 19.9%), high medical care rate (11.2%, 0.5%), and low commercial health insurance subscription rate (44%, 74.2%). Furthermore, people with disabilities visited TKM institutions more often (88.8%, 74.1%) with a high frequency TKM usage rate of ≥ 1-2 times a month (26.2%, 15.3%). They also reported that the cost of using the TKM was very high (14.7%, 8.8%) and that primarily the application of insurance benefits should be improved (52.6%, 47.5%). The treatment effectiveness for diseases was high for musculoskeletal disorders for both people with disabilities and the general population. Conclusion: Preferential application of insurance benefits for musculoskeletal diseases must be extended to the TKM treatment as well, as people with disabilities have a high recognition for these conditions with TKM. It is difficult to perform randomized controlled trials on people with disability. Therefore, large-scale observational and cohort studies should be conducted. We hope this study will help establish a suitable TKM policy for people with disabilities.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.2
• /
• pp.88-95
• /
• 2006

In this Paper. a method for improving the performance of automatic speech recognition (ASR) system for conversational speech is proposed. which mainly focuses on increasing the robustness against the rapidly speaking utterances. The proposed method doesn't require an additional speech recognition task to represent speaking rate quantitatively. Energy distribution for special bands is employed to detect the vowel regions, the number of vowels Per unit second is then computed as speaking rate. To improve the Performance for fast speech. in the pervious methods. a sequence of the feature vectors is expanded by a given scaling factor, which is computed by a ratio between the standard phoneme duration and the measured one. However, in the method proposed herein. utterances are classified by their speaking rates. and the scaling factor is determined individually for each class. In this procedure, a maximum likelihood criterion is employed. By the results from the ASR experiments devised for the 10-digits mobile phone number. it is confirmed that the overall error rate was reduced by $17.8\%$ when the proposed method is employed

• Journal of the Korean Society of Safety
• /
• v.37 no.5
• /
• pp.14-21
• /
• 2022

The purpose of this study was to apply the signal pattern recognition technique to the digital wireless fire-alarm system and to reduce unwanted fire alarms. In this study, the fire alarms of the K Institute, which operates the largest digital wireless fire-alarm system in Korea, were classified into normal operations and unwanted fire alarms, and these were analyzed and compared with actual fire signals. In addition, by designing a non-fire signal filter and applying it to the K Institute, we confirmed that the monthly unwanted fire alarm rate of all 5,713 detectors decreased sharply. In particular, the unwanted fire alarm rate for flame decreased from 1.09% to 0.11% and the unwanted fire alarm rate for smoke decreased from 0.65% to 0.035%.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.4
• /
• pp.42-48
• /
• 1997

This paper has apparaised ability of speaker recognition and speech recognition using correlation dimension and Lyapunov dimension. In this method, speech was regarded the cahos that the random signal is appeared in determinisitic raising system. we deduced exact correlation dimension and Lyapunov dimension with searching important orbit from AR model power spectrum when reconstruct strange attractor using Taken's embedding theory. We considered a usefulness of speech recognition and speaker recognition using correlation dimension and Lyapunov dimension that characterized reconstruction attractor. As a result of consideration, which were of use more the speaker recognition than speech recognition, and in case of speaker recognition using Lyapunov dimension were much recognition rate more than speaker recognitions using correlation dimension.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.2
• /
• pp.160-166
• /
• 2002

In this paper, we implement a new vocabulary-independent speech recognition system that uses CV, VCCV, VC recognition unit. Since these recognition units are extracted in the trowel region of syllable, the segmentation is easy and robust. And in the case of not existing VCCV unit, the units are replaced by combining VC and CV semi-syllable model. Clustering of vowel group and applying combination rule to the substitution model in the case of not existing of VCCV model lead to 5.2% recognition performance improvement from 90.4% (Model A) to 95.6% (Model C) in the first candidate. The recognition results that is 98.8% recognition rate in the second candidate confirm the effectiveness of the proposed method.

• Journal of the Korea Convergence Society
• /
• v.5 no.1
• /
• pp.35-41
• /
• 2014

An automatic speech recognition system is one of the popular research problems. There are many research groups working in this field for different language including Japanese. Japanese vowel recognition is one of important parts in the Japanese speech recognition system. The vowel classification system with the Mamdani fuzzy inference system was developed in this research. We tested our system on the blind test data set collected from one male native Japanese speaker and four male non-native Japanese speakers. All subjects in the blind test data set were not the same subjects in the training data set. We found out that the classification rate from the training data set is 95.0 %. In the speaker-independent experiments, the classification rate from the native speaker is around 70.0 %, whereas that from the non-native speakers is around 80.5 %.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.21 no.5
• /
• pp.501-509
• /
• 2010

In this paper, the interference avoidance performance of the RFID reader with the compressive receiver was analyzed. In the environment of the multiple dense readers operating, the recognition rates of the conventional RFID reader and the proposed RFID reader with the compressive receiver were measured and compared. The recognition rate of the proposed reader was improved more than 2.7 times compared to the conventional reader. Especially, in the environment of two proposed RFID readers operating simultaneously, little degradation of the recognition rate was observed.