• The Journal of Korean Institute of Next Generation Computing
• /
• v.15 no.6
• /
• pp.7-14
• /
• 2019

The automatic monitoring and detection of crowd behavior in the surveillance videos has obtained significant attention in the field of computer vision due to its vast applications such as security, safety and protection of assets etc. Also, the field of crowd analysis is growing upwards in the research community. For this purpose, it is very necessary to detect and analyze the crowd behavior. In this paper, we proposed a deep learning-based method which detects abnormal activities in surveillance cameras installed in a smart city. A fine-tuned VGG-16 model is trained on publicly available benchmark crowd dataset and is tested on real-time streaming. The CCTV camera captures the video stream, when abnormal activity is detected, an alert is generated and is sent to the nearest police station to take immediate action before further loss. We experimentally have proven that the proposed method outperforms over the existing state-of-the-art techniques.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.14 no.5
• /
• pp.53-59
• /
• 2018

Due to the recent developments in computer vision technology, complex actions can be recognized with reasonable accuracy in smart cities. In contrast, violence recognition such as events related to fight and knife, has gained less attention. The capability of visual surveillance can be used for detecting fight in streets or in prison centers. In this paper, we proposed a deep learning-based violence recognition method for surveillance cameras. A convolutional neural network (CNN) model is trained and fine-tuned on available benchmark datasets of fights and knives for violence recognition. When an abnormal event is detected, an alarm can be sent to the nearest police station to take immediate action. Moreover, when the probabilities of fight and knife classes are predicted very low, this situation is considered as normal situation. The experimental results of the proposed method outperformed other state-of-the-art CNN models with high margin by achieving maximum 99.21% accuracy.

• The Journal of Society for e-Business Studies
• /
• v.24 no.1
• /
• pp.105-120
• /
• 2019

The World Health Organization (WHO) and other government agencies aroundthe world have warned against antibiotic-resistant bacteria due to abuse of antibiotics and are strengthening their care and monitoring to prevent infection. However, it is highly necessary to develop an expeditious and accurate prediction and estimating method for preemptive measures. Because it takes several days to cultivate the infecting bacteria to identify the infection, quarantine and contact are not effective to prevent spread of infection. In this study, the disease diagnosis and antibiotic prescriptions included in Electronic Health Records were embedded through neural embedding model and matrix factorization, and deep learning based classification predictive model was proposed. The f1-score of the deep learning model increased from 0.525 to 0.617when embedding information on disease and antibiotics, which are the main causes of antibiotic resistance, added to the patient's basic information and hospital use information. And deep learning model outperformed the traditional machine hospital use information. And deep learning model outperformed the traditional machine learning models.As a result of analyzing the characteristics of antibiotic resistant patients, resistant patients were more likely to use antibiotics in J01 than nonresistant patients who were diagnosed with the same diseases and were prescribed 6.3 times more than DDD.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.3
• /
• pp.42-52
• /
• 2022

Bus Information System (BIS) services are expanding nationwide to small and medium-sized cities, including large cities, and user satisfaction is continuously improving. In addition, technology development related to improving reliability of bus arrival time and improvement research to minimize errors continue, and above all, the importance of information accuracy is emerging. In this study, accuracy performance was evaluated using LSTM, a machine learning method, and compared with existing methodologies such as Kalman filter and neural network. As a result of analyzing the standard error for the actual travel time and predicted values, it was analyzed that the LSTM machine learning method has about 1% higher accuracy and the standard error is about 10 seconds lower than the existing algorithm. On the other hand, 109 out of 162 sections (67.3%) were analyzed to be excellent, indicating that the LSTM method was not entirely excellent. It is judged that further improved accuracy prediction will be possible when algorithms are fused through section characteristic analysis.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.11
• /
• pp.1627-1634
• /
• 2021

This paper introduces a low-power compact ADC circuit for analog Convolutional filter for low-power neural network accelerator SOC. While convolutional neural network accelerators can speed up the learning and inference process, they have drawback of consuming excessive power and occupying large chip area due to large number of multiply-and-accumulate operators when implemented in complex digital circuits. To overcome these drawbacks, we implemented an analog convolutional filter that consists of an analog multiply-and-accumulate arithmetic circuit along with an ADC. This paper is focused on the design optimization of a low-power 8bit SAR ADC for the analog convolutional filter accelerator We demonstrate how to minimize the capacitor-array DAC, an important component of SAR ADC, which is three times smaller than the conventional circuit. The proposed ADC has been fabricated in CMOS 65nm process. It achieves an overall size of 1355.7㎛², power consumption of 2.6㎼ at a frequency of 100MHz, SNDR of 44.19 dB, and ENOB of 7.04bit.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.51 no.3
• /
• pp.70-82
• /
• 2023

The recent surge of IT and data acquisition is shifting the paradigm in all aspects of life, and these advances are also affecting academic fields. Research topics and methods are being improved through academic exchange and connections. In particular, data-based research methods are employed in various academic fields, including landscape architecture, where continuous research is needed. Therefore, this study aims to investigate the possibility of developing a landscape preference evaluation and prediction model using machine learning, a branch of Artificial Intelligence, reflecting the current situation. To achieve the goal of this study, machine learning techniques were applied to the landscaping field to build a landscape preference evaluation and prediction model to verify the simulation accuracy of the model. For this, wind power facility landscape images, recently attracting attention as a renewable energy source, were selected as the research objects. For analysis, images of the wind power facility landscapes were collected using web crawling techniques, and an analysis dataset was built. Orange version 3.33, a program from the University of Ljubljana was used for machine learning analysis to derive a prediction model with excellent performance. IA model that integrates the evaluation criteria of machine learning and a separate model structure for the evaluation criteria were used to generate a model using kNN, SVM, Random Forest, Logistic Regression, and Neural Network algorithms suitable for machine learning classification models. The performance evaluation of the generated models was conducted to derive the most suitable prediction model. The prediction model derived in this study separately evaluates three evaluation criteria, including classification by type of landscape, classification by distance between landscape and target, and classification by preference, and then synthesizes and predicts results. As a result of the study, a prediction model with a high accuracy of 0.986 for the evaluation criterion according to the type of landscape, 0.973 for the evaluation criterion according to the distance, and 0.952 for the evaluation criterion according to the preference was developed, and it can be seen that the verification process through the evaluation of data prediction results exceeds the required performance value of the model. As an experimental attempt to investigate the possibility of developing a prediction model using machine learning in landscape-related research, this study was able to confirm the possibility of creating a high-performance prediction model by building a data set through the collection and refinement of image data and subsequently utilizing it in landscape-related research fields. Based on the results, implications, and limitations of this study, it is believed that it is possible to develop various types of landscape prediction models, including wind power facility natural, and cultural landscapes. Machine learning techniques can be more useful and valuable in the field of landscape architecture by exploring and applying research methods appropriate to the topic, reducing the time of data classification through the study of a model that classifies images according to landscape types or analyzing the importance of landscape planning factors through the analysis of landscape prediction factors using machine learning.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.8
• /
• pp.307-324
• /
• 2018

Recently, recurrent neural networks have been attracting attention in solving prediction problem of sequential data through structure considering time dependency. However, as the time step of sequential data increases, the problem of the gradient vanishing is occurred. Long short-term memory models have been proposed to solve this problem, but there is a limit to storing a lot of data and preserving it for a long time. Therefore, research on memory-augmented neural network (MANN), which is a learning model using recurrent neural networks and memory elements, has been actively conducted. In this paper, we describe the structure and characteristics of MANN models that emerged as a hot topic in deep learning field and present the latest techniques and future research that utilize MANN.

• Phonetics and Speech Sciences
• /
• v.12 no.3
• /
• pp.55-63
• /
• 2020

Voice conversion can be applied to various voice processing applications. It can also play an important role in data augmentation for speech recognition. The conventional method uses the architecture of voice conversion with speech synthesis, with Mel filter bank as the main parameter. Mel filter bank is well-suited for quick computation of neural networks but cannot be converted into a high-quality waveform without the aid of a vocoder. Further, it is not effective in terms of obtaining data for speech recognition. In this paper, we focus on performing voice-to-voice conversion using only the raw spectrum. We propose a deep learning model based on the transformer network, which quickly learns the voice conversion properties using an attention mechanism between source and target spectral components. The experiments were performed on TIDIGITS data, a series of numbers spoken by an English speaker. The conversion voices were evaluated for naturalness and similarity using mean opinion score (MOS) obtained from 30 participants. Our final results yielded 3.52±0.22 for naturalness and 3.89±0.19 for similarity.

• Journal of Ocean Engineering and Technology
• /
• v.33 no.5
• /
• pp.427-434
• /
• 2019

Artificial intelligence (AI)-aided research currently enjoys active use in a wide array of fields thanks to the rapid development of computing capability and the use of Big Data. Until now, forecasting methods were primarily based on physics models and statistical studies. Today, AI is utilized in disaster prevention forecasts by studying the relationships between physical factors and their characteristics. Current studies also involve combining AI and physics models to supplement the strengths and weaknesses of each aspect. However, prior to these studies, an optimization algorithm for the AI model should be developed and its applicability should be studied. This study aimed to improve the forecast performance by constructing a model for neural network optimization. An artificial neural network (ANN) followed the ever-changing path of a typhoon to produce similar typhoon predictions, while the optimization achieved by the neural network algorithm was examined by evaluating the activation function, hidden layer composition, and dropouts. A learning and test dataset was constructed from the available digital data of one typhoon that affected Korea throughout the record period (1951-2018). As a result of neural network optimization, assessments showed a higher degree of forecast accuracy.

• Journal of Broadcast Engineering
• /
• v.24 no.2
• /
• pp.234-242
• /
• 2019

In this paper, we propose a deep neural network which extracts SIFT feature points by determining whether the center pixel of a cropped image is a SIFT feature point. The data set of this network consists of a DIV2K dataset cut into $33{\times}33$ size and uses RGB image unlike SIFT which uses black and white image. The ground truth consists of the RobHess SIFT features extracted by setting the octave (scale) to 0, the sigma to 1.6, and the intervals to 3. Based on the VGG-16, we construct an increasingly deep network of 13 to 23 and 33 convolution layers, and experiment with changing the method of increasing the image scale. The result of using the sigmoid function as the activation function of the output layer is compared with the result using the softmax function. Experimental results show that the proposed network not only has more than 99% extraction accuracy but also has high extraction repeatability for distorted images.