• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.8
• /
• pp.4021-4037
• /
• 2018

In network intrusion detection research, two characteristics are generally considered vital to building efficient intrusion detection systems (IDSs): an optimal feature selection technique and robust classification schemes. However, the emergence of sophisticated network attacks and the advent of big data concepts in intrusion detection domains require two more significant aspects to be addressed: employing an appropriate big data computing framework and utilizing a contemporary dataset to deal with ongoing advancements. As such, we present a comprehensive approach to building an efficient IDS with the aim of strengthening academic anomaly detection research in real-world operational environments. The proposed system has the following four characteristics: (i) it performs optimal feature selection using information gain and branch-and-bound algorithms; (ii) it employs machine learning techniques for classification, namely, Logistic Regression, Naïve Bayes, and Random Forest; (iii) it introduces bulk synchronous parallel processing to handle the computational requirements of large-scale networks; and (iv) it utilizes a real-time contemporary dataset generated by the Information Security Centre of Excellence at the University of Brunswick (ISCX-UNB) to validate its efficacy. Experimental analysis shows the effectiveness of the proposed framework, which is able to achieve high accuracy, low computational cost, and reduced false alarms.

• Journal of Convergence for Information Technology
• /
• v.8 no.3
• /
• pp.193-198
• /
• 2018

Recently, the casualties of automobile traffic accidents are rapidly increasing, and serious accidents involving serious injury and death are increasing more than those of ordinary people. More than 70% of major accidents occur in drowsy driving. Therefore, in this paper, we studied the drowsiness prevention system to prevent large-scale disasters of traffic accidents. In this paper, we propose a real-time flicker recognition method for drowsy driving detection system and drowsy recognition according to the increase of carbon dioxide. The drowsy driving detection system applied the existing image detection and the deep running, and the carbon dioxide detection was developed based on the IoT. The drowsy prevention system using both of these techniques improved the accuracy compared to the existing products.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.12
• /
• pp.4795-4815
• /
• 2020

Drone detection can be considered as a specific sort of small object detection, which has always been a challenge because of its small size and few features. For improving the detection rate of drones, we design a Deeper SSD network, which uses large-scale input image and deeper convolutional network to obtain more features that benefit small object classification. At the same time, in order to improve object classification performance, we implemented the up-sampling modules to increase the number of features for the low-level feature map. In addition, in order to improve object location performance, we adopted the down-sampling modules so that the context information can be used by the high-level feature map directly. Our proposed Deeper SSD and its variants are successfully applied to the self-designed drone datasets. Our experiments demonstrate the effectiveness of the Deeper SSD and its variants, which are useful to small drone's detection and recognition. These proposed methods can also detect small and large objects simultaneously.

• Journal of the Korean Society of Safety
• /
• v.37 no.2
• /
• pp.69-75
• /
• 2022

Fire-alarm systems are safety equipment that facilitate rapid evacuation and early suppression in case of fire. It is highly desirable that fire-alarm systems have low false-alarm rates and are thus reliable. Until now, researchers have attempted to improve detector performance by applying new technologies such as IoT. To this end, IoT-based fire-detection systems have been developed. However, due to scarcity of large-scale operational data, researchers have barely studied malfunctioning in fire-alarm systems or attempted to reduce false-alarm rates in these systems. In this study, we analyzed false-alarm rates of smoke/temperature detectors and unwanted fire-alarm signal patterns at K institution, where Korea's largest IoT-based fire-detection system operates. After analyzing the fire alarm occurrences at the institution for five years, we inferred that the IoT-based fire-detection system showed lower false-alarm rates compared to the automatic fire-detection equipment. We analyzed the detection pattern by dividing it into two parts: normal operation and unwanted fire alarms. When a specific signal pattern was filtered out, the false-alarm rate was reduced to 66.9% in the smoke detector and to 46.9% in the temperature detector.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.19 no.4
• /
• pp.117-126
• /
• 2023

Traditional markets, formed naturally, often feature aged buildings and facilities that are susceptible to fire. However, the lack of adequate fire detection systems in these markets can easily lead to large-scale fires upon ignition. Therefore, this study was conducted with the aim of detecting fires in traditional markets, utilizing thermal imaging cameras for data collection and the YOLOv8 model for object detection experiments. Data were collected in the night markets within traditional markets of xx city and by simulating fire scenarios. A comparative analysis of the Nano and XL models of YOLOv8 revealed that the XL model is more effective in detecting fires. The XL model not only demonstrated higher accuracy in correctly identifying flames but also tended to miss fewer fires compared to the Nano model. In the case of objects other than flames, the XL model showed superior performance over the Nano model. Taking all these factors into account, it is anticipated that with further data collection and improvement in model performance, a suitable fire detection system for traditional markets can be developed.

• Journal of Digital Convergence
• /
• v.11 no.8
• /
• pp.191-197
• /
• 2013

In this paper, we implemented a paper currency recognition system using IR(infrared) sensor. The system has 32 channel IR sensor to measure the reflection and penetration quantity of light. The IR image of paper currency of 10-bit gray scale is used to differentiate the real and counterfeit paper currency with image information from 0 to 4095. The characteristics of IR image are recognized by brightness and darkness and the positions of bright and dark portions are different between real and counterfeit paper currency. The price of IR sensors were relatively high, however, it is good price in these days due to mass production to apply to counterfeit detection area. We used a software table having the IR characteristics of real paper currency to compare with the IR images of the input paper currency. The performance of the implemented system shows 1-2% error rates for Euro real paper currency and 0% error rates for various counterfeit paper currencies of several countries.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.7
• /
• pp.47-55
• /
• 2020

In this paper, we propose one stage multi-scale face detector based Fully Convolution Network using anchor free method. Recently almost all state-of-the-art face detectors which predict location of faces using anchor-based methods rely on pre-defined anchor boxes. However this face detectors need to hyper-parameters and additional computation in training. The key idea of the proposed method is to eliminate hyper-parameters and additional computation using anchor free method. To do this, we apply two ideas. First, by eliminating the pre-defined set of anchor boxes, we avoid the additional computation and hyper-parameters related to anchor boxes. Second, our detector predicts location of faces using multi-feature maps to reduce foreground/background imbalance issue. Through Quantitative evaluation, the performance of the proposed method is evaluated and analyzed. Experimental results on the FDDB dataset demonstrate the effective of our proposed method.

• Korean journal of applied entomology
• /
• v.37 no.1
• /
• pp.65-71
• /
• 1998

Survey was conducted on the kinds and densities of pests associated with stored garlic collected from farms of major garlic production areas from 1994 to 1995 in Korea. Aceria tulipae, Rhizoglyphus sp., Ditylenchus dipsaci, and Tyrophagus putrescentiae were frequently detected with high densities and Tarsonemus bilobatus and Aphelenchus avenue showed relatively low detection rates and densities. Detection rate of A. tulipue was 38% in 1994, but the rate was 65% in 1995. Number of the mite ranged from 1 to 4,500 per scale. Detection rate of Rhizoglyphus sp. was 63% in 1994, but the rate was 13% in 1995 and average number of the mite ranged from 1 to 135 per scale in 1994. Garlics damaged by Rhizoglyphus sp. showed decaying symptom. T~rophagusp utrescentiae was detected from 22 farms among 32 farms surveyed in 1994 and from 21 farms among 39 farms surveyed in 1995. However, number of the mite on garlic scale was relatively lower than the other mites and its damages on stored garlic was not determined.

• Phonetics and Speech Sciences
• /
• v.11 no.4
• /
• pp.89-96
• /
• 2019

In this paper, we propose a deep learning architecture that can effectively detect speech segmentation in broadcast contents. We also propose a multi-scale time-dilated layer for learning the temporal changes of feature vectors. We implement several comparison models to verify the performance of proposed model and calculated the frame-by-frame F-score, precision, and recall. Both the proposed model and the comparison model are trained with the same training data, and we train the model using 32 hours of Korean broadcast data which is composed of various genres (drama, news, documentary, and so on). Our proposed model shows the best performance with F-score 91.7% in Korean broadcast data. The British and Spanish broadcast data also show the highest performance with F-score 87.9% and 92.6%. As a result, our proposed model can contribute to the improvement of performance of speech detection by learning the temporal changes of the feature vectors.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3729-3749
• /
• 2021

At present, deep convolution network-based salient object detection (SOD) has achieved impressive performance. However, it is still a challenging problem to make full use of the multi-scale information of the extracted features and which appropriate feature fusion method is adopted to process feature mapping. In this paper, we propose a new adjacency auxiliary network (AANet) based on multi-scale feature fusion for SOD. Firstly, we design the parallel connection feature enhancement module (PFEM) for each layer of feature extraction, which improves the feature density by connecting different dilated convolution branches in parallel, and add channel attention flow to fully extract the context information of features. Then the adjacent layer features with close degree of abstraction but different characteristic properties are fused through the adjacent auxiliary module (AAM) to eliminate the ambiguity and noise of the features. Besides, in order to refine the features effectively to get more accurate object boundaries, we design adjacency decoder (AAM_D) based on adjacency auxiliary module (AAM), which concatenates the features of adjacent layers, extracts their spatial attention, and then combines them with the output of AAM. The outputs of AAM_D features with semantic information and spatial detail obtained from each feature are used as salient prediction maps for multi-level feature joint supervising. Experiment results on six benchmark SOD datasets demonstrate that the proposed method outperforms similar previous methods.