• Safety and Health at Work
• /
• v.8 no.4
• /
• pp.364-370
• /
• 2017

Background: Labeled noise reduction (NR) data presented by manufacturers are considered one of the main challenging issues for occupational experts in employing hearing protection devices (HPDs). This study aimed to determine the actual NR data of typical HPDs using the objective fit testing method with a microphone in real ear (MIRE) method. Methods: Five available commercially earmuff protectors were investigated in 30 workers exposed to reference noise source according to the standard method, ISO 11904-1. Personal attenuation rating (PAR) of the earmuffs was measured based on the MIRE method using a noise dosimeter (SVANTEK, model SV102). Results: The results showed that means of PAR of the earmuffs are from 49% to 86% of the nominal NR rating. The PAR values of earmuffs when a typical eyewear was worn differed statistically (p < 0.05). It is revealed that a typical safety eyewear can reduce the mean of the PAR value by approximately 2.5 dB. The results also showed that measurements based on the MIRE method resulted in low variability. The variability in NR values between individuals, within individuals, and within earmuffs was not the statistically significant (p > 0.05). Conclusion: This study could provide local individual fit data. Ergonomic aspects of the earmuffs and different levels of users experience and awareness can be considered the main factors affecting individual fitting compared with the laboratory condition for acquiring the labeled NR data. Based on the obtained fit testing results, the field application of MIRE can be employed for complementary studies in real workstations while workers perform their regular work duties.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.4008-4023
• /
• 2022

Since machine learning was introduced into cross-site scripting (XSS) attack detection, many researchers have conducted related studies and achieved significant results, such as saving time and labor costs by not maintaining a rule database, which is required by traditional XSS attack detection methods. However, this topic came across some problems, such as poor generalization ability, significant false negative rate (FNR) and false positive rate (FPR). Moreover, the automatic clustering property of graph convolutional networks (GCN) has attracted the attention of researchers. In the field of natural language process (NLP), the results of graph embedding based on GCN are automatically clustered in space without any training, which means that text data can be classified just by the embedding process based on GCN. Previously, other methods required training with the help of labeled data after embedding to complete data classification. With the help of the GCN auto-clustering feature and labeled data, this research proposes an approach to detect XSS attacks (called GCNXSS) to mine the dependencies between the units that constitute an XSS payload. First, GCNXSS transforms a URL into a word homogeneous graph based on word co-occurrence relationships. Then, GCNXSS inputs the graph into the GCN model for graph embedding and gets the classification results. Experimental results show that GCNXSS achieved successful results with accuracy, precision, recall, F1-score, FNR, FPR, and predicted time scores of 99.97%, 99.75%, 99.97%, 99.86%, 0.03%, 0.03%, and 0.0461ms. Compared with existing methods, GCNXSS has a lower FNR and FPR with stronger generalization ability.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.5
• /
• pp.165-170
• /
• 2023

With the recent rise of blockchain technology, cryptocurrency platforms using it are increasing, and currency transactions are being actively conducted. However, crimes that abuse the characteristics of cryptocurrency are also increasing, which is a problem. In particular, phishing scams account for more than a majority of Ethereum cybercrime and are considered a major security threat. Therefore, effective phishing scams detection methods are urgently needed. However, it is difficult to provide sufficient data for supervised learning due to the problem of data imbalance caused by the lack of phishing addresses labeled in the Ethereum participating account address. To address this, this paper proposes a phishing scams detection method that uses both Trans2vec, an effective graph embedding techique considering Ethereum transaction networks, and semi-supervised learning model Tri-training to make the most of not only labeled data but also unlabeled data.

• Journal of KIISE:Software and Applications
• /
• v.35 no.5
• /
• pp.325-334
• /
• 2008

The goal of text categorization is to classify documents into a certain number of pre-defined categories. The previous studies in this area have used a large number of labeled training documents for supervised learning. One problem is that it is difficult to create the labeled training documents. While it is easy to collect the unlabeled documents, it is not so easy to manually categorize them for creating training documents. In this paper, we propose a new text categorization method based on semi-supervised learning. The proposed method uses only unlabeled documents and keywords of each category, and it automatically constructs training data from them. Then a text classifier learns with them and classifies text documents. The proposed method shows a similar degree of performance, compared with the traditional supervised teaming methods. Therefore, this method can be used in the areas where low-cost text categorization is needed. It can also be used for creating labeled training documents.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.1
• /
• pp.4-10
• /
• 2000

The work presented in this paper is about a postprocessor, which improves the performance of automatic speech segmentation system by correcting the phoneme boundary errors. We propose a postprocessor that reduces the range of errors in the auto labeled results that are ready to be used directly as synthesis unit. Starting from a baseline automatic segmentation system, our proposed postprocessor trains the features of hand labeled results using multi-layer perceptron(MLP) algorithm. Then, the auto labeled result combined with MLP postprocessor determines the new phoneme boundary. The details are as following. First, we select the feature sets of speech, based on the acoustic phonetic knowledge. And then we have adopted the MLP as pattern classifier because of its excellent nonlinear discrimination capability. Moreover, it is easy for MLP to reflect fully the various types of acoustic features appearing at the phoneme boundaries within a short time. At the last procedure, an appropriate feature set analyzed about each phonetic event is applied to our proposed postprocessor to compensate the phoneme boundary error. For phonetically rich sentences data, we have achieved 19.9 % improvement for the frame accuracy, comparing with the performance of plain automatic labeling system. Also, we could reduce the absolute error rate about 28.6%.

• Journal of Radiation Industry
• /
• v.12 no.4
• /
• pp.355-363
• /
• 2018

A novel $N_3S_1$ chelate, Pro-Lys-Cys (PKC) to cyclic RGD to radiolabel with $^{99m}Tc$ was conjugated in an effort to decrease the high intestinal accumulation observed for $^{99m}Tc$-labeled PGC-RGD. The target specificity of the resulting PKC-RGD was similar to that of PGC-RGD as determined by a cell binding assay and a competition binding assay. The $^{99m}Tc$ radiolabeling of PKC-RGD resulted in radiochemical yields of 98% under mild conditions at high specific activities. Biodistribution data in normal mice clearly showed a significant decrease in intestinal uptake at 2 h postinjection for the $^{99m}Tc-PKC-c$ (RGDyK) compared to the $^{99m}Tc-GC-c$ (RGDyK) (from $19.65%ID{\cdot}g^{-1}$ to $7.31%ID{\cdot}g^{-1}$ for the GI tract). The $^{99m}Tc-PKC-c$ (RGDyK) biodistribution was also shown by a higher retention of radioactivity in the whole body, but with kidney accumulation over 8-fold higher than observed with $^{99m}Tc-PGC-c$ (RGDyK) at 2 h ($12.62%ID{\cdot}g^{-1}$ for PKC-RGD and $1.54%ID{\cdot}g^{-1}$ for PGC-RGD, respectively). These results show that the biodistribution may be altered especially concerning lipophilicity resulting in renal rather than hepatobiliary excretion. This comparative study made it possible to explore the effects of lipophilicity on the biodistribution of $^{99m}Tc$-labeled c (RGDyK) through the use of different tripeptide $N_3S_1$ chelators. Therefore, $^{99m}Tc-PKC-c$ (RGDyK) may be an attractive alternative for the in vivo imaging of integrin receptors.

• ETRI Journal
• /
• v.46 no.3
• /
• pp.513-525
• /
• 2024

Deep neural networks trained on labeled medical data face major challenges owing to the economic costs of data acquisition through expensive medical imaging devices, expert labor for data annotation, and large datasets to achieve optimal model performance. The heterogeneity of diseases, such as Alzheimer's disease, further complicates deep learning because the test cases may substantially differ from the training data, possibly increasing the rate of false positives. We propose a reconstruction-based self-supervised anomaly detection model to overcome these challenges. It has a dual-subnetwork encoder that enhances feature encoding augmented by skip connections to the decoder for improving the gradient flow. The novel encoder captures local and global features to improve image reconstruction. In addition, we introduce an entropy-based image conversion method. Extensive evaluations show that the proposed model outperforms benchmark models in anomaly detection and classification using an encoder. The supervised and unsupervised models show improved performances when trained with data preprocessed using the proposed image conversion method.

• International Journal of Computer Science & Network Security
• /
• v.22 no.4
• /
• pp.193-202
• /
• 2022

The classification of hyperspectral imagery (HSI) is essential in the surface of earth observation. Due to the continuous large number of bands, HSI data provide rich information about the object of study; however, it suffers from the curse of dimensionality. Dimensionality reduction is an essential aspect of Machine learning classification. The algorithms based on feature extraction can overcome the data dimensionality issue, thereby allowing the classifiers to utilize comprehensive models to reduce computational costs. This paper assesses and compares two HSI classification techniques. The first is based on the Joint Spatial-Spectral Stacked Autoencoder (JSSSA) method, the second is based on a shallow Artificial Neural Network (SNN), and the third is used the SVM model. The performance of the JSSSA technique is better than the SNN classification technique based on the overall accuracy and Kappa coefficient values. We observed that the JSSSA based method surpasses the SNN technique with an overall accuracy of 96.13% and Kappa coefficient value of 0.95. SNN also achieved a good accuracy of 92.40% and a Kappa coefficient value of 0.90, and SVM achieved an accuracy of 82.87%. The current study suggests that both JSSSA and SNN based techniques prove to be efficient methods for hyperspectral classification of snow features. This work classified the labeled/ground-truth datasets of snow in multiple classes. The labeled/ground-truth data can be valuable for applying deep neural networks such as CNN, hybrid CNN, RNN for glaciology, and snow-related hazard applications.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.20 no.2
• /
• pp.77-84
• /
• 2000

Eight-week old perennial ryegrass (Lolium perenne L. cv. Reveille) plants were exposed to different NO3-concentrations or osmotic stress with NaCI. Previously labeled "N was chased during 14 days of non-labeled'NO3 feeding in order to investigate NO3 metabolism in relation to osmoregulation. The short termmeasurement of osmotic potential showed that the extemal concentration of Nos- had not great effect on theosmotic potential, but that osmotic adjustment was observed in NaCl-treated plants. Total uptake of NO 3 - waslargely increased by increasing supply level of NO3 while it was depressed by exposing to osmotic stress.Nitrate reduction increased to more than 29% by increasing extemal NO,- concentration from 1 mM to 10mM. When osmotically stressed with NaCI, nitrate reduction was depressed to about 37% as compared to thecontrol. The decrease in translocation of reduced N into leaves was also observed in NaCl exposed plants. Inthe medium exposed to 10 mM NO,., osmotic contribution of nitrate to cumulative osmotic potential wasdecreased, and it was osmotically compensated with soluble carbohydrate. When osmotically stressed withNaC1, the contribution of chloride was much higher than that of nitrate. The present data indicate that N03-in plant tissues, factually affected by the assimilation of this ion, plays an active role in osmotic regulation incorrelation with other osmotica such carbohydrate and chloride.(Key words : Nitrate metabolism, Osmotic stress, Nitrate supply level, Osmoregulation)ate supply level, Osmoregulation)

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.42 no.2
• /
• pp.536-544
• /
• 2017

Wireless RSSI (Received Signal Strength Indication) fingerprinting is one of the most popular methods for indoor positioning as it provides reasonable accuracy while being able to exploit existing wireless infrastructure. However, the process of radio map construction (aka fingerprint calibration) is laborious and time consuming as precise physical coordinates and wireless signals have to be measured at multiple locations of target environment. This paper proposes a method to build the map from a combination of RSSIs without location information collected in a crowdsourcing fashion, and a handful of labeled RSSIs using a semi-supervised self organizing map learning algorithm. Experiment on simulated data shows promising results as the method is able to recover the full map effectively with only 1% RSSI samples from the fingerprint database.