• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3889-3903
• /
• 2022

To address the problem of low detection accuracy due to training noise caused by mislabeling when Tri-training for network intrusion detection (NID), we propose a Tri-training algorithm based on cross entropy and K-nearest neighbors (TCK) for network intrusion detection. The proposed algorithm uses cross-entropy to replace the classification error rate to better identify the difference between the practical and predicted distributions of the model and reduce the prediction bias of mislabeled data to unlabeled data; K-nearest neighbors are used to remove the mislabeled data and reduce the number of mislabeled data. In order to verify the effectiveness of the algorithm proposed in this paper, experiments were conducted on 12 UCI datasets and NSL-KDD network intrusion datasets, and four indexes including accuracy, recall, F-measure and precision were used for comparison. The experimental results revealed that the TCK has superior performance than the conventional Tri-training algorithms and the Tri-training algorithms using only cross-entropy or K-nearest neighbor strategy.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.11
• /
• pp.4028-4042
• /
• 2021

Aiming at the problem of software defect prediction difficulty caused by insufficient software defect marker samples and unbalanced classification, a semi-supervised software defect prediction model based on a tri-training algorithm was proposed by combining feature normalization, over-sampling technology, and a Tri-training algorithm. First, the feature normalization method is used to smooth the feature data to eliminate the influence of too large or too small feature values on the model's classification performance. Secondly, the oversampling method is used to expand and sample the data, which solves the unbalanced classification of labelled samples. Finally, the Tri-training algorithm performs machine learning on the training samples and establishes a defect prediction model. The novelty of this model is that it can effectively combine feature normalization, oversampling techniques, and the Tri-training algorithm to solve both the under-labelled sample and class imbalance problems. Simulation experiments using the NASA software defect prediction dataset show that the proposed method outperforms four existing supervised and semi-supervised learning in terms of Precision, Recall, and F-Measure values.

• Smart Media Journal
• /
• v.10 no.1
• /
• pp.16-24
• /
• 2021

The exiting word embedding methodology such as word2vec represents words, which only occur in the raw training corpus, as a fixed-length vector into a continuous vector space, so when mapping the words incorporated in the raw training corpus into a fixed-length vector in morphologically rich language, out-of-vocabulary (OOV) problem often happens. Even for sentence embedding, when representing the meaning of a sentence as a fixed-length vector by synthesizing word vectors constituting a sentence, OOV words make it challenging to meaningfully represent a sentence into a fixed-length vector. In particular, since the agglutinative language, the Korean has a morphological characteristic to integrate lexical morpheme and grammatical morpheme, handling OOV words is an important factor in improving performance. In this paper, we propose parallel Tri-LSTM sentence embedding that is robust to the OOV problem by extending utilizing the morphological information of words into sentence-level. As a result of the sentiment analysis task with corpus in Korean, we empirically found that the character unit is better than the morpheme unit as an embedding unit for Korean sentence embedding. We achieved 86.17% accuracy on the sentiment analysis task with the parallel bidirectional Tri-LSTM sentence encoder.

• Physical Therapy Korea
• /
• v.17 no.4
• /
• pp.77-87
• /
• 2010

The present case study highlights the effects of a novel Comprehensive Hand Repetitive Intensive Strengthening Training (CHRIST) on morphological changes and associated upper extremity (UE) muscle strength and motor performance in a child with spastic quadriplegic cerebral palsy (CP). The Child, a 10-year-old girl with spastic quadriplegic CP, was treated with CHRIST for 60 minutes a day, five times a week, for 5 weeks. The CHRIST was designed to improve motor function and strength. Clinical tests including the modified Wolf Test, Jebsen-Taylor Hand Function Test, and Pediatric Motor Activity Log questionnaire were used to determine motor function. Ultrasound imaging was performed to determine the changes in the cross-section area (CSA) of the extensor carpi radialis (ECR) and triceps brachii (TRI). Muscle strength was measured with a dynamometer at pretest, and post-test, and 3-month follow-up. Ultrasound imaging data showed that the CSAs of both ECR and TRI muscles were enhanced as a function of the intervention. These changes were associated with muscle strength and motor performance and their effects remained even at a 3-month follow-up test. Our results suggest that the CHRIST was effective at treating muscle atrophy, weakness and motor dysfunction in a child with spastic quadriplegic CP.

• Phonetics and Speech Sciences
• /
• v.7 no.4
• /
• pp.3-8
• /
• 2015

In this paper, we investigate an input dimension reduction method using continuous word vector in deep neural network language model. In the proposed method, continuous word vectors were generated by using Google's Word2Vec from a large training corpus to satisfy distributional hypothesis. 1-of-${\left|V\right|}$ coding discrete word vectors were replaced with their corresponding continuous word vectors. In our implementation, the input dimension was successfully reduced from 20,000 to 600 when a tri-gram language model is used with a vocabulary of 20,000 words. The total amount of time in training was reduced from 30 days to 14 days for Wall Street Journal training corpus (corpus length: 37M words).

• Bulletin of the Korean Chemical Society
• /
• v.26 no.4
• /
• pp.594-598
• /
• 2005

Treatment of a solution of $CuCl_2$ in dimethyl phosphate (DMP) with DMSO under nitrogen atmosphere afforded to a light blue fluorescence powder. Slow evaporation of $H_2O$-DMSO solution of this powder resulted in blue-sky crystals of a new polymeric Cu(II) complex, with a unit cell composed of $Cu_2(DMP)_4$(DMSO), (1). The crystal and molecular structure of the complex acquired crystallographically. Compound (1) crystallizes in the monoclinic space group $P2_1$/n with a = 12.8920(11) $\AA$, b = 13.1966(11) $\AA$, c = 14.7926(13) $\AA$, $\alpha$ = 90$^{\circ}$, $\beta$ = 98.943(2)$^{\circ}$, $\gamma$ = 90$^{\circ}$, V= 2486.1(4) ${\AA}^3$, and Z = 4. A square pyramidal environment for the metal center was established by coordination of oxygen atoms of four bridging DMP ligands in the basal positions and binding a tri-centered oxygen atom of DMSO in the apical disposition of Cu(II). The sixth position was also affected by a weak interaction with the sulfur atom of another DMSO. The phosphorous atom in the bridging DMP was arranged in a deformed tetrahedron with (gg) conformation for methyl esters with $C_{2v}$ symmetry.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.05a
• /
• pp.229-232
• /
• 2008

A Neural network classification of human activity data is presented. The data acquisition system involves a tri-axial accelerometer in wireless sensor network environment. The wireless ad-hoc system has the advantage of small size, convenience for wearability and cost effectiveness. The system can further improve the range of user mobility with the inclusion of ad-hoc environment. The classification is based on the frequencies of the involved activities. The most significant Fast Fourier coefficients, of the acceleration of the body movement, are used for classification of the daily activities like, Rest walk and Run. A supervised learning approach is used. The work presents classification accuracy with the available fast batch training algorithms i.e. Levenberg-Marquardt and Resilient back propagation scheme is used for training and calculation of accuracy.

• Journal of Industrial Technology
• /
• v.35
• /
• pp.55-58
• /
• 2015

Natural shifting of rivers has been disturbed by anthropological activities. Urbanization in Kathmandu has been encroached the natural floodplain of Bagmati and currently channeled by training walls. The study compares the change in shape of Dhobikhola, a small tributary using 1966 and 2014 satellite images. It has been found that the original shape is heavily changed over time at the beginning and end section of river under study. The river width is now fixed by training walls and roads along the banks. Using multiple data sets like satellite images and GIS analysis, these shifts can be easily detected to plan for management and restoration of physical and ecological behaviors of rivers.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.6
• /
• pp.551-560
• /
• 2020

This research investigates the impact of vocational training on wages of ethnic minority labors in emerging countries; Vietnam is the case study. The study uses secondary data from 2014 to 2018 collected through Vietnam Household Living Standards Surveys (VHLSS) conducted by the General Statistics Office. In order to analyze the impact of vocational training on wages of ethnic minority areas in Vietnam, this research creates ethnic area variables. According to Vietnamese regulations, ethnic areas are communes of 51 different provinces, inhabited by ethnic minority people. The statistics from VHLSS in 2018, show that the proportion of labors of working age with a certificate was 22.5%. The research employs Heckman Sample Selection Model to estimate the impact of vocation training on wage of labors in ethnic minority areas. The results show that vocational training plays a crucial role in improving the wages of ethnic minorities and has a positive impact. However, apart from the achieved outcomes, vocational training and job creation for ethnic minorities are not without limitations and shortcomings. Based on the findings, some recommendations to ethnic minority labors, enterprises and the Government are proposed to encourage participation in vocational training for the purpose of promoting the efficiency of the labor market.

• 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.