• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권11호
• /
• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권5호
• /
• pp.1755-1777
• /
• 2022

The development of wireless communication technology has led to the underutilization of radio spectra. To address this limitation, an intelligent cognitive radio network was developed. Specific emitter identification (SEI) is a key technology in this network. However, in realistic non-cooperative scenarios, the system may detect signal classes beyond those in the training database, and only a few labeled signal samples are available for network training, both of which deteriorate identification performance. To overcome these challenges, a meta-learning-based open-set identification system is proposed for SEI. First, the received signals were pre-processed using bi-spectral analysis and a Radon transform to obtain signal representation vectors, which were then fed into an open-set SEI network. This network consisted of a deep feature extractor and an intrinsic feature memorizer that can detect signals of unknown classes and classify signals of different known classes. The training loss functions and the procedures of the open-set SEI network were then designed for parameter optimization. Considering the few-shot problems of open-set SEI, meta-training loss functions and meta-training procedures that require only a few labeled signal samples were further developed for open-set SEI network training. The experimental results demonstrate that this approach outperforms other state-of-the-art SEI methods in open-set scenarios. In addition, excellent open-set SEI performance was achieved using at least 50 training signal samples, and effective operation in low signal-to-noise ratio (SNR) environments was demonstrated.

• International Journal of Internet, Broadcasting and Communication
• /
• 제15권3호
• /
• pp.211-218
• /
• 2023

Due to the implementation of COVID-19 distancing, interest and users in 'home training' are rapidly increasing. Therefore, the purpose of this study is to identify the perception of 'home training' through big data analysis on social media channels and provide basic data to related business sector. Social media channels collected big data from various news and social content provided on Naver and Google sites. Data for three years from March 22, 2020 were collected based on the time when COVID-19 distancing was implemented in Korea. The collected data included 4,000 Naver blogs, 2,673 news, 4,000 cafes, 3,989 knowledge IN, and 953 Google channel news. These data analyzed TF and TF-IDF through text mining, and through this, semantic network analysis was conducted on 70 keywords, big data analysis programs such as Textom and Ucinet were used for social big data analysis, and NetDraw was used for visualization. As a result of text mining analysis, 'home training' was found the most frequently in relation to TF with 4,045 times. The next order is 'exercise', 'Homt', 'house', 'apparatus', 'recommendation', and 'diet'. Regarding TF-IDF, the main keywords are 'exercise', 'apparatus', 'home', 'house', 'diet', 'recommendation', and 'mat'. Based on these results, 70 keywords with high frequency were extracted, and then semantic indicators and centrality analysis were conducted. Finally, through CONCOR analysis, it was clustered into 'purchase cluster', 'equipment cluster', 'diet cluster', and 'execute method cluster'. For the results of these four clusters, basic data on the 'home training' business sector were presented based on consumers' main perception of 'home training' and analysis of the meaning network.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권12호
• /
• pp.4664-4681
• /
• 2020

Modulation recognition (MR) plays a key role in cognitive radar, cognitive radio, and some other civilian and military fields. While existing methods can identify the signal modulation type by extracting the signal characteristics, the quality of feature extraction has a serious impact on the recognition results. In this paper, an end-to-end MR method based on long short-term memory (LSTM) and the gated recurrent unit (GRU) is put forward, which can directly predict the modulation type from a sampled signal. Additionally, the sliding window method is applied to fast-changing mixed-modulation signals for which the signal modulation type changes over time. The recognition accuracy on training datasets in different SNR ranges and the proportion of each modulation method in misclassified samples are analyzed, and it is found to be reasonable to select the evenly-distributed and full range of SNR data as the training data. With the improvement of the SNR, the recognition accuracy increases rapidly. When the length of the training dataset increases, the neural network recognition effect is better. The loss function value of the neural network decreases with the increase of the training dataset length, and then tends to be stable. Moreover, when the fast-changing period is less than 20ms, the error rate is as high as 50%. As the fast-changing period is increased to 30ms, the error rates of the GRU and LSTM neural networks are less than 5%.

• 한국인터넷방송통신학회논문지
• /
• 제24권1호
• /
• pp.83-88
• /
• 2024

본 연구에서는 Railroad surface 데이터를 활용하여 Semi-Supervised learning방식으로 railroad surface의 defect를 검출해내는 방안을 제안한다. Resnet50에 ImageNet으로 pretrained된 모델을 이용한다. Label이 없는 데이터에서 무작위로 데이터를 선정, 선정한 데이터에 label을 부여한 뒤 이 데이터로 모델을 학습시킨다. 학습된 모델을 이용하여 나머지 데이터의 결과값을 예측한 후, 그 예측값이 일정한 threshold보다 큰 것을 골라내고, threshold보다 큰 값들을 값이 큰 순서대로 정렬하여, 일정한 크기만큼 training data에 추가한다. 이 때, 각 class에 속할 확률이 높은 쪽으로 pseudo-labeling을 수행한다. 초기에 label이 부여된 데이터 개수에 따른 전체적인 class 분류 성능을 확인하는 실험 또한 진행하였고, 전체 training data대비 10% 미만의 labeled data로 최대 98%의 정확도를 얻는 성능을 보였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권4호
• /
• pp.1110-1127
• /
• 2022

To improve the training efficiency and generalization performance of a support vector machine (SVM) in a large-scale set, an optimal SVM learning method based on adaptive sparse sampling and the granularity shift factor is presented. The proposed method combines sampling optimization with learner optimization. First, an adaptive sparse sampling method based on the potential function density clustering is designed to adaptively obtain sparse sampling samples, which can achieve a reduction in the training sample set and effectively approximate the spatial structure distribution of the original sample set. A granularity shift factor method is then constructed to optimize the SVM decision hyperplane, which fully considers the neighborhood information of each granularity region in the sparse sampling set. Experiments on an artificial dataset and three benchmark datasets show that the proposed method can achieve a relatively higher training efficiency, as well as ensure a good generalization performance of the learner. Finally, the effectiveness of the proposed method is verified.

• 한국반도체및디스플레이장비학회:학술대회논문집
• /
• 한국반도체및디스플레이장비학회 2003년도 추계학술대회 발표 논문집
• /
• pp.169-176
• /
• 2003

Telematic and new programming technologies support the increasing demand of education and training leading to the delivery of computer based learining systems open to distance and continuing education. Using LabVIEW, we designed and implemented an interactive learning environment for practice on electronics measurement methodologies. The environment provides remote access to real and simulated instrumentation and guided experiments on basic circuits. The environment is applied to the education and training on electronics for engineers in the field of semiconductor industry.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권1호
• /
• pp.368-391
• /
• 2018

Face recognition (FR) with a single sample per person (SSPP) is common in real-world face recognition applications. In this scenario, it is hard to predict intra-class variations of query samples by gallery samples due to the lack of sufficient training samples. Inspired by the fact that similar faces have similar intra-class variations, we propose a virtual sample generating algorithm called k nearest neighbors based virtual sample generating (kNNVSG) to enrich intra-class variation information for training samples. Furthermore, in order to use the intra-class variation information of the virtual samples generated by kNNVSG algorithm, we propose image set based multimanifold discriminant learning (ISMMDL) algorithm. For ISMMDL algorithm, it learns a projection matrix for each manifold modeled by the local patches of the images of each class, which aims to minimize the margins of intra-manifold and maximize the margins of inter-manifold simultaneously in low-dimensional feature space. Finally, by comprehensively using kNNVSG and ISMMDL algorithms, we propose k nearest neighbor virtual image set based multimanifold discriminant learning (kNNMMDL) approach for single sample face recognition (SSFR) tasks. Experimental results on AR, Multi-PIE and LFW face datasets demonstrate that our approach has promising abilities for SSFR with expression, illumination and disguise variations.

• 대한안전경영과학회:학술대회논문집
• /
• 대한안전경영과학회 2000년도 추계학술발표논문집
• /
• pp.1-5
• /
• 2000

With the advent of the internet era, web-based virtual training system is gaining its importance in recent years. Because of the fact that the training can take place in any place and at any time, the virtual system is now replacing many of the conventional off-line classes. Hardware environments such as communication bandwidth and computer performance gets fast enough to accommodate the virtual education. Based on the observations on current virtual training system, this paper proposes three critical design rules required when developing a new virtual training system: i) With conceptual mapping, the menu hierarchy can be organized in a clear-cut manner, ii) Extensive use of multimedia tools can help students keep their attention to the lecture materials, and iii) Provision of interaction mechanisms helps students to gain their identity and motivation.

• International Journal of Internet, Broadcasting and Communication
• /
• 제16권1호
• /
• pp.148-155
• /
• 2024

We are designed was to find an efficient warm-up method for resistance training for muscle hypertrophy, and 10 males with at least 3 years of resistance training experience were selected as subjects. The 75% 1RM was measured directly based on the pre-measured bench press 1RM. After that, the main experiment of 75% 1RM bench press according to the three warm-up methods was conducted one week apart, and all experiments were randomized and cross-over. Performance according to the warm-up method (3) was measured by total exercise volume, and physiological changes were determined by myocardial workload. All post-measurement data were analyzed using SPSS.22.0 and analyzed using repeated measures one-way ANOVA and contrast comparisons were made using the deviation method. The results showed that the method of gradually increasing the number of repetitions by performing the same intensity as the intensity of the main exercise in the form of muscle hypertrophy, but at submaximal repetitions, showed the highest performance.