• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권12호
• /
• pp.3166-3179
• /
• 2013

A pre-processing system for adaptive noise removal is proposed based on the principle of identifying and filtering object regions and background regions. Human perception of images depends on bright, well-focused object regions; these regions can be treated with the best filters, while simpler filters can be applied to other regions to reduce overall computational complexity. In the proposed method, bright region segmentation is performed, followed by segmentation of object and background regions. Noise in dark, background, and object regions is then removed by the median, fast bilateral, and bilateral filters, respectively. Simulations show that the proposed algorithm is much faster than and performs nearly as well as the bilateral filter (which is considered a powerful noise removal algorithm); it reduces computation time by 19.4 % while reducing PSNR by only 1.57 % relative to bilateral filtering. Thus, the proposed algorithm remarkably reduces computation while maintaining accuracy.

• 한국통신학회논문지
• /
• 제30권2C호
• /
• pp.41-48
• /
• 2005

본 논문에서는 H.264 표준 부호화 방식의 성능 향상 및 저 계산량을 위한 가우시안 모델 기반의 전처리 필터에 대해 제안한다. 일반적인 영상 획득 장치에서 첨가된 노이즈에 의해 훼손된 동영상은 다수의 고주파 성분으로 인하여 시각적으로 불편한 현상과 압축 효율의 저하를 초래한다. 본 논문에서는 필터링 과정에서 국부 통계적 특성과 양자화 매개변수를 이용하여, 주어진 양자화 스텝 사이즈에서 노이즈 성분을 제거하고 시각적인 효과와 비트율을 개선시켜 압축 효율을 개선하고자 한다. 또한 전처리 필터의 계산량을 줄이기 위하여 간단한 형태의 국부 통계적 특성을 재 정의하고 노이즈에 대한 매개변수를 H.264의 변환과 양자화 과정을 통하여 유추하여 적용하였다. 제안된 방식의 성능을 실험 결과로부터 확인할 수 있었다.

• 대한의용생체공학회:의공학회지
• /
• 제43권5호
• /
• pp.299-307
• /
• 2022

In this paper, we propose a pre-processing method that converts to Spider Chart image data for classification of gripping movement using EMG (electromyography) sensors and Convolution Neural Networks (CNN) deep learning. First, raw data for six hand gestures are extracted from five test subjects using an 8-channel armband and converted into Spider Chart data of octagonal shapes, which are divided into several sliding windows and are learned. In classifying six hand gestures, the classification performance is compared with the proposed pre-processing method and the existing methods. Deep learning was performed on the dataset by dividing 70% of the total into training, 15% as testing, and 15% as validation. For system performance evaluation, five cross-validations were applied by dividing 80% of the entire dataset by training and 20% by testing. The proposed method generates 97% and 94.54% in cross-validation and general tests, respectively, using the Spider Chart preprocessing, which was better results than the conventional methods.

• 품질경영학회지
• /
• 제50권3호
• /
• pp.459-471
• /
• 2022

Purpose: The purpose of this study was to increase prediction accuracy for an anomaly interval identified using an artificial intelligence-based time series anomaly detection technique by establishing a pre-processing process. Methods: Significant variables were extracted by applying feature selection techniques, and anomalies were derived using the TadGAN time series anomaly detection algorithm. After applying machine learning and deep learning methodologies using normal section data (excluding anomaly sections), the explanatory power of the anomaly sections was demonstrated through performance comparison. Results: The results of the machine learning methodology, the performance was the best when SHAP and TadGAN were applied, and the results in the deep learning, the performance was excellent when Chi-square Test and TadGAN were applied. Comparing each performance with the papers applied with a Conventional methodology using the same data, it can be seen that the performance of the MLR was significantly improved to 15%, Random Forest to 24%, XGBoost to 30%, Lasso Regression to 73%, LSTM to 17% and GRU to 19%. Conclusion: Based on the proposed process, when detecting unsupervised learning anomalies of data that are not actually labeled in various fields such as cyber security, financial sector, behavior pattern field, SNS. It is expected to prove the accuracy and explanation of the anomaly detection section and improve the performance of the model.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 춘계학술대회
• /
• pp.623-625
• /
• 2021

고무 오링은 일반적인 사출 성형 방식으로 생산된다. 이때 정상적으로 성형되지 않은 제품은 무조건 불량으로 판별한다. 그러나 영상기반 판독 시 획득한 영상을 원본 그대로 판독 할 경우 정확도가 떨어지는 문제가 발생한다. 이에 획득한 영상을 적응형 이진화와 Convex Hull 알고리즘을 사용한 전처리를 통해 원본영상에서 고무 오링 부분만 추출하여 합성곱 신경망에 학습하였다. 테스트 과정에서 제안하는 전처리를 적용한 학습방법의 불량검출 성능이 제시한 기준치 보다 나은 성능을 보이는 것을 확인 할 수 있었다.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제50권12호
• /
• pp.590-596
• /
• 2001

The pre-emphasis is an essential process for speech signal processing. Widely used two methods are the typical method using a fixed value near unity and te optimal method using the autocorrelation ratio of the signal. This study proposes a new pre-emphasis method using the short-term energy difference of speech signal, which can effectively compensate the glottal source characteristics and lip radiation characteristics. Using the proposed pre-emphasis, speech analysis, such as spectrum estimation, formant detection, is performed and the results are compared with those of the conventional two pre-emphasis methods. The speech analysis with 5 single vowels showed that the proposed method enhanced the spectral shapes and gave nearly constant formant frequencies and could escape the overlapping of adjacent two formants. comparison with FFT spectra had verified the above results and showed the accuracy of the proposed method. The computational complexity of the proposed method reduced to about 50% of the optimal method.

• 상하수도학회지
• /
• 제25권3호
• /
• pp.419-428
• /
• 2011

Recycling as a stabilizer of industrial by-product can be terms of the proper handling of industrial by-product and positive side in terms of recycling of waste. This study was performed to evaluate has the possibility as stabilizer by primary processing Pre-Red Mud and Bio-Solids which are generated as waste in soils contaminated with heavy metals and compared the efficiency with steel slug being applied in an existing site. In evaluation of the arsenic-fixing ability of stabilizer in batch test, Bio-Solids have the similar arsenic-fixing ability with Pre-Red Mud, which shows 17% h igher arsenic-fixing ability than PS Ball. Since the stabilization periods using Bio-Solids and Pre-Red Mud are faster than the PS Ball, they seems to be better stabilizer than PS Ball to decrease the leaching of arsenic in contaiminated soil.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2006년도 춘계학술발표대회
• /
• pp.1113-1116
• /
• 2006

Security in wireless sensor networks is very pressing especially when sensor nodes are deployed in hostile environments. To obtain security purposes, it is essential to be able to encrypt and authenticate messages sent amongst sensor nodes. Keys for encryption and authentication must be agreed upon by communicating nodes. Due to resource limitations and other unique features, obtaining such key agreement in wireless sensor network is extremely complex. Many key agreement schemes used in general networks, such as trusted server, Diffie-Hellman and public-key based schemes, are not suitable for wireless sensor networks [1], [2], [5], [7], [8]. In that situation, key pre-distribution scheme has been emerged and considered as the most appropriate scheme [2], [5], [7]. Based on that sense, we propose a new resource-optimal key pre-distribution scheme utilizing merits of the two existing key pre-distribution schemes [3], [4]. Our scheme exhibits the fascinating properties: substantial improvement in sensors' resource usage, rigorous guarantee of successfully deriving pairwise keys between any pair of nodes, greatly improved network resiliency against node capture attack. We also present a detailed analysis in terms of security and resource usage of the scheme.

• BMB Reports
• /
• 제39권6호
• /
• pp.717-721
• /
• 2006

In vitro analyses of type I signal peptidase activities require protein precursors as substrates. Usually, these pre-proteins are expressed in vitro and cleavage of the signal sequence is followed by SDS polyacrylamide gel electrophoresis coupled with autoradiography. Radioactive amino acids have to be incorporated in the expressed protein, since the amount of the in vitro expressed protein is usually very low and processing of the signal peptide cannot be followed by SDS polyacrylamide gel electrophoresis alone. Here we describe a rapid and simple method to express large amounts of a protein precursor in E. coli. We have analyzed the effect of ionophors as well as of azide on the accumulation of expressed protein precursors. Azide blocks the function of SecA and the ionophors dissipate the electrochemical gradient across the cytoplasmic membrane of E. coli. Addition of azide ions resulted in the formation of inclusion bodies, highly enriched with pre-apo-plastocyanine. Plastocyanine is a soluble copper protein, which can be found in the periplasmic space of cyanobacteria as well as in the thylakoid lumen of cyanobacteria and chloroplasts, and the pre-protein contains a cleavable signal sequence at its N-terminus. After purification of cyanobacterial pre-apo-plastocyanine, its signal sequence can be cleaved off by the E. coli signal peptidase, and protein processing was followed on Coomassie stained SDS polyacrylamide gels. We are optimistic that the presented method can be further developed and applied.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권3호
• /
• pp.771-791
• /
• 2022

Protein-protein interaction (PPI) extraction from original text is important for revealing the molecular mechanism of biological processes. With the rapid growth of biomedical literature, manually extracting PPI has become more time-consuming and laborious. Therefore, the automatic PPI extraction from the raw literature through natural language processing technology has attracted the attention of the majority of researchers. We propose a PPI extraction model based on the large pre-trained language model and adversarial training. It enhances the learning of semantic and syntactic features using BioBERT pre-trained weights, which are built on large-scale domain corpora, and adversarial perturbations are applied to the embedding layer to improve the robustness of the model. Experimental results showed that the proposed model achieved the highest F1 scores (83.93% and 90.31%) on two corpora with large sample sizes, namely, AIMed and BioInfer, respectively, compared with the previous method. It also achieved comparable performance on three corpora with small sample sizes, namely, HPRD50, IEPA, and LLL.