• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권10호
• /
• pp.2788-2808
• /
• 2023

Brain tumors are one of the most threatening malignancies for humans. Misdiagnosis of brain tumors can result in false medical intervention, which ultimately reduces a patient's chance of survival. Manual identification and segmentation of brain tumors from Magnetic Resonance Imaging (MRI) scans can be difficult and error-prone because of the great range of tumor tissues that exist in various individuals and the similarity of normal tissues. To overcome this limitation, the Amended Convolutional Neural Network (ACNN) model has been introduced, a unique combination of three techniques that have not been previously explored for brain tumor detection. The three techniques integrated into the ACNN model are image tissue preprocessing using the Kalman Bucy Smoothing Filter to remove noisy pixels from the input, image tissue segmentation using the Isotonic Regressive Image Tissue Segmentation Process, and feature extraction using the Marr Wavelet Transformation. The extracted features are compared with the testing features using a sigmoid activation function in the output layer. The experimental findings show that the suggested model outperforms existing techniques concerning accuracy, precision, sensitivity, dice score, Jaccard index, specificity, Positive Predictive Value, Hausdorff distance, recall, and F1 score. The proposed ACNN model achieved a maximum accuracy of 98.8%, which is higher than other existing models, according to the experimental results.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1994년도 추계학술대회 논문집
• /
• pp.360-364
• /
• 1994

This paper is concerned with extracting the diagnostic signature for motor-operated valves (MOV's) noninvasively. A torque estimator is developed and tested to obtain electical torque of the induction motors which are attached to the MOV's. Inverse filter is used to recover the gear meshing forces from the measured actuator housing vibration, which contain the gear rotation information. Frequency demodulation techniques are performed and an adaptive linear bandpass filter is implemented to improve signal-to-noise ratio. Finally, stand-alone valve experiments are carried out to validate the signature extraction scheme.

• 대한전자공학회논문지
• /
• 제25권9호
• /
• pp.1081-1090
• /
• 1988

A series of procedures using image processing techniques is presented for extracting layout information fast and automatically from chip images. CIF (caltech intermediate form) is chosen for representing such information. First, line-edges are extracted using a line-edge detector. Then, thinning and noise removal procedures follow. Subsequent procedures are vertex extraction and vertex grouping. Finally, CIF is extracted from the coordinates of the grouped vertices. In this paper, the final process is applied to only metal layer. In experiments, this processing scheme is shown to be very effective in extracting CIF.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1994년도 FIFTH WESTERN PACIFIC REGIONAL ACOUSTICS CONFERENCE SEOUL KOREA
• /
• pp.931-936
• /
• 1994

Although an ideal low-pass filter is not physically realizable, it can be approximated on the basis of time reversal techniques. In this paper, we describe a method to approximately implement the ideal low-pass filter and apply it to the pitch extraction system. Experimental results show that our method is effective to estimate the fundamental frequency of the speech signal.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권12호
• /
• pp.6038-6053
• /
• 2017

In this study, we propose an automatic melody extraction algorithm using deep learning. In this algorithm, feature images, generated using the energy of frequency band, are extracted from polyphonic audio files and a deep learning technique, a convolutional neural network (CNN), is applied on the feature images. In the training data, a short frame of polyphonic music is labeled as a musical note and a classifier based on CNN is learned in order to determine a pitch value of a short frame of audio signal. We want to build a novel structure of melody extraction, thus the proposed algorithm has a simple structure and instead of using various signal processing techniques for melody extraction, we use only a CNN to find a melody from a polyphonic audio. Despite of simple structure, the promising results are obtained in the experiments. Compared with state-of-the-art algorithms, the proposed algorithm did not give the best result, but comparable results were obtained and we believe they could be improved with the appropriate training data. In this paper, melody extraction and the proposed algorithm are introduced first, and the proposed algorithm is then further explained in detail. Finally, we present our experiment and the comparison of results follows.

• 정보보호학회논문지
• /
• 제34권3호
• /
• pp.403-416
• /
• 2024

악성코드는 금전적인 목적에 의하여 서비스의 한 형태로 블랙마켓에 판매되고 있다. 판매에 따른 수요가 증가함에 따라 악성코드를 통한 공격이 확장되었다. 이에 대응하기 위해 인공지능을 활용한 탐지 및 분류 연구들이 등장하였지만, 공격자들은 분석을 방지하고자 다양한 안티 분석기술을 악성코드에 적용하고 있다. 본 논문에서는 안티 분석 기술이 적용된 악성코드들로부터 데이터셋을 확보하기 위해 하이브리드형 바이너리 분석 프레임워크 Malware Analysis with Dynamic Extraction(MADE)을 제안한다. MADE 프레임워크는 Anti-VM, Anti-Debugging이 적재된 바이너리를 포함하여 자동화된 동적 분석을 수행할 수 있다. MADE 프레임워크는 Anti-Analysis 기술이 적용된 다양한 악성코드들에 대해 90% 이상 우회가 가능하며, API 호출 정보를 포함한 데이터셋 추출이 가능함을 실험을 통해 검증하였다.

• Journal of Information Processing Systems
• /
• 제7권3호
• /
• pp.459-472
• /
• 2011

The vast number of biomedical literature is an important source of biomedical interaction information discovery. However, it is complicated to obtain interaction information from them because most of them are not easily readable by machine. In this paper, we present a method for extracting biomedical interaction information assuming that the biomedical Named Entities (NEs) are already identified. The proposed method labels all possible pairs of given biomedical NEs as INTERACTION or NO-INTERACTION by using a Maximum Entropy (ME) classifier. The features used for the classifier are obtained by applying various NLP techniques such as POS tagging, base phrase recognition, parsing and predicate-argument recognition. Especially, specific verb predicates (activate, inhibit, diminish and etc.) and their biomedical NE arguments are very useful features for identifying interactive NE pairs. Based on this, we devised a twostep method: 1) an interaction verb extraction step to find biomedically salient verbs, and 2) an argument relation identification step to generate partial predicate-argument structures between extracted interaction verbs and their NE arguments. In the experiments, we analyzed how much each applied NLP technique improves the performance. The proposed method can be completely improved by more than 2% compared to the baseline method. The use of external contextual features, which are obtained from outside of NEs, is crucial for the performance improvement. We also compare the performance of the proposed method against the co-occurrence-based and the rule-based methods. The result demonstrates that the proposed method considerably improves the performance.

• 대한원격탐사학회지
• /
• 제19권6호
• /
• pp.421-430
• /
• 2003

Radarsat-1 위성으로부터 수신된 신호자료를 처리하여 영상을 생성하기 위해서는 도플러 정보(도플러 중심주파수(f$_{dc}$) 및 주파수 변화율 (f$_{r}$)를 정확하게 추정하는 것이 중요하다. 일반적으로 이들 정보들은 신호자료를 기반으로 하는 clutterlock 및 auto-focusing 기법이 사용되고 있으나 이들은 수신 신호만을 사용하여 추정하므로 SAR 프로세서 개발시 구현하기가 어려우며 계산 시간도 많이 걸리는 단점이 있다. 본 논문에서는 주어진 위성의 궤도 및 자세정보를 최대한 이용하며 수신신호 처리는 최소한이 되도록 하여 구현이 쉽고 계산상 이점이 있는 새로운 기법을 제안하였다. 실제 Radarsat-1 신호자료를 이용한 실험적용 결과, 본 기법이 실제 SAR 신호자료로부터 도플러 정보를 추출하는데 유용하게 사용될 수 있을 것으로 판단된다.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• 제46권6호
• /
• pp.403-408
• /
• 2020

Objectives: Appropriate and accurate local anesthetic (LA) techniques are indispensable in the field of oral and maxillofacial surgery to obtain a satisfactory outcome for both the operating surgeon and the patient. When used alone, the inferior alveolar nerve block (IANB) technique requires supplemental injections like long buccal nerve block for extraction of mandibular molars leading to multiple traumatic experiences for the patient. The aim of this study was to anesthetize the inferior alveolar, lingual, and long buccal nerves with single-needle penetration requiring a minimal skillset such as administering a conventional IANB through introduction of the Benny Joseph technique for extraction of mandibular molars. Materials and Methods: This was a prospective study conducted in the Department of Oral and Maxillofacial Surgery, Kunhitharuvai Memorial Charitable Trust (KMCT) Dental College, Calicut, India. The duration of the study was 6 months, from June to November 2017, with a maximum sample size of 616 cases. The LA solution was 2% lignocaine with 1:100,000 adrenaline. The patients were selected from a population in the range of 20 to 40 years of age who reported to the outpatient department for routine dental extraction of normally positioned mandibular right or left first or second molars. Results: Of the 616 patients, 42 patients (6.8%) required re-anesthetization, a success rate of 93.2%. There were no complications such as hematoma formation, trismus, positive aspiration, and nerve injuries. None of the cases required re-anesthetization in the perioperative period. Conclusion: The Benny Joseph technique can be employed and is effective compared with conventional IANB techniques by reducing trauma to the patient and also requires less technique sensitivity.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.1338-1343
• /
• 2003

Data is the expression of the language or numerical values that show some characteristics. And information is extracted from data for the specific purposes. The knowledge is utilized as information to construct rules that recognize patterns and make decisions. Today, knowledge extraction and application of the knowledge are broadly accomplished to improve the comprehension and to elevate the performance of systems in several industrial fields. The knowledge extraction could be achieved by some steps that include the knowledge acquisition, expression, and implementation. Such extracted knowledge can be drawn by rules. Clustering (CU, input space partition (ISP), neuro-fuzzy (NF), neural network (NN), extension matrix (EM), etc. are employed for expression the knowledge by rules. In this paper, the various approaches of the knowledge extraction are examined by categories that separate the methods by the applied industrial fields. Also, the several test data and the experimental results are compared and analysed based upon the applied techniques that include CL, ISP, NF, NN, EM, and so on.