• Journal of Power Electronics
• /
• 제15권2호
• /
• pp.469-478
• /
• 2015

In order to promote the application of switched reluctance machines (SRM) in electric vehicles (EVs), the braking torque closed-loop control of a SRM is proposed. A hysteresis current regulator with the soft chopping mode is employed to reduce the switching frequency and switching loss. A torque estimator is designed to estimate the braking torque online and to achieve braking torque feedback. A feed-forward plus saturation compensation torque regulator is designed to decrease the dynamic response time and to improve the steady-state accuracy of the braking torque. The turn-on and turn-off angles are optimized by a genetic algorithm (GA) to reduce the braking torque ripple and to improve the braking energy feedback efficiency. Finally, a simulation model and an experimental platform are built. The simulation and experimental results demonstrate the correctness of the proposed control strategy.

• Journal of Power Electronics
• /
• 제8권2호
• /
• pp.181-191
• /
• 2008

The task performed by induction motors grows increasingly complex in modern industry and hence improvements are sought in the field of fault diagnosis. It is essential to diagnose faults at their very inception, as unscheduled machine down time can upset critical dead lines and cause heavy financial losses. Artificial intelligence (AI) techniques have proved their ability in detection of incipient faults in electrical machines. This paper presents an application of AI techniques for the detection of inter-turn insulation and bearing wear faults in single-phase induction motors. The single-phase induction motor is considered a proto type model to create inter-turn insulation and bearing wear faults. The experimental data for motor intake current, rotor speed, stator winding temperature, bearing temperature and noise of the motor under running condition was generated in the laboratory. The different types of fault detectors were developed based upon three different AI techniques. The input parameters for these detectors were varied from two to five sequentially. The comparisons were made and the best fault detector was determined.

• 한국항행학회논문지
• /
• 제17권6호
• /
• pp.652-657
• /
• 2013

논문에서는 두 가지 혼돈맵들을 연결시킨 하나의 합성맵을 기초로 사용하는 독립된 하나의 합성상태머신을 설계하는 방법 및 그 결과를 제시하였다. 혼돈2진스트림발생기로 사용하기 위하여 혼돈합성맵에 관한 디지털회로를 설계하였다. 두 가지 혼돈함수들- 톱니함수와 비뚤어진 로지스틱 함수-로 구성되는 혼돈합성함수의 이산화 진리표를 작성하였고, 디지털회로의 수학적 모델로써 간략화 된 부울대수식들을 제시하였다. 결과로써 혼돈합성함수의 맵에 관한 디지털회로들을 제시하였다.

• Smart Structures and Systems
• /
• 제18권3호
• /
• pp.585-599
• /
• 2016

Steel cables serve as the key structural components in long-span bridges, and the force state of the steel cable is deemed to be one of the most important determinant factors representing the safety condition of bridge structures. The disadvantages of traditional cable force measurement methods have been envisaged and development of an effective alternative is still desired. In the last decade, the vision-based sensing technology has been rapidly developed and broadly applied in the field of structural health monitoring (SHM). With the aid of vision-based multi-point structural displacement measurement method, monitoring of the tensile force of the steel cable can be realized. In this paper, a novel cable force monitoring system integrated with a multi-point pattern matching algorithm is developed. The feasibility and accuracy of the developed vision-based force monitoring system has been validated by conducting the uniaxial tensile tests of steel bars, steel wire ropes, and parallel strand cables on a universal testing machine (UTM) as well as a series of moving loading experiments on a scale arch bridge model. The comparative study of the experimental outcomes indicates that the results obtained by the vision-based system are consistent with those measured by the traditional method for cable force measurement.

• International Journal of Computer Science & Network Security
• /
• 제21권1호
• /
• pp.97-106
• /
• 2021

Social networking platforms have become a smart way for people to interact and meet on internet. It provides a way to keep in touch with friends, families, colleagues, business partners, and many more. Among the various social networking sites, Twitter is one of the fastest-growing sites where users can read the news, share ideas, discuss issues etc. Due to its vast popularity, the accounts of legitimate users are vulnerable to the large number of threats. Spam and Malware are some of the most affecting threats found on Twitter. Therefore, in order to enjoy seamless services it is required to secure Twitter against malicious users by fixing them in advance. Various researches have used many Machine Learning (ML) based approaches to detect spammers on Twitter. This research aims to devise a secure system based on Hybrid Similarity Cosine and Soft Cosine measured in combination with Genetic Algorithm (GA) and Artificial Neural Network (ANN) to secure Twitter network against spammers. The similarity among tweets is determined using Cosine with Soft Cosine which has been applied on the Twitter dataset. GA has been utilized to enhance training with minimum training error by selecting the best suitable features according to the designed fitness function. The tweets have been classified as spammer and non-spammer based on ANN structure along with the voting rule. The True Positive Rate (TPR), False Positive Rate (FPR) and Classification Accuracy are considered as the evaluation parameter to evaluate the performance of system designed in this research. The simulation results reveals that our proposed model outperform the existing state-of-arts.

• 대한임베디드공학회논문지
• /
• 제17권6호
• /
• pp.309-317
• /
• 2022

In this paper, we propose a machine learning-based copy-move forgery detection network with dual branches. Because the rotation or scaling operation is frequently involved in copy-move forger, the conventional convolutional neural network is not effectively applied in detecting copy-move tampering. Therefore, we divide the input into rotation-invariant and scaling-invariant features based on the wavelet coefficients. Each of the features is input to different branches having the same structure, and is fused in the combination module. Each branch comprises feature extraction, correlation, and mask decoder modules. In the proposed network, VGG16 is used for the feature extraction module. To check similarity of features generated by the feature extraction module, the conventional correlation module used. Finally, the mask decoder model is applied to develop a pixel-level localization map. We perform experiments on test dataset and compare the proposed method with state-of-the-art tampering localization methods. The results demonstrate that the proposed scheme outperforms the existing approaches.

• 한국전자통신학회논문지
• /
• 제18권4호
• /
• pp.693-700
• /
• 2023

텍스트 문서에서 주관적인 의견과 감정을 긍정 혹은 부정으로 분류하고 식별하는 자연어 처리의 한 분야인 감성 분석은 고객 선호도 분석을 통해 다양한 홍보 및 서비스에 활용할 수 있다. 이를 위해 최근 머신러닝과 딥러닝의 다양한 기법을 활용한 연구가 진행되어 왔다. 본 연구에서는 기존의 RNN 기반 모델들과 최근 트랜스포머 기반 언어 모델들을 활용하여 영화, 상품 및 게임 리뷰를 대상으로 감성 분석의 정확도를 비교 분석하여 최적의 언어 모델을 제안하고자 한다. 실험 결과 한국어 말뭉치로 사전 학습된 모델들 중 LMKor-BERT와 GPT-3가 상대적으로 좋은 정확도를 보여주었다.

• 한국군사과학기술학회지
• /
• 제26권1호
• /
• pp.44-53
• /
• 2023

Adversarial attacks have received great attentions for their capacity to distract state-of-the-art neural networks by modifying objects in physical domain. Patch-based attack especially have got much attention for its optimization effectiveness and feasible adaptation to any objects to attack neural network-based object detectors. However, despite their strong attack performance, generated patches are strongly perceptible for humans, violating the fundamental assumption of adversarial examples. In this paper, we propose a camouflaged adversarial patch optimization method using military camouflage assessment metrics for naturalistic patch attacks. We also investigate camouflaged attack loss functions, applications of various camouflaged patches on army tank images, and validate the proposed approach with extensive experiments attacking Yolov5 detection model. Our methods produce more natural and realistic looking camouflaged patches while achieving competitive performance.

• International Journal of Internet, Broadcasting and Communication
• /
• 제15권2호
• /
• pp.124-132
• /
• 2023

In this paper, we present a simple classification model based on statistical features and demonstrate the successful implementation of a brain-computer interface (BCI) based light on/off control system. This research shows study and development of light on/off control system based on BCI technology, which allows the users to control switching a lamp using electroencephalogram (EEG) signals. The logistic regression algorithm is used for classification of the EEG signal to convert it into light on, light off control commands. Training data were collected using 14-channel BCI system which records the brain signals of participants watching a screen with flickering lights and saves the data into .csv file for future analysis. After extracting a number of features from the data and performing classification using logistic regression, we created commands to switch on a physical lamp and tested it in a real environment. Logistic regression allowed us to quite accurately classify the EEG signals based on the user's mental state and we were able to classify the EEG signals with 82.5% accuracy, producing reliable commands for turning on and off the light.

• International Journal of Computer Science & Network Security
• /
• 제23권12호
• /
• pp.213-219
• /
• 2023

In recent years, popularity of deep learning (DL) is increased due to its ability to extract features from Hyperspectral images. A lack of discrimination power in the features produced by traditional machine learning algorithms has resulted in poor classification results. It's also a study topic to find out how to get excellent classification results with limited samples without getting overfitting issues in hyperspectral images (HSIs). These issues can be addressed by utilising a new learning network structure developed in this study.EfficientNet-B4-Based Convolutional network (EN-B4), which is why it is critical to maintain a constant ratio between the dimensions of network resolution, width, and depth in order to achieve a balance. The weight of the proposed model is optimized by Search and Rescue Operations (SRO), which is inspired by the explorations carried out by humans during search and rescue processes. Tests were conducted on two datasets to verify the efficacy of EN-B4, with Indian Pines (IP) and the University of Pavia (UP) dataset. Experiments show that EN-B4 outperforms other state-of-the-art approaches in terms of classification accuracy.