• 반도체디스플레이기술학회지
• /
• 제22권3호
• /
• pp.161-165
• /
• 2023

One of the difficult works in an autonomous driving system is detecting road lanes or objects in the road boundaries. Detecting and tracking a vehicle is able to play an important role on providing important information in the framework of advanced driver assistance systems such as identifying road traffic conditions and crime situations. This paper proposes a vehicle detection scheme based on deep learning to classify and tracking vehicles in a complex and diverse environment. We use the modified YOLO as the object detector and polynomial regression as object tracker in the driving video. With the experimental results, using YOLO model as deep learning model, it is possible to quickly and accurately perform robust vehicle tracking in various environments, compared to the traditional method.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2015년도 추계학술발표대회
• /
• pp.1736-1739
• /
• 2015

Social learning encourages and enables learners with common interests to communicate and share knowledge with others through social networks. However, social learning suffers a barrier on communication among learners with various la nguage and culture background. Aiming to avoid this barrier, this paper proposes a framework of cross-language s ocial learning system which can involve more learners' participation on the web. With this framework, an illustrati ve example of task-oriented collaborative learning paradigm is elaborated. It is expected that our proposed system can stimulate more learners to share the learning resource for deep discussions as well as to promote the knowled ge innovation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권12호
• /
• pp.3855-3867
• /
• 2022

Name separation (splitting full names into surnames and given names) is not a tedious task in a multiethnic country because the procedure for splitting surnames and given names is ethnicity-specific. Malaysia has multiple main ethnic groups; therefore, separating Malaysian full names into surnames and given names proves a challenge. In this study, we develop a two-phase framework for Malaysian name separation using deep learning. In the initial phase, we predict the ethnicity of full names. We propose a recurrent neural network with long short-term memory network-based model with character embeddings for prediction. Based on the predicted ethnicity, we use a rule-based algorithm for splitting full names into surnames and given names in the second phase. We evaluate the performance of the proposed model against various machine learning models and demonstrate that it outperforms them by an average of 9%. Moreover, transfer learning and fine-tuning of the proposed model with an additional dataset results in an improvement of up to 7% on average.

• 대한수학회지
• /
• 제59권2호
• /
• pp.311-335
• /
• 2022

This paper treats Merton's classical portfolio optimization problem for a market participant who invests in safe assets and risky assets to maximize the expected utility. When the state process is a d-dimensional Markov diffusion, this problem is transformed into a problem of solving a Hamilton-Jacobi-Bellman (HJB) equation. The main purpose of this paper is to solve this HJB equation by a deep learning algorithm: the deep Galerkin method, first suggested by J. Sirignano and K. Spiliopoulos. We then apply the algorithm to get the solution to the HJB equation and compare with the result from the finite difference method.

• International Journal of Computer Science & Network Security
• /
• 제21권7호
• /
• pp.324-330
• /
• 2021

Agriculture is one of the essential needs of human life on planet Earth. It is the source of food and earnings for many individuals around the world. The economy of many countries is associated with the agriculture sector. Lots of diseases exist that attack various fruits and crops. Apple Tree Leaves also suffer different types of pathological conditions that affect their production. These pathological conditions include apple scab, cedar apple rust, or multiple diseases, etc. In this paper, an automatic detection framework based on deep learning is investigated for apple leaves disease classification. Different pre-trained models, VGG16, ResNetV2, InceptionV3, and MobileNetV2, are considered for transfer learning. A combination of parameters like learning rate, batch size, and optimizer is analyzed, and the best combination of ResNetV2 with Adam optimizer provided the best classification accuracy of 94%.

• Journal of Positioning, Navigation, and Timing
• /
• 제10권2호
• /
• pp.113-120
• /
• 2021

The Distance Measuring Equipment (DME) is a ground-based aircraft navigation system and is considered as an infrastructure that ensures resilient aircraft navigation capability during the event of a Global Navigation Satellite System (GNSS) outage. The main problem of DME as a GNSS back up is a poor positioning accuracy that often reaches over 100 m. In this paper, a novel approach of applying deep reinforcement learning to a DME pulse design is introduced to improve the DME distance measuring accuracy. This method is designed to develop multipath-resistant DME pulses that comply with current DME specifications. In the research, a Markov Decision Process (MDP) for DME pulse design is set using pulse shape requirements and a timing error. Based on the designed MDP, we created an Environment called PulseEnv, which allows the agent representing a DME pulse shape to explore continuous space using the Soft Actor Critical (SAC) reinforcement learning algorithm.

• 한국구조물진단유지관리공학회 논문집
• /
• 제25권4호
• /
• pp.65-74
• /
• 2021

빠르게 증가하는 노후 터널을 효율적으로 관리하기 위하여 최근 영상장비를 이용한 점검 방법론들이 많이 제안되고 있다. 하지만 기존의 방법론들은 대부분 국한된 영역에서 검증을 수행하였을 뿐 아니라, 다른 물체들이 존재하지 않는 깨끗한 콘크리트 표면에서 검증되어 실제 현장에 대한 적용성을 검증하기 어려웠다. 따라서 본 논문에서는 이러한 한계를 극복하기 위하여 비균열 물체 학습에 기반한 6단계 터널 균열 탐지 딥러닝 모델 개발 프레임워크를 제안한다. 제안된 프레임워크는 터널에서 취득된 이미지 내 균열 탐색, 픽셀 단위 균열 라벨링, 딥러닝 모델 학습, 비균열 물체 수집, 비균열 물체 재학습, 최종 학습 데이터 구축의 총 6단계로 이루어진다. 제안된 프레임워크를 이용하여 개발된 균열 탐지 딥러닝 모델 개발을 수행하였으며, 일반 균열 1561장, 비균열 206장으로 개별 물체 세분화(Instance Segmentation) 모델인 Cascade Mask R-CNN을 학습시켰다. 학습된 모델의 현장 적용성을 검토하기 위하여 전선, 전등 등을 포함하는 약 200m 길이의 실제 터널에서 균열 탐지를 수행하였다. 실험 결과 학습된 모델은 99% 정밀도와 92%의 재현율을 나타내며 뛰어난 현장 적용성을 나타내었다.

• 한국소프트웨어감정평가학회 논문지
• /
• 제16권2호
• /
• pp.63-68
• /
• 2020

본 논문에서는 딥러닝 프레임워크 기반의 얼굴인증 시스템에 대하여 제안한다. 제안 시스템은 딥러닝 알고리즘을 활용하여 얼굴영역 검출과 얼굴 특징 추출을 수행하고, 결합베이시안 학습 모델을 이용하여 얼굴인증을 수행한다. 제안 얼굴인증 알고리즘에 대한 성능 평가는 다양한 얼굴 사진들로 구성된 데이터베이스를 이용하여 수행하였으며, 한 명에 대한 얼굴 영상은 2장으로 구성하였다. 또한 얼굴인증 실험은 딥 뉴럴 네트워크를 통한 2048차원의 특징과 그 유사성을 측정하기 위해 결합베이시안 알고리즘을 적용하였으며, 얼굴인증에 실패한 동일오율을 계산함으로써 성능평가를 수행하였다. 실험 결과, 딥러닝 특징과 결합베이시안 알고리즘을 사용한 제안 방법은 1.2%의 동일오율을 보였다.

• 한국음향학회지
• /
• 제35권2호
• /
• pp.143-148
• /
• 2016

깊은 신경망은 데이터의 특성을 효과적으로 나타낼 수 있는 방법으로 최근 많은 응용 분야에서 활용되고 있다. 하지만, 제한적인 양의 데이터베이스는 깊은 신경망을 훈련하는 과정에서 과적합 문제를 야기할 수 있다. 본 논문에서는 풍부한 양의 음성 혹은 음악 데이터를 이용한 전이학습을 통해 제한적인 양의 사운드 이벤트에 대한 깊은 신경망을 효과적으로 훈련하는 방법을 제안한다. 일련의 실험을 통해 제안하는 방법이 적은 양의 사운드 이벤트 데이터만으로 훈련된 깊은 신경망에 비해 현저한 성능 향상이 있음을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권12호
• /
• pp.4345-4363
• /
• 2021

Deep Learning as a Service (DLaaS), utilizing the cloud-based deep neural network models to provide customer prediction services, has been widely deployed on mobile cloud computing (MCC). Such services raise privacy concerns since customers need to send private data to untrusted service providers. In this paper, we devote ourselves to building an efficient protocol to classify users' images using the convolutional neural network (CNN) model trained and held by the server, while keeping both parties' data secure. Most previous solutions commonly employ homomorphic encryption schemes based on Ring Learning with Errors (RLWE) hardness or two-party secure computation protocols to achieve it. However, they have limitations on large communication overheads and costs in MCC. To address this issue, we present LeHE4SCNN, a scalable privacy-preserving and communication-efficient framework for CNN-based DLaaS. Firstly, we design a novel low-expansion rate homomorphic encryption scheme with packing and unpacking methods (LeHE). It supports fast homomorphic operations such as vector-matrix multiplication and addition. Then we propose a secure prediction framework for CNN. It employs the LeHE scheme to compute linear layers while exploiting the data shuffling technique to perform non-linear operations. Finally, we implement and evaluate LeHE4SCNN with various CNN models on a real-world dataset. Experimental results demonstrate the effectiveness and superiority of the LeHE4SCNN framework in terms of response time, usage cost, and communication overhead compared to the state-of-the-art methods in the mobile cloud computing environment.