• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.11
• /
• pp.3991-4010
• /
• 2021

The Question Similarity Measurement of Chinese Crop Diseases and Insect Pests (QSM-CCD&IP) aims to judge the user's tendency to ask questions regarding input problems. The measurement is the basis of the Agricultural Knowledge Question and Answering (Q & A) system, information retrieval, and other tasks. However, the corpus and measurement methods available in this field have some deficiencies. In addition, error propagation may occur when the word boundary features and local context information are ignored when the general method embeds sentences. Hence, these factors make the task challenging. To solve the above problems and tackle the Question Similarity Measurement task in this work, a corpus on Chinese crop diseases and insect pests(CCDIP), which contains 13 categories, was established. Then, taking the CCDIP as the research object, this study proposes a Chinese agricultural text similarity matching model, namely, the AgrCQS. This model is based on mixed information extraction. Specifically, the hybrid embedding layer can enrich character information and improve the recognition ability of the model on the word boundary. The multi-scale local information can be extracted by multi-core convolutional neural network based on multi-weight (MM-CNN). The self-attention mechanism can enhance the fusion ability of the model on global information. In this research, the performance of the AgrCQS on the CCDIP is verified, and three benchmark datasets, namely, AFQMC, LCQMC, and BQ, are used. The accuracy rates are 93.92%, 74.42%, 86.35%, and 83.05%, respectively, which are higher than that of baseline systems without using any external knowledge. Additionally, the proposed method module can be extracted separately and applied to other models, thus providing reference for related research.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.11
• /
• pp.4065-4083
• /
• 2021

Super-resolution can improve the clarity of low-resolution (LR) images, which can increase the accuracy of high-level compute vision tasks. Portable devices have low computing power and storage performance. Large-scale neural network super-resolution methods are not suitable for portable devices. In order to save the computational cost and the number of parameters, Lightweight image processing method can improve the processing speed of portable devices. Therefore, we propose the Enhanced Information Multiple Distillation Network (EIMDN) to adapt lower delay and cost. The EIMDN takes feedback mechanism as the framework and obtains low level features through high level features. Further, we replace the feature extraction convolution operation in Information Multiple Distillation Block (IMDB), with Ghost module, and propose the Enhanced Information Multiple Distillation Block (EIMDB) to reduce the amount of calculation and the number of parameters. Finally, coordinate attention (CA) is used at the end of IMDB and EIMDB to enhance the important information extraction from Spaces and channels. Experimental results show that our proposed can achieve convergence faster with fewer parameters and computation, compared with other lightweight super-resolution methods. Under the condition of higher peak signal-to-noise ratio (PSNR) and higher structural similarity (SSIM), the performance of network reconstruction image texture and target contour is significantly improved.

• Journal of the Korea Convergence Society
• /
• v.10 no.1
• /
• pp.103-113
• /
• 2019

License plate recognition camera is dedicated device designed for acquiring images of the target vehicle for recognizing letters and numbers in a license plate. Mostly, it is used as a part of the system combined with server and image analysis module rather than as a single use. However, building a system for vehicle license plate recognition is costly because it is required to construct a facility with a server providing the management and analysis of the captured images and an image analysis module providing the extraction of numbers and characters and recognition of the vehicle's plate. In this study, we would like to develop an embedded type convergent camera (Edge Base) which can expand the function of the camera to not only the license plate recognition but also the security CCTV function together and to perform two functions within the camera. This embedded type convergence camera equipped with a high resolution 4K IP camera for clear image acquisition and fast data transmission extracted license plate area by applying YOLO, a deep learning software for multi object recognition based on open source neural network algorithm and detected number and characters of the plate and verified the detection accuracy and recognition accuracy and confirmed that this camera can perform CCTV security function and vehicle number plate recognition function successfully.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.1-16
• /
• 2022

Despite recent breakthroughs in deep learning and computer vision fields, the pixel-wise identification of tiny objects in high-resolution images with complex disturbances remains challenging. This study proposes a modified U-net for tiny crack segmentation in real-world steel-box-girder bridges. The modified U-net adopts the common U-net framework and a novel Self-Attention-Self-Adaption (SASA) neuron as the fundamental computing element. The Self-Attention module applies softmax and gate operations to obtain the attention vector. It enables the neuron to focus on the most significant receptive fields when processing large-scale feature maps. The Self-Adaption module consists of a multiplayer perceptron subnet and achieves deeper feature extraction inside a single neuron. For data augmentation, a grid-based crack random elastic deformation (CRED) algorithm is designed to enrich the diversities and irregular shapes of distributed cracks. Grid-based uniform control nodes are first set on both input images and binary labels, random offsets are then employed on these control nodes, and bilinear interpolation is performed for the rest pixels. The proposed SASA neuron and CRED algorithm are simultaneously deployed to train the modified U-net. 200 raw images with a high resolution of 4928 × 3264 are collected, 160 for training and the rest 40 for the test. 512 × 512 patches are generated from the original images by a sliding window with an overlap of 256 as inputs. Results show that the average IoU between the recognized and ground-truth cracks reaches 0.409, which is 29.8% higher than the regular U-net. A five-fold cross-validation study is performed to verify that the proposed method is robust to different training and test images. Ablation experiments further demonstrate the effectiveness of the proposed SASA neuron and CRED algorithm. Promotions of the average IoU individually utilizing the SASA and CRED module add up to the final promotion of the full model, indicating that the SASA and CRED modules contribute to the different stages of model and data in the training process.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.1
• /
• pp.15-26
• /
• 2013

This paper proposes a classification method of parallel, vertical parking states and pillars for parking assist system using ultrasonic sensors. Since, in general parking space detection module, the compressed amplitude of ultrasonic data are received, the analysis of them is difficult. To solve these problems, in preprocessing state, symmetric transform and noise removal are performed. In feature extraction process, four features, standard deviation of distance, reconstructed peak, standard deviation of reconstructed signal and sum of width, are proposed. Gaussian fitting model is used to reconstruct saturated peak signal and discriminability of each feature is measured. To find the best combination among these features, multi-class SVM and subset generator are used for more accurate and robust classification. The proposed method shows 92 % classification rate and proves the applicability to parking space detection modules.

• Journal of the Korean Society of Systems Engineering
• /
• v.15 no.2
• /
• pp.17-30
• /
• 2019

Due to difficulties in tracking design information of existing document-based configuration management, the research on the development of plant SysML model was started to apply the model-based system engineering methodology to comprehensively manage various design information. However, until now, in order to create the SysML model, the engineers are checking the design information and inputting it to the SysML model. This process requires a lot of time and manpower, it is required to minimize it. Therefore, this study has recognized the problem, a plug-in that extracts the plant design information in the design document and automatically converts the SysML plant model from it. Specifically, the development was performed in the following order. First, the extraction file was selected as the most commonly used Excel file as the plant design document. Next, the design information in the document was analyzed, and extracted information including tag number, name, and the capacity were selected. Finally, the plant SysML model conversion module was implemented. The developed plug-in is confirmed that the task load of the engineers by the SysML model conversion can be minimized and the model can be generated more quickly and accurately.

• Journal of Advanced Marine Engineering and Technology
• /
• v.36 no.8
• /
• pp.1123-1128
• /
• 2012

The goal of this research is to develop an error-driven noun-connection rules which is used for breaking complicate nouns in Korean morphology analysis module. We collected complicate nouns from Web sites, and analyzed them by CnuMa. Whenever we find errors from outputs of the analyzer, we write noun-connection rules to correct the errors. The noun-connection rules are devised by considering left/right contexts in compound nouns. The error-driven noun-connection rules are helpful in improving precision and recall of a Korean morphology analyzer, CnuMa by 2.8% and 10.8%, respectively.

• Journal of Intelligence and Information Systems
• /
• v.10 no.1
• /
• pp.65-75
• /
• 2004

It is notorious that PIN(Personal Identification Number) is used widely for user verification and authentication in networked environment. But, when the user Identification and password are exposed by hacking, we can be damaged monetary damage as well as invasion of privacy. In this paper, we adopt face recognition-based authentication which have nothing to worry what the ID and password will be exposed. Also, we suggest the remote authentication and verification system by considering not only 2-Tier system but also 3-Tier system getting be distributed. In this research, we analyze the face feature data using the SVM(Support Vector Machine) and PCA(Principle Component Analysis), and implement artificial intelligence face recognition module in distributed environment which increase the authentication speed and heightens accuracy by utilizing artificial intelligence techniques.

• Journal of Digital Contents Society
• /
• v.15 no.4
• /
• pp.473-480
• /
• 2014

As the use of computer has been popularized these days, an active research is in progress to make much more convenient and natural interface compared to the existing user interfaces such as keyboard or mouse. For this reason, there is an increasing interest toward Microsoft's motion sensing module called Kinect, which can perform hand motions and speech recognition system in order to realize communication between people. Kinect uses its built-in sensor to recognize the main joint movements and depth of the body. It can also provide a simple speech recognition through the built-in microphone. In this paper, the goal is to use Kinect's depth value data, skeleton tracking and labeling algorithm to recognize information about the extraction and movement of hand, and replace the role of existing peripherals using a virtual mouse, a virtual keyboard, and a speech recognition.

• Journal of Korea Game Society
• /
• v.20 no.1
• /
• pp.3-12
• /
• 2020

This paper proposes a structure based on a production method of concept art focused on the player's experience through a module by using the game aesthetics of the MDA framework. And also a partially automated process established in concept art production by using the 'Adobe Color image color extraction' as a tool in the work production process. This paper proposed a work process of not just a personal expression but a systematic molding expression to use, and this could see as the various possibilities of game concept art productions.