• 반도체디스플레이기술학회지
• /
• 제20권3호
• /
• pp.6-10
• /
• 2021

Recognition of characters printed or marked on the PCB components from images captured using cameras is an important task in PCB components inspection systems. Previous optical character recognition (OCR) of PCB components typically consists of two stages: character segmentation and classification of each segmented character. However, character segmentation often fails due to corrupted characters, low image contrast, etc. Thus, OCR without character segmentation is desirable and increasingly used via deep neural networks. Typical implementation based on deep neural nets without character segmentation includes convolutional neural network followed by recurrent neural network (RNN). However, one disadvantage of this approach is slow execution due to RNN layers. LPRNet is a segmentation-free character recognition network with excellent accuracy proved in license plate recognition. LPRNet uses a wide convolution instead of RNN, thus enabling fast inference. In this paper, LPRNet was adapted for recognizing characters printed on PCB components with fast execution and high accuracy. Initial training with synthetic images followed by fine-tuning on real text images yielded accurate recognition. This net can be further optimized on Intel CPU using OpenVINO tool kit. The optimized version of the network can be run in real-time faster than even GPU.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권1호
• /
• pp.147-165
• /
• 2021

In this work, we empirically evaluated the efficiency of the recent EfficientNetB0 model to identify and diagnose malaria parasite infections in blood smears. The dataset used was collected and classified by relevant experts from the Lister Hill National Centre for Biomedical Communications (LHNCBC). We prepared our samples with minimal image transformations as opposed to others, as we focused more on the feature extraction capability of the EfficientNetB0 baseline model. We applied transfer learning to increase the initial feature sets and reduced the training time to train our model. We then fine-tuned it to work with our proposed layers and re-trained the entire model to learn from our prepared dataset. The highest overall accuracy attained from our evaluated results was 94.70% from fifty epochs and followed by 94.68% within just ten. Additional visualization and analysis using the Gradient-weighted Class Activation Mapping (Grad-CAM) algorithm visualized how effectively our fine-tuned EfficientNetB0 detected infections better than other recent state-of-the-art DCNN models. This study, therefore, concludes that when fine-tuned, the recent EfficientNetB0 will generate highly accurate deep learning solutions for the identification of malaria parasites in blood smears without the need for stringent pre-processing, optimization, or data augmentation of images.

• 한국재료학회지
• /
• 제31권7호
• /
• pp.403-408
• /
• 2021

Various surface colors are predicted and implemented using the interference color generated by controlling the thickness of nano-level diamond like carbon (DLC) thin film. Samples having thicknesses of up to 385 nm and various interference colors are prepared using a single crystal silicon (100) substrate with changing processing times at low temperature by plasma-enhanced chemical vapor deposition. The thickness, surface roughness, color, phases, and anti-scratch performance under each condition are analyzed using a scanning electron microscope, colorimeter, micro-Raman device, and scratch tester. Coating with the same uniformity as the surface roughness of the substrate is possible over the entire experimental thickness range, and more than five different colors are implemented at this time. The color matched with the color predicted by the model, assuming only the reflection mode of the thin film. All the DLC thin films show constant D/G peak fraction without significant change, and have anti-scratch values of about 19 N. The results indicate the possibility that nano-level DLC thin films with various interference colors can be applied to exterior materials of actual mobile devices.

• 인터넷정보학회논문지
• /
• 제22권3호
• /
• pp.9-16
• /
• 2021

This study aims to develop a human activity recognition (HAR) system as a Deep-Learning (DL) classification model, distinguishing various human activities. We solely rely on the signals from a wristband accelerometer worn by a person for the user's convenience. 3-axis sequential acceleration signal data are gathered within a predefined time-window-slice, and they are used as input to the classification system. We are particularly interested in developing a Deep-Learning model that can outperform conventional machine learning classification performance. A total of 13 activities based on the laboratory experiments' data are used for the initial performance comparison. We have improved classification performance using the Convolutional Neural Network (CNN) combined with an auto-encoder feature reduction and parameter tuning. With various publically available HAR datasets, we could also achieve significant improvement in HAR classification. Our CNN model is also compared against Recurrent-Neural-Network(RNN) with Long Short-Term Memory(LSTM) to demonstrate its superiority. Noticeably, our model could distinguish both general activities and near-identical activities such as sitting down on the chair and floor, with almost perfect classification accuracy.

• 한국정보통신학회논문지
• /
• 제25권12호
• /
• pp.1777-1783
• /
• 2021

대단위 신재생 에너지 발전단지의 효율적인 유지관리를 위해 드론의 활용이 점차 증가하고 있다. 오래전부터 태양광 패널을 드론으로 촬영하여 패널의 유실 및 오염 등을 관리하고 있다. 본 논문에서는 열화상카메라를 장착한 드론을 이용하여 획득된 태양광패널 이미지에서 아크, 단선, 크랙 등의 고장 유무를 판별하기 위해 시멘틱세그멘테이션 기법을 이용한 분류모델을 제안한다. 또한 적은 데이터셋으로도 강인한 분류 성능을 보이는 U-Net의 튜닝을 통해 효율적인 분류모델을 구현하였다.

• International Journal of Computer Science & Network Security
• /
• 제22권10호
• /
• pp.171-176
• /
• 2022

A dramatic rise in the number of people dying from heart disease has prompted efforts to find a way to identify it sooner using efficient approaches. A variety of variables contribute to the condition and even hereditary factors. The current estimate approaches use an automated diagnostic system that fails to attain a high level of accuracy because it includes irrelevant dataset information. This paper presents an effective neural network with convolutional layers for classifying clinical data that is highly class-imbalanced. Traditional approaches rely on massive amounts of data rather than precise predictions. Data must be picked carefully in order to achieve an earlier prediction process. It's a setback for analysis if the data obtained is just partially complete. However, feature extraction is a major challenge in classification and prediction since increased data increases the training time of traditional machine learning classifiers. The work integrates the CNN-MDRP classifier (convolutional neural network (CNN)-based efficient multimodal disease risk prediction with TANFIS (tuned adaptive neuro-fuzzy inference system) for earlier accurate prediction. Perform data cleaning by transforming partial data to informative data from the dataset in this project. The recommended TANFIS tuning parameters are then improved using a Laplace Gaussian mutation-based grasshopper and moth flame optimization approach (LGM²G). The proposed approach yields a prediction accuracy of 98.40 percent when compared to current algorithms.

• Smart Structures and Systems
• /
• 제30권2호
• /
• pp.145-157
• /
• 2022

The design of safe and economical structures depends on the reliable live load from load survey. Live load surveys are traditionally conducted by randomly selecting rooms and weighing each item on-site, a method that has problems of low efficiency, high cost, and long cycle time. This paper proposes a deep learning-based method combined with Internet big data to perform live load surveys. The proposed survey method utilizes multi-source heterogeneous data, such as images, voice, and product identification, to obtain the live load without weighing each item through object detection, web crawler, and speech recognition. The indoor objects and face detection models are first developed based on fine-tuning the YOLOv3 algorithm to detect target objects and obtain the number of people in a room, respectively. Each detection model is evaluated using the independent testing set. Then web crawler frameworks with keyword and image retrieval are established to extract the weight information of detected objects from Internet big data. The live load in a room is derived by combining the weight and number of items and people. To verify the feasibility of the proposed survey method, a live load survey is carried out for a meeting room. The results show that, compared with the traditional method of sampling and weighing, the proposed method could perform efficient and convenient live load surveys and represents a new load research paradigm.

• Advances in aircraft and spacecraft science
• /
• 제9권5호
• /
• pp.367-375
• /
• 2022

Modeling the properties of complex alloys such as nickel superalloys is an extremely challenging scientific and engineering task. The model should take into account a large number of uncorrelated factors, for many of which information may be missing or vague. The individual contribution of one or another chemical element out of a dozen possible ligants cannot be determined by traditional methods. Moreover, there are no general analytical models describing the influence of elements on the characteristics of alloys. Artificial neural networks are one of the few statistical modeling tools that can account for many implicit correlations and establish correspondences that cannot be identified by other more familiar mathematical methods. However, such networks require careful tuning to achieve high performance, which is time-consuming. Data preprocessing can make model training much easier and faster. This article focuses on combining physics-based deep network configuration and input data engineering to simulate the solvus temperature of nickel superalloys. The used deep artificial neural network shows good simulation results. Thus, this method of numerical simulation can be easily applied to such problems.

• Smart Structures and Systems
• /
• 제29권5호
• /
• pp.677-691
• /
• 2022

Water cycle algorithm (WCA) has been a very effective optimization technique for complex engineering problems. This study employs the WCA for simultaneous prediction of heating load (L_H) and cooling load (L_C) in residential buildings. This algorithm is responsible for optimally tuning a neural network (NN). Utilizing 614 records, the behavior of the L_H and L_C is explored and the captured knowledge is then used to predict for 154 unanalyzed building conditions. Since the WCA is a population-based algorithm, different numbers of the searching agents were tested to find the most optimum configuration. It was observed that the best solution is discovered by 500 agents. A comparison with five newly-developed benchmark optimizers, namely equilibrium optimizer (EO), multi-tracker optimization algorithm (MTOA), slime mould algorithm (SMA), multi-verse optimizer (MVO), and electromagnetic field optimization (EFO) revealed that the WCANN predicts the desired parameters with considerably larger accuracy. Obtained root mean square errors (1.4866, 2.1296, 2.8279, 2.5727, 2.5337, and 2.3029 for the L_H and 2.1767, 2.6459, 3.1821, 2.9732, 2.9616, and 2.6890 for the L_C) indicated that the most reliable prediction was presented by the proposed model. The EFONN, however, provided a more time-effective solution. Lastly, an explicit predictive formula was elicited from the WCANN.

• 소성∙가공
• /
• 제32권2호
• /
• pp.74-80
• /
• 2023

A deformation behavior of commercially pure titanium (CP-Ti) is highly dependent on material and processing parameters, such as deformation temperature, deformation direction, and strain rate. This study aims to predict the multivariable and nonlinear tensile behavior of CP-Ti using machine learning based on three algorithms: artificial neural network (ANN), light gradient boosting machine (LGBM), and long short-term memory (LSTM). The predictivity for tensile behaviors at the cryogenic temperature was lower than those in the room temperature due to the larger data scattering in the train dataset used in the machine learning. Although LGBM showed the lowest value of root mean squared error, it was not the best strategy owing to the overfitting and step-function morphology different from the actual data. LSTM performed the best as it effectively learned the continuous characteristics of a flow curve as well as it spent the reduced time for machine learning, even without sufficient database and hyperparameter tuning.