• Journal of Software Assessment and Valuation
• /
• v.17 no.2
• /
• pp.161-172
• /
• 2021

Neuromorphic architecture is drawing attention as a next-generation computing that supports artificial intelligence technology with low energy. However, FPGA embedded boards based on Neuromorphic architecturehave limited resources due to size and power. In this paper, we compared and evaluated the image reduction method using the interpolation method that rescales the size without considering the feature points and the DCT (Discrete Cosine Transform) method that preserves the feature points as much as possible based on energy. The scaled images were compared and analyzed for accuracy through CNN (Convolutional Neural Networks) in a PC environment and in the Nengo framework of an FPGA embedded board.. As a result of the experiment, DCT based classification showed about 1.9% higher performance than that of interpolation representation in both CNN and FPGA nengo environments. Based on the experimental results, when the DCT method is used in a limited resource environment such as an embedded board, a lot of resources are allocated to the expression of neurons used for classification, and the recognition rate is expected to increase.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.181-193
• /
• 2022

Data-driven structural health monitoring (SHM) of civil infrastructure can be used to continuously assess the state of a structure, allowing preemptive safety measures to be carried out. Long-term monitoring of large-scale civil infrastructure often involves data-collection using a network of numerous sensors of various types. Malfunctioning sensors in the network are common, which can disrupt the condition assessment and even lead to false-negative indications of damage. The overwhelming size of the data collected renders manual approaches to ensure data quality intractable. The task of detecting and classifying an anomaly in the raw data is non-trivial. We propose an approach to automate this task, improving upon the previously developed technique of image-based pre-processing on one-dimensional (1D) data by enriching the features of the neural network input data with multiple channels. In particular, feature engineering is employed to convert the measured time histories into a 3-channel image comprised of (i) the time history, (ii) the spectrogram, and (iii) the probability density function representation of the signal. To demonstrate this approach, a CNN model is designed and trained on a dataset consisting of acceleration records of sensors installed on a long-span bridge, with the goal of fault detection and classification. The effect of imbalance in anomaly patterns observed is studied to better account for unseen test cases. The proposed framework achieves high overall accuracy and recall even when tested on an unseen dataset that is much larger than the samples used for training, offering a viable solution for implementation on full-scale structures where limited labeled-training data is available.

• International Journal of Computer Science & Network Security
• /
• v.22 no.9
• /
• pp.175-182
• /
• 2022

In our daily life, we come across different types of information, for example in the format of multimedia and text. We all need different types of information for our common routines as watching/reading the news, listening to the radio, and watching different types of videos. However, sometimes we could run into problems when a certain type of information is required. For example, someone is listening to the radio and wants to listen to jazz, and unfortunately, all the radio channels play pop music mixed with advertisements. The listener gets stuck with pop music and gives up searching for jazz. So, the above example can be solved with an automatic audio classification system. Deep Learning (DL) models could make human life easy by using audio classifications, but it is expensive and difficult to deploy such models at edge devices like nano BLE sense raspberry pi, because these models require huge computational power like graphics processing unit (G.P.U), to solve the problem, we proposed DL model. In our proposed work, we had gone for a low complexity model for Audio Event Detection (AED), we extracted Mel-spectrograms of dimension 128×431×1 from audio signals and applied normalization. A total of 3 data augmentation methods were applied as follows: frequency masking, time masking, and mixup. In addition, we designed Convolutional Neural Network (CNN) with spatial dropout, batch normalization, and separable 2D inspired by VGGnet [1]. In addition, we reduced the model size by using model quantization of float16 to the trained model. Experiments were conducted on the updated dataset provided by the Detection and Classification of Acoustic Events and Scenes (DCASE) 2020 challenge. We confirm that our model achieved a val_loss of 0.33 and an accuracy of 90.34% within the 132.50KB model size.

• Journal of the Korean Orthopaedic Association
• /
• v.56 no.6
• /
• pp.535-539
• /
• 2021

Vascular complications following a femoral fracture are rare but can result in serious issues. Several case studies have reported pseudoaneurysms occurring after direct trauma or the insertion of a proximal femoral nail in the case of a proximal femoral fracture. The authors encountered an 85-year-old patient treated with retrograde intramedullary nail fixation for a distal femur fracture and suffered a decrease in the hemoglobin level, swelling, and pain on the 9^th day after surgery. The authors initially attributed the temporary hematoma and pain to ordinary postoperative processes. On the 16^th day after surgery, a pseudoaneurysm originating from the descending branch of the lateral femoral convolutional artery was diagnosed and treated by percutaneous vascular embolization. After the procedure, the hemoglobin level increased, and the swelling and pain decreased.

• Nuclear Engineering and Technology
• /
• v.54 no.10
• /
• pp.3620-3630
• /
• 2022

The diagnosis of abnormalities in a nuclear power plant is essential to maintain power plant safety. When an abnormal event occurs, the operator diagnoses the event and selects the appropriate abnormal operating procedures and sub-procedures to implement the necessary measures. To support this, abnormality diagnosis systems using data-driven methods such as artificial neural networks and convolutional neural networks have been developed. However, data-driven models cannot always guarantee an accurate diagnosis because they cannot simulate all possible abnormal events. Therefore, abnormality diagnosis systems should be able to detect their own potential misdiagnosis. This paper proposes a rulebased diagnostic validation algorithm using a previously developed two-stage diagnosis model in abnormal situations. We analyzed the diagnostic results of the sub-procedure stage when the first diagnostic results were inaccurate and derived a rule to filter the inconsistent sub-procedure diagnostic results, which may be inaccurate diagnoses. In a case study, two abnormality diagnosis models were built using gated recurrent units and long short-term memory cells, and consistency checks on the diagnostic results from both models were performed to detect any inconsistencies. Based on this, a re-diagnosis was performed to select the label of the second-best value in the first diagnosis, after which the diagnosis accuracy increased. That is, the model proposed in this study made it possible to detect diagnostic failures by the developed consistency check of the sub-procedure diagnostic results. The consistency check process has the advantage that the operator can review the results and increase the diagnosis success rate by performing additional re-diagnoses. The developed model is expected to have increased applicability as an operator support system in terms of selecting the appropriate AOPs and sub-procedures with re-diagnosis, thereby further increasing abnormal event diagnostic accuracy.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.5
• /
• pp.977-984
• /
• 2022

Recently, with the economic development of Southeast Asia, the use of information devices is widely spreading, and the demand for application services using intelligent character recognition is increasing. This paper discusses deep learning-based feature extraction and recognition of Myanmar, one of the Southeast Asian countries. Myanmar alphabet (33 letters) and Myanmar numerals (10 numbers) are used for feature extraction. In this paper, the number of nine features are extracted and more than three new features are proposed. Extracted features of each characters and numbers are expressed with successful results. In the recognition part, convolutional neural networks are used to assess its execution on character distinction. Its algorithm is implemented on captured image data-sets and its implementation is evaluated. The precision of models on the input data set is 96 % and uses a real-time input image.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3904-3922
• /
• 2022

As a research hotspot, pedestrian detection has a wide range of applications in the field of computer vision in recent years. However, current pedestrian detection methods have problems such as insufficient detection accuracy and large models that are not suitable for large-scale deployment. In view of these problems mentioned above, a lightweight pedestrian detection and early warning method using a new model called you only look once (Yolov5) is proposed in this paper, which utilizing advantages of Yolov5s model to achieve accurate and fast pedestrian recognition. In addition, this paper also optimizes the loss function of the batch normalization (BN) layer. After sparsification, pruning and fine-tuning, got a lot of optimization, the size of the model on the edge of the computing power is lower equipment can be deployed. Finally, from the experimental data presented in this paper, under the training of the road pedestrian dataset that we collected and processed independently, the Yolov5s model has certain advantages in terms of precision and other indicators compared with traditional single shot multiBox detector (SSD) model and fast region-convolutional neural network (Fast R-CNN) model. After pruning and lightweight, the size of training model is greatly reduced without a significant reduction in accuracy, and the final precision reaches 87%, while the model size is reduced to 7,723 KB.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.12
• /
• pp.561-568
• /
• 2021

In recent years, autonomous driving technologies have become a high-value-added technology that attracts attention in the fields of science and industry. For smooth Self-driving, it is necessary to accurately detect an object and estimate its movement speed in real time. CNN-based deep learning algorithms and conventional dense optical flows have a large consumption time, making it difficult to detect objects and estimate its movement speed in real time. In this paper, using a single camera image, fast object detection was performed using the YOLOv5 algorithm, a deep learning algorithm, and fast estimation of the speed of the object was performed by using a local dense optical flow modified from the existing dense optical flow based on the detected object. Based on this algorithm, we present a system that can predict the collision time and probability, and through this system, we intend to contribute to prevent tram accidents.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4420-4438
• /
• 2021

Image dehazing is an ill-posed problem which is far from being solved. Traditional image dehazing methods often yield mediocre effects and possess substandard processing speed, while modern deep learning methods perform best only in certain datasets. The haze removal effect when processed by said methods is unsatisfactory, meaning the generalization performance fails to meet the requirements. Concurrently, due to the limited processing speed, most dehazing algorithms cannot be employed in the industry. To alleviate said problems, a lightweight fast dehazing network based on a multiple scale-patch framework (MSP) is proposed in the present paper. Firstly, the multi-scale structure is employed as the backbone network and the multi-patch structure as the supplementary network. Dehazing through a single network causes problems, such as loss of object details and color in some image areas, the multi-patch structure was employed for MSP as an information supplement. In the algorithm image processing module, the image is segmented up and down for processed separately. Secondly, MSP generates a clear dehazing effect and significant robustness when targeting real-world homogeneous and nonhomogeneous hazy maps and different datasets. Compared with existing dehazing methods, MSP demonstrated a fast inference speed and the feasibility of real-time processing. The overall size and model parameters of the entire dehazing model are 20.75M and 6.8M, and the processing time for the single image is 0.026s. Experiments on NTIRE 2018 and NTIRE 2020 demonstrate that MSP can achieve superior performance among the state-of-the-art methods, such as PSNR, SSIM, LPIPS, and individual subjective evaluation.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.5
• /
• pp.817-826
• /
• 2022

AI technology is being successfully introduced in many fields, and models deployed as a service are deployed with black box environment that does not expose the model's information to protect intellectual property rights and data. In a black box environment, attackers try to steal data or parameters used during training by using model output. This paper proposes a method of inferring the type of model to directly find out the composition of layer of the target model, based on the fact that there is no attack to infer the information about the type of model from the deep learning model. With ResNet, VGGNet, AlexNet, and simple convolutional neural network models trained with MNIST datasets, we show that the types of models can be inferred using the output values in the gray box and black box environments of the each model. In addition, we inferred the type of model with approximately 83% accuracy in the black box environment if we train the big and small relationship feature that proposed in this paper together, the results show that the model type can be infrerred even in situations where only partial information is given to attackers, not raw probability vectors.