• Smart Structures and Systems
• /
• 제28권6호
• /
• pp.811-825
• /
• 2021

High-voltage isolating switches play a paramount role in ensuring the safety of power supply systems. However, their exposure to outdoor environmental conditions may cause serious physical defects, which may result in great risk to power supply systems and society. Image processing-based methods have been used for anomaly detection. However, their accuracy is affected by numerous uncertainties due to manually extracted features, which makes the anomaly detection of isolating switches still challenging. In this paper, a vision-based anomaly detection method for isolating switches, which uses the rotational angle of the switch system for more accurate and direct anomaly detection with the help of deep learning (DL) and image processing methods (Single Shot Multibox Detector (SSD), improved frame differencing method, and Hough transform), is proposed. The SSD is a deep learning method for object classification and localization. In addition, an improved frame differencing method is introduced for better feature extraction and a hough transform method is adopted for rotational angle calculation. A number of experiments are conducted for anomaly detection of single and multiple switches using video frames. The results of the experiments demonstrate that the SSD outperforms the You-Only-Look-Once network. The effectiveness and robustness of the proposed method have been proven under various conditions, such as different illumination and camera locations using 96 videos from the experiments.

• 방송공학회논문지
• /
• 제26권7호
• /
• pp.844-854
• /
• 2021

Semi-supervised learning (SSL) and few-shot learning (FSL) have shown impressive performance even then the volume of labeled data is very limited. However, SSL and FSL can encounter a significant performance degradation if the diversity gap between the labeled and unlabeled data is high. To reduce this diversity gap, we propose a novel scheme that relies on an autoencoder for generating pseudo examples. Specifically, the autoencoder is trained on a specific class using the available labeled data and the decoder of the trained autoencoder is then used to generate N samples of that specific class based on N random noise, sampled from a standard normal distribution. The above process is repeated for all the classes. Consequently, the generated data reduces the diversity gap and enhances the model performance. Extensive experiments on MNIST and FashionMNIST datasets for SSL and FSL verify the effectiveness of the proposed approach in terms of classification accuracy and robustness against adversarial attacks.

• 대한조선학회논문집
• /
• 제59권6호
• /
• pp.362-371
• /
• 2022

As considerable interests in noise emission from the ships have been increased, International Maritime Organization (IMO) standardized the Underwater Radiated Noise (URN) measurement process of commercial ships in deep seas by enacting the related ISO standard ISO 17208-1 and classification societies responded with the enactment or revision of corresponding notations. According to this trend, a new hybrid underwater sound propagation model based on underwater sound propagation theories was developed and its accuracy on analysis was verified through the result comparison with the results of other generally used models. Using the verified model, each URN propagation characteristics adjusted by the correction methods proposed in the ISO standard and class notations were analyzed and compared in two assumed URN measurement cases. The results showed that the effects of transmission loss corrections in the circumstances with less bottom reflections generally similar but they had rather large differences in the model analysis results with bottom-reflection-dominant conditions. It was concluded that the deep consideration of effective bottom-reflection-correction method should be made in future revisions of ISO standard and class notations.

• International Journal of Computer Science & Network Security
• /
• 제22권5호
• /
• pp.127-134
• /
• 2022

Generally developed for medical testing, electrocardiogram (ECG) recordings seizure the cardiac electrical signals from the surface of the body. ECG study can consequently be a vital first step to support analyze, comprehend, and expect cardiac ailments accountable for 31% of deaths globally. Different tools are used to analyze ECG signals based on computational methods, and explicitly machine learning method. In all abovementioned computational simulations are prevailing tools for cataloging and clustering. This review demonstrates the different effective methods for heart disease based on computational methods for ECG analysis. The accuracy in machine learning and three-dimensional computer simulations, among medical inferences and contributions to medical developments. In the first part the classification and the methods developed to get data and cataloging between standard and abnormal cardiac activity. The second part emphases on patient analysis from entire ECG recordings due to different kind of diseases present. The last part represents the application of wearable devices and interpretation of computer simulated results. Conclusively, the discussion part plans the challenges of ECG investigation and offers a serious valuation of the approaches offered. Different approaches described in this review are a sturdy asset for medicinal encounters and their transformation to the medical world can lead to auspicious developments.

• Steel and Composite Structures
• /
• 제42권6호
• /
• pp.733-745
• /
• 2022

This study proposed a robust artificial intelligence (AI) model based on the social behaviour of the imperialist competitive algorithm (ICA) and artificial neural network (ANN) for modelling the deflection of reinforced concrete beams, abbreviated as ICA-ANN model. Accordingly, the ICA was used to adjust and optimize the parameters of an ANN model (i.e., weights and biases) aiming to improve the accuracy of the ANN model in modelling the deflection reinforced concrete beams. A total of 120 experimental datasets of reinforced concrete beams were employed for this aim. Therein, applied load, tensile reinforcement strength and the reinforcement percentage were used to simulate the deflection of reinforced concrete beams. Besides, five other AI models, such as ANN, SVM (support vector machine), GLMNET (lasso and elastic-net regularized generalized linear models), CART (classification and regression tree) and KNN (k-nearest neighbours), were also used for the comprehensive assessment of the proposed model (i.e., ICA-ANN). The comparison of the derived results with the experimental findings demonstrates that among the developed models the ICA-ANN model is that can approximate the reinforced concrete beams deflection in a more reliable and robust manner.

• International Journal of Computer Science & Network Security
• /
• 제22권9호
• /
• pp.23-30
• /
• 2022

Glaucoma is a chronic neuropathy that affects the optic nerve which can lead to blindness. The detection and prediction of glaucoma become possible using deep neural networks. However, the detection performance relies on the availability of a large number of data. Therefore, we propose different frameworks, including a hybrid of a generative adversarial network and a convolutional neural network to automate and increase the performance of glaucoma detection. The proposed frameworks are evaluated using five public glaucoma datasets. The framework which uses a Deconvolutional Generative Adversarial Network (DCGAN) and a DenseNet pre-trained model achieves 99.6%, 99.08%, 99.4%, 98.69%, and 92.95% of classification accuracy on RIMONE, Drishti-GS, ACRIMA, ORIGA-light, and HRF datasets respectively. Based on the experimental results and evaluation, the proposed framework closely competes with the state-of-the-art methods using the five public glaucoma datasets without requiring any manually preprocessing step.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권12호
• /
• pp.3943-3959
• /
• 2022

People are constantly exposed to stress and anxiety environment, which could contribute to a variety of psychological and physical health problems. Therefore, it is particularly important to identify psychological stress in time and to find a feasible and universal method of stress reduction. This research investigated the influence of different music, such as relaxation music and natural rhythm music, on stress relief based on Electroencephalogram signals. Mental arithmetic test was implemented to create a stressful environment. 23 participants performed the mental arithmetic test with and without music respectively, while their Electroencephalogram signal was recorded. The effect of music on stress relief was verified through stress test questionnaires, including Trait Anxiety Inventory (STAI-6) and Self-Stress Assessment. There was a significant change in the stress test questionnaire values with and without music according to paired t-test (p<0.01). Furthermore, a model based on Transformer for stress level classification from Electroencephalogram signal was proposed. Experimental results showed that the method of listening to relaxation music and natural rhythm music achieved the effect of reducing psychological stress and the proposed model yielded a promising accuracy in classifying the Electroencephalogram signal of mental stress.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권1호
• /
• pp.136-141
• /
• 2022

A very complex task in deep learning such as image classification must be solved with the help of neural networks and activation functions. The backpropagation algorithm advances backward from the output layer towards the input layer, the gradients often get smaller and smaller and approach zero which eventually leaves the weights of the initial or lower layers nearly unchanged, as a result, the gradient descent never converges to the optimum. We propose a two-factor non-saturating activation functions known as Bea-Mish for machine learning applications in deep neural networks. Our method uses two factors, beta (𝛽) and alpha (𝛼), to normalize the area below the boundary in the Mish activation function and we regard these elements as Bea. Bea-Mish provide a clear understanding of the behaviors and conditions governing this regularization term can lead to a more principled approach for constructing better performing activation functions. We evaluate Bea-Mish results against Mish and Swish activation functions in various models and data sets. Empirical results show that our approach (Bea-Mish) outperforms native Mish using SqueezeNet backbone with an average precision (AP50val) of 2.51% in CIFAR-10 and top-1accuracy in ResNet-50 on ImageNet-1k. shows an improvement of 1.20%.

• 한국기계가공학회지
• /
• 제21권3호
• /
• pp.77-85
• /
• 2022

In this study, to diagnose the grinding state of a micro drill bit, a sensor attachment location was selected through random vibration analysis of the grinding unit of the micro drill-bit grinding system. In addition, the vibration data generated during the drill bit grinding were collected from the grinding unit for the grinding wheels under the steady and worn conditions, and data feature extraction and dimension reduction were performed. The wear of the micro-drill-bit grinding wheel was diagnosed by applying KNN, a machine-learning algorithm. The classification model showed excellent performance, with an accuracy of 99.2%. The precision, recall and f1-score were higher than 99% in both the steady and wear conditions.

• ETRI Journal
• /
• 제44권4호
• /
• pp.613-623
• /
• 2022

Autism spectrum disorder (ASD) is a developmental disorder associated with cognitive and neurobehavioral disorders. It affects the person's behavior and performance. Autism affects verbal and non-verbal communication in social interactions. Early screening and diagnosis of ASD are essential and helpful for early educational planning and treatment, the provision of family support, and for providing appropriate medical support for the child on time. Thus, developing automated methods for diagnosing ASD is becoming an essential need. Herein, we investigate using various machine learning methods to build predictive models for diagnosing ASD in children using facial images. To achieve this, we used an autistic children dataset containing 2936 facial images of children with autism and typical children. In application, we used classical machine learning methods, such as support vector machine and random forest. In addition to using deep-learning methods, we used a state-of-the-art method, that is, automated machine learning (AutoML). We compared the results obtained from the existing techniques. Consequently, we obtained that AutoML achieved the highest performance of approximately 96% accuracy via the Hyperpot and tree-based pipeline optimization tool optimization. Furthermore, AutoML methods enabled us to easily find the best parameter settings without any human efforts for feature engineering.