• Computers and Concrete
• /
• v.21 no.1
• /
• pp.47-54
• /
• 2018

Artificial neural network models can be successfully used to simulate the complex behavior of many problems in civil engineering. As compared to conventional computational methods, this popular modeling technique is powerful when the relationship between system parameters is intrinsically nonlinear, or cannot be explicitly identified, as in the case of concrete behavior. In this investigation, an artificial neural network model was developed to assess the residual compressive strength of self-compacted concrete at elevated temperatures ($20-900^{\circ}C$) and various relative humidity conditions (28-99%). A total of 332 experimental datasets, collected from available literature, were used for model calibration and verification. Data used in model development incorporated concrete ingredients, filler and fiber types, and environmental conditions. Based on the feed-forward back propagation algorithm, systematic analyses were performed to improve the accuracy of prediction and determine the most appropriate network topology. Training, testing, and validation results indicated that residual compressive strength of self-compacted concrete, exposed to high temperatures and relative humidity levels, could be estimated precisely with the suggested model. As illustrated by statistical indices, the reliability between experimental and predicted results was excellent. With new ingredients and different environmental conditions, the proposed model is an efficient approach to estimate the residual compressive strength of self-compacted concrete as a substitute for sophisticated laboratory procedures.

• Advances in concrete construction
• /
• v.10 no.3
• /
• pp.247-256
• /
• 2020

In this paper the possibility of using different regression models to predict the mechanical properties of limestone concrete after exposure to high temperatures, based on the results of non-destructive techniques, that could be easily used in-situ, is discussed. Extensive experimental work was carried out on limestone concrete mixtures, that differed in the water to cement (w/c) ratio, the type of cement and the quantity of superplasticizer added. After standard curing, the specimens were exposed to various high temperature levels, i.e., 200℃, 400℃, 600℃ or 800℃. Before heating, the reference mechanical properties of the concrete were determined at ambient temperature. After the heating process, the specimens were cooled naturally to ambient temperature and tested using non-destructive techniques. Among the mechanical properties of the specimens after heating, known also as the residual mechanical properties, the residual modulus of elasticity, compressive and flexural strengths were determined. The results show that residual modulus of elasticity, compressive and flexural strengths can be reliably predicted using an artificial neural network approach based on ultrasonic pulse velocity, residual surface strength, some mixture parameters and maximal temperature reached in concrete during heating.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.12
• /
• pp.1184-1191
• /
• 2009

Energy harvesting from environment can make the energy constrained systems such as sensor networks to sustain their lifetimes. However, environmental energy is highly variable with time, location, and other factors. Unlike the existing solutions, we solved this problem by allowing the sensor nodes with mobilizer to move in search of energy and recharge from remote energy station. In this paper we present and analyze a new harvesting aware framework for mobile sensor networks with remote energy station. The framework consists of energy model, motion control system and data transfer protocol. Among them, the objective of our data transfer protocol is to route a data packet geographically towards the target region and at the same time balance the residual energy and the link connectivity on nodes with energy harvesting. Our results along with simulation can be used for further studies and provide certain guideline for realistic development of such systems.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.4
• /
• pp.1237-1255
• /
• 2014

In wireless sensor networks (WSNs), hierarchical clustering is an efficient approach for lower energy consumption and extended network lifetime. In cluster-based multi-hop communications, a cluster head (CH) closer to the sink is loaded heavier than those CHs farther away from the sink. In order to balance the energy consumption among CHs, we development a novel cluster-based routing protocol for corona-structured wireless sensor networks. Based on the relaying traffic of each CH conveys, adequate radius for each corona can be determined through nearly balanced energy depletion analysis, which leads to balanced energy consumption among CHs. Simulation results demonstrate that our clustering approach effectively improves the network lifetime, residual energy and reduces the number of CH rotations in comparison with the MLCRA protocols.

• Archives of Craniofacial Surgery
• /
• v.22 no.5
• /
• pp.223-231
• /
• 2021

The field of artificial intelligence (AI) is rapidly advancing, and AI models are increasingly applied in the medical field, especially in medical imaging, pathology, natural language processing, and biosignal analysis. On the basis of these advances, telemedicine, which allows people to receive medical services outside of hospitals or clinics, is also developing in many countries. The mechanisms of deep learning used in medical AI include convolutional neural networks, residual neural networks, and generative adversarial networks. Herein, we investigate the possibility of using these AI methods in the field of craniofacial surgery, with potential applications including craniofacial trauma, congenital anomalies, and cosmetic surgery.

• Nuclear Engineering and Technology
• /
• v.55 no.6
• /
• pp.2276-2282
• /
• 2023

We deploy artificial neural networks to unfold neutron spectra from measured energy-integrated quantities. These neutron spectra represent an important parameter allowing to compute the absorbed dose and the kerma to serve radiation protection in addition to nuclear safety. The built architectures are inspired from convolutional neural networks. The first architecture is made up of residual transposed convolution's blocks while the second is a modified version of the U-net architecture. A large and balanced dataset is simulated following "realistic" physical constraints to train the architectures in an efficient way. Results show a high accuracy prediction of neutron spectra ranging from thermal up to fast spectrum. The dataset processing, the attention paid to performances' metrics and the hyper-optimization are behind the architectures' robustness.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.8
• /
• pp.2090-2098
• /
• 1996

This paper analyzes decorrelating detector for synchronous packet CDMA communications where a set of quasiorthogonal code waveforms are generated from a common code by assigning distinct initial code phases to all users. In this analysis, we characterize the residual multiple-access interference (MAI) caused by possibletiming offsets when synchronous and simultanceous packet transmissions are on the reverse link of centralize networks. Also, to show feasibility of decorrelating detector employing the common code, we further investigate its robustness against the multipath channel. It is demonstrated that the decorrelating detector greatly reduces the residual MAI to the order of N$^{-2}$ , N number of chips/bit, and yields significant performance gain compared to the single user detector.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.1-15
• /
• 2022

The MobileNetV3 is specially designed for mobile devices with limited memory and computing power. To reduce the network parameters and improve the network inference speed, a new lightweight network is proposed based on MobileNetV3. Firstly, to reduce the computation of residual blocks, a partial residual structure is designed by dividing the input feature maps into two parts. The designed partial residual structure is used to replace the residual block in MobileNetV3. Secondly, a dual-path feature extraction structure is designed to further reduce the computation of MobileNetV3. Different convolution kernel sizes are used in the two paths to extract feature maps with different sizes. Besides, a transition layer is also designed for fusing features to reduce the influence of the new structure on accuracy. The CIFAR-100 dataset and Image Net dataset are used to test the performance of the proposed partial residual structure. The ResNet based on the proposed partial residual structure has smaller parameters and FLOPs than the original ResNet. The performance of improved MobileNetV3 is tested on CIFAR-10, CIFAR-100 and ImageNet image classification task dataset. Comparing MobileNetV3, GhostNet and MobileNetV2, the improved MobileNetV3 has smaller parameters and FLOPs. Besides, the improved MobileNetV3 is also tested on CPU and Raspberry Pi. It is faster than other networks

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.3
• /
• pp.962-975
• /
• 2020

The accurate segmentation of infant brain MR image into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) is very important for early studying of brain growing patterns and morphological changes in neurodevelopmental disorders. Because of inherent myelination and maturation process, the WM and GM of babies (between 6 and 9 months of age) exhibit similar intensity levels in both T1-weighted (T1w) and T2-weighted (T2w) MR images in the isointense phase, which makes brain tissue segmentation very difficult. We propose a deep network architecture based on U-Net, called Triple Residual Multiscale Fully Convolutional Network (TRMFCN), whose structure exists three gates of input and inserts two blocks: residual multiscale block and concatenate block. We solved some difficulties and completed the segmentation task with the model. Our model outperforms the U-Net and some cutting-edge deep networks based on U-Net in evaluation of WM, GM and CSF. The data set we used for training and testing comes from iSeg-2017 challenge (http://iseg2017.web.unc.edu).

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.6
• /
• pp.35-47
• /
• 2020

Box-office prediction is important to movie stakeholders. It is necessary to accurately predict box-office and select important variables. In this paper, we propose a multivariate time series classification and important variable selection method to improve accuracy of predicting the box-office. As a research method, we collected daily data from KOBIS and NAVER for South Korean movies, selected important variables using Random Forest and predicted multivariate time series using Deep Learning. Based on the Korean screen quota system, Deep Learning was used to compare the accuracy of box-office predictions on the 73^rd day from movie release with the important variables and entire variables, and the results was tested whether they are statistically significant. As a Deep Learning model, Multi-Layer Perceptron, Fully Convolutional Neural Networks, and Residual Network were used. Among the Deep Learning models, the model using important variables and Residual Network had the highest prediction accuracy at 93%.