• Journal of the Semiconductor & Display Technology
• /
• v.16 no.3
• /
• pp.65-70
• /
• 2017

This paper presents the implementation for the master changing algorithm between nodes in a general electric vehicle. The packet processing method based on the unique network method of an electric vehicle is that the method of processing a communication packet has the priority from the node of a vehicle installed at both ends. An important factor in deciding master or slave in a train is that the request data, the status data, and transmits or control codes of sub-devices are controlled from the node which master becomes. If the request data or the status data is transmitted from the non- master side, it is very important that only one of the devices of both stages be master since the data of the request data may collide with each other. This paper proposes an algorithm to select master or slave depending on which vehicle is started first, which node is master or slave, and whether the vehicle key is operation. Finally experimental results show the stable performance and effectiveness of the proposed algorithm.

• Journal of Korea Multimedia Society
• /
• v.21 no.12
• /
• pp.1407-1416
• /
• 2018

The purpose of this study was to train a model for the ulna and radius bone segmentation based on Convolutional Neural Networks and to verify the segmentation model. The data consisted of 840 training data, 210 tuning data, and 200 verification data. The learning model for the ulna and radius bone bwas based on U-Net (19 convolutional and 8 maximum pooling) and trained with 8 batch sizes, 0.0001 learning rate, and 200 epochs. As a result, the average sensitivity of the training data was 0.998, the specificity was 0.972, the accuracy was 0.979, and the Dice's similarity coefficient was 0.968. In the validation data, the average sensitivity was 0.961, specificity was 0.978, accuracy was 0.972, and Dice's similarity coefficient was 0.961. The performance of deep convolutional neural network based models for the segmentation was good for ulna and radius bone.

• Structural Engineering and Mechanics
• /
• v.70 no.4
• /
• pp.457-466
• /
• 2019

This study develops a damage detection method based on neural networks. The performance of the method is numerically and experimentally verified using a three-story shear building model. The framework is mainly composed of two hierarchical stages to identify damage location and extent using artificial neural network (ANN). The normalized damage signature index, that is a normalized ratio of the changes in the natural frequency and mode shape caused by the damage, is used to identify the damage location. The modal parameters extracted from the numerically developed structure for multiple damage scenarios are used to train the ANN. The positive alarm from the first stage of damage detection activates the second stage of ANN to assess the damage extent. The difference in mode shape vectors between the intact and damaged structures is used to determine the extent of the related damage. The entire procedure is verified using laboratory experiments. The damage is artificially modeled by replacing the column element with a narrow section, and a stochastic subspace identification method is used to identify the modal parameters. The results verify that the proposed method can accurately detect the damage location and extent.

• Smart Media Journal
• /
• v.8 no.2
• /
• pp.46-57
• /
• 2019

In recent research, deep learning-based methods have achieved state-of-the-art performance in various computer vision tasks. However, these methods are commonly supervised, and require huge amounts of annotated data to train. Acquisition of data demands an additional costly effort, particularly for the tasks where it becomes challenging to obtain large amounts of data considering the time constraints and the requirement of professional human diligence. In this paper, we present a data level synthetic sampling solution to learn from small and imbalanced data sets using Generative Adversarial Networks (GANs). The reason for using GANs are the challenges posed in various fields to manage with the small datasets and fluctuating amounts of samples per class. As a result, we present an approach that can improve learning with respect to data distributions, reducing the partiality introduced by class imbalance and hence shifting the classification decision boundary towards more accurate results. Our novel method is demonstrated on a small dataset of 2789 tomato plant disease images, highly corrupted with class imbalance in 9 disease categories. Moreover, we evaluate our results in terms of different metrics and compare the quality of these results for distinct classes.

• Journal of Broadcast Engineering
• /
• v.26 no.1
• /
• pp.79-87
• /
• 2021

In this paper, we analysis the semi-supervised learning (SSL), which is adopted in order to train a deep learning-based classification model using the small number of labeled data. The conventional SSL techniques can be categorized into consistency regularization, entropy-based, and pseudo labeling. First, we describe the algorithm of each SSL technique. In the experimental results, we evaluate the classification accuracy of each SSL technique varying the number of labeled data. Finally, based on the experimental results, we describe the limitations of SSL technique, and suggest the research direction to improve the classification performance of SSL.

• Computers and Concrete
• /
• v.27 no.5
• /
• pp.489-512
• /
• 2021

In this study, two powerful techniques, namely particle swarm optimization (PSO) and imperialist competitive algorithm (ICA) were selected and combined with a pre-developed ANN model aiming at improving its performance prediction of the compressive strength of concrete modified with fly ash. To achieve this study's aims, a comprehensive database with 379 data samples was collected from the available literature. The output of the database is the compressive strength (CS) of concrete samples, which are influenced by 9 parameters as model inputs, namely those related to mix composition. The modeling steps related to ICA-ANN (or neuro-imperialism) and PSO-ANN (or neuro-swarm) were conducted through the use of several parametric studies to design the most influential parameters on these hybrid models. A comparison of the CS values predicted by hybrid intelligence techniques with the experimental CS values confirmed that the neuro-swarm model could provide a higher degree of accuracy than another proposed hybrid model (i.e., neuro-imperialism). The train and test correlation coefficient values of (0.9042 and 0.9137) and (0.8383 and 0.8777) for neuro-swarm and neuro-imperialism models, respectively revealed that although both techniques are capable enough in prediction tasks, the developed neuro-swarm model can be considered as a better alternative technique in mapping the concrete strength behavior.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.12
• /
• pp.4816-4834
• /
• 2020

This paper proposes transfer learning and fine-tuning techniques for a deep learning model to detect three distinct brain tumors from Magnetic Resonance Imaging (MRI) scans. In this work, the recent YOLOv4 model trained using a collection of 3064 T1-weighted Contrast-Enhanced (CE)-MRI scans that were pre-processed and labeled for the task. This work trained with the partial 29-layer YOLOv4-Tiny and fine-tuned to work optimally and run efficiently in most platforms with reliable performance. With the help of transfer learning, the model had initial leverage to train faster with pre-trained weights from the COCO dataset, generating a robust set of features required for brain tumor detection. The results yielded the highest mean average precision of 93.14%, a 90.34% precision, 88.58% recall, and 89.45% F1-Score outperforming other previous versions of the YOLO detection models and other studies that used bounding box detections for the same task like Faster R-CNN. As concluded, the YOLOv4-Tiny can work efficiently to detect brain tumors automatically at a rapid phase with the help of proper fine-tuning and transfer learning. This work contributes mainly to assist medical experts in the diagnostic process of brain tumors.

• The Journal of Korea Robotics Society
• /
• v.16 no.1
• /
• pp.56-63
• /
• 2021

As the use of robots in service area increases, research has been conducted to replace human tasks in daily life with robots. Among them, this study focuses on the tidy-up task on a desk using a robot arm. The order in which tidy-up motions are carried out has a great impact on the success rate of the task. Therefore, in this study, a neural network-based method for determining the priority of the tidy-up motions from the input image is proposed. Reinforcement learning, which shows good performance in the sequential decision-making process, is used to train such a task planner. The training process is conducted in a virtual tidy-up environment that is configured the same as the actual tidy-up environment. To transfer the learning results in the virtual environment to the actual environment, the input image is preprocessed into a segmented image. In addition, the use of a neural network that excludes unnecessary tidy-up motions from the priority during the tidy-up operation increases the success rate of the task planner. Experiments were conducted in the real world to verify the proposed task planning method.

• International Journal of Computer Science & Network Security
• /
• v.21 no.2
• /
• pp.229-237
• /
• 2021

Our modern 'information-hungry' age demands delivery of information at unprecedented fast rates. Timely delivery of noteworthy information about recent events can help people from different segments of life in number of ways. As world has become global village, the flow of news in terms of volume and speed demands involvement of machines to help humans to handle the enormous data. News are presented to public in forms of video, audio, image and text. News text available on internet is a source of knowledge for billions of internet users. Urdu language is spoken and understood by millions of people from Indian subcontinent. Availability of online Urdu news enable this branch of humanity to improve their understandings of the world and make their decisions. This paper uses available online Urdu news data to train machines to automatically categorize provided news. Various machine learning algorithms were used on news headline for training purpose and the results demonstrate that Bernoulli Naïve Bayes (Bernoulli NB) and Multinomial Naïve Bayes (Multinomial NB) algorithm outperformed other algorithms in terms of all performance parameters. The maximum level of accuracy achieved for the dataset was 94.278% by multinomial NB classifier followed by Bernoulli NB classifier with accuracy of 94.274% when Urdu stop words were removed from dataset. The results suggest that short text of headlines of news can be used as an input for text categorization process.

• Journal of Distribution Science
• /
• v.19 no.9
• /
• pp.5-17
• /
• 2021

Purpose: As mobile devices are commonly used and contact-free services are widespread due to the COVID-19 pandemic in the recent distribution environment, this study suggests retail strategies for consumers using high-speed railways. To this end, we analyzed how consumer perception on technologies necessary for use of mobile apps is related to the attitude that drives consumers to continue using the app services. Research design, data and methodology: Based on the extended unified theory of technology acceptance and use of technology model by Venkatesh, Morris, Davis and Davis (2003), we added variables proposed by existing theories that studied the technology acceptance model from multiple perspectives and empirically analyzed the relationship between user satisfaction and use intention with structural equation modeling. Results: As expected, factors necessary for the use of app services such as performance expectancy, social influence, price value, facilitating conditions, security, and aesthetics had positive effects on user satisfaction, whereas the effect of effort expectancy on user satisfaction was rejected. And user satisfaction was found to have a significant effect on intention to use. Conclusions: The results provide implications that strategic retail management of the above factors can motivate passengers to continuously use high-speed railways.