• Journal of Internet Computing and Services
• /
• v.21 no.6
• /
• pp.95-104
• /
• 2020

In this paper, we propose the real time indoor air quality monitoring and controlling platform on cloud using IoT sensor data such as PM10, PM2.5, CO2, VOCs, temperature, and humidity which has direct or indirect impact to indoor air quality. The system is connected to air ventilator to manage and optimize the indoor air quality. The proposed system has three main parts; First, IoT data collection service to measure, and collect indoor air quality in real time from IoT sensor network, Second, Big data processing pipeline to process and store the collected data on cloud platform and Finally, Big data analysis and visualization service to give real time insight of indoor air quality on mobile and web application. For the implication of the proposed system, IoT sensor kits are installed on three different public day care center where the indoor pollution can cause serious impact to the health and education of growing kids. Analyzed results are visualized on mobile and web application. The impact of ventilation system to indoor air quality is tested statistically and the result shows the proper optimization of indoor air quality.

• Journal of Korea Water Resources Association
• /
• v.56 no.9
• /
• pp.587-602
• /
• 2023

Due to climate change, population growth, and economic development, the demand for water in the urban water system (UWS) and the energy required for water use constantly increase. Therefore, beyond the traditional method of considering only the water sector, the Nexus approach, which considers synergies and trade-offs between the water and energy sectors, has begun to draw attention. In previous researches, the Nexus methodology was used to demonstrate that the UWS is an energy-intensive system, analyze the water-energy efficiency relationship surrogated by energy intensity, and identify climate (long-term climate change, drought, type), geographic characteristics (topography, flat ratio, location), system characteristics (total supply water amount, population density, pipeline length), and operational management level (water network pressure, leakage rate, water saving) effects on the UWS. Through this, it was possible to suggest the direction of policies and institutions to UWS managers. However, there was a limit to establishing and implementing specific action plans. This study built the energy intensity matrix of the UWS, quantified the impact of city conditions, external influences, and operational management levels on the UWS using the water-energy Nexus model, and introduced water-energy efficiency criteria. With this, UWS managers will be able to derive strategies and action plans for efficient operation management of the UWS and evaluate suitability and validity after implementation.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.205-225
• /
• 2018

Convolutional Neural Network (ConvNet) is one class of the powerful Deep Neural Network that can analyze and learn hierarchies of visual features. Originally, first neural network (Neocognitron) was introduced in the 80s. At that time, the neural network was not broadly used in both industry and academic field by cause of large-scale dataset shortage and low computational power. However, after a few decades later in 2012, Krizhevsky made a breakthrough on ILSVRC-12 visual recognition competition using Convolutional Neural Network. That breakthrough revived people interest in the neural network. The success of Convolutional Neural Network is achieved with two main factors. First of them is the emergence of advanced hardware (GPUs) for sufficient parallel computation. Second is the availability of large-scale datasets such as ImageNet (ILSVRC) dataset for training. Unfortunately, many new domains are bottlenecked by these factors. For most domains, it is difficult and requires lots of effort to gather large-scale dataset to train a ConvNet. Moreover, even if we have a large-scale dataset, training ConvNet from scratch is required expensive resource and time-consuming. These two obstacles can be solved by using transfer learning. Transfer learning is a method for transferring the knowledge from a source domain to new domain. There are two major Transfer learning cases. First one is ConvNet as fixed feature extractor, and the second one is Fine-tune the ConvNet on a new dataset. In the first case, using pre-trained ConvNet (such as on ImageNet) to compute feed-forward activations of the image into the ConvNet and extract activation features from specific layers. In the second case, replacing and retraining the ConvNet classifier on the new dataset, then fine-tune the weights of the pre-trained network with the backpropagation. In this paper, we focus on using multiple ConvNet layers as a fixed feature extractor only. However, applying features with high dimensional complexity that is directly extracted from multiple ConvNet layers is still a challenging problem. We observe that features extracted from multiple ConvNet layers address the different characteristics of the image which means better representation could be obtained by finding the optimal combination of multiple ConvNet layers. Based on that observation, we propose to employ multiple ConvNet layer representations for transfer learning instead of a single ConvNet layer representation. Overall, our primary pipeline has three steps. Firstly, images from target task are given as input to ConvNet, then that image will be feed-forwarded into pre-trained AlexNet, and the activation features from three fully connected convolutional layers are extracted. Secondly, activation features of three ConvNet layers are concatenated to obtain multiple ConvNet layers representation because it will gain more information about an image. When three fully connected layer features concatenated, the occurring image representation would have 9192 (4096+4096+1000) dimension features. However, features extracted from multiple ConvNet layers are redundant and noisy since they are extracted from the same ConvNet. Thus, a third step, we will use Principal Component Analysis (PCA) to select salient features before the training phase. When salient features are obtained, the classifier can classify image more accurately, and the performance of transfer learning can be improved. To evaluate proposed method, experiments are conducted in three standard datasets (Caltech-256, VOC07, and SUN397) to compare multiple ConvNet layer representations against single ConvNet layer representation by using PCA for feature selection and dimension reduction. Our experiments demonstrated the importance of feature selection for multiple ConvNet layer representation. Moreover, our proposed approach achieved 75.6% accuracy compared to 73.9% accuracy achieved by FC7 layer on the Caltech-256 dataset, 73.1% accuracy compared to 69.2% accuracy achieved by FC8 layer on the VOC07 dataset, 52.2% accuracy compared to 48.7% accuracy achieved by FC7 layer on the SUN397 dataset. We also showed that our proposed approach achieved superior performance, 2.8%, 2.1% and 3.1% accuracy improvement on Caltech-256, VOC07, and SUN397 dataset respectively compare to existing work.

• Journal of the Korean Society of Radiology
• /
• v.14 no.2
• /
• pp.157-168
• /
• 2020

Advancements in segmentation methodology has made automatic segmentation of brain structures using structural images accurate and consistent. One method of automatic segmentation, which involves registering atlas information from template space to subject space, requires a high quality atlas with accurate boundaries for consistent segmentation. The Allen Mouse Brain Atlas, which has been widely accepted as a high quality reference of the mouse brain, has been used in various segmentations and can provide accurate coordinates and boundaries of mouse brain structures for tractography. Through probabilistic tractography, diffusion tensor images can be used to map comprehensive neuronal network of white matter pathways of the brain. Comparisons between neural networks of mouse and human brains showed that various clinical tests on mouse models were able to simulate disease pathology of human brains, increasing the importance of clinical mouse brain studies. However, differences between brain size of human and mouse brain has made it difficult to achieve the necessary image quality for analysis and the conditions for sufficient image quality such as a long scan time makes using live samples unrealistic. In order to secure a mouse brain image with a sufficient scan time, an Ex-vivo experiment of a mouse brain was conducted for this study. Using FSL, a tool for analyzing tensor images, we proposed a semi-automated segmentation and tractography analysis pipeline of the mouse brain and applied it to various mouse models. Also, in order to determine the useful signal-to-noise ratio of the diffusion tensor image acquired for the tractography analysis, images with various excitation numbers were compared.

• Journal of the Korean Applied Science and Technology
• /
• v.37 no.3
• /
• pp.473-483
• /
• 2020

This paper proposes a tourism recommendation system in intelligent cloud environment using information of tourist behavior applied with perceived value. This proposed system applied tourist information and empirical analysis information that reflected the perceptual value of tourists in their behavior to the tourism recommendation system using wide and deep learning technology. This proposal system was applied to the tourism recommendation system by collecting and analyzing various tourist information that can be collected and analyzing the values that tourists were usually aware of and the intentions of people's behavior. It provides empirical information by analyzing and mapping the association of tourism information, perceived value and behavior to tourism platforms in various fields that have been used. In addition, the tourism recommendation system using wide and deep learning technology, which can achieve both memorization and generalization in one model by learning linear model components and neural only components together, and the method of pipeline operation was presented. As a result of applying wide and deep learning model, the recommendation system presented in this paper showed that the app subscription rate on the visiting page of the tourism-related app store increased by 3.9% compared to the control group, and the other 1% group applied a model using only the same variables and only the deep side of the neural network structure, resulting in a 1% increase in subscription rate compared to the model using only the deep side. In addition, by measuring the area (AUC) below the receiver operating characteristic curve for the dataset, offline AUC was also derived that the wide-and-deep learning model was somewhat higher, but more influential in online traffic.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.3
• /
• pp.46-55
• /
• 2016

This work proposes a 13b 100MS/s 45nm CMOS ADC with a high dynamic performance for IF-domain high-speed signal processing systems based on a four-step pipeline architecture to optimize operating specifications. The SHA employs a wideband high-speed sampling network properly to process high-frequency input signals exceeding a sampling frequency. The SHA and MDACs adopt a two-stage amplifier with a gain-boosting technique to obtain the required high DC gain and the wide signal-swing range, while the amplifier and bias circuits use the same unit-size devices repeatedly to minimize device mismatch. Furthermore, a separate analog power supply voltage for on-chip current and voltage references minimizes performance degradation caused by the undesired noise and interference from adjacent functional blocks during high-speed operation. The proposed ADC occupies an active die area of $0.70mm^2$, based on various process-insensitive layout techniques to minimize the physical process imperfection effects. The prototype ADC in a 45nm CMOS demonstrates a measured DNL and INL within 0.77LSB and 1.57LSB, with a maximum SNDR and SFDR of 64.2dB and 78.4dB at 100MS/s, respectively. The ADC is implemented with long-channel devices rather than minimum channel-length devices available in this CMOS technology to process a wide input range of $2.0V_{PP}$ for the required system and to obtain a high dynamic performance at IF-domain input signal bands. The ADC consumes 425.0mW with a single analog voltage of 2.5V and two digital voltages of 2.5V and 1.1V.