• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.163-177
• /
• 2019

As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.

• Journal of Internet Computing and Services
• /
• v.15 no.3
• /
• pp.101-107
• /
• 2014

With the development of online service, recent forms of databases have been changed from static database structures to dynamic stream database structures. Previous data mining techniques have been used as tools of decision making such as establishment of marketing strategies and DNA analyses. However, the capability to analyze real-time data more quickly is necessary in the recent interesting areas such as sensor network, robotics, and artificial intelligence. Landmark window-based frequent pattern mining, one of the stream mining approaches, performs mining operations with respect to parts of databases or each transaction of them, instead of all the data. In this paper, we analyze and evaluate the techniques of the well-known landmark window-based frequent pattern mining algorithms, called Lossy counting and hMiner. When Lossy counting mines frequent patterns from a set of new transactions, it performs union operations between the previous and current mining results. hMiner, which is a state-of-the-art algorithm based on the landmark window model, conducts mining operations whenever a new transaction occurs. Since hMiner extracts frequent patterns as soon as a new transaction is entered, we can obtain the latest mining results reflecting real-time information. For this reason, such algorithms are also called online mining approaches. We evaluate and compare the performance of the primitive algorithm, Lossy counting and the latest one, hMiner. As the criteria of our performance analysis, we first consider algorithms' total runtime and average processing time per transaction. In addition, to compare the efficiency of storage structures between them, their maximum memory usage is also evaluated. Lastly, we show how stably the two algorithms conduct their mining works with respect to the databases that feature gradually increasing items. With respect to the evaluation results of mining time and transaction processing, hMiner has higher speed than that of Lossy counting. Since hMiner stores candidate frequent patterns in a hash method, it can directly access candidate frequent patterns. Meanwhile, Lossy counting stores them in a lattice manner; thus, it has to search for multiple nodes in order to access the candidate frequent patterns. On the other hand, hMiner shows worse performance than that of Lossy counting in terms of maximum memory usage. hMiner should have all of the information for candidate frequent patterns to store them to hash's buckets, while Lossy counting stores them, reducing their information by using the lattice method. Since the storage of Lossy counting can share items concurrently included in multiple patterns, its memory usage is more efficient than that of hMiner. However, hMiner presents better efficiency than that of Lossy counting with respect to scalability evaluation due to the following reasons. If the number of items is increased, shared items are decreased in contrast; thereby, Lossy counting's memory efficiency is weakened. Furthermore, if the number of transactions becomes higher, its pruning effect becomes worse. From the experimental results, we can determine that the landmark window-based frequent pattern mining algorithms are suitable for real-time systems although they require a significant amount of memory. Hence, we need to improve their data structures more efficiently in order to utilize them additionally in resource-constrained environments such as WSN(Wireless sensor network).

• Journal of Internet Computing and Services
• /
• v.17 no.1
• /
• pp.23-33
• /
• 2016

The current smart lighting is shaped to offer the lighting environment suitable for current context, after identifying user's action and location through a sensor. The sensor-based context awareness technology just considers a single user, and the studies to interpret many users' various context occurrences and conflicts lack. In existing studies, a fuzzy theory and algorithm including ReBa have been used as the methodology to solve context conflict. The fuzzy theory and algorithm including ReBa just avoid an opportunity of context conflict that may occur by providing services by each area, after the spaces where users are located are classified into many areas. Therefore, they actually cannot be regarded as customized service type that can offer personal preference-based context conflict. This paper proposes a priority-based LED lighting control system interpreting multiple context conflicts, which decides services, based on the granted priority according to context type, when service conflict is faced with, due to simultaneous occurrence of various contexts to many users. This study classifies the residential environment into such five areas as living room, 'bed room, study room, kitchen and bath room, and the contexts that may occur within each area are defined as 20 contexts such as exercising, doing makeup, reading, dining and entering, targeting several users. The proposed system defines various contexts of users using an ontology-based model and gives service of user oriented lighting environment through rule based on standard and context reasoning engine. To solve the issue of various context conflicts among users in the same space and at the same time point, the context in which user concentration is required is set in the highest priority. Also, visual comfort is offered as the best alternative priority in the case of the same priority. In this manner, they are utilized as the criteria for service selection upon conflict occurrence.

• Journal of Intelligence and Information Systems
• /
• v.17 no.2
• /
• pp.109-117
• /
• 2011

The exhibition industry, as technology-intensive, eco-friendly industry, contributes to regional and national development and enhancement of its image as well, if it joins cultural and tourist industry. Therefore, We need to revitalize the exhibition industry, as actively holding an exhibition event. However, to attract a number of exhibition audience, the work of enhancing audience satisfaction and awareness of value for participation should be prioritized after improving quality of service within exhibition hall. As one way to enhance the quality of service, it is thought that the way providing personalized service geared toward each audience is needed. that is, if audience avoids the complexity in exhibition space and it affords them service to enable effective time and space management, it will improve the satisfaction. All such personalized service affordable lets the audience's preference on the basis of each audience profile registered in advance online grasp. and Based on this information, it is provided with exhibition-related information suited their purpose that is the booth for the interesting audience, the shortest path to go to the booth and event via audience's smart phone. and it collects audience's reaction information, such as visiting the booth, participating the event through offered the information in this way and location information for the flow of movement, the present position so that it makes revision of existing each audience profile. After correcting the information, it extracts the individual's preference. hereunder, it provides recommend booth and event information. in other words, it provides optimal information for individual by amendment based on reaction information about recommending information built on basic profile. It provides personalized service dynamic and interactive with audience. This paper will be able to provide the most suitable information for each audience through circular and interactive structure and designed smart-phone application supportable for updating dynamic and interactive personalized service that is able to afford surrounding information in real time, as locating movement position through sensing. The proposed application collects user‘s context information and carrys information gathering function collecting the reaction about searched or provided information via sensing. and it also carrys information gathering function providing needed data for user in exhibition hall. In other words, it offers information about recommend booth of position foundation for user, location-based services of recommend booth and involves service providing detailed information for inside exhibition by using service of augmented reality, the map of whole exhibition as well. and it is also provided with SNS service that is able to keep information exchange besides intimacy. To provide this service, application is consisted of several module. first of all, it includes UNS identity module for sensing, and contain sensor information gathering module handling and collecting the perceived information through this module. Sensor information gathered like this transmits the information gathering server. and there is exhibition information interfacing with user and this module transmits to interesting information collection module through user's reaction besides interface. Interesting information collection module transmits collected information and If valid information out of the information gathering server that brings together sensing information and interesting information is sent to recommend server, the recommend server makes recommend information through inference with gathered valid information. If this server transmit by exhibition information process, exhibition information process module is provided with user by interface. Through this system it raises the dynamic, intelligent personalized service for user.

• Journal of Internet Computing and Services
• /
• v.16 no.2
• /
• pp.49-55
• /
• 2015

According to the statistics of traffic accidents over recent 5 years, traffic accidents during the night times happened more than the day times. There are various causes to occur traffic accidents and the one of the major causes is inappropriate or missing street lights that make driver's sight confused and causes the traffic accidents. In this paper, with smartphones, we designed and implemented a lane luminance measurement application which stores the information of driver's location, driving, and lane luminance into database in real time to figure out the inappropriate street light facilities and the area that does not have any street lights. This application is implemented under Native C/C++ environment using android NDK and it improves the operation speed than code written in Java or other languages. To measure the luminance of road, the input image with RGB color space is converted to image with YCbCr color space and Y value returns the luminance of road. The application detects the road lane and calculates the road lane luminance into the database sever. Also this application receives the road video image using smart phone's camera and improves the computational cost by allocating the ROI(Region of interest) of input images. The ROI of image is converted to Grayscale image and then applied the canny edge detector to extract the outline of lanes. After that, we applied hough line transform method to achieve the candidated lane group. The both sides of lane is selected by lane detection algorithm that utilizes the gradient of candidated lanes. When the both lanes of road are detected, we set up a triangle area with a height 20 pixels down from intersection of lanes and the luminance of road is estimated from this triangle area. Y value is calculated from the extracted each R, G, B value of pixels in the triangle. The average Y value of pixels is ranged between from 0 to 100 value to inform a luminance of road and each pixel values are represented with color between black and green. We store car location using smartphone's GPS sensor into the database server after analyzing the road lane video image with luminance of road about 60 meters ahead by wireless communication every 10 minutes. We expect that those collected road luminance information can warn drivers about safe driving or effectively improve the renovation plans of road luminance management.

• Korean Journal of Remote Sensing
• /
• v.21 no.6
• /
• pp.445-456
• /
• 2005

The land surface parameters should be determined with sufficient accuracy, because these play an important role in climate change near the ground. As the surface reflectance presents strong anisotropy, off-nadir viewing results a strong dependency of observations on the Sun - target - sensor geometry. They contribute to the random noise which is produced by surface angular effects. The principal objective of the study is to provide a database of accurate surface reflectance eliminated the angular effects from MODIS 250m reflective channel data over Korea. The MODIS (Moderate Resolution Imaging Spectroradiometer) sensor has provided visible and near infrared channel reflectance at 250m resolution on a daily basis. The successive analytic processing steps were firstly performed on a per-pixel basis to remove cloudy pixels. And for the geometric distortion, the correction process were performed by the nearest neighbor resampling using 2nd-order polynomial obtained from the geolocation information of MODIS Data set. In order to correct the surface anisotropy effects, this paper attempted the semiempirical kernel-driven Bi- directional Reflectance Distribution Function(BRDF) model. The algorithm yields an inversion of the kernel-driven model to the angular components, such as viewing zenith angle, solar zenith angle, viewing azimuth angle, solar azimuth angle from reflectance observed by satellite. First we consider sets of the model observations comprised with a 31-day period to perform the BRDF model. In the next step, Nadir view reflectance normalization is carried out through the modification of the angular components, separated by BRDF model for each spectral band and each pixel. Modeled reflectance values show a good agreement with measured reflectance values and their RMSE(Root Mean Square Error) was totally about 0.01(maximum=0.03). Finally, we provide a normalized surface reflectance database consisted of 36 images for 2001 over Korea.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1341-1352
• /
• 2023

The normalized difference vegetation index (NDVI) derived from satellite images is a crucial tool to monitor forests and agriculture for broad areas because the periodic acquisition of the data is ensured. However, optical sensor-based vegetation indices(VI) are not accessible in some areas covered by clouds. This paper presented a synthetic aperture radar (SAR) based approach to retrieval of the optical sensor-based NDVI using machine learning. SAR system can observe the land surface day and night in all weather conditions. Radar vegetation indices (RVI) from the Sentinel-1 vertical-vertical (VV) and vertical-horizontal (VH) polarizations, surface elevation, and air temperature are used as the input features for an automated machine learning (AutoML) model to conduct the gap-filling of the Sentinel-2 NDVI. The mean bias error (MAE) was 7.214E-05, and the correlation coefficient (CC) was 0.878, demonstrating the feasibility of the proposed method. This approach can be applied to gap-free nationwide NDVI construction using Sentinel-1 and Sentinel-2 images for environmental monitoring and resource management.

• Journal of KIISE:Information Networking
• /
• v.35 no.5
• /
• pp.453-463
• /
• 2008

The missing child problem is no more a personal problem. It became a social problem that all parents must consider. To this, this study applies USN/RFID technology integrated with GIS for the prevention of missing child. Although RFID is not designed for location sensing, but now it is regarded as a device to facilitate real time location awareness. Such advantages of RFID can be integrated with 4S(GIS/GPS/LBS/GNSS) achieving much synergy effects. In order to prevent kidnapping and missing child, it is necessary to provide a missing child preventing system using a ubiquitous computing system. Therefore, the missing child preventing system has been developed using high-tech such as RFID, GPS network, CCTV, and mobile communication. The effectiveness of the missing child prevention system can be improved through an accurate location tracking technology. This study propose and test a location sensing system using the active RFID tags. This study verifies technical applied service, and presents a system configuration model. Finally, this paper confirms missing child prevention system utilization possibility.

• Journal of Advanced Navigation Technology
• /
• v.16 no.6
• /
• pp.927-934
• /
• 2012

In this paper, we present relative positioning algorithm for moving land vehicle using GPS, MEMS IMU and B-CDMA module. This algorithm does not calculate precise absolute position but calculates relative position directly, so additional infrastructure and I2V communication device are not required. Proposed algorithm has several steps. Firstly, unbiased relative position is calculated using pseudorange difference between two vehicles. Simultaneously, the algorithm estimates position of each vehicle using GPS/INS integration. Secondly, proposed algorithm performs filtering and finally estimates relative position and relative velocity. Using proposed algorithm, we can obtain more precise relative position for moving land vehicles with short time interval as IMU sensor has. The simulation is performed to evaluate this algorithm and the several field tests are performed with real time program and miniature vehicles for verifying performance of proposed algorithm.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.24 no.3
• /
• pp.219-232
• /
• 2013

This paper presents a microstrip antenna which recovers its resonant frequency and impedance shifted automatically by the approach of other objects such as hands. This can be used for telemetry sensor applications in the ultrahigh frequency(UHF) industrial, scientific, and medical(ISM) band. It is the key element that an frequency-reconfigurable antenna could be electrically controlled. This antenna is miniaturized by loading the folded plates at both radiating edges, and varactor diodes are installed between the radiating edges and the ground plane to control the resonant frequency by adjusting the DC bias asymmetrically. Using this voltage-controlled antenna and the micro controller peripheral circuits of reading the returned level, the antenna is designed and fabricated which recovers its resonant frequency and impedance automatically. Designed frequency auto recovering antenna is conformed to be recovered within a few seconds when the resonant frequency and impedance are shifted by the approach of other objects such as hand, metal plate, dielectric and so on.