• Journal of Information Processing Systems
• /
• v.14 no.6
• /
• pp.1464-1479
• /
• 2018

In face recognition, sometimes the number of available training samples for single category is insufficient. Therefore, the performances of models trained by convolutional neural network are not ideal. The small sample face recognition algorithm based on novel Siamese network is proposed in this paper, which doesn't need rich samples for training. The algorithm designs and realizes a new Siamese network model, SiameseFacel, which uses pairs of face images as inputs and maps them to target space so that the $L_2$ norm distance in target space can represent the semantic distance in input space. The mapping is represented by the neural network in supervised learning. Moreover, a more lightweight Siamese network model, SiameseFace2, is designed to reduce the network parameters without losing accuracy. We also present a new method to generate training data and expand the number of training samples for single category in AR and labeled faces in the wild (LFW) datasets, which improves the recognition accuracy of the models. Four loss functions are adopted to carry out experiments on AR and LFW datasets. The results show that the contrastive loss function combined with new Siamese network model in this paper can effectively improve the accuracy of face recognition.

• International Journal of Computer Science & Network Security
• /
• v.21 no.6
• /
• pp.137-142
• /
• 2021

Machine-learning systems have proven their worth in various industries, including healthcare and banking, by assisting in the extraction of valuable inferences. Information in these crucial sectors is traditionally stored in databases distributed across multiple environments, making accessing and extracting data from them a tough job. To this issue, we must add that these data sources contain sensitive information, implying that the data cannot be shared outside of the head. Using cryptographic techniques, Privacy-Preserving Machine Learning (PPML) helps solve this challenge, enabling information discovery while maintaining data privacy. In this paper, we talk about how to keep your data mining private. Because Data mining has a wide variety of uses, including business intelligence, medical diagnostic systems, image processing, web search, and scientific discoveries, and we discuss privacy-preserving in deep learning because deep learning (DL) exhibits exceptional exactitude in picture detection, Speech recognition, and natural language processing recognition as when compared to other fields of machine learning so that it detects the existence of any error that may occur to the data or access to systems and add data by unauthorized persons.

• Journal of Korea Multimedia Society
• /
• v.20 no.9
• /
• pp.1559-1566
• /
• 2017

Recently in the IoT(Internet of Things) environment, a data collection in real-time through device's sensor has increased with an emergence of various devices. Collected data from IoT environment shows a large scale, non-uniform generation cycle and atypical. For this reason, the distributed processing technique is required to analyze the IoT sensor data. However if you do not consider the optimal scheduling for data and the processor of IoT in a distributed processing environment complexity increase the amount in assigning a task, the user is difficult to guarantee the QoS(Quality of Service) for the sensor data. In this paper, we propose APQTA(Adaptive Priority Queue-driven Task Allocation method for sensor data processing) to efficiently process the sensor data generated by the IoT environment. APQTA is to separate the data into job and by applying the priority allocation scheduling based on the deadline to ensure that guarantee the QoS at the same time increasing the efficiency of the data processing.

• Journal of Information Processing Systems
• /
• v.6 no.1
• /
• pp.67-78
• /
• 2010

In this study, a clustering algorithm that uses DCT transformed data is presented. The algorithm is a grid density-based clustering algorithm that can identify clusters of arbitrary shape. Streaming data are transformed and reconstructed as needed for clustering. Experimental results show that DCT is able to approximate a data distribution efficiently using only a small number of coefficients and preserve the clusters well. The grid based clustering algorithm works well with DCT transformed data, demonstrating the viability of DCT for data stream clustering applications.

• Journal of Korea Multimedia Society
• /
• v.17 no.10
• /
• pp.1182-1188
• /
• 2014

Recently, the research on database outsourcing has been actively done with the popularity of cloud computing. However, because users' data may contain sensitive personal information, such as health, financial and location information, the data encryption methods have attracted much interest. Existing data encryption schemes process a query without decrypting the encrypted databases in order to support user privacy protection. On the other hand, to efficiently handle the large amount of data in cloud computing, it is necessary to study the distributed index structure. However, existing index structure and query processing algorithms have a limitation that they only consider single-column query processing. In this paper, we propose a grid-based multi column indexing scheme and an encrypted query processing algorithm. In order to support multi-column query processing, the multi-dimensional index keys are generated by using a space decomposition method, i.e. grid index. To support encrypted query processing over encrypted data, we adopt the Hilbert curve when generating a index key. Finally, we prove that the proposed scheme is more efficient than existing scheme for processing the exact and range query.

• Journal of Information Processing Systems
• /
• v.15 no.6
• /
• pp.1335-1349
• /
• 2019

Crowdsensing technologies can improve the efficiency of smart parking system in comparison with present sensor based smart parking system because of low install price and no restriction caused by sensor installation. A lot of sensing data is necessary to predict parking lot saturation in real-time. However in real world, it is hard to reach the required number of sensing data. In this paper, we model a saturation predication combining a time-based prediction model and a sensing data-based prediction model. The time-based model predicts saturation in aspects of parking lot location and time. The sensing data-based model predicts the degree of saturation of the parking lot with high accuracy based on the degree of saturation predicted from the first model, the saturation information in the sensing data, and the number of parking spaces in the sensing data. We perform prediction model learning with real sensing data gathered from a specific parking lot. We also evaluate the performance of the predictive model and show its efficiency and feasibility.

• Journal of the korean Society of Automotive Engineers
• /
• v.11 no.6
• /
• pp.89-96
• /
• 1989

Engine analyzer is developed with the aids of personal computer, A/D converter, interfacing signal transducer and data processing computer programs. The objective of this development are that it should firstly be produced at the resonable low price compared with imported one taking advantage of using existing personal computer and printer, and it should also give good quality of performance. For the attainment of this objective, A/D converter should have been developed to meet the price limit of the equipment. The experiment is performed in a 4 cycle 4 cylinder gasoline engine by this analyzer, and all the information which are necessary for the combustion analysis can be obtained through the processing of the pressure data that are stored in the computer. These are pressure-volume curve, pressure-crank angle curve, the rate of pressure rise and heat release versus crank angle curve etc. With this developed experimental system of resonable price, it will be considered that more easy way of engine data pick-up and processing is possible.

• International Journal of Computer Science & Network Security
• /
• v.22 no.10
• /
• pp.223-229
• /
• 2022

LinkedIn is one of the most job hunting and career-growing applications in the world. There are a lot of opportunities and jobs available on LinkedIn. According to statistics, LinkedIn has 738M+ members. 14M+ open jobs on LinkedIn and 55M+ Companies listed on this mega-connected application. A lot of vacancies are available daily. LinkedIn data has been used for the research work carried out in this paper. This in turn can significantly tackle the challenges faced by LinkedIn and other job posting applications to improve the levels of jobs available in the industry. This research introduces Text Processing in natural language processing on datasets of LinkedIn which aims to find out the jobs that appear most in a month or/and year. Therefore, the large data became renewed into the required or needful source. This study thus uses Multinomial Naïve Bayes and Linear Support Vector Machine learning algorithms for text classification and developed a trained multilingual dataset. The results indicate the most needed job vacancies in any field. This will help students, job seekers, and entrepreneurs with their career decisions

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.04a
• /
• pp.1218-1221
• /
• 2011

The development of the internet and information management has enabled new applications which include: Electronic medical record (EMR), intelligent transportation, environmental monitoring, etc. In this paper, we design and implement the Continuity Care Record(CCR) Data Stream management server that compiled with DSMS and DBMS in EMR system for processing, monitoring the incoming CCR data stream and storing the processed result with high-efficiency. The proposed system enables users not only to query stored CCR information from DBMS, but also enables to execute continue query for the real-time CCR Data Stream. By using of CCR Viewer Application users can view or update their personal health records even compare self health care records with standard health care records in order to monitor the healthy status, and the on line updating information would be minimized and medical error.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.11a
• /
• pp.413-416
• /
• 2008

In the presence of multiple continuous queries, multi-query optimizing is a new challenge to process multiple stream data in real-time. So, in this paper, we proposed an approach to optimize multi-query of sliding window on network traffic data streams and do some comparisons to traditional queries without optimizing. We also detail some method of scheduling on different data streams, while different scheduling made different results. We test the results on variety of multi-query processing schedule, and proofed the proposed method is effectively optimized the data stream similar multi-queries.