• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.89-106
• /
• 2022

Recently, the amount of video data collected from smartphones, CCTVs, black boxes, and high-definition cameras has increased rapidly. According to the increasing video data, the requirements for analysis and utilization are increasing. Due to the lack of skilled manpower to analyze videos in many industries, machine learning and artificial intelligence are actively used to assist manpower. In this situation, the demand for various computer vision technologies such as object detection and tracking, action detection, emotion detection, and Re-ID also increased rapidly. However, the object detection and tracking technology has many difficulties that degrade performance, such as re-appearance after the object's departure from the video recording location, and occlusion. Accordingly, action and emotion detection models based on object detection and tracking models also have difficulties in extracting data for each object. In addition, deep learning architectures consist of various models suffer from performance degradation due to bottlenects and lack of optimization. In this study, we propose an video analysis system consists of YOLOv5 based DeepSORT object tracking model, SlowFast based action recognition model, Torchreid based Re-ID model, and AWS Rekognition which is emotion recognition service. Proposed model uses single-linkage hierarchical clustering based Re-ID and some processing method which maximize hardware throughput. It has higher accuracy than the performance of the re-identification model using simple metrics, near real-time processing performance, and prevents tracking failure due to object departure and re-emergence, occlusion, etc. By continuously linking the action and facial emotion detection results of each object to the same object, it is possible to efficiently analyze videos. The re-identification model extracts a feature vector from the bounding box of object image detected by the object tracking model for each frame, and applies the single-linkage hierarchical clustering from the past frame using the extracted feature vectors to identify the same object that failed to track. Through the above process, it is possible to re-track the same object that has failed to tracking in the case of re-appearance or occlusion after leaving the video location. As a result, action and facial emotion detection results of the newly recognized object due to the tracking fails can be linked to those of the object that appeared in the past. On the other hand, as a way to improve processing performance, we introduce Bounding Box Queue by Object and Feature Queue method that can reduce RAM memory requirements while maximizing GPU memory throughput. Also we introduce the IoF(Intersection over Face) algorithm that allows facial emotion recognized through AWS Rekognition to be linked with object tracking information. The academic significance of this study is that the two-stage re-identification model can have real-time performance even in a high-cost environment that performs action and facial emotion detection according to processing techniques without reducing the accuracy by using simple metrics to achieve real-time performance. The practical implication of this study is that in various industrial fields that require action and facial emotion detection but have many difficulties due to the fails in object tracking can analyze videos effectively through proposed model. Proposed model which has high accuracy of retrace and processing performance can be used in various fields such as intelligent monitoring, observation services and behavioral or psychological analysis services where the integration of tracking information and extracted metadata creates greate industrial and business value. In the future, in order to measure the object tracking performance more precisely, there is a need to conduct an experiment using the MOT Challenge dataset, which is data used by many international conferences. We will investigate the problem that the IoF algorithm cannot solve to develop an additional complementary algorithm. In addition, we plan to conduct additional research to apply this model to various fields' dataset related to intelligent video analysis.

• Journal of Biosystems Engineering
• /
• v.7 no.2
• /
• pp.18-29
• /
• 1983

A low cost and versatile data acquisition system for the field and laboratory use was developed by using a single board microcomputer. Data acquisition system based on a Z80 microprocessor was built, tested and modified to obtain the present functional system. The microcomputer developed consists of 6 kB ROM, 5 kB RAM, 6-seven segment LED display, 16-Hex. key and 8 command key board. And it interfaces with an 8 channel, 12 bits A/D converter, a microprinter, EPROM programmer for 2716, and RS232C interface to transfer data between the system and HP3000 mini-computer manufactured by Hewlett Packard Co., A software package was also developed, tested, and modified for the system. This package included drivers for the AID converter, LED display, key board, microprinter, EPROM programmer, and RS232c interface. All of these programs were written in 280 assembler language and converted to machine codes using a cross assembler by HP3000 computer to the system during modifying stage by data transferring unit of this system, then the machine language wrote to the EPROM by this EPROM programmer. The results are summarized as follows: 1. Measuring program developed was able to control the measuring intervals, No. of channels used, and No. of data, where the maximum measuring speed was 58.8 microsec. 2. Calibration of the system was performed with triangle wave generated by a function generator. The results of calibration agreed well to the test results. 3. The measured data was able to be written into EPROM, then the EPROM data was compared with original data. It took only 75 sec. for the developed program to write the data of 2 kB the EPROM. 4. For the slow speed measurements, microprinter instead of EPROM programmer proved to be useful. It took about 15 min. for microprinter to write the data of 2 kB. 5. Modified data transferring unit was very effective in communicating between the system and HP3000 computer. The required time for data transferring was only 1~2 min. 6. By using DC/DC converting devices such as 78-series, 79-series. and TL497 IC, this system was modified to convert the only one input power sources to the various powers. The available power sources of the system was DC 7~25 V and 1.8 A.

• Journal of Home Health Care Nursing
• /
• v.4
• /
• pp.5-22
• /
• 1997

The purpose of the study was to development an information delivery system for the home nursing service, to demonstrate and to evaluate the efficiency of it. The period of research conduct was from September 1996 to August 31, 1997. At the 1st stage to achieve the purpose, Firstly Assessment tool for the patients with cerebral vascular disease who have the first priority of HNS among the patients with various health problems at home was developed through literature review. Secondly, after identification of patient nursing problem by the home care nurse with the assessment tool, the patient's classification system developed by Park (1988) that was 128 nursing activities under 6 categories was used to identify the home care nurse's activities of the patient with CAV at home. The research team had several workshops with 5 clinical nurse experts to refine it. At last 110 nursing activities under 11 categories for the patients with CVA were derived. At the second stage, algorithms were developed to connect 110 nursing activities with the patient nursing problems identified by assessment tool. The computerizing process of the algorithms is as follows: These algorithms are realized with the computer program by use of the software engineering technique. The development is made by the prototyping method, which is the requirement analysis of the software specifications. The basic features of the usability, compatibility, adaptability and maintainability are taken into consideration. Particular emphasis is given to the efficient construction of the database. To enhance the database efficiency and to establish the structural cohesion, the data field is categorized with the weight of relevance to the particular disease. This approach permits the easy adaptability when numerous diseases are applied in the future. In paralleled with this, the expandability and maintainability is stressed through out the program development, which leads to the modular concept. However since the disease to be applied is increased in number as the project progress and since they are interrelated and coupled each other, the expand ability as well as maintainability should be considered with a big priority. Furthermore, since the system is to be synthesized with other medical systems in the future, these properties are very important. The prototype developed in this project is to be evaluated through the stage of system testing. There are various evaluation metrics such as cohesion, coupling and adaptability so on. But unfortunately, direct measurement of these metrics are very difficult, and accordingly, analytical and quantitative evaluations are almost impossible. Therefore, instead of the analytical evaluation, the experimental evaluation is to be applied through the test run by various users. This system testing will provide the viewpoint analysis of the user's level, and the detail and additional requirement specifications arising from user's real situation will be feedback into the system modeling. Also. the degree of freedom of the input and output will be improved, and the hardware limitation will be investigated. Upon the refining, the prototype system will be used as a design template. and will be used to develop the more extensive system. In detail. the relevant modules will be developed for the various diseases, and the module will be integrated by the macroscopic design process focusing on the inter modularity, generality of the database. and compatibility with other systems. The Home care Evaluation System is comprised of three main modules of : (1) General information on a patient, (2) General health status of a patient, and (3) Cerebrovascular disease patient. The general health status module has five sub modules of physical measurement, vitality, nursing, pharmaceutical description and emotional/cognition ability. The CVA patient module is divided into ten sub modules such as subjective sense, consciousness, memory and language pattern so on. The typical sub modules are described in appendix 3.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2004.05b
• /
• pp.217-220
• /
• 2004

According as utilization for web increases rapidly, it is demanded that model about support interaction between web-based applications systematically and solutions can integrate new distributed platforms and existing environment effectively, accordingly, Web Services appeared by solution in reply. These days, a lot of software and hardware companies try to adoption of Web Services to their market, attenpt to construct their applications associationing components from various Web Services providers. However, to execute Web Services completely. it must have interoperability and need the standardization work that avoid thing which is subject to platform, application as well as service and programming language from other companies. WS-I (Web Services Interoperability organization) have established Basic Profile 1.0 based on XML, UDDI, WSDL and SOAP for web services interoperability and developed usage scenario Profile to apply Web Services in practice. In this paper, to verify suitability Web Services interoperability between heterogeneous two applications, have design and implements the Book Information Web Services that based on the Web Services Client of J2SE platform and the Web Services Server of .NET platform, so that analysis and verify the service by adaptation of WS-I Basic Profile.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.2
• /
• pp.81-90
• /
• 2013

During the past decade, many changes and attempts have been tried and are continued developing new technologies in the computing area. The brick wall in computing area, especially power wall, changes computing paradigm from computing hardwares including processor and system architecture to programming environment and application usage. The high performance computing (HPC) area, especially, has been experienced catastrophic changes, and it is now considered as a key to the national competitiveness. In the late 2000's, many leading countries rushed to develop Exascale supercomputing systems, and as a results tens of PetaFLOPS system are prevalent now. In Korea, ICT is well developed and Korea is considered as a one of leading countries in the world, but not for supercomputing area. In this paper, we describe architecture design of MAHA supercomputing system which is aimed to develop 300 TeraFLOPS system for bio-informatics applications like human genome analysis and protein-protein docking. MAHA supercomputing system is consists of four major parts - computing hardware, file system, system software and bio-applications. MAHA supercomputing system is designed to utilize heterogeneous computing accelerators (co-processors like GPGPUs and MICs) to get more performance/$, performance/area, and performance/power. To provide high speed data movement and large capacity, MAHA file system is designed to have asymmetric cluster architecture, and consists of metadata server, data server, and client file system on top of SSD and MAID storage servers. MAHA system softwares are designed to provide user-friendliness and easy-to-use based on integrated system management component - like Bio Workflow management, Integrated Cluster management and Heterogeneous Resource management. MAHA supercomputing system was first installed in Dec., 2011. The theoretical performance of MAHA system was 50 TeraFLOPS and measured performance of 30.3 TeraFLOPS with 32 computing nodes. MAHA system will be upgraded to have 100 TeraFLOPS performance at Jan., 2013.

• 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.