• Title/Summary/Keyword: content adaptive

Search Result 265, Processing Time 0.03 seconds

Implementation of a Recommendation system using the advanced deep reinforcement learning method (고급 심층 강화학습 기법을 이용한 추천 시스템 구현)

  • Sony Peng;Sophort Siet;Sadriddinov Ilkhomjon;DaeYoung, Kim;Doo-Soon Park
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2023.11a
    • /
    • pp.406-409
    • /
    • 2023
  • With the explosion of information, recommendation algorithms are becoming increasingly important in providing people with appropriate content, enhancing their online experience. In this paper, we propose a recommender system using advanced deep reinforcement learning(DRL) techniques. This method is more adaptive and integrative than traditional methods. We selected the MovieLens dataset and employed the precision metric to assess the effectiveness of our algorithm. The result of our implementation outperforms other baseline techniques, delivering better results for Top-N item recommendations.

Assessment of Roof-rainwater Utilization System and Drought Resistance of Ground Cover Plants (지피식물을 이용한 우수저장형 옥상녹화 시스템 및 식물 내건성 평가)

  • Kang, Tai-Ho;Zhao, Hong-Xia
    • Journal of the Korean Institute of Landscape Architecture
    • /
    • v.41 no.5
    • /
    • pp.1-8
    • /
    • 2013
  • In order to evaluate 2 extensive green roof systems(Sedum Box Roof System and Roof-rainwater Utilization System) for urban greening and select ground-cover plants, which can adapt well to the drought tolerance in an extensive green roof system on 12 species. This study was carried out in order to suggest an experimental base in assessment of the Green Roof-rainwater Utilization System and selecting the drought resistance of plants. Adopting the natural drought method, this paper studies the drought resistance of 12 kinds of ground cover plants. The drought-resistance of ground cover plants subjected to dry processing time were evaluated using relative water content on leaves, relative electric conductivity and chlorophyll content in 12 kinds of plants, and the relation between soil water content under drought stress. Drought resistance of the plants were subject to rooftop drought resistance treatments. The result showed that with the increase of stress time, the relative water content and chlorophyll content on leaves were in a downward trend while the relative electric conductivity was in an upward trend. Among the 12 species of ground cover plants, excluding Pulsatilla koreana, Ainsliaea acerifolia was selected for rooftop plants because they showed resistance to drought strongly and took adaptive ability. These results showed that drought tolerance of plants in Roof-rainwater Utilization System were stronger than the Sedum Box Roof System. Therefore, the Roof-rainwater Utilization System is good for plants. It helps them adapt well to the drought tolerance in rooftops and can be used for urban greening.

Video Retrieval System supporting Adaptive Streaming Service (적응형 스트리밍 서비스를 지원하는 비디오 검색 시스템)

  • 이윤채;전형수;장옥배
    • Journal of KIISE:Computing Practices and Letters
    • /
    • v.9 no.1
    • /
    • pp.1-12
    • /
    • 2003
  • Recently, many researches into distributed processing on Internet, and multimedia data processing have been performed. Rapid and convenient multimedia services supplied with high quality and high speed are to be needed. In this paper, we design and implement clip-based video retrieval system on the Web enviroment in real-time. Our system consists of the content-based indexing system supporting convenient services for video content providers, and the Web-based retrieval system in order to make it easy and various information retrieval for users in the Web. Three important methods are used in the content-based indexing system, key frame extracting method by dividing video data, clip file creation method by clustering related information, and video database construction method by using clip unit. In Web-based retrieval system, retrieval method ny using a key word, two dimension browsing method of key frame, and real-time display method of the clip are used. In this paper, we design and implement the system that supports real-time display method of the clip are used. In this paper, we design and implement the system that supports real-time retrieval for video clips on Web environment and provides the multimedia service in stability. The proposed methods show a usefulness of video content providing, and provide an easy method for serching intented video content.

Tree Growth and Fruit Characteristics of 'Nero' Black Chokeberry According to Different Cultivation Regions and Altitudes (재배지역 및 고도에 따른 블랙초크베리 'Nero'의 수체 생육 및 과실 특성)

  • Won, Jungyeon;Shin, Hyunsuk;Oh, Youngjae;Han, Hyeondae;Kwon, Yeuseok;Kim, Daeil
    • Korean Journal of Plant Resources
    • /
    • v.31 no.2
    • /
    • pp.136-148
    • /
    • 2018
  • The study was performed to investigate basic tree growth and fruit characteristics of 'Nero' black chokeberry (Aronia melanocarpa) depending on the different cultivation regions and altitudes in 2014, 2015. Tree growth and change of developmental stages of 'Nero' were similar regardless of meteorological environment of the four cultivation regions (Danyang, Okcheon, Yeongdong, and Geumsan) in 2014. Fruit characteristics of 'Nero' were significant differences in berry weight and anthocyanin content among the four orchards due to difference in cultivation techniques and relatively wide daily temperature range just before harvest, respectively. Tree growth and change of developmental stages of 'Nero' grown at the two orchards with different altitudes appeared to be similar during the successive years 2014 and 2015. Soluble solids content of the berries cultivated at low altitude (117 m) was higher than at high altitude (342 m). Acidity showed an inverse pattern with soluble solids content. Anthocyanin content increased progressively until at the middle of August, 2014-15 and then it decreased. Our results showed that black chokeberry is a species adaptive to the domestic environment as there were no differences in tree growth and change of developmental stages of 'Nero'. Considering fruit quality of black chokeberry such as soluble solids content, acidity, and anthocyanin content, our results suggest that optimal harvest period of black chokeberry 'Nero' is August 8 to 19.

MPEG Omnidirectional Media Format (OMAF) for 360 Media (360 미디어를 위한 MPEG Omnidirectional Media Format (OMAF) 표준 기술)

  • Oh, Sejin
    • Journal of Broadcast Engineering
    • /
    • v.22 no.5
    • /
    • pp.600-607
    • /
    • 2017
  • Virtual Reality (VR) has lately gained significant attention primarily driven by the recent market availability of consumer devices, such as mobile phone-based Head Mounted Displays (HMDs). Apart from classic gaming use cases, the delivery of $360^{\circ}$ video is considered as another major application and is expected to be ubiquitous in the near future. However, the delivery and decoding of high-resolution $360^{\circ}$ videos in desirable quality is a challenging task due to network limitations and constraints on available end device decoding and processing. In this paper, we focus on aspects of $360^{\circ}$ video streaming and provide an overview and discussion of possible solutions as well as considerations for future VR video streaming applications. This paper mainly focuses on the status of the standardization activities, Omnidirectional MediA Format (OMAF), to support interoperable $360^{\circ}$ video streaming services. More concretely, MPEG's ongoing work for OMA aims at harmonization of VR video platforms and applications. The paper also discusses the integration in MPEG Dynamic Adaptive Streaming over HTTP (MPEG-DASH), which is considered as $360^{\circ}$ video streaming services with OMAF content. In context of the general OMAF service architecture.

Alteration in Pyridine Nucleotide Status in Cells as an Adaptive Response to Water Stress in Rice (Oryza sativa L.) Seedlings

  • Boo, Yong-Chool;Jung, Jin
    • Applied Biological Chemistry
    • /
    • v.41 no.4
    • /
    • pp.228-234
    • /
    • 1998
  • An adaptive measure of photosynthetic cells to a condition identified with a reduction of cellular energy charge, caused by water deficit-induced impairment of photosynthetic ATP production, was investigated using hydroponically cultured rice seedlings. Water stress treatment of the seedlings resulted in a marked decrease in cellular ATP level, a significant increase in the content of NAD(H) and concurrent decrease in that of NADP(H) in shoots, which accompanied a decrease in the activity of NAD kinase (EC 2.7.1.23) that specifically converts NAD(H) to NADP(H). The decline in the enzyme activity was particularly evident in the $Ca^{2+}/calmodulin-dependent$ kinase, the major form of NAD kinase in plants, whereas the level of active calmodulin remained unchanged during water deficit. The ratio of $NADP^+$ to NADPH was maintained nearly constant and no increases were seen in the level of $H_2O_2$ and the activities of $superoxide/H_2O_2-detoxifying$ enzymes in shoots stress-treated for two days. Based on these results, it may be suggested that rice plants take a strategy to cope with an adverse situation of limited photophosphorylation created by water deficit in that cells facilitate ATP production through glycolysis and oxidative phosphorylation; in doing so, rice cells suppress NAD kinase activity, consequently up-sizing the NAD(H) pool at the expense of the NADP(H) pool. Several parameters associated with the stress symptoms are also of implicative that there is no overproduction of superoxide radical or the related active oxygen at least in rice seedlings.

  • PDF

Deep Learning based Photo Horizon Correction (딥러닝을 이용한 영상 수평 보정)

  • Hong, Eunbin;Jeon, Junho;Cho, Sunghyun;Lee, Seungyong
    • Journal of the Korea Computer Graphics Society
    • /
    • v.23 no.3
    • /
    • pp.95-103
    • /
    • 2017
  • Horizon correction is a crucial stage for image composition enhancement. In this paper, we propose a deep learning based method for estimating the slanted angle of a photograph and correcting it. To estimate and correct the horizon direction, existing methods use hand-crafted low-level features such as lines, planes, and gradient distributions. However, these methods may not work well on the images that contain no lines or planes. To tackle this limitation and robustly estimate the slanted angle, we propose a convolutional neural network (CNN) based method to estimate the slanted angle by learning more generic features using a huge dataset. In addition, we utilize multiple adaptive spatial pooling layers to extract multi-scale image features for better performance. In the experimental results, we show our CNN-based approach robustly and accurately estimates the slanted angle of an image regardless of the image content, even if the image contains no lines or planes at all.

Wavelet based data Watermarking (웨이브릿 기반의 데이터 워터마킹)

  • 김동현
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.7 no.6
    • /
    • pp.1224-1228
    • /
    • 2003
  • The use of digital imaging technique and digital contents based on internet has grown rapidly for last several years, and the needs of digital image protection become more important. For the purpose of copyright protection on digital image, the verification of authentication techniques like content authentication, ownership authentication, illegal copy and etc are needs. Digital watermarking, the invisible encryption technique to insert digital watermarking into image, the sophisticated perceptual information should be used for providing transparency and robustness of images on watermarking process. In this paper, we implement the algorithm for preventing forged attack. ownership protection and authentication by transforming the wavelet algorithms in frequency domain in terms of human visual system.

Adaptive LSB Steganography for High Capacity in Spatial Color Images (컬러이미지 대상 고용량 적응형 LSB 스테가노그라피)

  • Lee, Haeyoung
    • Journal of the Korea Computer Graphics Society
    • /
    • v.24 no.1
    • /
    • pp.27-33
    • /
    • 2018
  • This paper presents a new adaptive LSB steganography for high capacity in spatial color images. The number of least signi ficant bit (LSB) of each RGB component in a color image pixel, to replace with the data bits to be hidden, was determine d through analysis of the worst case peak signal noise ratio (PSNR). In addition, the combination of the number of bits is determined adaptively according to image content. That is, 70% of the data to be hidden is proposed to be replaced with 3 bit LSB of two components, 2 bit LSB of the rest component, and 30% be replaced with 4 bit LSB of each RGB compon ent. To find edge areas in an image, delta sorting in local area is also suggested. Using the proposed method, the data cap acity is 9.2 bits per pixel (bpp). The average PSNR value of the tested images with concealed data of up to 60Kbyte was 43.9 db and also natural histograms were generated.

FPGA Design of Adaptive Digital Receiver for Wireless Identification (무선인식을 위한 적응적 디지털 수신기의 FPGA 설계)

  • Seo Young-Ho;Kim Dong-Wook
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.9 no.4
    • /
    • pp.745-752
    • /
    • 2005
  • In this paper we propose and implement a digital part of a receiver system for identifying a moving object and its tracking position in wireless environment. We assumed UWB(Ultra Wide Band)-based communication system for target application and used serial communication method(RS-232). The proposed digital receiver consists of RS-232-type1/RS-232-type2 for input and output of serial communication, ID Detector for detecting IDs, and PISO&Buffer circuit to buffer input signals for appropriate operation of ID Detector. We implemented the digital receiver with minimal hardware(H/W) resource according to target application of UWB-based communication system. So it correlates input patterns with pre-stored patterns though repeated detecting method for multiple IDs. Since it has reference panerns in the Ve-stored form, it can detect various IDs instantly. Also we can program content and size of reference patterns considering compatibility with other systems .The implemented H/W was mapped into XC2S100PQ208-5 FPGA of Xilinx, occupied 727($30\%$) cells, and stably operated in the clock frequency of 75MHz(13.341ns).