• Title/Summary/Keyword: Network loss

Search Result 2,304, Processing Time 0.026 seconds

Novel Maritime Wireless Communication based on Mobile Technology for the Safety of Navigation: LTE-Maritime focusing on the Cell Planning and its Verification

  • Shim, Woo-Seong;Kim, Bu-Young;Park, Chan-Yong;Lee, Byeong-Hyeok
    • Journal of Navigation and Port Research
    • /
    • v.45 no.5
    • /
    • pp.231-237
    • /
    • 2021
  • Enhancing the performance of maritime wireless communication has been highlighted by the issue of cell planning in the sea area because of lack of an appropriate Propagation Loss Model (PLM). To resolve the cell planning issue in vast sea areas, it was essential to develop the (PLM) matching the intended sea area. However, there were considerable gaps between the prediction of legacy PLMs and field measurement in propagation loss and there was a need to develop the adjusted PLM (A-PLM). Therefore, cell planning was performed on this adjusted model, including modification of the base station's location, altitude, and antenna azimuth to meet the quality objectives. Furthermore, in order to verify the availability of the cell planning, Communication Service Quality Monitoring System (CS-QMS) was developed in the LTE-Maritime project to collect LTE signal quality information from the onboard equipment at regular intervals and to ensure that the service quality was high enough to satisfy the goals in each designated grid. As a result of verification, the success rate of RSRP was 95.7% for the intensive management zone (IMZ) and 96.4% for the interested zone (IZ), respectively.

Study on the Surface Defect Classification of Al 6061 Extruded Material By Using CNN-Based Algorithms (CNN을 이용한 Al 6061 압출재의 표면 결함 분류 연구)

  • Kim, S.B.;Lee, K.A.
    • Transactions of Materials Processing
    • /
    • v.31 no.4
    • /
    • pp.229-239
    • /
    • 2022
  • Convolution Neural Network(CNN) is a class of deep learning algorithms and can be used for image analysis. In particular, it has excellent performance in finding the pattern of images. Therefore, CNN is commonly applied for recognizing, learning and classifying images. In this study, the surface defect classification performance of Al 6061 extruded material using CNN-based algorithms were compared and evaluated. First, the data collection criteria were suggested and a total of 2,024 datasets were prepared. And they were randomly classified into 1,417 learning data and 607 evaluation data. After that, the size and quality of the training data set were improved using data augmentation techniques to increase the performance of deep learning. The CNN-based algorithms used in this study were VGGNet-16, VGGNet-19, ResNet-50 and DenseNet-121. The evaluation of the defect classification performance was made by comparing the accuracy, loss, and learning speed using verification data. The DenseNet-121 algorithm showed better performance than other algorithms with an accuracy of 99.13% and a loss value of 0.037. This was due to the structural characteristics of the DenseNet model, and the information loss was reduced by acquiring information from all previous layers for image identification in this algorithm. Based on the above results, the possibility of machine vision application of CNN-based model for the surface defect classification of Al extruded materials was also discussed.

Presentation of potential genes and deleterious variants associated with non-syndromic hearing loss: a computational approach

  • Ray, Manisha;Rath, Surya Narayan;Sarkar, Saurav;Sable, Mukund Namdev
    • Genomics & Informatics
    • /
    • v.20 no.1
    • /
    • pp.5.1-5.10
    • /
    • 2022
  • Non-syndromic hearing loss (NSHL) is a common hereditary disorder. Both clinical and genetic heterogeneity has created many obstacles to understanding the causes of NSHL. The present study has attempted to ravel the genetic aetiology in NSHL progression and to screen out potential target genes using computational approaches. The reported NSHL target genes (2009-2020) have been studied by analyzing different biochemical and signaling pathways, interpretation of their functional association network, and discovery of important regulatory interactions with three previously established miRNAs in the human inner ear as well as in NSHL such as miR-183, miR-182, and miR-96. This study has identified SMAD4 and SNAI2 as the most putative target genes of NSHL. But pathogenic and deleterious non-synonymous single nucleotide polymorphisms discovered within SMAD4 is anticipated to have an impact on NSHL progression. Additionally, the identified deleterious variants in the functional domains of SMAD4 added a supportive clue for further study. Thus, the identified deleterious variant i.e., rs377767367 (G491V) in SMAD4 needs further clinical validation. The present outcomes would provide insights into the genetics of NSHL progression.

Study on the Optimal Design of Automatic Data Recovery System in case of Communication Loss in Remote Management of Hydraulic Facilities (수리시설물 원격관리에 있어 통신두절시 데이터 자동복구 시스템 최적설계에 관한 연구)

  • Ahn, Tae-Hyung;Kim, Sang-Yu;Ko, Jeong-Min;Kim, Jae-Yeol
    • Journal of the Korean Society of Manufacturing Process Engineers
    • /
    • v.21 no.4
    • /
    • pp.46-52
    • /
    • 2022
  • In the existing wired communication network, wired communication is frequently interrupted by lightning, which accompanies rain, and remote management cannot be performed when it is actually necessary. In the case of communication interruption, field data stored in the database are lost, and data at an important point in time may go missing; this causes a decrease in the reliability of the stored data. Therefore, in this study, wireless communication using the Internet of Things (IoT) communication network of the 4th industrial technology is installed in the prototype to reduce wired communication construction costs, prevent resource waste and environmental damage due to communication facility construction, and prepare for communication loss.

Characteristics of a 190 kVA Superconducting Fault current Limiting Element (190 kVA급 초전도한류소자의 특성)

  • Ma, Y.H.;Li, Z.Y.;Park, K.B.;Oh, I.S.;Ryu, K.Y.
    • Progress in Superconductivity and Cryogenics
    • /
    • v.9 no.1
    • /
    • pp.37-42
    • /
    • 2007
  • We are developing a 22.9 kV/25 MVA superconducting fault current limiting(SFCL) system for a power distribution network. A Bi-2212 bulk SFCL element, which has the merits of large current capacity and high allowable electric field during fault of the power network, was selected as a candidate for our SFCL system. In this work, we experimentally investigated important characteristics of the 190 kVA Bi-2212 SFCL element in its application to the power grid e.g. DC voltage-current characteristic, AC loss, current limiting characteristic during fault, and so on. Some experimental data related to thermal and electromagnetic behaviors were also compared with the calculated ones based on numerical method. The results show that the total AC loss at rated current of the 22.9 kV/25 MVA SFCL system, consisting of one hundred thirty five 190 kVA SFCL elements, becomes likely 763 W, which is excessively large for commercialization. Numerically calculated temperature of the SFCL element in some sections is in good agreement with the measured one during fault. Local temperature distribution in the190 kVA SFCL element is greatly influenced by non-uniform critical current along the Bi-2212 bulk SFCL element, even if its non-uniformity becomes a few percentages.

Facial Manipulation Detection with Transformer-based Discriminative Features Learning Vision (트랜스포머 기반 판별 특징 학습 비전을 통한 얼굴 조작 감지)

  • Van-Nhan Tran;Minsu Kim;Philjoo Choi;Suk-Hwan Lee;Hoanh-Su Le;Ki-Ryong Kwon
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2023.11a
    • /
    • pp.540-542
    • /
    • 2023
  • Due to the serious issues posed by facial manipulation technologies, many researchers are becoming increasingly interested in the identification of face forgeries. The majority of existing face forgery detection methods leverage powerful data adaptation ability of neural network to derive distinguishing traits. These deep learning-based detection methods frequently treat the detection of fake faces as a binary classification problem and employ softmax loss to track CNN network training. However, acquired traits observed by softmax loss are insufficient for discriminating. To get over these limitations, in this study, we introduce a novel discriminative feature learning based on Vision Transformer architecture. Additionally, a separation-center loss is created to simply compress intra-class variation of original faces while enhancing inter-class differences in the embedding space.

A Framework for Facial Expression Recognition Combining Contextual Information and Attention Mechanism

  • Jianzeng Chen;Ningning Chen
    • Journal of Information Processing Systems
    • /
    • v.20 no.4
    • /
    • pp.535-549
    • /
    • 2024
  • Facial expressions (FEs) serve as fundamental components for human emotion assessment and human-computer interaction. Traditional convolutional neural networks tend to overlook valuable information during the FE feature extraction, resulting in suboptimal recognition rates. To address this problem, we propose a deep learning framework that incorporates hierarchical feature fusion, contextual data, and an attention mechanism for precise FE recognition. In our approach, we leveraged an enhanced VGGNet16 as the backbone network and introduced an improved group convolutional channel attention (GCCA) module in each block to emphasize the crucial expression features. A partial decoder was added at the end of the backbone network to facilitate the fusion of multilevel features for a comprehensive feature map. A reverse attention mechanism guides the model to refine details layer-by-layer while introducing contextual information and extracting richer expression features. To enhance feature distinguishability, we employed islanding loss in combination with softmax loss, creating a joint loss function. Using two open datasets, our experimental results demonstrated the effectiveness of our framework. Our framework achieved an average accuracy rate of 74.08% on the FER2013 dataset and 98.66% on the CK+ dataset, outperforming advanced methods in both recognition accuracy and stability.

A survey on the topological design models for fiberoptic subscriber loop networks (광가입자 선로망 구성을 위한 설계모형 조사연구)

  • 윤문길;백영호
    • Korean Management Science Review
    • /
    • v.11 no.3
    • /
    • pp.103-128
    • /
    • 1994
  • Due to the trend of evolution toward a broadband communication network with fiber-optics, the design and operation of fiber-optic network have been received a great deal of research attention recently. Furthermore, even a single fiber link failure in the network may result in severe service loss. Thus, the network survivability becomes an importantissue in planning and designing the network. This survey is on modelling of various fiber-optic subscriber loop network(FSLN) design problems, which are essential ones for providing broadband communication services and B-ISDN services. Models are classified and investigated as either conventional decomposition-iteration approach or integrated design method. To build survivable networks, SHR models are also suggested by ring control schemes. The result of this study will be effectively applied to build a design model for FSLN in the practical applications.

  • PDF

Recirculating Shuffle-Exchange Interconnection ATM Switching Network Based on a Priority Control Algorithm (우선순위 제어기법을 기반으로 한 재순환 Shuffle-Exchage 상호연결 ATM 스위치)

  • Park, Byeong-Su
    • The Transactions of the Korea Information Processing Society
    • /
    • v.7 no.6
    • /
    • pp.1949-1955
    • /
    • 2000
  • This paper proposes a multistage interconnection ATM switching network without internal blocking. The first is recirculating shuffle-exchange network improved on hardware complexity. The next is connected to Rank network with tree structure. In this network, after the packets transferred to the same output ports are given each priority, only a packet with highest priority is sent to the next, an the others are recirculated to the first. Rearrangeability through decomposition and composition algorithm is applied for the transferred packets in hanyan network and all they arrive at a final destinations. To analyze throughput, waiting time and packet loss ratio according tothe size of buffer, the probabilities are modeled by a binomial distribution of packet arrival.

  • PDF

IP Mobility Supporting System in Heterogeneous Network (블루투스와 무선 LAN 환경을 위한 IP 이동성 지원 시스템)

  • Kang, Byoung-Hoon;Kim, Man-Bae;Choi, Chang-Yeol
    • Journal of Industrial Technology
    • /
    • v.28 no.B
    • /
    • pp.245-250
    • /
    • 2008
  • Recently, mobile devices have supported wireless LAN as well as bluetooth, where the services such as heterogeneous network access and seamless mobility connection are important. Even though the mobility and physical network might be varied, an efficient communication mechanism for the network access and a robust mobility management of mobile devices are needed. In this paper, we design and implement a Bluetooth system with mobile LAN access capability. The proposed system has the following features; 1) IP connection is enabled by BENP in the link layer, 2) The networks devices of heterogeneous mobile devices are integrated into a single virtual network interface, 3) IP mobility between the bluetooth and wireless LAN is supported by mobile IP. The experimented results show that the packet loss and delay time during the handover duration is reduced by predicting the handover among different networks followed by the setup of any required parameters in advance.

  • PDF