Digital Library[ Search Result ]
Knowledge Graph Embedding with Entity Type Constraints
Seunghwan Kong, Chanyoung Chung, Suheon Ju, Joyce Jiyoung Whang
http://doi.org/10.5626/JOK.2022.49.9.773
Knowledge graph embedding represents entities and relationships in the feature space by utilizing the structural properties of the graph. Most knowledge graph embedding models rely only on the structural information to generate embeddings. However, some real-world knowledge graphs include additional information such as entity types. In this paper, we propose a knowledge graph embedding model by designing a loss function that reflects not only the structure of a knowledge graph but also the entity-type information. In addition, from the observation that certain type constraints exist on triplets based on their relations, we present a negative sampling technique considering the type constraints. We create the SMC data set, a knowledge graph with entity-type restrictions to evaluate our model. Experimental results show that our model outperforms the other baseline models.
LSM Tree Compaction Offloading Using NVMe-oF
Sungho Moon, Hera Koo, Hyeongjun Jeon, Beomseok Nam
http://doi.org/10.5626/JOK.2022.49.7.569
NVMe-over-Fabrics (NVMe-oF) is drawing attraction in the industry as an alternative to disaggregated storage by providing fast access to remote NVMe SSDs through NVMe commands. In this paper, we propose RocksDB-oF, an LSM-Tree-based key-value store optimized for disaggregated storage using NVMe-oF. RocksDB-oF alleviated the Write Stall problem by offloading compaction from the computing node onto the storage node in consideration of the characteristics of NVMe-oF. In addition, a file system that uses Storage Performance Development Kit (SPDK) effectively solves the file system consistency problem of two nodes accessing the same NVMe SSD at the same time. Experimentally, in a disaggregated storage environment with NVMe-oF, RocksDB-oF showed higher write throughput than legacy RocksDB.
Xpass: NUMA-aware Persistent Memory Disaggregation
Jaeyoun Nam, Hokeun Cha, ByeongKeon Lee, Beomseok Nam
http://doi.org/10.5626/JOK.2021.48.7.735
The disaggregation method is used for efficient resource management in large-scale data centers, where each server consists of NUMA nodes. In the NUMA architecture, the latency difference between the remote and local access is known to be significant. In particular, remote NUMA access to persistent memory is even higher than DRAM. In this study, we propose Xpass, a memory disaggregation framework that considers the locality of NUMA architecture in a persistent memory disaggregation system. Xpass uses the dynamic hash table - CCEH to manage cached pages, and proposes a segment split algorithm that considers load balancing between the NUMA nodes in a NUMA environment.
Implementation and Evaluation of a DMA Controller for PCIe-based FPGA Boards
http://doi.org/10.5626/JOK.2021.48.2.141
An FPGA is an integrated circuit designed to be reconfigurable multiple times at runtime, which shows great performance and energy efficiency in modern applications such as deep learning and big data processing. Major FPGA vendors produce PCIe-based FPGA boards to use FPGAs as accelerators. To transfer large data between a host system and an FPGA, a DMA controller should be implemented inside the FPGA. In previous work, however, controllers did not fully utilize the PCIe bandwidth or were unable to send and receive simultaneously. This paper presents a new DMA controller architecture that can utilize the full-duplex bandwidth of a PCIe link. The DMA controller is implemented and evaluated on a board with Intel Stratix 10 FPGA. The results show that our controller is up to 2.3 times faster than the controller shipped with Intel FPGA Acceleration Stack.
Deep Learning-based Text Classification Model for Poisonous Clauses Classification
Gihyeon Choi, Youngjin Jang, Harksoo Kim, Kwanwoo Kim
http://doi.org/10.5626/JOK.2020.47.11.1054
Most companies sign contracts based on the contract prior to executing the task. However, several problems can occur if the poisonous clauses are not identified before the contract is concluded. To prevent this problem, companies have an expert review the contract, but the service requires much time and money. If there is a system in which the poisonous clauses can be identified through prior review of the contract, the high cost and time incurred in reviewing the contract can be mitigated. Thus, this paper proposes a text classification model that identifies any poisonous clause in the contract by inputing each paragraph in the contract. To improve the classification performance of the proposed model, the importance of each sentence is calculated based on the relationship information between the sentence in the paragraph and the class to be classified, and classification is performed by reflecting it in each sentence. The proposed model showed the performance of the F1 score 84.51%p in experiments using actual contract data and the highest performance with the F1 score 93.64%p in experiments using the WOS-5736 dataset for the performance comparison with the existing text classification models.
Dual Paraboloid Map-Based Real-Time Indirect Illumination Rendering
http://doi.org/10.5626/JOK.2019.46.11.1099
Indirect light rendering, which expresses the light expression more finely and delicately, has been studied in terms of the indirect illumination effect in real-time rendering environment due to the load of the physical calculation process. Among them, the Light Propagation Volumes technique achieved real-time performance by approximating the indirect lighting effect by propagating the volume containing the light information to the adjacent volume. However, as the size of the geometry increases, performance degradation occurs as the Reflective Shadow Map containing the light information is generated as a cube map in the rendering process. Although it is possible to replace the Reflective Shadow Map with other types of textures other than the cube map to reduce the occurrence of bottlenecks, distortion occurs in the nonlinear projection transformation of other type textures. In this study, the Reflective Shadow Map is generated as a dual paraboloid map types to reduce the bottleneck. Distortions occurring in the process of paraboloid map transformation were corrected by using fixed point iteration-based backward warping.
English-to-Korean Machine Translation using Image Information
Jangseong Bae, Hyunsun Hwang, Changki Lee
http://doi.org/10.5626/JOK.2019.46.7.690
Machine translation automatically converts a text in one language into another language. Conventional machine translations use only texts for translation which is a disadvantage in that various information related to input text cannot be utilized. In recent years, multimodal machine translation models have emerged that use images related to input text as additional inputs, unlike conventional machine translations which use only textual data. In this paper, image information was added at decoding time of machine translation according to recent research trends and used for English-to-Korean automated translation. In addition, we propose a model with a decoding gate to adjust the textual and image information at the decoding time. Our experimental results show that the proposed method resulted in better performance than the non-gated model.
Fast Blockchain Consensus Algorithm with Forward Secure Signatures
Jeonghyuk Lee, Jihye Kim, Hyunok Oh
http://doi.org/10.5626/JOK.2019.46.5.397
Recently blockchain has emerged as an alternative to central data management. Existing blockchains, such as Bitcoin or Ethereum use a PoW(Proof of Work) method to reliably add a new block to the blockchain. Since PoW method performs a hash function calculation and has a high computational cost, fast transactions are impossible with PoW. Therefore, we propose a delegation based blockchain that can replace PoW method and use a forward secure signature to enhance the blockchain security. We implemented a signature scheme that could be used in delegation based blockchains, and analyzed the performance and security of the proposed blockchain.
MQTT-based Gateway System for Auto-configuration of IoT Devices and Services
Geonwoo Kim, Jiwoo Park, Kwangsue Chung
http://doi.org/10.5626/JOK.2019.46.4.385
MQTT (Message Queuing Telemetry Transport) is a messaging protocol for the IoT(Internet of Things) selected by the OASIS (Organization for the Advancement of Structured Information Standards), which enables efficient data transmission to occur over low-power, unreliable networks. However, there is a problem that the service discovery is impossible, because the MQTT does not use multicast features, and there is no resource directory for managing resource information in the local network. In this paper, we propose an auto-configuration system that enables service discovery and device operation using a MQTT Publish/Subscribe message transmission method through a gateway acting as a resource directory. Through the implementation results, we confirmed that devices and services existing in the local network can be discovered and operated by using the proposed auto-configuration system.
Knowledge Base Population Model Using Non-Negative Matrix Factorization
Jiho Kim, Sangha Nam, Key-Sun Choi
http://doi.org/10.5626/JOK.2018.45.9.918
The purpose of a knowledge base is to incorporate all the knowledge in the world in a format that machines can understand. In order for a knowledge base to be useful, it must continuously acquire and add new knowledge. However, it cannot if it lacks knowledge-acquisition ability. Knowledge is mainly acquired by analyzing natural language sentences. However, studies on internal knowledge acquisition are being neglected. In this paper, we introduce a non-negative matrix factorization method for knowledge base population. The model introduced in this paper transforms a knowledge base into a matrix and then learns the latent feature vector of each entity tuple and relation by decomposing the matrix and reassembling the vectors to score the reliability of the new knowledge. In order to demonstrate the effectiveness and superiority of our method, we present results of experiments and analysis performed with Korean DBpedia.
Search
Journal of KIISE
- ISSN : 2383-630X(Print)
- ISSN : 2383-6296(Electronic)
- KCI Accredited Journal
Editorial Office
- Tel. +82-2-588-9240
- Fax. +82-2-521-1352
- E-mail. chwoo@kiise.or.kr