Central Bank Digital Currency (CBDC) is a digital currency issued by a central bank. Motivated by the financial crisis and prospect of a cashless society, countries are researching CBDC. Recently, global consideration has been given to paying basic income to avoid consumer sentiment shrinkage and recession due to epidemics. CBDC is coming into the spotlight as the way to manage the public finance policy of nations comprehensively. CBDC is studied by many countries. The bank of the Bahamas released Sand Dollar. Each country’s central bank should consider the situation in which CBDCs are exchanged. The transaction of the CDDB is open data. Transaction registers CBDC exchange information of the central bank in the blockchain. Open data on currency exchange between countries will provide information on the flow of money between countries. This paper proposes a blockchain system and management method based on the ISO/IEC 11179 metadata registry for exchange between CBDCs that records transactions between registered CBDCs. Each country’s CBDC will have a different implementation and time of publication. We implement the blockchain system and experiment with the operation method, measuring the block generation time of blockchains using the proposed method.

Coastal waste not only has a seriously destructive effect on human life and marine ecosystems, but it also poses a long-term economic and environmental threat. To solve the issues of a poor manual coastal waste sorting environment, such as low sorting efficiency and heavy tasks, we develop a novel deep convolutional neural network by combining several strategies to realize intelligent waste recognition and classification based on the state-of-the-art Faster R-CNN framework. Firstly, to effectively detect small objects, we consider multiple-scale fusion to get rich semantic information from the shallower feature map. Secondly, RoI Align is introduced to solve positioning deviation caused by the regions of interest pooling. Moreover, it is necessary to correct key parameters and take on data augmentation to improve model performance. Besides, we create a new waste object dataset, named IST-Waste, which is made publicly to facilitate future research in this field. As a consequence, the experiment shows that the algorithm’s mAP reaches 83%. Detection performance is significantly better than Faster R-CNN and SSD. Thus, the developed scheme achieves higher accuracy and better performance against the state-of-the-art alternative.

Bitcoin is the first cryptocurrency to participate in a network and receive compensation for online remittance and mining without any intervention from a third party, such as financial institutions. Bitcoin mining is done through proof of work (PoW). Given its characteristics, the higher hash rate results in a higher probability of mining, leading to the emergence of a mining pool, called a mining organization. Unlike central processing units or graphics processing units, high-cost application-specific integrated circuit miners have emerged with performance efficiency. The problem is that the obtained hash rate exposes Bitcoin’s mining monopoly and causes the risk of a double-payment attack. To solve this problem, we propose the error-correction code PoW (ECCPoW), combining the low-density parity-check decoder and hash function. The ECCPoW contributes to the phenomenon of symmetry in the proof of work (PoW) blockchain. This paper proposes the implementation of ECCPoW, replacing the PoW in Bitcoin. Finally, we compare the mining centralization, security, and scalability of ECCPoW and Bitcoin.

A sensor registry system (SRS) registers sensor metadata and provides them for a seamless semantic process. Recently, network coverage information-based SRS (NC-SRS) was developed to provide sensor information filtering by combining path prediction and network coverage checks. However, the NC-SRS has problems caused by issues such as termination of OpenSignal service and pre-building road segments. Therefore, this paper proposes a sensor registry system-based predictive information service (SRS-PIS) using a grid. SRS-PIS predicts a path based on the grid, checks the network coverage, and filters the sensor. This paper presents a grid-based real-time path prediction algorithm and an algorithm for grouping network service-disabled areas. To obtain network coverage information, we constructed and implemented a grid-based coverage map through experiment to measure the signal strength. As an evaluation, we compared features among SRS-based systems and SRS-PIS, and compared advantages and disadvantages between segment-based and grid-based methods.

머신러닝에 중요한 데이터 셋의 구성과 품질을 올리는 기술인 데이터 증강은 적은 양의 데이터를 바탕으로 다양한 알고리즘을 통해 데이터의 양을 늘리는 기술이다. 본 연구에서는 대규모 언어 모델인 GPT(Generative Pre-trained Transformer)를 활용한 데이터 증강으로 감정 분석 모델의 성능을 향상시키는 방법을 제안하고 평가한다. 데이터 셋의 클래스 불균형 문제를 해결하기 위해 가중치를 적용한 로직을 사용하였고, 생성된 데이터의 품질 및 다양성에 대한 한계를 극복하기 위해 프롬프트 엔지니어링을 적용했다. 실험결과, 제안한 방법은 데이터의 품질을 유지하면서 다양성을 높이고, 클래스 불균형 문제를 효과적으로 해결할 수 있어 KoBERT 모델을 이용해 GPT를 활용한 데이터 증강이 모델의 성능을 향상시킬 수 있음을 보였다.

게임에서 NPC(Non-Player Character)들은 각자의 역할에 맞는 인공지능이 적용되어 플레이어와 상호작용하며 플레이어에게 재미를 느끼게 해주는 중요한 요소이다. 게임 인공지능 구현 방법은 다양하며 최근 강화학습이 각광받고 있다. 강화학습은 에이전트가 게임 환경에서 스스로 학습하여 환경에 맞는 인공지능을 구현하는 방법이다. 강화학습을 게임 인공지능 구현에 사용하면 NPC가 취해야 하는 행동을 코드로 구현해야 하는 번거로움도 없고, 인공지능 구현을 목적으로 만들어졌기 때문에 복잡한 인공지능도 구현할 수 있다. 이 논문에서는 강화학습으로 구현된 목표 추적 인공지능의 성능을 분석하고자 게임 제작 플랫폼인 Unity의 ML-Agents를 통해 강화학습으로 목표 추적 인공지능을 구현하고 추가로 기존에 목표 추적 인공지능 구현 방법인 NavMeshAgent로 구현된 목표 추적 인공지능과 성능을 비교한다.