2022, Vol.27, No.2

Journal of The Korea Society of Computer and Information 2023 KCI Impact Factor : 0.65

pISSN : 1598-849X / eISSN : 2383-9945
https://journal.kci.go.kr/jksci

In this paper, we design and implement a GPU-based parallel algorithm to effectively solve the traveling salesman problem through an ant color system. The repetition process of generating hundreds or thousands of tours simultaneously in TSP utilizes GPU's task-level parallelism, and the update process of pheromone trails data actively exploits data parallelism by 32x32 thread blocks. In particular, through simultaneous memory access of multiple threads, the coalesced accesses on continuous memory addresses and concurrent accesses on shared memory are supported. This experiment used 127 to 1002 city data provided by TSPLIB, and compared the performance of sequential and parallel algorithms by using Intel Core i9-9900K CPU and Nvidia Titan RTX system. Performance improvement by GPU parallelization shows speedup of about 10.13 to 11.37 times.

In this study, we propose a method for moving a device such as a flexible air sculpture while stably maintaining the user's desired posture. To accomplish this, a robot system with a structure of a mobile robot capable of running according to a given trajectory was studied by applying the PI algorithm and horizontal maintenance posture control using IMU. The air sculptures used in this study often use thin strings in a fixed posture. Another method is to put a load on the center of gravity to maintain the posture, and it is a system with flexibility because it uses air pressure. It is expected that these structures can achieve various results by combining flexible structures and mobile robots through the convergence process of digital sensor technology. In this study, posture control was performed by fusion of the driving technology of AGV(Automatic Guided Vehicle),, a field of robot, and technologies applying various sensors. For verification, the given performance evaluation was performed through an accredited certification test, and its validity was verified through an experiment.

In the field of patents, as NLP(Natural Language Processing) is a challenging task due to the linguistic specificity of patent literature, there is an urgent need to research a language model optimized for Korean patent literature. Recently, in the field of NLP, there have been continuous attempts to establish a pre-trained language model for specific domains to improve performance in various tasks of related fields. Among them, ELECTRA is a pre-trained language model by Google using a new method called RTD(Replaced Token Detection), after BERT, for increasing training efficiency. The purpose of this paper is to propose KorPatELECTRA pre-trained on a large amount of Korean patent literature data. In addition, optimal pre-training was conducted by preprocessing the training corpus according to the characteristics of the patent literature and applying patent vocabulary and tokenizer. In order to confirm the performance, KorPatELECTRA was tested for NER(Named Entity Recognition), MRC(Machine Reading Comprehension), and patent classification tasks using actual patent data, and the most excellent performance was verified in all the three tasks compared to comparative general-purpose language models.