• The Journal of Bigdata
• /
• v.8 no.1
• /
• pp.49-59
• /
• 2023

There are various items in the safety and health standards of the manufacturing industry, but they can be divided into work-related diseases and musculoskeletal diseases according to the standards for sickness and accident victims. Musculoskeletal diseases occur frequently in manufacturing and can lead to a decrease in labor productivity and a weakening of competitiveness in manufacturing. In this paper, to detect the musculoskeletal harmful factors of manufacturing workers, we defined the musculoskeletal load work factor analysis, harmful load working postures, and key points matching, and constructed data for Artificial Intelligence(AI) learning. To check the effectiveness of the suggested dataset, AI algorithms such as YOLO, Lite-HRNet, and EfficientNet were used to train and verify. Our experimental results the human detection accuracy is 99%, the key points matching accuracy of the detected person is @AP0.5 88%, and the accuracy of working postures evaluation by integrating the inferred matching positions is LEGS 72.2%, NECT 85.7%, TRUNK 81.9%, UPPERARM 79.8%, and LOWERARM 92.7%, and considered the necessity for research that can prevent deep learning-based musculoskeletal diseases.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.9
• /
• pp.801-806
• /
• 2001

According as many people use a computer newly, damage of computer virus and hacking is rapidly increasing by the crucial users A computer virus is one of program in computer and has abilities of self reproduction ad destruction like a virus of biology. And hacking is to rob a person's data in a intruded computer and to delete data in a person s computer from the outside. To block hacking that is intrusion of a person s computer and the computer virus that destroys data, a study for intrusion-detection of system and virus detection using a biological immune system is in progress. In this paper, we make a model of positive selection and negative selection of self-recognition process that is ability of T-cytotoxic cell that plays an important part in biological immune system. So we embody a self-nonself distinction algorithm in computer, which is an important part when we detect an infected data by computer virus and a modified data by intrusion from the outside. The composed self-recognition process distinguishes self-file from the changed files. To prove the efficacy of self-recognition algorithm, we use simulation by a cell change and a string change of self file.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.12
• /
• pp.5083-5088
• /
• 2010

An implementation of NPC AI(artifical intelligence) is similar with real world's flocking can increase fun factor of game. To this end, we design fish flocking patten of analyzed real world, implement using Ogre engine in this paper. To determine the usefulness of implemented fish flocking, we compare fish flocking in real world with implemented fish flocking. Implemented behavioral patterns of fish flocking show similar behavioral patterns of fish flocking in real world.

• Ceramist
• /
• v.6 no.3
• /
• pp.35-41
• /
• 2003

• Optical Science and Technology
• /
• v.6 no.4
• /
• pp.9-16
• /
• 2002

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.16 no.2
• /
• pp.115-124
• /
• 2003

In this paper, the effects of vehicle loads on flat slab system are investigated on the basis of the previous studies for beam-gilder parking structural system. The influence surfaces of flat slab for a typical design section are constructed lot the purpose of obtaining maximum member forces under vehicle loads. In addition, the equivalent vehicle load factors for flat slab parking structures are suggested using artificial neural network. The network responses we compared with the results obtained by numerical analyses to verify the validation of Levenberg-Marquardt algorithm adopted as training method in this Paper. Many parameter studies for the flat slab structural system show dominant vehicle load effects at the center positive moments in both column and middle strips, like the beam-girder parking structural system.

• Journal of Practical Engineering Education
• /
• v.15 no.2
• /
• pp.365-371
• /
• 2023

In this study, we proposed a plan to educate computer students at industrial specialized high schools about artificial intelligence programming using Raspberry Pi. To create an educational program, we received advice from experts working in schools and industries, analyzed existing research and requirements, designed weekly learning plans, developed teaching materials, and conducted classes. Due to the small number of research subjects, interviews were conducted with students, and the results of the teacher's diary were also presented to derive qualitative research results. The main interview results show that although it is true that interest in the field of artificial intelligence has increased through the class, many responded that the learning content is still difficult. The teacher's diary mainly included information about the latest trends in the industry that informatics and computer teachers should not miss out on. We hope that this study will provide an opportunity to meet the needs of the industry by increasing the proportion of artificial intelligence programming in industrial specialized high schools.

• Journal of the Korea Concrete Institute
• /
• v.13 no.2
• /
• pp.175-183
• /
• 2001

Immersion tests with artificial seawater were carried out to investigate the resistance to seawater attack of 5 types of cement matrices. From the results of compressive strength and length change, it was found that blended cement mortars due to mineral admixtures, were superior to portland cement mortars with respect to the resistance to seawater attack. Moreover, XRD analysis indicated that the peak intensity ratio of low heat portland cement(LHC) paste, in portland cement pastes, had better results, and so did that of blended cement Paste. Pore volume of pastes by mercury intrusion porosimetry method demonstrated that total pore volume of ordinary portland cement(OPC) paste had a remarkable increase comparing with that of other pastes. In case of immersion of artificial seawater, the use of ground granulated blast-furnace slag and fly ash, however, showed the beneficial effects of 56% and 32% in reduction of total pore volume, respectively.

• Korean Journal of Poultry Science
• /
• v.30 no.2
• /
• pp.91-94
• /
• 2003

Artificial insemination of cryopreserved semen is not practiced in broiler breeder industry although its benefit has been recognized for years. Thus, the present study explored the possibility of artificial insemination with cryopreserved semen in Ross broiler breeders. Sixty Ross female broiler breeders were artificially inseminated either with fresh or with cryopreserved semen pooled from five male Ross broiler breeders. On.e hundred eighty eggs were collected from each semen treatment and hatched. Fertility and hatchability of fertilized eggs collected from hens artificially inseminated with cryopreserved semen were 68.0 and 47.1％, respectively, compared to 88.3 and 87.2％ with fresh semen. Both unfertilized eggs and dead embryos during hatch were significantly (P<0.05) higher in the cryopreserved semen­treated group by approximately 2.7­ and 3.2­fold than the fresh semen­treated counterparts. the moderately low fertility and markedly low hatchability of fertilized eggs obtained from cryopreserved semen observed in this study may be of practical interests in broiler breeder industry and deserves further study.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.25 no.6
• /
• pp.1-11
• /
• 2021

To develop an efficient procedure related to the flamelet library, the machine learning process based on artificial neural network(ANN) is applied for the gaseous hydrogen/liquid oxygen combustor under a supercritical pressure condition. For hidden layers, 25 combinations based on Rectified Linear Unit(ReLU) and hyperbolic tangent are adopted to find an optimum architecture in terms of the computational efficiency and the training performance. For activation functions, the hyperbolic tangent is proper to get the high learning performance for accurate properties. A transformation learning data is proposed to improve the training performance. When the optimal node is arranged for the 4 hidden layers, it is found to be the most efficient in terms of training performance and computational cost. Compared to the interpolation procedure, the ANN procedure reduces computational time and system memory by 37% and 99.98%, respectively.