• The Journal of Korea Robotics Society
• /
• v.19 no.1
• /
• pp.79-91
• /
• 2024

Large warehouses are building automation systems to increase efficiency. However, small warehouses, military bases, and local stores are unable to introduce automated logistics systems due to lack of space and budget, and are handling tasks manually, failing to improve efficiency. To solve this problem, this study designed small loading and unloading equipment that can be mounted on transportation vehicles. The equipment can be controlled remotely and is automatically controlled from the point where pallets loaded with cargo are visible using real-time video from an attached camera. Cargo recognition and control command generation for automatic control are achieved through a newly designed deep learning model. This model is designed to be optimized for loading and unloading equipment and mission environments based on the YOLOv3 structure. The trained model recognized 10 types of palettes with different shapes and colors with an average accuracy of 100% and estimated the state with an accuracy of 99.47%. In addition, control commands were created to insert forks into pallets without failure in 14 scenarios assuming actual loading and unloading situations.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.55 no.6
• /
• pp.946-953
• /
• 2022

Using the management strategy evaluation methods and data on the Korea chub mackerel Scomber japonicus where the state-space logistic production model is used as the operation and the estimation model respectivley, we examined the effects of both Dorn's rule, α and the buffer value for ABC (allowable biological catch), which are used by the Korea fishery managers for decision rules. We set scenarios that have different pairs of buffer and α values, which include those currently used in the management in Korea. Under each sceanario, we projected the fish population biomass until year 2050, during which ABC is determined in each year with the decision rule. We used three kinds of performance measures: (i) whether the biomass in 2050 is overfished; (ii) the average of annual yields over the simulation period; and (iii) the variability of annual yields over the period. We found that the current practice (buffer=0.9, and α = 0.05) resulted in the best performance in terms of avoiding the "overfished" status. However, the current practice failed to reach the maximum average of the annual yields and led to larger uncertainty in the annual yields.

• International Journal of Computer Science & Network Security
• /
• v.21 no.8
• /
• pp.288-296
• /
• 2021

Automated face recognition in a runtime environment is gaining more and more important in the fields of surveillance and urban security. This is a difficult task keeping in mind the constantly volatile image landscape with varying features and attributes. For a system to be beneficial in industrial settings, it is pertinent that its efficiency isn't compromised when running on roads, intersections, and busy streets. However, recognition in such uncontrolled circumstances is a major problem in real-life applications. In this paper, the main problem of face recognition in which full face is not visible (Occlusion). This is a common occurrence as any person can change his features by wearing a scarf, sunglass or by merely growing a mustache or beard. Such types of discrepancies in facial appearance are frequently stumbled upon in an uncontrolled circumstance and possibly will be a reason to the security systems which are based upon face recognition. These types of variations are very common in a real-life environment. It has been analyzed that it has been studied less in literature but now researchers have a major focus on this type of variation. Existing state-of-the-art techniques suffer from several limitations. Most significant amongst them are low level of usability and poor response time in case of any calamity. In this paper, an improved face recognition system is developed to solve the problem of occlusion known as FRS-OCC. To build the FRS-OCC system, the color and texture features are used and then an incremental learning algorithm (Learn++) to select more informative features. Afterward, the trained stack-based autoencoder (SAE) deep learning algorithm is used to recognize a human face. Overall, the FRS-OCC system is used to introduce such algorithms which enhance the response time to guarantee a benchmark quality of service in any situation. To test and evaluate the performance of the proposed FRS-OCC system, the AR face dataset is utilized. On average, the FRS-OCC system is outperformed and achieved SE of 98.82%, SP of 98.49%, AC of 98.76% and AUC of 0.9995 compared to other state-of-the-art methods. The obtained results indicate that the FRS-OCC system can be used in any surveillance application.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.32 no.6C
• /
• pp.267-274
• /
• 2012

The conventional approach to evaluate the contaminant transport in soils adopts the macro-scale implementation while the pore configuration and network is a dominant factor to determine the fate of contaminant. However, the observation of fate and transport at pore scale may not be readily approachable because of the computational expenses to solve Navier-Stokes equation. We herein present the 2D Lattice-Boltzmann method that enables to assess the local fluid velocity and density efficiently for the case of single phase and multi-components. The solute fate spatio-temperal space is explicitly determined by the advection of fluid flow. Two different types of idealized pore space provides the path of fluid. Also, solute transport, the velocity field and average concentration of solute are computed in steady state. Results show that the pore geometry such as tortuosity mainly affect the solute fate. It highlights the significance of the pore configuration and shape in granular soils and rock discontinuity in spite of the equivalent porosity.

• Journal of Oral Medicine and Pain
• /
• v.14 no.1
• /
• pp.57-66
• /
• 1989

66 patients with temporomandibular disorders were selected for experimental group, and 45 normal subjects who were Dental students were selected for control group. Average age of experimental group was 30.5 years, Male to Female ratio was 2 : 3, and their age distribution were teen-ages to seventh decades. Transcranial radiography (TR) with Denar Accurad 100 was used for each group to get the values of width in joint spaces and to investigate the bony changes of articular surfaces and relative condylar position to articular fossa. In addition to TR, clinical interview and routine charting about amount of mandibular movements and occlusal variations were carried out in experimental group. The obtained results were as follows : 1. The mean values of joint space with in control group were 2.15mm to anterior, 2.98mm to superior and 2.29mm to posterior and the value of relative condylar position to the deepest portion of articular fossa was 0.21mm to anterior. In experimental group, those values were 2.01mm, 2.14mm 2.22mm and 0.12mm to posterior in sequence, respectively. Joint spaces in experimental group, therefore, were inclined to decreased, and relative condylar position was inclined to retrude. Joint space in control group showed symmetric condylar position, but in experimental group showed asymmetry. 2. Non-affected joints with no bony changes in experimental group showed the narrowest joint spaces which were thought to manifest the abnormal stress to non-affected side to dysfunctional state of contralateral affected joints. 3. Amount of mandibular movements in experimental group were within normal values in lateral movements and in protrusive movement but in opening movement with or without passive stretch, those were lower than normal values. Frequency of occlusal variation, for example, protrusive posterior contacts, open bite, median line shift to lateral side were inclined to increase with bony changes and with crepitus.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.4 no.4
• /
• pp.343-353
• /
• 2002

In the past many tunnels have been built to lowest capital investment cost without adequate regard for the cost of operation. But according to increasing the capacity of a ventilation system and to becoming diverse, it is to become more important to come up with the optimal operation stage of ventilation system. In this study, the tunnel ventilation dynamic simulation program had been developed. it is used to calculate the unsteady-state tunnel air velocity and concentration of pollutants according to the assumed average day traffic profile and summarize the energy consumption for the operation of ventilation system. And the operation energy consumption for the electric precipitation system and vertical vent shaft system are evaluated and compared in various operation mode. As the results of this study, the optimal operation stage for these ventilation system are provided.

• The Journal of the Korea Contents Association
• /
• v.11 no.11
• /
• pp.482-491
• /
• 2011

Pavilion(樓亭) was a Building for rest and scene appreciation in chosun dynasty. This research was to analyze construction method and the structure of Pavilion. The detail objectives of the research was ; First, the location of Pavilion and the layout of facilities were analyzed and composition principle was found. Second, Pavilion were analyzed about dimension, form, constructive method, and structure. Pavilion location was selected on the consideration of natural condition such as configuration of the ground, climate, and scene state. The Length of Building remained until present was about 8~12m, the depth was about average 3~4m. The results of these study can give deep understand of physical structure and help to reconstruct future Pavilion.

• Korean Journal of Ecology and Environment
• /
• v.36 no.2 s.103
• /
• pp.172-180
• /
• 2003

For a biological assessment of Pyeongtaek Reservoir and its major influent streams, an algal growth potential test (AGPT) was conducted with the blue-green algae Microcystis aeruginosa in March, June, September and December, 2000. The range and average value of AGPT were from 0 to 463 mg dw/l and 90 mg dw/l, respectively. For the influent streams in particular, the average of AGPT was the in the Hwangguchi Stream (343 mg dw/l). It decreased to 158, 66, 29, 21, and 21 mg dw/l in the Sojong Stream, Songhwan Stream, Osan Stream, Chinwi Stream, and Ansong Stream, respectively. The AGPT values in the reservoir ranged from 0 to 138 mg dw/1(mean 54 mg dw/1) with a tendency to increase in the upstream, which was close to the influent streams. In general, the AGPT values decreased further in the downstream. Immediately after the abrupt increase in influent discharge in summer, the AGPT value in the downstream almost doubled due to the proliferation of blue-green algae. The water quality of Pyeongtaek Reservoir and its influent streams further deteriorated during the drought period. Similarly, the AGPT value was the highest during this period. The AGPT values showed the closest correlation with the content of P (r = 0.999, p<0,001). Thus, it could be concluded that the content of P is highly effective in the growth of algae. In the Pyeongtaek Reservoir Watershed, the AGPT values varied in space and time. It was also closely related to the nutrient content of influent streams. The AGPT values revealed that the water quality state was hypertrophic (> 20 mg dw/1). Thus, control of the aquatic environment is essential. AGPT is very useful in evaluating the fertility and pollution state of the water as well as determining the nutrients that limit the growth of algae.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.6
• /
• pp.81-89
• /
• 2004

In this paper, we compare face recognition rate by PCA algorithm using distance change and embedded data being input left side and right side image in stereo images. The proposed method detects face region from RGB color space to YCbCr color space. Also, The extracted face image's scale up/down according to distance change and extracts more robust face region. The proposed method through an experiment could establish standard distance (100cm) in distance about 30∼200cm, and get 99.05% (100cm) as an average recognition result by scale change. The definition of super state is specification region in normalized size (92${\times}$112), and the embedded data extracts the inner factor of defined super state, achieved face recognition through PCA algorithm. The orignal images can receive specification data in limited image's size (92${\times}$112) because embedded data to do learning not that do all learning, in image of 92${\times}$112 size averagely 99.05%, shows face recognition rate of test 1 99.05%, test 2 98.93%, test 3 98.54%, test 4 97.85%. Therefore, the proposed method through an experiment showed that if apply distance change rate could get high recognition rate, and the processing speed improved as well as reduce face information.

• Asia Marketing Journal
• /
• v.9 no.2
• /
• pp.97-129
• /
• 2007

The critical link between consumer-based internet ordering and the delivery of the product to the consumer is a key success factor in online shopping. Market areas of online shopping company implies the range of space where products ordered from online shopping can be physically delivered to customers distributed over space with reasonable shipping cost and lead time through the physical distribution network. The average rate of growth in online shopping is 36% per year in Korea for the last 5 years. But there are no maps available that describe sales/delivery density of online shopping, few researches are focused on the short-term/long-term adaptation to demand increase by online shopping. In this paper (1) Maps of trade area are described indicating the sales/delivery density around the nation. (2) Empirical researches suggested that short-term adaptation to demand increase resulted in price reduction and service in enhancement of service quality in local transportation. But the long-term adaptation on the parts of parcel delivery industry are to be investigated in future researches.