• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.152-159
• /
• 2024

Cracks in structural materials present a critical challenge to infrastructure safety and long-term durability. Timely and precise crack detection is essential for proactive maintenance and the prevention of catastrophic structural failures. This study introduces an innovative approach to tackle this issue using U-Net deep learning architecture. The primary objective of the intended research is to explore the potential of U-Net in enhancing the precision and efficiency of crack detection across various concrete crack detection under various environmental conditions. Commencing with the assembling by a comprehensive dataset featuring diverse images of concrete cracks, optimizing crack visibility and facilitating feature extraction through advanced image processing techniques. A wide range of concrete crack images were collected and used advanced techniques to enhance their visibility. The U-Net model, well recognized for its proficiency in image segmentation tasks, is implemented to achieve precise segmentation and localization of concrete cracks. In terms of accuracy, our research attests to a substantial advancement in automated of 95% across all tested concrete materials, surpassing traditional manual inspection methods. The accuracy extends to detecting cracks of varying sizes, orientations, and challenging lighting conditions, underlining the systems robustness and reliability. The reliability of the proposed model is measured using performance metrics such as, precision(93%), Recall(96%), and F1-score(94%). For validation, the model was tested on a different set of data and confirmed an accuracy of 94%. The results shows that the system consistently performs well, even with different concrete types and lighting conditions. With real-time monitoring capabilities, the system ensures the prompt detection of cracks as they emerge, holding significant potential for reducing risks associated with structural damage and achieving substantial cost savings.

• Journal of the Korean Solar Energy Society
• /
• v.30 no.1
• /
• pp.25-33
• /
• 2010

Use of daylight in underground space interacts with physiological need for human beings and provides relief from feeling secluded. Light pipe system can deliver natural light into the space where it is needed and can be used as primary or a secondary light source with benefits of energy, productivity and health. To use light pipe system effectively under various conditions, it is important to investigate the effectiveness of light pipe system with reliable monitoring protocol. This paper presents the results of light pipe system performance used in underground parking lot under different sky conditions. Comparisons were made between the illuminance standards of underground parking lot and the monitored data. The results indicated that adequate illuminance level was shown until 4.5m distance from the light pipe under clear sky condition. However, additional lighting device showed be used under overcast sky to meet the proper illuminance level.

• Korean Journal of Poultry Science
• /
• v.36 no.4
• /
• pp.329-335
• /
• 2009

The aim of the present study was to investigate the behavior and performance of male and female broiler chickens reared under three different colors of light (white, blue and red) in a 23L:1D of lighting program. Day-old broiler chicks were obtained and assigned to six pens (16 males and 16 females per pen). Two pens each were located in three different rooms in an environmentally controlled shed and received the different light colors. All birds received same husbandry conditions. After a 3-day adaptation to the light color, behavior observations (pecking, resting, standing and walking) were made on six focal birds per pen, representing the sex ratio, by direct visual scans for 120 minutes daily for five days a week throughout the 5-week study. Body weights and feed intake were recorded at weekly intervals. On days 19 and 33, welfare indicators (tonic immobility reaction on the 19 and 33 days old; gait scores, foot pad and hock burns scores on 33 days old) were determined. Light color had no significant effect (P>0.05) on the weight gain and feed intake of broilers, but significantly (P<0.05) influenced the feed conversion ratio. Birds receiving the blue light were more (P<0.05) efficient than those receiving white and red lights. Resting was observed to be the major behavior pattern, irrespective of sex or light color. During early growth, resting behavior tended to be lower in birds receiving red light. However, standing and walking behaviors tended to be higher in birds receiving red light in 4 to 18 day-old age and all of experimental periods, respectively. These data indicate that light color can influence broiler performance and behavior.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.237-250
• /
• 2022

Structural health monitoring (SHM) plays an important role in ensuring the safety and functionality of critical civil infrastructure. In recent years, numerous researchers have conducted studies to develop computer vision and machine learning techniques for SHM purposes, offering the potential to reduce the laborious nature and improve the effectiveness of field inspections. However, high-quality vision data from various types of damaged structures is relatively difficult to obtain, because of the rare occurrence of damaged structures. The lack of data is particularly acute for fatigue crack in steel bridge girder. As a result, the lack of data for training purposes is one of the main issues that hinders wider application of these powerful techniques for SHM. To address this problem, the use of synthetic data is proposed in this article to augment real-world datasets used for training neural networks that can identify fatigue cracks in steel structures. First, random textures representing the surface of steel structures with fatigue cracks are created and mapped onto a 3D graphics model. Subsequently, this model is used to generate synthetic images for various lighting conditions and camera angles. A fully convolutional network is then trained for two cases: (1) using only real-word data, and (2) using both synthetic and real-word data. By employing synthetic data augmentation in the training process, the crack identification performance of the neural network for the test dataset is seen to improve from 35% to 40% and 49% to 62% for intersection over union (IoU) and precision, respectively, demonstrating the efficacy of the proposed approach.

• Asian-Australasian Journal of Animal Sciences
• /
• v.25 no.5
• /
• pp.738-748
• /
• 2012

One of the main goals of small, medium and large farms is to improve the reproductive performance of rabbit does. Stocks of lower productivity can be improved by crossing with intensive breeds. A better nutritional status of both foetuses and suckling kits has a positive effect on their later productivity. Overfeeding young females before first mating can lead to conditions of fattiness. Using restricted feeding or higher fibre content in the feed and changing it for a higher level ad libitum feeding about one week prior to first mating leads to longer lifespan and higher productive level. Intensive reproductive rhythm creates a negative energy balance in does : they are unable to consume enough feed (energy) for the nutritional requirements of foetus and lactation, and therefore lose most of their fat reserves. Furthermore, primiparous does also expend energy because they are still growing. Under intensive conditions, the 42-d reproductive rhythm (re-mating 11 days after parturition) is recommended. Under extensive conditions, the 18 or 25-d mating interval with 35 to 42-d weaning could be suitable. On small farms, natural mating is favoured; on large farms AI is commonly employed. The main advantage of AI is the all-in, all-out system. Hormonal (PMSG) treatment is used with AI to increase receptivity on d 11. Frequent and high level PMSG use can lead to higher anti-PMSG antibody rates. Lower level (max. 20 IU) and less frequent PMSG injection or non-hormonal alternative methods (short dam-litter separation, changing nursing method or lighting programs) are recommended for this reason.

• Physical Therapy Rehabilitation Science
• /
• v.4 no.1
• /
• pp.32-37
• /
• 2015

Objective: This study was conducted to test the effects of mobile texting and gaming on gait with obstructions under different illumination levels. Design: Cross-sectional study. Methods: Twelve healthy adults aged 20 to 36 years (mean 23.5 years) were tested under six different conditions. All participants used touchscreen smartphones. Testing conditions included: 1) Walking with an obstruction under a bright illumination level; 2) walking with an obstruction with a low level of illumination; 3) walking with an obstruction while texting under a bright illumination level; 4) walking with an obstruction while texting with a low level of illumination; 5) walking with an obstruction while gaming under a bright illumination level; and 6) walking with an obstruction while gaming with a low level of illumination. All participants were asked to text the Korean national anthem by their own phone and play Temple Run 2 using an iPhone 5. Gait variances were measured over a distance of 3 m, and the mean value after three trials was used. A gait analyzer was used to measure the data. Results: Compared to normal gait with obstruction, gait speed, step length, stride length, step time, stride time, cadence while texting and gaming showed significant differences (p<0.05). Differences between the illumination levels included gait speed, step length, stride length, and step time (p<0.05) with no significant differences in stride time and cadence. Conclusions: Dual-tasking using a smartphone under low levels of illumination lowers the quality of gait with obstructions.

• Asian-Australasian Journal of Animal Sciences
• /
• v.31 no.1
• /
• pp.149-156
• /
• 2018

Objective: Broilers show clear preference towards red color light (RL). However setting of an optimum light intensity is difficult since dim intensities that favor growth reduce welfare. This experiment was conducted to test the most effective RL intensity regimen (Dim [5 lux; DI] vs high [320 lux; HI]) in combination applied at different growth stages that favors for both performance and welfare. Methods: Complete randomize design was adopted with 6 replicates. Treatments were; T1 = early DI (8-21 d)+latter HI (22-35 d); T2 = early DI (8-28 d)+latter HI (29-35 d), T3 = early HI (8-21 d)+latter DI (22-35 d), T4 = early HI (8-28 d)+latter DI (29-35 d) and T5 = control (white light; WT) (8-35 d) at medium intensity (20 lux). Body weight (BW), weight gain (WG), water/feed intake and ratio, feed conversion ratios (FCR) were assessed. Common behaviours (15) were recorded by scan sampling method. Lameness, foot pad dermatitis, breast blisters, hock burning damage were assessed as welfare parameters. Fear reactions were tested using Tonic Immobility Test. Ocular and carcass evaluations were done. Meat and tibiae were analyzed for fat and bone ash respectively. Results: On 35 d, the highest BW ($2,155.72{\pm}176g$), WG ($1,967.78{\pm}174g$) were recorded by T2 compared to WT ($BW_{WT}=1,878.22{\pm}155$, $WG_{WT}=1,691.83{\pm}160$). But, application of RL, either DI, or HI during early/latter stage had no significant effect on FCR. Under HI, birds showed much higher active behaviours. DI encourages eating. Though LI changed from DI to HI, same trend could be seen even under HI. The highest leg strength ($218.5{\pm}120s$) was recorded by T2. The lowest leg strength ($64.58{\pm}33s$) and the highest ocular weight ($2.48{\pm}1g$) were recorded by T1. Significantly (p<0.05) the highest skin weight ($162.17{\pm}6g$) but the lowest fat% in meat ($13.03%{\pm}5%$) was recorded by T2. Conclusion: Early exposure to DI-RL up to 28 days followed by exposure to HI-RL is the most favorable lighting regimen for optimizing production, better welfare of broilers and improving health benefits of meat.

• Korean Journal of Poultry Science
• /
• v.49 no.3
• /
• pp.139-144
• /
• 2022

This study was conducted to investigate the effect of three different photoperiods on growth performance, blood properties, and stress indicators in broiler chicks between 1-7 days after hatching. Two hundred and fifty-two 1-day-old male broiler chicks (57.0±0.12 g) were divided into three treatments, with 4 replicates per treatment and 22 birds per replicate subjected to three different photoperiods of 24L, 22L/2D and 18L/6D. A light-emitting diode bulb served as the light source, with an illuminance of 30 lx. As an experimental diet, a commercial feed based on a corn-soybean meal, with 22% CP and 3,150 kcal/kg ME diet, and water were fed ad libitum. Body weight gain, feed conversion ratio, and liver weight ratio showed a statistically significant difference between the 18L/6D and 24L treatments (P<0.05), but with no significant difference between the 22L/2D treatment and either the 24L or 18L/6D treatment. The breast meat ratio was 5.59% in the 18L/6D treatment group, which was lower than that of other treatment groups (P<0.05). The triglyceride levels were highest (P<0.05) in the 18L/6D treatment among treatments, but alanine aminotransferase levels were significantly higher (P<0.05) in the 22L/2D treatment than in the 24L treatment. Levels of cytokines, i.e., Interleukin-6 and Tumor Necrosis Factor-α did not show a significant difference among the treatments, but corticosterone content was significantly higher (P<0.05) in the 24L treatment than in the 18L/6D treatment. In conclusion, 22 hours of lighting is appropriate between 1~7 days after hatching, considering growth performance and the overall health of broiler chicks.