• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.1215-1217
• /
• 2023

가정에서 대형 폐기물을 배출하고 수거하는 과정에서 폐기물을 수동적으로 분류를 하는 것은 시간이 많이 소요되는 작업이다. 본 논문에서는 YOLOv4, 5, 7 모델을 비교하여 실생활에 사용가능한 대형 폐기물 탐지에 가장 적합한 모델을 찾는다. 이미지 증강 전 결과는 YOLOv7이 가장 좋은 성능을 보였다. 배출자가 촬영하는 각도나 위치, 시간 등의 변수를 고려하고자 증강을 시도하였고 증강 후 탐지 결과도 YOLOv7이 F1-score 93 %, mAP 96.6% 로 다른 모델보다 전체적으로 더 좋은 성능을 보였다.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.236-241
• /
• 2024

Due to the recent emphasis on carbon neutrality and environmental regulations, the global electric vehicle (EV) market is experiencing rapid growth. This surge has raised concerns about the recycling and disposal methods for EV batteries. Unlike traditional internal combustion engine vehicles, EVs require unique and safe methods for the recovery and disposal of their batteries. In this process, predicting the lifespan of the battery is essential. Impedance and State of Charge (SOC) analysis are commonly used methods for this purpose. However, predicting the lifespan of batteries with complex chemical characteristics through electrical measurements presents significant challenges. To enhance the accuracy and precision of existing measurement methods, this paper proposes using a Long Short-Term Memory (LSTM) model, a type of deep learning-based recurrent neural network, to diagnose battery performance. The goal is to achieve safe classification through this model. The designed structure was evaluated, yielding results with a Mean Absolute Error (MAE) of 0.8451, a Root Mean Square Error (RMSE) of 1.3448, and an accuracy of 0.984, demonstrating excellent performance.

• Journal of the Korea Organic Resources Recycling Association
• /
• v.9 no.4
• /
• pp.117-124
• /
• 2001

This study was executed for utilizing it as basic data in appropriate recycling way and design by examining and analyzing various characteristics of food waste which is being discharged from various restaurant and apartment house. In general, there were differences in restaurants classification and Japanese restaurant showed big differences as compared to other restaurants. Vegetable had the highest composition and its contents had big difference according to seasons. In alien substances, oyster shells were the highest and restaurants showed high rate of alien substances than apartments, therefore it was required to divide them in advance. Salinity was the highest in Japanese restaurants and most restaurants had rate of up to 1%, so it was not appropriate for recycling. However, it was considered that if there is cleaning operation in the whole process, there might not be a problem. Feed Ingredient had 28% of fiber, 25% of protein, and 11% of fats. We analyzed noxious germs and heavy metal too. However microorganisms of etiological cause were not detected and each harmful material showed less values of control concentration. In the result of analysis of each characteristic, it is required to consider collection rate from restaurants and apartments and seasonal cause into design regarding recycling. And apartments are compatible to compost than feed and food waste from Chinese, flour restaurant and collective feeding facilities are compatible for feed, as it is evaluated.

• Journal of the Korean Geotechnical Society
• /
• v.30 no.3
• /
• pp.47-58
• /
• 2014

To investigate the unsaturated characteristics of the tailings obtained from the waste dump at Imgi mine, matric suction and volumetric water content were measured in both drying and wetting processes using Automated Soil-Water Characteristics Curve Apparatus. Based on the measured result, Soil Water Characteristic Curves (SWCC) were estimated by van Genuchten model. According to the unsaturated soil classification method, the tailings of the waste dump correspond to clayey sand. As a result of Suction Stress Characteristic Curve (SSCC) by Lu and Likos model, SSCC has a shape of S which is similar to SWCC. The hysteresis phenomenon occurred in SSCCs, which means the suction stress of drying path is larger than that of wetting path in the same effective degree of saturation. The effective stress of unsaturated soil is equal to that of saturated soil when matric suction is less than Air Entry Value (AEV). However, the effective stress of unsaturated soil is larger than that of saturated soil when matic suction is more than AEV. Meanwhile, unsaturated hydraulic conductivity by van Genuchten model decreased with increasing matric suction, and the hydraulic conductivity of drying path is larger than that of wetting path.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.8 no.2
• /
• pp.227-234
• /
• 2020

Under consideration of construction waste recycling, candidate secondary products applicable for the civil and construction areas can be reliably employed based on the recycling cost analysis. For the validation purpose, probability-based cost analyses were performed to estimate recycling cost profit considering uncertainties. When recycling construction wastes, the costs at each stage are fully dependent on target products to be adopted. To achieve commercialization of each product, its quality has to be improved with economic efficiency through accurate evaluation of input costs. Based on the probabilistic recycling cost analysis, the cost benefit for target products was estimated with waste classification cost, transportation cost to recycling treatment facilities and production cost. All necessary information on the cost analysis were collected from literature, disclosure, and existing recycling companies. In addition, a cost difference between recycled and non-recycled events was made. As a result, a probability-based recycling cost estimate for candidate secondary products was herein presented.

• Journal of Korean Society of Environmental Engineers
• /
• v.30 no.11
• /
• pp.1102-1110
• /
• 2008

This research was performed to analyze the characteristics of wood wastes from origin and to suggest grade-classification for them. Korean proximate analysis was conducted, and heating value, heavy metals and Cl concentrations were analyzed for gradeclassification. Wood wastes were sampled from forest, living, construction and demolition, and industrial areas with origin. Moisture content of most wood wastes was ranged in 5$\sim$10%. VS (volatile solids) and ash contents of them showed > 95% and < 5%, respectively. Most wood wastes except wood for growing mushroom permitted the standard (low heating value $\geq$ 3,500 kcal/kg) for refusederived fuel. CCA (Cr, Cu, As) concentration of wood wastes used in bench, wasted fishing boat, and railroad crosstie was higher than that of the other ones. Cl content showed approximately 1.3% in wood box for fish and $\leq$ 0.2% in the other wood wastes. Cl content of all wood wasted used in this research permitted the standard (Cl $\leq$ 0.2%, dry weight basis) for refuse-derived fuel. If the wood wastes were classified in 3-grade, plywoods would be in 2nd grade, and MDF (medium density fiber), wooden bench, painted electric wire drum, wasted fishing boat, and railroad crosstie be in 3rd grade.

• Resources Recycling
• /
• v.26 no.2
• /
• pp.46-55
• /
• 2017

In this study, the design methodology of Radial Basis Function Neural Networks is developed with the aid of Laser Induced Breakdown Spectroscopy and also applied to the practical plastics sorting system. To identify black plastics such as ABS, PP, and PS, RBFNNs classifier as a kind of intelligent algorithms is designed. The dimensionality of the obtained input variables are reduced by using PCA and divided into several groups by using K-means clustering which is a kind of clustering techniques. The entire data is split into training data and test data according to the ratio of 4:1. The 5-fold cross validation method is used to evaluate the performance as well as reliability of the proposed classifier. In case of input variables and clusters equal to 5 respectively, the classification performance of the proposed classifier is obtained as 96.78%. Also, the proposed classifier showed superiority in the viewpoint of classification performance where compared to other classifiers.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.365-368
• /
• 2021

In this study, a plastic bottle recycling bin system that utilizes an infrared sensor was implemented. The proposed system consists of a recognition unit, a control unit, an alarm unit, and a driving unit. The recognition unit detects the plastic bottle, measures the distance between the plastic bottle and the infrared sensor, extracts the value of the bottle, compares the extracted value with a standard range, and then transmits the control value to the control unit if the extracted value of the bottle is outside the standard range. In this case, the result of the presence or absence of a brand label or bottle cap is transmitted to the controller. The control unit opens the entrance of the recycling bin or alerts the alarm unit according to the result value transmitted from the sensor unit. In order to implement the proposed system, the recognition unit was implemented with an infrared sensor, and the control unit was made with an Arduino IDE controller, based on the C programming language. Additionally, the recognition unit and the control unit are able to communicate using analog signals. The proposed system accurately judges the presence or absence of a brand label and bottle cap of plastic bottles according to a predetermined algorithm. It then blocks the entrance of the recycling bin when a brand label or bottle cap is still attached. As the amount of waste discharged per person is relatively high and the majority of such waste is incinerated rather than recycled, the system proposed in this study is expected to increase the recycling rate of plastic bottles.

• Resources Recycling
• /
• v.18 no.4
• /
• pp.70-81
• /
• 2009

The patents were searched to investigate the trend and the direction of technologies about the recycling of WEEE (waste electric and electronic equipment). Database was collected from WIPS site, and then 223 patents were selected by investigating abstracts. The patents from 1986 to 2007 were analyzed according to countries, international patent classification (IPC), companies, technologies, and recycling-target materials. The most patents were applied in Japan and by Japan companies. Patents about physical pretreatment technology are the most among the patents of the WEEE recycling technologies. Patents about printed circuit boards among target materials are the most because of its high value-added.

• Resources Recycling
• /
• v.14 no.6 s.68
• /
• pp.44-59
• /
• 2005

In this paper the world wide patents on the recycling of used batteries were inspected. The trend and direction of on-going and future technologies on this matter were analyzed. The range of search was limited in the open patents and in DB of U.S.A.(USPTO, DLPHION), Japan(PAJ), Europe(EPO), and Korea(KIPRIS). For the search condition the keyword, battery, batteries, electric cell, patent, and recycling, and IPC classification were used. The total of 2,490 cases was found at the first search stage, then, through the 2 steps of filtering processes the total of 871 cases was selected for the final analysis. These 871 cases were classified by countries, companies, and technologies between the year 1971 and the you 2000.