PURPOSES : This study is to evaluate environmental improvement effects of underground road project, as a case study of ‘Seobu’underground expressway project in Korea. METHODS : The environmental improvement effects of underground road construction were classified into tree sector in this study – air quality, noise, and thermal environment. To evaluate these effects, this study collected and divided environment dataset into before, during, and after ‘Seobu’underground expressway construction, and compared the change of values with entire city. In addition, the quantification method of environmental improvement effects was suggested based on the literature review. RESULTS : The result of this study indicates that there exist significant improvement effects of urban environment after the construction of ‘Seobu’underground expressway. Specifically, the concentration of particulate matters (PM10) and daytime/nighttime noise, and land surface temperature (LST) were improved along the expressway. In addition, the overall environmental benefit of ‘Seobu’ underground expressway was estimated to 1.15 billion won per year. CONCLUSIONS : To promote systematic and consistent underground road project, it is required to establish legislative system for evalauting and supporting urban improvement effects.

Currently, there is no definitive regulation for the appropriate frequency of data sampling in water distribution networks, yet it plays a crucial role in the efficient operation of these systems. This study proposes a new methodology for determining the optimal frequency of data acquisition in water distribution networks. Based on the decomposition of signals using harmonic series, this methodology has been validated using actual data from water distribution networks. By analyzing 12 types of data collected from two points, it was demonstrated that utilizing the factors and cumulative periodograms of harmonic series enables similar accuracy at lower data acquisition frequencies compared to the original signals.

폴리에틸렌 글라이콜 다이아크릴레이트 (polyethylene glycol diacrylate, PEGDA) 하이드로젤을 정삼투 (forward osmosis, FO) 분리막의 지지체로 사용하여 고성능의 FO 분리막을 제조하였다. 친수성의 PEGDA를 자외선 조사를 통한 중합 과 그에 따른 상분리를 이용하여 다공성으로 구조화하였고, 매우 높은 친수성을 가진 하이드로젤 지지체를 얻을 수 있었다. 제조된 친수성 PEGDA 지지체 위에 높은 수투과도와 염 선택도를 확보하기 위해서 일반적인 계면중합 방식이 아닌 톨루엔 을 유기 용매로 사용한 계면중합 방식(TIP)으로 선택층을 도입하였다. 제조된 PEGDA 지지체 기반 분리막은 1.0 M NaCl 유 도 용액과 증류수 유입수를 통한 FO 성능 측정에서 상용 HTI 분리막들에 비해서 매우 높은 수투과도와 낮은 염 선택도를 나 타내었다. 본 연구를 통해, 기존의 소수성 지지체를 추가적으로 개질하는 방식이 아닌 새로운 물질과 제조방식을 사용한 FO 지지체의 가능성을 제시하고자 한다.

This study was conducted to investigate the growth characteristics of domestic 'Sulhyang' strawberry (Fragaria × ananassa Duch.) seedlings and to analyze their relationships in order to develop a growth prediction model. Fresh weight, dry weight, and leaf area were measured to validate the newly developed growth model. The relative growth rate (RGR) of ‘Sulhyang’ seedlings’ dry weight was an average of 0.026 g·g-1·d-1, and it increased to 0.066 g·g-1·d-1 on the 49th day after transplanting (DAT). The relationship between DAT and RGR was represented as RGR (dry weight)(g·g- 1·d-1) = 0.0392/(1 + exp(–(DAT – 34.9940)/5.8662)). The crop growth rate (CGR) was an average of 0.060 g·m-2·d-1, and it increased to 0.211 g·m-2·d-1 on the 70th DAT. The relationship between DAT and CGR was calculated as CGR (dry weight)(g·m-2·d-1) = 0.1293/(1 + exp(–(DAT – 49.3917)/6.0928)). The relationship between shoot fresh weight (y) and shoot dry weight (x) per plant showed a linear relationship of y = 4.3189x + 0.7812 (R2 = 0.9976). Fresh weight, dry weight, and leaf area with respect to DAT and cumulative temperature increased exponentially, and sigmoid curve models were developed based on these data. The model with the highest coefficient of determination was found for the relationship between shoot dry weight (y) and cumulative temperature (x), represented as y = 14.2285/(1 + exp(–(x – 1590.1295)/377.8112)) (R2 = 0.9715). The results of this study can be utilized as valuable information for establishing a systematic management system for seedling production using strawberry cutting propagation methods. For the development of a more precise growth prediction model in the future, it is necessary to analyze and apply a wider range of growth indicators and meteorological factors related to strawberry seedlings.

This research was conducted to analyze the relationship between the induction time of runners and the growing degree days for domestic strawberry cultivars, 'Sulhyang' and 'Arihyang'. Runners were induced at 15-day intervals over five periods, starting from late April to early June, and the study compared the number of runner formations and temperature changes for each period while it also investigated the plantlet quality on the transplanting date. Based on back calculations from the transplanting date of September 18th, 'Sulhyang' required induction from late April to early May to achieve 70-day-old plantlets and from late April to mid-May for 60-day-old plantlets. On the other hand, 'Arihyang' needed induction from late April for 70-day-old plantlets and from late April to early May for 60-day-old plantlets. To secure about 20 daughter plants, the growing degree days needed to be around 1,000°C, and a delay in runner induction led to a delay in formation of daughter plants. The relationship between growing degree days and runner formation was expressed as the following quadratic equations: for 'Sulhyang,' y = 9E-06x2 + 0.0124x – 2.4806 (R2 = 0.9696), and for 'Arihyang,' y = 1E-06x2 + 0.0192x – 2.9274 (R2 = 0.9431), and these equations showed high correlations. The crown diameter on the transplanting date was thickest in mid-May for 'Sulhyang', and it tended to increase with delayed runner induction for 'Arihyang'. In conclusion, this study confirmed that the number of daughter plants and growth characteristics varied depending on strawberry cultivars and the timing of runner inducement time. The relationship equations derived through measurements of growing degree days can be used as the fundamental data for reasonable production of daughter plants in the future.

본 연구에서는 중공사형 이산화탄소 분리막 모듈을 사용하여 수소개질기 배가스로부터 이산화탄소 포집을 목적 으로 한 분리막 공정 최적화 연구를 진행하였다. 랩스케일의 소형 분리막 모듈을 사용하여 혼합기체를 대상으로 이산화탄소 순도 90% 및 회수율 90%을 달성하는 2단 공정 조건을 도출하였다. 막 면적이 정해진 모듈의 분리막 공정에서는 스테이지-컷, 주입부 및 투과부 압력에 따라서 포집 순도 및 회수율이 모두 다르게 나타나기 때문에 운전 조건에 대한 최적화가 필수적이 다. 본 연구에서는 다양한 운전 조건에서 1단 분리막에서 보이는 공정 포집 효율의 한계를 확인하고, 높은 순도와 회수율을 동시에 달성하기 위한 2단 회수 공정을 최적화하였다.

좁은가슴잎벌레는 십자화과작물을 가해하는 해충으로 알려져 있다. 본 연구는 온도가 좁은가슴잎벌레의 발육단계별 발육기간, 성충의 수 명과 산란특성에 미치는 영향을 파악하고자 성충 전 발육단계는 15, 20, 25, 27.5°C에서, 성충은 10, 15, 20, 25, 27.5°C 항온조건에서 조사하였 다. 알과 유충은 항온조건에서 다음 발육 단계로 성공적으로 발육하였다. 알, 유충, 번데기의 발육기간은 온도가 상승할수록 짧아지는 경향을 보 였다. 좁은가슴잎벌레의 발육영점온도, 유효적산온일도는 선형회귀분석을 통해 추정하였으며 알에서 성충출현까지 발육영점온도와 유효적산온 일도는 8.7°C와 344.73DD였다. 좁은가슴잎벌레 발육단계별 최저, 최고 온도의 한계는 Briere함수를 이용하여 추정하였으며 알에서 성충출현 까지 최저, 최고한계는 5.3°C와 40.4°C였다. 성충은 10°C와 27.5°C 범위에서 산란이 가능하였고 21.7°C에서 최대 약 627.5개의 알을 낳는 것 으로 추정되었다. 노화율, 나이별 생존율, 나이별 누적산란율, 온도의존 산란수와 관련된 성충모델들을 작성하였다. 본 연구에서 제시한 온도발육 모형과 성충산란모형은 좁은가슴잎벌레 개체군동태를 이해하는데 유용할 것이며 십자화과작물의 종합적 해충군관리체계를 마련하는데 기초자 료로 활용될것으로 기대된다.

Recently, there has been an increasing attempt to replace defect detection inspections in the manufacturing industry using deep learning techniques. However, obtaining substantial high-quality labeled data to enhance the performance of deep learning models entails economic and temporal constraints. As a solution for this problem, semi-supervised learning, using a limited amount of labeled data, has been gaining traction. This study assesses the effectiveness of semi-supervised learning in the defect detection process of manufacturing using the MixMatch algorithm. The MixMatch algorithm incorporates three dominant paradigms in the semi-supervised field: Consistency regularization, Entropy minimization, and Generic regularization. The performance of semi-supervised learning based on the MixMatch algorithm was compared with that of supervised learning using defect image data from the metal casting process. For the experiments, the ratio of labeled data was adjusted to 5%, 10%, 25%, and 50% of the total data. At a labeled data ratio of 5%, semi-supervised learning achieved a classification accuracy of 90.19%, outperforming supervised learning by approximately 22%p. At a 10% ratio, it surpassed supervised learning by around 8%p, achieving a 92.89% accuracy. These results demonstrate that semi-supervised learning can achieve significant outcomes even with a very limited amount of labeled data, suggesting its invaluable application in real-world research and industrial settings where labeled data is limited.

PURPOSES : This study aims to identify the thresholds at which various factors affecting traffic crashes lead to actual traffic crashes METHODS : To verify the thresholds, we created scenarios and ran simulations with a combination of factors that affect traffic crashes. Lateral offset and minimum TTC were used to evaluate whether an incident occurred. RESULTS : In the first scenario, the most significant factor affecting traffic crashes is curvature, and it was found that the smaller the curvature(200 meters or less), the greater the deviation from the lane. And in the second scenario, especially the passenger car scenario, no accidents occurred when the curvature was greater than 90 meters and the speed was 40 km/h or less. The smaller the curvature and the higher the speed, the more accidents occurred. Similarly, in the bus scenario, no accidents occurred when the curvature was 120 meters or more and the speed was 30 km/h or less. Also, accidents tended to occur when the curvature was smaller and the speed was higher. CONCLUSIONS : Through this study, we derived the thresholds of factors that influence traffic crashes. The results are expected to help design and operate roads in the future and contribute to reducing traffic crashes.

PURPOSES : This study evaluates the effectiveness of traffic flow optimization when giving safety strategy guidance to a connected autonomous vehicle (CAV) based on information received through infrastructure cooperation in a V2X environment for non-signal intersection. METHODS : To evaluate the effectiveness of safety strategy guidance based on developed traffic flow control algorithm at a non-signalized intersection, it was implemented on simulation. A scenario based on the Level of Service (LOS) and the market penetration rate(MPR) of autonomous vehicles was established. The simulation results were divided into safety, operation, and environment to evaluate the effect, and the effect of optimizing traffic flow was finally derived through the integrated evaluation score. RESULTS : As a result, when safety strategy guidance was provided, the number of conflicts and CO emissions decreased by about 29% and about 15%, improving safety and environmental performance. In the case of operation, the mean of delay time was increased overall by 1%, but in the case of MPR 50 and above, the delay time was reduced by about 38%, thereby increasing operation. Finally, the aspect of traffic flow optimization, effectiveness of safety strategy guidance was derived through the integrated evaluation score, and the average integrated evaluation score improved from MPR 20 or higher. CONCLUSIONS : Providing guidance had the effect of optimizing traffic flow at a non-signal intersection. In the future, V2X communications will provide CAV with algorithm-based guidance developed in this study to control driving behavior. it will support safe and efficient driving at non-signal intersections.

The grassland section of the greenhouse gas inventory has limitations due to a lack of review and verification of biomass compared to organic carbon in soil while grassland is considered one of the carbon storages in terrestrial ecosystems. Considering the situation at internal and external where the calculation of greenhouse gas inventory is being upgraded to a method with higher scientific accuracy, research on standards and methods for calculating carbon accumulation of grassland biomass is required. The purpose of this study was to identify international trends in the calculation method of the grassland biomass sector that meets the Tier 2 method and to conduct a review of variables applicable to the Republic of Korea. Identify the estimation methods and access levels for grassland biomass through the National Inventory Report in the United Nations Framework Convention on Climate Change and type the main implications derived from overseas cases. And, a field survey was conducted on 28 grasslands in the Republic of Korea to analyse the applicability of major issues. Four major international issues regarding grassland biomass were identified. 1) country-specific coefficients by land use; 2) calculations on woody plants; 3) loss and recovery due to wildfire; 4) amount of change by human activities. As a result of field surveys and analysis of activity data available domestically, it was found that there was a significant difference in the amount of carbon in biomass according to use type classification and climate zone-soil type classification. Therefore, in order to create an inventory of grassland biomass at the Tier 2 level, a policy and institutional system for making activity data should develop country-specific coefficients for climate zones and soil types.

In this study, we examined the effects of gamma irradiation dosage on the mycelial growth of Auricularia auriculajudae and performed analyses of fruiting body yield, growth characteristics, taste, fragrance, and mineral composition. Assessments of mycelial growth in response to gamma irradiation at different intensities revealed an enhancement in the growth of fungi exposed to irradiation at 200 Gy. Fruiting body yield was also highest at 200 Gy, followed by 800 Gy and the control group. On the basis of these observations, we subsequently applied gamma ray doses of 200 and 800 Gy to examine the effects of irradiation on fungal quality characteristics. In terms of the taste of fruiting bodies, we detected no significant differences among the control, 200 Gy, and 800 Gy groups. Contrastingly, with respect to fragrance, we found that fungi treated with 200 Gy were characterized by a pattern that differed from those of the control and other treatment groups. Furthermore, whereas we detected no significant difference among treatments with respect total dietary fiber content, calcium content was found to be higher in the treatment groups compared with the control group, with the highest content being measured in fungi exposed to 800 Gy irradiation. Copper content was confirmed to be higher in the control group, whereas there were no significant differences between the fungi irradiated with 200 and 800 Gy. Contrastingly, the highest levels of zinc were detected in response to 200 Gy irradiation, followed by 800 Gy. Collectively, our findings thus indicate that gamma irradiation can contribute to promoting increases in the fruiting body yield and mineral contents of mushrooms.

This experiment investigated the effects of feed additives of Sasa quelpaertensis Nakai (SQN) extract on Landrace pigs on economic traits such as the quality, physiological characteristics, and productivity. Sixteen pigs with an average age of 154 days were selected as experimental subjects. The experiment was conducted by dividing the group into eight pigs for the supplementation group, feeding with SQN extract, and another eight for the control group feeding without SQN extract. Water was fed ad libitum. On the 30th day, there was no significant difference between meat quality and productivity. However, the glucose and thyroxine were statistically lower with the supplementation group than with the control group (p<0.05). Also, the levels of creatinine difference between 1.18 ± 0.12 ㎎/㎗ with the supplementation group and 0.70 ± 0.06 ㎎/㎗ with the control group (p<0.05). However, all serum biochemistry values were within a normal range, with no health problems. The present study will help solve the problem of reducing the diversity of plant species in Halla Mountain by increasing the availability of the SQN as a pig feed additive.

PURPOSES : The wedge-type anchorage system requires a complex analysis of not only the tensile stress of the CFRP plate, but also the compressive stress and shear stress generated by the wedge action. The purpose of this study is to find a composite material failure theory that is suitable for analyzing the behavior of wedge-type anchorage system among various failure theories. METHODS : In this study, numerical analysis of various composite material failure theories was performed to analyze the anchorage strength and failure mode of the wedge-type anchorage system according to each failure theory, and compared with actual test results to determine the composite material failure theory most suitable for analyzing the behavior of a wedge-type anchorage system. RESULTS : Since the Maximum Stress failure theory shows similar results to the actual test in terms of failure mode and anchorage strength, there is no significant problem in applying it to the wedge-type anchorage system. However, it is judged to be difficult to apply under property conditions where interactions between stresses are highlighted. The Tsai-Hill and Tsai-Wu failure theories are considered unsuitable for application to wedge-type anchorage systems because the wedge angle conditions at which the most advantageous anchorage strength occurs are significantly different from other theories and the fracture type cannot be predicted. The Hashin-Rotem failure theory is considered to be the most appropriate to apply as a failure theory for the wedge-shaped anchorage system because the anchorage strength was slightly lower than the actual test results, but there was no significant difference, and the failure mode was consistent with the test results. The Hashin failure theory is judged to be unsuitable for application as a failure theory for the wedge-type anchorage system because the anchorage strength and failure mode were interpreted differently from the actual test results. CONCLUSIONS : The Hashin-Rotem failure theory was presented as the composite material failure theory most suitable for analyzing the behavior of wedge-type anchorage system.

Since maize (Zea mays L.) originated in central and south America, it requires warm climate conditions throughout its growing season. Growth halts when night-time temperatures drop below 10℃, and the plant may die if temperature reach -1.7℃. Thus, temperature should be maintained between 10 and 30℃ from seeding to maturity. The germination temperature for maize should be at least 8-11℃, whit an optimal range 32-34℃. Since temperature significantly affects the germination rate and period, it plays a crucial role in maize growth. In this study, we evaluated the quantity and feed value of 11 major varieties to determine those best suited for maize cultivation as feed in higher latitude, specifically in Democratic People’s of Republic of Korea, below 38 degrees north. A cultivation test was also conducted in Suwon in Republic of Korea, to assess adaptability in areas south of Mt. Suyang. Among the varieties tested, Shinhwangok2 reached silking the fastest, in 65 days, while Gwangpyeongok took the longest at 75 days. The stem length of all varieties exceeded 230 cm. Gwangpyeongok had the tallest stems, while Daanok and Shinhwangok2ho displayed the highest ear ratios. Dacheongok presented the highest values in both dry matter and TDN quantity, with 31,420 kg/ha and 21,66 kg/ha respectively. Pyeonggangok had the highest crude protein content at 8.0%. TDN (%) ranged from 57-68%, with Hwangdaok reaching up to 68%. Based on these findings, Dacheongok and Pyeonggangok appear to be the most suitable varieties for cultivation in terms of both quantity and feed value.

This study was performed to investigate immune changes by comparing the proportion and function of immune cells in the blood under high-temperature period and convalescence temperature period in Holstein dairy cows. The experiment was conducted using Holstein dairy cows of five animals per group (60 ± 20 months old, 175 ± 78 non-day) from the National Institute of Animal Science at high-temperature period (THI: 76 ± 1.2) and convalescence temperature period (THI: 66 ± 1.3). Complete blood count results showed no change in the number of immune cells between groups. In the analysis using Flow Cytometry of PBMCs, no significant differences were observed among B cells, Helper T cells, cytotoxic T cells, and γδ T cells between groups. However, there was an increase in Th17 cells producing IL-17a, while Th1 cells decreased during the convalescence temperature period. The results of gene expression analysis using qRT-PCR in PBMCs revealed an increase in IL-10 during the convalescence temperature period, while a decrease in HSP70 and HSP90 was observed. In conclusion, the increased expression of IL-10 and the decrease in HSP expression suggest the possibility of a weak recovery from heat stress. However, the lack of observed changes in B cells, T cells, and other immune cells indicates incomplete recovery from heat stress during the convalescence temperature period.

algorithms for deriving and analyzing retroreflectivity influence factors through regression analysis. METHODS : An experimental road lane was created to examine the trends of retroreflectivity and LiDAR intensity values, and a controlled indoor experiment was conducted to identify influencing factors. The optimal algorithm was developed by regression analysis of the experimental data. RESULTS : The significance probability (P-value) through SPSS linear regression analysis was 0.000 for measured height, 0.001 for perpendicular angle, 0.157 for vertical angle, and 0.000 for LiDAR intensity, indicating that measured height, vertical angle, and LiDAR intensity are significant factors because the significance probability is less than 0.05, and vertical angle is not significant. The NNR regression model performed the best, so the measurement data with height (1.2m, 2m, 2.2m) and vertical angle (11.3°, 12.3°, 13.5°) were analyzed to derive the optimal LiDAR Intensity measurement height and vertical angle. CONCLUSIONS : For each LiDAR measurement height and vertical angle, the highest correlation between LiDAR Intensity and retroreflectivity was found at a measurement height of 1.2 meters and a vertical angle of 12.3°, where the model learning accuracy (R2) was the highest.

큰징거미새우(Macrobrachium rosenbergii)는 양식 시설 내에서 체색 불량 및 갑각 약화와 같은 문제로 경제적 손실을 겪고 있다. 이 종은 동물성 원료 기반의 사료로 양식되지만, 야생에서는 식물체 비중이 높은 detritus를 주로 섭취한다. 새우가 야생에서 섭취한 식물체는 기본 영양소 뿐만 아니라 체색의 재료인 카로티노이드의 공급원이기도 하다. 개나리(Forsythia koreana)는 우리나라에 널리 분포하는 꽃나무로 잎에는 황색 당근에 버금가는 양의 카로티노이드가 함유 되어 있다. 본 연구에서는 큰징거미새우에게 개나리 잎을 공급하여 체색 및 건강도에 미치는 효과를 조사하였다. 실험사료는 「배합사료 100%(대조구), CON」, 「배합사료 80%+개나리 잎 분말 20%, FP」, 「배합사료 80%+가공하지 않은 개나리 잎 20%, FL」의 세 가지였으며, 각 조건 의 사료를 평균 체중 1.1 ± 0.2 g의 어린 새우들에게 10주간 공급하였다. 실험 결과, 체색의 경 우, CON의 새우들은 일관적으로 투명한 상아색을 띠었으나, FP와 FL 새우의 경우 사육일의 경과에 따라 푸른색을 거쳐 암갈색으로 변화하였다. 생존과 성장은 CON과 FP 또는 FL 사이에 유의한 차이가 없었다. 간췌장을 조직학적으로 비교한 결과, hepatopancreatic tubule의 구성 세포 중 B cell의 vacuole 크기가 CON에 비해 FP과 FL에서 훨씬 컸다. B cell의 vacuole은 영 양소의 흡수 및 소화의 역할을 하며, 개나리 잎의 공급이 큰징거미새우의 건강에 긍정적으로 작용했을 가능성을 시사한다. 이상의 결과는 큰징거미새우의 양식에 개나리 잎을 활용하면 성장 저해 없이 체색의 개선 및 건강도의 향상을 기대할 수 있음을 보여준다.

PURPOSES : The purpose of this study is to statistically analyze the meteorological factors that contribute to the formation of road surface icing based on actual cases of icing accidents and provide directions for improving icing evaluation criteria. METHODS : In this study, we collected cases of domestic road icing accidents by searching news articles with the keyword ‘icing collision accidents’. Subsequently, we determined the latitude, longitude, and altitude of accident locations using satellite map service. We applied the Inverse Distance Weighting (IDW) method and temperature lapse rate to estimate meteorological data at each location. Finally, statistical analysis was conducted for temperature, humidity, and precipitation occurrence using probability density functions. RESULTS : As a result, road icing accident data points with identifiable location coordinates were collected. Among these, temperature, humidity, and precipitation occurrence from Automated Weather Stations (AWS) data were selected for analysis. During the process of correcting meteorological factors using the Inverse Distance Weighting (IDW) method, the optimal Weighting Exponent (p) that minimizes the error was determined and applied. The results showed that accidents occurring in the morning indicated the highest accident occurrence rate. The average temperature at the time of the accidents was -1.4°C, with a humidity level of 85.1%. Precipitation was observed at the time of the accident in 19 cases. CONCLUSIONS : Icing on pavement can occur not only under extreme weather conditions but also under typical meteorological conditions. Typically, icing can occur when the relative humidity is above 70%. Accordingly, for future improvements in the evaluation criteria for icing-prone areas by the Ministry of Land, Infrastructure and Transport, it is possible to incorporate the temperature and humidity ranges that generally lead to icing, taking into account climate characteristics.

This study endeavors to enrich investment prospects in cryptocurrency by establishing a rationale for investment decisions. The primary objective involves evaluating the predictability of four prominent cryptocurrencies – Bitcoin, Ethereum, Litecoin, and EOS – and scrutinizing the efficacy of trading strategies developed based on the prediction model. To identify the most effective prediction model for each cryptocurrency annually, we employed three methodologies – AutoRegressive Integrated Moving Average (ARIMA), Long Short-Term Memory (LSTM), and Prophet – representing traditional statistics and artificial intelligence. These methods were applied across diverse periods and time intervals. The result suggested that Prophet trained on the previous 28 days' price history at 15-minute intervals generally yielded the highest performance. The results were validated through a random selection of 100 days (20 target dates per year) spanning from January 1st, 2018, to December 31st, 2022. The trading strategies were formulated based on the optimal-performing prediction model, grounded in the simple principle of assigning greater weight to more predictable assets. When the forecasting model indicates an upward trend, it is recommended to acquire the cryptocurrency with the investment amount determined by its performance. Experimental results consistently demonstrated that the proposed trading strategy yields higher returns compared to an equal portfolio employing a buy-and-hold strategy. The cryptocurrency trading model introduced in this paper carries two significant implications. Firstly, it facilitates the evolution of cryptocurrencies from speculative assets to investment instruments. Secondly, it plays a crucial role in advancing deep learning- based investment strategies by providing sound evidence for portfolio allocation. This addresses the black box issue, a notable weakness in deep learning, offering increased transparency to the model.