• International Journal of Computer Science & Network Security
• /
• v.23 no.8
• /
• pp.210-216
• /
• 2023

Demand prediction is an essential component of any business or supply chain. Large retailers need to keep track of tens of millions of items flows each day to ensure smooth operations and strong margins. The demand prediction is in the epicenter of this planning tornado. For business processes in retail companies that deal with a variety of products with short shelf life and foodstuffs, forecast accuracy is of the utmost importance due to the shifting demand pattern, which is impacted by an environment of dynamic and fast response. All sectors strive to produce the ideal quantity of goods at the ideal time, but for retailers, this issue is especially crucial as they also need to effectively manage perishable inventories. In light of this, this research aims to show how Machine Learning approaches can help with demand forecasting in retail and future sales predictions. This will be done in two steps. One by using historic data and another by using open data of weather conditions, fuel, Consumer Price Index (CPI), holidays, any specific events in that area etc. Several machine learning algorithms were applied and compared using the r-squared and mean absolute percentage error (MAPE) assessment metrics. The suggested method improves the effectiveness and quality of feature selection while using a small number of well-chosen features to increase demand prediction accuracy. The model is tested with a one-year weekly dataset after being trained with a two-year weekly dataset. The results show that the suggested expanded feature selection approach provides a very good MAPE range, a very respectable and encouraging value for anticipating retail demand in retail systems.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.8
• /
• pp.2188-2208
• /
• 2023

Quality of Service (QoS) is a critical feature of Wireless Sensor Networks (WSNs) with routing algorithms. Data packets are moved between cluster heads with QoS using a number of energy-efficient routing techniques. However, sustaining high scalability while increasing the life of a WSN's networks scenario remains a challenging task. Thus, this research aims to develop an energy-balancing component that ensures equal energy consumption for all network sensors while offering flexible routing without congestion, even at peak hours. This research work proposes a Gravitational Blackhole Search Optimised splay tree routing framework. Based on the splay tree topology, the routing procedure is carried out by the suggested method using three distinct steps. Initially, the proposed GBSO decides the optimal route at initiation phases by choosing the root node with optimum energy in the splay tree. In the selection stage, the steps for energy update and trust update are completed by evaluating a novel reliance function utilising the Parent Reliance (PR) and Grand Parent Reliance (GPR). Finally, in the routing phase, using the fitness measure and the minimal distance, the GBSO algorithm determines the best route for data broadcast. The model results demonstrated the efficacy of the suggested technique with 99.52% packet delivery ratio, a minimum delay of 0.19 s, and a network lifetime of 1750 rounds with 200 nodes. Also, the comparative analysis ensured that the suggested algorithm surpasses the effectiveness of the existing algorithm in all aspects and guaranteed end-to-end delivery of packets.

• Clinical and Experimental Reproductive Medicine
• /
• v.50 no.3
• /
• pp.200-205
• /
• 2023

Objective: Polycystic ovary (PCO), a diagnostic component of polycystic ovary syndrome (PCOS), requires either an ovarian volume (OV) criterion or a follicle number per ovary (FNPO) criterion. This study investigated the association of OV and FNPO criteria with various manifestations of PCOS. Methods: This cross-sectional study was conducted at a university hospital among 100 patients newly diagnosed with PCOS (according to the revised Rotterdam criteria). Fasting blood samples were collected to measure glucose, total testosterone (TT), luteinizing hormone (LH), follicle-stimulating hormone (FSH), lipid, insulin, and hemoglobin A1c levels. An oral glucose tolerance test was performed. Transabdominal or transvaginal ultrasound of the ovaries was done, depending on patients' marital status. All investigations were conducted in the follicular phase of the menstrual cycle. OV >10 mL and/or FNPO ≥12 indicated PCO. A homeostasis model assessment of insulin resistance (IR) value ≥2.6 indicated IR, and metabolic syndrome (MS) was defined according to the international harmonization criteria. Results: Seventy-six participants fulfilled the OV criterion, 70 fulfilled the FNPO criterion, and 89 overall had PCO. Both maximum OV and mean OV had a significant correlation with TT levels (r=0.239, p=0.017 and r=0.280, p=0.005, respectively) and the LH/FSH ratio (r=0.212, p=0.034 and r=0.200, p=0.047, respectively). Mean OV also had a significant correlation with fasting insulin levels (r=0.210, p=0.036). Multivariate binary logistic regression analysis showed that IR (odds ratio [OR], 9.429; 95% confidence interval [CI], 1.701 to 52.271; p=0.010) and MS (OR, 7.952; 95% CI, 1.821 to 34.731; p=0.006) had significant predictive associations with OV alone, even after adjustment for age and body mass index. Conclusion: OV may be more closely related to the androgenic and metabolic characteristics of PCOS than FNPO.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.413-415
• /
• 2022

Since human joints can be used as useful information for analyzing human behavior as a component of the human body, many studies have been conducted on human action recognition using joint information. However, it is a very complex problem to recognize human action that changes every moment using only each independent joint information. Therefore, an additional information extraction method to be used for learning and an algorithm that considers the current state based on the past state are needed. In this paper, we propose a human action recognition technique considering the positional relationship of connected joints and the change of the position of each joint over time. Using the pre-trained joint extraction model, position information of each joint is obtained, and bone information is extracted using the difference vector between the connected joints. In addition, a simplified neural network is constructed according to the two types of inputs, and spatio-temporal features are extracted by adding LSTM. As a result of the experiment using a dataset consisting of 9 behaviors, it was confirmed that when the action recognition accuracy was measured considering the temporal and spatial relationship features of each joint, it showed superior performance compared to the result using only single joint information.

• Journal of the Korean Geotechnical Society
• /
• v.22 no.1
• /
• pp.15-23
• /
• 2006

During earthquake, force components acting on quay walls consist of inertia force, earth pressure and water pressure. The earth pressure is largely influenced by the backfill condition such as soil density and the installation of gravel backfill. Therefore, shaking table tests were performed by using four different model sections, which were designed by varying the soil density and the backfill materials. The magnitude and the phase of force components acting on quay wall were analyzed. Test results showed that the gravel backfill and the soil compaction were effective to reduce the excess pore pressure in backfill and the magnitude and phase of backfill thrust were much influenced by the excess pore pressure in backfill. When the input acceleration was 0.10g, the average ratios of the inertia force, the front dynamic water force and the thrust to the total force were $64\%,\;21\%\;and\;16\%$, respectively. As the excess pore pressure increased, the ratio of the thrust to the total force increased.

• Journal of the Korean Geotechnical Society
• /
• v.24 no.7
• /
• pp.37-42
• /
• 2008

This paper estimates the long-term settlement of Incheon unsanitary solid waste landfill, which is 20 years old. The unsanitary solid waste landfill was subjected to pre-loading system over a period of 1 year, and 300 settlement monitoring provided the long term settlement data. This landfill contains relatively small amount of organic component, and therefore the initial stage of settlement was very small. The existing settlement models were examineed by comparing the observed behaviors of this site, and also they were used to predict the long-term settlement. Power Creep Law (PCL) model showed good agreement with the measured settlement obtained from the initial stage of the measurement, but other models showed satisfactory agreements after $50{\sim}70$ days of measurement.

• Journal of the Korean Institute of Gas
• /
• v.27 no.1
• /
• pp.38-47
• /
• 2023

In the hydrogen filling process, hydrogen flows by the pressure difference between the supply pressure at a filling station and a storage tank in the vehicle, and the flow rate depends on the pressure difference. Therefore, it is essential to consider the pressure drop of hydrogen occurring during the filling process, and the efficiency of the hydrogen filling process can be improved through its analysis. In this study, the pressure drop was analyzed for a hose, a nozzle/receptacle coupling, a pipe, and a valve in a filling line. The pressure drops through hose and pipe, the nozzle,receptacle coupling, and the valve were calculated by using a equation for a straight conduit, a flow nozzle formula, and a gas flow respectively. In addition, as a result of comprehensive analysis of the pressure drop effect occurring in each component, it was found that the factor that has the greatest influence on the pressure drop in the entire filling line is the pressure drop through the valve. This study can be used to develop a model of the hydrogen filling process by analyzing hydrogen flow including hydrogen filling in the future.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.5
• /
• pp.155-161
• /
• 2023

97.5% of our country's exports and 87.2% of imports are transported by sea, making ports an important component of the Korean economy. To efficiently operate these ports, it is necessary to improve the short-term prediction of port water volume through scientific research methods. Previous research has mainly focused on long-term prediction for large-scale infrastructure investment and has largely concentrated on container port water volume. In this study, short-term predictions for petroleum and liquefied gas cargo water volume were performed for Ulsan Port, one of the representative petroleum ports in Korea, and the prediction performance was confirmed using the deep learning model LSTM (Long Short Term Memory). The results of this study are expected to provide evidence for improving the efficiency of port operations by increasing the accuracy of demand predictions for petroleum and liquefied gas cargo water volume. Additionally, the possibility of using LSTM for predicting not only container port water volume but also petroleum and liquefied gas cargo water volume was confirmed, and it is expected to be applicable to future generalized studies through further research.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.6
• /
• pp.691-697
• /
• 2022

In this work, a straightforward component design of a direct current (DC) relay equipped in electric vehicles is discussed. The work aims to provide and evaluate effective measures for reducing high-frequency sound from the DC relay carrying electric power. From the operation experiments for the relay, it is observed that noise is caused by the resonance from the forced vibration by the electromagnetic repulsive force originating at the area of electric contacts with a resonance frequency of around 710 Hz ~ 730 Hz. A finite element model for the relay was established to conduct vibration mode analysis, consisting of stationary and movable contacts and a contact spring. Vibration mode analysis indicates that in the resonance frequency, the movable contact with two-point contacts experiences rotational vibration mode. For the proposed relay with a three-point contact, vibration mode analyses give reasonable results of reducing noise at that frequency. Furthermore, for the fabricated relays with the three-point contact, similar results have been obtained. In conclusion, one can see that the proposed measures provide one of the feasible solutions to the reduction of relay noise.

• Journal of Ginseng Research
• /
• v.47 no.3
• /
• pp.420-428
• /
• 2023

Background: Ginsenoside F2 (GF2), a minor component of Panax ginseng, has been reported to possess a wide variety of pharmacological activities. However, its effects on glucose metabolism have not yet been reported. Here, we investigated the underlying signaling pathways involved in its effects on hepatic glucose. Methods: HepG2 cells were used to establish insulin-resistant (IR) model and treated with GF2. Cell viability and glucose uptake-related genes were also examined by real-time PCR and immunoblots. Results: Cell viability assays showed that GF2 up to 50 μM did not affect normal and IR-HepG2 cell viability. GF2 reduced oxidative stress by inhibiting phosphorylation of the mitogen-activated protein kinases (MAPK) signaling components such as c-Jun N-terminal kinase (JNK), extracellular signal-regulated kinase 1/2 (ERK1/2), and p38 MAPK, and reducing the nuclear translocation of NF-κB. Furthermore, GF2 activated PI3K/AKT signaling, upregulated the levels of glucose transporter 2 (GLUT-2) and GLUT-4 in IR-HepG2 cells, and promoted glucose absorption. At the same time, GF2 reduced phosphoenolpyruvate carboxykinase and glucose-6-phosphatase expression as well as inhibiting gluconeogenesis. Conclusion: Overall, GF2 improved glucose metabolism disorders by reducing cellular oxidative stress in IR-HepG2 cells via MAPK signaling, participating in the PI3K/AKT/GSK-3β signaling pathway, promoting glycogen synthesis, and inhibiting gluconeogenesis.