• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.301-307
• /
• 2022

Energy consumption has grown alongside dramatic population increases. Statistics show that buildings in particular utilize a significant amount of energy, worldwide. Because of this, building energy prediction is crucial to best optimize utilities' energy plans and also create a predictive model for consumers. To improve energy prediction performance, this paper proposes a ResNet-LSTM model that combines residual networks (ResNets) and long short-term memory (LSTM) for energy consumption prediction. ResNets are utilized to extract complex and rich features, while LSTM has the ability to learn temporal correlation; the dense layer is used as a regression to forecast energy consumption. To make our model more robust, we employed Huber loss during the optimization process. Huber loss obtains high efficiency by handling minor errors quadratically. It also takes the absolute error for large errors to increase robustness. This makes our model less sensitive to outlier data. Our proposed system was trained on historical data to forecast energy consumption for different time series. To evaluate our proposed model, we compared our model's performance with several popular machine learning and deep learning methods such as linear regression, neural networks, decision tree, and convolutional neural networks, etc. The results show that our proposed model predicted energy consumption most accurately.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2022.10a
• /
• pp.233-233
• /
• 2022

As the world's population grows and food needs diversify, the demand for horticultural crops for beneficial traits is increasing. In order to meet this demand, it is necessary to develop suitable cultivars and breeding methods accordingly. Breeding methods have changed over time. With the recent development of sequencing technology, the concept of genomic selection (GS) has emerged as large-scale genome information can be used. GS shows good predictive ability even for quantitative traits by using various markers, breaking away from the limitations of Marker Assisted Selection (MAS). Moreover, GS using machine learning (ML) and deep learning (DL) has been studied recently. In this study, we aim to build a system that selects phenotype-related markers using the genomic information of the pepper population and trains a genomic selection model to select individuals from the validation population. We plan to establish an optimal genome wide association analysis model by comparing and analyzing five models. Validation of molecular markers by applying linkage markers discovered through genome wide association analysis to breeding populations. Finally, we plan to establish an optimal genome selection model by comparing and analyzing 12 genome selection models. Then We will use the genome selection model of the learning group in the breeding group to verify the prediction accuracy and discover a prediction model.

• Electronics and Telecommunications Trends
• /
• v.38 no.6
• /
• pp.31-40
• /
• 2023

Given recent accidents involving autonomous vehicles, driver monitoring technology related to the transition of control in autonomous vehicles is gaining prominence. Driver status monitoring systems recognize the driver's level of alertness and identify possible impairments in the driving ability owing to conditions including drowsiness and distraction. In autonomous vehicles, predictive factors for the transition to manual driving should also be included. During traditional human driving, monitoring the driver's status is relatively straightforward owing to the consistency of crucial cues, such as the driver's location, head orientation, gaze direction, and hand placement. However, monitoring becomes more challenging during autonomous driving because of the absence of direct manual control and the driver's engagement in other activities, which may obscure the accurate assessment of the driver's readiness to intervene. Hence, safety-ensuring technology must be balanced with user experience in autonomous driving. We explore relevant global and domestic regulations, the new car assessment program, and related standards to extract requirements for driver status monitoring. This kind of monitoring can both enhance the autonomous driving performance and contribute to the overall safety of autonomous vehicles on the road.

• Journal of Navigation and Port Research
• /
• v.48 no.2
• /
• pp.116-124
• /
• 2024

Automatic docking of small planing ship is a critical aspect of maritime operations, requiring accurate prediction of motion states to ensure safe and efficient maneuvers. This study investigates the use of Artificial Neural Network (ANN) to predict motion state of a small planing ship to enhance navigation automation in port environments. To achieve this, simulation tests were conducted to control a small planing ship while docking at various heading angles in calm water and in waves. Comprehensive analysis of the ANN-based predictive model was conducted by training and validation using data from various docking situations to improve its ability to accurately capture motion characteristics of a small planing ship. The trained ANN model was used to predict the motion state of the small planning ship based on any initial motion state. Results showed that the small planing ship could dock smoothly in both calm water and waves conditions, confirming the accuracy and reliability of the proposed method for prediction. Moreover, the ANN-based prediction model can adjust the dynamic model of the small planing ship to adapt in real-time and enhance the robustness of an automatic positioning system. This study contributes to the ongoing development of automated navigation systems and facilitates safer and more efficient maritime transport operations.

• Korean Journal of Radiology
• /
• v.22 no.10
• /
• pp.1697-1707
• /
• 2021

The recent introduction of various high-dimensional modeling methods, such as radiomics and deep learning, has created a much greater diversity in modeling approaches for survival prediction (or, more generally, time-to-event prediction). The newness of the recent modeling approaches and unfamiliarity with the model outputs may confuse some researchers and practitioners about the evaluation of the performance of such models. Methodological literacy to critically appraise the performance evaluation of the models and, ideally, the ability to conduct such an evaluation would be needed for those who want to develop models or apply them in practice. This article intends to provide intuitive, conceptual, and practical explanations of the statistical methods for evaluating the performance of survival prediction models with minimal usage of mathematical descriptions. It covers from conventional to deep learning methods, and emphasis has been placed on recent modeling approaches. This review article includes straightforward explanations of C indices (Harrell's C index, etc.), time-dependent receiver operating characteristic curve analysis, calibration plot, other methods for evaluating the calibration performance, and Brier score.

• Clinical and Experimental Reproductive Medicine
• /
• v.29 no.1
• /
• pp.57-66
• /
• 2002

Objective : This study was designed to investigate the interrelationship and clinical usefulness of sperm morphology by strict criteria (SM), acrosome reaction following ionophore challenge test (ARIC) and sperm penetration assay (SPA) using zona-free hamster ova as prognostic factors in in vitro fertilization. Materials and Methods: Semen samples were provided by 83 patients undergoing IVF. We first evaluated the differences between normal fertilization group and poor fertilization group on three andrologic tests. Secondly, we analyzed the relationship between the three andrologic tests and in vitro fertilization on IVF settings. Finally, we evaluated the effectiveness of the three andrologic tests as the prognostic indicators for fertilizing ability. Results: The fertilization rate of all men in the poor fertilization group was less than 30%; but there was no evidence that this poor fertilization was due to oocyte defects. The results of three andrologic tests were significatly higher in normal fertilization group. Fertilization rate (%) in vitro was highly correlated (p<0.001) with % normal sperm by SM, ARIC value (%), and SPA result. By using Receiver-Operator-Characteristic curve (ROC), we evaluated the effectiveness of these three tests. The sensitivity and specificity of SM, ARIC test and SPA in predicting fertilization potential in IVF setting were 76% and 75%, 84% and 90%, and 76% and 95%, respectively. Conclusion: Our data suggest that the three andrologic tests can be reliable tools as prognostic factors of sperm fertilizing ability. Among these test, ARIC test and SPA gave more accurate information on fertilizing capacity. ARIC test was shown to have a predictive value for fertilizing ability comparable to that of SPA that appears to be a simple and cost-effective addition to current andrology laboratory. Combined application of these three tests may give more information on predicting sperm fertilizing capacity.

• Korean Journal of Clinical Laboratory Science
• /
• v.50 no.1
• /
• pp.44-53
• /
• 2018

The WHtR (waist to height ratio) and ABSI (a body shape index) are indicators that reflect abdominal obesity. This study examined the insulin resistance and metabolic syndrome prediction ability of ABSI and WHtR. In this study, 4,395 people aged 20 years or older, who underwent physical examinations at a General Hospital in Gyeonggi-do from January 2017 to September 2017 were assessed on a cross section survey. Metabolic syndrome was defined according to the criteria of the AHA/NHLBI. Insulin resistance was judged to be insulin resistance when the HOMA-IR value was 3.0 or more. Both men and women showed a stronger correlation between WHtR and the metabolic risk factors than ABSI. The AUC value of WHtR and ABSI was 0.849 and 0.676, respectively (p<0.001). The AUC value of WHtR and ABSI for predicting insulin resistance was 0.818 and 0.641, respectively (p<0.001). In conclusion, the ABSI has low predictive power of insulin resistance and metabolic syndrome whereas the WHtR has good predictive power for metabolic syndrome and insulin resistance.

• 한국지구물리탐사학회:학술대회논문집
• /
• 2009.05a
• /
• pp.57-65
• /
• 2009

Selection of good mineralized area is a combination of the integration of all the available geo-scientific (i.e., geological, geochemical, and geophysical) information, extrapolation of likely features from known mineralized terrenes and the ability to be predictive. The time-space relationships of the hydrothermal deposits in the East Asia are closely related to the changing plate motions. Also, two distinctive hydrothermal systems during Mesozoic occurred in Korea: the Jurassic/Early Cretaceous deep-level ones during the Daebo orogeny and the Late Cretaceous/Tertiary shallow geothermal ones during the Bulguksa event. Both the Mesozoic geothermal system and the mineralization document a close spatial and temporal relationship with syn- to post-tectonic magmatism. The Jurassic mineral deposits were formed at the relatively high temperature and deep-crustal level from the mineralizing fluids characterized by the relatively homogeneous and similar ranges of ${\delta}^{18}O$ values, suggesting that ore-forming fluids were principally derived from spatially associated Jurassic granitoid and related pegmatite. Most of the Jurassic auriferous deposits (ca. 165-145 Ma) show fluid characteristics typical of an orogenic-type gold deposits, and were probably generated in a compressional to transpressional regime caused by an orthogonal to oblique convergence of the Izanagi Plate into the East Asian continental margin. On the other hand, Late Cretaceous ferroalloy, base-metal and precious-metal deposits in the Taebaeksan, Okcheon and Gyeongsang basins occurred as vein, replacement, breccia-pipe, porphyry-style and skarn deposits. Diverse mineralization styles represent a spatial and temporal distinction between the proximal environment of sub-volcanic activity and the distal to transitional condition derived from volcanic environments. However, Cu (-Au) or Fe-Mo-W deposits are proximal to a magmatic source, whereas polymetallic or precious-metal deposits are more distal to transitional. Strike-slip faults and caldera-related fractures together with sub-volcanic activity are associated with major faults reactivated by a northward (oblique) to northwestward (orthogonal) convergence, and have played an important role in the formation of the Cretaceous Au-Ag lode deposits (ca. 110-45 Ma) under a continental arc setting. The temporal and spatial distinctions between the two typical Mesozoic deposit styles in Korea reflect a different thermal episodes (i.e., late orogenic and post-orogenic) and ore-forming fluids related to different depths of emplacement of magma (i.e., plutonic and sub-volcanic) due to regional changes in tectonic settings.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.10
• /
• pp.4223-4228
• /
• 2015

Objective: To investigate the diagnostic value of the R-way colposcopic evaluation system (R-way system) in cervical cancer screening. Materials and Methods: Between August 2013 and August 2014, a total of 1,059 cases referred to colposcopy in Peking University First Hospital were studied using both the R-way system and conventional colposcopy. Our study evaluated and compared the diagnostic ability of the two methods in detecting high-grade lesions and cervical cancer (hereinafter called CIN2+). Evaluation indicators including sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), Youden index and the area under the curve (AUC) of the receiver operating characteristic (ROC) were calculated. Results: The R-way system had a slightly lower specificity (94.5%) than conventional colposcopy (96.0%) for CIN2+ detection (P=0.181). However, the sensitivity (77.8%) was significantly higher than with the conventional colposcopic method (46.6%) (${\chi}^2=64.351$, P<0.001). In addition, the AUC of the ROC for CIN2+ detection using the R-way system (0.839) was larger than that with conventional colposcopy (0.731) (Z=4.348, P<0.001). If preliminary result had been drawn from cervical exfoliated cytology before colposcopy referral, combination of the R-way system with cytology could increase the sensitivity to 93.9% for CIN2+ detection (excluding ASCUS\LSIL), confirmed by multipoint biopsy or ECC. Conclusions: The diagnostic value of the R-way evaluation system is higher than that of conventional colposcopic evaluation in cervical cancer screening. Moreover, taking the ease of use and standardized quality control management into account, the R-way system is highly preferable.

• Korean Journal of Cognitive Science
• /
• v.25 no.2
• /
• pp.159-187
• /
• 2014

Approximate number sense(hereafter, ANS) is the ability to compare and operate upon numerosity information. The numerosity comparison task is used to measure ANS. However, there is considerable variance among previous reports of ANS acuity which may be related to different task formats used. Here, we aim to investigate whether the format of the numerosity comparison task influences measurements of ANS acuity. We compared two task formats; 1) an intermixed format presenting two intermixed arrays of black and white dots, and 2) a side-by-side format showing two arrays of dots side by side. The intermixed format likely makes additional demands on general cognitive resources for inhibitory control, selective attention, or visuospatial working memory. The performance on the intermixed format was significantly lower than that of the side-by-side format resulting in an underestimation of ANS acuity compared to the expected trajectory of ANS development. In addition, the ANS acuity measured from only the side-by-side format was correlated with children's mathematical achievement and age. Our results demonstrate that measurement of ANS from the side-by-side format has higher construct and predictive validity compared to that of the intermixed format.