Earticle

The purpose of this study suggests a personalized algorithm of physical activity energy expenditure prediction through comparison and analysis of individual physical activity. The research for a 3-axial accelerometer sensor has increased the role of physical activity in promoting health and preventing chronic disease has long been established. Estimating algorithm of physical activity energy expenditure was implemented by using a tri-axial accelerometer motion detector of the SVM(Signal Vector Magnitude) of 3-axis(x, y, z). A total of 10 participants(5 males and 5 females aged between 20 and 30 years). The activities protocol consisted of three types on treadmill; participants performed three treadmill activity at three speeds(3, 5, 8 km/h). These activities were repeated four weeks.

Given that most of the link prediction algorithms for signed social networks can only complete sign prediction, a novel algorithm is proposed aiming to achieve both link prediction and sign prediction in signed networks. Based on the structural balance theory, the local link tightness and global link tightness are defined respectively by using the structural information of paths with the step size of 2 and 3 between the two nodes. Then the total similarity of the node pair can be obtained by combining them. Its absolute value measures the possibility of the two nodes to establish a link, and its sign is the sign prediction result of the predicted link. The effectiveness and correctness of the proposed algorithm are verified on six typical datasets. Comparison and analysis are also carried out with the classical prediction algorithms in signed networks such as CN-Predict, ICN-Predict, and PSNBS (prediction in signed networks based on balance and similarity) using the evaluation indexes like area under the curve (AUC), Precision, improved AUC', improved Accuracy', and so on. Results show that the proposed algorithm achieves good performance in both link prediction and sign prediction, and its accuracy is higher than other algorithms. Moreover, it can achieve a good balance between prediction accuracy and computational complexity.

The essence of PHM technology is to process the collected information with the help of the system information collected by sensors, using information fusion, artificial intelligence, big data, reasoning algorithms and other technologies, and realize the monitoring management, status evaluation and fault prediction functions of the target system. PHM is an important part of the intelligent equipment detection and maintenance system. Its application and realization in the railway field is the key link of the intelligent operation and maintenance of multiple units, and is an important means to realize the shift from planned preventive maintenance to digital and accurate condition maintenance. It is of great significance for China's high-speed railway to maintain the world's advanced level and move towards higher quality, efficiency and efficiency. With the improvement of operation speed and the growth of application scale of High-Speed Electric Multiple Units in China, hereinafter referred to as EMU, the technical challenges of operation safety and security of EMUs are increasingly prominent. As a kind of equipment health management technology, PHM can realize equipment status monitoring, abnormal prediction, fault diagnosis, maintenance prediction and maintenance decision-making. In order to improve the safety assurance capability of high-speed EMU, reduce the maintenance cost and improve the maintenance efficiency, this paper deeply integrates big data technology, algorithm model and PHM technology, and explores the theory and method of intelligent fault prediction of key components of high-speed EMU based on PHM technology. Focus on the research of EMU condition monitoring and fault diagnosis technology based on HSMM and DBN algorithms, as well as the component maintenance prediction and maintenance decision-making technology based on fixed repair schedule prevention, so as to transfer the theoretical basis and technical support for the maintenance mode of EMU from "planned repair" to "planned repair predictive maintenance".

Many new techniques have been adopted in HEVC (High efficiency video coding) standard, such as quadtree-structured coding unit (CU), prediction unit (PU) partition, 35 intra-mode, and so on. To reduce computational complexity, the paper proposes two optimization algorithms which include fast CU depth range decision and fast PU partition mode decision. Firstly, depth range of CU is predicted according to spatial-temporal correlation. Secondly, we utilize the depth difference between the current CU and CU corresponding to the same position of adjacent frame for PU mode range selection. The number of traversal candidate modes is reduced. The experiment result shows the proposed algorithm obtains a lot of time reducing, and the loss of coding efficiency is inappreciable.

In recent years, the rapid development of artificial intelligence technology has brought new opportunities to the meteorological field. Specifically, machine learning (ML) algorithms have proven valuable tools in rainfall retrievals, demonstrating the practicability of using ML algorithms when facing high-dimensional and complex data. By collecting data and using ML algorithms to mine and analyze the data, ML models can solve the problem of rainfall prediction in meteorology. Spurred by this advantage, this paper compared five ML algorithms for rainfall prediction using the National Population Health Science data from China, and the five ML algorithms were optimized appropriately. The data employed was first preprocessed to find and fill in the missing values, remove duplicate values, mine the correlation between data features, and generate visual results. Then, logistic regression, k-nearest neighbor algorithm, naive Bayes, decision tree algorithms, and random forest were used to mine and analyze the meteorological data for weather prediction. Finally, the performance of the models before and after optimization is compared to provide decision support for rainfall prediction.

High efficiency video coding (HEVC) employs quadtree coding tree unit (CTU) structure to improve its coding efficiency, but at the same time, it also requires a very high computational complexity due to its exhaustive search processes for an optimal coding unit (CU) partition. With the aim of solving the problem, a fast CU size decision optimal algorithm based on neighborhood prediction is presented for HEVC in this paper. The contribution of this paper lies in the fact that we successfully use the partition information of neighborhood CUs in different depth to quickly determine the optimal partition mode for the current CU by neighborhood prediction technology, which can save much computational complexity for HEVC with negligible RD-rate (rate-distortion rate) performance loss. Specifically, in our scheme, we use the partition information of left, up, and left-up CUs to quickly predict the optimal partition mode for the current CU by neighborhood prediction technology, as a result, our proposed algorithm can effectively solve the problem above by reducing many unnecessary prediction and partition operations for HEVC. The simulation results show that our proposed fast CU size decision algorithm based on neighborhood prediction in this paper can reduce about 19.0% coding time, and only increase 0.102% BD-rate (Bjontegaard delta rate) compared with the standard reference software of HM16.1, thus improving the coding performance of HEVC.

High-risk pregnancy endangers both mother and baby, with one maternal death every two minutes in 2023. This study has proposed three Gradient Boosting models?GB-Base, GB-SMOTE, and ZOA-GB?using the West Lombok Pregnancy Risk Prediction Dataset. GB-Base and GB-SMOTE have achieved 90.46% and 90.28% accuracy, while ZOA-GB, using 10 selected features, has reached 88.89%. GB-SMOTE has shown the best performance with an F-score of 84.41%. SHAP has identified Maternal Age, Hemoglobin, and Parity as key features, and DiCE has validated feature-driven prediction control. The study is limited by a single-source dataset, the absence of external-validation, and unexplored optimizers.

An early warning system was developed to help identify stock status as early as possible. For performance to improve, there needs to be a feature to predict the amount of stock that must be provided and a feature to estimate when to buy goods. This research was conducted to improve the inventory early warning system and optimize the Reminder Block's performance in minimum stock settings. The models used in this study are the single exponential smoothing (SES) method for prediction and the economic order quantity (EOQ) model for determining the quantity. The research was conducted by analyzing the Reminder Block in the early warning system, identifying data needs, and implementing the SES and EOQ mathematical models into the Reminder Block. This research proposes a new Reminder Block that has been added to the SES and EOQ models. It is hoped that this study will help in obtaining accurate information about the time and quantity of repurchases for efficient inventory management.

With the deepening of population aging, pension has become an urgent problem in most countries. Community smart pension can effectively resolve the problem of traditional pension, as well as meet the personalized and multi-level needs of the elderly. To predict the pension intention of the elderly in the community more accurately, this paper uses the decision tree classification method to classify the pension data. After missing value processing, normalization, discretization and data specification, the discretized sample data set is obtained. Then, by comparing the information gain and information gain rate of sample data features, the feature ranking is determined, and the C4.5 decision tree model is established. The model performs well in accuracy, precision, recall, AUC and other indicators under the condition of 10-fold cross-validation, and the precision was 89.5%, which can provide the certain basis for government decision-making.

The prediction of short-term traffic flow is the theoretical basis of intelligent transportation as well as the key technology in traffic flow induction systems. The research on short-term traffic flow prediction has showed the considerable social value. At present, the support vector regression (SVR) intelligent prediction model that is suitable for small samples has been applied in this domain. Aiming at parameter selection difficulty and prediction accuracy improvement, the artificial bee colony (ABC) is adopted in optimizing SVR parameters, which is referred to as the ABC-SVR algorithm in the paper. The simulation experiments are carried out by comparing the ABC-SVR algorithm with SVR algorithm, and the feasibility of the proposed ABC-SVR algorithm is verified by result analysis. Continuously, the simulation experiments are carried out by comparing the ABC-SVR algorithm with particle swarm optimization SVR (PSO-SVR) algorithm and genetic optimization SVR (GA-SVR) algorithm, and a better optimization effect has been attained by simulation experiments and verified by statistical test. Simultaneously, the simulation experiments are carried out by comparing the ABC-SVR algorithm and wavelet neural network time series (WNN-TS) algorithm, and the prediction accuracy of the proposed ABC-SVR algorithm is improved and satisfactory prediction effects have been obtained.

Data mining techniques develop a more accurate classification algorithm for patients classified as either normotensive, prehypertensive, or hypertensive. Logistic Model Tree, NBTree, and Bagging were chosen as the three classification models with tenfold cross-validation (LMT). Over 24 hours, we collected ABP readings from 1161 patients. To analyze the data, data mining techniques were used and a tool called WEKA. The data was analyzed based on age, gender, wake-up blood pressure, medication, sleep-up blood pressure, and overall blood pressure. According to bagging results, 886 cases (76.3 percent) are correctly classified, with 270 cases classified as pre-hypertensive, 436 cases as Normotensive, and 180 cases as hypertensive. NBTree's results show that 882 (75.9%) of the 1161 instances are correctly classified. Pre-hypertensive patients make up 256, normotensive patients 442, and hypertensive patients 184. Of the 1161 instances, the LMT algorithm correctly classified 878 (75.6 percent). According to the results, 275 people are pre-hypertensive, 431 are normotensive, and 172 are hypertensive. According to our findings, bagging is the most accurate classifier for the 24 hour ABP Monitoring dataset we used. Bagging achieves less overfitting because it focuses on global accuracy. It stabilizes and improves the accuracy of unstable methods compared to single classifiers.

본 연구에서는 계절적인 요인과 급변하는 상품의 트렌드를 사전예측하기 위해 로지스틱 회귀 알고리즘을 이용 한 상품기획 예측 모형을 제안하고자 수행되었다. 먼저 웹크롤링을 이용하여 포털 사이트 및 온라인 마켓의 소비자의 비정형 데이터를 수집하고 정형 데이터 변환을 위한 전처리 작업을 통해 상품에 대한 의미 있는 정보를 분석하였다. 최종 수집된 11,200개의 데이터셋은 Logistic Regression을 이용하여 상품에 대한 소비자의 만족도, 빈도분석, 상품 에 대한 장점과 단점을 분석할 수 있었다. 분석 결과 소비자의 만족도는 92%이었으며, 빈도분석을 통해 상품에 대한 불량이슈를 확인할 수 있었다. 또한, 개발된 상품 기획 예측 프로그램에 대한 사용 만족도, 시스템 효율성, 시스템 효과 성 항목에 대한 분석결과에서도 만족도가 높게 나타났다. 특히, 불량이슈는 상품에 대한 현 문제를 신속히 인지하고 개선 전략을 수립하는데 필요한 정보를 제공한다는 점에서 매우 의미 있는 자료가 된다.

This study was conducted to propose a product planning prediction model using logistic regression algorithm to predict seasonal factors and rapidly changing product trends. First, we collected unstructured data of consumers in portal sites and online markets using web crawling, and analyzed meaningful information about products through preprocessing for transformation of standardized data. The datasets of 11,200 were analyzed by Logistic Regression to analyze consumer satisfaction, frequency analysis, and advantages and disadvantages of products. The result of analysis showed that the satisfaction of consumers was 92% and the defective issues of products were confirmed through frequency analysis. The results of analysis on the use satisfaction, system efficiency, and system effectiveness items of the developed product planning prediction program showed that the satisfaction was high. Defective issues are very meaningful data in that they provide information necessary for quickly recognizing the current problem of products and establishing improvement strategies.

BIS (Bus Information System:버스정보시스템, 이하 BIS)는 시내버스 운행과 관련된 각종 정보를 수집하고 예측알고리즘을 통해 이용객에게 정보를 제공하고 있다. 동일 구간의 최근 정보를 통한 예측방법은 해당 구간의 소통상황을 반영하지만 예측 대상노선의 특성을 반영할 수 없다는 한계가 있다. 해당노선의 동시간대 과거이력자료를 통해 예측하는 방법은 소통상황의 변동성이 큰 첨두시 예측에 한계가 있는 실정이다. 따라서 예측대상 시점의 통행패턴을 인식하고 가장 유사한 과거 시점의 통행패턴을 선택할 수 있는 패턴인식형 버스도착시간 예측 알고리즘을 개발하였다. 본연구의 예측 결과를 서울시 BIS 도착예측정보이력과 비교 검증한 결과 각 정류장 간 통행시간의 평균제곱근오차가 비첨두시 약 35초(기존: 40초), 첨두시 약 40초(기존: 60초)로 기존대비 약 10~20 %의 개선을 보였다. 이는 동일 과거 시간대 외의 시간대에 현재 교통상황을 대표할 수 있는 자료가 존재함을 의미한다.

Bus Information System (BIS) collects information related to the operation of buses and provides information to users through predictive algorithms. Method of predicting through recent information in same section reflects the traffic situation of the section, but cannot reflect the characteristics of the target line. The method of predicting the historical data at the same time zone is limited in forecasting peak time with high volatility of traffic flow. Therefore, we developed a pattern recognition bus arrival time prediction algorithm which could be overcome previous limitation. This method recognize the traffic pattern of target flow and select the most similar past traffic pattern. The results of this study were compared with the BIS arrival forecast information history of Seoul. RMSE of travel time between estimated and observed was approximately 35 seconds (40 seconds in BIS) at the off-peak time and 40 seconds (60 seconds in BIS) at the peak time. This means that there is data that can represent the current traffic situation in other time zones except for the same past time zone.

Departure Manager (DMAN) is a tool to optimize the departure sequence and to suggest appropriate take-off time and off-block time of each departure aircraft to the air traffic controllers. To that end, Variable Taxi Time (VTT), which is time duration of the aircraft from the stand to the runway, should be estimated. In this paper, a study for development of VTT prediction algorithm based on machine learning techniques is presented. The factors affecting aircraft taxi speeds were identified through the analysis of historical traffic data on the airport surface. The prediction model suggested in this study consists of several sub-models that reflect different types of surface maneuvers based on the analysis result. The prediction performance of the proposed method was evaluated using the actual operational data.

본 논문에서는 예측영상을 생성하고 예측영상과 원본영상 사이의 차분영상의 히스토그램을 이용하여 워터마크를 삽입하는 알고리즘을 제안한다. 제안하는 알고리즘은 예측영상의 예측성능을 향상시키기 위해 적응적으로 참조 픽셀을 선택하였다. 선택된 참조픽셀은 양선형 보간과 방향성 예측을 통해 나머지 픽셀들을 예측하는데 이용된다. 실험결과 PSNR의 증가와 많은 워터마크 삽입량을 확인할 수 있었다.

The proposed watermark embedding algorithm uses histogram of difference image between a modified original image and predicted image. To increase the prediction performance of the predicted image, the reference pixels for prediction are adaptively selected and the other pixels are directionally interpolated with the reference pixels. The simulation result shows that the proposed algorithm gives good performances in the embedding capacity and the PSNR values.

물 사용량 예측은 최적의 용수 공급 운영 방안을 수립하고 전력 소비량 절감을 위하여 꼭 필요한 과정이라고 할 수 있다. 그러나 수용가 단위의 물 사용량은 용도, 사용자의 패턴, 날씨 등의 다양한 요인으로 인해 변화하는 비선형적 특성을 지니고 있다. 따라서 본 연구에서는 비선형적인 수용가 단위의 물 사용량을 예측하기 위하여 다양한 기법들을 연계한 KWD 프레임워크를 제안하고자 하였다. 즉, 먼저 개별 수용가 마다 용도에 따른 유사한 패턴을 파악하기 위해 K-means (K) 군집분석을 수행하였고, 잡음성분을 제거함으로써 핵심적인 주기패턴을 파악하기 위해 Wavelet (W) 방법을 적용하였다. 또한 비선형적 특성을 학습시키기 위해 Deep learning (D) 알고리즘을 적용하였다. 그리고 기존의 선형 시계열 모형인 ARMA 모형과 비교하여 KWD 프레임워크의 성능을 분석하였다. 그 결과 제안된 모형의 상관성은 92%, ARMA 모형은 약 39%로 KWD 프레임워크가 2배 이상의 성능을 가지는 것으로 분석되었다. 따라서 본 연구에서 제안한 방법을 활용할 경우 정확한 물 사용량 예측이 가능해질 것이며, 상황에 따른 최적의 공급 방안을 수립할 수 있을 것이다.

It is an essential to predict water usage for establishing an optimal supply operation plan and reducing power consumption. However, the water usage by consumer has a non-linear characteristics due to various factors such as user type, usage pattern, and weather condition. Therefore, in order to predict the water consumption, we proposed the methodology linking various techniques that can consider non-linear characteristics of water use and we called it as KWD framework. Say, K-means (K) cluster analysis was performed to classify similar patterns according to usage of each individual consumer; then Wavelet (W) transform was applied to derive main periodic pattern of the usage by removing noise components; also, Deep (D) learning algorithm was used for trying to do learning of non-linear characteristics of water usage. The performance of a proposed framework or model was analyzed by comparing with the ARMA model, which is a linear time series model. As a result, the proposed model showed the correlation of 92% and ARMA model showed about 39%. Therefore, we had known that the performance of the proposed model was better than a linear time series model and KWD framework could be used for other nonlinear time series which has similar pattern with water usage. Therefore, if the KWD framework is used, it will be possible to accurately predict water usage and establish an optimal supply plan every the various event.

본 연구는 건물의 위치 정보만으로 태양광 발전을 예측할 수 있는 알고리즘을 개발하여 노후건축물을 대 상으로 건물에너지 효율성 향상을 위한 그린리모델링 기대효과 및 건물에너지 자립률 향상을 목표로 한다. 이를 위해, 기존 문헌에서의 태양광 발전 모델과 천공청명도 및 직산분리 방정식 등을 다중 회귀분석식으로 결합한 예 측 알고리즘을 개발하고, 테스트베드를 활용한 실증실험 데이터와의 검증을 통해 예측 알고리즘의 신뢰성을 검증 하였다. 예측 알고리즘의 신뢰성 검증결과, 회귀식의 설명력을 나타내는 R2값의 범위가 하절기(6월-8월) 기준 0.80-0.96으로 높은 예측정확도를 확보하였으며, 7곳 대상지의 건물에너지 자립률은 46%-60%로 산출되어 본 수 식이 그린리모델링 기대효과 예측 시 유용할 것으로 기대된다.

This study aims to develop a prediction algorithm that can predict solar power generation using only the location information of buildings, and to improve the expected effects of green remodeling for improving building energy efficiency and building energy self-sufficiency in aged buildings. As the results of this study, the range of the reliability verification of the prediction algorithm(R2 value) was 0.80-0.96 for the summer season (June-August) and the building energy self-sufficiency rates of the seven target sites were calculated to be 46%-60%. Through these results, this prediction algorithm were verified to be useful for predicting the effects of green remodeling.

연구목적: 이 연구는 토석류로 발생하는 토사유출량 예측 알고리즘을 개발하고, 이를 활용한 GIS 기반 사방댐 적정배치 의사결정 지원 시스템 구현을 목적으로 하였다. 연구방법: 평균 계류 폭과 길이를 이용 한 누적 토사유출량 예측 방법에 초기 붕괴량과 이에 영향하는 집수길이를 입력인자로 활용하여 토석 류로 인해 발생하는 누적 토사유출량 예측 알고리즘을 제시하였다. 연구결과: 알고리즘을 통해 산출된 예측 토사유출량과 실제 토사유출량은 평균 1.1배 차이가 나타나 정확도는 비교적 높았다. 또한 구현된 프로그램은 사방댐의 위치 및 규모를 결정하는 객관적인 지표로서 실무자의 합리적인 의사결정에 도 움을 줄 수 있다. 결론: 사방사업이 매년 시행되고 있는 상황에서 합리적인 사방댐 위치 및 규모 결정을 통해 산지토사재해 방재에 기여할 수 있을 것으로 기대된다.

Purpose: This study aims to develop an algorithm for predicting sediment discharge by debris flow, and develop GIS-based decision support system for optimal arrangement of check dam. Method: The average stream width and flow length were used to predict the cumulative sediment discharge by debris flow. At this time, the amount of slope failure on source area and average flow length were utilized as input factors. Result: The predicted sediment discharge calculated through the algorithm was 1.1 times different on average compared to the actual sediment discharge by debris flow. In addition, the program is an objective indicator that selects the location and size of the check dam, and it can help practitioners make rational decisions. Conclusion: The soil erosion control works are being implemented every year. Therefore, it is expected that the GIS-based decision support system for location and size of the check dam will contribute to the prevention of sediment-related disasters.

광용적맥파(PPG)는 빛의 흡수 변화를 통해 피부 미세혈관의 혈액량 변화를 비침습적으로 측정하는 방법으로, 웨어러 블 기기에서 심박수 및 산소포화도 측정에 널리 활용되고 있다. 특히 다양한 파장을 동시에 사용한 다중 파장 PPG는 단일 파 장 대비 인체 특성에 따른 간섭을 줄이고 측정 정확도를 높일 수 있음이 보고되었다. 본 논문에서는 이러한 광학 원리와 선행 연구를 바탕으로, 다중 파장 PPG 신호를 입력으로 하는 딥러닝 기반 테스토스테론 예측 알고리즘 구상을 제안한다. 알고리즘 설계는 다중 파장 신호의 동기화･정규화, 독립성분분석(ICA) 등을 통한 잡음 분리, 심박변이도(HRV) 등 추가 특징 추출, 그리 고 LSTM 계열 네트워크를 활용한 회귀 모델 학습 단계로 구성된다. 최종적으로 제안된 방식은 비침습적 연속 모니터링의 가 능성을 제시하나, 임상 데이터 부족과 생리적 메커니즘 미확인 등의 한계를 가지므로, 대규모 실증 연구가 뒤따라야 한다.

Photoplethysmography (PPG) is an optical biosensing technique that noninvasively monitors blood volume changes in the microvasculature by detecting variations in light absorption. Multi-wavelength PPG, which employs several light wavelengths simultaneously, has been shown to improve signal robustness and accuracy by separating contributions from different tissue layers. In this study, based on a survey of existing literature, we propose a design for a testosterone prediction algorithm using wearable multi-wavelength PPG signals. The algorithm concept includes: synchronized acquisition of multi-wavelength PPG, preprocessing such as interference removal using independent component analysis (ICA), feature extraction including heart rate variability and relevant user parameters, and a deep learning regression model to predict circadian testosterone variations. This literature-based framework highlights the potential of non-invasive hormone monitoring in wearable health devices. However, it remains a conceptual proposal: clinical validation and larger-scale data are required. Future work should focus on empirical testing, sensor optimization, and model refinement to establish practical utility.