Defect Detection Model Using Time Series Data Augmentation and Transformation

Time-series data provide important information in many fields,and their processing and analysis have been the focus of much research.However,detecting anomalies is very difficult due to data imbalance,temporal dependence,and noise.Therefore,methodologies for data augmentation and conversion of time series data into images for analysis have been studied.This paper proposes a fault detection model that uses time series data augmentation and transformation to address the problems of data imbalance,temporal dependence,and robustness to noise.The method of data augmentation is set as the addition of noise.It involves adding Gaussian noise,with the noise level set to 0.002,to maximize the generalization performance of the model.In addition,we use the Markov Transition Field(MTF)method to effectively visualize the dynamic transitions of the data while converting the time series data into images.It enables the identification of patterns in time series data and assists in capturing the sequential dependencies of the data.For anomaly detection,the PatchCore model is applied to show excellent performance,and the detected anomaly areas are represented as heat maps.It allows for the detection of anomalies,and by applying an anomaly map to the original image,it is possible to capture the areas where anomalies occur.The performance evaluation shows that both F1-score and Accuracy are high when time series data is converted to images.Additionally,when processed as images rather than as time series data,there was a significant reduction in both the size of the data and the training time.The proposed method can provide an important springboard for research in the field of anomaly detection using time series data.Besides,it helps solve problems such as analyzing complex patterns in data lightweight.

Weighted Forwarding in Graph Convolution Networks for Recommendation Information Systems

Recommendation Information Systems(RIS)are pivotal in helping users in swiftly locating desired content from the vast amount of information available on the Internet.Graph Convolution Network(GCN)algorithms have been employed to implement the RIS efficiently.However,the GCN algorithm faces limitations in terms of performance enhancement owing to the due to the embedding value-vanishing problem that occurs during the learning process.To address this issue,we propose a Weighted Forwarding method using the GCN(WF-GCN)algorithm.The proposed method involves multiplying the embedding results with different weights for each hop layer during graph learning.By applying the WF-GCN algorithm,which adjusts weights for each hop layer before forwarding to the next,nodes with many neighbors achieve higher embedding values.This approach facilitates the learning of more hop layers within the GCN framework.The efficacy of the WF-GCN was demonstrated through its application to various datasets.In the MovieLens dataset,the implementation of WF-GCN in LightGCN resulted in significant performance improvements,with recall and NDCG increasing by up to+163.64%and+132.04%,respectively.Similarly,in the Last.FM dataset,LightGCN using WF-GCN enhanced with WF-GCN showed substantial improvements,with the recall and NDCG metrics rising by up to+174.40%and+169.95%,respectively.Furthermore,the application of WF-GCN to Self-supervised Graph Learning(SGL)and Simple Graph Contrastive Learning(SimGCL)also demonstrated notable enhancements in both recall and NDCG across these datasets.

Systematic Security Guideline Framework through Intelligently Automated Vulnerability Analysis

This research aims to propose a practical framework designed for the automatic analysis of a product’s comprehensive functionality and security vulnerabilities,generating applicable guidelines based on real-world software.The existing analysis of software security vulnerabilities often focuses on specific features or modules.This partial and arbitrary analysis of the security vulnerabilities makes it challenging to comprehend the overall security vulnerabilities of the software.The key novelty lies in overcoming the constraints of partial approaches.The proposed framework utilizes data from various sources to create a comprehensive functionality profile,facilitating the derivation of real-world security guidelines.Security guidelines are dynamically generated by associating functional security vulnerabilities with the latest Common Vulnerabilities and Exposure(CVE)and Common Vulnerability Scoring System(CVSS)scores,resulting in automated guidelines tailored to each product.These guidelines are not only practical but also applicable in real-world software,allowing for prioritized security responses.The proposed framework is applied to virtual private network(VPN)software,wherein a validated Level 2 data flow diagram is generated using the Spoofing,Tampering,Repudiation,Information Disclosure,Denial of Service,and Elevation of privilege(STRIDE)technique with references to various papers and examples from related software.The analysis resulted in the identification of a total of 121 vulnerabilities.The successful implementation and validation demonstrate the framework’s efficacy in generating customized guidelines for entire systems,subsystems,and selected modules.

Tests on Alkali-Activated Slag Foamed Concrete with Various Water-Binder Ratios and Substitution Levels of Fly Ash

To provide basic data for the reasonable mixing design of the alkali-activated (AA) foamed concrete as a thermal insulation material for a floor heating system, 9 concrete mixes with a targeted dry density less than 400 kg/m3 were tested. Ground granulated blast-furnace slag (GGBS) as a source material was activated by the following two types of alkali activators: 10% Ca(OH)2 and 4% Mg(NO3)2, and 2.5% Ca(OH)2 and 6.5% Na2SiO3. The main test parameters were water-to-binder (W/B) ratio and the substitution level (RFA) of fly ash (FA) for GGBS. Test results revealed that the dry density of AA GGBS foamed concrete was independent of the W/B ratio an RFA, whereas the compressive strength increased with the decrease in W/B ratio and with the increase in RFA up to 15%, beyond which it decreased. With the increase in the W/B ratio, the amount of macro capillaries and artificial air pores increased, which resulted in the decrease of compressive strength. The magnitude of the environmental loads of the AA GGBS foamed concrete is independent of the W/B ratio and RFA. The largest reduction percentage was found in the photochemical oxidation potential, being more than 99%. The reduction percentage was 87% - 93% for the global warming potential, 81% - 84% for abiotic depletion, 79% - 84% for acidification potential, 77% - 85% for eutrophication potential, and 73% - 83% for human toxicity potential. Ultimately, this study proved that the developed AA GGBS foamed concrete has a considerable promise as a sustainable construction material for nonstructural element.

Association of resting heart rate and hypertension stages on all-cause and car- diovascular mortality among elderly Koreans： the Kangwha Cohort Study

Background Elevated resting heart rate and hypertension independently increase the risk of mortality. However, their combined ef- fect on mortality in stages of hypertension according to updated clinical guidelines among dderly population is unclear. Methods We fol- lowed a cohort of 6100 residents （2600 males and 3500 females） of Kangwha County, Korea, ranging from 55 to 99 year-olds as of March 1985, for all-cause and cardiovascular mortality for 20.8 years until December 31, 2005. Mortality data were collected through telephone calls and visits （to 1991）, and were confirmed by death record matching with the National Statistical Office （1992-2005）. Hazard ratios were calculated for all-cause and cardiovascular mortality by resting heart rate and hypertension defined by Eighth Joint National Committee crite- ria using the Cox proportional hazard model after controlling for confounding factors. Results The hazard ratios associated with resting heart rate 〉 80 beats/min were higher in hypertensive men compared with normotensives with heart rate of 61-79 beats/rain, with hazard ratios values of 1.43 （95% CI： 1.00-1.92） on all-cause mortality for prehypertension, 3.01 （95% CI： 1.07-8.28） on cardiovascular mortality for prehypertension, and 8.34 （95% CI： 2.52-28.19） for stage 2 hypertension. Increased risk （HR： 3.54, 95% CI： 1.16-9.21） was observed among those with both a resting heart rate 〉 80 beats/rain and prehypertension on cardiovascular mortality in women. Conclusions Indi- viduals with coexisting elevated resting heart rate and hypertension, even in prehypertension, have a greater risk for all-cause and cardiovas- cular mortality compared to those with elevated resting heart rate or hypertension alone. These findings suggest that elevated resting heart rate should not be regarded as a less serious risk factor in elderly hypertensive patients.

Comparison of Risk Assessment for a Nuclear Power Plant Construction Project Based on Analytic Hierarchy Process and Fuzzy Analytic Hierarchy Process

Recently, plant construction throughout the world, including nuclear power plant construction, has grown significantly. The scale of Korea’s nuclear power plant construction in particular, has increased gradually since it won a contract for a nuclear power plant construction project in the United Arab Emirates in 2009. However, time and monetary resources have been lost in some nuclear power plant construction sites due to lack of risk management ability. The need to prevent losses at nuclear power plant construction sites has become more urgent because it demands professional skills and large-scale resources. Therefore, in this study, the Analytic Hierarchy Process (AHP) and Fuzzy Analytic Hierarchy Process (FAHP) were applied in order to make comparisons between decision-making methods, to assess the potential risks at nuclear power plant construction sites. To suggest the appropriate choice between two decision-making methods, a survey was carried out. From the results, the importance and the priority of 24 risk factors, classified by process, cost, safety, and quality, were analyzed. The FAHP was identified as a suitable method for risk assessment of nuclear power plant construction, compared with risk assessment using the AHP. These risk factors will be able to serve as baseline data for risk management in nuclear power plant construction projects.

Deep Learning-Based Action Classification Using One-Shot Object Detection

Deep learning-based action classification technology has been applied to various fields,such as social safety,medical services,and sports.Analyzing an action on a practical level requires tracking multiple human bodies in an image in real-time and simultaneously classifying their actions.There are various related studies on the real-time classification of actions in an image.However,existing deep learning-based action classification models have prolonged response speeds,so there is a limit to real-time analysis.In addition,it has low accuracy of action of each object ifmultiple objects appear in the image.Also,it needs to be improved since it has a memory overhead in processing image data.Deep learning-based action classification using one-shot object detection is proposed to overcome the limitations of multiframe-based analysis technology.The proposed method uses a one-shot object detection model and a multi-object tracking algorithm to detect and track multiple objects in the image.Then,a deep learning-based pattern classification model is used to classify the body action of the object in the image by reducing the data for each object to an action vector.Compared to the existing studies,the constructed model shows higher accuracy of 74.95%,and in terms of speed,it offered better performance than the current studies at 0.234 s per frame.The proposed model makes it possible to classify some actions only through action vector learning without additional image learning because of the vector learning feature of the posterior neural network.Therefore,it is expected to contribute significantly to commercializing realistic streaming data analysis technologies,such as CCTV.

Comparison of School Building Construction Costs Estimation Methods Using Regression Analysis, Neural Network, and Support Vector Machine

Accurate cost estimation at the early stage of a construction project is key factor in a project’s success. But it is difficult to quickly and accurately estimate construction costs at the planning stage, when drawings, documentation and the like are still incomplete. As such, various techniques have been applied to accurately estimate construction costs at an early stage, when project information is limited. While the various techniques have their pros and cons, there has been little effort made to determine the best technique in terms of cost estimating performance. The objective of this research is to compare the accuracy of three estimating techniques (regression analysis (RA), neural network (NN), and support vector machine techniques (SVM)) by performing estimations of construction costs. By comparing the accuracy of these techniques using historical cost data, it was found that NN model showed more accurate estimation results than the RA and SVM models. Consequently, it is determined that NN model is most suitable for estimating the cost of school building projects.

Shadow Detection and Removal From Photo-Realistic Synthetic Urban Image Using Deep Learning

Recently,virtual reality technology that can interact with various data is used for urban design and analysis.Reality,one of the most important elements in virtual reality technology,means visual expression so that a person can experience three-dimensional space like reality.To obtain this realism,real-world data are used in the various fields.For example,in order to increase the realism of 3D modeled building textures real aerial images are utilized in 3D modelling.However,the aerial image captured during the day can be shadowed by the sun and it can cause the distortion or deterioration of image.To resolve this problem,researches on detecting and removing shadows have been conducted,but the detecting and removing shadow is still considered as a challenging problem.In this paper,we propose a novel method for detecting and removing shadows using deep learning.For this work,we first a build a new dataset of photo-realistic synthetic urban data based on the virtual environment using 3D spatial information provided by VWORLD.For detecting and removing shadow from the dataset,firstly,the 1-channel shadow mask image is inferred from the 3-channel shadow image through the CNN.Then,to generate a shadow-free image,a 3-channel shadow image and a detected 1-channel shadow mask into the GAN is executed.From the experiments,we can prove that the proposed method outperforms the existing methods in detecting and removing shadow.

Comparison of Missing Data Imputation Methods in Time Series Forecasting

Time series forecasting has become an important aspect of data analysis and has many real-world applications.However,undesirable missing values are often encountered,which may adversely affect many forecasting tasks.In this study,we evaluate and compare the effects of imputationmethods for estimating missing values in a time series.Our approach does not include a simulation to generate pseudo-missing data,but instead perform imputation on actual missing data and measure the performance of the forecasting model created therefrom.In an experiment,therefore,several time series forecasting models are trained using different training datasets prepared using each imputation method.Subsequently,the performance of the imputation methods is evaluated by comparing the accuracy of the forecasting models.The results obtained from a total of four experimental cases show that the k-nearest neighbor technique is the most effective in reconstructing missing data and contributes positively to time series forecasting compared with other imputation methods.

Effect of Partial Ground Plane Removal on the Radiation Characteristics of a Microstrip Antenna

This study presents a new, simple method for reducing the back-lobe radiation of a microstrip antenna (MSA) by a partially removed ground plane of the antenna. The effect of the partial ground plane removal in different configurations on the radiation characteristics of a MSA are investigated numerically. The partial ground plane removal reduces the backlobe radiation of the MSA by suppressing the surface wave diffraction from the edges of the antenna ground plane. For further improving the front-to-back (F/B) ratio of the MSA, a new soft-surface configuration consisting of an array of stand-up split ring resonators (SRRs) are placed on a bare dielectric substrate near the two ground plane edges. Compared to the F/B ratio of a conventional MSA with a full ground plane of the same size, an improved F/B ratio of 9.7 dB has been achieved experimentally for our proposed MSA.

Chrysoeriol ameliorates hyperglycemia by regulating the carbohydrate metabolic enzymes in streptozotocin-induced diabetic rats

The present study aimed to evaluate the effects of chrysoeriol from Cardiospermum halicacabum in streptozotocin induced Wistar rats.Thirty rats were categorized as control,diabetic control supplemented with 0,20 mg/kg chrysoeriol and 600μg/kg BW of glibenclamide for 45-day trial period.Our results indicated that the inclusion of chrysoeriol(20 mg/kg)showed a significant reduction in plasma glucose,hemoglobin and glycosylated hemoglobin level with a rising of plasma insulin sensitivity.Further,downregulated enzymes including glucose 6-phosphatase,fructose 1,6-bisphosphatase,and glycogen phosphorylase as well upregulated enzymes such as hexokinase,glucose-6-phosphate dehydrogenase,pyruvate kinase,and hepatic glycogen content.There was a diminish action found in liver glycogen synthase of tested rat with a rise in gamma-glutamyl transpeptidase,towards normal levels upon treatment with chrysoeriol.The histopathological study confirmed that renewal of the beta cells of pancreatic of chrysoeriol and glibenclamide treated rats.In addition,the molecular docking of chrysoeriol against glycolytic enzymes including hexokinase,glucose-6-phosphate dehydrogenase,pyruvate kinase,using Argus software shows chrysoeriol had greatest ligand binding energy as equivalent to glibenclamide,as a standard drug.Thus,chrysoeriol found to be non-toxic with potential regulation on glycemic control and upregulation of the carbohydrate metabolic enzymes.

The Architectural Expression of Space and Form Created by the Light in the Works of Alvaro Siza

The light is an important element which helps people perceive objects. Therefore, it is important for architects to make the light and space be in harmony with each other. In this study, we analyzed the works of Alvaro Siza with a view to understand the conceptual value of the light expressed in his works and his principles in controlling it. According to the results of the study, the Siza’s architecture is not a mere theoretical one trapped inside formality, but is a sensual and experiential one based on the locality. He was willing to use void spaces to invite the light in free-flowing plans, in order to invigorate and extend architectural spatiality to create deeper visual effect. In addition, the refined light in his works helped visitors experience the continuous forms and spaces by their own movements, while using the changes of the light to stimulate the interest of visitors and highlight the sequence of spaces.

Explainable Anomaly Detection Using Vision Transformer Based SVDD

Explainable AI extracts a variety of patterns of data in the learning process and draws hidden information through the discovery of semantic relationships.It is possible to offer the explainable basis of decision-making for inference results.Through the causality of risk factors that have an ambiguous association in big medical data,it is possible to increase transparency and reliability of explainable decision-making that helps to diagnose disease status.In addition,the technique makes it possible to accurately predict disease risk for anomaly detection.Vision transformer for anomaly detection from image data makes classification through MLP.Unfortunately,in MLP,a vector value depends on patch sequence information,and thus a weight changes.This should solve the problem that there is a difference in the result value according to the change in the weight.In addition,since the deep learning model is a black box model,there is a problem that it is difficult to interpret the results determined by the model.Therefore,there is a need for an explainablemethod for the part where the disease exists.To solve the problem,this study proposes explainable anomaly detection using vision transformerbasedDeep Support Vector Data Description(SVDD).The proposed method applies the SVDD to solve the problem of MLP in which a result value is different depending on a weight change that is influenced by patch sequence information used in the vision transformer.In order to draw the explainability of model results,it visualizes normal parts through Grad-CAM.In health data,both medical staff and patients are able to identify abnormal parts easily.In addition,it is possible to improve the reliability of models and medical staff.For performance evaluation normal/abnormal classification accuracy and f-measure are evaluated,according to whether to apply SVDD.Evaluation Results The results of classification by applying the proposed SVDD are evaluated excellently.Therefore,through the proposed method,it is possible to improve the reliability of decision-making by identifying the location of the disease and deriving consistent results.

Multiple-Object Tracking Using Histogram Stamp Extraction in CCTV Environments

Object tracking,an important technology in the field of image processing and computer vision,is used to continuously track a specific object or person in an image.This technology may be effective in identifying the same person within one image,but it has limitations in handling multiple images owing to the difficulty in identifying whether the object appearing in other images is the same.When tracking the same object using two or more images,there must be a way to determine that objects existing in different images are the same object.Therefore,this paper attempts to determine the same object present in different images using color information among the unique information of the object.Thus,this study proposes a multiple-object-tracking method using histogram stamp extraction in closed-circuit television applications.The proposed method determines the presence or absence of a target object in an image by comparing the similarity between the image containing the target object and other images.To this end,a unique color value of the target object is extracted based on its color distribution in the image using three methods:mean,mode,and interquartile range.The Top-N accuracy method is used to analyze the accuracy of each method,and the results show that the mean method had an accuracy of 93.5%(Top-2).Furthermore,the positive prediction value experimental results show that the accuracy of the mean method was 65.7%.As a result of the analysis,it is possible to detect and track the same object present in different images using the unique color of the object.Through the results,it is possible to track the same object that can minimize manpower without using personal information when detecting objects in different images.In the last response speed experiment,it was shown that when the mean was used,the color extraction of the object was possible in real time with 0.016954 s.Through this,it is possible to detect and track the same object in real time when using the proposed method.

Deep Learning Model Ensemble for the Accuracy of Classification Degenerative Arthritis

Artificial intelligence technologies are being studied to provide scientific evidence in the medical field and developed for use as diagnostic tools.This study focused on deep learning models to classify degenerative arthritis into Kellgren–Lawrence grades.Specifically,degenerative arthritis was assessed by X-ray radiographic images and classified into five classes.Subsequently,the use of various deep learning models was investigated for automating the degenerative arthritis classification process.Although research on the classification of osteoarthritis using deep learning has been conducted in previous studies,only local models have been used,and an ensemble of deep learning models has never been applied to obtain more accurate results.To address this issue,this study compared the classification performance of deep learning models,includingVGGNet,DenseNet,ResNet,TinyNet,EfficientNet,MobileNet,Xception,and ViT,on a dataset commonly used for osteoarthritis classification tasks.Our experimental results verified that even without applying a separate methodology,the performance of the ensemble was comparable to that of existing studies that only used the latest deep learning model and changed the learning method.From the trained models,two ensembles were created and evaluated:weight and specialist.The weight ensemble showed an improvement in accuracy of 1%,and the proposed specialist ensemble improved accuracy,precision,recall,and F1 score by 5%,6%,6%,and 6%,respectively,compared with the results of prior studies.

Effects of La^(3+) on microwave dielectric properties of(Pb_(0.5)Ca_(0.5))(Fe-(0.5)Ta_(0.5))O_3 ceramics

This work investigated the microwave dielectric properties of A-site substitution by rare earth La3＋in（Pb0.5Ca0.5）（Fe0.5Ta0.5）O3（PCFT） system.A single perovskite phase was obtained only when the doping content was 2%.Suitable La3＋ doping improved microwave dielectric performances.Excessive La3＋doping caused the formation of secondary phase,which resulted in the decreasing of permittivity εrand quality factor Qfvalues.Especially,when the doping content is 2%-5%,permittivity εrwas above 75 and Qfvalues were 6 902-7 416 GHz.

SlowFast Based Real-Time Human Motion Recognition with Action Localization

Artificial intelligence is increasingly being applied in the field of video analysis,particularly in the area of public safety where video surveillance equipment such as closed-circuit television(CCTV)is used and automated analysis of video information is required.However,various issues such as data size limitations and low processing speeds make real-time extraction of video data challenging.Video analysis technology applies object classification,detection,and relationship analysis to continuous 2D frame data,and the various meanings within the video are thus analyzed based on the extracted basic data.Motion recognition is key in this analysis.Motion recognition is a challenging field that analyzes human body movements,requiring the interpretation of complex movements of human joints and the relationships between various objects.The deep learning-based human skeleton detection algorithm is a representative motion recognition algorithm.Recently,motion analysis models such as the SlowFast network algorithm,have also been developed with excellent performance.However,these models do not operate properly in most wide-angle video environments outdoors,displaying low response speed,as expected from motion classification extraction in environments associated with high-resolution images.The proposed method achieves high level of extraction and accuracy by improving SlowFast’s input data preprocessing and data structure methods.The input data are preprocessed through object tracking and background removal using YOLO and DeepSORT.A higher performance than that of a single model is achieved by improving the existing SlowFast’s data structure into a frame unit structure.Based on the confusion matrix,accuracies of 70.16%and 70.74%were obtained for the existing SlowFast and proposed model,respectively,indicating a 0.58%increase in accuracy.Comparing detection,based on behavioral classification,the existing SlowFast detected 2,341,164 cases,whereas the proposed model detected 3,119,323 cases,which is an increase of 33.23%.

Abnormal Behavior Detection Using Deep-Learning-Based Video Data Structuring

With the increasing number of digital devices generating a vast amount of video data,the recognition of abnormal image patterns has become more important.Accordingly,it is necessary to develop a method that achieves this task using object and behavior information within video data.Existing methods for detecting abnormal behaviors only focus on simple motions,therefore they cannot determine the overall behavior occurring throughout a video.In this study,an abnormal behavior detection method that uses deep learning(DL)-based video-data structuring is proposed.Objects and motions are first extracted from continuous images by combining existing DL-based image analysis models.The weight of the continuous data pattern is then analyzed through data structuring to classify the overall video.The performance of the proposed method was evaluated using varying parameter settings,such as the size of the action clip and interval between action clips.The model achieved an accuracy of 0.9817,indicating excellent performance.Therefore,we conclude that the proposed data structuring method is useful in detecting and classifying abnormal behaviors.

Power Information System Database Cache Model Based on Deep Machine Learning

At present,the database cache model of power information system has problems such as slow running speed and low database hit rate.To this end,this paper proposes a database cache model for power information systems based on deep machine learning.The caching model includes program caching,Structured Query Language(SQL)preprocessing,and core caching modules.Among them,the method to improve the efficiency of the statement is to adjust operations such as multi-table joins and replacement keywords in the SQL optimizer.Build predictive models using boosted regression trees in the core caching module.Generate a series of regression tree models using machine learning algorithms.Analyze the resource occupancy rate in the power information system to dynamically adjust the voting selection of the regression tree.At the same time,the voting threshold of the prediction model is dynamically adjusted.By analogy,the cache model is re-initialized.The experimental results show that the model has a good cache hit rate and cache efficiency,and can improve the data cache performance of the power information system.It has a high hit rate and short delay time,and always maintains a good hit rate even under different computer memory;at the same time,it only occupies less space and less CPU during actual operation,which is beneficial to power The information system operates efficiently and quickly.