In order to achieve fault recognition for isolating switch infrared images, this paper utilizes an improved SLIC algorithm to segment and label the fault areas of the isolating switch based on color space conversion, ...
详细信息
This paper investigates the effect of Leca-filled barriers, both single and double-walled trenches, on mitigating ground vibrations due to harmonic loads. A three-dimensional finite element program, validated in compa...
详细信息
This paper investigates the effect of Leca-filled barriers, both single and double-walled trenches, on mitigating ground vibrations due to harmonic loads. A three-dimensional finite element program, validated in comparison by aforementioned studies, was used alongside automated models created via Plaxis and Python integration. This approach facilitated the evaluation of trench effectiveness in both active and passive design scenarios. Our findings suggest that optimal trench dimensions for effective vibration reduction in active designs are a depth and width of approximately 1 lambda r and 0.2 lambda r, respectively. In passive designs, while trench depth becomes less significant, width plays a crucial role in both single and double-wall systems. Additionally, a support vector machine algorithm was developed to forecast the performance of single-wall trenches, showing a high correlation with numerical model outcomes. This underscores the algorithm's utility in predicting trench efficiency, highlighting the practical application of machine learning in geotechnical engineering. Three dimensional investigating on ground vibration attenuation through leca-filled trenches. image
Traditional resident travel survey methods, such as paper questionnaire, telephone interview and mail inquiry, have disadvantage of low data accuracy, difficult organization and limited sampling size. GPS based travel...
详细信息
ISBN:
(数字)9781510652071
ISBN:
(纸本)9781510652071;9781510652064
Traditional resident travel survey methods, such as paper questionnaire, telephone interview and mail inquiry, have disadvantage of low data accuracy, difficult organization and limited sampling size. GPS based travel survey method is playing an increasingly important role in modern transportation planning. This paper proposes an innovative method for detecting individual trip mode recognition by using mobile phone GPS positioning data. First, a smartphone GPS sensor-based application is developed for multi-mode travel trajectory data collection. Data characteristics of different trip modes are deeply analyzed and the characterization indexes of different modes are put forward. Second, a supportvectormachine (SVM) algorithm is proposed for trip mode detection. SVM can map low-dimensional data to high-dimensional space for segmentation, is especially suitable for traffic mode recognition. Results show that the average mode detection accuracy reaches 92% for walk, bike, bus and car. This paper can provide solid data support for urban traffic planning.
This article aims to explore the use of big data and integrated learning technologies to build a more efficient and accurate financial enterprise risk assessment system. By analyzing the limitations of current financi...
详细信息
This article aims to explore the use of big data and integrated learning technologies to build a more efficient and accurate financial enterprise risk assessment system. By analyzing the limitations of current financial risk assessment methods, this paper proposes a comprehensive framework based on random forests. The performance of a financial enterprise risk assessment system based on random forest was evaluated through four experiments in the experimental stage. Through systematic comparative experiments, it was found that the random forest method showed better performance compared to the supportvectormachine (SVM) algorithm, with an accuracy of 92%, SVM at 85%, recall index at 90%, better than SVM at 82%, and F1 score of 91%, higher than SVM at 83%. In the multi scenario risk assessment experiment, the accuracy of random forest in conventional market scenarios is 85%, the recall rate is 80%, and the F1 score is 82%. In real-time data evaluation experiments, the accuracy of the model gradually increased from the initial 85% to 95% at 10 different time points. The above experimental data results collectively confirm that systems based on random forests have strong adaptability and efficient risk assessment capabilities in diverse financial environments.
This paper presents a unique security approach for detecting cyber-attacks against embedded systems (ESs). The proposed approach has been shaped within an architectural framework called anomalous resource consumption ...
详细信息
This paper presents a unique security approach for detecting cyber-attacks against embedded systems (ESs). The proposed approach has been shaped within an architectural framework called anomalous resource consumption detection (ARCD). The approach's detection mechanism detects cyber-attacks by distinguishing anomalous performance and resource consumption patterns from a pre-determinable reference model. The defense mechanism of this approach acts as an additional layer of protection for ESs. This technique's effectiveness was previously evaluated statistically, and in this paper, we tested this approach's efficiency computationally by using the support-vectormachinealgorithm. The datasets were generated and collected based on a testbed model, where it was run repeatedly under different operation conditions (normal cases (Rs) versus attacked cases). The executed attack scenarios are 1) denial-of-service (DoS);2) brute force (BF);and 3) remote code execution (RCE), and man-in-the-middle (MITM). A septenary tuple model, which consists of seven determinants that are analyzed based on seven statistical criteria, is the core of the detection mechanism. The prediction accuracy in terms of classifying anomalous patterns compared to normal patterns based on the confusion matrix revealed promising results, proving this approach's effectiveness, where the final results confirmed very high prediction accuracies in terms of distinguishing anomalous patterns from the typical patterns. Integrating the ARCD concept into an operating system's functionality could help software developers augment the existing security countermeasures of ESs. Adopting the ARCD approach will pave the way for software engineers to build more secure operating systems in line with the embedded system's capabilities, without depleting its resources.
Many scholars mentioned various dimensions and complex relations for manufacturing flexibility that implementing all of them is not possible for a manufacturing firm. On the other hand, today's dynamic environment...
详细信息
Many scholars mentioned various dimensions and complex relations for manufacturing flexibility that implementing all of them is not possible for a manufacturing firm. On the other hand, today's dynamic environment convinces flexible organizations to create capabilities in order to take over competitors. Hence, the aim of this study is to determine dominant groups of flexibility for manufacturing firms and to prioritize them under the influence of dynamic organizational capabilities. In this research, firstly components of dynamic organizational capabilities and flexibility of manufacturing are identified by content analysis method. Then, based on that, taxonomy for Iran's manufacturing firms was determined using support vector machine algorithm. In the next step, based on experts' view using FDEMATEL method, conceptual model for relationship of manufacturing flexibility dimension as well as dynamic capabilities are provided. Conceptual model in three flexibility clusters was tested by structural equation modeling, and dominant groups were prioritized based on dynamic organizational capabilities. Results show that the best number of clusters is three. Results also show that dynamic organizational capabilities not only affect flexibility dimensions of manufacturing but also this influence is different in manufacturing firms with various industry fields.
An efficient diagnosis method dedicated to embedded wiring network based on reflectometry technique is developed in this study. The proposed methodology is based on the two complementary steps. In the first step, the ...
详细信息
An efficient diagnosis method dedicated to embedded wiring network based on reflectometry technique is developed in this study. The proposed methodology is based on the two complementary steps. In the first step, the time-domain reflectometry (TDR) method is simulated, by RLCG (R: resistance, L: inductance, C: capacitance and G: conductance) circuit model and the numerical finite-difference time-domain method, and at the same time the datasets are created. In the second step, the supportvectormachine (SVM) algorithm is combined with a principal component analysis to identify the faults on wiring network from the TDR response. Two types of SVM models have been used in the diagnosis procedure: SVM classifiers and SVM regression models. In order to illustrate the performances and the feasibility of the proposed approach, numerical and experimental results are presented.
Based on the research of predicting β-hairpin motifs in proteins,we apply Random Forest and support vector machine algorithm to predict β-hairpin motifs in ArchDB40 *** motifs with the loop length of 2 to 8 amino ac...
详细信息
Based on the research of predicting β-hairpin motifs in proteins,we apply Random Forest and support vector machine algorithm to predict β-hairpin motifs in ArchDB40 *** motifs with the loop length of 2 to 8 amino acid residues are extracted as research object and the fixed-length pattern of 12 amino acids are *** using the same characteristic parameters and the same test method,Random Forest algorithm is more effective than supportvector *** addition,because of Random Forest algorithm doesn't produce overfitting phenomenon while the dimension of characteristic parameters is higher,we use Random Forest based on higher dimension characteristic parameters to predict β-hairpin *** better prediction results are obtained;the overall accuracy and Matthew's correlation coefficient of 5-fold cross-validation achieve 83.3% and 0.59,respectively.
In order to cope with the complex risk environment of the current financial market, achieve portfolio optimization and accurate risk prediction, this paper conducts effective research using SVM algorithm. This article...
详细信息
In order to cope with the complex risk environment of the current financial market, achieve portfolio optimization and accurate risk prediction, this paper conducts effective research using SVM algorithm. This article uses stock data as a sample to empirically analyze the risk return and risk prediction performance of investment portfolio strategies based on SVM algorithm. Compared with traditional index fund investment strategies, the risk resistance of investment portfolio strategies is significantly improved, and the risk return is also stable at a high level. In addition, with the support of SVM algorithm, the risk prediction error level in the financial market remains within a relatively low range. From the perspective of practical applications, the financial market investment portfolio selection and risk prediction based on SVM algorithm has strong feasibility.
There are many accidents that occur daily on highways, roads, and there are many reasons for it to occur. According to surveys done the major cause of the accident was either the driver was not completely awake or the...
详细信息
ISBN:
(纸本)9781665426428
There are many accidents that occur daily on highways, roads, and there are many reasons for it to occur. According to surveys done the major cause of the accident was either the driver was not completely awake or they were feeling drowsy and this resulted in accidents either major or minor. Hence, detection of the driver's fatigue and alerting on time is the main motive of this research. Few methods which detect drowsiness are intrusive and distract the driver whereas some methods of heavy sensors are installed which are expensive. Therefore, in this study, a budget-friendly, a real-time driver's fatigue detection system is developed. The proposed system incorporates the Histogram of Oriented Gradients [HOG] algorithm and supportvectormachine [SVM] algorithm for face detection and Regression Trees algorithm to get the facial landmarks and calculate two major factors which can help us determine the status of driver fatigue. The two major factors that help us determine the driver's fatigue are eye aspect ratio, mouth aspect ratio. Here, this research study will calculate the values first when the driver of the vehicle is completely awake. Such values will be recorded and later it will be set as threshold values. After threshold values are set, the Eye Aspect Ratio and Mouth Opening Ratio are recorded. Then the recorded values are compared with the threshold values. If there are deviations in the values measured then the system sends out an alarm saying that drowsiness is detected. This proposed system helps in the reduction of accidents happening due to Drivers fatigue.
暂无评论