Search

In this paper, exploiting a geometric argument, a novel and intuitive approach to portfolio diversification is proposed. The risk-adjusted geometric diversified portfolio is obtained as the point that is equally distant, for a given distance, from the vertices of the simplex, as they represent the single asset portfolios, the worst portfolios in terms of diversification. The definition of risk-adjusted distance as a special case of weighted Euclidean distance permits to introduce the information on the risks of the assets composing the portfolio in a very general way. The closed form solution for the allocation problem is provided and interesting theoretical properties are proved. Further, a direct comparison with Rao's Quadratic Entropy maximization problem is outlined, thus yielding a different perspective to the use of such entropy as a diversification measure. Finally, the effectiveness of our proposal is emphasized through a comprehensive empirical out-of-sample exercise on real financial data. [ABSTRACT FROM AUTHOR]

Multi-layer solid-state lidar has become an important tool for environment perception of unmanned platform,and has been widely used in vehicle-mounted environment modeling.Due to the low resolution of lidar,the sensitivity of environmental noise,and the complexity of the scene,the fast and effective segmentation of the scene becomes a key problem in the real-time environment modeling.In view of the obvious curvature difference between buildings and vegetation in the actual collected point cloud data,this paper proposes an improved fast segmentation method of 3D point cloud based on multi-layer lidar.After the initial segmentation of building facade is realized based on curvature segmentation,the weighted Euclidean clustering is used for the second iterative segmentation of the initial segmented point cloud,which can reduce the iterative process and avoid falling into local optimum.Through the unmanned platform data acquisition and processing experiments and public data experiments,the effectiveness of this method in the segmentation of building and vegetation is verified.According to the final segmentation results of the scene,the over segmentation rate,under segmentation rate and correct segmentation rate of the scene are counted,and compared with the traditional region growing segmentation algorithm.The results show that the algorithm has strong applicability and segmentation accuracy in different scenes.

In this paper, we study the retrieval of desired or relevant points of interest, a set of spatial skyline points, related to a set of query points to establish distance restrictions. Note that each point of interest has different importance, assigned to each of them as weight, and the weighted Euclidean distance is used. In order to efficiently handle the weighted spatial skyline queries, this research presents a novel MapReduce-based solution for the first time. The proposed method prevents the bottleneck of centrally finding the global skyline from the local skylines and reduces the dominance test by performing the necessary dominance tests in parallel. Finally, the experimental results show that the proposed method obtains significant performance improvement. [ABSTRACT FROM AUTHOR]

Cell voltage inconsistency in a battery pack is an important signal released by the deterioration of battery performance. In this paper, voltage inconsistency is categorized into static inconsistency and dynamic inconsistency, and the latter contains progressive fluctuation fault and sudden fluctuation fault. For voltage dynamic inconsistency, this paper innovatively proposes a fault diagnosis and type identification method based on weighted Euclidean distance evaluation and statistical analysis. Specifically, firstly, the Euclidean distance evaluation method is used to quantify the cumulative length of the voltage curve of each individual cell in the time window, and at the same time, different forgetting factors are weighted on the voltage line segments to mitigate the fault diagnostic delay and memory effect defects of the time window. Then, a voltage abnormality evaluation coefficient is introduced to characterize the degree of inconsistent fluctuation of the cell voltage, and statistical methods are used to find a reasonable threshold. Further, fault type identification algorithm layer is conducted to identify the type of cell voltage fluctuation by using the optimized correlation coefficient method while the cell is detected by the fault diagnosis algorithm layer. Finally, the effectiveness of the proposed fault diagnosis strategy is verified by experimental data, and an online platform is utilized to obtain voltage data with different fault characteristics to test the practical application of the method. By comparing the proposed method with various data-driven methods with the same data evaluation significance, the results show that the method in this paper is more robust to static voltage inconsistency and the length of the time window, and is capable to recognize the various data patterns of potential threats, with higher accuracy and computational efficiency. • Euclidean distance evaluation is used for cell voltage inconsistency fault diagnosis. • Forgetting factor is used to mitigate fault diagnosis delay and memory effect defects of time window. • Optimized correlation coefficient is used to isolate pattern of cell voltage inconsistent fluctuations. • The accuracy is more than 99%. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

• A new fast and robust i-vectors scoring approach for automatic speaker recognition. • Combining Euclidean distance and Inner product to evaluate similarity in voice biometrics. • Improving accuracy and computation cost in automatic speaker recognition. • Use of Neumann series decomposition to fit a fast scoring model in voice biometrics. • Evaluate implementations using real life speech corpuses. It is commonly agreed that the main performance indicators in real life biometric applications are: accuracy, calibration quality and computation cost in the case of large databases use. Thus, the Gaussian Probabilistic Linear Discriminant Analysis (GPLDA) has been considered, during the last decade, as one of the most promising scoring techniques in Automatic Speaker Recognition. In this paper, the Algerian Modern Colloquial Arabic Speech Corpus has been used to evaluate a new i-vectors scoring approach based on Neumann series decomposition to fit the Weighted Euclidean Distance and Weighted Inner Product scoring models. This realistic evaluation investigates how this new approach can improve the global recognition performance compared to the GPLDA baseline system, considered as a reference point. The obtained results have shown that the proposed method outperforms the GPLDA baseline system in terms of recognition accuracy and calibration quality. More interestingly, the computational cost of the proposed method is significantly reduced compared to the GPLDA baseline counterpart. These results have an important implication in real-life speaker verification scenarios, especially in some tracking applications, where the computation cost is one of the main concerns besides performance. Image, graphical abstract [ABSTRACT FROM AUTHOR]

Graphical abstract Highlights • A Gaussian mixture model to classify the pixel distribution of main brain tissues is introduced. • A hemisphere approach is proposed. • Mixing probabilities at the sub-class and class levels are estimated. • The k-means algorithm optimizes the parameters of the mixture distributions. • A difference in the mixing probabilities between hemispheres is determined. Abstract A Gaussian mixture model (GMM)-based classification technique is employed for a quantitative global assessment of brain tissue changes by using pixel intensities and contrast generated by b-values in diffusion tensor imaging (DTI). A hemisphere approach is also proposed. A GMM identifies the variability in the main brain tissues at a macroscopic scale rather than searching for tumours or affected areas. The asymmetries of the mixture distributions between the hemispheres could be used as a sensitive, faster tool for early diagnosis. The k-means algorithm optimizes the parameters of the mixture distributions and ensures that the global maxima of the likelihood functions are determined. This method has been illustrated using 18 sub-classes of DTI data grouped into six levels of diffusion weighting (b = 0; 250; 500; 750; 1000 and 1250 s/mm2) and three main brain tissues. These tissues belong to three subjects, i.e., healthy, multiple haemorrhage areas in the left temporal lobe and ischaemic stroke. The mixing probabilities or weights at the class level are estimated based on the sub-class-level mixing probability estimation. Furthermore, weighted Euclidean distance and multiple correlation analysis are applied to analyse the dissimilarity of mixing probabilities between hemispheres and subjects. The silhouette data evaluate the objective quality of the clustering. By using a GMM in the present study, we establish an important variability in the mixing probability associated with white matter and grey matter between the left and right hemispheres. [ABSTRACT FROM AUTHOR]

Hierarchical clustering based on semantic feature thresholds is well applied in data mining. However, this method uses systematic sampling to select the edge points of the region during the region merging phase, resulting in the problems of under-consolidation and computational complexity when region merging based on the Euclidean distance criterion. To solve this problem, an improved hierarchical clustering method is proposed, which adopts the weighted Euclidean distance and optimizes the components of region combination. According to the orientation of the centers of two region clustering and the geometric relation among the edge points, two novel type of edge point selection strategies are established to reduce the number of edge points involved in the operation and ensure that the selected ones possess the minimum Euclidean distance in all edge point combinations. Experimental results show that the main advantages of this research project lie in its high clustering accuracy and less average clustering time. [ABSTRACT FROM AUTHOR]

• Three suitable composite drought indices were selected for coastal drought monitoring. • The Precipitation Evaporation Runoff Composite Index has advantages in detecting short-term drought conditions. • The response of salinity to long-term droughts varies by basin. Given the complexity of coastal drought events and their unique impacts on coastal ecosystems, it is vital to develop drought indices that can reflect both freshwater availability and impacts on ecological resources to better assess drought conditions over coastal regions. Existing drought indices developed for upland areas may not be suitable to capture the timing and severity of drought in the coastal regions. To explore coastal drought issue more comprehensively, this paper constructed the Coastal Composite Drought Indices (CCDIs) based on the entropy-weighted Euclidean distance method by freely combining six variables: precipitation (P), evaporation (E), runoff (R), salinity (S), Normalized Difference Vegetation Index (NDVI) and Land Surface Temperature (LST), in the Jinjiang River Basin (JJRB) and the Jiulong River Basin (JLRB). The CCDIs were later compared to the Standardized Precipitation Index (SPI) and Palmer Drought Severity Index (PDSI) to select the Optimized Drought Indices (ODIs). The results demonstrated that the Precipitation Evaporation Runoff Composite Index (PER) is more sensitive to capturing short-term coastal drought events compared to other CCDIs. PER performed better than SPI and PDSI in detecting the onset of drought development and reflecting drought persistence. The salinity exhibited mixed responses to long-term drought events in different river basins depending on the size of each coastal system and its characteristics, thus raising the issue of regional applicability. Through a series of cross-comparisons and validations, the Runoff NDVI LST Composite Index (RNL) and the Runoff Salinity NDVI Composite Index (RSN) were chosen to monitor long-term droughts in the JJRB and JLRB, respectively. Overall, all three indices have the ability to capture the dynamics and trends of the variables and provide better information on the occurrence, persistence, and end of droughts in coastal areas. [ABSTRACT FROM AUTHOR]

Clustering electric load curves is an important part of the load data mining process. In this paper, we propose a clustering algorithm by combining singular value decomposition and KICIC clustering algorithm (SVD-KICIC) for analyzing the characteristics of daily load curves to mitigate some of the traditional clustering algorithm problems, such as only considering intra-class distance and low computational efficiency when dealing with massive load data. Our method identifies effective daily load curve characteristics using the singular value decomposition technique to improve dimensionality reduction, which improves low computational efficiency by reducing the number of dimensions inherent in big data. Additionally, the method performs SVD on the load data to obtain singular values for determination of weight of the KICIC algorithm, which leverages intra-class and inter-class distances of the load data and further improves the computational efficiency of the algorithm. Finally, we perform a series of simulations of actual load curves from a certain city to validate that the algorithm proposed in this paper has a short operation time, high clustering quality, and solid robustness that improves the clustering performance of the load curves.

Anti-detection is becoming as an emerging challenge for anti-phishing. This paper solves the threats of anti-detection from the threshold setting condition. Enough webpages are considered to complicate threshold setting condition when the threshold is settled. According to the common visual behavior which is easily attracted by the salient region of webpages, image retrieval methods based on texton correlation descriptor (TCD) are improved to obtain enough webpages which have similarity in the salient region for the images of webpages. There are two steps for improving TCD which has advantage of recognizing the salient region of images: (1) This paper proposed Weighted Euclidean Distance based on neighborhood location (NLW-Euclidean distance) and double cross windows, and combine them to solve the problems in TCD; (2) Space structure is introduced to map the image set to Euclid space so that similarity relation among images can be used to complicate threshold setting conditions. Experimental results show that the proposed method can improve the effectiveness of anti-phishing and make the system more stable, and significantly reduce the possibilities of being hacked to be used as mining systems for blockchain. [ABSTRACT FROM AUTHOR]

Highlights • An integrated task performance score of the building occupants was developed. • The score was improved when the operative temperature was changed to neutral. • Occupants in high CO 2 concentration cannot well conduct task. • Best score (0.187) was found when operative temperature was changed from cold to neutral. • The score was improved when operative temperature is cold (0.271) rather than slightly warm (0.346). Abstract The task performance can be analyzed though various indices related to cognitive tasks, but few studies have been conducted to analyze various indices of task performance considering both the indoor air pollutants and the climate factors. Therefore, this study aimed to develop an integrated task performance score for 22 building occupants based on the IEQ condition changes. The experiment was designed with three scenarios simulating the IEQ condition changes during an 8-hour work period. In each scenario, six cognitive tasks were performed before and after the occurrence of IEQ condition changes. The relationship between cognitive task and IEQ condition was analyzed using a paired t -test. In addition, an integrated task performance score of the building occupants was developed with the use of a weighted Euclidean distance to utilize the results of this study in building design and operation. As a result, when the operative temperature is changed from 18.70 °C (cold) to 25 °C (neutral), the best task performance score was calculated as 0.187. The noticeable fact is that although scenario 1-1 was worse than scenario 2-1 based on the predicted percentage of dissatisfaction, a better occupants’ task performance score was obtained from scenario 1-1 (0.271) than from scenario 2-1 (0.346). Through the results of this study, the building occupants’ task performance according to the IEQ condition considering both the CO 2 concentration and the indoor climate can be expressed as a single index. Thus, it is expected that using this single index, decision makers, including facility managers, building occupants, and mechanical system designers, will be able to manage the IEQ conditions of buildings based on the quantitative indicators of the building occupants’ task performance. [ABSTRACT FROM AUTHOR]

Aiming at the data release and weight sequence attacks of weighted social networks, this paper proposed a weighting anonymous method based on node segmentation to realize the privacy protection of network structure, side weight and weight sequence. Based on the concept of edge space of the graph, this paper constructed the vector set model of the weighted social network by using the idea of node clustering segmentation, reallocated the weight by using the center of the interval, adjusted the weight by the distance between the group diameter and the relative distance of the node sequence, used the weighted Euclidean distance to construct the candidate vector set, and selected the vector from the candidate vector set to realize the social network.This method guaranteed the structural characteristics needed by the social network analysis, the validity of the published data and the effective protection of the weight sequence attacks under the premise of ensuring the privacy and security. [ABSTRACT FROM AUTHOR]

Older people living alone in the home should be monitored constantly to avoid the consequences of diseases like paralytic attack. It’s very difficult to do the continuous monitoring of elder people by a caretaker manually. This motivated us to propose an automatic paralytic attack detection scheme using surveillance video analysis. Due to the unavailability of standard video dataset, we collected the training video data from different people that contain the persons’ behavior during normal conditions and in the presence of a paralytic attack (simulated). Principal component analysis (PCA) has been used to extract the features from the collected training video set and labeled it into two classes, say normal or abnormal. Basically, we analyzed the facial expression change as the criteria, and for better classification accuracy a new weighted euclidean distance based measure is introduced in this article while dealing with PCA features. An experimental study has been carried out on the collected video data, and we analyzed classification accuracy, sensitivity, and specificity. Classification accuracy obtained while using proposed weighted euclidean distance methods are compared with the other well-known classification techniques such as minimum euclidean distance based classification, support vector machine (SVM) classification, k-nearest neighborhood (k-NN). The comparative study shows that proposed weighted euclidean distance along with PCA features is able to detect faster than other methods with almost the same detection accuracy. [ABSTRACT FROM AUTHOR]

Photovoltaic (PV) power is volatile in nature and raises the level of uncertainty in power systems. PV power forecasting is an important measure to solve this problem. It helps to improve the reliability and reduces the generation cost. Advances in computer technology and sensors make the numeric modeling methods a hotspot in the field of PV power forecasting. However, data modeling methods strongly rely on the accuracy of measurement data. Unavoidable outliers in the measured meteorological data have an adverse effect on the model due to their heteroscedasticity. Although many studies can be found focusing on outlier detection, only a few have incorporated outlier detection with regression models. In this study, an innovative method employing the weighted Gaussian process regression approach is proposed, such that data samples with higher outlier potential have a low weight. A density-based local outlier detection approach is introduced to compensate the deterioration of Euclidean distance for high-dimensional data. A novel concept of the degree of nonlinear correlation is incorporated to compute the contribution of every individual data attribute. Effectiveness of the proposed method is demonstrated by performing an experimental analysis and making comparisons with other typical data-based approaches, and the results exhibit higher estimation accuracy. [ABSTRACT FROM PUBLISHER]

WiFi fingerprint positioning has been widely used in the indoor positioning field. The weighed K-nearest neighbor (WKNN) algorithm is one of the most widely used deterministic algorithms. The traditional WKNN algorithm uses Euclidean distance or Manhattan distance between the received signal strengths (RSS) as the distance measure to judge the physical distance between points. However, the relationship between the RSS and the physical distance is nonlinear, using the traditional Euclidean distance or Manhattan distance to measure the physical distance will lead to errors in positioning. In addition, the traditional RSS-based clustering algorithm only takes the signal distance between the RSS as the clustering criterion without considering the position distribution of reference points (RPs). Therefore, to improve the positioning accuracy, we propose an improved WiFi positioning method based on fingerprint clustering and signal weighted Euclidean distance (SWED). The proposed algorithm is tested by experiments conducted in two experimental fields. The results indicate that compared with the traditional methods, the proposed position label-assisted (PL-assisted) clustering result can reflect the position distribution of RPs and the proposed SWED-based WKNN (SWED-WKNN) algorithm can significantly improve the positioning accuracy.

In this paper, an approach to biometric verification based on human body communication (HBC) is presented for wearable devices. For this purpose, the transmission gain S21 of volunteer's forearm is measured by vector network analyzer (VNA). Specifically, in order to determine the chosen frequency for biometric verification, 1800 groups of data are acquired from 10 volunteers in the frequency range 0.3 MHz to 1500 MHz, and each group includes 1601 sample data. In addition, to achieve the rapid verification, 30 groups of data for each volunteer are acquired at the chosen frequency, and each group contains only 21 sample data. Furthermore, a threshold-adaptive template matching (TATM) algorithm based on weighted Euclidean distance is proposed for rapid verification in this work. The results indicate that the chosen frequency for biometric verification is from 650 MHz to 750 MHz. The false acceptance rate (FAR) and false rejection rate (FRR) based on TATM are approximately 5.79% and 6.74%, respectively. In contrast, the FAR and FRR were 4.17% and 37.5%, 3.37% and 33.33%, and 3.80% and 34.17% using K-nearest neighbor (KNN) classification, support vector machines (SVM), and naive Bayesian method (NBM) classification, respectively. In addition, the running time of TATM is 0.019 s, whereas the running times of KNN, SVM and NBM are 0.310 s, 0.0385 s, and 0.168 s, respectively. Therefore, TATM is suggested to be appropriate for rapid verification use in wearable devices. [ABSTRACT FROM AUTHOR]

The ability to timely and accurately forecast the evolution of traffic is very important in traffic management and control applications. This paper proposes a non-parametric and data-driven methodology for short-term traffic forecasting based on identifying similar traffic patterns using an enhanced K-nearest neighbor (K-NN) algorithm. Weighted Euclidean distance, which gives more weight to recent measurements, is used as a similarity measure for K-NN. Moreover, winsorization of the neighbors is implemented to dampen the effects of dominant candidates, and rank exponent is used to aggregate the candidate values. Robustness of the proposed method is demonstrated by implementing it on large datasets collected from different regions and by comparing it with advanced time series models, such as SARIMA and adaptive Kalman Filter models proposed by others. It is demonstrated that the proposed method reduces the mean absolute percent error by more than 25%. In addition, the effectiveness of the proposed enhanced K-NN algorithm is evaluated for multiple forecast steps and also its performance is tested under data with missing values. This research provides strong evidence suggesting that the proposed non-parametric and data-driven approach for short-term traffic forecasting provides promising results. Given the simplicity, accuracy, and robustness of the proposed approach, it can be easily incorporated with real-time traffic control for proactive freeway traffic management. [ABSTRACT FROM AUTHOR]