Article
Humanities, Multidisciplinary
Shuyu Wu, Jingyang Zhong, Hui Ye, Xusheng Kang
Summary: It is important to identify the category of cultural relics through chemical composition analysis. This study used distance discriminant analysis to classify glass artifacts into two categories, based on their chemical composition distribution. Key feature factors such as SiO2, K2O, PbO, and the presence of weathering on the surface were selected through regression analysis. Using Mahalanobis distance discriminant modeling, the study successfully differentiated unknown glass artifacts, with the Spearman-Mahalanobis method outperforming the stepwise regression-Mahalanobis method.
Article
Operations Research & Management Science
Ning Wang, Zhuo Zhang, Jiao Zhao, Dawei Hu
Summary: The paper proposes a modified Mahalanobis-Taguchi system (MTS) method amended by Fischer linear discriminant analysis (FLDA) for recognizing the running state of equipment. By discussing the limitations of using Mahalanobis distance (MD) as the measurement scale and introducing balanced accuracy as the evaluation index, the paper improves the imbalanced classification ability of the traditional MTS. The results demonstrate the effectiveness and superiority of the modified model in terms of accuracy index and the size of abnormal samples.
ANNALS OF OPERATIONS RESEARCH
(2022)
Article
Computer Science, Artificial Intelligence
Juan Luis Suarez, Salvador Garcia, Francisco Herrera
Summary: Distance metric learning is a branch of machine learning that focuses on learning distances from data to improve the performance of similarity-based algorithms. This tutorial covers theoretical background, foundations, and popular methods of distance metric learning, evaluating their capabilities through exhaustive testing. Results highlighted outstanding algorithms, with discussion on future prospects and challenges.
Article
Mathematics
Ishaq Adeyanju Raji, Nasir Abbas, Mu'azu Ramat Abujiya, Muhammad Riaz
Summary: This study proposes a robust multivariate control chart based on the Stahel-Donoho robust estimator, and examines how parameter estimation and outliers impact the efficacy of control charts through Monte-Carlo simulations. The new outlier detector restores the sensitivity and efficacy of the chart, as demonstrated in a real-life application on a dataset from the manufacturing process of carbon fiber tubes.
Article
Computer Science, Artificial Intelligence
Ya-Juan Han, Zhen He, Yun-Fang Peng
Summary: The paper proposes an improved Mahalanobis-Taguchi system (MTS) method for analyzing the potential causes of abnormal observations in multidimensional systems. By dividing the traditional MTS method into two phases and introducing the weighted Mahalanobis distance function and MYT decomposition method, the diagnosis becomes more reasonable and accurate, and the analysis of abnormal causes becomes more comprehensive and reliable. By applying the improved MTS method in a blood viscosity diagnosis system in a hospital, the number of variables in the system decreased by 37.5%, and the differentiation between abnormal conditions and the health group increased by 102%. The potential causes of abnormal observations were also identified using the MYT decomposition method. These results validate the feasibility and effectiveness of the method proposed in this paper.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Multidisciplinary Sciences
Saujan Bashyal, Ashmita Upadhyay, Dipendra Kumar Ayer, Prabesh Dhakal, G. C. Bimochana, Jiban Shrestha
Summary: This study evaluated the phenotypic diversity of twelve amaranth accessions and conducted principal component analysis and cluster analysis. The results showed significant differences among these accessions in multiple traits, forming four distinct clusters.
Article
Engineering, Electrical & Electronic
Iyad Kadoun, Hossein Khaleghi Bizaki
Summary: This paper proposes two new algorithms (TFDA and SFDA) aiming to improve the AMC performance accuracy of overlapped digital modulations in feature space. Simulation results show that these algorithms significantly enhance the AMC performance, achieving higher accuracy compared to the reference papers.
PHYSICAL COMMUNICATION
(2022)
Article
Chemistry, Multidisciplinary
Jan Bocianowski, Kamila Nowosad, Henryk Bujak
Summary: Knowledge of the genetic potential and variation in parental forms is crucial for shortening the breeding process and achieving desired traits in hybrids. The effects of heterosis and specific combining ability can be predicted through selection of genetically diverse parental forms. Preliminary studies suggest that selecting phenotypically equal but genetically diverse parental forms is the best approach for obtaining favorable hybrids.
APPLIED SCIENCES-BASEL
(2023)
Article
Economics
Shi Xiong, Weidong Chen
Summary: This paper proposes a novel hybrid method called Weighted Turbulence, which combines dynamic network and weighted Mahalanobis distance to measure the overall systemic risk level of the international energy markets system. The proposed method accurately detects the spikes of systemic risk in international energy markets and eliminates the negative impact of non-systematic markets, showing practical and theoretical significance.
Article
Neurosciences
Xianjun Li, Mengxuan Li, Miaomiao Wang, Fan Wu, Heng Liu, Qinli Sun, Yuli Zhang, Congcong Liu, Chao Jin, Jian Yang
Summary: The study investigated white matter maturation in neonates using diffusion kurtosis imaging (DKI) with multiparametric analysis, revealing additional changing patterns and stronger negative correlations compared to traditional diffusion tensor (DT) metrics. Results suggest that DKI benefits the understanding of white matter maturation processes and degrees in neonates.
HUMAN BRAIN MAPPING
(2022)
Article
Mathematics, Applied
Yunfeng Shi, Shu Lv, Kaibo Shi
Summary: This paper proposes a new parallel data geometry analysis (PDGA) algorithm for Support Vector Machine (SVM), which introduces Mahalanobis distance and cosine angle distance analysis methods to reduce the training set of SVM and improve training efficiency without sacrificing classification accuracy. The algorithm is implemented in parallel, significantly reducing training time and memory requirements, and outperforming five competitive algorithms in terms of performance.
Article
Engineering, Electrical & Electronic
S. Deepak, P. M. Ameer
Summary: The study focuses on developing accurate models for brain tumour classification using a siamese neural network trained effectively on a smaller number of data samples. The SNN features extracted from brain MRI images are found to be more effective than hand-designed features and deep transfer learned features, demonstrating high classification accuracy on cross-validation.
INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY
(2021)
Article
Engineering, Civil
J. Prawin, R. Anbarasan
Summary: A two-stage novel Mel-frequency cepstral analysis based damage diagnostic technique is proposed for detection, localization, and characterization using ambient vibration data. The technique effectively distinguishes damage from other variations and is robust enough to identify multiple damages present in the structure. The proposed approach has been verified using synthetic datasets and experimental datasets, demonstrating its practical viability.
ENGINEERING STRUCTURES
(2021)
Article
Agronomy
Jan Bocianowski, Alina Liersch
Summary: This study investigated the effects of genotype, environment, and their interaction on seed yield and breeding traits of winter oilseed rape. The results showed significant differences in yield and other traits among the tested genotypes across different years and locations. The correlation analysis indicated a strong negative relationship between seed yield and the beginning of flowering. Multivariate statistical methods were used to characterize the tested genotypes in terms of multiple traits, revealing variations between different cultivars and lines.
Article
Engineering, Electrical & Electronic
Manish N. Tibdewal, Dhanashri N. Nagbhide, M. Mahadevappa, AjoyKumar Ray, Ashok Dhoke, Monica Malokar
Summary: This study analyzed the cognitive effects of meditation on the human brain using electroencephalogram (EEG) signals. The results demonstrate that meditation improves relaxation, cognitive functions, calmness, and mental concentration. Statistical, spatial, and spectral analyses support these findings.
SIGNAL IMAGE AND VIDEO PROCESSING
(2022)
Article
Statistics & Probability
Lyron J. Winderbaum, Inge Koch, Ove J. R. Gustafsson, Stephan Meding, Peter Hoffmann
ANNALS OF APPLIED STATISTICS
(2015)
Article
Biochemical Research Methods
Sean Robinson, Garique Glonek, Inge Koch, Mark Thomas, Christopher Davies
BMC BIOINFORMATICS
(2015)
Article
Biochemical Research Methods
John Zaunders, Junmei Jing, Michael Leipold, Holden Maecker, Anthony D. Kelleher, Inge Koch
Article
Biochemical Research Methods
Lyron Winderbaum, Inge Koch, Parul Mittal, Peter Hoffmann
Article
Computer Science, Interdisciplinary Applications
Inge Koch, Kanta Naito
COMPUTATIONAL STATISTICS & DATA ANALYSIS
(2010)
Article
Statistics & Probability
Mitsuru Tamatani, Inge Koch, Kanta Naito
JOURNAL OF MULTIVARIATE ANALYSIS
(2012)
Article
Statistics & Probability
Junmei Jing, Inge Koch, Kanta Naito
SCANDINAVIAN JOURNAL OF STATISTICS
(2012)
Article
Statistics & Probability
Sara Taskinen, Inge Koch, Hannu Oja
STATISTICS & PROBABILITY LETTERS
(2012)
Article
Statistics & Probability
Inge Koch, Peter Hoffmann, J. S. Marron
ELECTRONIC JOURNAL OF STATISTICS
(2014)
Article
Statistics & Probability
Xiaosun Lu, Inge Koch, J. S. Marron
ELECTRONIC JOURNAL OF STATISTICS
(2014)
Editorial Material
Statistics & Probability
J. S. Marron, Inge Koch, Peter Hoffmann
ELECTRONIC JOURNAL OF STATISTICS
(2014)
Article
Computer Science, Artificial Intelligence
Abd-Krim Seghouane, Navid Shokouhi, Inge Koch
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2019)
Article
Statistics & Probability
Inge Koch, Kanta Naito, Hiroaki Tanaka
AUSTRALIAN & NEW ZEALAND JOURNAL OF STATISTICS
(2019)
Article
Meteorology & Atmospheric Sciences
Seth Westra, Casey Brown, Upmanu Lall, Inge Koch, Ashish Sharma
INTERNATIONAL JOURNAL OF CLIMATOLOGY
(2010)