Principle Component Research Articles

Improvement detection system on complex network using hybrid deep belief network and selection features

The challenge for intrusion detection system on internet of things networks (IDS-IoT) as a complex networks is the constant evolution of both large and small attack techniques and methods. The IoT network is growing very rapidly, resulting in very large and complex data. Complex data produces large data dimensions and is one of the problems of IDS in IoT networks. In this work, we propose a dimensional reduction method to improve the performance of IDS and find out the effect of the method on IDS-IoT using deep belief network (DBN). The proposed method for feature selection uses information gain (IG) and principle component analysis (PCA). The experiment of IDS-IoT with DBN successfully detects attacks on complex networks. The calculation of accuracy, precision, and recall, shows that the performance of the combination DBN with PCA is superior to DBN with information gain for Wi-Fi datasets. Meanwhile, the Xbee dataset with information gain is superior to using PCA. The final result of measuring the average value of accuracy, precision, and recall from each IDSDBN test for IoT is 99%. Other results also show that the proposed method has better performance than previous studies increasing by 4.12%.

The Carnegie Supernova Project I

An analysis leveraging 170 optical spectra of 35 stripped-envelope (SE) core-collapse supernovae (SNe) observed by the Carnegie Supernova Project I and published in a companion paper is presented. Mean template spectra were constructed for the SNe IIb, Ib, and Ic subtypes, and parent ions associated with designated spectral features are identified with the aid of the spectral synthesis code SYNAPPS. Our modeled mean spectra suggest the ∼6150 Å feature in SNe IIb may have an underlying contribution due to silicon, while the same feature in some SNe Ib may have an underlying contribution due to hydrogen. Standard spectral line diagnostics consisting of pseudo-equivalent widths (pEWs) and blue-shifted Doppler velocity were measured for each of the spectral features. Correlation matrices and rolling mean values of both spectral diagnostics were constructed. A principle component analysis (PCA) was applied to various wavelength ranges of the entire dataset and suggests clear separation among the different SE SN subtypes, which follows from trends previously identified in the literature. In addition, our findings reveal the presence of two SNe IIb subtypes, a select number of SNe Ib displaying signatures of weak, high-velocity hydrogen, and a single SN Ic with evidence of weak helium features. Our PCA results can be leveraged to obtain robust subtyping of SE SNe based on a single spectrum taken during the so-called photospheric phase, separating SNe IIb from SNe Ib with ∼80% completion.

Poster 150: Immunophenotyping of Synovial Tissue in Adolescents Undergoing ACL Reconstruction Reveals Distinct Inflammatory Responses to Injury

Objectives: Tears of the anterior cruciate ligament (ACL) are common in the pediatric athletic population. In spite of trends towards early surgical reconstruction to minimize the risk of secondary meniscus and cartilage injuries, long term disruption of knee joint homeostasis and progression to post- traumatic osteoarthritis (PTOA) occurs in 50-90% of patients - a particularly challenging problem in this young cohort. The exact pathogenesis of PTOA after ACL injury and reconstruction remains unknown. Evidence from animal models of PTOA suggests a critical role of synovial inflammatory infiltration in both the onset and progression of PTOA. However, there is a scarcity of in vivo human data documenting the synovial inflammatory response to ACL injury. One recent study has looked at immune cell composition in synovial fluid, but there are no comparable publications using synovial tissue. Our primary objective was to use flow cytometry with an advanced immune cell panel to provide a snapshot of the cellular composition of immune infiltrates in the synovium of adolescent patients at the time of ACL reconstruction. Our secondary objective was to look for correlations between demographic and injury parameters and inflammatory cell composition. Methods: Patients between the ages of 12 and 18 years who were undergoing primary ACL reconstruction were enrolled in an IRB-approved prospective study. Exclusion criteria included multiligament knee injuries, revision ACL reconstruction, history of prior knee surgery, and history of inflammatory joint disease. Demographic variables and intraoperative data were recorded. At the time of surgery, an arthroscopic synovial biopsy from the prefemoral synovium was obtained. Synovium tissue was enzymatically digested into a single cell suspension for immune profiling by multicolor flow cytometry. Data was acquired on a BD lsrFortessa flow cytometer and analyzed with FlowJo v10. Statistical analyses were performed with GraphPad Prism including parametric ANOVA (one-way or two- way), simple linear regression, Kruskal Wallis analysis of variance, Mann Whitney T-test, and parallel Principal component analyses (Eigenvalue with Monte Carlo simulation). Heat map variable scaling was calculated relative to the mean and standard deviation of all measurements. Results: Twelve patients were prospectively enrolled in the study (33% male, 67% female, n = 12). Mean age was 15.5 +/- 2.02 years. Median time between injury and surgery was 35.5 days (23.3-67.5). Meniscal tears were present in 58.3% of patients (8.3% medial only, 33.3% lateral only, 16.7% both). Cells isolated from synovium were 36.8% fibroblasts, 9.89% fibrocytes, and 36.0% hematopoietic lineage cells (Fig. 1A). Within the hematopoietic lineage, the dominant cell types were monocytes, macrophages, and T-cells (Fig. 1B). Principle component analysis (PCA) revealed three immunophenotypes. Immunotype 1 had higher mast cell content than other groups and fewer inflammatory cells such as T cells, B cells, and macrophages. Immunotype 2 had strong T/B cell infiltration and lower levels of innate immune cells. These patients also had the highest overall levels of inflammatory cells (Figure 2). Immunotype 3 had a strong innate immune response - in particular higher levels of M2 polarized macrophages - and significantly fewer T/B cells. There were no obvious effects of age, skeletal maturity, or the presence of meniscal tears on immunotype (Table 1). There was a trend towards a correlation between delay in surgery and classification within immunotype 1 (p = 0.09, Table 1). Conclusions: Our study provides the first in vivo analysis of inflammatory cell behavior in the synovium of ACL injured knees. In young patients undergoing primary ACL reconstruction, three immunotypes were discovered. Our pilot data suggest a possible relationship between delay in surgery and a high prevalence of synovial mast cells. This would be of particular interest since mast cells are known to play a role in the development of OA and possibly PTOA. In the more acute setting, two separate immunotypes were encountered, one with heavy inflammation and a predominance of T/B cells, and the other with more moderate inflammation and a higher percentage of innate immune cells / M2 polarized macrophages. These were not clearly tied to patient demographic factors, and could represent intrinsic differences in the response to injury. Future work investigating the correlation between initial immunotype and clinical outcomes – in particular the development of PTOA – may provide insight into the role of synovial inflammation in post-ACL joint health and degeneration, as well as provide strategies for personalized treatments in the prevention of PTOA. [Table: see text]

A Kernel-Based Multi-Featured Rock Modeling and Detection Framework for a Mars Rover.

This article presents two kernel-based rock detection methods for a Mars rover. Rock detection on planetary surfaces is particularly pivotal for planetary vehicles regarding navigation and obstacle avoidance. However, the diverse morphologies of Martian rocks, the sparsity of pixel-wise features, and engineering constraints are great challenges to current pixel-wise object detection methods, resulting in inaccurate and delayed object location and recognition. We therefore propose a region-wise rock detection framework and design two detection algorithms, kernel principle component analysis (KPCA)-based rock detection (KPRD) and kernel low-rank representation (KLRR)-based rock detection (KLRD), using hypotheses of feature and sub-spatial separability. KPRD is based on KPCA and is expert in real-time detection yet with less accurate performance. KLRD is based on KPRD with KLRR which can generate more precise rock detection results with less delay. To validate the efficiency of the proposed methods, we build a small-scale Martian rock dataset, MarsData, containing various rocks. Preliminary experimental results show that our methods are efficient in dealing with complex images containing rocks, shadows, and gravel. The code and data are available at: https://github.com/CVIR-Lab/MarsData.

Significant Factors of Job Satisfaction among the Library Professionals in Tamilnadu: A Study

Library professionals play a vital role in supporting learning, research, and community development. Job satisfaction is important for these professionals as it can affect their motivation, productivity, and overall well-being. The researcher aims to evaluate the various job satisfaction factors among the library professionals in Tamilnadu. Data were collected through survey questionnaire method among the 150 library professionals and analysed using Principle Component analysis, Rotated component matrix and SPSS. This study resulted that 50% of the library professionals are satisfied with the salary, 48.2% of the respondents were satisfied with the promotion criteria, 45 % of the library professionals were happy about the job security, 69.8 % were felt the good relationship of the employer and the higher recognition.

Identification of Seawater Intrusion in the Dibdibba Coastal Aquifer, South of Iraq Using Chemical Indicators and Multivariate Analyses

Seawater intrusion into the groundwater is a major environmental disaster which affects the environment as well as community. This research aims to analyze the seawater intrusion in the Dibdibba coastal aquifer. In this study, researchers used statistical techniques to examine the impact of seawater intrusion in the Dibddiba coastal aquifer in southern Iraq. They collected 15 groundwater samples from pumping wells during wet and dry periods and analyzed those using multivariate statistical analyses and ionic ratios based on the GIS technique. The results showed that there was a strong linear correlation between total dissolved solids (TDS) and several other ions, including Ca2+, Mg2+, Na+, Cl− SO−2 4, and NO−3. The principle component analysis revealed two factor loadings, with the first accounting for a significant portion of the total variance and showing a high loading for TDS, Na+, Cl−, SO−2 4, Mg2+, Ca2+, and NO−3. The second factor had a high loading for K+. The seawater influence was detected in 33.33 percent of the low zone groundwater, 26.66 percent of the moderate zone groundwater, and 40 percent of the high zone groundwater that was studied. Eighty and sixty-seven percent of the groundwater samples, respectively, belonged to the seawater field as Na-Cl type, as shown by Chadha’s graphic, demonstrating the effect of seawater intrusion. Also, during the wet time, 20% of the samples belonged to the reverse ion exchange water field as Ca-Mg-Cl type, but during the dry period, 33.3% did. This is further evidence of the impact of seawater intrusion.

Estimating genetic diversity among durum wheat (Triticum durum desf.) landraces using morphological and SRAP markers

The durum wheat (Triticum turgidum L. ssp. durum Desf.) Landraces are a valuable source of natural germplasm for enhancing the genetic diversity of existing durum wheat cultivars. The study analyzed the genetic diversity of twenty-two durum wheat landraces including eight local Saudi landraces and fourteen introduced landraces using sixteen morphological descriptors and sequence-related amplified polymorphism (SRAP) markers. The results showed significant differences between the analyzed agro-morphological parameters and a large degree of genetic variation across the tested landraces. Principle components analysis (PCA) was used to determine agro-morphological relationships among different traits. The first six principal components (PCs) accounted for 78.47 % of the cumulative variability among 22 landraces. The PC1demonstrated variability in coleoptile anthocyanin coloration, straw pith, culm neck glaucosity, flag leaf glaucosity, ear glaucosity, and length of awn at tip relative to length of ear. Wheat landraces (L8, L14, L497, L569, L590, L594, L600, L601, and L602) showed increased diversity in dry region and contributed to PC1. A couple landraces had higher plant height (L12, L598, and L654), heading days (650, 656), and ear length (L12, L594, and L650) respectively. The dendrogram generated from the standardized morphological data separated the twenty-two durum wheat genotypes mainly into two clusters. The landraces 14, 600 and 602 grouped into separate cluster with strong correlation to ear glaucosity. Genetic diversity of these landraces was also evaluated using eight SRAP markers, with 482 amplified fragments and an average polymorphic information content (PIC) of 0.27. The dendrogram based on SRAP markers separated into two clusters with some diversified landraces (L8, 594, 602, 977, and L650). The Mantel test found no significant correlation (phenotypic or genetic) between 22 wheat durum landraces (r = 0.013, p = 0.84, =0.05). The results demonstrated the power of morphological and SRAP markers for detecting diversity among durum wheat landraces in the semi-arid region of Saudi Arabia. Thus, study provides insights into wheat diversity for better in-situ and ex-situ conservation and paves the road for their use in a Saudi durum wheat breeding program.

Automatic lineaments detection using radar and optical data with an emphasis on geologic and tectonic implications: a case study of Kabul Block, eastern Afghanistan

The earth’s surface linear features, expressing geological lineaments, play a key role in identifying hydrothermal alteration and mineralization zones, as well as in understanding tectonic settings of a region. The objective of this investigation is to utilize a method for extracting lineaments automatically, which will be integrated and applied to identify geological-based lineaments by making use of remote sensing data. The study will further examine the structural pattern and temporal-spatial evolution of the lineaments and establish their connection with the primary active faults present in the Kabul Block. Multi-sensor data from radar (DEM (Digital Elevation Model)-5m, Sentinel-1B GRD (Ground Range Detected)) and optical sensors (Sentinel-2 MSI (Multispectral Instrument) and ASTER) were processed using spatial and spectral filters before automatic lineament extraction. LINE-module algorithm was applied to various illuminated hill-shades of DEM-5m, filtered HH (Horizonal-Horizonal) and VH (Vertical-Horizontal) of Sentinel-1GRD and PC1 (Principle Component) of Sentinel-2A MSI, and ASTER data to detect linear surface features. Extensive testing was conducted to verify the accuracy of extracted lineaments and to exclude any artificial lineaments in the study area. The radar and optical data results were compared while taking into consideration the geological and tectonic settings of the study area to select the most appropriate extracted lineaments. The DEM-5m and Sentinel-1B GRD showed the best result for identifying lineaments, and these were found to be highly correlated with previously available data in the Kabul Block. The final results of DEM-5m and Sentinel-1B GRD were further analyzed. The extracted lineaments were found to trend predominantly in a NW-SE and NE-SW directions, which is consistent with the results of other data. Temporal evolution and spatial distribution reveal that a high density of the lineaments is associated with Paleogene and Quaternary formations, while a low density is observed in Proterozoic, Paleozoic, and Mesozoic formations. The west and southwest edges of the Kabul Block are controlled by compressive stress trending NNW-SSE, while the north and southeast margins are influenced by NE-SW and ∼ N-S trending compressive stress.

Predicting the reaction rates between flavonoids and methylglyoxal by combining molecular properties and machine learning

The kinetics of the reaction between methylglyoxal (MGO) and epigallocatechin gallate have been investigated at pH 7.4 and 37 °C, and the kinetic data were combined with previously obtained data of six other flavonoids to develop a model that allows to predict the trapping capacity of MGO based on the molecular properties of the seven flavonoids. The observed data were augmented by using synthetic minority oversampling technique forming a new data set that was used to create the predicting models for the trapping rate constant of MGO by flavonoids via principal component regression (PCR) and back-propagation neural network algorithm, respectively. The PCR model based on the first six principle components was robust and accurate comparing other created models, with an associated root-mean-square error value of 8.02 × 10−7 on the testing set. This work provides quantitative structure-activity models for rapid and accurate prediction of the trapping rate constant of MGO by flavonoids.

Upwelling impact and lateral transport of dissolved PAHs in the Taiwan Strait and adjacent South China Sea

The spatial distribution and depth profile of dissolved polycyclic aromatic hydrocarbons (PAHs) were investigated in the western Taiwan Strait (TWS) and northeastern South China Sea (SCS) during the southwest monsoon for a comprehensive study of spatial distribution, potential sources, upwelling, and lateral PAHs transport flux to assess the impacts of oceanic processes. The concentrations of ∑14PAHs were 33 ± 14 ng L−1 and 23 ± 11 ng L−1 in western TWS and northeastern SCS, respectively. A minor difference in potential sources in different areas was shown in principle component analysis results, which illustrated mixed sources (petrogenic and pyrogenic) in western TWS and petrogenic sources in northeastern SCS. An “enrichment in surface or deep but depletion in medium water” distribution pattern of PAHs depth profile during summertime was observed in Taiwan Bank, which was potentially influenced by the upwelling. The greatest lateral ∑14PAHs transport flux was found along the Taiwan Strait Current area (43.51 g s−1), followed by those along South China Sea Warm Current and Guangdong Coastal Current areas. Though the oceanic response to PAHs varied relatively slowly, the ocean current was a less-dominant pathway for PAHs exchange between the SCS and the East China Sea (ECS).

Strategic Orientations to Strengthen Policymaking: Study of Small-Scale Cassava-Based Agroindustry in Central Java, Indonesia

The cassava agroindustry is an essential part of the food sub-sector, and as it provides economic benefits for business actors from upstream to downstream. The development of the industry has been focused on aspects of cultivation, whereas the aspects of processing, marketing, management, and business innovation also need support. This study aims to formulate strategic orientations of SMEs in developing cassava-based agroindustry. This exploratory study was conducted on SMEs in the agroindustry with products made from cassava. A total of 115 SMEs in Central Java Province were taken as samples using stratified random sampling. Factor analysis was performed with the Principle Component Analysis (PCA). The strategic orientations covered product focus and short-term orientation to survive; market knowledge and flexibility; long-term orientation for market penetration or development; product development innovation to create differentiation; and reactive strategy orientation for stability. These five aspects should be considered to win the competition, build a competitive advantage, and face changes in the business environment. However, implementing them required the commitment of cassava-based SMEs, government support, and the development of collaboration with larger industries. Thus, the strategic orientations could be applied as a regional policy to improve the business performance in the cassava agroindustry in Central Java.

Structural and functional effects of the L84S mutant in the SARS-COV-2 ORF8 dimer based on microsecond molecular dynamics study

The L84S mutation has been observed frequently in the ORF8 protein of SARS-CoV-2, which is an accessory protein involved in various important functions such as virus propagation, pathogenesis, and evading the immune response. However, the specific effects of this mutation on the dimeric structure of ORF8 and its impacts on interactions with host components and immune responses are not well understood. In this study, we performed one microsecond molecular dynamics (MD) simulation and analyzed the dimeric behavior of the L84S and L84A mutants in comparison to the native protein. The MD simulations revealed that both mutations caused changes in the conformation of the ORF8 dimer, influenced protein folding mechanisms, and affected the overall structural stability. In particular, the 73YIDI76 motif has found to be significantly affected by the L84S mutation, leading to structural flexibility in the region connecting the C-terminal β4 and β5 strands. This flexibility might be responsible for virus immune modulation. The free energy landscape (FEL) and principle component analysis (PCA) have also supported our investigation. Overall, the L84S and L84A mutations affect the ORF8 dimeric interfaces by reducing the frequency of protein–protein interacting residues (Arg52, Lys53, Arg98, Ile104, Arg115, Val117, Asp119, Phe120, and Ile121) in the ORF8 dimer. Our findings provide detail insights for further research in designing structure-based therapeutics against the SARS-CoV-2. Communicated by Ramaswamy H. Sarma

Keragaman Morfologi Kerang Hotate (Patinopecten yessoensis) di Teluk Funka Hokkaido Jepang

Hotate scallop are cold water species that can only be cultivated in cold waters. Consumption of Patinopecten yessoensis, Jay 1857 from Japan and other countries shows greater demand, so research related to hotate scallop is important to manage hotate culture and its broodstock to maintain continous supply of this marine product. The purpose of this study is to determine the similarities and dissimilarities morphological characters of hotate scallop in Funka Bay Japan based on landmark characteristics. Data collection technique used was purposive sampling. Morphological measurements was conducted using Image-J software, principle component analysis using PAST software. The results indicate that the level of similarity of hotate scallop in cluster I is 70% and in cluster II is 85%. The principal components of hotate scallop morphometric landmarks is growth line number A20, A21, A22, A23, A25 from total 35 landmarks.

The impact of maize straw incorporation on arsenic and cadmium availability, transformation and microbial communities in alkaline-contaminated soils

Increasing evidence of the uncertainty of crop straw returning in heavy metal-contaminated soil is a significant concern. The present study investigated the influence of 1 and 2% maize straws (MS) amendment on As and Cd bioavailability in two different alkaline soils (A-industrial and B-irrigation) after 56 days of ageing. Adding MS to the two soils decreased the pH by 1.28 (A soil) and 1.13 (B soil) and increased the concentration of dissolved organic carbon (DOC) by 54.40 mg/kg (A soil) and 100.00 mg/kg (B soil) during the study period. After 56 days of ageing, the overall NaHCO3–As and DTPA-Cd increased by 40% and 33% (A) and 39% and 41% (B) soils, respectively. The MS additions increased the alteration of As and Cd exchangeable and residual fractions, whereas advanced solid-state 13C nuclear magnetic resonance (NMR) revealed that alkyl C and alkyl O–C–O in A soil and alkyl C, Methoxy C/N-alkyl, and alkyl O–C–O in B soil significantly contributed to the As and Cd mobilisation. Collectively, 16 S rRNA analyses revealed Acidobacteria, Firmicutes, Chloroflexi, Actinobacteria and Bacillus promoted the As and Cd mobilisation following the MS addition, while principle component analysis (PCA) demonstrated that bacterial proliferation significantly influenced MS decomposition, resulting in As and Cd mobilisation in the two soils. Overall, the study highlights the implications of applying MS to As- and Cd-contaminated alkaline soil and offers the framework for conditions to be considered during As- and Cd-remediation efforts, especially when MS is the sole remediation component.

Evaluation of biochemical, physiological traits and percentage of essential oil of sickleweed (Falcaria vulgaris) population in different geographical and climatic regions.

Sickleweed (Falcaria vulgaris) is the name of a species of annual, and perennial herbaceous plants of the genus Falcaria. Climate change could negatively influnces the performance of various plant species in plant kingdom. In this study, 15 different sickleweed populations from seven provinces of the country were collected based on an unbalanced nest design with 10 replications and the percentage of essential oil, types of chlorophyll, phenol, proline, protein, and carotenoids were measured on them. The results showed that there was a significant difference between populations at the level of one percent for the studied traits. The results of the mean comparison showed that populations Ard-Shaban and Qaz-Ilan in terms of the evaluated traits and especially the percentage of essential oil were at the upper of the studied samples and selected as suitable populations. In addition, populations Gilan-Deylaman and Kur-Gerger-e Sofla were also identified as superior populations in terms of studied traits by cluster analysis and principle component analysis (PCA). Since the high level of proline and biochemical and physiological traits in plants can play a role in plants' tolerance to stresses, therefore, populations with high values of these traits can be used in stress tolerance breeding programs. Therefore, in this study, populations Gilan-Deylaman and Kur-Gerger-e Sofla can be suitable populations for this purpose. In addition, the essential oil of this plant is used in the treatment of diseases, and therefore populations Ard-Shaban and Qaz-Ilan, which showed a high percentage of essential oil, can be used in breeding programs to increase the performance of this trait.

A new method to assess sustainability of agricultural systems by integrating ecosystem services and environmental impacts

Agricultural stakeholders disagree on how to put the general concept of sustainability into practice. But most recognize the need for assessment methods to characterize the current situation and gauge progress yet to be made. Many sustainability assessment methods for agricultural systems have been published, but very few integrate ecosystem services (ES). And yet, ES indicators are key to better integrating biological processes to support the agroecological transition. Although researchers have attempted to link the concept of environmental impact (EI) and ES through life cycle analysis (LCA), gaps remain when it comes to doing so within a sustainability assessment method. Here a new method based on an original conceptual indicator framework embedding new predictive indicators of EI and ES indicators was developed. This framework covers 22 environmental themes and integrates few basic economic and social indicators. The method was implemented on 33 farms with different certifications and production specifications. All farms were members of an agricultural cooperative in north-eastern France. We selected 250 plots to cover the farms’ crop rotations. The correlation analysis showed no systemic trade-off between EI or ES and economic indicators. Meanwhile, the joint assessment of ES and EI (like the multivariate analysis), delivered more nuanced results than a classical opposition between intensive and organic farming. Some farms with a moderate or even good level of ES often do not leverage them, as shown by their high EI. The principle component analysis and subsequent hierarchical ascendant classification allowed us to distinguish five clusters providing a more complex picture than simply opposing conventional and organic agriculture. Finally, the positive deviance analysis revealed that economic, environmental and social considerations can be balanced in a way that seems to be more sustainable than, for example, an organic farm that has very successfully reduced EI but at a cost of several economic and social trade-offs.

A Hybrid Method for Magnetic Resonance Brain Images Classification and Segmentation Using Soft Computing Techniques

Nowadays, Brain tumor is a serious life-threatening disease that can often be treated with risky surgeries. Various classification and segmentation methods for MR (Magnetic Resonance) brain images have been proposed but the expected accuracy value could not be reached so far. In this paper, we proposed a hybrid approach that includes modified fuzzy C-means and ANN classifier. It consists of five stages (a) Noise removal (b) Feature extraction (c) Feature selection (d) Classification (e) Segmentation. Initially, a genetic optimized median filter (GOMF) is used to remove noise present in the input image, and then the essential features are extracted and selected using Discrete Wavelet Transform (DWT) & Principle Component Analysis (PCA) algorithms respectively. The normal and abnormal images are classified using the ANN classifier. Finally, it is processed through a Modified fuzzy C-means algorithm to segment the tumor portion separately. The proposed segmentation technique has been tested on the BRATS dataset and produces a sensitivity of 98%, Jaccard index of 97%, specificity of 98%, and accuracy of 95%.

Systematic selection of ancestry informative SNPs for differentiating Han, Japanese, Dai, and Kinh populations.

Biogeographical origin inferences of different populations can provide valuable clues in the forensic investigation by narrowing down the detection scope. However, much research mainly focuses on forensic ancestral origin analyses of major continental populations, which may provide limited information in forensic practice. To improve the ancestral resolution of East Asian populations, we systematically selected ancestry informative single-nucleotide polymorphisms (AISNPs) for differentiating Han, Dai, Japanese, and Kinh populations. In addition, we evaluated the performance of the selected AISNPs to differentiate these populations via multiple methods. Totally 116 AISNPs were selected from the genome-wide data to infer the population origins of these four populations. Results of principle component analysis and population genetic structure of these populations indicated that the selected 116 AISNPs could achieve ancestral resolution of most individuals. Furthermore, the machine learning model built by 116 AISNPs unveiled that most individuals from these four populations could be assigned to correct population origins. To sum up, the selected 116 SNPs could be available for ancestral origin predictions of Han, Dai, Japanese, and Kinh populations, which could provide valuable information for forensic research and genome-wide association study in East Asian populations to some extent.

Low-rank latent matrix-factor prediction modeling for generalized high-dimensional matrix-variate regression.

Motivated by diagnosing the COVID-19 disease using two-dimensional (2D) image biomarkers from computed tomography (CT) scans, we propose a novel latent matrix-factor regression model to predict responses that may come from an exponential distribution family, where covariates include high-dimensional matrix-variate biomarkers. A latent generalized matrix regression (LaGMaR) is formulated, where the latent predictor is a low-dimensional matrix factor score extracted from the low-rank signal of the matrix variate through a cutting-edge matrix factor model. Unlike the general spirit of penalizing vectorization plus the necessity of tuning parameters in the literature, instead, our prediction modeling in LaGMaR conducts dimension reduction that respects the geometric characteristic of intrinsic 2D structure of the matrix covariate and thus avoids iteration. This greatly relieves the computation burden, and meanwhile maintains structural information so that the latent matrix factor feature can perfectly replace the intractable matrix-variate owing to high-dimensionality. The estimation procedure of LaGMaR is subtly derived by transforming the bilinear form matrix factor model onto a high-dimensional vector factor model, so that the method of principle components can be applied. We establish bilinear-form consistency of the estimated matrix coefficient of the latent predictor and consistency of prediction. The proposed approach can be implemented conveniently. Through simulation experiments, the prediction capability of LaGMaR is shown to outperform some existing penalized methods under diverse scenarios of generalized matrix regressions. Through the application to a real COVID-19 dataset, the proposed approach is shown to predict efficiently the COVID-19.

Masked face reconstruction and recognition through principle components analysis

Due to the Covid-19 virus infecting humans since 2019, the traditional methods of face recognition are not suitable anymore, for the reason that lots of countries and regions request people to wear masks in public places, whereas the masks will add additional noise in the recognition process. To solve this problem, we suggest a new method named masked face recognition, whose principle is first converting the masked face image to an unmasked reconstruction image by applying Principle Components Analysis. We call it the Reconstruction Process; then using Convolutional Neural Network to exert face recognition on unmasked reconstruction images, we call it the Recognition Process. During the Reconstruction Process, we first detect the unmasked area, then linearly fit the unmasked area with Eigenfaces generated from the PCA process and a set of coefficients, which are the objectives we optimize. After the optimization, we are able to obtain the reconstruction image by the linear combination of the Eigenface with its corresponding coefficient. Experimental results clearly show the high effectiveness of our method, and the accuracy of being recognized correctly is increased from about 80% if we use the original masked images to 96.36% if we use the unmasked reconstruction images.