Tree Components Research Articles

Comprehensive analysis of the genetic variation dataset among wild soybean (Glycine soja) in Shandong Province, China.

Wild soybean (Glycine soja), the ancestor of domesticated soybean, retains a higher level of genetic diversity and adaptability to harsh environments, making it highly valuable for breeding. Here, we re-sequenced 69 wild soybean individuals collected by the Shandong Academy of Agricultural Sciences and identified 1,613,162 high-quality SNPs which not only enriches our understanding of the genetic structure of wild soybean, but also provides valuable resources for further genomic research and genetic improvement of soybean. In this study, we collected 69 wild soybean accessions from Shandong Province, China, and performed re-sequencing on the DNBSEQ platform, followed by SNPs identification. We then integrated ADMIXTURE, neighbor-joining tree, and principal component analysis to illustrate population characteristics. The results showed that these wild soybean accessions could be divided into three distinct subpopulations, exhibiting significant genetic differences.

Efficient Semantic Segmentation for Large-Scale Agricultural Nursery Managements via Point Cloud-Based Neural Network

Remote sensing technology has found extensive application in agriculture, providing critical data for analysis. The advancement of semantic segmentation models significantly enhances the utilization of point cloud data, offering innovative technical support for modern horticulture in nursery environments, particularly in the area of plant cultivation. Semantic segmentation results aid in obtaining tree components, like canopies and trunks, and detailed data on tree growth environments. However, obtaining precise semantic segmentation results from large-scale areas can be challenging due to the vast number of points involved. Therefore, this paper introduces an improved model aimed at achieving superior performance for large-scale points. The model incorporates direction angles between points to improve local feature extraction and ensure rotational invariance. It also uses geometric and relative distance information for better adjustment of different neighboring point features. An external attention module extracts global spatial features, and an upsampling feature adjustment strategy integrates features from the encoder and decoder. A specialized dataset was created from real nursery environments for experiments. Results show that the improved model surpasses several point-based models, achieving a Mean Intersection over Union (mIoU) of 87.18%. This enhances the precision of nursery environment analysis and supports the advancement of autonomous nursery managements.

Comparative population genomics analysis for chicken body sizes using genome-wide SNPs.

This study aims to investigate the selection history, genome regions, and candidate genes associated with different chicken body sizes, thereby providing insights into the genetic basis of complex economic traits such as chicken body size and growth. In this study, a total of 217 individuals from eight breeds were selected. According to body size, they were divided into two groups: large chickens and bantam chickens, with four breeds in each group. Firstly, we investigate population structure by principal component analysis (PCA), phylogenetic tree, and ancestry component analysis. Next, we recognize runs of homozygosity (ROH) islands through calculating ROH. Finally, we carry out selection signatures analysis utilizing population differentiation index and nucleic acid diversity. The population structure analysis show that large and bantam chickens are clearly separated. Large chickens are clustered together, the bantam chickens are relatively dispersed. The results of ROH island analysis show that 48 and 56 ROH islands were identified in large and bantam chickens respectively. Among the interesting ROH islands, a total of eight candidate genes were identified. In selection signatures analysis, a total of 322 selected genes were annotated in large chickens, such as POU1F1, BMP10, enrichment in 16 GO terms. In bantam chickens, a total of 447 selected genes were annotated, such as IGF1, GRB10, enrichment in 20 GO terms and 2 KEGG pathways. The haplotype analysis results show that GRB10 has differences in chickens of different body sizes. By population structure, ROH islands, and selection signatures analysis, we have identified multiple genes associated with chicken body size, growth, and development (such as BMP10, IGF1, GRB10, etc). This provides a theoretical reference for the subsequent development of molecular markers for chicken body size and the analysis of the genetic mechanism of chicken body size.

Heterogeneous Mediation Analysis for Cox Proportional Hazards Model With Multiple Mediators.

This study proposes a heterogeneous mediation analysis for survival data that accommodates multiple mediators and sparsity of the predictors. We introduce a joint modeling approach that links the mediation regression and proportional hazards models through Bayesian additive regression trees with shared typologies. The shared tree component is motivated by the fact that confounders and effect modifiers on the causal pathways linked by different mediators often overlap. A sparsity-inducing prior is incorporated to capture the most relevant confounders and effect modifiers on different causal pathways. The individual-specific interventional direct and indirect effects are derived on the scale of the logarithm of hazards and survival function. A Bayesian approach with an efficient Markov chain Monte Carlo algorithm is developed to estimate the conditional interventional effects through the Monte Carlo implementation of the mediation formula. Simulation studies are conducted to verify the empirical performance of the proposed method. An application to the ACTG175 study further demonstrates the method's utility in causal discovery and heterogeneity quantification.

Carbon Stock Estimation of Poplar Plantations Based on Additive Biomass Models

Accurate estimation of biomass and carbon stocks in forest ecosystems is critical for understanding their roles in carbon sequestration and climate change mitigation. Currently, the development of stand biomass models and carbon stock estimation at the regional scale has emerged as a prominent research priority. In this study, 225 Populus spp. (poplar) trees in Shandong Province, China, were destructively sampled to obtain the biomass of their components. Two models (MS1 and MS2) were developed using allometric equations and the seemingly unrelated regression (SUR) method to ensure additive properties across tree components. The model evaluation employed the leave-one-out jackknife (LOO) method, considering statistics such as adjusted R-squared (Ra2), root mean square error (RMSE), mean absolute percent error (MAPE), and mean absolute error (MAE). The results from our models demonstrated high accuracy, with MS2 slightly outperforming MS1 after incorporating tree height as an independent variable. The models reliably estimated component-specific biomass and carbon stocks, with distinct variations observed in the carbon content among foliage (47.14 ± 2.07%), branches (47.26 ± 2.48%), stems (47.67 ± 2.21%), and roots (46.37 ± 2.78%). Carbon stocks in poplar plantations increased with the diameter class, ranging from 5 to 35 cm and correspondingly from 3.670 to 172.491 Mg C ha−1. As the diameter class increases, the carbon allocation strategy of poplars aligns with the CSR strategy, transitioning from prioritizing growth competition to emphasizing self-stabilization. Our research proposes a robust framework for assessing biomass and carbon stocks in poplar plantations, which is essential for evidence-based forest management strategies.

Light distribution at the fruit tree-crop interface and consequences for yield in sloping upland agroforestry

Agroforestry can improve soil conservation and overall farm productivity compared with sole-crop systems, but its benefits are limited by competitive interactions between tree and crop components. Studies on light competition have been performed on relatively flat land, but slope can influence light distribution. Little is known about optimizing light utilization and enhancing system productivity and/or income from agroforestry on sloping land.This study examined how slope influences light distribution and performance of maize and coffee crops in fruit tree-crop agroforestry. Starting hypotheses were that 1) crops upslope of tree rows receive and intercept greater amounts of light than those downslope; and 2) position of the crop is more important for light interception and yield when fruit trees have a large, dense canopy.Five-year-old fruit-crop agroforestry experiments on west-southwest facing slopes were revisited. Each agroforestry treatment was divided into nine zones relative to the tree rows (zone 5), with zones 1–4 upslope and 6–9 downslope of the fruit tree row. Light distribution was assessed using Hemiview and SunScan and compared with that in sole-maize and sole-coffee systems. Crop growth and yield were also recorded.Incident light to the crop was higher in the sole-crop system than in agroforestry. In agroforestry, incident light to the crops was lower downslope of trees than upslope but increased with increasing distance from the tree rows. On average, 0.40–0.50 fraction of total light reached the soil surface. Downslope had a stronger negative effect on light distribution and crop yield than upslope. The available light at the soil surface provides scope for additional components. Further studies on the light demands of different crops during the season could improve system design.

Population data for 12 X-STRs loci in Malaysian Malay and Chinese populations

The utilization of X-chromosome short tandem repeats (X-STRs) for human identification particularly in resolving complex kinship cases has been advocated. Since, forensic statistical parameters vary among different populations, and because the X-STRs population data representing the diverse population of Peninsular Malaysia remain unavailable, the specific attempt reported here for the Malays (n = 224) and Chinese (n = 201) populations appears forensically relevant to support the evidential value of the 12 X-STRs markers for human identification in Malaysia. Results derived from the Qiagen Investigator® Argus X-12 kit revealed that DXS10135 as the most polymorphic locus with high genetic diversity, polymorphic information content, heterozygosity as well as power of exclusion. Based on allele frequencies, the combined power of discrimination as well as the mean exclusion chance (MECKrüger, MECKishida, MECDesmarais and MECDesmaraisDuo) values for the Malays and Chinese were individually ≥0.999995532964908. As for the combined power of discrimination as well as the mean exclusion chance (MECKrüger, MECKishida, MECDesmarais and MECDesmaraisDuo) calculated based on haplotype frequencies, the values were ≥0.9999986410567 for the Malays and Chinese populations. In addition, results from the genetic distance, neighbor-joining phylogenetic tree and principal component analysis revealed close biogeographical distributions of the studied populations with other South East Asian populations. Hence, the utilization of the X-STRs data for identifying individuals among the Malays and Chinese populations in Peninsular Malaysia for forensic application appears as highly supported.

Legacy ICS Cybersecurity Assessment Using Hybrid Threat Modeling—An Oil and Gas Sector Case Study

As security breaches are increasingly widely reported in today’s culture, cybersecurity is gaining attention on a global scale. Threat modeling methods (TMM) are a proactive security practice that is essential for pinpointing risks and limiting their impact. This paper proposes a hybrid threat modeling framework based on system-centric, attacker-centric, and risk-centric approaches to identify threats in Operational Technology (OT) applications. OT is made up of software and hardware used to manage, secure, and control industrial control systems (ICS), and its environments include factories, power plants, oil and gas refineries, and pipelines. To visualize the “big picture” of its infrastructure risk profile and improve understanding of the full attack surface, the proposed framework builds on several threat modeling methodologies: PASTA modeling, STRIDE, and attack tree components. Nevertheless, the continuity and stability of vital infrastructure will continue to depend heavily on legacy equipment. Thus, protecting the availability, security, and safety of industrial environments and vital infrastructure from cyberattacks requires operational technology (OT) cybersecurity. The feasibility of the proposed approach is illustrated with a case study from a real oil and gas production plant control system where numerous significant cyberattacks in recent years have targeted OT networks more frequently as hackers realized the possibility of disruption due to insufficient OT security, particularly for outdated systems. The proposed framework achieved better results in detecting threats and severity in the design of the case study system, helping to increase security and support cybersecurity assessment of legacy control systems.

Tree diversity drives understory carbon storage rather than overstory carbon storage across forest types

Although numerous studies have proposed explanations for the specific and relative effects of stand structure, plant diversity, and environmental conditions on carbon (C) storage in forest ecosystems, understanding how these factors collectively affect C storage in different community layers (trees, shrubs, and herbs) and forest types (mixed, broad-leaved (E), broad-leaved (M), and coniferous forest) continues to pose challenges. To address this, we used structural equation models to quantify the influence of biotic factors (mean DBH, mean height, maximum height, stem density, and basal area) and abiotic factors (elevation and canopy openness), as well as metrics of species diversity (Shannon–Wiener index, Simpson index, and Pielou’s evenness) in various forest types. Our analysis revealed the critical roles of forest types and elevation in explaining a substantial portion of variability in C storage in the overstory layer, with a moderate influence of stand factors (mean DBH and basal area) and a slightly negative impact of tree species diversity (Shannon–Wiener index). Notably, forest height emerged as the primary predictor of C storage in the herb layer. Regression relationships further highlighted the significant contribution of tree species diversity to mean height, understory C storage, and branch biomass within the forest ecosystem. Our insights into tree species diversity, derived from structural equation modeling of C storage in the overstory, suggest that the effects of tree species diversity may be influenced by stem biomass in statistical reasoning within temperate forests. Further research should also integrate tree species diversity with tree components biomass, forest mean height, understory C, and canopy openness to understand complex relationships and maintain healthy and sustainable ecosystems in the face of global climate challenges.

Generic Workflow of a Highly Effective and Easy Anther Culture Method for Both Japonica and Indica Rice.

As one of the most important staple crops in the world, rice plays a pivotal role in world food security. The creation of doubled haploids based on anther culture is an important technology for rice breeding. However, at present, rice anther culture technology still faces many problems, such as genotype dependency, especially genotypes of indica rice. In this study, fifteen rice genotypes, including twelve japonica rice genotypes and three indica rice genotypes, were randomly selected and used to study anther culture by using a modified M8 medium. The results showed that the total callus induction rates of these different rice genotypes ranged from 0.81 to 13.95%, with an average of 6.64%, while the callus induction rates calculated for the top ten highest callus inductions for each rice genotype ranged from 2.75 to 17.00%, with an average of 10.56%. There were varying gaps between the total callus induction rates and the callus induction rates in these different rice genotypes. The fact that the gaps for some rice genotypes were relatively large indicated that standard tiller or anther collection was not applicable to all rice genotypes and that there was still a lot of room for improvement in the callus induction rate of some rice genotypes through optimization of the sampling method. The plantlet regeneration rates ranged from 12.55 to 456.54%, with an average of 200.10%. Although there were many albinos from anther culture for some rice genotypes, these would still meet the requirement if the rice genotypes had higher callus induction rates or regeneration rates. The percentages of seed setting of regenerated green seedlings ranged from 14% to 84%, with an average of 48.73%. Genetic diversity analysis showed that the genetic background of these different rice genotypes was representative, and the phylogenetic tree and Principal Component Analysis (PCA) divided them into indica and japonica types. Therefore, in this study, an anther culture method suitable for both indica and japonica rice genotypes was established, which could improve doubled haploid breeding in rice.

Non-minimal elliptic threefolds at infinite distance. Part I. Log Calabi-Yau resolutions

We study infinite-distance limits in the complex structure moduli space of elliptic Calabi-Yau threefolds. In F-theory compactifications to six dimensions, such limits include infinite-distance trajectories in the non-perturbative open string moduli space. The limits are described as degenerations of elliptic threefolds whose central elements exhibit non-minimal elliptic fibers, in the Kodaira sense, over curves on the base. We show how these non-crepant singularities can be removed by a systematic sequence of blow-ups of the base, leading to a union of log Calabi-Yau spaces glued together along their boundaries. We identify criteria for the blow-ups to give rise to open chains or more complicated trees of components and analyse the blow-up geometry. While our results are general and applicable to all non-minimal degenerations of Calabi-Yau threefolds in codimension one, we exemplify them in particular for elliptic threefolds over Hirzebruch surface base spaces. We also explain how to extract the gauge algebra for F-theory probing such reducible asymptotic geometries. This analysis is the basis for a detailed F-theory interpretation of the associated infinite-distance limits that will be provided in a companion paper [1].

Therapeutic Potential and Benefits of Moringa oleifera: An updated Overview

In this review, we have tried to explore the therapeutic potential and benefits of Moringa oleifera. Further investigation is required in this area, along with conducting clinical trials to assess any potential negative or toxic effects of Moringa oleifera in humans, ensuring its safe usage. This review delves into the intricate phytochemical composition, medicinal applications, and pharmacological characteristics of various components of this versatile tree. These parts have been found to have stimulating effects on the heart and circulation, as well as anti-tumor, anti-inflammatory, and antioxidant properties. The extensive range of pharmacological and botanical compound activities, as well as the traditional medicinal uses of Moringa oleifera, require a more thorough and comprehensive analysis. This will allow for a rigorous scientific examination of the documented literature, further justifying its effectiveness.

Anticancer Effects of Secoiridoids-A Scoping Review of the Molecular Mechanisms behind the Chemopreventive Effects of the Olive Tree Components Oleocanthal, Oleacein, and Oleuropein.

The olive tree (Olea europaea) and olive oil hold significant cultural and historical importance in Europe. The health benefits associated with olive oil consumption have been well documented. This paper explores the mechanisms of the anti-cancer effects of olive oil and olive leaf, focusing on their key bioactive compounds, namely oleocanthal, oleacein, and oleuropein. The chemopreventive potential of oleocanthal, oleacein, and oleuropein is comprehensively examined through this systematic review. We conducted a systematic literature search to identify eligible articles from Scopus, PubMed, and Web of Science databases published up to 10 October 2023. Among 4037 identified articles, there were 88 eligible articles describing mechanisms of chemopreventive effects of oleocanthal, oleacein, and oleuropein. These compounds have the ability to inhibit cell proliferation, induce cell death (apoptosis, autophagy, and necrosis), inhibit angiogenesis, suppress tumor metastasis, and modulate cancer-associated signalling pathways. Additionally, oleocanthal and oleuropein were also reported to disrupt redox hemostasis. This review provides insights into the chemopreventive mechanisms of O. europaea-derived secoiridoids, shedding light on their role in chemoprevention. The bioactivities summarized in the paper support the epidemiological evidence demonstrating a negative correlation between olive oil consumption and cancer risk. Furthermore, the mapped and summarized secondary signalling pathways may provide information to elucidate new synergies with other chemopreventive agents to complement chemotherapies and develop novel nutrition-based anti-cancer approaches.

Insights into the genomic homogeneity of Moroccan indigenous sheep breeds though the lens of runs of homozygosity

Numerous studies have indicated that Morocco’s indigenous sheep breeds are genetically homogenous, posing a risk to their survival in the challenging harsh climate conditions where they predominantly inhabit. To understand the genetic behind genetic homogeneity through the lens of runs of homozygosity (ROH), we analyzed the whole genome sequences of five indigenous sheep breeds (Beni Guil, Ouled Djellal, D’man, Sardi, Timahdite and Admixed).The results from principal component, admixture, Fst, and neighbour joining tree analyses consistently showed a homogenous genetic structure. This structure was characterized by an average length of 1.83 Mb for runs of homozygosity (ROH) segments, with a limited number of long ROH segments (24–48 Mb and > 48 Mb). The most common ROH segments were those ranging from 1–6 Mb. The most significant regions of homozygosity (ROH Islands) were mostly observed in two chromosomes, namely Chr1 and Chr5. Specifically, ROH Islands were exclusively discovered in the Ouled Djellal breed on Chr1, whereas Chr5 exhibited ROH Islands in all breeds. The analysis of ROH Island and iHS technique was employed to detect signatures of selection on Chr1 and Chr5. The results indicate that Chr5 had a high level of homogeneity, with the same genes being discovered across all breeds. In contrast, Chr1 displays some genetic variances between breeds. Genes identified on Chr5 included SLC39A1, IL23A, CAST, IL5, IL13, and IL4 which are responsible for immune response while genes identified on Chr1 include SOD1, SLAMF9, RTP4, CLDN1, and PRKAA2. ROH segment profile and effective population sizes patterns suggests that the genetic uniformity of studied breeds is the outcome of events that transpired between 250 and 300 generations ago. This research not only contributes to the understanding of ROH distribution across breeds but helps design and implement native sheep breeding and conservation strategies in Morocco. Future research, incorporating a broader sample size and utilizing the pangenome for reference, is recommended to further elucidate these breeds’ genomic landscapes and adaptive mechanisms.

Natural regeneration in edge and interior of a forest fragment at the Catarinense Plateau

Forest fragmentation is one of the greatest challenges for forest conservation in the Catarinense Plateau region. Thus, this work aimed to evaluate the edge effect on the structure and floristics of natural tree regeneration in a fragment of Mixed Ombrophylous Forest in São José do Cerrito, Santa Catarina. The natural regeneration of the tree component in the understory was sampled in four transects placed perpendicular to the edge of the fragment. Eight plots of 20 m² were installed on the edge (contact with the surrounding matrix) and inside (100 m from the edge) of the fragment, subdivided into smaller plots according to the class of regenerants. The regenerants were identified, measured in height and classified according to their successional group, conservation status, endemism and calculated the regeneration index for each class of height and total. For statistical analysis, Non-Metric Multidimensional Scaling (NMDS) analysis was used. The results showed a significant difference between the interior and edge of the fragment, with the regenerating community on the edge being significantly more abundant and more diverse than the interior. The species with the highest rate of total regeneration towards the interior were Myrcia hatschbachii (TNR=12.1%) and Banara tomentosa (TNR=11.1%), and towards the edge it was Myrcia oblongata (TNR=15.1%). It is concluded that the edge effect appears to have been a determining factor for the alteration in the structure and floristic composition of the regenerants.

Associations between natural blue and green space and preschool children's movement behaviours

Abstract Natural outdoor environments provide important settings for children to engage in physical activity. It is unclear if these relationships also exist in preschool aged children. We examined associations between amount and type of neighbourhood vegetation and blue space, proximity to the beach and preschooler's device‐measured movement behaviours. Accelerometer data from 1081 preschool children were processed into physical activity and sedentary behaviours using a machine learned random forest physical activity classification model specifically developed for children under five. High‐resolution aerial imagery data and Geographic Information Systems were used to identify total percentage of neighbourhood vegetation and vegetation components (grass, shrubs and trees) and presence and total percentage of blue space (ocean, riverways and lakes and swamps) for 500, 1600 and 5000 m service areas around children's residences. Distance to the closest beach, patrolled beach, and dog beach were also calculated. Amount of neighbourhood vegetation was inversely associated with boys sedentary time in the 500 m (β = −0.91 min/day, p = 0.006, 95% CI [−1.55, −0.33]) and 1600 m (β = −1.30 min/day, p = 0.001, 95% CI [−2.08, −0.53]) service area, and positively associated with walking time in the 1600 m (β = 0.12 min/day, p = 0.045, 95% CI [0.02, 0.22]) service area. The presence of local riverways was positively associated with girls walking time in the 1600 m (β = 2.34 min/day, p = 0.009, 95% CI [0.59, 4.09]), and 5000 m (β = 1.67 min/day, p = 0.019, 95% CI [0.27, 3.06]) buffer. Distance to dog beach was positively associated with boys sedentary behaviours. Presence of lake and swamps were negatively associated with boys walking, and presence of riverways was negatively associated with girls moderate‐to‐vigorous activities and games and boys running in the 5000 m service area. These findings suggest higher amounts of neighbourhood vegetation and certain types of blue space such as riverways and dog beaches could facilitate positive movement behaviours in young children. Our findings that natural outdoor environments are associated with preschool children's movement behaviours add to evidence which could contribute to policy implications for urban planning and the provision and protection of natural environments within cities. Read the free Plain Language Summary for this article on the Journal blog.

Soil Chemical Quality in Integrated Production Systems with the Presence of Native and Exotic Tree Components in the Brazilian Eastern Amazon

Soil Chemical Quality in Integrated Production Systems with the Presence of Native and Exotic Tree Components in the Brazilian Eastern Amazon

Allometric equations for estimation of above- and below-ground biomass of Acacia mearnsii in northwestern Ethiopia

Correct estimation of tree biomass is important when calculating uptake or emission of CO2 in relation to land-use and land-use change. The objectives of this study were (1) to estimate the root/shoot ratio for the estimation of root biomass based on the above-ground biomass (AGB) of Acacia mearnsii, and (2) to develop allometric equations for the estimation of the above-and below-ground biomass (BGB) of Acacia mearnsii. To estimate the AGB and BGB, twenty-four trees of varying ages (3, 4, 5, and 6 years) were harvested, with six trees per age group. We measured the dry biomass for different tree parts and developed allometric models using tree height (H) and diameter at breast height (DBH) as independent variables. The results showed that the biomass of the stem accounted for 69% of the total biomass, followed by branches (14%), roots (8.1%), and leaves (7.3%). The recorded mean root/shoot ratio was 0.11. The biomass of the stem and coarse roots increased with increasing tree age, while a contrary trend was observed for the other tree components. Each component has its unique allometric model.

Machine learning techniques to identify risk factors of breast cancer among women in Mashhad, Iran.

Low survival rates of breast cancer in developing countries are mainly due to the lack of early detection plans and adequate diagnosis and treatment facilities. This study aimed to apply machine learning techniques to recognize the most important breast cancer risk factors. This case-control study included women aged 17-75 years who were referred to medical centers affiliated with Mashhad University of Medical Science between March 21, 2015, and March 19, 2016. The study had two datasets: one with 516 samples (258 cases and 258 controls) and another with 606 samples (303 cases and 303 controls). Written informed consent has been observed. Decision Tree (DT), Random Forest (RF), Logistic Regression (LR), and Principal Component Analysis (PCA) were applied using R studio software. Regarding the DT and RF, the most important features that impact breast cancer were family cancer, individual history of breast cancer, biopsy sampling, rarely consumption of a dairy, fruit, and vegetable meal, while in PCA and LR these features including family cancer, pregnancy number, pregnancy tendency, abortion, first menstruation, the age of first childbirth and childbirth number. Machine learning algorithms can be used to extract the most important factors in the diagnosis of breast cancer in developing countries such as Iran.

Predicting performance of students by optimizing tree components of random forest using genetic algorithm

Prediction of student academic performance is still a problem because of the limitations of the existing methods specifically low generalizability and lack of interpretability. This study suggests a new approach that deals with the current problems and provides more reliable predictions. The proposed approach combines the information gain (IG) and Laplacian score (LS) for feature selection. In this feature selection scheme, combination of IG and LS is used for ranking features and then, Sequential Forward Selection mechanism is used for determining the most relevant indicators. Also, combination of random forest algorithm with a genetic algorithm for is introduced for multi-class classification. This approach strives to attain more accuracy and reliability than current techniques. The case study shows the proposed strategy can predict performance of students with average accuracy of 93.11 % which shows a minimum improvement of 2.25 % compared to the baseline methods. The findings were further confirmed by the analysis of different evaluation metrics (Accuracy, Precision, Recall, F-Measure) to prove the efficiency of the proposed mechanism.