Dissimilar Methods Research Articles

Transfer learning for molecular property predictions from small datasets

Machine learning has emerged as a new tool in chemistry to bypass expensive experiments or quantum-chemical calculations, for example, in high-throughput screening applications. However, many machine learning studies rely on small datasets, making it difficult to efficiently implement powerful deep learning architectures such as message passing neural networks. In this study, we benchmark common machine learning models for the prediction of molecular properties on two small datasets, for which the best results are obtained with the message passing neural network PaiNN as well as SOAP molecular descriptors concatenated to a set of simple molecular descriptors tailored to gradient boosting with regression trees. To further improve the predictive capabilities of PaiNN, we present a transfer learning strategy that uses large datasets to pre-train the respective models and allows us to obtain more accurate models after fine-tuning on the original datasets. The pre-training labels are obtained from computationally cheap ab initio or semi-empirical models, and both datasets are normalized to mean zero and standard deviation one to align the labels’ distributions. This study covers two small chemistry datasets, the Harvard Organic Photovoltaics dataset (HOPV, HOMO–LUMO-gaps), for which excellent results are obtained, and the FreeSolv dataset (solvation energies), where this method is less successful, probably due to a complex underlying learning task and the dissimilar methods used to obtain pre-training and fine-tuning labels. Finally, we find that for the HOPV dataset, the final training results do not improve monotonically with the size of the pre-training dataset, but pre-training with fewer data points can lead to more biased pre-trained models and higher accuracy after fine-tuning.

Emergence of multivariate climate change signals

Abstract The emergence of a climate change signal relative to background variability is a useful metric for understanding local changes and their consequences. Studies have identified emergent signals of climate change, particularly in temperature-based indices with weaker signals found for precipitation metrics. In this study, we adapt climate analogue methods to examine multivariate climate change emergence over the historical period. We use seasonal temperature and precipitation observations and apply a sigma dissimilarity method to demonstrate that large local climate changes may already be identified, particularly in low-latitude regions. The multivariate methodology brings forward the time of emergence by several decades in many areas relative to analysing temperature in isolation. We observed particularly large departures from an early-20th century climate in years when the global warming signal is compounded by an El Niño-influence. The latitudinal dependence in the emergent climate change signal means that lower-income nations have experienced earlier and stronger emergent climate change signals than the wealthiest regions. Analysis based on temperature and precipitation extreme indices finds weaker signals and less evidence of emergence but is hampered by lack of long-running observations in equatorial areas. The framework developed here may be extended to attribution and projections analyses.

Snow Persistence and Snow Line Elevation Trends in a Snowmelt-Driven Basin in the Central Andes and Their Correlations with Hydroclimatic Variables

The mountain cryosphere is crucial for socio-economic processes, especially during the dry seasons. However, anthropogenic climate change has had a detrimental impact on the cryosphere due to its sensitivity. Over the past two decades, there has been a decline in precipitation and a temperature rise, leading to a substantial reduction in the timing and extent of snow cover. This increase in temperature also elevates the snow line elevation (SLE), further diminishing the volume of available freshwater in the snow-driven basins of the Andes. In this study, we use 22 years (2000–2021) of 8-day snow product (MOD10A2) from the Moderate Resolution Imaging Spectroradiometer (MODIS) to analyze the annual and seasonal variability of snow cover area, SLE, and snow persistence (SP, an indicator of the duration of snow) in the Yeso River basin in Central Chile and the correlation of SP and SLE with hydrometeorological variables and climatic indices. We introduce a new approach called the Maximum Dissimilarity Method to obtain the SLE even on cloudy days. The results are as follows: (1) Snow cover area reductions of 34.0 km2 at low elevations in spring and 86.5 km2 at mid elevations in summer were found when comparing the period 2016–2021 to 2000–2004; (2) SP trends at the annual scale revealed a significant decrease in 89% of its area and an average of 3.6 fewer days of snow cover per year; (3) an upward and significant trend of 21 m‧year−1 in the annual SLE was found; and (4) annual SP and SLE were highly correlated with annual hydrometeorological variables, and spring and summer snow variables were significantly correlated with dry streamflow. This methodology can potentially serve as a valuable tool for detecting trends in snow-covered surfaces, and thereby associate these changes with climate change or other anthropogenic effects in future research.

Distance‐based weighting methods for composite indicators, with applications related to energy sustainability

AbstractIn this paper, we propose a novel use of four distance‐based methods for constructing composite indicators: namely, the maximizing deviations method, the weighted least‐square (WLD) deviation from the mean method, the WLD deviation from the ideal method, and the WLD dissimilarity method. The main advantages of these methods are that they have analytical solutions. Thus, there is no need to solve the underlying programming problem for each application. They also result in common (but not necessarily equal) weights that allow complete comparison and ranking. We explore the potential of the suggested weighting method by using it to re‐estimate the Sustainable Energy Index and the Sustainable Development Goal 7 composite indicator.

Online damping control of power system with LME function of wind farm

The wide-area damping controller (WADC) is suggested by this paper in an online for power systems based on the line modal energy (LME) function of the wind farm. The presence of a wind farm always increases inter-area oscillations, but the proposed method has been made doubly-fed induction generators (DFIG) as a strong point to improve inter-area oscillations. For this purpose, an approach was presented based on energy function, a simple Brunovsky system, and an extended state observer (ESO) to control DFIG. The modal energy function supply traits in a network are evaluated in dissimilar methods, and the system overriding mode is recognized with the Tufts-Kumaresan method (TK). Finally, the wide-area control signals in the DFIG grid side converter (GSC) are selected and it is implemented with the voltage-oriented control (VOC). It is effected in diverse conditions on the standard two-area standard network to authenticate the suggested technique by MATLAB.

From brainwaves and ripples to Helen of Troy and Orlan: the depiction and significance of salience

ABSTRACT The averaging of waveforms necessary to detect small cortical evoked potentials which was pioneered by George Dawson, and the periodicity of component waves resulting from interference identified by Thomas Young, reveal selected components of the visual record to be diminished and others to be enhanced and thus salient. Surprisingly, these examples of achieving salience in neurophysiology and physics were anticipated two millennia ago by the Greek artist Zeuxis. When commissioned to paint a portrait of Helen of Troy, Zeuxis used a not dissimilar method of selection which still resonates today in the carnal artistry of Orlan. These examples reveal the important contribution of graphic methods to the depiction and hence the significance of salience in both the sciences and the humanities.

Study on the Difference of Human Body Balance Stability Regulation Characteristics by Time-Frequency and Time-Domain Data Processing Methods.

In all, 16 subjects were tested, including 8 from the Chinese national team who had won the world championships of freestyle skiing aerials, with 10+ years of training (age: 23 ± 23.1 years, Height: 176 ± 2.1 cm, and weight: 69 ± 3.5 kg), and 8 ordinary graduate students of Shenyang Institute of Physical Education (age: 22.6 ± 4.6 years, Height: 179 ± 3.3 cm, and weight: 73 ± 4.1 kg). When performing the tasks, the research subjects were required to stand on the steady support surface (with eyes closed and legs closed) for 30 s in each testing. The displacement data of the anteroposterior (AP) direction and the mediolateral (ML) direction of their centre of pressure (COP) were recorded. Then, WT and OSI were calculated. Two dissimilar methods were compared to analyse the characteristics of balance ability. (1) The athletes' WT values in the AP direction and the ML direction were concentrated in the interval of 22~30 s and 0-8 s, respectively, while the ordinary graduate students' WT values in the AP direction and the ML direction were concentrated in the interval of 10~25 s and 0-7 s, respectively; (2) the WT values of the regular graduate students in the AP direction and the ML direction were higher than those of the athletes (p < 0.01); and (3) the OSI value in the AP direction of the athletes was higher than of the ordinary graduate students, while the OSI value in the ML direction of the athletes was lower than that of regular graduate students. Compared to the OSI, WT can analyse the characteristics of balance control ability more effectively. The COP displacement frequencies of the athletes and ordinary graduate students were concentrated in the low-frequency bands. The athletes had superior adjustment ability in an imbalanced state and could adjust to the best position without effort. In addition, the athletes had a stronger adaptive ability. In comparison, the ordinary graduate students had comparatively poor adaptive ability and weak adjustment ability in the imbalanced state, so it was difficult for them to attain the best angle after adjustment.

The science behind “values”: Applying moral foundations theory to strategic foresight

Abstract“Values” play an oversized role in strategic foresight: they help define scanning frameworks, direct scanning efforts, inform change driver and scenario development, and underpin change within various systems and domains (e.g., politics, society, etc.). And yet, values are largely understudied within foresight. They are rarely defined consistently or explored with reference to a theoretical model of how values emerge or evolve. Rather, values are researched using dissimilar methods depending on the foresight research at hand, which can lead to gaps in analysis and inconsistency between foresight projects. Moral Foundations Theory (MFT), a social psychological theory that identifies common human moral values, offers a solution. MFT describes six moral values or “foundations”—care, fairness, loyalty, authority, sanctity, and liberty—each explained through the evolutionary development of humanity and detectable across cultures. Within foresight, MFT can be applied to understand and identify shifts in the influence of different values, which can result in more novel and unexpected conclusions. With these potential benefits available, we propose adopting and adapting MFT for use within the foresight to improve the way it approaches, identifies, and utilizes values. Our article unpacks MFT into its core tenets and illustrates how it can be used to inform scanning, change driver development, and scenario construction.

Aberrantly expressed long noncoding RNAs as potential prognostic biomarkers in newly diagnosed multiple myeloma: A systemic review and meta-analysis.

Numerous studies have manifested long noncoding RNAs (lncRNAs) as biomarkers to determine the prognosis of multiple myeloma (MM) patients. Nevertheless, the prognostic role of lncRNAs in MM is still ambiguous. Herein, we performed a meta-analysis to evaluate the predictive value of aberrantly expressed lncRNAs in MM. A systemic literature search was performed in PubMed, EMBASE, Cochrane, and Web of Science databases until October 9, 2021, and the protocol was registered in the PROSPERO database (CRD42021284364). Our study extracted the hazard ratios (HRs) and 95% confidence intervals (CIs) of overall survival (OS), progression-free survival (PFS), or event-free survival (EFS). Begg's and Egger's tests were employed to correct publication bias. Twenty-six individual studies containing 3501 MM patients were enrolled in this study. The results showed that aberrant expression of lncRNAs was associated with poor OS and PFS of MM patients. The pooled HRs for univariate OS and PFS were 1.48 (95% CI=1.17-1.88, p < 0.001) and 1.30 (95% CI=1.18-1.43, p< 0.001), respectively, whereas the pooled HRs for multivariate OS and PFS were 1.50 (95% CI=1.16-1.95, p < 0.001) and 1.59 (95% CI=1.22-2.07, p < 0.001), respectively. Subgroup analysis suggested that MALAT1, TCF7, NEAT1, and PVT1 upregulation were associated with poor OS (p< 0.05), PVT1, and TCF7 upregulation were implicated with worse PFS (p< 0.05), while only TCF7 overexpression was correlated with reduced EFS (p< 0.05). Moreover, the contour-enhanced funnel plot demonstrated the reliability of our current conclusion, which was not affected by publication bias. Aberrantly expressed particular lncRNAs are critical prognostic indicators in long-term survival as well as promising biomarkers in progression-free status. However, different cutoff values and dissimilar methods to assess lncRNA expression among studies may lead to heterogeneity.

Exploring methods to summarize gut microbiota composition for microbiability estimation and phenotypic prediction in swine.

The microbial composition resemblance among individuals in a group can be summarized in a square covariance matrix and fitted in linear models. We investigated eight approaches to create the matrix that quantified the resemblance between animals based on the gut microbiota composition. We aimed to compare the performance of different methods in estimating trait microbiability and predicting growth and body composition traits in three pig breeds. This study included 651 purebred boars from either breed: Duroc (n = 205), Landrace (n = 226), and Large White (n = 220). Growth and body composition traits, including body weight (BW), ultrasound backfat thickness (BF), ultrasound loin depth (LD), and ultrasound intramuscular fat (IMF) content, were measured on live animals at the market weight (156 ± 2.5 d of age). Rectal swabs were taken from each animal at 158 ± 4 d of age and subjected to 16S rRNA gene sequencing. Eight methods were used to create the microbial similarity matrices, including 4 kernel functions (Linear Kernel, LK; Polynomial Kernel, PK; Gaussian Kernel, GK; Arc-cosine Kernel with one hidden layer, AK1), 2 dissimilarity methods (Bray-Curtis, BC; Jaccard, JA), and 2 ordination methods (Metric Multidimensional Scaling, MDS; Detrended Correspondence analysis, DCA). Based on the matrix used, microbiability estimates ranged from 0.07 to 0.21 and 0.12 to 0.53 for Duroc, 0.03 to 0.21 and 0.05 to 0.44 for Landrace, and 0.02 to 0.24 and 0.05 to 0.52 for Large White pigs averaged over traits in the model with sire, pen, and microbiome, and model with the only microbiome, respectively. The GK, JA, BC, and AK1 obtained greater microbiability estimates than the remaining methods across traits and breeds. Predictions were made within each breed group using four-fold cross-validation based on the relatedness of sires in each breed group. The prediction accuracy ranged from 0.03 to 0.18 for BW, 0.08 to 0.31 for BF, 0.21 to 0.48 for LD, and 0.04 to 0.16 for IMF when averaged across breeds. The BC, MDS, LK, and JA achieved better accuracy than other methods in most predictions. Overall, the PK and DCA exhibited the worst performance compared to other microbiability estimation and prediction methods. The current study shows how alternative approaches summarized the resemblance of gut microbiota composition among animals and contributed this information to variance component estimation and phenotypic prediction in swine.

Weibull Reliability Estimation of (3+1) Cascade Model

In this paper presents the R reliability mathematical formula of (3+1) Weibull Cascade model. The reliability of the model is expressed by Weibull random variables, which are stress and strength distributions. The reliability model was estimated by six dissimilar methods (ML, Mo, LS, WLS, Rg and Pr) and simulation was performed using MATLAB 2012 program to compare the results of the reliability model estimates using the MSE criterion, the results indicated that the best estimator among the six estimators was ML.

Comparison of Three Methods for Measuring Dietary Composition of Plains Hog-nosed Snakes

Wild animal diets are challenging to quantify, and the various methods for doing so have strengths and weaknesses. Combining multiple methods can allow ecologists to assess their level of confidence in particular results, increase sample size, and investigate diet over varying time scales. The biases of traditional gut content–based methods are mostly well understood. Newer methods may have important biases that can only be worked out through comparison to established ones. We collected data on the diet of wild Plains Hog-nosed Snakes (Heterodon nasicus) using multiple, fundamentally dissimilar methods, combined analytically using a Bayesian framework to describe an ontogenetic dietary shift. Gut contents were the most straightforward, but yielded a small sample size that fell below any reasonable threshold for making generalizations. Stable isotopes indicated an obvious ontogenetic dietary shift, but were labor-intensive, and conclusions are limited by multiple methodological caveats including similarity among prey groups, maternal carryover effects, and uncertainty in trophic enrichment factors. Fecal environmental DNA (eDNA) was intermediate in terms of effort, yielding results congruent with the other two methods, but the interpretation of which would likely have been confounded by contaminants had we not used all three methods in tandem. Several apparent artifacts are discussed. There are some reassuring similarities among methods. There are also several differences. The most complete picture uses data from all methods taken together. Future studies should attempt to compare the biases, expense, and potential drawbacks of these and other methods in greater detail.

Neutrsophic Health Analysis in Times of COVID-19

The current COVID-19 pandemic represents a danger for which efforts have been joined to find an effective treatment. This pandemic has evolved so quickly that new data emerge daily on the number of sick and fatal cases. As of September 2021, more than 180 countries with positive COVID-19 cases have been notified to the World Health Organization, including 228,807,631 confirmed cases, including 4,697,099 deaths. So far, the Americas region is the most affected with a total of 88,207,746 confirmed cases, and during this period, Ecuador has reported 246 new infections on average each day, for a total of 507,003 infections and 32,661 deaths. To date, dissimilar methods and treatments have been used to mitigate its effects. However, no effective treatment option has been found against it, generating uncertainty, social panic, and impacts on the population's mental health as a result of the fear of infection and death. That is why the present work focuses on analyzing and determining the alternatives for the control of detection of the pandemic, through the processing of the neutrosophic TOPSIS method. It offers many benefits in the analysis of neutralities to the study of indeterminacies in the field of Medicine. The processing using neutrosophic methods allowed obtaining the best alternative to fight against COVID-19.

An enhanced version of Harris Hawks Optimization by dimension learning-based hunting for Breast Cancer Detection

Swarm intelligence techniques have a vast range of real world applications.Some applications are in the domain of medical data mining where, main attention is on structure models for the classification and expectation of numerous diseases. These biomedical applications have grabbed the interest of numerous researchers because these are most serious and prevalent causes of death among the human whole world out of which breast cancer is the most serious issue. Mammography is the initial screening assessment of breast cancer. In this study, an enhanced version of Harris Hawks Optimization (HHO) approach has been developed for biomedical databases, known as DLHO. This approach has been introduced by integrating the merits of dimension learning-based hunting (DLH) search strategy with HHO. The main objective of this study is to alleviate the lack of crowd diversity, premature convergence of the HHO and the imbalance amid the exploration and exploitation. DLH search strategy utilizes a dissimilar method to paradigm a neighborhood for each search member in which the neighboring information can be shared amid search agents. This strategy helps in maintaining the diversity and the balance amid global and local search. To evaluate the DLHO lot of experiments have been taken such as (i) the performance of optimizers have analysed by using 29-CEC -2017 test suites, (ii) to demonstrate the effectiveness of the DLHO it has been tested on different biomedical databases out of which we have used two different databases for Breast i.e. MIAS and second database has been taken from the University of California at Irvine (UCI) Machine Learning Repository.Also to test the robustness of the proposed method its been tested on two other databases of such as Balloon and Heart taken from the UCI Machine Learning Repository. All the results are in the favour of the proposed technique.

Assessment of Multisource Remote Sensing Image Fusion by several dissimilarity Methods

Recently, advancements in remote sensing technology have made it easier to obtain various temporal and spatial resolution satellite data. Remote sensing techniques can be a useful tool to detect vegetation and soil conditions, monitor crop diseases and natural disaster prevention, etc. Although the same scene taken by different sensors belong to the same ground object, the information that they offered are redundant, complementary and collaborative due to the spatial, spectral and temporal resolution are different. The method of image fusion can integrate an image with rich details and valuable information from multi-source remote sensing images, which aim to obtain more comprehensive and precise observations of the ground object. By using aspects from multi-source image fusion, this review presents the current status and future trends in remote sensing image fusion. First, different image properties and their applications are presented for remote sensing datasets at home and abroad. Second, a general summary and inductive analysis of the challenging difficulty of different types of multisource image fusion methods is conducted. Third, experiments are tested on eight different methodological approaches, and experimental results demonstrate that GSA method is the best alternative in terms of obtaining high spatial resolution and retaining the spectral information.

Performance enhancement of BLDC motor using PID controller

Mainly the DC motors are employed in most of the application. The main objective is to Regulate the DC motor system. A motor which displays the appearances of a DC motor but there is no commutator and brushes is called as brushless DC motor. These motors are widespread to their compensations than other motors in relationships of dependability, sound, efficiency, preliminary torque and longevity. To achieve the operation more reliable and less noisy, brushless dc motors are employed. In the proposed work, dissimilar methods of speed control are analysed. In real time submission of speed control of BLDC motor, numerous strategies are executed for the speed control singularity. The modified approaches are the employment of PI controller, use of PID controller and proposed current controller.

A predictive equation for residual strength using a hybrid of subset selection of maximum dissimilarity method with Pareto optimal multi-gene genetic programming

More accurate and reliable estimation of residual strength friction angle (ϕr) of clay is crucial in many geotechnical engineering applications, including riverbank stability analysis, design, and assessment of earthen dam slope stabilities. However, a general predictive equation for ϕr, with applicability in a wide range of effective parameters, remains an important research gap. The goal of this study is to develop a more accurate equation for ϕr using the Pareto Optimal Multi-gene Genetic Programming (POMGGP) approach by evaluating a comprehensive dataset of 290 experiments compiled from published literature databases worldwide. A new framework for integrated equation derivation proposed that hybridizes the Subset Selection of Maximum Dissimilarity Method (SSMD) with Multi-gene Genetic Programming (MGP) and Pareto-optimality (PO) to find an accurate equation for ϕr with wide range applicability. The final predictive equation resulted from POMGGP modeling was assessed in comparison with some previously published machine learning-based equations using statistical error analysis criteria, Taylor diagram, revised discrepancy ratio (RDR), and scatter plots. Base on the results, the POMGGP has the lowest uncertainty with U95 = 2.25, when compared with Artificial Neural Network (ANN) (U95 = 2.3), Bayesian Regularization Neural Network (BRNN) (U95 = 2.94), Levenberg-Marquardt Neural Network (LMNN) (U95 = 3.3), and Differential Evolution Neural Network (DENN) (U95 = 2.37). The more reliable results in estimation of ϕr derived by POMGGP with reliability 59.3%, and resiliency 60% in comparison with ANN (reliability = 30.23%, resiliency = 28.33%), BRNN (reliability = 10.47%, resiliency = 10.39%), LMNN (reliability = 19.77%, resiliency = 20.29%) and DENN (reliability = 27.91%, resiliency = 24.19%). Besides the simplicity and ease of application of the new POMGGP equation to a broad range of conditions, using the uncertainty, reliability, and resilience analysis confirmed that the derived equation for ϕr significantly outperformed other existing machine learning methods, including the ANN, BRNN, LMNN, and DENN equations.

Molecular Docking and Three‐Dimensional Quantitative Structure–Activity Relationships for Antitubercular Pyrimidine Derivatives

Enoyl Acyl Carrier Protein (ACP) Reductase, a key enzyme, which catalyzes the last reductive step of fatty acid biosynthesis and it, is one of the key enzymes for the development of antitubercular agents. In this pursuit, molecular docking and 3D-QSAR studies (CoMFA and CoMSIA) have been performed on a series of pyrimidine derivatives (29 compounds) to understand the binding sites, interactions to improve over the existing leads in terms of improved biological and physico-chemical properties. Molecular docking was performed on a protein InhA (T2A mutant) (PDB ID: 5OIR) using the Surflex-Dock suite available in SYBYL-X 2.1.1 (Tripose Inc., USA). In addition, 3D-QSAR studies have been performed to validate the models using the data set, which was segregated into training and test set by using the Diversity and Dissimilarity method. Structural features required for the prediction of better inhibitory potency was generated in the form of contour maps from the CoMFA and CoMSIA models (Steric, Electrostatic, Hydrophobicity, H-bond donor and acceptor maps) and predicted values for r2 = 0.966, q2 = 0.22 for the CoMFA model and r2 = 0.925, q2 = 0.576 for the CoMSIA model. From this study, it is observed that interaction with amino acid residues TYR158, MET199, MET161, GLY96, and PHE97 are important for the activity that helped to predict SARs by providing important structural features. Both the models were good in understanding the specific activity of some of the compounds that will facilitate to develop new types of Enoyl ACP reductase inhibitors.

Favorable asymptotic solutions of the Graetz problem employing two dissimilar methods, each method engages three eigenvalues: Vestiges of history

The present study focuses on the determination of an asymptotic Graetz series for the demanding upstream sub-region of the Graetz problem where the Graetz series converges slowly. The Method Of Lines (MOL) is the computational procedure that transforms the descriptive two–dimensional energy equation in the axial and radial variables into an allied system of ordinary differential equations of first order in the axial variable. An allied system of ordinary differential equations of first order having three equations is deduced and solved analytically with the robust eigenvalue method of linear algebra theory. The strategy to follow revolves around the level of difficulty in the determination of the eigenquantities with MOL as compared to the level of difficulty confronted by Nusselt and Jakob in the past. From a qualitative perspective, the obtained three-term MOL series representative of the asymptotic mean bulk temperature in the sub-region near the origin exhibits good convergence patterns. The three-term MOL series supplements the truncated three-term Graetz series depictive of the asymptotic mean bulk temperature in the downstream sub-region far from the origin.

Efficiency of Probabilistic Network Model for Assessment in E-Learning System

The knowledge acquirement by the learner is a major assignment of an E-Learning framework. Evaluation is required in order to adapt knowledge resources and task to learner ability. Assessment provides learner’s an approach to evaluate the skills gained through the e-learning domain they are accessing. A dissimilar method can be used to assess the information acquirement, such as probabilistic Bayesian Network model. A Bayesian Network is a graphical representation of the probabilistic relationships of a complex system. This network can be used for reasoning with uncertainty. Bayesian Network is the most challenging task in e-learning system as learner evaluation model are an element of uncertainty. In this paper the current proposed scheme is constructed on Bayesian Network to deduce the stage of knowledge possessed by the learner. It also proposes type of assessment to identify the knowledge whatever the learner identifies. Throughout the assessment, it can be performed by two approaches namely Sequential and Random. In Sequential approach, questions can be displayed on the learner machine in sequential order. In Random approach, questions can be displayed on the learner machine in random order. However, both have their inherent limitations. Questions that are considered to be answered easily by the learner may also be presented to the learner who is not desirable. This system determined on the illustration of Bayesian Network model and algorithm for inference about learner’s knowledge. The Bayesian Network model was efficiently implemented for three levels of learner called Higher Learners (HL), Regular Learners (RL) and Irregular Learners (IL) for learner’s assessment and was successfully implemented with 81.1% of probabilities for learner’s assessment.