Md. Sarwar Kamal

Students dropout prediction for intelligent system from tertiary level in developing country

Students dropout prediction is an indispensable for numerous intelligent systems to measure the national and international loss for developing countries as well as for developed country throughout the world. The main purpose of this research is to develop a dynamic dropout prediction model for universities, institutes and colleges. In this work, We first apply chi square test to separate factors such as gender, financial condition and dropping year to classify the successful from unsuccessful students. The main purpose of applying it is feature selection to data. Degree of freedom is used to P-value (Probability value) for best predicators of dependent variable. After being separation of factors we have had examined by using data mining techniques Classification and Regression Tree (CART) and CHAID tree. Among classification tree, growing methods Classification and Regression Tree (CART) was the most successful in growing the tree with an overall percentage of correct classification than CHAID tree. A maximum tree depth has been reached: 3 levels for the CHAID tree and 4 levels for the CART tree. After generating, the classification matrix rules for CART and CHAID tree (Study outcome) have generated. Both the risk estimated by the cross-validation and the gain diagram suggests that all trees based only enrolment data are not quite good in separating successful from unsuccessful students. Here we have considered most important factors to classify the successful students over unsuccessful students are gender, financial condition and dropping year as well as age, gender, ethnicity, education, work status, and disability and study environment that may in-flounce persistence or dropout of students at university level.

StrucBreak: A Computational Framework for Structural Break Detection in DNA Sequences

Damages or breaks in DNA may change the characteristics of genomes and causes various diseases. In this work we construct a system that incorporates the maximum likelihood-based probabilistic formula to assess the number of damages that have occurred in any DNA sequence. This approach has been progressively benchmarked by implementing simulated data sets so that the outcomes can be compared with a ground truth or reference value. At first the sequence data set order is checked through the statistical cumulative sum (STACUMSUM). The verified sequences are then estimated by prior and posterior probability to count the percentages of breaks and mutations. Maximum-likelihood estimation then finds out the exact numbers and positions of breaks and detections. In database manipulation, one factor that decides the orientation and order of the sequence is geometric distance between consecutive sequences. The geometric distance is measured for smooth representation of the genome or DNA sequences. Finally, we compared the performance of our system with DAMBE5: (A Comprehensive Software Package for Data Analysis in Molecular Biology and Evaluation), and in response to time and space complexity, StrucBreak is much faster and consumes much less space due to our algorithmic approaches.

ExSep: An exon separation process using Neural Skyline Filter

Exons and Introns are complimentary parts of DNA and RNA. Due to excessive data set in biological science, it is sometimes very expensive and costly to extract meaningful information from such data set. To accelerate efficient and faster exons separation an automated system designed under Neural Skyline Filter(NeuralSF) and Bloom filter. This development allows the comparative analysis on performances among NeuralSF, Bloom Filter and processing without filter. The outcome of the experiments and simulations shows that NeuralSF outperforms other processes in both the cases as number of exons finding and timing. This system may help to reduce the redundant data set from large number of collections. Apart from that it will enable to handle big biological data.

Next generation sequencing under de novo genome assembly

The next generation sequencing (NGS) is an important process which assures inexpensive organization of vast size of raw sequence dataset over any traditional sequencing systems or methods. Various aspects of NGS such as template preparation, sequencing imaging and genome alignment and assembly outline the genome sequencing and alignment. Consequently, de Bruijn graph (dBG) is an important mathematical tool that graphically analyzes how the orientations are constructed in groups of nucleotides. Basically, dBG describes the formation of the genome segments in circular iterative fashions. Some pivotal dBG-based de novo algorithms and software packages such as T-IDBA, Oases, IDBA-tran, Euler, Velvet, ABySS, AllPaths, SOAPde novo and SOAPde novo2 are illustrated in this paper. Consequently, overlap layout consensus (OLC) graph-based algorithms also play vital role in NGS assembly. Some important OLC-based algorithms such as MIRA3, CABOG, Newbler, Edena, Mosaik and SHORTY are portrayed in this paper. It has been experimented that greedy graph-based algorithms and software packages are also vital for proper genome dataset assembly. A few algorithms named SSAKE, SHARCGS and VCAKE help to perform proper genome sequencing.

Chapman–Kolmogorov equations for global PPIs with Discriminant-EM

Ongoing improvements in Computational Biology research have generated massive amounts of Protein–Protein Interactions (PPIs) dataset. In this regard, the availability of PPI data for several organisms provoke the discovery of computational methods for measurements, analysis, modeling, comparisons, clustering and alignments of biological data networks. Nevertheless, fixed network comparison is computationally stubborn and as a result several methods have been used instead. We illustrate a probabilistic approach among proteins nodes that are part of various networks by using Chapman–Kolmogorov (CK) formula. We have compared CK formula with semi-Markov random method, SMETANA. We significantly noticed that CK outperforms the SMETANA in all respects such as efficiency, speed, space and complexity. We have modified the SMETANA source codes available in MATLAB in the light of CK formula. Discriminant-Expectation Maximization (D-EM) accesses the parameters of a protein network datasets and determines a linear transformation to simplify the assumption of probabilistic format of data distributions and find good features dynamically. Our implementation finds that D-EM has a satisfactory performance in protein network alignment applications.

Efficient low cost supervisory system for Internet of Things enabled smart home

Internet of Things (IoT) is a hot and debated subject in current digitalized era. IoT enables internet connectivity for all kinds of devices and physical objects. The current world is approaching towards virtualization of different types of systems that enables performing activities without direct physical interaction. The combination of high-speed internet and intelligent devices makes it easier to manage multiple jobs smoothly without the limitation of distances. The outstanding advantages of these promising technologies require the deployment and utilization of proper methods to handle the difficulties arise with these new applications. in the real world. This paper propose an efficient low cost supervisory system for smart home automation that can be managed using IoT. The proposed system is based on Apriori algorithm and will help to monitor and control all the home appliances and electronic devices through a supervisory system in a most efficient and reliable manner. Both the consumers and the suppliers will get the opportunity to manage the power distribution by monitoring the electricity consumption.

Neural Skyline Filtering for Imbalance Features Classification

In the current digitalized era, large datasets play a vital role in features extractions, information processing, knowledge mining and management. Sometimes, existing mining approaches are not suff...

Large Scale Medical Data Mining for Accurate Diagnosis: A Blueprint

Medical care and machine learning are associated together in the current era. For example, machine learning (ML) techniques support the medical diagnosis process/decision making on large scale of diseases. Advanced data mining techniques in diseases information processing context become essential. The present study covered several aspects of large scale knowledge mining for medical and diseases investigation. A genome-wide association study was reported including the interactions and relationships for the Alzheimer disease (AD). In addition, bioinformatics pipeline techniques were implied for matching genetic variations. Moreover, a novel ML approaches to construct a framework for large scale gene-gene interactions were addressed. Particle swam optimization (PSO) based cancer cytology is another discussed pivotal field. An assembly ML Random forest algorithm was mentioned as it was carried out to classify the features that are responsible for Bacterial vaginosis (BV) in vagina microbiome. Karhunen-Loeve transformation assures features finding from various level of ChIP-seq genome dataset. In the current work, some significant comparisons were conducted based on several ML techniques used for diagnosis medical datasets.

Generation of UNL Attributes and Resolving Relations for Bangla EnConverter

ConversionofBanglalanguagetoanothernativelanguageandanotherlanguageto BanglalanguageusingUniversalNetworkingLanguage(UNL)ishighlydemanding due to rapidly increasing the usage of Internet-based applications. UNL has been usedbyvariousresearchersasaninter-lingualapproachforanAutomatedMachine Translation (AMT) scheme. This article presents a novel work on construction of EnConverterforBanglalanguagewithaspecialfocusongenerationofUNLattributes and resolving relations of Bangla text. The architecture of Bangla EnConverter, algorithmsforunderstandingtheBanglainputsentence;resolutionofUNLrelations; andattributesforBanglatext/languagearealsoexplainedinthisarticle.Thisarticle highlights the analysis rules forEnConverter and indicates its usage ingeneration ofUNLexpressions.Thisarticlepresents the resultsof implementationofBangla EnConverterandcompares thesewith thesystemavailableatRussianandEnglish LanguageServer. KEywoRdS Analysis Rule, Bangla Language Text, EnConverter, Machine Translation, Morphological Analysis, Universal Networking Language (UNL), Universal Words

New Dropout Prediction for Intelligent System

The main purpose of this research is to develop a dynamic dropout prediction model for universities, institutes and colleges. In this work, we first identify dependent and independent variables and dropping year to classify the successful from unsuccessful students. Then we have classify the data using Support Vector Machines(SVM). SVM helped the data set to be properly design and manipulated . The main purpose of applying this identification is to design a Knowledge Base which is sometimes known as joint probability distribution . The concepts of propositional logic helped to build the knowledge Base. Bayes theorem will perform the prediction by collecting the information from knowledge Base. Here we have considered most important factors to classify the successful students over unsuccessful students are gender, financial condition and dropping year. We also consider the socio-demographic variables such as age, gender, ethnicity, education, work status, and disability and study environment that may in-flounce persistence or dropout of students at university level