Anubha Dubey - Academia.edu (original) (raw)

Papers by Anubha Dubey

Deleted Journal, 2020

Machine learning makes the machines learn from provided data and with the help of its algorithms ... more Machine learning makes the machines learn from provided data and with the help of its algorithms it predicts and analyzes the data. This makes the machines artificially intelligent. These techniques spread its wings in all the areas of healthcare whether it is the diagnosis, treatment etc. Here a brief overview of all the areas where machine learning / artificial intelligence techniques can be applied.

A honey pot is a technique of cloud computing that is proposed for capturing hackers or tracking ... more A honey pot is a technique of cloud computing that is proposed for capturing hackers or tracking unusual methods of attack. This technique will seize, recognize and duplicate the hacker behavior. It works in Cloud environment where anything like technology, tool, and result can be offered as a service. Purveyors offer and deliver such services to their customers via the network. Production honeypot is one of the types of honeypot which is used to solve the problem of data security in organizations. Honeypot techniques are used to detains the actions of intruder and create a log-file for providing better security in to the cloud network. Kerberos is a protocol for validating the services which requests between true hosts across the network, such as the internet. Kerberos builds on symmetric key cryptography and needed trusted third party, Key Distribution Centre(KDC) which uses public key cryptography. This paper presents the concept of production and research Honeypot as a service in cloud environment by implementing the benefits of Kerberos Authentication system, which distinguishes between hackers and users, and to provide overall security to the data/network.

International journal of bioinformatics research, Dec 30, 2011

MicroRNAs (miRNA's) constitute a large family of non coding RNAs that function to regulate gene e... more MicroRNAs (miRNA's) constitute a large family of non coding RNAs that function to regulate gene expression. Wet lab experiments usually used to classify the miRNA of plants and animals are highly expensive, labor intensive and time consuming. Thus there arises a need for computational approach for classification of plant and animal miRNA. These computational approaches are fast and economical as compared to wet lab techniques. Here a machine learning approach is used to classify miRNA of HIV, plants and animals. The new SVM learning algorithm called Weka LibSVM has been used for classification of plant and animal and HIVmiRNA. The model has been tested on available data and it gives results with 95% accuracy.

Elsevier eBooks, 2023

Big data, it's a trend in every company whether it is the healthcare or the IT industry. ... more Big data, it's a trend in every company whether it is the healthcare or the IT industry. A huge amount of data is generated everywhere which needs to be managed properly. These managed data are important for interpretation and analysis in the future. These will enhance the new computational techniques to work on big "V"s that is volume, velocity, veracity, variety, and value. In healthcare too, lots of data are generated which is stored in electronic form. The evolution of data on daily basis requires proper handling and management. As big data to knowledge is the latest demand (Margolis et al., 2014). The term big data is introduced in 1997 (Cox & Ellsworth, 1997) by John R. Mashey. And is a big challenge in biomedical research. All the big databases like international cancer genome consortium, some disease databases like international rare disease consortium, and the international human epigenome consortium, are the ones that are part of data resources. These analytics require capabilities for the representation and modeling of the health data, optimization of different algorithms, and computational power. In the healthcare industry, five distinctive capabilities of data are required: identification of patterns in data that provides care, analysis of unstructured data, providing decision support, better prediction, and traceability (Wang, Kung, & Byrd, 2018). Data generation and collection are faster than data preprocessing and analysis. To cover this gap there is a need for technological progress in various kinds of data acquisition. All this information generated and fed to computers is of utmost importance whether it is molecular information, phenotypic information of an individual patient, or others. These biomedical data need protection, storage capacity, etc. Hence cloud computing techniques come into existence. The cloud computing (CC) standard has engrossed a lot of attraction from both industry and scholars. It proposes diverse services including asset pooling, multi-tenancy, and flexibility (Chkirbene et al., 2020). While the cloud computing standard raises economic efficiency, security is one of the important concerns in adopting the cloud computing model (Chkirbene, Erbad, & Hamila, 2019). Cloud computing is a new operating technology that advanced the information technology (IT) industry, it is an expansion of equivalent computing, distributed computing, and grid computing over the same or different networks, (Sniezynski, Nawrocki, & Wilk, 2019). Cloud computing technology is the combination and development of virtualization, utility computing, and all the

Objectives: The objective of this cross sectional study is to evaluate the probability of finding... more Objectives: The objective of this cross sectional study is to evaluate the probability of finding healthy control subjects according to the results of multiple lab tests in multiple domains including biochemical hematological and immunological measurements. Material and methods: During the period March-June 2016 a sample of 217 apparently healthy Iraqi adults were investigated whether or not they satisfactorily meet the criteria accomplishing the reality of being healthy. Blood specimens were collected from each participant using standard procedures. The following measurements and tests were carried out for all studied participants: anthropometric measurements, complete blood picture test, enzymatic colorimetric assay for serum lipid profile, glucose, urea, creatinine, alanine transferase, and Enzyme Linked Immunosorbent Assay (ELISA) for serum high sensitive C reactive protein and interleukin 1 beta. Results: The prevalence rates (PR) of apparently healthy individuals (AHI) were in descending order of wellness requirements as follow: in those with a completely normal lipid profile it was 25.3%, for biochemistry domain 31.3%, for white blood cell count domain 57.2%, for red blood cell count (RBC) domain 11.5% and for platelets domain tests it was 31.3%. A completely normal hematologic domain tests was found in only 8.8% of tested individuals, while for immunologic domain 9.2%. The probability of finding a normal control subject based on multiple testing domains was as low as 13.4%. Conclusions: Avery considerable proportion of population who appear to be healthy, are not in reality, accordingly not all apparently healthy controls are qualified as eligible control. The really healthy control subject is of low probability (13.4%) among Iraqi apparently healthy adults. The WBC domain ranked at the top of restriction normality pyramid, followed by biochemistry, lipid profile, RBC domain and immunological domain respectively.

Open Access Journal of Pharmaceutical Research

The diversity of data leads to volume, velocity, variety, variability and value, the "V"s of big ... more The diversity of data leads to volume, velocity, variety, variability and value, the "V"s of big data worldwide known. And these are the challenges for biomedical and data scientists to bring proper information out of them. Day by day a protein is isolated and biological databases are enhanced. The biological databases like Genbank, PDB etc are growing in a fast way. Not only protein, DNA, RNA database are enriched but also disease databases like eBioportal for cancer genomics [1] is widely used resource that integrates and visualizes cancer genomic data, including mutations, copy number variation, gene expression and clinical trial information. These are the first generation databases having complete information of particular nucleic acids, gene, and disease. Now as researches in bioinformatics are speeds up, our understanding of life and diseases are also achieving heights. With this we have second generation system cloud computing with biomedical data which enables researches of the world to compute over the data. BLAST Basic local Alignment search tool of NCBI is its very good example.

Digital Health Transformation with Blockchain and Artificial Intelligence

Cloud computing an emerging technology provides various services to the users like infrastructure... more Cloud computing an emerging technology provides various services to the users like infrastructure, hardware, software, storage etc. So, it is necessary that cloud computing network should always free from attack. Various strict security checking systems are used for making network bugs free and honey pot is among one of the tool that is used to provide security. Various models are proposed for honey pot to solve the problem of industries and that is used to captures the activities of attackers and maintains a log for providing better security to the cloud network. Here in this paper we proposed an algorithm to resolve some of the issues of network security.

Dr. Anubha Dubey, Machine learning models for evaluation of domain based classification of AIDS H... more Dr. Anubha Dubey, Machine learning models for evaluation of domain based classification of AIDS HIV-1 groups, Onl J Bioinform 18(2):53-57, 2017. HIV-1 evolves through rapid accumulation of mutations and recombination which actively contribute to its genetic diversity producing many groups, types and subtypes, this is similar to protein domain sequences and structures that evolve function and exist independently from the rest of the protein chain. Each domain forms a compact 3D structure which is independently stable and folded. One protein may appear in a variety of evolutionarily related proteins. Software and methods such as SVM, HMM and Neural Networks for prediction of domains generate different results and accuracy for the same input. A machine learning model for classifying HIV 1 M, N, O group domains is described. The HIV-1 domain based classification model was developed using Uniprot database as input for SBASE, SMART, NCBI Conserved Domain, Scan Prosite and Phylodome with J48, Bayes Net, Naive Bayes and Bagging algorithms. Results showed that SBASE predicted 98.59% and other programs 95.07-97.18% domains.

HIV infected patients who are on Anti-retroviral Therapy, their gut micro biome is very different... more HIV infected patients who are on Anti-retroviral Therapy, their gut micro biome is very different from those of healthy individuals. In HIV infected persons dysbiosis may lead to a breakdown in the guts immunologic activity, causing systemic bacteria diffusion and inflammation. But the use of probiotics for health improvement in HIV infection leads to long life expectancy. This mini review will focus on the importance of probiotics to prevent and attenuate several gastrointestinal manifestations and improve Gut associated lymphoid tissue (GALT) immunity in HIV infection.

Bioscience Biotechnology Research Communications, 2018

All over the world the scientists working in biophotons and biophotonic therapy gave the hope to ... more All over the world the scientists working in biophotons and biophotonic therapy gave the hope to those who have struggled with a disease that have not been treated. This method is inexpensive and shows no side effects prove better in diagnosis and treatment such as HIV transmission. Some biomedical techniques of HIV detection need photons as source of light. These results have been obtained by CCD cameras or highly modifi ed digital systems. The noisy background in these pictures gave the idea of implementing machine learning models. They can be extremely fast, offer high degree of picture quality and differentiation or classifi cation of molecules of interest. In this paper libSVM (Support Vector Machines) models are applied to classify CD4+ cells from whole blood cells with great accuracy.

International Journal of Molecular Biology, 2018

Due to the complexity of HIV/AIDS cutting edge machine learning technologies are used for drug de... more Due to the complexity of HIV/AIDS cutting edge machine learning technologies are used for drug delivery and development. In this review drug delivery methods are discussed with machine learning techniques. Combination of both these computational methods will give new hope to enhance the life of HIV infected persons. As these methods are time consuming and easy to interpret than wet lab techniques.

Computational Molecular Biology, 2016

In the last few years there is a remarkable progress of research in machine learning. This field ... more In the last few years there is a remarkable progress of research in machine learning. This field has gained an unprecedented popularity, several new areas have developed and some are gaining new momentum. Machine learning is useful in cases where algorithmic solutions are not available i.e. there is lack of formal models or the knowledge about the application domain is poorly defined. The fact that various scientific communities are involved in machine learning research led this scientific field to incorporate ideas from different areas, such as computational learning theory, artificial neural networks, statistics, stochastic modelling, genetic algorithms and pattern recognition. The domain of machine learning has gained immense popularity in HIV diagnosis, screening, treatment and nowadays for designing & production of vaccines for cure of HIV. In this review article it is summarized the progression of machine learning techniques in HIV-AIDS.

International Journal of Scientific Research in Knowledge, 2014

The introduction of disulphide bonds into proteins is an important mechanism by which they have e... more The introduction of disulphide bonds into proteins is an important mechanism by which they have evolved and are evolving. Most protein disulphide bonds are motifs that stabilize the tertiary and quaternary protein structure. These bonds also thought to assist protein folding by decreasing the entropy of the unfolded form. Amino acid cysteine plays a fundamental role in formation of disulphide bonds. In the present study, proteomics of disulphide bonding in HIV is studied through a machine learning model which has been developed to classify disulphide bonds from different species of lentiviruses like bovine immunodeficiency virus (BIV), simian immunodeficiency virus (SIV), Feline immunodeficiency virus, murine infectious virus (MIV) and equine infectious anaemia virus (EIV) and Human immunodeficiency virus (HIV). Phylogenetic relationship is also studied by the prediction of disulphide bonding among these viruses. Hence by different algorithms of WEKA classifier J48 predicts better classification with an accuracy of 89.6104%.

Protein (or in general, proteome) Analysis Subcellular Localization Prediction is a process (usua... more Protein (or in general, proteome) Analysis Subcellular Localization Prediction is a process (usually through the use of web-based software) of predicting the location or destination of a protein within the cell using only the protein sequence as its inputs. Proteins are then likened to letters with proper address and stamps to deliver it on the proper destination. Since the proteins should have proper address to ensure its delivery to the proper localization. The destination of various protein sequences is predicted by the subcellular localization prediction servers. Hence a machine learning simulation model is developed to predict and classify HIV apoptosis proteins subcellular localization sites by their amino acid composition. Of the various predictions software's used Eukaryotic Mploc predicts better results mitochondria with accuracy of 99.1304%, Subloc shows better results with mitochondria with accuracy of 90%, and Virus Ploc shows better results with extracellular space with accuracy of 98.889%.

2009 International Conference on Advances in Computing, Control, and Telecommunication Technologies, 2009

MicroRNAs (miRNAs) constitute a large family of non coding RNAs that function to regulate gene ex... more MicroRNAs (miRNAs) constitute a large family of non coding RNAs that function to regulate gene expression. Wet lab experiments usually used to classify the miRNA of plants and animals are highly expensive, labor intensive and time consuming. Thus there arises a need for computational approach for classification of plant and animal miRNA. These computational approaches are fast and economical as

A honey pot is a technique of cloud computing that is proposed for capturing hackers or tracking ... more A honey pot is a technique of cloud computing that is proposed for capturing hackers or tracking unusual methods of attack. This technique will seize, recognize and duplicate the hacker behavior. It works in Cloud environment where anything like technology, tool, and result can be offered as a service. Purveyors offer and deliver such services to their customers via the network. Production honeypot is one of the types of honeypot which is used to solve the problem of data security in organizations. Honeypot techniques are used to detains the actions of intruder and create a log-file for providing better security in to the cloud network. Kerberos is a protocol for validating the services which requests between true hosts across the network, such as the internet. Kerberos builds on symmetric key cryptography and needed trusted third party, Key Distribution Centre (KDC) which uses public key cryptography. This paper presents the concept of production and research Honeypot as a service ...

Deleted Journal, 2020

International journal of bioinformatics research, Dec 30, 2011

Elsevier eBooks, 2023

Open Access Journal of Pharmaceutical Research

Digital Health Transformation with Blockchain and Artificial Intelligence

Bioscience Biotechnology Research Communications, 2018

International Journal of Molecular Biology, 2018

Computational Molecular Biology, 2016

International Journal of Scientific Research in Knowledge, 2014

2009 International Conference on Advances in Computing, Control, and Telecommunication Technologies, 2009

A honey pot is a technique of cloud computing that is proposed for capturing hackers or tracking ... more A honey pot is a technique of cloud computing that is proposed for capturing hackers or tracking unusual methods of attack. This technique will seize, recognize and duplicate the hacker behavior. It works in Cloud environment where anything like technology, tool, and result can be offered as a service. Purveyors offer and deliver such services to their customers via the network. Production honeypot is one of the types of honeypot which is used to solve the problem of data security in organizations. Honeypot techniques are used to detains the actions of intruder and create a log-file for providing better security in to the cloud network. Kerberos is a protocol for validating the services which requests between true hosts across the network, such as the internet. Kerberos builds on symmetric key cryptography and needed trusted third party, Key Distribution Centre (KDC) which uses public key cryptography. This paper presents the concept of production and research Honeypot as a service ...

KERBEROS AUTHENTICATION MODEL FOR DATA SECURITY IN CLOUD COMPUTING USING HONEY-POT, 2019

Journal of Clinical Genomics, 2018

ELSVIER, 2022

Big data, it's a trend in every company whether it is the healthcare or the IT industry. A huge a... more Big data, it's a trend in every company whether it is the healthcare or the IT industry. A huge amount of data is generated everywhere which needs to be managed properly. These managed data are important for interpretation and analysis in the future. These will enhance the new computational techniques to work on big "V"s that is volume, velocity, veracity, variety, and value. In healthcare too, lots of data are generated which is stored in electronic form. The evolution of data on daily basis requires proper handling and management. As big data to knowledge is the latest demand (Margolis et al., 2014). The term big data is introduced in 1997 (Cox & Ellsworth, 1997) by John R. Mashey. And is a big challenge in biomedical research. All the big databases like international cancer genome consortium, some disease databases like international rare disease consortium, and the international human epigenome consortium, are the ones that are part of data resources. These analytics require capabilities for the representation and modeling of the health data, optimization of different algorithms, and computational power. In the healthcare industry, five distinctive capabilities of data are required: identification of patterns in data that provides care, analysis of unstructured data, providing decision support, better prediction, and traceability (Wang, Kung, & Byrd, 2018). Data generation and collection are faster than data preprocessing and analysis. To cover this gap there is a need for technological progress in various kinds of data acquisition. All this information generated and fed to computers is of utmost importance whether it is molecular information, phenotypic information of an individual patient, or others. These biomedical data need protection, storage capacity, etc. Hence cloud computing techniques come into existence. The cloud computing (CC) standard has engrossed a lot of attraction from both industry and scholars. It proposes diverse services including asset pooling, multi-tenancy, and flexibility (Chkirbene et al., 2020). While the cloud computing standard raises economic efficiency, security is one of the important concerns in adopting the cloud computing model (Chkirbene, Erbad, & Hamila, 2019). Cloud computing is a new operating technology that advanced the information technology (IT) industry, it is an expansion of equivalent computing, distributed computing, and grid computing over the same or different networks, (Sniezynski, Nawrocki, & Wilk, 2019). Cloud computing technology is the combination and development of virtualization, utility computing, and all the