Sudip Mandal - Academia.edu (original) (raw)

Papers by Sudip Mandal

Computer Science & Information Technology ( CS & IT ), 2013

vol. 3(1), 2017

Simulation is a discipline of modeling some real life problem or theoretical concept and observin... more Simulation is a discipline of modeling some real life problem or theoretical concept and observing corresponding output in artificial or synthetic environment e.g. computers. Simulation has great importance in the field of application of Electronics engineering where electronic engineers or students can check their models or their models or theory before applying for development practically. In this article, I mainly emphasize some important simulation software tools in the field of electronics and communication engineering. These tools are widely used for numerical simulations and applications. From this article, students will familiarize about these simulation software tools so that they can apply these tools in their own problems and also carry out research work for further development or modifications of these software tools.

Automated age estimation is an important processing task that serves many purposes such as survei... more Automated age estimation is an important processing task that serves many purposes such as surveillance monitoring, marketing of products, authentication systems, find out the fugitive or missing person and security control etc. Therefore, estimating age from still face images by using facial features is trending research topic from past few years. An automated age group prediction system using wrinkle features of facial images and neural network is proposed in this paper. Three age groups including child, young, and old, are considered in the classification system. The prediction process is divided into three phases: image accumulation from different website, wrinkles feature extraction using image processing technique, and age classification using Neural Network. Different facial images of different age groups are collected from several websites. The wrinkles features are extracted from each image using image processing techniques and make a corresponding database. Finally, an Artificial Neural Network (ANN) is constructed for classification of new images which will use the wrinkle features as inputs to classify the image into one of three age groups. Using this process, we can predict the age group of a face of a person with satisfactory accuracy.

The correct inference of gene regulatory networks (GRN) remains as a fascinating task for researc... more The correct inference of gene regulatory networks (GRN) remains as a fascinating task for researchers to understand the detailed process of complex biological regulations and functions. With availability of large dimensional microarray data, relationships among thousands of genes can be extracted simultaneously that is a reverse engineering problem. Among the different popular models to infer GRN, Recurrent Neural Networks (RNN) are considered as most popular and promising mathematical tool to model the dynamics of, as well as to infer the correct dependencies among genes from, biological data like time series microarray. RNN is closed loop Neural Network with a delay feedback. By observing the weights of RNN model, it is possible to extract the regulations among genes. Several metaheuristics or optimization techniques were already proposed to search the optimal value of RNN model parameters. In this review, we illustrate different problems regarding reverse engineering of GRN and how different proposed models can overcome these problems. It is observed that finding out the most suitable and efficient optimization techniques for the accurate inference of small artificial, large artificial, Dream4 Network, and real world GRNs with less computational complexity are still an open research problem to all.

We have proposed a methodology for the reverse engineering of biologically plausible gene regulat... more We have proposed a methodology for the reverse engineering of biologically plausible gene regulatory networks from temporal genetic expression data. We have used established information and the fundamental mathematical theory for this purpose. We have employed the Recurrent Neural Network formalism to extract the underlying dynamics present in the time series expression data accurately. We have introduced a new hybrid swarm intelligence framework for the accurate training of the model parameters. The proposed methodology has been first applied to a small artificial network, and the results obtained suggest that it can produce the best results available in the contemporary literature, to the best of our knowledge. Subsequently, we have implemented our proposed framework on experimental (in vivo) datasets. Finally, we have investigated two medium sized genetic networks (in silico) extracted from GeneNetWeaver, to understand how the proposed algorithm scales up with network size. Additionally, we have implemented our proposed algorithm with half the number of time points. The results indicate that a reduction of 50% in the number of time points does not have an effect on the accuracy of the proposed methodology significantly, with a maximum of just over 15% deterioration in the worst case.

The accurate prediction of genetic networks using computational tools is one of the greatest chal... more The accurate prediction of genetic networks using computational tools is one of the greatest challenges in the postgenomic era. Recurrent Neural Network is one of the most popular but simple approaches to model the network dynamics from time-series microarray data. To date, it has been successfully applied to computationally derive small-scale artificial and real-world genetic networks with high accuracy. However, they underperformed for large-scale genetic networks. Here, a new methodology has been proposed where a hybrid Cuckoo Search-Flower Pollination Algorithm has been implemented with Recurrent Neural Network. Cuckoo Search is used to search the best combination of regulators. Moreover, Flower Pollination Algorithm is applied to optimize the model parameters of the Recurrent Neural Network formalism. Initially, the proposed method is tested on a benchmark large-scale artificial network for both noiseless and noisy data. The results obtained show that the proposed methodology is capable of increasing the inference of correct regulations and decreasing false regulations to a high degree. Secondly, the proposed methodology has been validated against the real-world dataset of the DNA SOS repair network of Escherichia coli. However, the proposed method sacrifices computational time complexity in both cases due to the hybrid optimization process.

An exact algorithm for microwave tomography of biological body using multiview observations has b... more An exact algorithm for microwave tomography of biological body using multiview observations has been proposed here. The result of applying the algorithm on a small scale biological normal model and diseased model having simplified data collecting arrangement from all sides operating at 1GHz frequency have been extremely encouraging and indicate the possibility for achieving a high resolution microwave imaging system which is also a non invasive technique. The contrast in the reconstructed diseased model is a bit poor mainly due to 1) small object size 2) the averaging effect in computation of complex permittivity for a large number of adjacent cells. It is expected to realize a better result when a significantly large observation region well immersed in saline water for better impedance matching and less beam shape distortion due to boundary reflection at the edges is considered.

Proceedings of the 2015 Third International Conference on Computer, Communication, Control and Information Technology (C3IT), 2015

ABSTRACT Gene Regulatory Networks (GRN) is used to model the regulations in living organisms. Inf... more ABSTRACT Gene Regulatory Networks (GRN) is used to model the regulations in living organisms. Inferring genetic network from different experimental high throughput biological data (like microarray) is a challenging job for all researchers. In this paper, Artificial Neural Network, which is a very effective soft computing tool to learn and model the dynamics or dependencies between genes, is used for reconstruction of small scale GRN from the reduced microarray dataset of Lung Adenocarcinoma. The significance of regulations of one gene to other genes of the system are expressed by a weight matrix which is computed using Perceptron based biologically significant weight updating method by minimizing the error during learning. Based on the values of elements of filtered weight matrix, a directed weighted graph can be drawn successfully that denotes gene regulatory network.

Proceedings of the 2015 Third International Conference on Computer, Communication, Control and Information Technology (C3IT), 2015

ABSTRACT The correct inference of gene regulatory network plays a critical role in understanding ... more ABSTRACT The correct inference of gene regulatory network plays a critical role in understanding biological regulation in cells and genome based therapeutics. DNA microarray is the most widely used technology for extracting the relationships between thousands of genes simultaneously. Since S-system is based on the rate law, it is considered as a suitable mathematical model for representing complex biological reactions between genes. As, this problem has multiple solutions, optimized solution need to be identified via different nature inspired metaheuristic algorithms. So, in this paper, a new method is elaborated that helps to infer gene regulatory network for Lung Adenocarcinoma using S-system and Firefly Optimization which is an efficient but simple metaheuristic inspired by natural motion of fireflies. By optimizing the values of parameters of the S-system model, gene network can be easily reconstructed and inferred. Though direct biological validation of the network is not possible, but accuracy of the proposed method can be described as how well the network fit with the initial training data for different genes which is quite satisfactory for our research work.

2014 Fourth International Conference of Emerging Applications of Information Technology, 2014

ABSTRACT Suitable analysis of microarray dataset can unlock the mystery of the origin of many dre... more ABSTRACT Suitable analysis of microarray dataset can unlock the mystery of the origin of many dreaded disease like cancer which can subsequently be investigated for its rectification, resulting into search for drug design. A critical challenge of the post-genomic era is to find out the cancer causing genes that induce changes in gene expression profiles in the microarray dataset. Various algorithms based on SVM, Data Mining Techniques, Information theory based investigations, Clustering Techniques etc. were used by previous researchers. In this paper, Rough Set Theory and Bayesian Network based techniques have been applied for the same purpose. Rough Set has been used to isolate genes from microarray dataset responsible for cervical cancer. Bayesian approach has been used for extracting the Gene Regulating Network using the isolated genes. The same has been repeated for a normal healthy person. By superimposing these two networks, it is possible to find out the distinct cellular pathway for development of cancer from the departure of directed edges of the two networks. The results obtained in this work are quite satisfactory.

Biological databases, containing genetic information of patients, are undergoing tremendous growt... more Biological databases, containing genetic information of patients, are undergoing tremendous growth beyond our
analysing capability. However such analysis can reveal new findings about the cause and subsequent treatment
of any disease. Interactions between genes and the proteins they synthesize shape Genetic Regulatory Networks
(GRN). In this context, it has been developed a model capable of representing small dominant GRN, combining
characteristics from the Rough Set and Bayesian Network. The investigation has been carried out on the publicly
available microarray dataset for Lung Adenocarcinoma, obtained from the National Center for Biotechnology
Information (NCBI) website. The analysis revealed that Rough Set Theory (RST) is able to extract the various
dominant genes in term of reducts which play an important role in causing the disease and also able to provide a
unique simplified rule set for building expert systems in medical sciences with high accuracy and coverage factor.
The next part of this work is based on reconstruction of GRN using Bayesian network, which is a mathematical tool
for modelling conditional independences between stochastic variables like different gene expression. This proposed
Bayesian approach using scaled mutual information for scoring is applied to the dataset corresponding to most
dominant responsible genes for Adenocarcinoma to uncover, gene/protein interactions and key biological features
of the cellular system. Finally different interacting regulatory path which are the gene signature for a particular
disease, between dominating genes are inferred from the probability distribution table and Bayesian Graph. Such
reconstructed regulatory network is attractive for their ability to describe complex stochastic processes like gene
transcription, classification of biological sequencing and intuitive model of causal influence successfully. This may
serve as a signature pattern of the disease Adenocarcinoma, which has been extracted from huge microarray
dataset. Extraction of this signature pattern is very useful for diagnosis of this disease.

Current progress in cellular biology and bioinformatics allow researchers to get a distinct pictu... more Current progress in cellular biology and bioinformatics allow researchers to get a distinct picture of the complex biochemical processes those occur within a cell of the human body and remain as the cause for many diseases. Therefore, this technology opened up a new door to the researchers of computer science as well as to biologists to work together to investigate the causes of a disease. One of the greatest challenges of the post-genomic era is the investigation and inference of the regulatory interactions or dependencies between genes from the microarray data. Here, a new methodology has been devised for investigating the genetic interactions among genes from temporal gene expression data by combining the features of Neural Network and Cuckoo Search optimization. The developed technique has been applied on the real-world microarray dataset of Lung Adenocarcinoma for detection of genes which may be directly responsible for the cause of Lung Adenocarcinoma.

Naturally, cells in human body grow and divide in a controlled way to produce more cells to maint... more Naturally, cells in human body grow and divide in a controlled way to produce more cells to maintain health. Cancer affects human body when abnormal cells divide without control and becomes able to invade other tissues. The genetic material (DNA) of these cells becomes damaged or changed that affects normal cell growth and division. Early diagnosis is of considerable significance of the physician's skills conducted based on their knowledge and experience yet an error might occur. A range of therapies have been provided by researchers already. Use of various Artificial Intelligence methods for medical diagnosis of diseases has recently become widespread. These intelligent systems help physicians as a diagnosis assistant. Now, various Artificial Neural Network, Rough Set, Decision Tree, Bayesian Network are very popular for this purpose. In this paper, Multi layer Feed Forward Neural Network was used to detect cancer from Microarray Data and UCI Machine Learning Data. Back Propagation Rule was used for training the model. Throughout this paper, two types of validations were performed: cross validation and new case testing for above two datasets with different combination of hidden layers and corresponding nodes. It was found that, NN model can classify the data with very good accuracy and this will lead to automated medical diagnosis system for the particular disease.

In this paper, a Modified Exact Reconstruction Algorithm for Microwave Tomography has been propos... more In this paper, a Modified Exact Reconstruction Algorithm for Microwave Tomography has been proposed and applied on a diseased semi-human-sized biological target. An Exact Algorithm already developed for imaging has been used on a semi-human-sized normal biological model and, thereby, a reconstructed image on the basis of complex permittivities of the cells is obtained with an average accuracy of (90%-99%) for different regions. When a particular portion of the model is affected by some diseases, those cells are characterized by different values of complex permittivity from the normal ones. But the result provided by the Exact Algorithm is not very accurate for medical diagnosis when applied on such diseased model. It creates suspicion only about any disease on that portion. The aforesaid algorithm is, therefore, modified by considering the deviations in electric fields in all cells on account of change of permittivity in the diseased region. The image is reconstructed iteratively only on clinically suspected region keeping the values of complex permittivity in other cells the same as in its normal states. The reconstructed image thus obtained by using Modified Exact Algorithm is supposed to have sufficient accuracy of 95% for the diagnosis in medical field and may be helpful for detection of disease in human body in future.

Neural networks have been used during several years to solve classification problems in the Artif... more Neural networks have been used during several years to solve classification problems in the Artificial Intelligence. A neural network is inspired by the biological neuron of our human body and its performance depends directly on the design of the hidden layers, and in the calculation of the weights that connect the different nodes. On this paper, the structure of the hidden layer is not modified, as the interest lies only on the calculation of the weights of the system. In order to obtain a feasible result, the weights of the neural network are calculated or optimized by minimizing function cost or error. A Firefly Algorithm, which is an efficient but simple metaheuristic optimization technique inspired by natural motion of fireflies towards more light, is used for the training of neural network. The simulation results show that the computational efficiency of training process using Firefly Optimization technique.

In this paper an Exact Simultaneous Iterative Reconstruction Algorithm is developed and applied o... more In this paper an Exact Simultaneous Iterative Reconstruction Algorithm is developed and
applied on a large semi human size normal biological model and a diseased model (liver
region affected) to verify the efficiency of the algorithm. The algorithm is successfully
reconstructed the normal model having 15%-20% perturbation i.e. change in permittivity
during disease. In diseased case, reconstructed imaginary part of complex permittivity clearly
detects the affected zone and it may help the medical diagnosis. Hence it may be a powerful tool
for early detection of cancerous tumors as the interrogating wave is a noninvasive one at the
ultra high frequency range. The resolution of this system is increased with the reduction of
wavelength by immersing the antenna system and the model in saline water region. The
advantage of this algorithm is that the calculation of cofactor are done offline to save the
computational time and cofactors are expressed as a function of distances irrespective of their
positions .

Biological databases related to medical science, containing pathological, radiological and geneti... more Biological databases related to medical science, containing pathological, radiological and genetic information
of patients is undergoing tremendous growth, beyond our analyzing capability. However such analysis can reveal
new findings about the cause and subsequent treatment of any disease. Here the genetic information of Lung
Adenocarcinoma, in the form of microarray dataset has been investigated which have five different stages. Rough
Set Theory (RST) has been used in analysis with an aim to effectively extract biologically relevant information,
as RST is a tool that works well in an environment, heavy with inconsistent and ambiguous data, or with missing
data and provides efficient algorithms for finding hidden patterns in data. The investigation has been carried out
on the publicly available microarray dataset obtained from the GEO profiles at National Centre for Biotechnology
Information (NCBI) website. Cross validation of the generated rule sets shows 100% accuracy. Now to extract the
hidden biological dependencies between responsible genes, Decision Tree is used at consecutive two stages of
cancer development to identify the main culprit genes for cancer development from one stage to another and that
may lead to the drug design. The analysis revealed that hybrid Rough- Decision Tree is able to extract hidden
relationships among the various genes which play an important role in causing the disease and also able to provide
a unique rule set for automated medical diagnosis. Moreover at the end, the functions of the identified genes are
studied and validated from Gene Ontology website DAVID which clearly shows the direct or indirect relation of
genes with the cancer. This study highlights the usefulness and efficiency of RST and Decision Tree in the disease
diagnosis process and its potential use in inductive learning and as a valuable aid for building more biologically
significant expert systems in medical sciences.

Number of Patients with cancer, heart disease & Diabetes are increasing day by day because of exc... more Number of Patients with cancer, heart disease & Diabetes are increasing day by day because of excessive consumption of alcohol, inhale of harmful gases, intake of contaminated food, drugs and smoking etc. A range of therapies have been provided by researchers already. Early diagnosis is of considerable significance of the physician's skills conducted based on their knowledge and experience yet an error might occur. Using various Artificial Intelligence methods for medical diagnosis of diseases has recently become widespread. These intelligent systems help physicians as a diagnosis assistant. Now, various Artificial Neural Network, Rough Set, Decision Tree, Bayesian Network are very popular for this purpose. This paper provides a review of different soft computing method in diagnosis and detection of above mentioned disorders acuteness. The survey is carried out for three different types of data of different diseases with cross validation and percentage split for testing new data sets of each. The results indicates that Rough Set Theory gives maximum accuracy and coverage area but with maximum computational time complexity. On the other hand Neural and Bayesian Network give quite satisfactory results. Moreover the obtained results also suggest that accuracy depends on the quality of normalization of data.

Computer Science & Information Technology ( CS & IT ), 2013

vol. 3(1), 2017

Proceedings of the 2015 Third International Conference on Computer, Communication, Control and Information Technology (C3IT), 2015

2014 Fourth International Conference of Emerging Applications of Information Technology, 2014