Skip to main content

Dr. Ardhendu Mandal

UNIVERSITY OF NORTH BENGAL, Department of Computer Science and Technology, Faculty Member

UNIVERSITY OF NORTH BENGAL, Dept. of Computer Science and Application, Faculty Member

Followers

247

Following

76

Co-authors

10

Mentions

1

Public Views

Dr. Ardhendu Mandal, Associate Professor, is associated with the Department of Computer Science and Application, University of North Bengal, Dist-Darjeeling, West Bengal, Pin-734013, India. His research interest includes Software Engineering, Medical Image Processing and Analysis, Bioinformatics, High Performance Computing (HPC)
Phone: +919474390844
Address: Dept. of Computer Sc. and Technology, University of North Bengal(N.B.U.), Raja Rammhunpur, PO-N.B.U., Siliguri, Darjeeling, West Bengal, Pin-734013, India

less

InterestsView All (12)

Uploads

Papers by Dr. Ardhendu Mandal

An analysis on SVM and BPNN for CT Patient Table Detection using Distance-verses-angle Signature Feature

IEEE, 2021

Biomedical imaging plays an essential role in analyzing and diagnosing diseases related to the br... more Biomedical imaging plays an essential role in analyzing and diagnosing diseases related to the brain. There is a considerable variation in brain medical datasets, such as some CT scan datasets containing a patient table along with the brain object, whereas others only have the brain. In the first said category, the worthless undesirable tables are needed to be removed for further processing. On the other hand, no such removal techniques are required to be applied for the second case. This article has computed the classification performance of the Support Vector Machine(SVM) and Back Propagation algorithm(BPNN). The proposed method has been trained with 661 images and tested with 165 images. And the performance matrices show that both classifiers have the almost same level of accuracy, i.e., for SVM, average accuracy is 98.58% and for BPNN, it is 98.11%.

Realization of Combinational Circuits Using A Proposed Reversible Gate

IEEE, 2021

Because of the tremendous importance of very low power consumption, reversible logic synthesis ca... more Because of the tremendous importance of very low power consumption, reversible logic synthesis came out as a significant method in circuit design. It is one of several design strategies available for creating digital logic circuits. Here we have presented a reversible gate which, the ‘HAS’ gate, that can function as a Universal circuit. The suggested gate can carry out fundamental operations such as AND, OR, NOT, NAND, NOR, XOR, and so on. It also can be used to perform the complex functionalities of adder, subtractor, decoder, multiplexer, magnitude comparator etc. The proposed design efficiently implements all the basic functionalities of all combinational circuits with ease.

Follicle Segmentation from Ultrasound images of Ovary by using sub-band Entropy-based Wavelet thresholding and object contours

IEEE, 2021

Ultrasonography (USG) images are widely used all over the globe for Gynecological diagnosis of th... more Ultrasonography (USG) images are widely used all over the globe for Gynecological diagnosis of the ovary. USG images are highly contaminated by non-Gaussian multiplicative speckle noises which muffle critical clinical information. Thus despeckling and segmentation of Ovarian USG images has become an inseparable wing of obstetrical diagnosis. The proposed method employs multiresolution discrete wavelet thresholding based on sub-band entropy for eliminating noises. The follicles and other object regions are then beautifully segmented by finding the contour points. Dice Score, Jaccard Similarity Index, Sensitivity, and Specificity measures are used to demonstrate the performance of the proposed method and to illustrate how it outperforms the existing methods available to date.We have achieved state-of-the-art results with Dice Score 95.15%, Sensitivity rate 95.85%, Jaccard Similarity Index 78.9%.

Transparent Decision Support System for Breast Cancer (TDSSBC) to Determine the Risk Factor

Springer, 2021

Breast cancer is a fatal disease for women but infrequently for men. Many expert systems have bee... more Breast cancer is a fatal disease for women but infrequently for men. Many expert systems have been established for quick diagnosis of breast cancer utilizing various Machine Learning approaches; however, there is lack of explanation for their decision to justify the principles. The medical sector is now searching for an automated decision support system for evaluating the major risk of breast cancer. This paper has proposed a medical expert system named Transparent Decision Support System for Breast Cancer (TDSSBC) to manage BC by evaluating the Major Risk factors. The proposed TDSSBC has taken the property of the white-box NN method named “Rule Extraction from Neural Network (NN) applying Classified and Misclassified data” (RxNCM). It is used for the rule production from the BC dataset. In this gadget, the obtained rules are justifiable from the NN tool for the major risk factor of breast cancer. tenfold Cross-validation is used to test the overall system with the other two exiting systems (RxNCM) and (RxREN).

A Neural Expert System to Identify Major Risk Factors of Breast Cancer

IEEE, 2020

Now a days Breast Cancer (BC) is a very common cancer among women and rarely man. BC incidence ra... more Now a days Breast Cancer (BC) is a very common cancer among women and rarely man. BC incidence rate keeps increasing since 2000. Many intelligent systems have been proposed using different Machine Learning (ML) Techniques for early diagnosis of BC. Neural Networks (NN) is considered as one of the best ML classification techniques. In this paper we propose a medical expert system which named Transparent Neural Expert System for Breast Cancer (TNESBC) to manage BC by identifying Major Risk factors. The proposed TNESBC adopts the white-box NN model which named “Rule Extraction from Artificial Neural Network(ANN) applying Classified and Misclassified data” (RxNCM) for rule extraction from BC database. The rules are generated in this system which are most transparent to verify the Major Risk factors of BC. The proposed TNESBC algorithm is comparable the RxREN algorithm. The experimental analysis, it is noticed that TNESBC algorithm performs better than RxREN. The comparison is formed using 10-fold Cross-Validation(CV) accuracy, average recall rate, average number of antecedents per rules and average false positive rate.

Follicle Segmentation Using K-Means Clustering from Ultrasound Image of Ovary

Springer, 2020

Detection of number, shape and size of follicles in the ovary can play an important role in the d... more Detection of number, shape and size of follicles in the ovary can play an important role in the diagnosis and monitoring of different diseases like infertility, PCOS (Polycystic Ovarian Syndrome), ovarian cancer, etc. Nowadays the identification of these characteristics of follicles is done manually by radiologists and doctors from the Ultrasound Images of ovaries. Sometimes manual analysis can be tedious and thus may lead to erroneous results. In this paper, a method is proposed for automatic segmentation of follicles from Ultrasound Images using the K-means clustering technique.

An Empirical Study and Analysis of the Dynamic Load Balancing Techniques Used in Parallel Computing Systems

Proc. of the International Conference on Computing and Systems- 2010 (ICCS-2010), ISBN: 93-80813-01-5, 2010

A parallel computer system is a collection of processing elements that communicate and cooperate ... more A parallel computer system is a collection of processing elements that communicate and cooperate to solve large computational problems efficiently. To achieve this, at first the large computational problem is partitioned into several tasks with different work-loads and then are assigned to the different processing elements for computation. Distribution of the work load is known as Load Balancing. An appropriate distribution of work-loads across the various processing elements is very important as disproportional workloads can eliminate the performance benefit of parallelizing the job. Hence, load balancing on parallel systems is a critical and challenging activity. Load balancing algorithms can be broadly categorized as static or dynamic. Static load balancing algorithms distribute the tasks to processing elements at compile time, while dynamic algorithms bind tasks to processing elements at run time. This paper explains only the different dynamic load balancing techniques in brief used in parallel systems and concluding with the comparative performance analysis result of these algorithms.

BRIDGE: A Model for Modern Software Development Process to Cater the Present Software Crisis

IEEE, 2009

As hardware components are becoming cheaper and powerful day by day, the expected services from m... more As hardware components are becoming cheaper and powerful day by day, the expected services from modern software are increasing like any thing. Developing such software has become extremely challenging. Not only the complexity, but also the developing of such software within the time constraints and budget has become the real challenge. Quality concern and maintainability are added flavour to the challenge. On stream, the requirements of the clients are changing so frequently that it has become extremely tough to manage these changes. More often, the clients are unhappy with the end product. Large, complex software projects are notoriously late to market, often exhibit quality problems, and don't always deliver on promised functionality. None of the existing models are helpful to cater the modern software crisis. Hence, a better modern software development process model to handle with the present software crisis is badly needed. This paper suggests a new software development process model, BRIDGE, to tackle present software crisis.

An Empirical Study on Credit Risk Assessment Using Ensemble Classifiers

Advances in Data Science and Computing Technologies (ADSC 2022), Springer, 2022

Credit risk assessment is the major concerning issue for every financial organization. A simple c... more Credit risk assessment is the major concerning issue for every financial organization. A simple change in evaluation procedure can have a large influence on the financial market. The impact of machine learning techniques in credit risk assessment is highly influential. The intention of this research is to give insight into ensemble strategies for credit risk assessment and to evaluate with other standalone methods. The paper compares four tree-based classifiers namely—Decision Tree (DT), Random Forest (RF), AdaBoost and XGBoost using three different train-test splits for two publicly available German and Australian datasets. As per the findings, bagging based Random Forest classifier outperforms all the other classifiers for both datasets.

Machine Learning based Intelligent System for Breast Cancer Prediction (MLISBCP)

by Dr. Ardhendu Mandal, Akhil kumar Das, and Arijit Bhattacharya

Expert Systems with Applications, 2024

Risks of death from Breast Cancer (BC) are drastically rising in recent years. The diagnosis of b... more Risks of death from Breast Cancer (BC) are drastically rising in recent years. The diagnosis of breast cancer is time-consuming due to the limited availability of diagnostic systems such as dynamic MRI, X-rays etc. Early detection and diagnosis of breast cancer significantly impacts life expectancy as current medical technologies are not advanced enough to treat patients in later stages effectively. Even though researchers have created many expert systems for early detection of BC such as WNBC, AR + NN system, AdaBoost ELM etc., but still most expert systems frequently lack adequate handling of the class imbalance problem, proper data pre-processing, and systematic feature selection. To overcome these limitations, this work proposes an expert system named “Machine Learning Based Intelligent System for Breast Cancer Prediction (MLISBCP)” for better prediction of breast cancer using machine learning analytics. The suggested system utilises the ‘K-Means SMOTE’ oversampling method to handle the class imbalance problem and ‘Boruta’ feature selection technique to select the most relevant features of the BC dataset. To understand the effectiveness of the proposed model – MLISBCP, its performance is compared with various single classifier based models, ensemble models and various models present in literature in terms of performance metrics- accuracy, precision, recall, F1-score and RoC AUC Score. The results reveal that the MLISBCP obtained the highest accuracy of 97.53 % with respect to existing models present in the literature.

Comparison of Some Classical Edge Detection Techniques with their Suitability Analysis for Medical Images Processing

International Journal of Computer Sciences and Engineering, 2015

In digital image processing, understanding the scene is one of the most important and challenging... more In digital image processing, understanding the scene is one of the most important and challenging tasks. Along with many features of an image like texture, color, line, point etc. edges are most vital feature that carries the information about the structure and overall geometry of objects the image is composed of. Edge detection is based on finding meaningful discontinuities in gray levels. This brief study is aimed towards exploring different edge detection techniques, the theories behind them and distinguishing their efficiency in finding suitable, meaningful edges in digital medical images.

Follicle Segmentation from Ovarian USG Image Using Horizontal Window Filtering and Filled Convex Hull Technique

Advances in Intelligent Systems and Computing, 2020

Achieving Agility through BRIDGE Process Model: An Approach to Combine the Agile and the Disciplined Software Development

Innovations in Systems and Software Engineering , 2014

Despite of many criticisms, agile software development (Beck et al., Manifesto for Agile Software... more Despite of many criticisms, agile software development (Beck et al., Manifesto for Agile Software Development, http://agilemanifesto.org, [1]) philosophy has been proved to be quite successful to increase the project success rate up to a significant extent. The primary reasons behind the criticism of agile are the strong violation of the traditional disciplined software engineering theories, principles and practices. The goal of this research paper is to establish the fact that agility may also be achieved by following traditional process models especially with BRIDGE (Mandal, 2009 IEEE International Advance Computing Conference (IACC 2009) Patiala, India, [2]) process model. Hence, the aim of this paper is to integrate the agile and traditional disciplined software development process models and establish the compatibility between both the approaches. At the beginning, we have explored the objectives and principles of agile software development. Next, we briefly discussed the BRIDGE process model and further justified that—following BRIDGE process model, the philosophy of agile may also be achieved and conclude that BRIDGE model has both the capability of traditional software development process model as well as of the agile process

A Comparative Analysis of BRIDGE and Some Other Well Known Software Development Life Cycle Models

International Journal of Computer Science & Engineering Technology (IJCSET) , 2014

The existing Software Development Life Cycle Models (SDLC) models were quite successful earlier, ... more The existing Software Development Life Cycle Models (SDLC) models were quite successful earlier, but are rarely used in modern software development because of their limitations and non suitability for modern projects. To cater with the present software crisis, Mandal [13] proposed a SDLC model named BRIDGE for modern software development. In this paper we have outlined the BRIDGE process model. Further we performed a comparative analysis of the existing well know models and BRIDGE. Then, we discussed the results of the comparative analysis. Finally we conclude by recommending the BRIDGE process model to be the best generic process model for software development suitable for modern software development projects.

Least Centre Distance Based MAXNET Architecture to Obtain Threshold for Brain Tumor Edema Segmentation From FLAIR MRI

International Journal of Computer Sciences and Engineering, 2017

In recent years, Brain Tumor has become one of the most common deadly diseases and MRI is commonl... more In recent years, Brain Tumor has become one of the most common deadly diseases and MRI is commonly used to diagnose it. Automated recognition of brain tumors from MRI is a difficult task because of the variability of size, shape, and contrast of the tumor. On the other hand, it has a huge impact in helping the physicians by assessing the type, size, exact topological location and other related parameters of the tumor. Image segmentation techniques are often applied in identifying the tumor from the MRI images in addition to other techniques. There are numerous
segmentation techniques available for this purpose such as: (i) Region based (ii) Edge based (iii) Threshold based. Here a threshold based approach has been designed and proposed to do the segmentation of edema, where the threshold is determined by MAXNET, a Self Organization Map (SOM) based artificial neural network.

An Automated Skull-Stripping Method by Windowing the Histogram

International Journal of Computer Sciences and Engineering, 2017

The human brain is very complex structure composed of Neurons, Glial cells, Neural Stem cells and... more The human brain is very complex structure composed of Neurons, Glial cells, Neural Stem cells and blood vessels. A key issue in neuro-image e.g. Magnetic Resonance Image, (MRI) analysis is so called skull-stripping, which plays an important role in neuro-image processing, is the task of
separating predominant tissues in head, e.g. Gray Matter (GM), White Matter (WM) and Cerebrospinal Fluid(CSF), from the other tissues in head such as Bone, Skin, Muscle, Fat Dura etc. The accuracy of skull-stripping method affects the later stages of neuro-image analysis to a great extent. The measured signal intensity of brain tissue and non-brain tissue can overlap. This overlapping produces ambiguity in separation procedure and thus resulting false positive and false negative identification. This problem is so called nonseparability in the context of digital image processing.

Comparative Review on Efficient Design of Reversible Sequential Circuits based on Optimization Parameters

Journal of University of Shanghai for Science and Technology, 2021

Reversible computing, a well known research area in the field of computer science. One of the aim... more Reversible computing, a well known research area in the field of computer science. One of the aims of reversible computing is to design low power digital circuits that dissipates no energy to heat. The main challenge of designing reversible circuits is to optimize the parameters which make the design costly. In this paper, we review different designs of efficient reversible sequential circuits and prepare a comparative statement based on eight optimization parameters such as Quantum Cost (QC), Delay (del), Garbage Output (GO), Constant Input (CI), Gate Level (GL), Number of Gate (NoG), Type of Gate (ToG), Hardware Complexity (HC) of Circuit.

Credit Risk Evaluation: A Comprehensive Survey

Multimedia Tools and Applications, 2022

To date, there has been relatively little research in the field of credit risk analysis that comp... more To date, there has been relatively little research in the field of credit risk analysis that compares all of the well known statistical, optimization technique (heuristic methods) and machine learning based approaches in a single article. Review on credit risk assessment using sixteen well-known approaches has been conducted in this work. The accuracy of the machine learning approaches in dealing with financial difficulties is superior to that of traditional statistical methods, especially when dealing with nonlinear patterns, according to the findings. Hybrid or Ensemble algorithms, on the other hand have been found to outperform their traditional counterparts – standalone classifiers in the vast majority of situations. Finally, the paper compares the models with nine machine learning classifiers utilizing two benchmark datasets. In this study, we have encountered with 46 datasets, among them 35 datasets have been utilized for once; whereas among the other 11 datasets, Australian, German and Japanese are the three most frequently utilized datasets by the researchers. The study showed that the performance of ensemble classifiers were very much significant. As per the experimental result, for both datasets ensemble classifiers outperformed other standalone classifiers which validate with the prior research also. Although some of these approaches have a high level of accuracy, additional study is required to discover the right parameters and procedures for better outcomes in a transparent manner. Additionally this study is a valuable reference source for analyzing credit risk for both academic and practical domains, since it contains relevant information on the most major machine learning approaches employed so far.

An Expert System for Breast Cancer Prediction (ESBCP) using Decision Tree

Indian Journal of Science and Technology, 2022

Objectives: Breast cancer is one of the major concerns in present day scenario. Detecting breast ... more Objectives: Breast cancer is one of the major concerns in present day scenario. Detecting breast cancer at early stage increases the chances of survival. The objective of this research is to propose suitable feature selection method to improve the efficiency of breast cancer prediction at early stages to increase the survival rate. Methods: In this work, an expert intelligent technique has been proposed named “Expert System for Breast Cancer Prediction (ESBCP)” to detect breast cancer. To validate the results, the proposed system determines accuracy, precision, F-measure, and recall. The proposed model introduced a feature selection technique named - Undiluted Feature Set (UFS) to select the most relevant and promising features. The experimental work was carried out using Python 2.8 version in a Windows environment, taking a dataset on breast cancer from the UCI machine learning repository. There were 699 occurrences in the dataset with nine attributes and two classes. The proposed work utilized a decision tree and a new feature selection technique based on a heuristic search and the Stochastic Hill method. The experimental results were evaluated using the 10-fold Cross-Validation (CV). Findings: The experimental findings showed that the suggested model - ESBCP can accurately detect breast cancer at an early stage. As per the result, with simple decision tree the accuracy recorded 93.42 percent whereas ESBCP obtained 94.01 percent. It may seem that the improvement of 0.59 percent is very small, but for a large population even this mere change can have a greater impact. Novelty: The suggested model ESBCP and the feature selection technique - UFS have a lot of potential in the fields of medical research and bioinformatics in terms of classification capability and predictive power. Keywords: Expert System; Decision Tree; Undiluted Feature Set; Breast Cancer; Feature Selection

MU Net: Ovarian Follicle Segmentation Using Modified U-Net Architecture

International Journal of Engineering and Advanced Technology (IJEAT), 2022

Ovaries play a pivotal role in production by generating eggs through oogenesis in the female repr... more Ovaries play a pivotal role in production by generating eggs through oogenesis in the female reproductive system. This is one crucial aspect of reproduction as eggs are fertilized by the sperm which eventually leads to fertilization and eventually ending in embryo formation. Ovaries are often susceptible to diseases like infertility, polycystic ovarian syndrome (PCOS), ovarian cancer etc. Screening of ovarian follicles via ultrasound images can be of great help in the diagnosis of these abnormal situations. However, screening in most scenarios is still carried out manually by doctors and sonographers leading it to be a monotonous, time consuming and laborious job as well. Thus automatic detection of follicles can reduce the burden of doctors. In our work, we propose MU-net, a novel 2D segmentation network, combination of both MobileNetV2 and U-Net for segmentation of the follicles from ovarian ultrasound images. The test is conducted on the USOVA3D Training Set 1. Although low contrast issues are common setback for ultrasound images, our model has achieved a descent accuracy rate of 98.4%.

An analysis on SVM and BPNN for CT Patient Table Detection using Distance-verses-angle Signature Feature

IEEE, 2021

Biomedical imaging plays an essential role in analyzing and diagnosing diseases related to the br... more Biomedical imaging plays an essential role in analyzing and diagnosing diseases related to the brain. There is a considerable variation in brain medical datasets, such as some CT scan datasets containing a patient table along with the brain object, whereas others only have the brain. In the first said category, the worthless undesirable tables are needed to be removed for further processing. On the other hand, no such removal techniques are required to be applied for the second case. This article has computed the classification performance of the Support Vector Machine(SVM) and Back Propagation algorithm(BPNN). The proposed method has been trained with 661 images and tested with 165 images. And the performance matrices show that both classifiers have the almost same level of accuracy, i.e., for SVM, average accuracy is 98.58% and for BPNN, it is 98.11%.

Realization of Combinational Circuits Using A Proposed Reversible Gate

IEEE, 2021

Because of the tremendous importance of very low power consumption, reversible logic synthesis ca... more Because of the tremendous importance of very low power consumption, reversible logic synthesis came out as a significant method in circuit design. It is one of several design strategies available for creating digital logic circuits. Here we have presented a reversible gate which, the ‘HAS’ gate, that can function as a Universal circuit. The suggested gate can carry out fundamental operations such as AND, OR, NOT, NAND, NOR, XOR, and so on. It also can be used to perform the complex functionalities of adder, subtractor, decoder, multiplexer, magnitude comparator etc. The proposed design efficiently implements all the basic functionalities of all combinational circuits with ease.

Follicle Segmentation from Ultrasound images of Ovary by using sub-band Entropy-based Wavelet thresholding and object contours

IEEE, 2021

Ultrasonography (USG) images are widely used all over the globe for Gynecological diagnosis of th... more Ultrasonography (USG) images are widely used all over the globe for Gynecological diagnosis of the ovary. USG images are highly contaminated by non-Gaussian multiplicative speckle noises which muffle critical clinical information. Thus despeckling and segmentation of Ovarian USG images has become an inseparable wing of obstetrical diagnosis. The proposed method employs multiresolution discrete wavelet thresholding based on sub-band entropy for eliminating noises. The follicles and other object regions are then beautifully segmented by finding the contour points. Dice Score, Jaccard Similarity Index, Sensitivity, and Specificity measures are used to demonstrate the performance of the proposed method and to illustrate how it outperforms the existing methods available to date.We have achieved state-of-the-art results with Dice Score 95.15%, Sensitivity rate 95.85%, Jaccard Similarity Index 78.9%.

Transparent Decision Support System for Breast Cancer (TDSSBC) to Determine the Risk Factor

Springer, 2021

Breast cancer is a fatal disease for women but infrequently for men. Many expert systems have bee... more Breast cancer is a fatal disease for women but infrequently for men. Many expert systems have been established for quick diagnosis of breast cancer utilizing various Machine Learning approaches; however, there is lack of explanation for their decision to justify the principles. The medical sector is now searching for an automated decision support system for evaluating the major risk of breast cancer. This paper has proposed a medical expert system named Transparent Decision Support System for Breast Cancer (TDSSBC) to manage BC by evaluating the Major Risk factors. The proposed TDSSBC has taken the property of the white-box NN method named “Rule Extraction from Neural Network (NN) applying Classified and Misclassified data” (RxNCM). It is used for the rule production from the BC dataset. In this gadget, the obtained rules are justifiable from the NN tool for the major risk factor of breast cancer. tenfold Cross-validation is used to test the overall system with the other two exiting systems (RxNCM) and (RxREN).

A Neural Expert System to Identify Major Risk Factors of Breast Cancer

IEEE, 2020

Now a days Breast Cancer (BC) is a very common cancer among women and rarely man. BC incidence ra... more Now a days Breast Cancer (BC) is a very common cancer among women and rarely man. BC incidence rate keeps increasing since 2000. Many intelligent systems have been proposed using different Machine Learning (ML) Techniques for early diagnosis of BC. Neural Networks (NN) is considered as one of the best ML classification techniques. In this paper we propose a medical expert system which named Transparent Neural Expert System for Breast Cancer (TNESBC) to manage BC by identifying Major Risk factors. The proposed TNESBC adopts the white-box NN model which named “Rule Extraction from Artificial Neural Network(ANN) applying Classified and Misclassified data” (RxNCM) for rule extraction from BC database. The rules are generated in this system which are most transparent to verify the Major Risk factors of BC. The proposed TNESBC algorithm is comparable the RxREN algorithm. The experimental analysis, it is noticed that TNESBC algorithm performs better than RxREN. The comparison is formed using 10-fold Cross-Validation(CV) accuracy, average recall rate, average number of antecedents per rules and average false positive rate.

Follicle Segmentation Using K-Means Clustering from Ultrasound Image of Ovary

Springer, 2020

Detection of number, shape and size of follicles in the ovary can play an important role in the d... more Detection of number, shape and size of follicles in the ovary can play an important role in the diagnosis and monitoring of different diseases like infertility, PCOS (Polycystic Ovarian Syndrome), ovarian cancer, etc. Nowadays the identification of these characteristics of follicles is done manually by radiologists and doctors from the Ultrasound Images of ovaries. Sometimes manual analysis can be tedious and thus may lead to erroneous results. In this paper, a method is proposed for automatic segmentation of follicles from Ultrasound Images using the K-means clustering technique.

An Empirical Study and Analysis of the Dynamic Load Balancing Techniques Used in Parallel Computing Systems

Proc. of the International Conference on Computing and Systems- 2010 (ICCS-2010), ISBN: 93-80813-01-5, 2010

A parallel computer system is a collection of processing elements that communicate and cooperate ... more A parallel computer system is a collection of processing elements that communicate and cooperate to solve large computational problems efficiently. To achieve this, at first the large computational problem is partitioned into several tasks with different work-loads and then are assigned to the different processing elements for computation. Distribution of the work load is known as Load Balancing. An appropriate distribution of work-loads across the various processing elements is very important as disproportional workloads can eliminate the performance benefit of parallelizing the job. Hence, load balancing on parallel systems is a critical and challenging activity. Load balancing algorithms can be broadly categorized as static or dynamic. Static load balancing algorithms distribute the tasks to processing elements at compile time, while dynamic algorithms bind tasks to processing elements at run time. This paper explains only the different dynamic load balancing techniques in brief used in parallel systems and concluding with the comparative performance analysis result of these algorithms.

BRIDGE: A Model for Modern Software Development Process to Cater the Present Software Crisis

IEEE, 2009

As hardware components are becoming cheaper and powerful day by day, the expected services from m... more As hardware components are becoming cheaper and powerful day by day, the expected services from modern software are increasing like any thing. Developing such software has become extremely challenging. Not only the complexity, but also the developing of such software within the time constraints and budget has become the real challenge. Quality concern and maintainability are added flavour to the challenge. On stream, the requirements of the clients are changing so frequently that it has become extremely tough to manage these changes. More often, the clients are unhappy with the end product. Large, complex software projects are notoriously late to market, often exhibit quality problems, and don't always deliver on promised functionality. None of the existing models are helpful to cater the modern software crisis. Hence, a better modern software development process model to handle with the present software crisis is badly needed. This paper suggests a new software development process model, BRIDGE, to tackle present software crisis.

An Empirical Study on Credit Risk Assessment Using Ensemble Classifiers

Advances in Data Science and Computing Technologies (ADSC 2022), Springer, 2022

Credit risk assessment is the major concerning issue for every financial organization. A simple c... more Credit risk assessment is the major concerning issue for every financial organization. A simple change in evaluation procedure can have a large influence on the financial market. The impact of machine learning techniques in credit risk assessment is highly influential. The intention of this research is to give insight into ensemble strategies for credit risk assessment and to evaluate with other standalone methods. The paper compares four tree-based classifiers namely—Decision Tree (DT), Random Forest (RF), AdaBoost and XGBoost using three different train-test splits for two publicly available German and Australian datasets. As per the findings, bagging based Random Forest classifier outperforms all the other classifiers for both datasets.

Machine Learning based Intelligent System for Breast Cancer Prediction (MLISBCP)

by Dr. Ardhendu Mandal, Akhil kumar Das, and Arijit Bhattacharya

Expert Systems with Applications, 2024

Risks of death from Breast Cancer (BC) are drastically rising in recent years. The diagnosis of b... more Risks of death from Breast Cancer (BC) are drastically rising in recent years. The diagnosis of breast cancer is time-consuming due to the limited availability of diagnostic systems such as dynamic MRI, X-rays etc. Early detection and diagnosis of breast cancer significantly impacts life expectancy as current medical technologies are not advanced enough to treat patients in later stages effectively. Even though researchers have created many expert systems for early detection of BC such as WNBC, AR + NN system, AdaBoost ELM etc., but still most expert systems frequently lack adequate handling of the class imbalance problem, proper data pre-processing, and systematic feature selection. To overcome these limitations, this work proposes an expert system named “Machine Learning Based Intelligent System for Breast Cancer Prediction (MLISBCP)” for better prediction of breast cancer using machine learning analytics. The suggested system utilises the ‘K-Means SMOTE’ oversampling method to handle the class imbalance problem and ‘Boruta’ feature selection technique to select the most relevant features of the BC dataset. To understand the effectiveness of the proposed model – MLISBCP, its performance is compared with various single classifier based models, ensemble models and various models present in literature in terms of performance metrics- accuracy, precision, recall, F1-score and RoC AUC Score. The results reveal that the MLISBCP obtained the highest accuracy of 97.53 % with respect to existing models present in the literature.

Comparison of Some Classical Edge Detection Techniques with their Suitability Analysis for Medical Images Processing

International Journal of Computer Sciences and Engineering, 2015

In digital image processing, understanding the scene is one of the most important and challenging... more In digital image processing, understanding the scene is one of the most important and challenging tasks. Along with many features of an image like texture, color, line, point etc. edges are most vital feature that carries the information about the structure and overall geometry of objects the image is composed of. Edge detection is based on finding meaningful discontinuities in gray levels. This brief study is aimed towards exploring different edge detection techniques, the theories behind them and distinguishing their efficiency in finding suitable, meaningful edges in digital medical images.

Follicle Segmentation from Ovarian USG Image Using Horizontal Window Filtering and Filled Convex Hull Technique

Advances in Intelligent Systems and Computing, 2020

Achieving Agility through BRIDGE Process Model: An Approach to Combine the Agile and the Disciplined Software Development

Innovations in Systems and Software Engineering , 2014

Despite of many criticisms, agile software development (Beck et al., Manifesto for Agile Software... more Despite of many criticisms, agile software development (Beck et al., Manifesto for Agile Software Development, http://agilemanifesto.org, [1]) philosophy has been proved to be quite successful to increase the project success rate up to a significant extent. The primary reasons behind the criticism of agile are the strong violation of the traditional disciplined software engineering theories, principles and practices. The goal of this research paper is to establish the fact that agility may also be achieved by following traditional process models especially with BRIDGE (Mandal, 2009 IEEE International Advance Computing Conference (IACC 2009) Patiala, India, [2]) process model. Hence, the aim of this paper is to integrate the agile and traditional disciplined software development process models and establish the compatibility between both the approaches. At the beginning, we have explored the objectives and principles of agile software development. Next, we briefly discussed the BRIDGE process model and further justified that—following BRIDGE process model, the philosophy of agile may also be achieved and conclude that BRIDGE model has both the capability of traditional software development process model as well as of the agile process

A Comparative Analysis of BRIDGE and Some Other Well Known Software Development Life Cycle Models

International Journal of Computer Science & Engineering Technology (IJCSET) , 2014

The existing Software Development Life Cycle Models (SDLC) models were quite successful earlier, ... more The existing Software Development Life Cycle Models (SDLC) models were quite successful earlier, but are rarely used in modern software development because of their limitations and non suitability for modern projects. To cater with the present software crisis, Mandal [13] proposed a SDLC model named BRIDGE for modern software development. In this paper we have outlined the BRIDGE process model. Further we performed a comparative analysis of the existing well know models and BRIDGE. Then, we discussed the results of the comparative analysis. Finally we conclude by recommending the BRIDGE process model to be the best generic process model for software development suitable for modern software development projects.

Least Centre Distance Based MAXNET Architecture to Obtain Threshold for Brain Tumor Edema Segmentation From FLAIR MRI

International Journal of Computer Sciences and Engineering, 2017

In recent years, Brain Tumor has become one of the most common deadly diseases and MRI is commonl... more In recent years, Brain Tumor has become one of the most common deadly diseases and MRI is commonly used to diagnose it. Automated recognition of brain tumors from MRI is a difficult task because of the variability of size, shape, and contrast of the tumor. On the other hand, it has a huge impact in helping the physicians by assessing the type, size, exact topological location and other related parameters of the tumor. Image segmentation techniques are often applied in identifying the tumor from the MRI images in addition to other techniques. There are numerous
segmentation techniques available for this purpose such as: (i) Region based (ii) Edge based (iii) Threshold based. Here a threshold based approach has been designed and proposed to do the segmentation of edema, where the threshold is determined by MAXNET, a Self Organization Map (SOM) based artificial neural network.

An Automated Skull-Stripping Method by Windowing the Histogram

International Journal of Computer Sciences and Engineering, 2017

The human brain is very complex structure composed of Neurons, Glial cells, Neural Stem cells and... more The human brain is very complex structure composed of Neurons, Glial cells, Neural Stem cells and blood vessels. A key issue in neuro-image e.g. Magnetic Resonance Image, (MRI) analysis is so called skull-stripping, which plays an important role in neuro-image processing, is the task of
separating predominant tissues in head, e.g. Gray Matter (GM), White Matter (WM) and Cerebrospinal Fluid(CSF), from the other tissues in head such as Bone, Skin, Muscle, Fat Dura etc. The accuracy of skull-stripping method affects the later stages of neuro-image analysis to a great extent. The measured signal intensity of brain tissue and non-brain tissue can overlap. This overlapping produces ambiguity in separation procedure and thus resulting false positive and false negative identification. This problem is so called nonseparability in the context of digital image processing.

Comparative Review on Efficient Design of Reversible Sequential Circuits based on Optimization Parameters

Journal of University of Shanghai for Science and Technology, 2021

Reversible computing, a well known research area in the field of computer science. One of the aim... more Reversible computing, a well known research area in the field of computer science. One of the aims of reversible computing is to design low power digital circuits that dissipates no energy to heat. The main challenge of designing reversible circuits is to optimize the parameters which make the design costly. In this paper, we review different designs of efficient reversible sequential circuits and prepare a comparative statement based on eight optimization parameters such as Quantum Cost (QC), Delay (del), Garbage Output (GO), Constant Input (CI), Gate Level (GL), Number of Gate (NoG), Type of Gate (ToG), Hardware Complexity (HC) of Circuit.

Credit Risk Evaluation: A Comprehensive Survey

Multimedia Tools and Applications, 2022

To date, there has been relatively little research in the field of credit risk analysis that comp... more To date, there has been relatively little research in the field of credit risk analysis that compares all of the well known statistical, optimization technique (heuristic methods) and machine learning based approaches in a single article. Review on credit risk assessment using sixteen well-known approaches has been conducted in this work. The accuracy of the machine learning approaches in dealing with financial difficulties is superior to that of traditional statistical methods, especially when dealing with nonlinear patterns, according to the findings. Hybrid or Ensemble algorithms, on the other hand have been found to outperform their traditional counterparts – standalone classifiers in the vast majority of situations. Finally, the paper compares the models with nine machine learning classifiers utilizing two benchmark datasets. In this study, we have encountered with 46 datasets, among them 35 datasets have been utilized for once; whereas among the other 11 datasets, Australian, German and Japanese are the three most frequently utilized datasets by the researchers. The study showed that the performance of ensemble classifiers were very much significant. As per the experimental result, for both datasets ensemble classifiers outperformed other standalone classifiers which validate with the prior research also. Although some of these approaches have a high level of accuracy, additional study is required to discover the right parameters and procedures for better outcomes in a transparent manner. Additionally this study is a valuable reference source for analyzing credit risk for both academic and practical domains, since it contains relevant information on the most major machine learning approaches employed so far.

An Expert System for Breast Cancer Prediction (ESBCP) using Decision Tree

Indian Journal of Science and Technology, 2022

Objectives: Breast cancer is one of the major concerns in present day scenario. Detecting breast ... more Objectives: Breast cancer is one of the major concerns in present day scenario. Detecting breast cancer at early stage increases the chances of survival. The objective of this research is to propose suitable feature selection method to improve the efficiency of breast cancer prediction at early stages to increase the survival rate. Methods: In this work, an expert intelligent technique has been proposed named “Expert System for Breast Cancer Prediction (ESBCP)” to detect breast cancer. To validate the results, the proposed system determines accuracy, precision, F-measure, and recall. The proposed model introduced a feature selection technique named - Undiluted Feature Set (UFS) to select the most relevant and promising features. The experimental work was carried out using Python 2.8 version in a Windows environment, taking a dataset on breast cancer from the UCI machine learning repository. There were 699 occurrences in the dataset with nine attributes and two classes. The proposed work utilized a decision tree and a new feature selection technique based on a heuristic search and the Stochastic Hill method. The experimental results were evaluated using the 10-fold Cross-Validation (CV). Findings: The experimental findings showed that the suggested model - ESBCP can accurately detect breast cancer at an early stage. As per the result, with simple decision tree the accuracy recorded 93.42 percent whereas ESBCP obtained 94.01 percent. It may seem that the improvement of 0.59 percent is very small, but for a large population even this mere change can have a greater impact. Novelty: The suggested model ESBCP and the feature selection technique - UFS have a lot of potential in the fields of medical research and bioinformatics in terms of classification capability and predictive power. Keywords: Expert System; Decision Tree; Undiluted Feature Set; Breast Cancer; Feature Selection

MU Net: Ovarian Follicle Segmentation Using Modified U-Net Architecture

International Journal of Engineering and Advanced Technology (IJEAT), 2022

Ovaries play a pivotal role in production by generating eggs through oogenesis in the female repr... more Ovaries play a pivotal role in production by generating eggs through oogenesis in the female reproductive system. This is one crucial aspect of reproduction as eggs are fertilized by the sperm which eventually leads to fertilization and eventually ending in embryo formation. Ovaries are often susceptible to diseases like infertility, polycystic ovarian syndrome (PCOS), ovarian cancer etc. Screening of ovarian follicles via ultrasound images can be of great help in the diagnosis of these abnormal situations. However, screening in most scenarios is still carried out manually by doctors and sonographers leading it to be a monotonous, time consuming and laborious job as well. Thus automatic detection of follicles can reduce the burden of doctors. In our work, we propose MU-net, a novel 2D segmentation network, combination of both MobileNetV2 and U-Net for segmentation of the follicles from ovarian ultrasound images. The test is conducted on the USOVA3D Training Set 1. Although low contrast issues are common setback for ultrasound images, our model has achieved a descent accuracy rate of 98.4%.