Time filter

Source Type

Kar S.,Dumkal Institute of Engineering and Technology | Majumder D.D.,Indian Statistical Institute | Majumder D.D.,Institute of Cybernetics Systems and Information Technology
International Journal of Clinical Oncology | Year: 2017

Background: Investigation of brain cancer can detect the abnormal growth of tissue in the brain using computed tomography (CT) scans and magnetic resonance (MR) images of patients. The proposed method classifies brain cancer on shape-based feature extraction as either benign or malignant. The authors used input variables such as shape distance (SD) and shape similarity measure (SSM) in fuzzy tools, and used fuzzy rules to evaluate the risk status as an output variable. We presented a classifier neural network system (NNS), namely Levenberg–Marquardt (LM), which is a feed-forward back-propagation learning algorithm used to train the NN for the status of brain cancer, if any, and which achieved satisfactory performance with 100% accuracy. Methods: The proposed methodology is divided into three phases. First, we find the region of interest (ROI) in the brain to detect the tumors using CT and MR images. Second, we extract the shape-based features, like SD and SSM, and grade the brain tumors as benign or malignant with the concept of SD function and SSM as shape-based parameters. Third, we classify the brain cancers using neuro-fuzzy tools. In this experiment, we used a 16-sample database with SSM (μ) values and classified the benignancy or malignancy of the brain tumor lesions using the neuro-fuzzy system (NFS). Results: We have developed a fuzzy expert system (FES) and NFS for early detection of brain cancer from CT and MR images. In this experiment, shape-based features, such as SD and SSM, were extracted from the ROI of brain tumor lesions. These shape-based features were considered as input variables and, using fuzzy rules, we were able to evaluate brain cancer risk values for each case. We used an NNS with LM, a feed-forward back-propagation learning algorithm, as a classifier for the diagnosis of brain cancer and achieved satisfactory performance with 100% accuracy. The proposed network was trained with MR image datasets of 16 cases. The 16 cases were fed to the ANN with 2 input neurons, one hidden layer of 10 neurons and 2 output neurons. Of the 16-sample database, 10 datasets for training, 3 datasets for validation, and 3 datasets for testing were used in the ANN classification system. From the SSM (µ) confusion matrix, the number of output datasets of true positive, false positive, true negative and false negative was 6, 0, 10, and 0, respectively. The sensitivity, specificity and accuracy were each equal to 100%. Conclusion: The method of diagnosing brain cancer presented in this study is a successful model to assist doctors in the screening and treatment of brain cancer patients. The presented FES successfully identified the presence of brain cancer in CT and MR images using the extracted shape-based features and the use of NFS for the identification of brain cancer in the early stages. From the analysis and diagnosis of the disease, the doctors can decide the stage of cancer and take the necessary steps for more accurate treatment. Here, we have presented an investigation and comparison study of the shape-based feature extraction method with the use of NFS for classifying brain tumors as showing normal or abnormal patterns. The results have proved that the shape-based features with the use of NFS can achieve a satisfactory performance with 100% accuracy. We intend to extend this methodology for the early detection of cancer in other regions such as the prostate region and human cervix. © 2017 Japan Society of Clinical Oncology

Mukherjee J.,Indian Central Glass and Ceramic Research Institute | Ranjan A.,Defence Materials and Stores Research and Development Establishment | Saxena A.K.,Defence Materials and Stores Research and Development Establishment | Karan S.,University of Calcutta | And 5 more authors.
Journal of Materials Chemistry C | Year: 2013

This paper presents a novel rectifying interface material using carbon rich crystalline (C)-SiC and n-type Si by a modified CVD technique, using liquid polycarbosilane as a precursor at 900 °C. The equilibrium band diagram and Fermi level alignment was explained using Poisson's model and the depletion approximation. The junction capacitance, depletion width and saturation current were evaluated and further discussed from the perspective of temperature dependency. The junction was found to be Schottky in nature, with a large breakdown voltage of 69 V and low space charge. This type of junction material, having good mechanical strength, is promising for high temperature and high power applications. This journal is © 2013 The Royal Society of Chemistry.

Majumder D.D.,Indian Statistical Institute | Dattamajumder A.,Institute of Cybernetics Systems and Information Technology | Dattamajumder D.,Institute of Cybernetics Systems and Information Technology | Karan S.,Institute of Cybernetics Systems and Information Technology | And 3 more authors.
International Conference on Soft Computing Techniques and Implementations, ICSCTI 2015 | Year: 2015

In this paper we presented the Role of Consciousness in the Physical World and also we attempt to explore the scientific foundation of Non-Equilibrium Psychodynamics, Altered-awareness, logics, geometries, and other states of mind-as the continuum of the Source of Reality. In the present state of human knowledge the absolute and Universal Reality and truth system would be inaccessible to the human mind. A System of reality being evolutionary in nature may remain incomplete and will need revision. Even if, mathematically perfect reality remains indeterminate, an algorithmic approach based on knowledge engineering approaches involving pattern recognition, image/speech processing, computer vision and AI, of avoiding the limitations has been attempted for applications to the emerging science of mind and consciousness and the resulting technologies. © 2015 IEEE.

Majumder D.D.,ECS Unit | Majumder D.D.,Indian Statistical Institute | Majumder D.D.,CSIR - Central Electrochemical Research Institute | Majumder D.D.,Institute of Cybernetics Systems and Information Technology | Ray D.,Indian School of Mines
IETE Journal of Research | Year: 2011

Medical images of different modalities, such as computed tomography/magnetic resonance/Positron Emission Tomography/Single Photon Emission Computed Tomography/ultrasonography, etc., of a particular object of interest provide complimentary information about the conditions of diseases and that of patients. Mapping of one image over that of other and a subsequent fusion of images is of immense importance from the point of view of diagnostics and treatment planning. In this paper, we have presented major theoretical/practical approaches of medical image registration. After making both methodological and technical survey of almost all the approaches in literature of both functional and anatomical images, we presented an in-depth study of two relatively recent approaches that we consider most promising. These are shape theoretic and image entropy-based methods. We have also proposed a soft computing approach of fusion of registered images using Dempster Shafer Theory of Evidence Accumulation along with some experimental results on some critical human body components such as brain, chest, and bones.

Karan S.,University of Calcutta | Chakraborty A.,Thomas College | Majumder D.D.,Indian Statistical Institute | Majumder D.D.,Institute of Cybernetics Systems and Information Technology
International Conference on Soft Computing Techniques and Implementations, ICSCTI 2015 | Year: 2015

Quantum Consciousness will play an important role in future Information Communication Technology (ICT) for its fast information processing requirement and the advancement of Nano-science and Technology radically explore the field recently. In this paper we present a mathematical formalism of nanoscale dynamics in the light of quantum consciousness. A parametric methodology for establishing self-organizing property of nanoscopic particle using deterministic quantum relativistic parameters instead of probabilistic quantum mechanical terms for energy and momentum has also been designed. The physical dynamics of the particle towards a common point (self-assembled) has been explained with the help of hidden consciousness parameter, avoiding uncertainty relations in a limiting range where the tiny nano particle 1-100nm, constitute an elementary unit of cognition. A brief study of the situations (multi particle dynamical system) in case of nanoparticles fabrication both in bottom-up and top-down has been performed. Self assembly as dynamic interacting pattern formation in multi particle dynamical system has also been presented. © 2015 IEEE.

Karan S.,University of Calcutta | Karan S.,Institute of Cybernetics Systems and Information Technology | Dutta Majumder D.,Institute of Cybernetics Systems and Information Technology | Dutta Majumder D.,Indian Statistical Institute | Goswami A.,Indian Statistical Institute
Indian Journal of Physics | Year: 2012

The molecular nanotechnology is the concept of functional mechanical system at the molecular scale, i.e., machines at the molecular scale, designed and built atom by atom. This idea along with self recognition (self assembly) can be used in the development of intelligent nanoparticles (NPs). In this paper we present a mathematical formalism of force balance and self assembly along with a quantum mechanical algorithmic approach for avoiding uncertainty relations in a limited range, where tiny nano particle (1-100 nm), constitute an elementary unit. We explain the natural self organization, where, the system organizes itself, but there is no known agent inside the system doing the organizing. Thiol, aspartic acid, citrate and bovine serum albumin capped gold NPs were synthesised in the laboratory with potentially useful size and shape dependent properties. We used colloidal method for synthesis of NPs confinement at 2, 5, 10 and 20 nm. The particle shape contours were measured by transmission electron microscope with high resolution field emission scanning electron microscope (FE-SEM, FEI Quanta 200F). AFM (AFM-STM, Ntegra Ts-150) study was performed to see the surface topology and confinement. SPR spectra study including pH stability analysis is used to study the properties of quantum confinement. © 2012 IACS.

Karan S.,University of Calcutta | Karan S.,Computational Intelligence and Nanotechnology Research Society | Banerjee B.,Institute of Cybernetics Systems and Information Technology | Tripathi A.,Institute of Cybernetics Systems and Information Technology | And 3 more authors.
Advances in Intelligent Systems and Computing | Year: 2015

Nanorobotics is currently emerging as an attractive area of scientific research bridging biological and computational science along with mechanical science at the molecular level. We present a new approach to control the machines at the nano-meter or molecular scale (10-9 meter) in the perspective of the theory of cybernetics, the science of control, communication and computation with integration to complex man–machines systems. The problem under study concentrates its main focus on nano-robot control systems design including systems casualty, state notation and automata. We also describe the theory of nano-scale thermodynamically driven self assembly for collaborative information processing in a Bio-nanorobotics systems. A fuzzy shaped based approach is described in context of recognizing a single malignant cell along with its stage, as a target for medical treatment. The synthesis and imaging of magnetic nanoparticles, that can be functionally bind with the medicine and reached the effected regions for targeted drug delivery, such as in cancer treatment is also presented. © Springer International Publishing Switzerland 2015.

Mondal D.,Jalpaiguri Government Engg College | Chakraborty A.,Thomas College | Chakraborty A.,Institute of Cybernetics Systems and Information Technology | Kole D.K.,Jalpaiguri Government Engg College | And 2 more authors.
International Conference on Soft Computing Techniques and Implementations, ICSCTI 2015 | Year: 2015

Okra (Abelmoschus esculentus (L) Moench), is widely grown all over tropical, subtropical and warm temperature regions of the world. It is a popular crop in India due to its ease of cultivation and adaptability to varying moisture conditions. But the crop is prone to damage by various diseases caused by various insects, fungi, nematodes and viruses. The most common disease of okra is Yellow Vein Mosaic Virus (YVMV), spread by white fly (Bemisiatabaci). This paper presents an efficient technique to detect and classify the presence of YVMV disease in okra leaf with the joint use of image processing, K-means and Naive Bayesian classifier. The proposed technique is experimented on 79 standard diseased and non-diseased okra leaf images. The input leaf images are of four classes, namely Highly Susceptible (HS), Moderately Susceptible (MS), Tolerable (T) and Resistive (R), depending upon the severity of the YVMV infection. The proposed technique achieves 87% success rate using 10 features only. © 2015 IEEE.

Chanda D.,Jadavpur University | Majumder D.D.,Indian Statistical Institute | Majumder D.D.,Institute of Cybernetics Systems and Information Technology | Bhattacharya S.,National Institute of Technology Durgapur | Bhattacharya S.,Jadavpur University
SEKE 2010 - Proceedings of the 22nd International Conference on Software Engineering and Knowledge Engineering | Year: 2010

For creating virtual enterprise (VE), which is in general the collaborative partnership between business partners in value chains, the business processes (services) of the resulting organization need to be composed of the individual business processes of the participating organizations. This can be realized by means of Service Oriented Architecture (SOA). In our paper we propose a SOA Framework based on Knowledge Bases.

Majumdar D.,Indian Institute of Technology Guwahati | Kole D.K.,Jalpaiguri Government Engineering College | Chakraborty A.,Thomas College | Majumder D.D.,Institute of Cybernetics Systems and Information Technology
ACM International Conference Proceeding Series | Year: 2015

Wheat leaves need to be scouted routinely for early detection and recognition of rust diseases. This facilitates timely management decisions. In this paper, an integrated image processing and analysis system has been developed to automate the inspection of these leaves and detection of any disease present in them. Disease features of wheat leaves have been extracted using Fuzzy c-means Clustering algorithm and disease detection, recognition of its type and identification algorithm has been developed based on artificial neural network (ANN). Through the use of ANN and more specifically multilayer perceptrons, detection of the presence of disease in wheat leaves have been successful in 97% of the cases, after analysis of about 300 test images of wheat leaves. Also, identification of type of disease, if present, in wheat leaf has been successful in 85% of the cases. © 2015 ACM.

Loading Institute of Cybernetics Systems and Information Technology collaborators
Loading Institute of Cybernetics Systems and Information Technology collaborators