LEAD DATA SCIENTIST (COMPUTER VISION AND RESEARCH)

​

SIEMENS ADVANTA

AND 

ACM DISTINGUISHED SPEAKER

​

ASSOCIATION FOR COMPUTING MACHINERY, NEW YORK, USA

Interest Areas: Medical Imaging, Deep Learning, Machine Learning, Computer Vision

I’m thrilled you’re here. Please take a moment to explore my site, where you’ll find details on my background, experience, skills and more. To learn more or connect on an opportunity, don’t hesitate to reach out.

SUMMARY

I take keen interest in researching with Computer Vision, Machine Learning and Deep Learning. My interest areas include Content Based Image Classification, Retrieval, Fusion Based Recognition, Classification and Retrieval of Medical Images, Deep Neural Networks (Supervised and Unsupervised).  I am open to new research ideas and collaborative research work with a strong thrust on real time applications.

LOW POWER AND HIGH SPEED FLOATING POINT DIVIDER

Published Patent

The present invention describes custom designed Floating Point Divider algorithm according to IEEE-754 standard 32-bit single precision format using Verilog on Xilinx ISE 13.2. The salient feature of the proposed methodology is its simplicity and elegance in evaluating the mantissa and the exponent, yielding better computational speed, better power efficiency and consequently enhancing
the performance of the processor having this floating point divider scheme. For the computation of the sign part of the division, the
traditional method have been used. Hence the core objective is to integrate this suggested scheme of the floating point divider on FPGA using Verilog Hardware Description Language and to ascertain our claim of its being fast, effective and power efficient
simultaneously. Most specifically, the system is configured with five ports which are also consisting of four input and one output ports. The first two input ports intakes two numbers in IEEE-754 standard 32-bit single precision format as DIVIDEND and DIVISOR to be operated in division process and to produce the desired quotient (RESULT) consequently. The other two inputs CLOCK and RESET are utilized to synchronize as well as to reset and restart the system respectively. The divider will be implemented through FPGA board and the hardware a reconfigurable structure along with its economic benefits while also maintaining a competent clock
speed and a reasonable amount of low power consumption. Consequently, this developed arrangement upholds the dual advantage of superior output generation speed while keeping in mind the cost cutting obligations of the hardware system as well along with its capability to work in an environment with power constraints.

AN IMAGE FEATURE FUSION HARDWARE SYSTEM FOR FASTER CONVERGENCE OF CLASSIFICATION

Published Patent

The present invention describes an Image Feature Fusion Hardware System ( 3) for Faster Convergence of Classification which discloses a set of feature that is extracted from an image dataset using binarization and then the same image dataset is again exposed to morphological technique for feature extraction. More specifically the features have been concatenated to form a fused feature set and can be provided as input to a classifier for superior classification performance. The feasibility of the proposed technique is based on FPGA system. Two different image features are passed to the system and the system will normalize them to a certain scale and create a single ultimate feature. In an aspect of the invention, the Top-level block diagram that can interface with two features (Feature Set_1 and Set_2) with their respective input and will collect elements row-wise. The row-wise data will be saved into two different FIFO.
Based on the maximum and minimum value among the features, row-wise minimum and maximum value will be supplied to the
system. The system will accept inputs when accept pin will get a high value and when Accept _I/P pin input value is low the system
will start processing the data to get a single ultimate feature. After getting a single row value of both the features, the system will
normalize them to a certain scale and pass the data to decision making block to create a single ultimate feature. The decision making
block is again a FIFO which will concatenate both the normalized feature value, store them and pass them to output as single row-wise
feature. When the output will contain data values for further processing to other interfaces, the valid pin will produce high value as
acknowledgement of valid data otherwise it produce low value.

SCI/ SCI(E) PUBLICATIONS

• Das, R., & Walia, E. (2019). Partition selection with sparse autoencoders for content based image classification. Neural Computing and Applications, Springer, 31(3), 675-690, Springer Verlag, doi:10.1007/s00521-017-3099-0, I.F.: 4.213, (Thomson Reuters JCR (2018))

• Das, R., Thepade, S., & Ghosh, S. (2016). Framework for Content‐Based Image Identification with
  Standardized Multiview Features. ETRI Journal, 38(1), 174-184.
  http://dx.doi.org/10.4218/etrij.16.0115.0102 (Science Citation Indexed) I.F.: 1.116 (Thomson Reuters JCR (2016))

• Thepade, S., Das, R., & Ghosh, S. (2016). Block truncation coding with color clumps: A novel feature
  extraction technique for content based image classification. Sādhanā, 41(9), 939-958, Springer.
  (Science Citation Indexed (Expanded), Scopus etc.) I.F.: 0.465 (Thomson Reuters JCR (2016))

• Das, R., Thepade, S., & Ghosh, S. (2015). Multi technique amalgamation for enhanced information identification with content based image data. SpringerPlus, 4(1), 749, Springer.

EMERGING SOURCE CITATION INDEXED (ESCI) (WEB OF SCIENCE)
PUBLICATIONS

• Thepade, S. D., Abin, D., Das, R., & Sarode, T. (2020). Human face gender identification using Thepade's sorted N-ary block truncation coding and machine learning classifiers. International Journal of Intelligent Engineering Informatics, 8(2), 77-94. (Web of Science Indexed, ESCI, DBLP and ACM Digital Library)

•  Thepade, S., Das, R., & Ghosh, S. (2017). Decision fusion-based approach for content-based image classification. International Journal of Intelligent Computing and Cybernetics, 10(3), 310-331, Emerald Publishing (Web of Science Indexed, ESCI and Scopus Indexed)

•  Das, R., Thepade, S., Bhattacharya, S., & Ghosh, S. (2016). Retrieval architecture with classified query for content based image recognition. Applied Computational Intelligence and Soft Computing, http://dx.doi.org/10.1155/2016/1861247, Hindawi Publishing Corporation , (Web of Science Indexed, ESCI etc.)

•  Thepade, S., Das, R., & Ghosh, S. (2014). A novel feature extraction technique using binarization of bit planes for content based image classification. Journal of Engineering, http://dx.doi.org/10.1155/2014/439218, Hindawi Publishing Corporation,  (Web of Science Indexed, ESCI etc.)

SCOPUS INDEXED PUBLICATIONS

• Thepade, S., Ketan, J., Sange, S. & Das, R (2020) Covid19 Identification from Chest X-RAY using Local Binary Patterns and Multilayer Perceptrons. Journal of Critical Reviews, 7 (19), 4277-4285. doi:10.31838/jcr.07.19.502 (Scopus Indexed) 

• Das, R., Arshad, M., Manjhi, P.K. & Mahanta, H.S. (2019). Melanoma Identification with Content Based Image Classification using Bit Plane Features. International Journal of Innovative Technology and Exploring Engineering, 8(12), (pp. 3746-3749), Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP) (Scopus Indexed) 

• Das, R., De, S. & Thepade, S. (2019). Machine Learning in Hybrid Environment for Information Identification with Remotely Sensed Image Data. In Transactions on Computational Science, Springer, Berlin, Heidelberg (Accepted). (Scopus Indexed)

• Das, R., Thepade, S., & Ghosh, S. (2017). Novel feature extraction technique for content-based image recognition with query classification. International Journal of Computational Vision and Robotics, 7(1-2), 123-147,  Inderscience Publishers (IEL) (Scopus Indexed)

• Das, R., Thepade, S., & Ghosh, S. (2017). Decision Fusion for Classification of Content Based Image Data. In Transactions on Computational Science XXIX (pp. 121-138). Springer, Berlin, Heidelberg. (Scopus Indexed)

• Thepade, S., Das, R., & Ghosh, S. (2015). A novel feature extraction technique with binarization of significant bit information. International Journal of Imaging and Robotics™, 15(3), 164-178, CESER Publications (Scopus indexed)

• Thepade, S., Das, R., & Ghosh, S. (2015). Novel technique in block truncation coding based feature extraction for content based image identification. In Transactions on Computational Science XXV (pp. 55-76). Springer, Berlin, Heidelberg (Scopus Indexed)

BOOK CHAPTERS

• Das, R., De, S., & Singh, S.N. (2019). A Study of Recent Trends in Content Based Image Classification.
Intelligent Multimedia Data Analysis, 2, (pp. 65-94), De Gruyter, Germany.
• Das, R., Singh, S. N., Banerjee, M., Mayank, S., & Shashank, T. V. (2018). An Integrated Framework
for Information Identification With Image Data Using Multi-Technique Feature Extraction. In Feature
Dimension Reduction for Content-Based Image Identification (pp. 1-25). IGI Global
• Singh, S. N. & Das, R. (2018). Achieving Sustainable Development with Identification of Content
Based Remotely Sensed Image Data. In Leadership, Innovation and Management Education for a
Sustainable World, vol.-1, (pp. 127-140). Catholic Press, ISBN: 81-904112-1-7

OTHER INTERNATIONAL PUBLICATIONS

• Das, R., Thepade, S., & Ghosh, S.  (2015). Content based image recognition by information fusion with multiview features. International Journal of Information Technology and Computer Science, 7(10), 61- 73, MECS Publishers , DOI: 10.5815/ijitcs.2015.10.08

SELECTED CONFERENCE PUBLICATIONS

• Ganguly, A. Das, R., Setua, S. (2020, July). Histopathologival Image and Lymphoma Image Classification using Customized Deep Learning Models and Different Optimization Algorithms. In 2020 11th. International Conference on Computing, Communication and Networking Technologies (ICCCNT) , IIT Kharagpur (Accepted). IEEE. (Scopus Indexed)

• Das, R., Arshad, M., Manjhi, P.K. & Thepade, S. (2020, July). Improved Feature Generalization in Smaller Datasets with Early Feature Fusion of Handcrafted and Automated Features for Content Based Image Classification. In 2020 11th. International Conference on Computing, Communication and Networking Technologies (ICCCNT) , IIT Kharagpur (Accepted). IEEE. (Scopus Indexed)

• Das, R., Anurag, A., Jha, G.K. & Banerjee, M. (2020, October). Feature Dimension Reduction for Efficient Classification of Dermoscopic Images with Feature Fusion. In 2020, International Conference on Emerging Trends in Wireless Communication Technologies & Information Security (EWCIS) , Amity University, Jharkhand (Accepted). IEEE. (Scopus Indexed)

• Das, R., Kumari, K., Manjhi, P. K., & Thepade, S. D. (2019, December). Ensembling Handcarafted Features to Representation Learning for Content Based Image Classification. In 2019 IEEE Pune Section International Conference (PuneCon) (pp. 1-4). IEEE. (Scopus Indexed)

• Das, R., De, S., Bhattacharyya, S., Platos, J., Snasel, V., & Hassanien, A. E. (2019, March). Data Augmentation and Feature Fusion for Melanoma Detection with Content Based Image Classification. In International Conference on Advanced Machine Learning Technologies and Applications (pp. 712-721). Springer, Cham. (Scopus Indexed)

• Mukherjee, D., Das, R., Majumdar, S., Ghosh, S., Thepade, S., & Basu, A. (2019). Energy Efficient Face Recognition in Mobile-Fog Environment. Procedia Computer Science, 152, 274-281. (Scopus Indexed)

• Das, R., Ghosh, S., & Mukherjee, D. (2018, November). Bayesian Estimator Based Weather Forecasting using WSN. In 2018 3rd International Conference and Workshops on Recent Advances and Innovations in Engineering (ICRAIE) (pp. 1-4). IEEE. (Scopus Indexed)

• Jadhav, S. R., Das, R., Thepade, S. D., & De, S. (2018, August). Applications of Hybrid Machine Learning for Improved Content Based Image Classification. In 2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA) (pp. 1-6). IEEE. (Scopus Indexed)

•  Thepade, S. D., Sange, S., Das, R., & Luniya, S. Enhanced Image Classification with Feature Level Fusion of Niblack Thresholding and Thepade’s Sorted N-ary Block Truncation Coding using Ensemble of Machine Learning Algorithms. In 2018 IEEE Punecon (pp. 1-7). IEEE. (Scopus Indexed)

• Thepade, S., Das, R. and Ghosh, S. (2013, December). Performance comparison of feature vector extraction techniques in RGB color space using block truncation coding for content based image classification with discrete classifiers. In India Conference (INDICON), 2013 Annual IEEE (pp. 1-6). IEEE, December 13-15, 2013, IIT Mumbai, India (Scopus Indexed)

• Thepade, S. D., Das, R. & Ghosh, S. (2013, January). Image classification using advanced block truncation coding with ternary image maps. In Advances in Computing, Communication, and Control (pp. 500-509). Springer, Berlin, Heidelberg, Third International Conference, ICAC3 2013, January 18-19, 2013, Mumbai, India. (Scopus Indexed)

• Kekre, H. B., Thepade, S., Das, R. K. K. & Ghosh, S. (2013, January). Multilevel Block Truncation Coding with diverse color spaces for image classification. In Advances in Technology and Engineering (ICATE), 2013 International Conference on (pp. 1-7). IEEE, January 23-25, 2013, Mumbai, India 

AUTHORED BOOKS

• Das, R (2020). Content-Based Image Classification: Efficient Machine Learning using Robust Feature Extraction Techniques, CRC Press (Taylor and Francis Group). (In Press)

• Das, R and Kumari, K. (2017). Recent Trends and Techniques in Content Based Image Classification, ISBN: 978-620-2-02937-7, LAP LAMBERT ACADEMIC PUBLISHING.
• Das, R, Thepade, S and Bhattacharya, S. (2016). Ingenious Image Data for Digital Age Customer Contentment, ISBN: 978-3-659-81864-6, LAP LAMBERT ACADEMIC PUBLISHING.

EDITED VOLUMES

• Das, R, and Bhattacharya, S (Eds.). (2019).  Emerging Trends in Machine Learning Applications, ISBN: 978-3-11-061098-7, De Gruyter, Germany​

• Das, R, Banerjee, M and De, S (Eds.). (2019). Emerging Trends in Disruptive Technology Management for Sustainable Development, ISBN: 978-0-36-724964-9 CRC Press, Taylor and Francis.

• Das, R, De, S and Bhattacharya, S (Eds.). (2018). Feature Dimension Reduction for Content-Based Image Identification, IGI Global, Hershey, Pennsylvania, USA

PROGRAM COMMITTEE AND / OR TECHNICAL COMMITTEE MEMBER

GET IN TOUCH FOR

Invited Sessions and Speeches at Conferences, Webinars, FDPs, MDPs and other Events of Relevance
Training and Consultancies
Ph.D. Supervision
Research Writing Tips
Collaborative Research
Patent Ideas
Industry-Academia Collaboration
Career Guidance Suggestions

Xavier Institute of Social Service, Dr. Camil Bulcke Path, Ranchi
PIN : 834001
Jharkhand, India

rikdas78@gmail.com

+91 7992339074