Saikat Mukherjee

ORCID: 0000-0002-4637-445X
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Web Data Mining and Analysis
  • Algorithms and Data Compression
  • Distributed and Parallel Computing Systems
  • Semantic Web and Ontologies
  • Optimization and Search Problems
  • Distributed systems and fault tolerance
  • Service-Oriented Architecture and Web Services
  • Peer-to-Peer Network Technologies
  • Advanced Database Systems and Queries
  • Cloud Computing and Resource Management
  • Data Management and Algorithms
  • Image Retrieval and Classification Techniques
  • Natural Language Processing Techniques
  • Biomedical Text Mining and Ontologies
  • Software Engineering Research
  • Digital Accessibility for Disabilities
  • COVID-19 diagnosis using AI
  • Caching and Content Delivery
  • Text and Document Classification Technologies
  • Auction Theory and Applications
  • Graph Theory and Algorithms
  • Advanced Software Engineering Methodologies
  • Machine Learning and Algorithms
  • Access Control and Trust
  • Mathematics, Computing, and Information Processing

Hewlett Packard Enterprise (United States)
2020-2021

Intuit (United States)
2021

Hewlett-Packard (India)
2013-2020

Tata Consultancy Services (India)
2019

International Institute of Information Technology
2010-2013

Christ University
2013

Siemens (United States)
2007-2010

Siemens (Germany)
2006-2009

International Institute of Information Technology Bangalore
2006-2009

Stony Brook University
2002-2006

Stefanie Warnat‐Herresthal Hartmut Schultze Krishnaprasad Lingadahalli Shastry Sathyanarayanan Manamohan Saikat Mukherjee and 95 more Vishesh Garg Ravi Sarveswara Kristian Händler Peter Pickkers N. Ahmad Aziz Sofia Ira Ktena Florian Tran Michael Bitzer Stephan Ossowski Nicolas Casadei Christian Herr Daniel Petersheim Uta Behrends Fabian Kern Tobias Fehlmann Philipp Schommers Clara Lehmann Max Augustin Jan Rybniker Janine Altmüller Neha Mishra Joana P. Bernardes Benjamin Krämer Lorenzo Bonaguro Jonas Schulte-Schrepping Elena De Domenico Christian Siever Michael Kraut Milind Y. Desai Bruno Monnet Maria Saridaki Charles Siegel Anna Drews Melanie Nuesch-Germano Heidi Theis Jan Heyckendorf Stefan Schreiber Sarah Kim-Hellmuth Paul Balfanz Thomas Eggermann Peter Boor Ralf Hausmann Hannah Kuhn Susanne Isfort Julia C. Stingl Günther Schmalzing Christiane Kühl Rainer Röhrig Gernot Marx Stefan Uhlig Edgar Dahl Dirk Müller‐Wieland Michael Dreher Nikolaus Marx Jacob Nattermann Dirk Skowasch Ingo Kurth Andreas Keller Robert Bals Peter Nürnberg Olaf Rieß Philip Rosenstiel Mihai G. Netea Fabian J. Theis Sach Mukherjee Michael Backes Anna C. Aschenbrenner Thomas Ulas Angel Angelov Alexander Bartholomäus Anke Becker Daniela Bezdan Conny Blumert Ezio Bonifacio Peer Bork Boyke Bunk Helmut Blum Thomas Clavel Maria Colomé‐Tatché Markus Cornberg Inti Alberto De La Rosa Velázquez Andreas Diefenbach Alexander Dilthey Nicole Fischer Konrad U. Förstner Sören Franzenburg Julia-Stefanie Frick Gisela Gabernet Julien Gagneur Tina Ganzenmueller Marie Gauder Janina Geißert Alexander Goesmann Siri Göpel Adam Grundhoff

Fast and reliable detection of patients with severe heterogeneous illnesses is a major goal precision medicine1,2. Patients leukaemia can be identified using machine learning on the basis their blood transcriptomes3. However, there an increasing divide between what technically possible allowed, because privacy legislation4,5. Here, to facilitate integration any medical data from owner worldwide without violating laws, we introduce Swarm Learning-a decentralized machine-learning approach that...

10.1038/s41586-021-03583-3 article EN cc-by Nature 2021-05-26

Diagnosis and treatment planning for patients can be significantly improved by comparing with clinical images of other similar anatomical pathological characteristics. This requires the to annotated using common vocabulary from ontologies. Current approaches such annotation are typically manual, consuming extensive clinician time, cannot scaled large amounts imaging data in hospitals. On hand, automated image analysis while being very scalable do not leverage standardized semantics thus used...

10.1117/12.844207 article EN Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE 2010-03-04

With the development of information technology, a large volume data is growing and getting stored electronically.Thus, volumes processing by many applications will routinely cross petabyte threshold range, in that case it would increase computational requirements.Efficient algorithms implementation techniques are key meeting scalability performance requirements such scientific analyses.So for same here, has been analyzed with various MapReduce Programs parallel clustering algorithm (PKMeans)...

10.5120/12518-9099 article EN International Journal of Computer Applications 2013-06-26

Abstract Identification of patients with life-threatening diseases including leukemias or infections such as tuberculosis and COVID-19 is an important goal precision medicine. We recently illustrated that leukemia are identified by machine learning (ML) based on their blood transcriptomes. However, there increasing divide between what technically possible allowed because privacy legislation. To facilitate integration any omics data from owner world-wide without violating laws, we here...

10.1101/2020.06.25.171009 preprint EN cc-by-nc-nd bioRxiv (Cold Spring Harbor Laboratory) 2020-06-26

Template-driven HTML documents possess an implicit, fixed schema denoting concepts and their relationships in a hierarchical fashion. Discovering this remains relatively unexplored problem. By exploiting key observation that semantically related items exhibit spatial locality, we develop algorithm for automatically partitioning them into tree-like semantic structures which expose the implicit schema.

10.1109/icdar.2003.1227667 article EN 2004-03-01

Enormous amount of semantic data is still being encoded in HTML documents. Identifying and annotating the concepts implicit such documents makes them directly amenable for Web processing. In this paper we describe a highly automated technique documents, especially template-based content-rich containing many different per document. Starting with (small) seed hand-labeled instances set bootstrap an annotation process that automatically identifies unlabeled concept present other The...

10.1109/icde.2005.28 article EN 2005-04-19

Quantifiability is a concept in MapReduce Analytics based on the following two conditions: (a) mapper should be cautious, that is, not exclude any reducer's shuffle and sort strategy from consideration; (b) respect reducers' preferences, deem k i infinitely more likely than k' if it premises reducer to prefer .A quantifiable can optimally chosen under common conjecture events (b).In this paper we present an algorithm for every finite operation computes set of all strategies.The new idea...

10.5120/13741-1551 article EN International Journal of Computer Applications 2013-10-18

This paper represents a design and implementation of Wireless Heart rate monitor system using ARDUINO Lilypad which is enabled with the feature sending SOS messages or calls through GSM module. Upon monitoring if abnormal conditions arise, call-ring (for 5 sec) message (customized message) will be sent to predefined mobile number depending upon how bad situation is. There are two parts whole process, transmitting circuit receiving circuit. The most important part (the transmitter section)...

10.1109/vitecon.2019.8899504 article EN 2019 International Conference on Vision Towards Emerging Trends in Communication and Networking (ViTECoN) 2019-03-01

Actual Quantifiability is a concept in MapReduce that based on two assumptions: (1) every mapper cautious, i.e., does not exclude any reducer's key-value split pattern choice from consideration, and (2) respects the preferences, deems one to be infinitely more likely than another whenever it premises reducer prefer other.In this paper we provide new approach for actual quantifiability, by assuming mappers have asymmetric about utilities.We show that, if uncertainty of each utilities vanishes...

10.5120/15023-3311 article EN International Journal of Computer Applications 2014-01-16

The enormous volume of medical images and the complexity clinical information systems make searching for relevant a challenging task. We describe techniques annotating using ontological semantic concepts. In contrast to extant multimedia annotation work, our technique uses context from mappings between multiple ontologies constrain space quickly identify have implemented system FMA RadLex anatomical ontologies, ICD disease taxonomy, coupled with DICOM standard easy deployment in current PAC...

10.5220/0001550202940299 article EN 2009-01-01

Bookmarks are shortcuts that enable quick access of the desired Web content. They have become a standard feature in any browser and recent studies shown they can be very useful for non-visual as well. Current bookmarking techniques assistive browsers rigidly tied to structure pages. Consequently susceptible even slight changes In this paper we propose <i>semantic bookmarking</i> access. With help an ontology represents concepts domain, content pages semantically associated with bookmarks. As...

10.1145/1028630.1028663 article EN 2003-09-01

Online transactions (e.g., buying a book on the Web) typically involve number of steps spanning several pages. Conducting such under constrained interaction modalities as exemplified by small screen handhelds or interactive speech interfaces - primary mode communication for visually impaired individuals is strenuous, fatigue-inducing activity. But usually one needs to browse only fragment Web page perform transactional step form fillout, selecting an item from search results list, etc. We...

10.1145/1135777.1135843 article EN 2006-05-23

For the rapid increase in resource requirements large scale Data Centers (DCs), enterprises have brought hyperconverged architecture where storage pool is built up by individual components associated with different servers, and it shared among all Virtual Machines (VMs) or containers through a common network infrastructure. Due to sharing of bandwidth application generated traffic from infrastructure, quality service (QoS) performances networking intensive applications are affected, which...

10.1109/tcc.2020.2969154 article EN IEEE Transactions on Cloud Computing 2020-01-23

Online transactions (e.g., buying a book on the Web) typically involve number of steps spanning several pages. Conducting such under constrained interaction modalities as exemplified by small screen handhelds or interactive speech interfaces—the primary mode communication for visually impaired individuals—is strenuous, fatigue-inducing activity. But usually one needs to browse only fragment Web page perform transactional step form fillout, selecting an item from search results list, and so...

10.1145/1281480.1281482 article EN ACM Transactions on the Web 2007-09-01

Focused Web browsing activities such as periodically looking up headline news, weather reports, etc., which require only selective fragments of particular pages, can be made more efficient for users limited-display-size handheld mobile devices by delivering the target fragments. Semantic bookmarks provide a robust conceptual framework recording and retrieving targeted content not from specific pages used in creating but also any user-specified page with similar semantics. This paper...

10.1145/1060745.1060832 article EN 2005-01-01

Query optimization in sensor grids have two major challenges: (a) optimizing a multi-query environment, and (b) continuous re-optimization occurring due to new query registrations de-queries, i.e. queries being stopped unexpectedly. Addressing this problem continuously on system-wide basis is an infeasible option. In work called EstuaryDB, we propose notion of emergent optimization, where globally optimal configurations emerge as result number local autonomous decisions carried out...

10.1109/cec.2007.4424543 article EN 2007-09-01

The Web has established itself as the dominant medium for doing electronic commerce. Consequently number of service providers, both large and small, advertising their services on web continues to proliferate. In this paper we describe new extraction algorithms mining directories from pages. We develop a novel propagation technique identifying accumulating all attributes related entity in page. provide experimental results effectiveness our techniques by database veterinarian providers sources.

10.1109/icdm.2002.1184008 article EN 2003-06-26
Coming Soon ...