A5101420427- Distributed and Parallel Computing Systems
- Scientific Computing and Data Management
- Advanced Data Storage Technologies
- Cloud Computing and Resource Management
- Particle physics theoretical and experimental studies
- IoT and Edge/Fog Computing
- Advanced Database Systems and Queries
- High-Energy Particle Collisions Research
- Data Management and Algorithms
- Web Data Mining and Analysis
- Data Mining Algorithms and Applications
- Mobile Ad Hoc Networks
- Quantum Chromodynamics and Particle Interactions
- Simulation Techniques and Applications
- Energy Efficient Wireless Sensor Networks
- Opportunistic and Delay-Tolerant Networks
- Big Data and Business Intelligence
- Scheduling and Optimization Algorithms
- Graph Theory and Algorithms
- Energy Harvesting in Wireless Networks
- Service-Oriented Architecture and Web Services
- Web Applications and Data Management
- Smart Parking Systems Research
- Artificial Intelligence in Healthcare
- Advanced Neural Network Applications
Amazon (United States)
2019-2022
Seattle University
2020
Biju Patnaik University of Technology
2018-2019
Winbond (Taiwan)
2018
University of California, San Diego
2008-2014
Utkal University
2011
European Organization for Nuclear Research
2008
University of Wisconsin–Madison
2007
Deutsches Elektronen-Synchrotron DESY
2004
Grid computing has become very popular in big and widespread scientific communities with high demands, like energy physics. Computing resources are being distributed over many independent sites only a thin layer of grid middleware shared between them. This deployment model proven to be convenient for resource providers, but introduced several problems the users system, three major complexity job scheduling, non-uniformity compute resources, lack good monitoring. Pilot jobs address all above...
We present state-of-the-art cross section predictions for the production of supersymmetric squarks and gluinos at upcoming LHC run with a centre-of-mass energy $$\sqrt{s} = 13$$ $$14$$ TeV, potential future $$pp$$ colliders operating 33$$ $$100$$ TeV. The results are based on calculations which include resummation soft-gluon emission next-to-leading logarithmic accuracy, matched to order QCD corrections. Furthermore, we provide an estimate theoretical uncertainty due variation...
This document emerged from work that started in January 2012 as a joint effort by the ATLAS, CMS and LPCC supersymmetry (SUSY) working groups to compile state-of-the-art cross section predictions for SUSY particle production at LHC. We present sections various processes pp collisions $\sqrt{s} =7$ TeV, including an estimate of theoretical uncertainty due scale variation parton distribution functions. Further results higher LHC centre-of-mass energies will be collected...
As the size of web increases along with number users, it is very much essential for website owners to better understand their customers so that they can provide service, and also enhance quality website. To achieve this depend on access log files. The files be mined extract interesting pattern user behaviour understood. This paper presents an overview usage mining provides a survey extraction algorithms used mining.
Machine learning (ML) has been embedded in many Internet of Things (IoT) applications (e.g., smart home and autonomous driving). Yet it is often infeasible to deploy ML models on IoT devices due resource limitation. Thus, deploying trained the cloud providing inference services becomes a plausible solution. To provide low-latency serving massive devices, natural promising approach use parallelism computation. However, existing systems Tensorflow) ML-serving platforms SageMaker) are...
Physicists have access to thousands of CPUs in grid federations such as OSG and EGEE. With the start-up LHC, it is essential for individuals or groups users wrap together available resources from multiple sites across grids under a higher user-controlled layer order provide homogeneous pool resources. One system glideinWMS, which based on Condor batch system. A general discussion glideinWMS can be found elsewhere. Here, we focus recent advances extending its reach: scalability integration...
The computing system of the CMS experiment uses distributed resources from more than 60 centres worldwide. Located in Europe, America and Asia, these are interconnected by Worldwide LHC Computing Grid. operation requires a stable reliable behavior underlying infrastructure. has established procedure to extensively test all relevant aspects Grid site, such as ability efficiently use their network transfer data, services for capability sustain various workflows (Monte Carlo simulation, event...
A major limitation for time-to-science can be the lack of available computing resources. Depending on capacity resources, executing an application suite with hundreds thousands jobs take weeks when resources are in high demand. We describe how we dynamically provision a large scale performance cluster more than one million cores utilizing Amazon Web Services (AWS). discuss trade-offs, challenges, and solutions associated creating such commercial cloud utilize our to study parameter sweep...
Snowmass is a US long-term planning study for the high-energy community by American Physical Society's Division of Particles and Fields. For its simulation studies, opportunistic resources are harnessed using Open Science Grid infrastructure. Late binding grid technology, GlideinWMS, was used distributed scheduling jobs across many sites mainly in US. The pilot infrastructure also uses Parrot mechanism to dynamically access CvmFS order ascertain homogeneous environment nodes. This report...
In preparation for first data at the LHC, a series of Data Challenges, increasing scale and complexity, have been performed. Large quantities simulated produced on three different Grids, integrated into ATLAS production system. During 2006, emphasis moved towards providing stable continuous production, as is required in immediate run-up to data, thereafter. Here, we discuss experience done EGEE resources, using submission based gLite WMS, CondorG system Condor Glide-ins. The overall walltime...
Machine learning enjoys widespread success in High Energy Physics (HEP) analyses at LHC. However the ambitious HL-LHC program will require much more computing resources next two decades. Quantum may offer speed-up for HEP physics HL-LHC, and can be a new computational paradigm big data Physics. We have successfully employed three methods (1) Variational Classifier (VQC) method, (2) Support Vector Kernel (QSVM-kernel) method (3) Neural Network (QNN) LHC flagship analyses: ttH (Higgs...
In terms of the gLite middleware, current LCG-CE used by four LHC experiments is about to be deprecated. The new CREAM-CE service (Computing Resource Execution And Management) has been approved replace previous service. a lightweight created handle job management operations at CE level. It able accept requests both via WMS and also direct submission for transmission local batch system.
Condor glidein-based workload management system (glideinWMS) has been developed and integrated with distributed physics analysis Monte Carlo (MC) production at Compact Muon Solenoid (CMS) experiment. The late-binding between the jobs computing element (CE), validation of WorkerNode (WN) environment help significantly reduce failure rate Grid jobs. For CPU-consuming MC data production, opportunistic grid resources can be effectively explored via extended pool built on top various...
Considerable Progress has been made in the last few years improving performance of distributed database systems. The development Fragment allocation models Distributed is becoming difficult due to complexity huge number sites and their communication considerations. Under such conditions, simulation clustering data adequate tools for understanding evaluating databases. Clustering fragment are key challenges performance, considered be efficient methods that have a major role reducing...
Data mining is a part of know ledge Discovery in database process (KDD). As technology advances, floods data can be produced and shared many appliances such as wireless Sensor networks or Web click streams. This calls for extracting useful information knowledge from streams data. In this paper, We have proposed an efficient algorithm, where, at any time the current frequencies all frequent item sets immediately produced. The frequency set stream defined its maximal over possible windows...
This paper presents a web-based Job Monitoring framework for individual Grid sites that allows users to follow in detail their jobs quasi-real time. The consists of several independent components : (a) set sensors run on the site CE and worker nodes update database, (b) simple yet extensible web services (c) an Ajax powered interface having look-and-feel control similar desktop application. monitoring supports LSF, Condor PBS-like batch systems. is one first systems where X.509 authenticated...
The network scalability can be achieved by grouping sensor nodes into a clustering hierarchy. Cluster head is referred as the leader of every cluster. In order to achieve stable for mobile environments many schemes are used Wireless Sensor Network. this paper, we have proposed an extension Low Energy Adaptive Head protocol namely energy efficient mechanism wireless with symmetric cluster formation which known Highest Clustering Hierarchy (HECH) protocol. Mathematical simulation studies show...