48 results
Search Results
2. Charged Track Reconstruction with Artificial Intelligence for CLAS12.
- Author
-
Gavalian, Gagik, Thomadakis, Polykarpos, Angelopoulos, Angelos, and Chrisochoides, Nikos
- Subjects
ARTIFICIAL intelligence ,ARTIFICIAL neural networks ,DRIFT chambers ,PARTICLE detectors ,MULTILAYER perceptrons - Abstract
In this paper, we present the results of charged particle track reconstruction in CLAS12 using artificial intelligence. In our approach, we use neural networks working together to identify tracks based on the raw signals in the Drift Chambers. A Convolutional Auto-Encoder is used to de-noise raw data by removing the hits that do not satisfy the patterns for tracks, and second Multi-Layer Perceptron is used to identify tracks from combinations of clusters in the drift chambers. Our method increases the tracking efficiency by 50% for multi-particle final states already conducted experiments. The de-noising results indicate that future experiments can run at higher luminosity without degradation of the data quality. This in turn will lead to significant benefits for the CLAS12 physics program. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
3. Predicting Resource Utilization Trends with Southern California Petabyte Scale Cache.
- Author
-
Sim, Caitlin, Wu, Kesheng, Sim, Alex, Monga, Inder, Guok, Chin, Hazen, Damian, Würthwein, Frank, Davila, Diego, Newman, Harvey, and Balcas, Justas
- Subjects
PHYSICS ,PHYSICAL sciences ,MACHINE learning ,ARTIFICIAL intelligence ,TIME series analysis - Abstract
Large community of high-energy physicists share their data all around world making it necessary to ship a large number of files over wide- area networks. Regional disk caches such as the Southern California Petabyte Scale Cache have been deployed to reduce the data access latency. We observe that about 94% of the requested data volume were served from this cache, without remote transfers, between Sep. 2022 and July 2023. In this paper, we show the predictability of the resource utilization by exploring the trends of recent cache usage. The time series based prediction is made with a machine learning approach and the prediction errors are small relative to the variation in the input data. This work would help understanding the characteristics of the resource utilization and plan for additional deployments of caches in the future. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
4. FAIR AI Models in High Energy Physics.
- Author
-
Li, Haoyang, Duarte, Javier, Roy, Avik, Zhu, Ruike, Huerta, E. A., Diaz, Daniel, Harris, Philip, Kansal, Raghav, Katz, Daniel S., Kavoori, Ishaan H., Kindratenko, Volodymyr V., Mokhtar, Farouk, Neubauer, Mark S., Park, Sang Eon, Quinnan, Melissa, Rusack, Roger, and Zhao, Zhizhen
- Subjects
- *
PARTICLE physics , *ARTIFICIAL intelligence , *MACHINE learning , *DATA modeling , *ARTIFICIAL neural networks - Abstract
The findable, accessible, interoperable, and reusable (FAIR) data principles serve as a framework for examining, evaluating, and improving data sharing to advance scientific endeavors. There is an emerging trend to adapt these principles for machine learning models—algorithms that learn from data without specific coding—and, more generally, AI models, due to AI's swiftly growing impact on scientific and engineering sectors. In this paper, we propose a practical definition of the FAIR principles for AI models and provide a template program for their adoption. We exemplify this strategy with an implementation from high-energy physics, where a graph neural network is employed to detect Higgs bosons decaying into two bottom quarks. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
5. Accelerate Scientific Deep Learning Models on Heterogeneous Computing Platform with FPGA.
- Author
-
Doglioni, C., Kim, D., Stewart, G.A., Silvestris, L., Jackson, P., Kamleh, W., Jiang, Chao, Ojika, David, Vallecorsa, Sofia, Kurth, Thorsten, Prabhat, Patel, Bhavesh, and Lam, Herman
- Subjects
DEEP learning ,ARTIFICIAL intelligence ,HETEROGENEOUS computing ,SOFTWARE analytics ,BIG data - Abstract
AI and deep learning are experiencing explosive growth in almost every domain involving analysis of big data. Deep learning using Deep Neural Networks (DNNs) has shown great promise for such scientific data analysis applications. However, traditional CPU-based sequential computing without special instructions can no longer meet the requirements of mission-critical applications, which are compute-intensive and require low latency and high throughput. Heterogeneous computing (HGC), with CPUs integrated with GPUs, FPGAs, and other science-targeted accelerators, offers unique capabilities to accelerate DNNs. Collaborating researchers at SHREC
1 at the University of Florida, CERN Openlab, NERSC2 at Lawrence Berkeley National Lab, Dell EMC, and Intel are studying the application of heterogeneous computing (HGC) to scientific problems using DNN models. This paper focuses on the use of FPGAs to accelerate the inferencing stage of the HGC workflow. We present case studies and results in inferencing state-of-the-art DNN models for scientific data analysis, using Intel distribution of OpenVINO, running on an Intel Programmable Acceleration Card (PAC) equipped with an Arria 10 GX FPGA. Using the Intel Deep Learning Acceleration (DLA) development suite to optimize existing FPGA primitives and develop new ones, we were able accelerate the scientific DNN models under study with a speedup from 2.46x to 9.59x for a single Arria 10 FPGA against a single core (single thread) of a server-class Skylake CPU. [ABSTRACT FROM AUTHOR]- Published
- 2020
- Full Text
- View/download PDF
6. Research and Evaluation of RoCE in IHEP Data Center.
- Author
-
Zeng, Shan, Qi, Fazhi, Han, Lei, Gong, Xiangyu, and Wu, Tao
- Subjects
COMPUTER operating systems ,ARTIFICIAL intelligence ,MESSAGE passing (Computer science) ,CLOUD computing ,INFINIBAND (Standard) ,COMPUTER input-output equipment standards - Abstract
With more and more large-scale scientific facilities are built, more and more HPC requirements are needed in IHEP. RDMA is a technology that allows servers in a network to exchange data in main memory without involving the processor, cache or operating system of either server, which can provide high bandwidth and low latency. There are two RDMA technologies which were InfiniBand and a relative newcomer called RoCE – RDMA over Converged Ethernet. This paper introduces the RoCE technology, we research and compare the performance of both IB and RoCE in IHEP data center, and we also evaluate the application scenarios of RoCE which can support our future technology selection in HEPS. In the end, we present our future plan. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
7. Improving the Learning Power of Artificial Intelligence Using Multimodal Deep Learning.
- Author
-
Nadykto, A., Aleksic, N., Lima, P., Pivkin, P., Uvarova, L., Jiang, X., Zelensky, A., Shchetinin, Eugene Yu., and Sevastianov, Leonid
- Subjects
ARTIFICIAL intelligence ,DEEP learning ,PARALINGUISTICS ,EMOTION recognition ,ARTIFICIAL neural networks - Abstract
Computer paralinguistic analysis is widely used in security systems, biometric research, call centers and banks. Paralinguistic models estimate different physical properties of voice, such as pitch, intensity, formants and harmonics to classify emotions. The main goal is to find such features that would be robust to outliers and will retain variety of human voice properties at the same time. Moreover, the model used must be able to estimate features on a time scale for an effective analysis of voice variability. In this paper a paralinguistic model based on Bidirectional Long Short-Term Memory (BLSTM) neural network is described, which was trained for vocal-based emotion recognition. The main advantage of this network architecture is that each module of the network consists of several interconnected layers, providing the ability to recognize flexible long-term dependencies in data, which is important in context of vocal analysis. We explain the architecture of a bidirectional neural network model, its main advantages over regular neural networks and compare experimental results of BLSTM network with other models. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
8. A versatile multi-objective FLUKA optimization using Genetic Algorithms.
- Author
-
Vlachoudis, Vasilis, Antoniucci, Guido Arnau, Mathot, Serge, Kozlowska, Wioletta Sandra, and Vretenar, Maurizio
- Subjects
GENETIC algorithms ,MONTE Carlo method ,NUMERICAL analysis ,ARTIFICIAL intelligence ,ALLELES ,GENETIC mutation - Abstract
Quite often Monte Carlo simulation studies require a multi phase-space optimization, a complicated task, heavily relying on the operator experience and judgment. Examples of such calculations are shielding calculations with stringent conditions in the cost, in residual dose, material properties and space available, or in the medical field optimizing the dose delivered to a patient under a hadron treatment. The present paper describes our implementation inside flair[1] the advanced user interface of FLUKA[2,3] of a multi-objective Genetic Algorithm[Erreur ! Source du renvoi introuvable.] to facilitate the search for the optimum solution. [ABSTRACT FROM AUTHOR]
- Published
- 2017
- Full Text
- View/download PDF
9. Computing within the 2021 Snowmass process.
- Author
-
Elvira, V. Daniel
- Subjects
PARTICLE physics ,HETEROGENEOUS computing ,ARTIFICIAL intelligence ,QUANTUM computing ,MACHINE learning - Abstract
We present different elements of the 2021–2022 Computational Frontier (CompF) effort within the Snowmass process, including organization, events, and highlights of the final report [1]. With focus in the next 10–15 years, we analyze the impact of newly established and emerging technologies, identify challenges within theoretical, experimental and observational research programs, and present the report recommendations. We emphasize the main recommendation, which is the formation of a Coordinating Panel for Software and Computing (CPSC). [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
10. Towards High-Performance AI4NP Applications on Modern GPU Platforms.
- Author
-
Mei, Xinxin, Brei, Nathan, and Lawrence, David
- Subjects
GRAPHICS processing units ,ARTIFICIAL intelligence ,NUCLEAR physics ,MULTILAYER perceptrons ,ARTIFICIAL neural networks - Abstract
The evolution of modern heterogeneous accelerators, such as GPUs, has significantly advanced the landscape of artificial intelligence (AI). There is a notable surge to adopt AI within the nuclear physics domain (AI4NP). While most AI4NP studies focus on feasibility analysis, our attention is directed towards evaluating their performance on contemporary GPUs that integrate tensor cores. We first benchmark the throughput of hyperparameterized multi-layer perceptron (MLP) models. We then examine the performance of an AI4NP application: Hydra. We assess the performance gain and accuracy loss caused by the tensor cores for low-precision floating-point operations. Our experiments encompass the PyTorch and TensorFlow Keras frameworks on NVIDIA's T4 and A100 GPUs. We explore the behavior of different GPU hardware platforms and AI software tools. This study can be a valuable resource for guiding the performance optimization of larger-scale deployments of AI4NP applications. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
11. A method for inferring signal strength modifiers by conditional invertible neural networks.
- Author
-
Farkas, Máté Zoltán, Diekmann, Svenja, Eich, Niclas, and Erdmann, Martin
- Subjects
ARTIFICIAL neural networks ,PARTICLE physics ,COLLIDERS (Nuclear physics) ,PARTICLE detectors ,ARTIFICIAL intelligence - Abstract
The continuous growth in model complexity in high-energy physics (HEP) collider experiments demands increasingly time-consuming model fits. We show first results on the application of conditional invertible networks (cINNs) to this challenge. Specifically, we construct and train a cINN to learn the mapping from signal strength modifiers to observables and its inverse. The resulting network infers the posterior distribution of the signal strength modifiers rapidly and for low computational cost. We present performance indicators of such a setup including the treatment of systematic uncertainties. Additionally, we highlight the features of cINNs estimating the signal strength for a vector boson associated Higgs production analysis of simulated samples of events, which include a simulation of the CMS detector. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
12. Data Management Package for the novel data delivery system, ServiceX, and Applications to various physics analysis workflows.
- Author
-
Choi, KyungEon and Onyisi, Peter
- Subjects
DATA management ,PHYSICS ,PHYSICAL sciences ,MACHINE learning ,ARTIFICIAL intelligence - Abstract
Recent developments of HEP software allow novel approaches to physics analysis workflows. The novel data delivery system, ServiceX, can be very effective when accessing a fraction of large datasets at remote grid sites. ServiceX can deliver user-selected columns with filtering and run at scale. We introduce the ServiceX data management package, ServiceX DataBinder, for easy manipulations of ServiceX delivery requests and delivered data using a single configuration file. We show various practical use cases within analysis pipelines that range from a data delivery of a few columns for machine learning study to a data delivery for full-scale physics analysis. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
13. AI Enabled Data Quality Monitoring with Hydra.
- Author
-
Britton, Thomas, Lawrence, David, and Rajput, Kishansingh
- Subjects
- *
DATA quality , *ARTIFICIAL intelligence , *NUCLEAR physics experiments , *DATA acquisition systems , *PHOTOMULTIPLIERS - Abstract
Data quality monitoring is critical to all experiments impacting the quality of any physics results. Traditionally, this is done through an alarm system, which detects low level faults, leaving higher level monitoring to human crews. Artificial Intelligence is beginning to find its way into scientific applications, but comes with difficulties, relying on the acquisition of new skill sets, either through education or acquisition, in data science. This paper will discuss the development and deployment of the Hydra monitoring system in production at Gluex. It will show how "off-the-shelf" technologies can be rapidly developed, as well as discuss what sociological hurdles must be overcome to successfully deploy such a system. Early results from production running of Hydra will also be shared as well as a future outlook for development of Hydra. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
14. Deep Learning Methods On Neutron Scattering Data.
- Author
-
Lyoussi, A., Giot, M., Carette, M., Jenčič, I., Reynard-Carette, C., Vermeeren, L., Snoj, L., Le Dû, P., Song, Guanghan, Porcar, Lionel, Boehm, Martin, Cecillon, Franck, Dewhurst, Charles, Le Goc, Yannick, Locatelli, Jérome, Mutti, Paolo, and Weber, Tobias
- Subjects
- *
DEEP learning , *NEUTRON scattering , *ARTIFICIAL intelligence , *IMAGE analysis , *DATA analysis - Abstract
Recently, by using deep learning methods, a computer is able to surpass or come close to matching human performance on image analysis and recognition. This advanced methods could also help extracting features from neutron scattering experimental data. Those data contain rich scientific information about structure and dynamics of materials under investigation. Deep learning could help researchers better understand the link between experimental data and materials properties. Moreover,it could also help to optimize neutron scattering experiment by predicting the best possible instrument configuration. Among all possible experimental methods, we begin our study on the small-angle neutron scattering (SANS) data and by predicting the structure geometry of the sample material at an early stage. This step is a keystone to predict the experimental parameters to properly setup the instrument as well as the best measurement strategy. In this paper, we propose to use transfer learning to retrain a convolutional neural networks (CNNs) based pre rained model to adapt the scattering images classification, which could predict the structure of the materials at an early stage in the SANS experiment. This deep neural network is trained and validated on simulated database, and tested on real scattering images. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
15. Expert System For Diagnosis Pest And Disease In Fruit Plants.
- Author
-
Dewanto, Satrio and Lukas, Jonathan
- Subjects
EXPERT systems ,FRUIT diseases & pests ,DIAGNOSIS of plant diseases ,ARTIFICIAL intelligence ,COMPUTER software - Abstract
This paper discussed the development of an expert system to diagnose pests and diseases on fruit plants. Rule base method was used to store the knowledge from experts and literatures. Control technique using backward chain and started from the symptoms to get conclusions about the pests and diseases that occur. Development of the system has been performed using software Corvid Exsys developed by Exsys company. Results showed that the development of this expert system can be used to assist users in identifying the type of pests and diseases on fruit plants. Further development and possibility of using internet for this system are proposed. [ABSTRACT FROM AUTHOR]
- Published
- 2014
- Full Text
- View/download PDF
16. Convolutional neural network optimisation to enhance ESPI fringe visibility.
- Author
-
Crespo, J.M. and Moreno, V.
- Subjects
- *
CONVOLUTIONAL neural networks , *INTERFEROMETRY , *ARTIFICIAL intelligence , *DATA visualization , *SIGNAL denoising - Abstract
The use of convolutional neuronal networks (CNN) for the treatment of interferometric fringes has been introduced in recent years. In this paper, we optimize and build a CNN model, based U-NET architecture, to maximize its performance processing electronic speckle interferometry fringes (ESPI). [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
17. Large-scale HPC deployment of Scalable CyberInfrastructure for Artificial Intelligence and Likelihood Free Inference (SCAILFIN).
- Author
-
Doglioni, C., Kim, D., Stewart, G.A., Silvestris, L., Jackson, P., Kamleh, W., Hildreth, Michael, Paolo Hurtado Anampa, Kenyi, Kankel, Cody, Hampton, Scott, Brenner, Paul, Johnson, Irena, and Simko, Tibor
- Subjects
ARTIFICIAL intelligence ,CYBERINFRASTRUCTURE ,REPRODUCIBLE research ,HIGH performance computing ,WORKFLOW management systems - Abstract
The NSF-funded Scalable CyberInfrastructure for Artificial Intelligence and Likelihood Free Inference (SCAILFIN) project aims to develop and deploy artificial intelligence (AI) and likelihood-free inference (LFI) techniques and software using scalable cyberinfrastructure (CI) built on top of existing CI elements. Specifically, the project has extended the CERN-based REANA framework, a cloud-based data analysis platform deployed on top of Kubernetes clusters that was originally designed to enable analysis reusability and reproducibility. REANA is capable of orchestrating extremely complicated multi-step workflows, and uses Kubernetes clusters both for scheduling and distributing container-based workloads across a cluster of available machines, as well as instantiating and monitoring the concrete workloads themselves. This work describes the challenges and development efforts involved in extending REANA and the components that were developed in order to enable large scale deployment on High Performance Computing (HPC) resources. Using the Virtual Clusters for Community Computation (VC3) infrastructure as a starting point, we implemented REANA to work with a number of differing workload managers, including both high performance and high throughput, while simultaneously removing REANA's dependence on Kubernetes support at the workers level. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
18. Trends in computing technologies and markets: The HEPiX TechWatch WG.
- Author
-
Doglioni, C., Kim, D., Stewart, G.A., Silvestris, L., Jackson, P., Kamleh, W., Sciaba, Andrea, Meinhard, Helge, Cancio, Germán, Gasthuber, Martin, Hollowell, Christopher, Michelotto, Michele, Martelli, Edoardo, Muralidharan, Servesh, Panzer-Steindel, Bernd, Seuster, Rolf, Wegner, Peter, Yen, Eric, and Misawa, Shigeki
- Subjects
LARGE Hadron Collider ,DATA libraries ,HIGH performance computing ,GRAPHICS processing units ,ARTIFICIAL intelligence ,APPLICATION-specific integrated circuits - Abstract
Driven by the need to carefully plan and optimise the resources for the next data taking periods of Big Science projects, such as CERN's Large Hadron Collider and others, sites started a common activity, the HEPiX Technology Watch Working Group, tasked with tracking the evolution of technologies and markets of concern to the data centres. The talk will give an overview of general and semiconductor markets, server markets, CPUs and accelerators, memories, storage and networks; it will highlight important areas of uncertainties and risks. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
19. Operational Intelligence for Distributed Computing Systems for Exascale Science.
- Author
-
Doglioni, C., Kim, D., Stewart, G.A., Silvestris, L., Jackson, P., Kamleh, W., Di Girolamo, Alessandro, Legger, Federica, Paparrigopoulos, Panos, Klimentov, Alexei, Schovancová, Jaroslava, Kuznetsov, Valentin, Lassnig, Mario, Clissa, Luca, Rinaldi, Lorenzo, Sharma, Mayank, Bakhshiansohi, Hamed, Zvada, Marian, Bonacorsi, Daniele, and Rossi Tisbeni, Simone
- Subjects
DISTRIBUTED computing ,ARTIFICIAL intelligence ,COMPUTER software development ,MACHINE learning ,DATA analysis - Abstract
In the near future, large scientific collaborations will face unprecedented computing challenges. Processing and storing exabyte datasets require a federated infrastructure of distributed computing resources. The current systems have proven to be mature and capable of meeting the experiment goals, by allowing timely delivery of scientific results. However, a substantial amount of interventions from software developers, shifters and operational teams is needed to efficiently manage such heterogeneous infrastructures. A wealth of operational data can be exploited to increase the level of automation in computing operations by using adequate techniques, such as machine learning (ML), tailored to solve specific problems. The Operational Intelligence project is a joint effort from various WLCG communities aimed at increasing the level of automation in computing operations. We discuss how state-of-the-art technologies can be used to build general solutions to common problems and to reduce the operational cost of the experiment computing infrastructure. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
20. Comparison of methods for flow border detection in images of smoke visualization
- Author
-
Petr Caletka, Frantisek Lizal, Jan Jedelsky, Miroslav Jicha, and Ondrej Pech
- Subjects
Physics ,Brightness ,Image quality ,business.industry ,QC1-999 ,Airflow ,Separation (aeronautics) ,smoke vizualization ,Pattern recognition ,Image segmentation ,Quality (physics) ,Flow (mathematics) ,Car vent ,Benchmark (computing) ,Artificial intelligence ,business ,smoke visualization ,border detection ,Cartography - Abstract
A separation of the flow region from the surroundings is an essential step in the analysis of smoke visualization images. The separation can be performed using several detection methods from the image segmentation group. This paper deals with the border detection of the air flow downstream of a benchmark automotive vent using different threshold-based detection methods. An assessment of the methods on the basis of the resulting image quality is also addressed. The quality level depends on the quantity and brightness of disturbances in the background area. The disturbance is usually an isolated region of smoke, which naturally cannot be a part of the flow. Three representative images of different quality levels were selected for the detection, and three methods were used for the evaluation. Each of the methods was used to determine the threshold differently (by the level, by the ratio, and by the change of brightness). It is demonstrated that the change-based method with an appropriately selected parameter is the most convenient for images with the worst quality level while level- and ratio-based methods are only applicable for images of good quality. A separation of the flow region from the surroundings is an essential step in the analysis of smoke visualization images. The separation can be performed using several detection methods from the image segmentation group. This paper deals with the border detection of the air flow downstream of a benchmark automotive vent using different threshold-based detection methods. An assessment of the methods on the basis of the resulting image quality is also addressed. The quality level depends on the quantity and brightness of disturbances in the background area. The disturbance is usually an isolated region of smoke, which naturally cannot be a part of the flow. Three representative images of different quality levels were selected for the detection, and three methods were used for the evaluation. Each of the methods was used to determine the threshold differently (by the level, by the ratio, and by the change of brightness). It is demonstrated that the change-based method with an appropriately selected parameter is the most convenient for images with the worst quality level while level- and ratio-based methods are only applicable for images of good quality.
- Published
- 2016
21. Deep Learning Methods On Neutron Scattering Data
- Author
-
Song Guanghan, Porcar Lionel, Boehm Martin, Cecillon Franck, Dewhurst Charles, Le Goc Yannick, Locatelli Jérome, Mutti Paolo, and Weber Tobias
- Subjects
artificial intelligence ,deep learning ,convolutional neural network ,transfer learning ,small-angle neutron scattering ,Physics ,QC1-999 - Abstract
Recently, by using deep learning methods, a computer is able to surpass or come close to matching human performance on image analysis and recognition. This advanced methods could also help extracting features from neutron scattering experimental data. Those data contain rich scientific information about structure and dynamics of materials under investigation. Deep learning could help researchers better understand the link between experimental data and materials properties. Moreover,it could also help to optimize neutron scattering experiment by predicting the best possible instrument configuration. Among all possible experimental methods, we begin our study on the small-angle neutron scattering (SANS) data and by predicting the structure geometry of the sample material at an early stage. This step is a keystone to predict the experimental parameters to properly setup the instrument as well as the best measurement strategy. In this paper, we propose to use transfer learning to retrain a convolutional neural networks (CNNs) based pre rained model to adapt the scattering images classification, which could predict the structure of the materials at an early stage in the SANS experiment. This deep neural network is trained and validated on simulated database, and tested on real scattering images.
- Published
- 2020
- Full Text
- View/download PDF
22. Towards a realistic track reconstruction algorithm based on graph neural networks for the HL-LHC
- Author
-
Charline Rougier, Sylvain Caillou, Catherine Biscarat, Jan Stark, Jad Zahreddine, Laboratoire des deux Infinis de Toulouse (L2IT), Université Toulouse III - Paul Sabatier (UT3), and Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut National de Physique Nucléaire et de Physique des Particules du CNRS (IN2P3)-Centre National de la Recherche Scientifique (CNRS)
- Subjects
data analysis method ,Physics - Instrumentation and Detectors ,neural network ,QC1-999 ,FOS: Physical sciences ,Track (rail transport) ,Tracking (particle physics) ,programming ,01 natural sciences ,High Energy Physics - Experiment ,High Energy Physics - Experiment (hep-ex) ,Software ,numerical methods ,0103 physical sciences ,[PHYS.HEXP]Physics [physics]/High Energy Physics - Experiment [hep-ex] ,[PHYS.PHYS.PHYS-INS-DET]Physics [physics]/Physics [physics]/Instrumentation and Detectors [physics.ins-det] ,numerical calculations ,010306 general physics ,Large Hadron Collider ,Artificial neural network ,track data analysis ,010308 nuclear & particles physics ,business.industry ,Physics ,Reconstruction algorithm ,Instrumentation and Detectors (physics.ins-det) ,artificial intelligence ,CERN LHC Coll ,Computer engineering ,Proof of concept ,Physics - Data Analysis, Statistics and Probability ,Pattern recognition (psychology) ,business ,Data Analysis, Statistics and Probability (physics.data-an) ,[PHYS.PHYS.PHYS-DATA-AN]Physics [physics]/Physics [physics]/Data Analysis, Statistics and Probability [physics.data-an] - Abstract
The physics reach of the HL-LHC will be limited by how efficiently the experiments can use the available computing resources, i.e. affordable software and computing are essential. The development of novel methods for charged particle reconstruction at the HL-LHC incorporating machine learning techniques or based entirely on machine learning is a vibrant area of research. In the past two years, algorithms for track pattern recognition based on graph neural networks (GNNs) have emerged as a particularly promising approach. Previous work mainly aimed at establishing proof of principle. In the present document we describe new algorithms that can handle complex realistic detectors. The new algorithms are implemented in ACTS, a common framework for tracking software. This work aims at implementing a realistic GNN-based algorithm that can be deployed in an HL-LHC experiment., Comment: Paper submitted to vCHEP2021 (25th International Conference on Computing in High-Energy Physics and Nuclear Physics), 10 pages, 4 figures
- Published
- 2021
23. Accelerating End-to-End Deep Learning for Particle Reconstruction using CMS open data
- Author
-
Ulrich Heintz, Bjorn Burkle, Sergei Gleyzer, Manfred Paulini, Meenakshi Narain, Emanuele Usai, Michael Benjamin Andrews, Davide Di Croce, and Shravan Chaudhari
- Subjects
Open data ,End-to-end principle ,business.industry ,Computer science ,Deep learning ,Physics ,QC1-999 ,Particle ,Artificial intelligence ,Aerospace engineering ,business - Abstract
Machine learning algorithms are gaining ground in high energy physics for applications in particle and event identification, physics analysis, detector reconstruction, simulation and trigger. Currently, most data-analysis tasks at LHC experiments benefit from the use of machine learning. Incorporating these computational tools in the experimental framework presents new challenges. This paper reports on the implementation of the end-to-end deep learning with the CMS software framework and the scaling of the end-to-end deep learning with multiple GPUs. The end-to-end deep learning technique combines deep learning algorithms and low-level detector representation for particle and event identification. We demonstrate the end-to-end implementation on a top quark benchmark and perform studies with various hardware architectures including single and multiple GPUs and Google TPU.
- Published
- 2021
24. Event Classification with Multi-step Machine Learning
- Author
-
K. Terashi, Tomoe Kishimoto, Junichi Tanaka, Yuya Kaneta, Yutaro Iiyama, Taichi Itoh, Ryu Sawada, Masahiko Saito, and Yoshiaki Umeda
- Subjects
FOS: Computer and information sciences ,Computer Science - Machine Learning ,Event (computing) ,Computer science ,business.industry ,Physics ,QC1-999 ,Inference ,Value (computer science) ,Machine learning ,computer.software_genre ,Machine Learning (cs.LG) ,Task (computing) ,Hyperparameter optimization ,Path (graph theory) ,Differentiable function ,Artificial intelligence ,business ,computer ,Selection (genetic algorithm) - Abstract
The usefulness and value of Multi-step Machine Learning (ML), where a task is organized into connected sub-tasks with known intermediate inference goals, as opposed to a single large model learned end-to-end without intermediate sub-tasks, is presented. Pre-optimized ML models are connected and better performance is obtained by re-optimizing the connected one. The selection of an ML model from several small ML model candidates for each sub-task has been performed by using the idea based on Neural Architecture Search (NAS). In this paper, Differentiable Architecture Search (DARTS) and Single Path One-Shot NAS (SPOS-NAS) are tested, where the construction of loss functions is improved to keep all ML models smoothly learning. Using DARTS and SPOS-NAS as an optimization and selection as well as the connections for multi-step machine learning systems, we find that (1) such a system can quickly and successfully select highly performant model combinations, and (2) the selected models are consistent with baseline algorithms, such as grid search, and their outputs are well controlled.
- Published
- 2021
25. RESEARCH ON THE CROSS-SECTION GENERATING METHOD IN HTGR SIMULATOR BASED ON MACHINE LEARNING METHODS
- Author
-
Xiaoye Qian, Chunlin Wei, Li Zeguang, Zhe Sui, and Jun Sun
- Subjects
Polynomial ,htgr ,QC1-999 ,Machine learning ,computer.software_genre ,01 natural sciences ,law.invention ,Cross section (physics) ,law ,0103 physical sciences ,Nuclear power plant ,Range (statistics) ,010306 general physics ,Simulation ,cross section ,010308 nuclear & particles physics ,business.industry ,Physics ,Function (mathematics) ,Expression (mathematics) ,Nonlinear system ,machine learning ,engineering simulator ,Artificial intelligence ,business ,computer ,Scope (computer science) - Abstract
With the increasing needs of accurate simulation, the 3-D diffusion reactor physics module has been implemented in HTGR’s engineering simulator to give better neutron dynamics results instead of point kinetics model used in previous nuclear power plant simulators. As the requirement of real-time calculation of nuclear power plant simulator, the cross-sections used in 3-D diffusion module must be calculated very efficiently. Normally, each cross-section in simulator is calculated in the form of polynomial by function of several concerned variables, the expression of which was finalized by multivariate regression from large number scattered database generated by previous calculation. Since the polynomial is explicit and prepared in advance, the cross-sections could be calculated quickly enough in running simulator and achieve acceptable accuracy especially in LWR simulations. However, some of concerned variables in HTGR are in large scope and also the relationships of these variables are non-linear and very complex, it is very hard to use polynomial to meet full range accuracy. In this paper, a cross-section generating method used in HTGR simulator is proposed, which is based on machine learning methods, especially deep neuron network and tree regression methods. This method first uses deep neuron networks to consider the nonlinear relationships between different variables and then uses a tree regression to achieve accurate cross-section results in full range, the parameters of deep neuron networks and tree regression are learned automatically from the scattered database generated by VSOP. With the numerical tests, the proposed cross-section generating method could get more accurate cross-section results and the calculation time is acceptable by the simulator.
- Published
- 2021
26. Improving the Learning Power of Artificial Intelligence Using Multimodal Deep Learning
- Author
-
Leonid A. Sevastianov and Eugene Yu. Shchetinin
- Subjects
Network architecture ,Biometrics ,Artificial neural network ,business.industry ,Speech recognition ,Deep learning ,Physics ,QC1-999 ,020206 networking & telecommunications ,Context (language use) ,02 engineering and technology ,Paralanguage ,Formant ,0202 electrical engineering, electronic engineering, information engineering ,Artificial intelligence ,business ,Human voice - Abstract
Computer paralinguistic analysis is widely used in security systems, biometric research, call centers and banks. Paralinguistic models estimate different physical properties of voice, such as pitch, intensity, formants and harmonics to classify emotions. The main goal is to find such features that would be robust to outliers and will retain variety of human voice properties at the same time. Moreover, the model used must be able to estimate features on a time scale for an effective analysis of voice variability. In this paper a paralinguistic model based on Bidirectional Long Short-Term Memory (BLSTM) neural network is described, which was trained for vocal-based emotion recognition. The main advantage of this network architecture is that each module of the network consists of several interconnected layers, providing the ability to recognize flexible long-term dependencies in data, which is important in context of vocal analysis. We explain the architecture of a bidirectional neural network model, its main advantages over regular neural networks and compare experimental results of BLSTM network with other models.
- Published
- 2021
27. Building lighting energy consumption modelling with hybrid neural-statistic approaches.
- Author
-
Lauro, F., Meloni, C., and Pizzuti, S.
- Subjects
ENERGY consumption ,INTERIOR lighting ,ARTIFICIAL intelligence ,ARTIFICIAL neural networks ,BUILDINGS - Abstract
In the proposed work we aim at modelling building lighting energy consumption. We compared several classical methods to the latest Artificial Intelligence modelling technique : Artificial Neural Networks Ensembling (ANNE). Therefore, in this study we show how we built the ANNE and a new hybrid model based on the statistical-ANNE combination. Experimentation has been carried out over a three months data set coming from a real office building located in the ENEA 'Casaccia' Research Centre. Experimental results show that the proposed hybrid statistical-ANNE approach can get a remarkable improvement with respect to the best classical method (the statistical one). [ABSTRACT FROM AUTHOR]
- Published
- 2012
- Full Text
- View/download PDF
28. Deep Siamese Networks for Plant Disease Detection
- Author
-
Alexander Uzhinskiy, Pavel Goncharov, Julia Zudikhina, Gennady Ososkov, and Andrey Nechaevskiy
- Subjects
business.industry ,Physics ,QC1-999 ,Classifier (linguistics) ,Feature (machine learning) ,Artificial intelligence ,Perceptron ,Machine learning ,computer.software_genre ,business ,computer ,Plant disease ,Extractor - Abstract
Crop losses are a major threat to the wellbeing of rural families, to the economy and governments, and to food security worldwide. The goal of our research is to develop a multi-functional platform to help the farming community to tilt against plant diseases. In our previous works, we reported about the creation of a special database of healthy and diseased plants’ leaves consisting of five sets of grapes images and proposed a special classification model based on a deep siamese network followed by k-nearest neighbors (KNN) classifier. Then we extended our database to five sets of images for grape, corn, and wheat – 611 images in total. Since after this extension the classification accuracy decreased to 86 %, we propose in this paper a novel architecture with a deep siamese network as feature extractor and a single-layer perceptron as a classifier that results in a significant gain of accuracy, up to 96 %.
- Published
- 2020
29. Machine Learning based Global Particle Identification Algorithms at the LHCb Experiment
- Author
-
Nikita Kazeev, Denis Derkach, and Mikhail Hushchyn
- Subjects
Computer science ,Physics::Instrumentation and Detectors ,QC1-999 ,Hadron ,PID controller ,Machine learning ,computer.software_genre ,01 natural sciences ,Particle identification ,Pion ,0103 physical sciences ,010306 general physics ,Cherenkov radiation ,Artificial neural network ,010308 nuclear & particles physics ,business.industry ,Physics ,Charged particle ,Computing and Computers ,High Energy Physics::Experiment ,Gradient boosting ,Artificial intelligence ,business ,Algorithm ,computer ,Particle Physics - Experiment - Abstract
One of the most important aspects of data processing at flavor physics experiments is the particle identification (PID) algorithm. In LHCb, several different sub-detector systems provide PID information: the Ring Imaging Cherenkov detectors, the hadronic and electromagnetic calorimeters, and the muon chambers. The charged PID based on the sub-detectors response is considered as a machine learning problem solved in different modes: one-vs-rest, one-vs-one and multi-classification, which affect the models training and prediction. To improve charged particle identification for pions, kaons, protons, muons and electrons, neural network and gradient boosting models have been tested. This paper presents these models and their performance evaluated on Run 2 data and simulation samples. A discussion of the performances is also presented.
- Published
- 2019
30. Photometric Redshift Analysis using Supervised Learning Algorithms and Deep Learning
- Author
-
Abel Yang and Chong, De Wei, Kenny
- Subjects
Computer science ,business.industry ,Deep learning ,Physics ,QC1-999 ,FOS: Physical sciences ,Astrophysics::Cosmology and Extragalactic Astrophysics ,Machine learning ,computer.software_genre ,Artificial intelligence ,business ,Astrophysics - Instrumentation and Methods for Astrophysics ,computer ,Instrumentation and Methods for Astrophysics (astro-ph.IM) ,Supervised training ,Astrophysics::Galaxy Astrophysics ,Photometric redshift - Abstract
We present a catalogue of galaxy photometric redshifts for the Sloan Digital Sky Survey (SDSS) Data Release 12. We use various supervised learning algorithms to calculate redshifts using photometric attributes on a spectroscopic training set. Two training sets are analysed in this paper. The first training set consists of 995,498 galaxies with redshifts up to $z \approx 0.8$. On the first training set, we achieve a cost function of 0.00501 and a root mean squared error value of 0.0707 using the XGBoost algorithm. We achieved an outlier rate of 2.1\% and 86.81\%, 95.83\%, 97.90\% of our data points lie within one, two, and three standard deviation of the mean respectively. The second training set consists of 163,140 galaxies with redshifts up to $z\approx0.2$ and is merged with the Galaxy Zoo 2 full catalog. We also experimented on convolutional neural networks to predict five morphological features (Smooth, Features/Disk, Star, Edge-on, Spiral). We achieve a root mean squared error of 0.117 when validated against an unseen dataset with over 200 epochs. Morphological features from the Galaxy Zoo, trained with photometric features are found to consistently improve the accuracy of photometric redshifts., Comment: Poster presented at the XLVIII International Symposium on Multiparticle Dynamics (ISMD2018)
- Published
- 2019
31. Computationally efficient approach to quantify 2D particle morphological descriptors
- Author
-
N.S.S.P. Kalyan and RK Kandasami
- Subjects
Materials science ,business.industry ,Noise (signal processing) ,Physics ,QC1-999 ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,0211 other engineering and technologies ,Process (computing) ,Image processing ,Pattern recognition ,02 engineering and technology ,Kinematics ,Computational geometry ,01 natural sciences ,Roundness (object) ,Sphericity ,0103 physical sciences ,Artificial intelligence ,010306 general physics ,business ,Smoothing ,021101 geological & geomatics engineering - Abstract
The macro-scale behavior of granular materials is strongly influenced by grain kinematics. The mobility of the grains in turn is affected by grain morphology which needs to be comprehensively characterized. Initially, morphological descriptors were determined by manual processes which were tedious and cumbersome. But with the help of image processing techniques and computational geometry, this problem can be handled with ease. The long-established descriptors such as sphericity and roundness can be estimated by operating over the grain boundary obtained from 2D images of the particle. The main objective of this study is to quantify these descriptors in a computationally effective way. The roundness quantification in previous studies involves the sequence of processes such as removing the noise, corner identification and fitting circles. This paper details the necessary modifications to the quantification process required to reduce the cost of time for a single particle. Further, the influence of different smoothing techniques and a new corner identification method will be detailed.
- Published
- 2021
32. Gradient-Based Algorithm for Tracking the Activity of Neural Network Weights Changing
- Author
-
Anton Starodub, Natalia Eliseeva, and Milen Georgiev
- Subjects
Artificial neural network ,010308 nuclear & particles physics ,business.industry ,Physics ,QC1-999 ,Work (physics) ,Training (meteorology) ,Process (computing) ,Machine learning ,computer.software_genre ,Tracking (particle physics) ,Object (computer science) ,01 natural sciences ,Field (computer science) ,Set (abstract data type) ,0103 physical sciences ,Artificial intelligence ,010306 general physics ,business ,computer - Abstract
The research conducted in this paper is in the field of machine learning. The main object of the research is the learning process of an artificial neural network in order to increase its efficiency. The algorithm based on the analysis of retrospective learning data. The dynamics of changes in the values of the weights of an artificial neural network during training is an important indicator of training efficiency. The algorithm proposed in this work is based on changing the weight gradients values. Changing of the gradients weights makes it possible to understand how actively the network weights change during training. This knowledge helps to diagnose the training process and makes an adjusting the training parameters. The results of the algorithm can be used to train an artificial neural network. The network will help to determine the set of measures (actions) needed to optimize the learning process by the algorithm results.
- Published
- 2021
33. Evaluation of Portable Acceleration Solutions for LArTPC Simulation Using Wire-Cell Toolkit
- Author
-
Meifeng Lin, Haiwang Yu, Zhihua Dong, Kwangmin Yu, B. Viren, and K. Knoepfel
- Subjects
FOS: Computer and information sciences ,Delegate ,business.industry ,Physics ,QC1-999 ,Deep learning ,Symmetric multiprocessor system ,Porting ,Acceleration ,Software ,Computer Science - Distributed, Parallel, and Cluster Computing ,Computer engineering ,Scalability ,Code (cryptography) ,Distributed, Parallel, and Cluster Computing (cs.DC) ,Artificial intelligence ,business - Abstract
The Liquid Argon Time Projection Chamber (LArTPC) technology plays an essential role in many current and future neutrino experiments. Accurate and fast simulation is critical to developing efficient analysis algorithms and precise physics model projections. The speed of simulation becomes more important as Deep Learning algorithms are getting more widely used in LArTPC analysis and their training requires a large simulated dataset. Heterogeneous computing is an efficient way to delegate computing-heavy tasks to specialized hardware. However, as the landscape of the compute accelerators is evolving fast, it becomes more and more difficult to manually adapt the code constantly to the latest hardware or software environments. A solution which is portable to multiple hardware architectures while not substantially compromising performance would be very beneficial, especially for long-term projects such as the LArTPC simulations. In search of a portable, scalable and maintainable software solution for LArTPC simulations, we have started to explore high-level portable programming frameworks that support several hardware backends. In this paper, we will present our experience porting the LArTPC simulation code in the Wire-Cell toolkit to NVIDIA GPUs, first with the CUDA programming model and then with a portable library called Kokkos. Preliminary performance results on NVIDIA V100 GPUs and multi-core CPUs will be presented, followed by a discussion of the factors affecting the performance and plans for future improvements., 10 pages, vCHEP2021
- Published
- 2021
34. Heat Prediction of High Energy Physical Data Based on LSTM Recurrent Neural Network
- Author
-
Gang Chen, Lu Wang, Zhenjing Cheng, and Yaodong Cheng
- Subjects
business.industry ,Heuristic (computer science) ,Physics ,QC1-999 ,Deep learning ,computer.software_genre ,Data access ,Recurrent neural network ,Computer data storage ,Data mining ,Artificial intelligence ,Namespace ,business ,computer ,Predictive modelling ,Data migration - Abstract
High-energy physics computing is a typical data-intensive calculation. Each year, petabytes of data needs to be analyzed, and data access performance is increasingly demanding. The tiered storage system scheme for building a unified namespace has been widely adopted. Generally, data is stored on storage devices with different performances and different prices according to different access frequency. When the heat of the data changes, the data is then migrated to the appropriate storage tier. At present, heuristic algorithms based on artificial experience are widely used in data heat prediction. Due to the differences in computing models of different users, the accuracy of prediction is low. A method for predicting future access popularity based on file access characteristics with the help of LSTM deep learning algorithm is proposed as the basis for data migration in hierarchical storage. This paper uses the real data of high-energy physics experiment LHAASO as an example for comparative testing. The results show that under the same test conditions, the model has higher prediction accuracy and stronger applicability than existing prediction models.
- Published
- 2020
35. Machine Learning-based Anomaly Detection of Ganglia Monitoring Data in HEP Data Center
- Author
-
Qingbao Hu, Juan Chen, and Lu Wang
- Subjects
050208 finance ,business.industry ,Lustre (programming language) ,Physics ,QC1-999 ,05 social sciences ,02 engineering and technology ,Machine learning ,computer.software_genre ,Visualization ,Daily operation ,Monitoring data ,0502 economics and business ,Scalability ,0202 electrical engineering, electronic engineering, information engineering ,020201 artificial intelligence & image processing ,Anomaly detection ,Data center ,Performance measurement ,Artificial intelligence ,business ,computer ,computer.programming_language - Abstract
This paper introduces a generic and scalable anomaly detection framework. Anomaly detection can improve operation and maintenance efficiency and assure experiments can be carried out effectively. The framework facilitates common tasks such as data sample building, retagging and visualization, deviation measurement and performance measurement for machine learning-based anomaly detection methods. The samples we used are sourced from Ganglia monitoring data. There are several anomaly detection methods to handle spatial and temporal anomalies within the framework. Finally, we show the rudimental application of the framework on Lustre distributed file systems in daily operation and maintenance.
- Published
- 2020
36. Deep learning methods on neutron scattering data
- Author
-
Guanghan Song, Yannick Le Goc, J.Locatelli, Lionel Porcar, Paolo Mutti, Franck Cecillon, Martin Boehm, Tobias Weber, and Charles Dewhurst
- Subjects
Computer science ,QC1-999 ,convolutional neural network ,02 engineering and technology ,transfer learning ,010501 environmental sciences ,Neutron scattering ,computer.software_genre ,01 natural sciences ,Convolutional neural network ,0202 electrical engineering, electronic engineering, information engineering ,0105 earth and related environmental sciences ,small-angle neutron scattering ,Artificial neural network ,Scattering ,business.industry ,Physics ,Deep learning ,deep learning ,Experimental data ,artificial intelligence ,Small-angle neutron scattering ,020201 artificial intelligence & image processing ,Artificial intelligence ,Data mining ,Transfer of learning ,business ,computer - Abstract
Recently, by using deep learning methods, a computer is able to surpass or come close to matching human performance on image analysis and recognition. This advanced methods could also help extracting features from neutron scattering experimental data. Those data contain rich scientific information about structure and dynamics of materials under investigation. Deep learning could help researchers better understand the link between experimental data and materials properties. Moreover,it could also help to optimize neutron scattering experiment by predicting the best possible instrument configuration. Among all possible experimental methods, we begin our study on the small-angle neutron scattering (SANS) data and by predicting the structure geometry of the sample material at an early stage. This step is a keystone to predict the experimental parameters to properly setup the instrument as well as the best measurement strategy. In this paper, we propose to use transfer learning to retrain a convolutional neural networks (CNNs) based pre rained model to adapt the scattering images classification, which could predict the structure of the materials at an early stage in the SANS experiment. This deep neural network is trained and validated on simulated database, and tested on real scattering images.
- Published
- 2020
37. Accelerate Scientific Deep Learning Models on Heterogeneous Computing Platform with FPGA
- Author
-
Prabhat, Herman Lam, Chao Jiang, Sofia Vallecorsa, David Ojika, Bhavesh Patel, and Thorsten Kurth
- Subjects
Speedup ,Artificial neural network ,business.industry ,Physics ,QC1-999 ,Deep learning ,Big data ,Symmetric multiprocessor system ,Computing and Computers ,Workflow ,Computer architecture ,Single-core ,Artificial intelligence ,business ,Field-programmable gate array - Abstract
AI and deep learning are experiencing explosive growth in almost every domain involving analysis of big data. Deep learning using Deep Neural Networks (DNNs) has shown great promise for such scientific data analysis applications. However, traditional CPU-based sequential computing without special instructions can no longer meet the requirements of mission-critical applications, which are compute-intensive and require low latency and high throughput. Heterogeneous computing (HGC), with CPUs integrated with GPUs, FPGAs, and other science-targeted accelerators, offers unique capabilities to accelerate DNNs. Collaborating researchers at SHREC1at the University of Florida, CERN Openlab, NERSC2at Lawrence Berkeley National Lab, Dell EMC, and Intel are studying the application of heterogeneous computing (HGC) to scientific problems using DNN models. This paper focuses on the use of FPGAs to accelerate the inferencing stage of the HGC workflow. We present case studies and results in inferencing state-of-the-art DNN models for scientific data analysis, using Intel distribution of OpenVINO, running on an Intel Programmable Acceleration Card (PAC) equipped with an Arria 10 GX FPGA. Using the Intel Deep Learning Acceleration (DLA) development suite to optimize existing FPGA primitives and develop new ones, we were able accelerate the scientific DNN models under study with a speedup from 2.46x to 9.59x for a single Arria 10 FPGA against a single core (single thread) of a server-class Skylake CPU.
- Published
- 2020
38. Lessons Learned from the Assessment of Software Defect Prediction on WLCG Software: A Study with Unlabelled Datasets and Machine Learning Techniques
- Author
-
Davide Salomoni, Marco Canaparo, Elisabetta Ronchieri, B Martelli, and Mauro Belgiovine
- Subjects
business.industry ,Physics ,QC1-999 ,020207 software engineering ,02 engineering and technology ,Machine learning ,computer.software_genre ,Software metric ,Software modules ,ComputingMethodologies_PATTERNRECOGNITION ,Software ,Software bug ,Middleware ,0202 electrical engineering, electronic engineering, information engineering ,020201 artificial intelligence & image processing ,Artificial intelligence ,business ,computer ,Predictive modelling - Abstract
Software defect prediction is an activity that aims at narrowing down the most likely defect-prone software modules and helping developers and testers to prioritize inspection and testing. This activity can be addressed by using Machine Learning techniques applied to software metrics datasets that are usually unlabelled, i.e. they lack modules classification in terms of defectiveness. To overcome this limitation, in addition to the usual data pre-processing operations to manage mission values and/or to remove inconsistencies, researches have to adopt an approach to label their unlabelled software datasets. The extraction of defectiveness data to label all the instances of the datasets is an extremely time and effort consuming operation. In literature, many studies have introduced approaches to build a defect prediction models on unlabelled datasets.In this paper, we describe the analysis of new unlabelled datasets from WLCG software, coming from HEP-related experiments and middleware, by using Machine Learning techniques. We have experimented new approaches to label the various modules due to the heterogeneity of software metrics distribution. We discuss a number of lessons learned from conducting these activities, what has worked, what has not and how our research can be improved.
- Published
- 2020
39. Application of Deep Learning on Integrating Prediction, Provenance, and Optimization
- Author
-
Ilkay Altintas, Nathan R. Tallent, Malachi Schram, Alok R. Singh, and Ryan Friese
- Subjects
Job scheduler ,Workflow ,business.industry ,Physics ,QC1-999 ,Deep learning ,Artificial intelligence ,Scale (map) ,business ,computer.software_genre ,Machine learning ,computer ,Energy (signal processing) - Abstract
In this research, we investigated two approaches to detect job anomalies and/or contention for large scale computing efforts: 1. Preemptive job scheduling using binomial classification long short-term memory networks 2. Forecasting intra-node computing loads from the active jobs and additional job(s) For approach 1, we achieved a 14% improvement in computational resources utilization and an overall classification accuracy of 85% on real tasks executed in a High Energy Physics computing workflow. For this paper, we present the preliminary results used in second approach.
- Published
- 2019
40. Modified Depth-Map Inpainting Method Using the Neural Network
- Author
-
Yigang Cen, Nikolay Gapon, Marina Zhdanova, Roman A. Sizyakin, and Oksana Balabaeva
- Subjects
Image structure ,Pixel ,Artificial neural network ,business.industry ,Physics ,QC1-999 ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,0211 other engineering and technologies ,Inpainting ,Stereo pair ,02 engineering and technology ,Image (mathematics) ,020303 mechanical engineering & transports ,0203 mechanical engineering ,Depth map ,021105 building & construction ,Computer vision ,Artificial intelligence ,Geometric modeling ,business - Abstract
This paper proposes a method for reconstructing a depth map obtained using a stereo pair image. The proposed approach is based on a geometric model for the synthesis of patches. The entire image is preliminarily divided into blocks of different size, where large blocks are used to restore homogeneous areas, and small blocks are used to restore details of the image structure. Lost pixels are recovered by copying the pixel values from the source based on the similarity criterion. We used a trained neural network to select the “best like” patch. Experimental results show that the proposed method gives better results than other modern methods, both in subjective and objective measurements for reconstructing a depth map.
- Published
- 2019
41. Development and Application of MRF Based on Robot Arm
- Author
-
Song Chi, Zhang Xue-jun, Ai Bo, Li Longxiang, and Xue Donglin
- Subjects
Tool path ,ComputingMethodologies_PATTERNRECOGNITION ,business.industry ,Physics ,QC1-999 ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,Magnetorheological finishing ,Polishing ,Computer vision ,Development (differential geometry) ,Artificial intelligence ,business ,Robotic arm - Abstract
Magnetorheological Finishing (MRF) is widely regarded as an effective technique to polish and figure aspheric optics. MRF based on Robot Arm is developed by us. This new machine is more flexible, efficient, cost-effective and smaller space-usage in optical shop, compared with the traditional MRF machines. The components of MRF based on Robot Arm are introduced firstly. Position-attitude control and polishing tool path are also studied in this paper. The experiments and application of MRF based on Robot Arm demonstrate the effectiveness and validity of MRF based on Robot Arm in optical fabrication.
- Published
- 2019
42. Deep Reinforcement Learning for Energy Microgrids Management Considering Flexible Energy Sources
- Author
-
Alexander Domyshev, Alexey E. Zhukov, and Nikita Tomin
- Subjects
Consumption (economics) ,Operations research ,business.industry ,Physics ,QC1-999 ,020209 energy ,Deep learning ,020208 electrical & electronic engineering ,02 engineering and technology ,Order (exchange) ,0202 electrical engineering, electronic engineering, information engineering ,Reinforcement learning ,Production (economics) ,Electricity ,Artificial intelligence ,Microgrid ,Energy source ,business - Abstract
The problem of optimally activating the flexible energy sources (short- and long-term storage capacities) of electricity microgrid is formulated as a sequential decision making problem under uncertainty where, at every time-step, the uncertainty comes from the lack of knowledge about future electricity consumption and weather dependent PV production. This paper proposes to address this problem using deep reinforcement learning. To this purpose, a specific deep learning architecture has been used in order to extract knowledge from past consumption and production time series as well as any available forecasts. The approach is empirically illustrated in the case of off-grid microgrids located in Belgium and Russia.
- Published
- 2019
43. Application of Artificial Neural Networks and Singular-Spectral Analysis in Forecasting the Daily Traffic in the Moscow Metro
- Author
-
Evgenii Osetrov and Victor Ivanov
- Subjects
Basis (linear algebra) ,Artificial neural network ,business.industry ,Physics ,QC1-999 ,Spectral analysis ,Artificial intelligence ,business - Abstract
In this paper, we investigate the possibility of applying various approaches to solving the problem of medium-term forecasting of daily passenger traffic volumes in the Moscow metro (MM): 1) on the basis of artificial neural networks (ANN); 2) using the singular-spectral analysis implemented in the package “Caterpillar”-SSA; 3) sharing the ANN and the “Caterpillar”-SSA approach. We demonstrate that the developed methods and algorithms allow us to conduct medium-term forecasting of passenger traffic in the MM with reasonable accuracy.
- Published
- 2018
44. Comparison of edge detection techniques for M7 subtype Leukemic cell in terms of noise filters and threshold value
- Author
-
Afifah Salmi Abdul Salam, Muhammad Imran Ahmad, Mohd Nazrin Md Isa, and Rizalafande Che Ismail
- Subjects
010308 nuclear & particles physics ,Image quality ,business.industry ,Noise (signal processing) ,Physics ,QC1-999 ,Speech recognition ,Feature extraction ,Sobel operator ,Pattern recognition ,02 engineering and technology ,Filter (signal processing) ,Image segmentation ,01 natural sciences ,Edge detection ,0103 physical sciences ,0202 electrical engineering, electronic engineering, information engineering ,Canny edge detector ,020201 artificial intelligence & image processing ,Artificial intelligence ,business - Abstract
This paper will focus on the study and identifying various threshold values for two commonly used edge detection techniques, which are Sobel and Canny Edge detection. The idea is to determine which values are apt in giving accurate results in identifying a particular leukemic cell. In addition, evaluating suitability of edge detectors are also essential as feature extraction of the cell depends greatly on image segmentation (edge detection). Firstly, an image of M7 subtype of Acute Myelocytic Leukemia (AML) is chosen due to its diagnosing which were found lacking. Next, for an enhancement in image quality, noise filters are applied. Hence, by comparing images with no filter, median and average filter, useful information can be acquired. Each threshold value is fixed with value 0, 0.25 and 0.5. From the investigation found, without any filter, Canny with a threshold value of 0.5 yields the best result.
- Published
- 2017
45. Aerodynamics simulation studies on the observation head placed on a board of the unmanned aerial vehicle
- Author
-
Slawomir Blasiak and Izabela Krzysztofik
- Subjects
Engineering ,021103 operations research ,business.industry ,Physics ,QC1-999 ,0211 other engineering and technologies ,Navigation system ,030206 dentistry ,02 engineering and technology ,Aerodynamics ,Deck ,03 medical and health sciences ,0302 clinical medicine ,Professional video camera ,Laser pointer ,Global Positioning System ,Head (vessel) ,Computer vision ,Daylight ,Artificial intelligence ,business ,Simulation - Abstract
An important element of UAV equipment are observation heads. Observation head is multisensor optoelectronic system. It includes TV camera and infrared camera, safe for the eye rangefinder and laser pointer and a navigation system GPS. Image stability is provided by electro-mechanical gyro stability system. Optoelectronic head are designed for use in systems of detection, identification and observation of ground and air targets and in daylight and at night. In this paper simulation studies of the air masses flow around the observation head placed on the UAV deck, for different speeds of UAV movement were conducted. The results of numerical research were presented in a graphical form.
- Published
- 2017
46. Measurement of multiparametric quantities at perception of sensory information by living creatures
- Author
-
Roald Taymanov and Kseniia Sapozhnikova
- Subjects
Engineering ,Creatures ,business.industry ,Mechanism (biology) ,Physics ,QC1-999 ,Infrasound ,Speech recognition ,media_common.quotation_subject ,020208 electrical & electronic engineering ,010401 analytical chemistry ,Process (computing) ,Sensory system ,02 engineering and technology ,01 natural sciences ,0104 chemical sciences ,Identification (information) ,Perception ,0202 electrical engineering, electronic engineering, information engineering ,Selection (linguistics) ,Artificial intelligence ,business ,media_common - Abstract
In the paper it is shown that at present the problem of measurements of emotions as multidimensional (multiparametric) quantities is of interest. A measurement model developed by the authors is presented. It enables signals-stimuli generating emotions in sound combinations and their series to be selected and quantitatively estimated. The measurement model provides an adjusted delay (short-time memory) and joint non-linear conversion of audible and delayed acoustical signals, selection of infrasound signals-stimuli as well as identification of emotional images including the ensembles of signals-stimuli and their series. It is demonstrated how the “mechanism” of emotional perception of sound impacts was developed in the process of evolution. Possibilities to decode the emotional content of biolinguistic signals of animals are considered. Future trends of investigations are indicated.
- Published
- 2014
47. Monitoring of civil engineering structures using Digital Image Correlation technique
- Author
-
Malgorzata Kujawinska, D. Szczepanek, Andrzej Świercz, Marcin Malesa, and Przemysław Kołakowski
- Subjects
Engineering ,Digital image correlation ,Speedup ,business.industry ,Physics ,QC1-999 ,Mechanical engineering ,Full field ,Finite element method ,Bridge (nautical) ,Software ,Correlation analysis ,Computer vision ,Artificial intelligence ,business ,Adaptation (computer science) - Abstract
The Digital Image Correlation (DIC) technique enables full field, noncontact measurements of displacements and strains of a wide variety of objects. An adaptation of the DIC technique for monitoring of civil-engineering structures is presented in the paper. A general concept of the complex, automatic monitoring system, in which the DIC sensor plays an important role is described. Some new software features, which aim to facilitate outdoor measurements and speed up the correlation analysis, is also introduced. As an example of application, measurements of a railway bridge in Nieporet (Poland) are presented. The experimental results are compared with displacements of a FEM model of the bridge.
- Published
- 2010
48. Unwrapping techniques for speckle phase maps: study and comparison of the performance of principal methods
- Author
-
H. Lopes, João Everthon da Silva Ribeiro, J. F. Silva Gomes, and Mário Vaz
- Subjects
Continuous phase modulation ,business.industry ,Physics ,QC1-999 ,Computation ,Phase (waves) ,Image processing ,Holographic interferometry ,Displacement (vector) ,Phase maps ,Speckle pattern ,Computer vision ,Artificial intelligence ,business ,Cartography ,Phase modulation ,Unwrapping techniques - Abstract
Holographic interferometry (HI) techniques are powerful tools for experimental mechanics which can be used for displacement fields assessment on a loaded object surface. Used with no contact and high resolution HI can be combined with image processing methods for data analysis. In these techniques the speckle should be fully resolved by the image detector to record an interferogram. This leads to noisy recordings which makes it's post-processing much difficult. Each measurement with HI ends normally in a phase map computation representing the object displacement. Phase calculation algorithms are based on spatial or temporal phase modulation and lead to wrapped phase maps. To obtain the continuous phase distribution several solutions have been implemented. This paper describes the main filtering and unwrapping algorithms available and compares it's performance to solve discontinuities in noisy recordings.
- Published
- 2010
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.