To see the other types of publications on this topic, follow the link: Proton Learning Model.
Journal articles on the topic 'Proton Learning Model'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Proton Learning Model.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Dhuri, Dattaraj B., Dimitra Atri, and Ahmed AlHantoobi. "An Explainable Deep-learning Model of Proton Auroras on Mars." Planetary Science Journal 5, no. 6 (2024): 136. http://dx.doi.org/10.3847/psj/ad45ff.
Full textAbstract:
Abstract Proton auroras are widely observed on the dayside of Mars, identified as a significant intensity enhancement in the hydrogen Lyα (121.6 nm) emission at altitudes of ∼110 and 150 km. Solar wind protons penetrating as energetic neutral atoms into Mars’ thermosphere are thought to be primarily responsible for these auroras. Recent observations of spatially localized “patchy” proton auroras suggest a possible direct deposition of protons into Mars’ atmosphere during unstable solar wind conditions. Improving our understanding of proton auroras is therefore important for characterizing the interaction of the solar wind with Mars’ atmosphere. Here, we develop a first purely data-driven model of proton auroras using Mars Atmosphere and Volatile Evolution (MAVEN) in situ observations and limb scans of Lyα emissions between 2014 and 2022. We train an artificial neural network that reproduces individual Lyα intensities and relative Lyα peak intensity enhancements with Pearson correlations of ∼94% and ∼60% respectively for the test data, along with a faithful reconstruction of the shape of the observed altitude profiles of Lyα emission. By performing a Shapley Additive Explanations (SHAP) analysis, we find that solar zenith angle, solar longitude, CO2 atmosphere variability, solar wind speed, and temperature are the most important features for the modeled Lyα peak intensity enhancements. Additionally, we find that the modeled peak intensity enhancements are high for early local-time hours, particularly near polar latitudes, and the induced magnetic fields are weaker. Through SHAP analysis, we also identify the influence of biases in the training data and interdependences between the measurements used for the modeling, and an improvement of those aspects can significantly improve the performance and applicability of the ANN model.
2
Asuroglu, Tunc. "Enhancing precision in proton therapy: Utilizing machine learning for predicting Bragg curve peak location in cancer treatment." Communications Faculty of Sciences University of Ankara Series A2-A3 Physical Sciences and Engineering 66, no. 2 (2024): 140–61. http://dx.doi.org/10.33769/aupse.1417403.
Full textAbstract:
In proton beam therapy, the Bragg peak is the point where protons lose energy the fastest. This point is crucial for dose control, preserving healthy tissues, minimizing lateral scattering, and the success of treatment planning. However, accurately predicting the location of the Bragg peak is challenging due to the complex interactions of protons with tissues. This study proposes a machine learning (ML) approach to predict the exact location of the Bragg peak from phantom tissue proton beam therapy experiments. A dataset comprising the eight most commonly used biomaterials, which mimic human tissue in proton therapy procedures, has been curated for this study. Various ML models are benchmarked to find the most successful approach. ML model parameters are further optimized using a metaheuristic approach to achieve the highest prediction capability. In addition, feature contributions of each feature in the dataset are analyzed using an explainable artificial intelligence (XAI) technique. According to experimental results, Random Forest (RF) model that is optimized with Genetic Algorithm (GA) achieved 0.742 Correlation Coefficient (CC) value, 0.069 Mean Absolute Error (MAE) and 0.145 Root Mean Square Error (RMSE) outperforming other ML models. The proposed approach can track and predict the movement of the proton beam in real-time during treatment, enhancing treatment safety and contributing to the more effective management of the treatment process. This study is the first to predict exact Bragg curve peak locations from proton beam therapy experiments using ML approaches. The optimized ML model can provide higher precision in identifying the needed beam dosage for targeted tumor and improving treatment outcomes.
3
Fathul, Jannah, Fahlevi Reja, Sari Raihanah, Radiansyah, Yuda, and Azizah Ni'mah. "Improving Learning Activities and Writing Skills in Indonesian Language Content the Environmental Theme of Our Friends Using the Proton Model at Sdn Hatungun 1 Tapin." International Journal of Social Science And Human Research 05, no. 11 (2022): 5091–96. https://doi.org/10.5281/zenodo.7333040.
Full textAbstract:
Learning activities have a big influence on the success of a lesson, this also has a big influence on students' writing skills. But in fact, the method used when learning is still one-way, learning is less meaningful so that students are unable to find ideas/ideas into written form, students' writing interest is low because they use multiple choice questions, many students are still not correct in determining the choice. words (diction) in a sentence, the placement of punctuation marks is not right and they don't understand what a nonfiction story is. This study aims to determine the increase in learning activities and writing skills of elementary school students using the PROTON model. This study uses a qualitative research approach with the type of research in the form of Classroom Action Research which consists of four meetings, data analysis uses two methods, namely qualitative and quantitative. The results showed that by using the PROTON model on the Indonesian content of the Friends of Our Environment Theme there was an increase in student learning activities at the fourth meeting, namely 87.5% in the very active category and in students' writing skills at the fourth meeting as much as 93.75% in the very category. good. The results of this study are expected to be used as an alternative in improving the learning activities and writing skills of elementary school students, especially in the Indonesian content of the Environmental Theme of Our Friends in grade 5.
4
Li, Meng, and Dong Ding. "Accelerated Discovery of Proton-Conducting Perovskites through Density Functional Theory and Machine Learning." ECS Meeting Abstracts MA2022-02, no. 49 (2022): 1913. http://dx.doi.org/10.1149/ma2022-02491913mtgabs.
Full textAbstract:
Hydrogen is an important energy carrier resource in response to limiting greenhouse gas emissions. Proton-conducting perovskite oxide is one of the key materials for highly efficient carbon-neutral hydrogen technologies, such as hydrogen production, CO2 hydrogenation, and ammonia synthesis. Many attempts have been made based on doped perovskites made of well-tested materials, such as BaZrO3, BaCeO3, BaHfO3, BaTiO3, and SrZrO3. However, the resulting perovskites have often suffered stability and conductivity problems. Furthermore, complex phenomena occurring during hydration present challenges for expanding the materials library. Herein, we demonstrate accelerated discovery of proton-conducting perovskites with high conductivity using machine learning (ML) predictions. We constructed consistent training data using density functional theory (DFT) which enable high accuracy of ML model. DFT computations were performed on > 1000 doped perovskite compositions to get their properties of lattice parameters, point defects (e.g., O vacancies, H interstitials), density of states, hydration energy, and proton migration energy. Several ML algorithms including Linear Regression, Bayesian Ridge Regression, Random Forest Regression, Neural networks, and k-Nearest Neighbor were tested for minimum errors and coefficient of determination. The multidimensional relationships between a set of >50 features and conductivity were mapped out using the optimized ML model. We screened a large material space of A-site and B-site doped perovskites to predict potential proton-conducting materials for various energy applications. The outcomes are promising for accelerating the design and applications of proton-conducting perovskite oxides in hydrogen technologies.
5
Pastor-Serrano, Oscar, and Zoltán Perkó. "Learning the Physics of Particle Transport via Transformers." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 11 (2022): 12071–79. http://dx.doi.org/10.1609/aaai.v36i11.21466.
Full textAbstract:
Particle physics simulations are the cornerstone of nuclear engineering applications. Among them radiotherapy (RT) is crucial for society, with 50% of cancer patients receiving radiation treatments. For the most precise targeting of tumors, next generation RT treatments aim for real-time correction during radiation delivery, necessitating particle transport algorithms that yield precise dose distributions in sub-second times even in highly heterogeneous patient geometries. This is infeasible with currently available, purely physics based simulations. In this study, we present a data-driven dose calculation algorithm predicting the dose deposited by mono-energetic proton beams for arbitrary energies and patient geometries. Our approach frames particle transport as sequence modeling, where convolutional layers extract important spatial features into tokens and the transformer self-attention mechanism routes information between such tokens in the sequence and a beam energy token. We train our network and evaluate prediction accuracy using computationally expensive but accurate Monte Carlo (MC) simulations, considered the gold standard in particle physics. Our proposed model is 33 times faster than current clinical analytic pencil beam algorithms, improving upon their accuracy in the most heterogeneous and challenging geometries. With a relative error of 0.34±0.2% and very high gamma pass rate of 99.59±0.7% (1%, 3 mm), it also greatly outperforms the only published similar data-driven proton dose algorithm, even at a finer grid resolution. Offering MC precision 4000 times faster, our model could overcome a major obstacle that has so far prohibited real-time adaptive proton treatments and significantly increase cancer treatment efficacy. Its potential to model physics interactions of other particles could also boost heavy ion treatment planning procedures limited by the speed of traditional methods.
6
Ball, Richard D., Alessandro Candido, Juan Cruz-Martinez, et al. "Evidence for intrinsic charm quarks in the proton." Nature 608, no. 7923 (2022): 483–87. http://dx.doi.org/10.1038/s41586-022-04998-2.
Full textAbstract:
AbstractThe theory of the strong force, quantum chromodynamics, describes the proton in terms of quarks and gluons. The proton is a state of two up quarks and one down quark bound by gluons, but quantum theory predicts that in addition there is an infinite number of quark–antiquark pairs. Both light and heavy quarks, whose mass is respectively smaller or bigger than the mass of the proton, are revealed inside the proton in high-energy collisions. However, it is unclear whether heavy quarks also exist as a part of the proton wavefunction, which is determined by non-perturbative dynamics and accordingly unknown: so-called intrinsic heavy quarks1. It has been argued for a long time that the proton could have a sizable intrinsic component of the lightest heavy quark, the charm quark. Innumerable efforts to establish intrinsic charm in the proton2 have remained inconclusive. Here we provide evidence for intrinsic charm by exploiting a high-precision determination of the quark–gluon content of the nucleon3 based on machine learning and a large experimental dataset. We disentangle the intrinsic charm component from charm–anticharm pairs arising from high-energy radiation4. We establish the existence of intrinsic charm at the 3-standard-deviation level, with a momentum distribution in remarkable agreement with model predictions1,5.We confirm these findings by comparing them to very recent data on Z-boson production with charm jets from the Large Hadron Collider beauty (LHCb) experiment6.
7
Kim, Jiwoong, Chang-Seong Moon, Hokyeong Nam, et al. "Multi-Jet Event classification with Convolutional neural network at Large Scale." Journal of Physics: Conference Series 2438, no. 1 (2023): 012103. http://dx.doi.org/10.1088/1742-6596/2438/1/012103.
Full textAbstract:
Abstract We present an application of Scalable Deep Learning to analyze simulation data of the LHC proton-proton collisions at 13 TeV. We built a Deep Learning model based on the Convolutional Neural Network (CNN) which utilizes detector responses as two-dimensional images reflecting the geometry of the Compact Muon Solenoid (CMS) detector. The model discriminates signal events of the R-parity violating Supersymmetry (RPV SUSY) from the background events with multiple jets due to the inelastic QCD scattering (QCD multi-jets). With the CNN model, we obtained x1.85 efficiency and x1.2 expected significance with respect to the traditional cut-based method. We demonstrated the scalability of the model at a Large Scale with the High-Performance Computing (HPC) resources at the Korea Institute of Science and Technology Information (KISTI) up to 1024 nodes.
8
Indraniyati, Indraniyati, Abdul Hadjranul Fatah, and Nopriawan Berkat Asi. "Pemahaman Konsep Struktur Atom Setelah Pembelajaran Menggunakan Model Discovery Learning Berbantuan LKS pada Siswa Kelas X MIA-1 SMA Negeri 1 Paku." Jurnal Ilmiah Kanderang Tingang 11, no. 1 (2020): 180–92. http://dx.doi.org/10.37304/jikt.v11i1.85.
Full textAbstract:
Model Discovery Learning merupakan nama lain dari pembelajaran penemuan. Sesuai dengan namanya, model ini mengarahkan siswa untuk dapat menemukan sesuatu melalui proses pembelajaran yang dijalaninya. Siswa diarahkan untuk terbiasa menjadi saintis. Tujuan penelitian ini adalah untuk mendeskripsikan pemahaman konsep struktur atom: partikel penyusun inti atom, nomor atom, nomor massa, isotop, isoton, dan isobar. Setelah pembelajaran menggunakan model Discovery Learning berbantuan LKS pada Siswa Kelas X MIA-1 SMA Negeri 1 Paku, Barito Timur TahunAjaran 2017/2018. Penelitian ini melibatkan 25 siswa kelas X MIA-1 SMA Negeri 1 Paku, Barito Timur. Data hasil pemahaman konsep siswa diperoleh melalui pemberian tes tertulis berbentuk essay (uraian) terhadap siswa sebelum dan sesudah menggunakan model Discovery Learning, lembar pengamatan pengelolaan pembelajaran, lembar aktivitas belajar siswa menggunakan rubrik penilaian aktivitas kelompok. Data dianalisis dengan teknik deskriptif. Hasil penelitian menunjukkan bahwa sebagian besar pemahaman konsep siswa sudah benar menuliskan dan menjelaskan simbol atom sebagai lambang unsur yang dilengkapi dengan nomor atom dan nomor massa berjumlah 80%. Mendeskripsikan pengertian nomor atom (jumlah proton) sebagai identitas suatu unsur berjumlah 77,33%. Mendeskripsikan pengertian nomor massa sebagai jumlah proton dan neutron dalam suatu inti atom berjumlah 68%. Menuliskan nomor massa, jumlah proton, jumlah neutron, jumlah elektron pada unsur yang diketahui notasinya berjumlah 69,33%, menjelaskan pengertian isotop, isobar, isoton berjumlah 74,66%. Rata-rata pemahaman konsep siswa pada materi struktur atom berjumlah 73,86%.
9
Mohamed Zabidi, Zubainun, Nurul Batrisyia Muhamad Suhaimy, Ahmad Nazib Alias, Nur Diyana Nazihah Fuadi, and Nur Hanisah Hamzi. "Prediction Of Carboxylic Acid Toxicity Using Machine Learning Model." Malaysian Journal of Applied Sciences 8, no. 2 (2023): 28–36. http://dx.doi.org/10.37231/myjas.2023.8.2.357.
Full textAbstract:
Carboxylic acids are organic compounds characterized by the presence of a carboxyl functional group capable of donating a proton and forming carboxylate ions in aqueous solutions. The carboxylic acid has widely been used in in manufacturing and medical applications. The rapid growth in carboxylic acid has established a need to predict its toxicity. The purpose of this paper to build predictive toxicity of carboxylic acid models by using five molecular descriptors (refractive index, The octanol/water partition coefficient (log P), acid dissociation constant (pKa), density, and dipole moment) through Machine Learning algorithms. The accuracy of the Machine Learning algorithm was determined by using three different types of models which are Decision Tree, Random Forest and k-Nearest Neighbour (k-NN). Among the machine learning algorithms used, we have determined that the decision tree is the best model for predicting the toxicity of carboxylic acid. This finding demonstrates that the decision tree model exhibits an acceptable level of performance in predicting toxicity within the field of toxicology.
10
JUNG, Emrae JUNG, and Erhan ATAY. "Internationalization of the Automotive Industry by Extending IOL3 model: A Case Study of Geely Automobile." Eurasian Journal of Business and Economics 15, no. 29 (2022): 1–17. http://dx.doi.org/10.17015/ejbe.2022.029.01.
Full textAbstract:
Chinese companies have been heavily expanding their businesses globally during recent decades. In the literature, studies examine the dynamics behind their expansion strategies and build multinational Chinese companies called 'dragon multinationals.’ Pointing out the shortcomings of the ownership-locationinternalization (OLI) paradigm to explain the internationalization of these dragon multinationals, the linkage-leverage-learning (LLL) model was introduced by Mathews (2006). It was extended to the inward linkages-outward linkages-leveragelearning (IOL3) model by Lu et al. (2017). This paper aims to investigate forwarded linkages to understand how these linkages are utilized during further expansions of Chinese multinational companies (MNCs) in developing countries. Inward linkages that Geely gained through earlier acquisitions were studied through secondary sources. Then, Geely's latest acquisition of Proton was examined to identify forwarded linkages. Interviews were conducted with the management of Proton and its suppliers to define sources of know-how transferred to Proton and classify them as direct and indirect forwarded linkages.
11
Chen, S., L. Zhao, P. Liu, et al. "Deep Learning-Based Dose Prediction Model for Automated Spot-Scanning Proton Arc Planning." International Journal of Radiation Oncology*Biology*Physics 117, no. 2 (2023): e652. http://dx.doi.org/10.1016/j.ijrobp.2023.06.2077.
Full text
12
Mohamed, Amira, Hatem Ibrahem, Rui Yang, and Kibum Kim. "Optimization of Proton Exchange Membrane Electrolyzer Cell Design Using Machine Learning." Energies 15, no. 18 (2022): 6657. http://dx.doi.org/10.3390/en15186657.
Full textAbstract:
We propose efficient multiple machine learning (ML) models using specifically polynomial and logistic regression ML methods to predict the optimal design of proton exchange membrane (PEM) electrolyzer cells. The models predict eleven different parameters of the cell components for four different input parameters such as hydrogen production rate, cathode area, anode area, and the type of cell design (e.g., single or bipolar). The models fit well as we trained multiple machine learning models on 148 samples and validated the model performance on a test set of 16 samples. The average accuracy of the classification model and the mean absolute error is 83.6% and 6.825, respectively, which indicates that the proposed technique performs very well. We also measured the hydrogen production rate using a custom-made PEM electrolyzer cell fabricated based on the predicted parameters and compared it to the simulation result. Both results are in excellent agreement and within a negligible experimental uncertainty (i.e., a mean absolute error of 0.615). Finally, optimal PEM electrolyzer cells for commercial-scaled hydrogen production rates ranging from 500 to 5000 mL/min were designed using the machine learning models. To the best of our knowledge, we are the first group to model the PEM design problem with such large parameter predictions using machine learning with those specific input parameters. This study opens the route for providing a form of technology that can greatly save the cost and time required to develop water electrolyzer cells for future hydrogen production.
13
Akar, Simon, Gowtham Atluri, Thomas Boettcher, et al. "Progress in developing a hybrid deep learning algorithm for identifying and locating primary vertices." EPJ Web of Conferences 251 (2021): 04012. http://dx.doi.org/10.1051/epjconf/202125104012.
Full textAbstract:
The locations of proton-proton collision points in LHC experiments are called primary vertices (PVs). Preliminary results of a hybrid deep learning algorithm for identifying and locating these, targeting the Run 3 incarnation of LHCb, have been described at conferences in 2019 and 2020. In the past year we have made significant progress in a variety of related areas. Using two newer Kernel Density Estimators (KDEs) as input feature sets improves the fidelity of the models, as does using full LHCb simulation rather than the “toy Monte Carlo” originally (and still) used to develop models. We have also built a deep learning model to calculate the KDEs from track information. Connecting a tracks-to-KDE model to a KDE-to-hists model used to find PVs provides a proof-of-concept that a single deep learning model can use track information to find PVs with high efficiency and high fidelity. We have studied a variety of models systematically to understand how variations in their architectures affect performance. While the studies reported here are specific to the LHCb geometry and operating conditions, the results suggest that the same approach could be used by the ATLAS and CMS experiments.
14
Geng, Huaizhi, Zhongxing Liao, Quynh-Nhu Nguyen, et al. "Implementation of Machine Learning Models to Ensure Radiotherapy Quality for Multicenter Clinical Trials: Report from a Phase III Lung Cancer Study." Cancers 15, no. 4 (2023): 1014. http://dx.doi.org/10.3390/cancers15041014.
Full textAbstract:
The outcome of the patient and the success of clinical trials involving RT is dependent on the quality assurance of the RT plans. Knowledge-based Planning (KBP) models using data from a library of high-quality plans have been utilized in radiotherapy to guide treatment. In this study, we report on the use of these machine learning tools to guide the quality assurance of multicenter clinical trial plans. The data from 130 patients submitted to RTOG1308 were included in this study. Fifty patient cases were used to train separate photon and proton models on a commercially available platform based on principal component analysis. Models evaluated 80 patient cases. Statistical comparisons were made between the KBP plans and the original plans submitted for quality evaluation. Both photon and proton KBP plans demonstrate a statistically significant improvement of quality in terms of organ-at-risk (OAR) sparing. Proton KBP plans, a relatively emerging technique, show more improvements compared with photon plans. The KBP proton model is a useful tool for creating proton plans that adhere to protocol requirements. The KBP tool was also shown to be a useful tool for evaluating the quality of RT plans in the multicenter clinical trial setting.
15
Zhu, Cong, Radhe Mohan, Steven H. Lin, et al. "Identifying Individualized Risk Profiles for Radiotherapy-Induced Lymphopenia Among Patients With Esophageal Cancer Using Machine Learning." JCO Clinical Cancer Informatics, no. 5 (September 2021): 1044–53. http://dx.doi.org/10.1200/cci.21.00098.
Full textAbstract:
PURPOSE Radiotherapy (RT)-induced lymphopenia (RIL) is commonly associated with adverse clinical outcomes in patients with cancer. Using machine learning techniques, a retrospective study was conducted for patients with esophageal cancer treated with proton and photon therapies to characterize the principal pretreatment clinical and radiation dosimetric risk factors of grade 4 RIL (G4RIL) as well as to establish G4RIL risk profiles. METHODS A single-institution retrospective data of 746 patients with esophageal cancer treated with photons (n = 500) and protons (n = 246) was reviewed. The primary end point of our study was G4RIL. Clustering techniques were applied to identify patient subpopulations with similar pretreatment clinical and radiation dosimetric characteristics. XGBoost was built on a training set (n = 499) to predict G4RIL risks. Predictive performance was assessed on the remaining n = 247 patients. SHapley Additive exPlanations were used to rank the importance of individual predictors. Counterfactual analyses compared patients' risk profiles assuming that they had switched modalities. RESULTS Baseline absolute lymphocyte count and volumes of lung and spleen receiving ≥ 15 and ≥ 5 Gy, respectively, were the most important G4RIL risk determinants. The model achieved sensitivitytesting-set 0.798 and specificitytesting-set 0.667 with an area under the receiver operating characteristics curve (AUCtesting-set) of 0.783. The G4RIL risk for an average patient receiving protons increased by 19% had the patient switched to photons. Reductions in G4RIL risk were maximized with proton therapy for patients with older age, lower baseline absolute lymphocyte count, and higher lung and heart dose. CONCLUSION G4RIL risk varies for individual patients with esophageal cancer and is modulated by radiotherapy dosimetric parameters. The framework for machine learning presented can be applied broadly to study risk determinants of other adverse events, providing the basis for adapting treatment strategies for mitigation.
16
Williams, Michael T., Chiho Sugimoto, Samantha L. Regan, et al. "Cognitive and behavioral effects of whole brain conventional or high dose rate (FLASH) proton irradiation in a neonatal Sprague Dawley rat model." PLOS ONE 17, no. 9 (2022): e0274007. http://dx.doi.org/10.1371/journal.pone.0274007.
Full textAbstract:
Recent studies suggest that ultra-high dose rates of proton radiation (>40 Gy/s; FLASH) confer less toxicity to exposed healthy tissue and reduce cognitive decline compared with conventional radiation dose rates (~1 Gy/s), but further preclinical data are required to demonstrate this sparing effect. In this study, postnatal day 11 (P11) rats were treated with whole brain irradiation with protons at a total dose of 0, 5, or 8 Gy, comparing a conventional dose rate of 1 Gy/s vs. a FLASH dose rate of 100 Gy/s. Beginning on P64, rats were tested for locomotor activity, acoustic and tactile startle responses (ASR, TSR) with or without prepulses, novel object recognition (NOR; 4-object version), striatal dependent egocentric learning ([configuration A] Cincinnati water maze (CWM-A)), prefrontal dependent working memory (radial water maze (RWM)), hippocampal dependent spatial learning (Morris water maze (MWM)), amygdala dependent conditioned freezing, and the mirror image CWM [configuration B (CWM-B)]. All groups had deficits in the CWM-A procedure. Weight reductions, decreased center ambulation in the open-field, increased latency on day-1 of RWM, and deficits in CWM-B were observed in all irradiated groups, except the 5 Gy FLASH group. ASR and TSR were reduced in the 8 Gy FLASH group and day-2 latencies in the RWM were increased in the FLASH groups compared with controls. There were no effects on prepulse trials of ASR or TSR, NOR, MWM, or conditioned freezing. The results suggest striatal and prefrontal cortex are sensitive regions at P11 to proton irradiation, with reduced toxicity from FLASH at 5 Gy.
17
Pan, Yuwei, Haijun Ruan, Yagya N. Regmi, Billy Wu, Huizhi Wang, and Nigel Brandon. "A Machine Learning Accelerated Hierarchical 3D+1D Model for Proton Exchange Membrane Fuel Cells." ECS Meeting Abstracts MA2023-02, no. 37 (2023): 1706. http://dx.doi.org/10.1149/ma2023-02371706mtgabs.
Full textAbstract:
Physics-based continuum models for proton exchange membrane fuel cells (PEMFCs) are an essential tool for fuel cell design and management. To date, many continuum models, ranging from 1D to 3D, have been developed for PEMFCs. Although computationally efficient, 1D models do not account for heterogeneity in flow fields, which negatively impact their accuracy. In contrast, 2D and 3D models are usually more representative of actual operating conditions but computationally intensive due to the coupled partial differential equations and large number of mesh elements involved. To overcome these issues, a hierarchical approach that combines a 2D/3D description of flow fields, gas diffusion layers (GDLs) and a simplified microporous layer (MPL)/catalyst layer (CL)/membrane sub-model has been proposed in the literature. However, studies based on this method often use a simplified or 0D MPL/CL/membrane sub-model, whose results may deviate from a full 1D description due to the neglected nonlinearity, especially at higher loads. In this study, we present a computationally efficient 3D+1D hierarchical model for PEMFCs accelerated by machine learning. The 3D model, which captures the two-phase flow in the gas channels and GDLs, is coupled with a full 1D description of the MPLs, membrane, CLs, and CL agglomerates by exchanging boundary values and fluxes, as shown in the figure. To avoid the high computing cost increase associated with the full 1D description, we develop a physics-informed neural network to replace the 1D sub-model for coupling with the 3D model, while maintaining the full description of fuel cell internal states. Large synthetic datasets are generated using the 1D model for training the neural network, ensuring the accuracy of the model. The proposed 3D+1D model is validated against experimentally obtained polarization curves and high frequency resistances under different relative humidities. The proposed model is then used to study the nonlinear distribution of the internal states along the thickness direction of the membrane electrode assembly as well as in the 3D flow field. The model is also highly effective in elucidating the dominant voltage loss factor under different operating conditions. Our developed model offers high accuracy at low computing cost under a wide range of operating conditions, potentially aiding the rapid optimization of both the membrane electrode assembly and the gas channel geometry and advance the water and thermal management of existing fuel cell designs. Figure 1
18
Ricks, L. J., A. Sambyal, J. McDonald, et al. "Utilization of Machine Learning and Proton Collaborative Group Data to Develop a Model for Predictive Prostate Cancer Proton Radiation Therapy Outcomes." International Journal of Radiation Oncology*Biology*Physics 99, no. 2 (2017): E262. http://dx.doi.org/10.1016/j.ijrobp.2017.06.1230.
Full text
19
Przepiórski, Michał, and Marcin Moździerz. "Artificial Neural Networks as Efficient Models of Proton Exchange Membrane Fuel Cells." Journal of Physics: Conference Series 2812, no. 1 (2024): 012022. http://dx.doi.org/10.1088/1742-6596/2812/1/012022.
Full textAbstract:
Abstract Utilization of machine learning methodologies, particularly artificial neural networks (ANNs), presents a good approach to accurately model physical systems. Such predictive simulations offer the ability to predict system performance across diverse operational conditions without the need of use mathematical descriptions. This approach contrast with traditional, time-consuming and unstable approaches reliant on partial differential equations. In this study, ANN methodology is used to obtain the characteristics of proton exchange membrane fuel cells (PEMFCs). PEMFC are low temperature devices which convert chemical energy into electricity. This devices are promising applications in the automotive sector. Utilizing data gained from computational fluid dynamics simulations of PEMFCs, was explored various data collection techniques and network architectures to check their impact on predictive fidelity. Conclusions show that the ANN-based framework enables rapid prediction of current-voltage characteristics, achieving accuracy levels surpassing 90%. Practical of machine learning model implications were discussed, accenting its utility in optimizing PEMFC operational parameters and its potential integration within digital twin frameworks as a data-driven surrogate model. This study underscores the efficiency of machine learning techniques in advancing the comprehension and optimization of complex physical systems such as PEM-FCs, thereby paving the way for their use in engineering and energy sectors.
20
Stumpo, Mirko, Monica Laurenza, Simone Benella, and Maria Federica Marcucci. "Predicting the Energetic Proton Flux with a Machine Learning Regression Algorithm." Astrophysical Journal 975, no. 1 (2024): 8. http://dx.doi.org/10.3847/1538-4357/ad7734.
Full textAbstract:
Abstract The need for real-time monitoring and alerting systems for space weather hazards has grown significantly in the last two decades. One of the most important challenges for space mission operations and planning is the prediction of solar proton events (SPEs). In this context, artificial intelligence and machine learning techniques have opened a new frontier, providing a new paradigm for statistical forecasting algorithms. The great majority of these models aim to predict the occurrence of an SPE, i.e., they are based on the classification approach. This work is oriented toward the successful implementation of onboard prediction systems, which is essential for the future of space exploration. We present a simple and efficient machine learning regression algorithm that is able to forecast the energetic proton flux up to 1 hr ahead by exploiting features derived from the electron flux only. This approach could be helpful in improving monitoring systems of the radiation risk in both deep space and near-Earth environments. The model is very relevant for mission operations and planning, especially when flare characteristics and source location are not available in real time, as at Mars distance.
21
Graziani, G., L. Anderlini, S. Mariani, E. Franzoso, L. L. Pappalardo, and P. di Nezza. "A Neural-Network-defined Gaussian Mixture Model for particle identification applied to the LHCb fixed-target programme." Journal of Instrumentation 17, no. 02 (2022): P02018. http://dx.doi.org/10.1088/1748-0221/17/02/p02018.
Full textAbstract:
Abstract Particle identification in large high-energy physics experiments typically relies on classifiers obtained by combining many experimental observables. Predicting the probability density function (pdf) of such classifiers in the multivariate space covering the relevant experimental features is usually challenging. The detailed simulation of the detector response from first principles cannot provide the reliability needed for the most precise physics measurements. Data-driven modelling is usually preferred, though sometimes limited by the available data size and different coverage of the feature space by the control channels. In this paper, we discuss a novel approach to the modelling of particle identification classifiers using machine-learning techniques. The marginal pdf of the classifiers is described with a Gaussian Mixture Model, whose parameters are predicted by Multi Layer Perceptrons trained on calibration data. As a proof of principle, the method is applied to the data acquired by the LHCb experiment in its fixed-target configuration. The model is trained on a data sample of proton-neon collisions and applied to smaller data samples of proton-helium and proton-argon collisions collected at different centre-of-mass energies. The method is shown to perform better than a detailed simulation-based approach, to be fast and suitable to be applied to a large variety of use cases.
22
Kalendralis, Petros, Mr Matthijs Sloep, Mr Jasper Snel, et al. "A FEDERATED LEARNING IT-INFRASTRUCTURE TO SUPPORT THE DUTCH MODEL-BASED APPROACH FOR PROTON THERAPY." Physica Medica 104 (December 2022): S155—S156. http://dx.doi.org/10.1016/s1120-1797(22)02491-7.
Full text
23
Radi, Amr. "Modeling charged-particle multiplicity distributions at LHC." Modern Physics Letters A 35, no. 36 (2020): 2050302. http://dx.doi.org/10.1142/s0217732320503022.
Full textAbstract:
With many applications in high-energy physics, Deep Learning or Deep Neural Network (DNN) has become noticeable and practical in recent years. In this article, a new technique is presented for modeling the charged particles multiplicity distribution [Formula: see text] of Proton-Proton [Formula: see text] collisions using an efficient DNN model. The charged particles multiplicity n, the total center of mass energy [Formula: see text], and the pseudorapidity [Formula: see text] used as input in DNN model and the desired output is [Formula: see text]. DNN was trained to build a function, which studies the relationship between [Formula: see text]. The DNN model showed a high degree of consistency in matching the data distributions. The DNN model is used to predict with [Formula: see text] not included in the training set. The expected [Formula: see text] had effectively merged the experimental data and the values expected indicate a strong agreement with Large Hadron Collider (LHC) for ATLAS measurement at [Formula: see text], 7 and 8 TeV.
24
Tsoi, Ho Fung, Adrian Alan Pol, Vladimir Loncar, et al. "Symbolic Regression on FPGAs for Fast Machine Learning Inference." EPJ Web of Conferences 295 (2024): 09036. http://dx.doi.org/10.1051/epjconf/202429509036.
Full textAbstract:
The high-energy physics community is investigating the potential of deploying machine-learning-based solutions on Field-Programmable Gate Arrays (FPGAs) to enhance physics sensitivity while still meeting data processing time constraints. In this contribution, we introduce a novel end-to-end procedure that utilizes a machine learning technique called symbolic regression (SR). It searches the equation space to discover algebraic relations approximating a dataset. We use PySR (a software to uncover these expressions based on an evolutionary algorithm) and extend the functionality of hls4ml (a package for machine learning inference in FPGAs) to support PySR-generated expressions for resource-constrained production environments. Deep learning models often optimize the top metric by pinning the network size because the vast hyperparameter space prevents an extensive search for neural architecture. Conversely, SR selects a set of models on the Pareto front, which allows for optimizing the performance-resource trade-off directly. By embedding symbolic forms, our implementation can dramatically reduce the computational resources needed to perform critical tasks. We validate our method on a physics benchmark: the multiclass classification of jets produced in simulated proton-proton collisions at the CERN Large Hadron Collider. We show that our approach can approximate a 3-layer neural network using an inference model that achieves up to a 13-fold decrease in execution time, down to 5 ns, while still preserving more than 90% approximation accuracy.
25
Auricchio, Silvia, Francesco Cirotto, and Antonio Giannini. "VBF Event Classification with Recurrent Neural Networks at ATLAS’s LHC Experiment." Applied Sciences 13, no. 5 (2023): 3282. http://dx.doi.org/10.3390/app13053282.
Full textAbstract:
A novel machine learning (ML) approach based on a recurrent neural network (RNN) for event topology identification in high energy physics (HEP) is presented. The vector-boson fusion (VBF) production mechanism arising in proton-to-proton collisions is predicted both from the current theoretical model of the particle physics, the standard model, and from its extensions that foresee potential new physics phenomena. This physical process has a well-defined event topology in the final state and a distinctive detector signature. In this work, an ML approach based on the RNN architecture is developed to deal with hadronic-only event information in order to enhance the acceptance of this production mechanism in physics analysis of the data. This technique was applied to a physics analysis in the context of high-mass diboson resonance searches using data collected by the ATLAS experiment.
26
Aad, G., E. Aakvaag, B. Abbott, et al. "Accuracy versus precision in boosted top tagging with the ATLAS detector." Journal of Instrumentation 19, no. 08 (2024): P08018. http://dx.doi.org/10.1088/1748-0221/19/08/p08018.
Full textAbstract:
Abstract The identification of top quark decays where the top quark has a large momentum transverse to the beam axis, known as top tagging, is a crucial component in many measurements of Standard Model processes and searches for beyond the Standard Model physics at the Large Hadron Collider. Machine learning techniques have improved the performance of top tagging algorithms, but the size of the systematic uncertainties for all proposed algorithms has not been systematically studied. This paper presents the performance of several machine learning based top tagging algorithms on a dataset constructed from simulated proton-proton collision events measured with the ATLAS detector at √ s = 13 TeV. The systematic uncertainties associated with these algorithms are estimated through an approximate procedure that is not meant to be used in a physics analysis, but is appropriate for the level of precision required for this study. The most performant algorithms are found to have the largest uncertainties, motivating the development of methods to reduce these uncertainties without compromising performance. To enable such efforts in the wider scientific community, the datasets used in this paper are made publicly available.
27
Malinović-Milićević, Slavica, Milan M. Radovanović, Sonja D. Radenković, et al. "Application of Solar Activity Time Series in Machine Learning Predictive Modeling of Precipitation-Induced Floods." Mathematics 11, no. 4 (2023): 795. http://dx.doi.org/10.3390/math11040795.
Full textAbstract:
This research is devoted to the determination of hidden dependencies between the flow of particles that come from the Sun and precipitation-induced floods in the United Kingdom (UK). The analysis covers 20 flood events during the period from October 2001 to December 2019. The parameters of solar activity were used as model input data, while precipitations data in the period 10 days before and during each flood event were used as model output. The time lag of 0–9 days was taken into account in the research. Correlation analysis was conducted to determine the degree of randomness for the time series of input and output parameters. For establishing a potential causative link, machine learning classification predictive modeling was applied. Two approaches, the decision tree, and the random forest were used. We analyzed the accuracy of classification models forecast from 0 to 9 days in advance. It was found that the most important factors for flood forecasting are proton density with a time lag of 9, differential proton flux in the range of 310–580 keV, and ion temperature. Research in this paper has shown that the decision tree model is more accurate and adequate in predicting the appearance of precipitation-induced floods up to 9 days ahead with an accuracy of 91%. The results of this study confirmed that by increasing technical capabilities, using improved machine learning techniques and large data sets, it is possible to improve the understanding of the physical link between the solar wind and tropospheric weather and help improve severe weather forecasting.
28
Li, Qi, Wei Rong Chen, Zhi Xiang Liu, Shu Kui Liu, and Wei Min Tian. "A Nonlinear Fuel Cell Model Based on Adaptive Neuro-Fuzzy Inference System." Applied Mechanics and Materials 321-324 (June 2013): 1357–60. http://dx.doi.org/10.4028/www.scientific.net/amm.321-324.1357.
Full textAbstract:
A nonlinear model of proton exchange membrane fuel cell (PEMFC) based on an adaptive neuro-fuzzy inference system (ANFIS) is proposed to study different operational conditions effect on the dynamic response of Ballard 1.2kW Nexa power module. A hybrid learning algorithm combining back propagation (BP) and least squares estimate (LSE) is adopted to identify the parameters of input and output membership functions for the improvement of training efficiency in the ANFIS. The comparisons with the experimental data demonstrate that the obtained ANFIS model can efficiently approximate the dynamic output response of Nexa power module and is capable of predicting dynamic performance in terms of stack output voltage with a high accuracy.
29
Li, Xin, Lu Bai, Zuhao Ge, Zhizhe Lin, Xi Yang, and Teng Zhou. "Early Diagnosis of Neuropsychiatric Systemic Lupus Erythematosus by Deep Learning Enhanced Magnetic Resonance Spectroscopy." Journal of Medical Imaging and Health Informatics 11, no. 5 (2021): 1341–47. http://dx.doi.org/10.1166/jmihi.2021.3378.
Full textAbstract:
The neuropsychiatric systemic lupus erythematosus (NPSLE) has higher disability and mortality rates, which is one of the main causes of death in systemic lupus erythematosus (SLE) patients. Magnetic resonance spectroscopy (MRS) can detect the changes of metabolites in different intracranial areas in vivo in patients with SLE, so as to provide evidence for the early diagnosis of NPSLE. Different from the conventional single-voxel MRS, which can only screen one brain region with one metabolic change, we simultaneously detect 13 kinds of intracranial metabolic changes in nine brain regions by multivoxel proton MRS (MVS). We use a recursive feature elimination algorithm to select the most related metabolites for better identifying NPSLE. To accurately diagnosis NPSLE by these intracranial metabolites, we train a support vector machine deep stacked network (SVM-DSN) for quantitative analysis of these metabolites. Comparing with the conventional statistic method, which is about 70% of accuracy, the proposed model achieves 97.5% of accuracy for NPSLE diagnosis. We conclude the trained SVM-DSN can effectively analyze the metabolites obtained by multivoxel proton MRS for NPSLE diagnosis, which may help to early diagnosis and intervention of NPSLE, and alleviate the bias of manual screening.
30
Atkinson, M. C., and W. H. Dickhoff. "Learning from knockout reactions using a dispersive optical model." Frontiers in Physics 12 (January 6, 2025). https://doi.org/10.3389/fphy.2024.1505982.
Full textAbstract:
We present the empirical dispersive optical model (DOM) as applied to direct nuclear reactions. The DOM links both scattering and bound-state experimental data through a dispersion relation, which allows for fully consistent, data-informed predictions for nuclei where such data exist. In particular, we review investigations of the electron-induced proton knockout reaction from both 40Ca and 48Ca in a distorted-wave impulse approximation (DWIA) utilizing the DOM for a fully consistent description. Viewing these reactions through the lens of the DOM allows us to connect the documented quenching of spectroscopic factors with the increased high-momentum proton content in neutron-rich nuclei. A similar DOM-DWIA description of the proton-induced knockout from 40Ca, however, does not currently fit in the consistent story of its electron-induced counterpart. With the main difference in the proton-induced case being the use of an effective proton–proton interaction, we suggest that a more sophisticated in-medium interaction would produce consistent results.
31
Gao, Yuan, Chih-Wei Chang, Shaoyan Pan, et al. "Deep learning-based synthetic dose-weighted LET map generation for intensity modulated proton therapy." Physics in Medicine & Biology, December 13, 2023. http://dx.doi.org/10.1088/1361-6560/ad154b.
Full textAbstract:
Abstract The advantage of proton therapy as compared to photon therapy stems from the Bragg peak effect, which allows protons to deposit most of their energy directly at the tumor while sparing healthy tissue. However, even with such benefits, proton therapy does present certain challenges. The biological effectiveness differences between protons and photons are not fully incorporated into clinical treatment planning processes. In current clinical practice, the relative biological effectiveness (RBE) between protons and photons is set as constant 1.1. Numerous studies have suggested that the RBE of protons can exhibit significant variability. Given these findings, there is a substantial interest in refining proton therapy treatment planning to better account for the variable RBE. Dose-average Linear Energy Transfer (LETd) is a key physical parameter for evaluating the RBE of proton therapy and aids in optimizing proton treatment plans. Calculating precise LETd distributions necessitates the use of intricate physical models and the execution of specialized Monte-Carlo simulation software, which is a computationally intensive and time-consuming progress. In response to these challenges, we propose a deep learning (DL) based framework designed to predict the LETd distribution map using the dose distribution map. This approach aims to simplify the process and increase the speed of LETd map generation in clinical settings. The proposed CycleGAN model has demonstrated superior performance over other GAN-based models. The Mean Absolute Error (MAE), Peak Signal-to-Noise Ratio (PSNR) and Normalized Cross Correlation (NCC) of the LETd maps generated by the proposed method are 0.096±0.019 keV/µm, 24.203±2.683 dB, and 0.997±0.002, respectively. The MAE of the proposed method in the clinical target volume, bladder, and rectum are 0.193±0.103, 0.277±0.112, and 0.211±0.086 keV/µm, respectively. The proposed framework has demonstrated the feasibility of generating synthetic LETd maps from dose maps and has the potential to improve proton therapy planning by providing accurate LETd information。
32
Williams, Michael T., Chiho Sugimoto, Samantha L. Regan, et al. "Whole brain proton irradiation in adult Sprague Dawley rats produces dose dependent and non-dependent cognitive, behavioral, and dopaminergic effects." Scientific Reports 10, no. 1 (2020). http://dx.doi.org/10.1038/s41598-020-78128-1.
Full textAbstract:
AbstractProton radiotherapy causes less off-target effects than X-rays but is not without effect. To reduce adverse effects of proton radiotherapy, a model of cognitive deficits from conventional proton exposure is needed. We developed a model emphasizing multiple cognitive outcomes. Adult male rats (10/group) received a single dose of 0, 11, 14, 17, or 20 Gy irradiation (the 20 Gy group was not used because 50% died). Rats were tested once/week for 5 weeks post-irradiation for activity, coordination, and startle. Cognitive assessment began 6-weeks post-irradiation with novel object recognition (NOR), egocentric learning, allocentric learning, reference memory, and proximal cue learning. Proton exposure had the largest effect on activity and prepulse inhibition of startle 1-week post-irradiation that dissipated each week. 6-weeks post-irradiation, there were no effects on NOR, however proton exposure impaired egocentric (Cincinnati water maze) and allocentric learning and caused reference memory deficits (Morris water maze), but did not affect proximal cue learning or swimming performance. Proton groups also had reduced striatal levels of the dopamine transporter, tyrosine hydroxylase, and the dopamine receptor D1, effects consistent with egocentric learning deficits. This new model will facilitate investigations of different proton dose rates and drugs to ameliorate the cognitive sequelae of proton radiotherapy.
33
Jiang, Zhuoran, Jerimy C. Polf, Carlos A. Barajas, Matthias K. Gobbert, and Lei Ren. "A feasibility study of enhanced prompt gamma imaging for range verification in proton therapy using deep learning." Physics in Medicine & Biology, February 27, 2023. http://dx.doi.org/10.1088/1361-6560/acbf9a.
Full textAbstract:
Abstract Range uncertainty is a major concern affecting delivery precision in proton therapy. The Compton camera (CC)-based prompt-gamma (PG) imaging is a promising technique to provide 3D in-vivo range verification. However, conventional back-projected PG images suffer from severe distortions due to the limited view of CC, significantly limiting its clinical utility. Deep learning has demonstrated effectiveness in enhancing medical images from limited-view measurements. But different from other medical images with abundant anatomical structures, PGs emitted from a proton pencil beam take up an extremely low portion of the 3D image space, presenting both the attention and the imbalance challenge for deep learning. To solve these issues, we proposed a two-tier deep learning-based method with a novel weighted axis-projection loss to generate precise 3D PG images for proton range verification. This method consists of two models: first, a localization model is trained to define a region-of-interest (ROI) in the distorted back-projected PG image that contains the proton pencil beam; second, an enhancement model is trained to restore the true PG emissions with ROI attention. In this study, we simulated proton pencil beams delivered at clinical dose rates and levels in a tissue-equivalent phantom using Monte-Carlo (MC). PG detection with a CC was simulated using the MC-Plus-Detector-Effects model. Images were reconstructed using kernel-weighted-back-projection algorithm, and were then enhanced by the proposed method. Results demonstrated that the method effectively restored the 3D shape of PGs with proton pencil beam range clearly visible in all testing cases. Range errors were within 2 pixels (4 mm) in all directions in most cases at a dose level of 10^9 protons/beam. The method is fully automatic and nearly real-time. Overall, the preliminary study demonstrated the feasibility of the proposed method to generate accurate 3D PG images, providing a powerful tool for high-precision in-vivo range verification of proton therapy.
34
Zhu, Jiahua, Taoran Cui, Yin Zhang, et al. "Comprehensive Output Estimation of Double Scattering Proton System With Analytical and Machine Learning Models." Frontiers in Oncology 11 (January 31, 2022). http://dx.doi.org/10.3389/fonc.2021.756503.
Full textAbstract:
ObjectivesThe beam output of a double scattering proton system varies for each combination of beam option, range, and modulation and therefore is difficult to be accurately modeled by the treatment planning system (TPS). This study aims to design an empirical method using the analytical and machine learning (ML) models to estimate proton output in a double scattering proton system.Materials and MethodsThree analytical models using polynomial, linear, and logarithm–polynomial equations were generated on a training dataset consisting of 1,544 clinical measurements to estimate proton output for each option. Meanwhile, three ML models using Gaussian process regression (GPR) with exponential kernel, squared exponential kernel, and rational quadratic kernel were also created for all options combined. The accuracy of each model was validated against 241 additional clinical measurements as the testing dataset. Two most robust models were selected, and the minimum number of samples needed for either model to achieve sufficient accuracy ( ± 3%) was determined by evaluating the mean average percentage error (MAPE) with increasing sample number. The differences between the estimated outputs using the two models were also compared for 1,000 proton beams with a randomly generated range, and modulation for each option.ResultsThe polynomial model and the ML GPR model with exponential kernel yielded the most accurate estimations with less than 3% deviation from the measured outputs. At least 20 samples of each option were needed to build the polynomial model with less than 1% MAPE, whereas at least a total of 400 samples were needed for all beam options to build the ML GPR model with exponential kernel to achieve comparable accuracy. The two independent models agreed with less than 2% deviation using the testing dataset.ConclusionThe polynomial model and the ML GPR model with exponential kernel were built for proton output estimation with less than 3% deviations from the measurements. They can be used as an independent output prediction tool for a double scattering proton beam and a secondary output check tool for a cross check between themselves.
35
Hasibuan, Israwati, Cawang Cawang, and Dedeh Kurniasih. "PENGARUH PENGGUNAAN MODEL PEMBELAJARAN KOOPERATIF TIPE STUDENT TEAMS ACHIEVEMENT DIVISION (STAD) TERHADAP HASIL BELAJAR PADA MATERI STRUKTUR ATOM SISWA KELAS X SMA NEGERI 10 PONTIANAK." AR-RAZI Jurnal Ilmiah 7, no. 2 (2019). http://dx.doi.org/10.29406/ar-r.v7i2.1726.
Full textAbstract:
This study was conducted to determine the differences in student learning outcomes based on the low student learning outcomes which are below the KKM value ≥ 70 and aimed at knowing the magnitude of the influence of the use of cooperative models Student Teams Achievement Division (STAD) with those taught using conventional models of class X class 10 Pontianak SMA on the material of the atomic structure sub protons, neutrons, electrons and isotopes, isobar, isoton. The form of the research used was quasi-experimental research with a pretest-posttest design control group research design. The sample in this study was class XA students as the control class and XB as the experimental class. The data collection technique used was a measurement technique. Data collection tools used were interviews and test results of student learning in the form of essays. The results of statistical tests using the Mann Whitney U-test with α = 5% obtained a probability of <0.05, which meanth that Ho was rejected. These results indicated that there were significant differences between the learning outcomes of class X students of Pontianak State Senior High School on the material of atomic structure sub proton, neutron, electron and isotope, isobar, isoton. The magnitude of the influence of the use of the cooperative model Student Teams Achievement Division (STAD) on the atomic structure material of protons, neutrons, electrons and isotopes, isobars, isotons on student learning outcomes calculated by Effect Size was 0.431 which is categorized as medium. This showed that the use of the cooperative model Student Teams Achievement Division (STAD) type had a categorical influence on the learning outcomes of class X students of SMA Negeri 10 Pontianak on the material of atomic structure sub proton, neutron, electron and isotope, isobar, isoton.
36
Chiravalle, Vincent P. "Using deep machine learning to interpret proton radiography data from a pulsed power experiment." AIP Advances 13, no. 8 (2023). http://dx.doi.org/10.1063/5.0158167.
Full textAbstract:
Deep machine learning is used to analyze a proton radiograph from a tin pulsed power experiment and determine density values for each pixel in the image. Two promising convolutional neural network architectures that have proven to be effective for image analysis in other applications are applied to analyze a proton radiograph and find density values. The process of creating a suitable training dataset is described, involving the Lagrangian hydrodynamic model used for simulations of the experiment, the proton radiography forward model to make synthetic images for training, and the manner in which data augmentation is used to expand the resulting image dataset. It is shown that machine learning not only produces a reasonable density field but is also able to predict features in the density field that are suggested by the proton radiograph but not captured by simulations.
37
Rentería, David, Roger J. Hernández-Pinto, German Sborlini, and Pia Zurita. "Reconstructing partonic kinematics at colliders with machine learning." SciPost Physics Core 5, no. 4 (2022). http://dx.doi.org/10.21468/scipostphyscore.5.4.049.
Full textAbstract:
In the context of high-energy physics, a reliable description of the parton-level kinematics plays a crucial role for understanding the internal structure of hadrons and improving the precision of the calculations. In proton-proton collisions, this represents a challenging task since extracting such information from experimental data is not straightforward. With this in mind, we propose to tackle this problem by studying the production of one hadron and a direct photon in proton-proton collisions, including up to Next-to-Leading Order Quantum Chromodynamics and Leading-Order Quantum Electrodynamics corrections. Using Monte-Carlo integration, we simulate the collisions and analyze the events to determine the correlations among measurable and partonic quantities. Then, we use these results to feed three different Machine Learning algorithms that allow us to find the momentum fractions of the partons involved in the process, in terms of suitable combinations of the final state momenta. Our results are compatible with previous findings and suggest a powerful application of Machine-Learning to model high-energy collisions at the partonic-level with high-precision.
38
Desai, Ronak, Thomas Zhang, John J. Felice, et al. "Applying Machine‐Learning Methods to Laser Acceleration of Protons: Lessons Learned From Synthetic Data." Contributions to Plasma Physics, November 22, 2024. http://dx.doi.org/10.1002/ctpp.202400080.
Full textAbstract:
ABSTRACTIn this study, we consider three different machine‐learning methods—a three‐hidden‐layer neural network, support vector regression, and Gaussian process regression—and compare how well they can learn from a synthetic data set for proton acceleration in the Target Normal Sheath Acceleration regime. The synthetic data set was generated from a previously published theoretical model by Fuchs et al. 2005 that we modified. Once trained, these machine‐learning methods can assist with efforts to maximize the peak proton energy, or with the more general problem of configuring the laser system to produce a proton energy spectrum with desired characteristics. In our study, we focus on both the accuracy of the machine‐learning methods and the performance on one GPU including memory consumption. Although it is arguably the least sophisticated machine‐learning model we considered, support vector regression performed very well in our tests.
39
Tang, Xueyan, Hok Wan Chan Tseung, Douglas Moseley, et al. "Deep learning based linear energy transfer calculation for proton therapy." Physics in Medicine & Biology, May 7, 2024. http://dx.doi.org/10.1088/1361-6560/ad4844.
Full textAbstract:
Abstract Objective: This study aims to address the limitations of traditional methods for calculating linear energy transfer (LET), a critical component in assessing relative biological effectiveness (RBE). Currently, Monte Carlo (MC) simulation, the gold-standard for accuracy, is resource-intensive and slow for dose optimization, while the speedier analytical approximation has compromised accuracy. Our objective was to prototype a deep-learning-based model for calculating dose-averaged LET (LETd) using patient anatomy and dose-to-water (DW) data, facilitating real-time biological dose evaluation and LET optimization within proton treatment planning systems.&#xD;Approach: 275 4-field prostate proton Stereotactic Body Radiotherapy (SBRT) plans were analyzed, rendering a total of 1100 fields. Those were randomly split into 880, 110, and 110 fields for training, validation, and testing. A 3D Cascaded UNet model, along with data processing and inference pipelines, was developed to generate patient-specific LETd distributions from CT images and DW. The accuracy of the LETd of the test dataset was evaluated against MC-generated ground truth through voxel-based mean absolute error (MAE) and gamma analysis.&#xD;Main Results: The proposed model accurately inferred LETd distributions for each proton field in the test dataset. A single-field LETd calculation took around 100 ms with trained models running on a NVidia A100 GPU. The selected model yielded an average MAE of 0.94±0.14 MeV/cm and a gamma passing rate of 97.4% ± 1.3% when applied to the test dataset, with the largest discrepancy at the edge of fields where the dose gradient was the largest and counting statistics was the lowest.&#xD;Significance: This study demonstrates that deep-learning-based models can efficiently calculate LETd with high accuracy as a fast-forward approach. The model shows great potential to be utilized for optimizing the RBE of proton treatment plans. Future efforts will focus on enhancing the model’s performance and evaluating its adaptability to different clinical scenarios.
40
Devlin, Peter, Jian-Wei Qiu, Felix Ringer, and Nobuo Sato. "Diffusion model approach to simulating electron-proton scattering events." Physical Review D 110, no. 1 (2024). http://dx.doi.org/10.1103/physrevd.110.016030.
Full textAbstract:
Generative artificial intelligence is a fast-growing area of research offering various avenues for exploration in high-energy nuclear physics. In this work, we explore the use of generative models for simulating electron-proton collisions relevant to experiments like the Continuous Electron Beam Accelerator Facility and the future Electron-Ion Collider (EIC). These experiments play a critical role in advancing our understanding of nucleons and nuclei in terms of quark and gluon degrees of freedom. The use of generative models for simulating collider events faces several challenges such as the sparsity of the data, the presence of global or eventwide constraints, and steeply falling particle distributions. In this work, we focus on the implementation of diffusion models for the simulation of electron-proton scattering events at EIC energies. Our results demonstrate that diffusion models can reproduce relevant observables such as momentum distributions and correlations of particles, momentum sum rules, and the leading electron kinematics, all of which are of particular interest in electron-proton collisions. Although the sampling process is relatively slow compared to other machine-learning architectures, we find diffusion models can generate high-quality samples. We foresee various applications of our work including inference for nuclear structure, interpretable generative machine learning, and searches of physics beyond the Standard Model. Published by the American Physical Society 2024
41
Belis, Vasilis, Patrick Odagiu, Michele Grossi, Florentin Reiter, Günther Dissertori, and Sofia Vallecorsa. "Guided quantum compression for high dimensional data classification." Machine Learning: Science and Technology, July 5, 2024. http://dx.doi.org/10.1088/2632-2153/ad5fdd.
Full textAbstract:
Abstract Quantum machine learning provides a fundamentally different approach to analyzing data. However, many interesting datasets are too complex for currently available quantum computers. Present quantum machine learning applications usually diminish this complexity by reducing the dimensionality of the data, e.g., via auto-encoders, before passing it through the quantum models. Here, we design a classical-quantum paradigm that unifies the dimensionality reduction task with a quantum classification model into a single architecture: the guided quantum compression model. We exemplify how this architecture outperforms conventional quantum machine learning approaches on a challenging binary classification problem: identifying the Higgs boson in proton-proton collisions at the LHC. Furthermore, the guided quantum compression model shows better performance compared to the deep learning benchmark when using solely the kinematic variables in our dataset.
42
Chang, Chih-Wei, Shuang Zhou, Yuan Gao, et al. "Validation of a deep learning-based material estimation model for Monte Carlo dose calculation in proton therapy." Physics in Medicine & Biology, September 29, 2022. http://dx.doi.org/10.1088/1361-6560/ac9663.
Full textAbstract:
Abstract Objective: Computed tomography (CT) to material property conversion dominates proton range uncertainty, impacting the quality of proton treatment planning. Physics-based and machine learning-based methods have been investigated to leverage dual-energy CT (DECT) to predict proton ranges. Recent development includes physics-informed deep learning (DL) for material property inference. This paper aims to develop a framework to validate Monte Carlo dose calculation (MCDC) using CT-based material characterization models. Approach: The proposed framework includes two experiments to validate in vivo dose and water equivalent thickness (WET) distributions using anthropomorphic and porcine phantoms. Phantoms were irradiated using anteroposterior proton beams, and the exit doses and residual ranges were measured by MatriXX PT and multi-layer strip ionization chamber. Two pre-trained conventional and physics-informed residual networks (RN/PRN) were used for mass density inference from DECT. Additional two heuristic material conversion models using single-energy CT (SECT) and DECT were implemented for comparisons. The gamma index was used for dose comparisons with criteria of 3%/3mm (10% dose threshold). Main results: The phantom study showed that MCDC with PRN achieved mean gamma passing rates of 95.9% and 97.8% for the anthropomorphic and porcine phantoms. The rates were 86.0% and 79.7% for MCDC with the empirical DECT model. WET analyses indicated that the mean WET variations between measurement and simulation were -1.66 mm, -2.48 mm, and -0.06 mm for MCDC using a Hounsfield look-up table with SECT and empirical and PRN models with DECT. Validation experiments indicated that MCDC with PRN achieved consistent dose and WET distributions with measurement. Significance: The proposed framework can be used to identify the optimal CT-based material characterization model for MCDC to improve proton range uncertainty. The framework can systematically verify the accuracy of proton treatment planning, and it can potentially be implemented in the treatment room to be instrumental in online adaptive treatment planning.
43
Pang, Bo, Shuoyan Chen, Yiling Zeng, et al. "Lightweight and universal deep learning model for fast proton spot dose calculation at arbitrary energies." Physics in Medicine & Biology, May 2, 2025. https://doi.org/10.1088/1361-6560/add3b9.
Full textAbstract:
Abstract Objective: To better integrate into processes like rapid adaptive planning and quality assurance, this study aims to propose a lightweight and universal proton spot dose calculation model suitable for arbitrary energies.&#xD;&#xD;Approach: Given the alignment between the characteristics of proton spot dose deposition and the sequence learning capabilities of the long short-term memory (LSTM) network, the lightweight model, Multi-Energy Dose LSTM (MED-LSTM), is proposed. To comprehensively investigate the effectiveness of model, we trained and evaluated it on prostate, nasopharynx, and lung cases consistently.&#xD;&#xD;Main results: Regarding the results for spot dose, the prostate, nasopharynx, and lung models achieved average gamma passing rates of 99.93%, 99.81%, and 99.89% respectively under the (1%, 3mm) criterion. Under the (1%, 1mm) criterion, the rates were 99.06%, 97.18%, and 98.32%, respectively. For the intensity-modulated proton therapy (IMPT) plan dose, the prostate model achieved optimal performance with gamma passing rates of 99.88% and 98.52% under the (1%, 3mm) and (1%, 1mm) criteria, respectively. Following this, the lung model achieved rates of 99.22% and 93.41%. The nasopharynx model exhibited the poorest performance, with rates of 99.56% and 88.95%, respectively. It is evident that the MED-LSTM model demonstrates extremely high dose calculation accuracy in most cases. However, visible deviations occur in some spot samples for the nasopharynx and lung cases due to structural tissue differences.&#xD;&#xD;Significance: The MED-LSTM model can rapidly and accurately determine the proton spot dose at any energy with relatively low number of parameters. This exciting outcome holds broad prospects for applications and research directions.&#xD;&#xD;
44
Croxford, William, Anna France, Matthew Clarke, et al. "Online learning in proton radiation therapy: the future in the post-Covid-19 pandemic era?" BJR|Open 3, no. 1 (2021). http://dx.doi.org/10.1259/bjro.20210054.
Full textAbstract:
Objective: The Covid-19 pandemic placed unprecedented strain on medical education and led to a vast increase in online learning. Subsequently, the Christie International Proton School moved from face-to-face to online. Delegate feedback and current literature were studied to determine benefits, challenges, and potential solutions, for online proton therapy education. Methods: The course was converted to a 6-week online course with twice weekly 2-h sessions. Feedback was studied pre-, during-, and post-course regarding demographics, learning objectives, proton therapy knowledge, ease of engagement, technical difficulties, and course format. Statistical analyses were performed for proton therapy knowledge pre- and post-course. Results: An increase in delegate attendance was seen with increased international and multidisciplinary diversity. Learner objectives included treatment planning, clinical applications, physics, and centre development. Average learner reported scores of confidence in proton therapy knowledge improved significantly from 3, some knowledge, to 4, adequate knowledge after the course (p<0.0001). There were minimal reported difficulties using the online platform, good reported learner engagement, and shorter twice weekly sessions were reported conducive for learning. Recordings for asynchronous learning addressed time zone difficulties. Conclusion: The obligatory switch to online platforms has catalysed a paradigm shift towards online learning with delegates reporting educational benefit. We propose solutions to challenges of international online education, and a pedagogical model for online proton therapy education. Advances in knowledge: Online education is an effective method to teach proton therapy to international audiences. The future of proton education includes a hybrid of online and practical face-to-face learning depending on the level of cognitive skill required.
45
Chen, Mei, Bo Pang, Yiling Zeng, et al. "Evaluation of an automated clinical decision system with deep learning dose prediction and NTCP model for prostate cancer proton therapy." Physics in Medicine & Biology, May 8, 2024. http://dx.doi.org/10.1088/1361-6560/ad48f6.
Full textAbstract:
Abstract Objective: To evaluate the feasibility of using a deep learning dose prediction approach to identify patients who could benefit most from proton therapy based on the normal tissue complication probability (NTCP) model.&#xD;Approach: Two 3D UNets were established to predict photon and proton doses. A dataset of 95 patients with localized prostate cancer was randomly partitioned into 55, 10, and 30 for training, validation, and testing, respectively. We selected NTCP models for late rectum bleeding and acute urinary urgency of grade 2 or higher to quantify the benefit of proton therapy. Propagated uncertainties of predicted ΔNTCPs resulting from the dose prediction errors were calculated. Patient selection accuracies for a single endpoint and a composite evaluation were assessed under different ΔNTCP thresholds.&#xD;Main results: Our deep learning-based dose prediction technique can reduce the time spent on plan comparison from approximately 2 days to as little as 5 seconds. The expanded uncertainty of predicted ΔNTCPs for rectum and bladder endpoints propagated from the dose prediction error were 0.0042 and 0.0016, respectively, which is less than one-third of the acceptable tolerance. The averaged selection accuracies for rectum bleeding, urinary urgency, and composite evaluation were 90%, 93.5%, and 93.5%, respectively.&#xD;Significance: Our study demonstrates that deep learning dose prediction and NTCP evaluation scheme could distinguish the NTCP differences between photon and proton treatment modalities. In addition, the dose prediction uncertainty does not significantly influence the decision accuracy of NTCP-based patient selection for proton therapy. Therefore, automated deep learning dose prediction and NTCP evaluation schemes can potentially be used to screen large patient populations and to avoid unnecessary delays in the start of prostate cancer radiotherapy in the future.
46
Gao, Yuan, Chih-Wei Chang, Justin Roper, et al. "Single energy CT-based mass density and relative stopping power estimation for proton therapy using deep learning method." Frontiers in Oncology 13 (November 23, 2023). http://dx.doi.org/10.3389/fonc.2023.1278180.
Full textAbstract:
BackgroundThe number of patients undergoing proton therapy has increased in recent years. Current treatment planning systems (TPS) calculate dose maps using three-dimensional (3D) maps of relative stopping power (RSP) and mass density. The patient-specific maps of RSP and mass density were obtained by translating the CT number (HU) acquired using single-energy computed tomography (SECT) with appropriate conversions and coefficients. The proton dose calculation uncertainty of this approach is 2.5%-3.5% plus 1 mm margin. SECT is the major clinical modality for proton therapy treatment planning. It would be intriguing to enhance proton dose calculation accuracy using a deep learning (DL) approach centered on SECT.ObjectivesThe purpose of this work is to develop a deep learning method to generate mass density and relative stopping power (RSP) maps based on clinical single-energy CT (SECT) data for proton dose calculation in proton therapy treatment.MethodsArtificial neural networks (ANN), fully convolutional neural networks (FCNN), and residual neural networks (ResNet) were used to learn the correlation between voxel-specific mass density, RSP, and SECT CT number (HU). A stoichiometric calibration method based on SECT data and an empirical model based on dual-energy CT (DECT) images were chosen as reference models to evaluate the performance of deep learning neural networks. SECT images of a CIRS 062M electron density phantom were used as the training dataset for deep learning models. CIRS anthropomorphic M701 and M702 phantoms were used to test the performance of deep learning models.ResultsFor M701, the mean absolute percentage errors (MAPE) of the mass density map by FCNN are 0.39%, 0.92%, 0.68%, 0.92%, and 1.57% on the brain, spinal cord, soft tissue, bone, and lung, respectively, whereas with the SECT stoichiometric method, they are 0.99%, 2.34%, 1.87%, 2.90%, and 12.96%. For RSP maps, the MAPE of FCNN on M701 are 0.85%, 2.32%, 0.75%, 1.22%, and 1.25%, whereas with the SECT reference model, they are 0.95%, 2.61%, 2.08%, 7.74%, and 8.62%. ConclusionThe results show that deep learning neural networks have the potential to generate accurate voxel-specific material property information, which can be used to improve the accuracy of proton dose calculation.Advances in knowledgeDeep learning-based frameworks are proposed to estimate material mass density and RSP from SECT with improved accuracy compared with conventional methods.
47
Starke, Sebastian, Aaron Kieslich, Martina Palkowitsch, et al. "A deep-learning-based surrogate model for Monte-Carlo simulations of the linear energy transfer in primary brain tumor patients treated with proton-beam radiotherapy." Physics in Medicine & Biology, July 17, 2024. http://dx.doi.org/10.1088/1361-6560/ad64b7.
Full textAbstract:
Abstract Objective: This study explores the use of neural networks (NNs) as surrogate models for Monte-Carlo (MC) simulations in predicting the dose-averaged linear energy transfer (LETd) of protons in proton-beam therapy based on the planned dose distribution and patient anatomy in the form of computed tomography (CT) images. As LETd is associated with variability in the relative biological effectiveness (RBE) of protons, we also evaluate the implications of using NN predictions for normal tissue complication probability (NTCP) models within a variable-RBE context.&#xD;&#xD;Approach: The predictive performance of three-dimensional NN architectures was evaluated using five-fold cross-validation on a cohort of brain tumor patients (n=151). The best-performing model was identified and externally validated on patients from a different center (n=107). LETd predictions were compared to MC-simulated results in clinically relevant regions of interest. We assessed the impact on NTCP models by leveraging LETd predictions to derive RBE-weighted doses, using the Wedenberg RBE model.&#xD;&#xD;Main results: We found NNs based solely on the planned dose profile, i.e. without additional usage of CT images, can approximate MC-based LETd distributions. Root mean squared errors (RMSE) for the median LETd within the brain, brainstem, CTV, chiasm, lacrimal glands (ipsilateral/contralateral) and optic nerves (ipsilateral/contralateral) were 0.36, 0.87, 0.31, 0.73, 0.68, 1.04, 0.69 and 1.24~keV/μm, respectively. Although model predictions showed statistically significant differences from MC outputs, these did not result in substantial changes in NTCP predictions, with RMSEs of at most 3.2 percentage points.&#xD;&#xD;Significance: The ability of NNs to predict LETd based solely on planned dose profiles suggests a viable alternative to the compute-intensive MC simulations in a variable-RBE setting. This is particularly useful in scenarios where MC simulation data are unavailable, facilitating resource-constrained proton therapy treatment planning, retrospective patient data analysis and further investigations on the variability of proton RBE.
48
Tang, Chunmei, Baoyin Yuan, Xinyi Xie, Yoshitaka Aoki, Ning Wang, and Siyu Ye. "Machine learning-assisted advances and perspectives for electrolytes of protonic solid oxide fuel cells." Energy Materials 5, no. 9 (2025). https://doi.org/10.20517/energymater.2025.17.
Full textAbstract:
Protonic solid oxide fuel cells (P-SOFCs), as a promising power generation technology, have garnered increasing attention due to their advantages of cleanliness, high efficiency, and high reliability. As a critical component of P-SOFCs, proton-conducting electrolytes exhibit high ionic conductivity, enabling high chemical-to-electrical energy conversion efficiency at intermediate temperatures. However, there are still many challenges in further enhancing the proton conductivity and stability of the currently widely used Ba(Zr, Ce)O3 electrolytes through traditional experimental methods. Herein, this review firstly summarized the current research status of proton-conducting oxides, including ABO3 perovskite-type oxides and other structural oxides, and highlighted the challenges faced by electrolyte development in terms of proton conductivity, compatibility with other components, and long-term durability. Then, the relevant progress of machine learning (ML) in the research of P-SOFC electrolytes was meticulously discussed and the promising applications of ML in proton-conducting electrolyte performance screening, stability prediction, and morphology analysis were pointed out. More importantly, the challenges and solutions of proton-conducting electrolytes designed by ML were uncovered by considering the reliable database, feature engineering, accurate model, and experimental validation. Overall, this review concluded the advances of ML-assisted P-SOFC electrolytes and addressed the future research directions in the synergy of ML and electrolytes.
49
Chen, C., O. Cerri, T. Q. Nguyen, J. R. Vlimant, and M. Pierini. "Analysis-Specific Fast Simulation at the LHC with Deep Learning." Computing and Software for Big Science 5, no. 1 (2021). http://dx.doi.org/10.1007/s41781-021-00060-4.
Full textAbstract:
AbstractWe present a fast-simulation application based on a deep neural network, designed to create large analysis-specific datasets. Taking as an example the generation of W + jet events produced in $$\sqrt{s}=$$ s = 13 TeV proton–proton collisions, we train a neural network to model detector resolution effects as a transfer function acting on an analysis-specific set of relevant features, computed at generation level, i.e., in absence of detector effects. Based on this model, we propose a novel fast-simulation workflow that starts from a large amount of generator-level events to deliver large analysis-specific samples. The adoption of this approach would result in about an order-of-magnitude reduction in computing and storage requirements for the collision simulation workflow. This strategy could help the high energy physics community to face the computing challenges of the future High-Luminosity LHC.
50
El-Dahshan, EL-Sayed. "Application of genetic programming for proton-proton interactions." Open Physics 9, no. 3 (2011). http://dx.doi.org/10.2478/s11534-010-0088-7.
Full textAbstract:
AbstractThe aim of the present work is to use one of the machine learning techniques named the genetic programming (GP) to model the p-p interactions through discovering functions. In our study, GP is used to simulate and predict the multiplicity distribution of charged pions (P(n ch)), the average multiplicity (〈n ch〉) and the total cross section (σ tot) at different values of high energies. We have obtained the multiplicity distribution as a function of the center of mass energy ($$ \sqrt s $$) and charged particles (n ch). Also, both the average multiplicity and the total cross section are obtained as a function of $$ \sqrt s $$. Our discovered functions produced by GP technique show a good match to the experimental data. The performance of the GP models was also tested at non-trained data and was found to be in good agreement with the experimental data.