He, X.
AI-assisted Optimization of the ECCE Tracking System at the Electron Ion Collider
Fanelli, C., Papandreou, Z., Suresh, K., Adkins, J. K., Akiba, Y., Albataineh, A., Amaryan, M., Arsene, I. C., Gayoso, C. Ayerbe, Bae, J., Bai, X., Baker, M. D., Bashkanov, M., Bellwied, R., Benmokhtar, F., Berdnikov, V., Bernauer, J. C., Bock, F., Boeglin, W., Borysova, M., Brash, E., Brindza, P., Briscoe, W. J., Brooks, M., Bueltmann, S., Bukhari, M. H. S., Bylinkin, A., Capobianco, R., Chang, W. -C., Cheon, Y., Chen, K., Chen, K. -F., Cheng, K. -Y., Chiu, M., Chujo, T., Citron, Z., Cline, E., Cohen, E., Cormier, T., Morales, Y. Corrales, Cotton, C., Crafts, J., Crawford, C., Creekmore, S., Cuevas, C., Cunningham, J., David, G., Dean, C. T., Demarteau, M., Diehl, S., Doshita, N., Dupre, R., Durham, J. M., Dzhygadlo, R., Ehlers, R., Fassi, L. El, Emmert, A., Ent, R., Fatemi, R., Fegan, S., Finger, M., Finger, M. Jr., Frantz, J., Friedman, M., Friscic, I., Gangadharan, D., Gardner, S., Gates, K., Geurts, F., Gilman, R., Glazier, D., Glimos, E., Goto, Y., Grau, N., Greene, S. V., Guo, A. Q., Guo, L., Ha, S. K., Haggerty, J., Hayward, T., He, X., Hen, O., Higinbotham, D. W., Hoballah, M., Horn, T., Hoghmrtsyan, A., Hsu, P. -h. J., Huang, J., Huber, G., Hutson, A., Hwang, K. Y., Hyde, C., Inaba, M., Iwata, T., Jo, H. S., Joo, K., Kalantarians, N., Kalicy, G., Kawade, K., Kay, S. J. D., Kim, A., Kim, B., Kim, C., Kim, M., Kim, Y., Kim, Y., Kistenev, E., Klimenko, V., Ko, S. H., Korover, I., Korsch, W., Krintiras, G., Kuhn, S., Kuo, C. -M., Kutz, T., Lajoie, J., Lawrence, D., Lebedev, S., Lee, H., Lee, J. S. H., Lee, S. W., Lee, Y. -J., Li, W., Li, W. B., Li, X., Li, X., Li, X., Li, X., Liang, Y. T., Lim, S., Lin, C. -h., Lin, D. X., Liu, K., Liu, M. X., Livingston, K., Liyanage, N., Llope, W. J., Loizides, C., Long, E., Lu, R. -S., Lu, Z., Lynch, W., Marchand, D., Marcisovsky, M., Markowitz, P., Marukyan, H., McGaughey, P., Mihovilovic, M., Milner, R. G., Milov, A., Miyachi, Y., Mkrtchyan, A., Monaghan, P., Montgomery, R., Morrison, D., Movsisyan, A., Mkrtchyan, H., Mkrtchyan, A., Camacho, C. Munoz, Murray, M., Nagai, K., Nagle, J., Nakagawa, I., Nattrass, C., Nguyen, D., Niccolai, S., Nouicer, R., Nukazuka, G., Nycz, M., Okorokov, V. A., Oresic, S., Osborn, J. D., O'Shaughnessy, C., Paganis, S., Pate, S. F., Patel, M., Paus, C., Penman, G., Perdekamp, M. G., Perepelitsa, D. V., da Costa, H. Periera, Peters, K., Phelps, W., Piasetzky, E., Pinkenburg, C., Prochazka, I., Protzman, T., Purschke, M. L., Putschke, J., Pybus, J. R., Rajput-Ghoshal, R., Rasson, J., Raue, B., Read, K. F., Roed, K., Reed, R., Reinhold, J., Renner, E. L., Richards, J., Riedl, C., Rinn, T., Roche, J., Roland, G. M., Ron, G., Rosati, M., Royon, C., Ryu, J., Salur, S., Santiesteban, N., Santos, R., Sarsour, M., Schambach, J., Schmidt, A., Schmidt, N., Schwarz, C., Schwiening, J., Seidl, R., Sickles, A., Simmerling, P., Sirca, S., Sharma, D., Shi, Z., Shibata, T. -A., Shih, C. -W., Shimizu, S., Shrestha, U., Slifer, K., Smith, K., Sokhan, D., Soltz, R., Sondheim, W., Song, J., Song, J., Strakovsky, I. I., Steinberg, P., Stepanov, P., Stevens, J., Strube, J., Sun, P., Sun, X., Tadevosyan, V., Tang, W. -C., Araya, S. Tapia, Tarafdar, S., Teodorescu, L., Timmins, A., Tomasek, L., Trotta, N., Trotta, R., Tveter, T. S., Umaka, E., Usman, A., van Hecke, H. W., Van Hulse, C., Velkovska, J., Voutier, E., Wang, P. K., Wang, Q., Wang, Y., Wang, Y., Watts, D. P., Wickramaarachchi, N., Weinstein, L., Williams, M., Wong, C. -P., Wood, L., Wood, M. H., Woody, C., Wyslouch, B., Xiao, Z., Yamazaki, Y., Yang, Y., Ye, Z., Yoo, H. D., Yurov, M., Zachariou, N., Zajc, W. A., Zha, W., Zhang, J., Zhang, Y., Zhao, Y. X., Zheng, X., Zhuang, P.
The Electron-Ion Collider (EIC) is a cutting-edge accelerator facility that will study the nature of the "glue" that binds the building blocks of the visible matter in the universe. The proposed experiment will be realized at Brookhaven National Laboratory in approximately 10 years from now, with detector design and R&D currently ongoing. Notably, EIC is one of the first large-scale facilities to leverage Artificial Intelligence (AI) already starting from the design and R&D phases. The EIC Comprehensive Chromodynamics Experiment (ECCE) is a consortium that proposed a detector design based on a 1.5T solenoid. The EIC detector proposal review concluded that the ECCE design will serve as the reference design for an EIC detector. Herein we describe a comprehensive optimization of the ECCE tracker using AI. The work required a complex parametrization of the simulated detector system. Our approach dealt with an optimization problem in a multidimensional design space driven by multiple objectives that encode the detector performance, while satisfying several mechanical constraints. We describe our strategy and show results obtained for the ECCE tracking system. The AI-assisted design is agnostic to the simulation framework and can be extended to other sub-detectors or to a system of sub-detectors to further optimize the performance of the EIC detector.
Compressed Sensing with Probability-based Prior Information
Jiang, Q., Li, S., Zhu, Z., Bai, H., He, X., de Lamare, R. C.
This paper deals with the design of a sensing matrix along with a sparse recovery algorithm by utilizing the probability-based prior information for compressed sensing system. With the knowledge of the probability for each atom of the dictionary being used, a diagonal weighted matrix is obtained and then the sensing matrix is designed by minimizing a weighted function such that the Gram of the equivalent dictionary is as close to the Gram of dictionary as possible. An analytical solution for the corresponding sensing matrix is derived which leads to low computational complexity. We also exploit this prior information through the sparse recovery stage and propose a probability-driven orthogonal matching pursuit algorithm that improves the accuracy of the recovery. Simulations for synthetic data and application scenarios of surveillance video are carried out to compare the performance of the proposed methods with some existing algorithms. The results reveal that the proposed CS system outperforms existing CS systems.