Article
Engineering, Multidisciplinary
Consolatina Liguori, Alessandro Ruggiero, Domenico Russo, Paolo Sommella, Jan Lundgren
Summary: Accurate measurement of noise exposure in the workplace is crucial for employee health and cost implications for employers. This paper proposes an innovative approach for estimating noise exposure levels for bus drivers, with results showing feasibility for accurately measuring acoustic noise exposure in a typical work situation.
Article
Meteorology & Atmospheric Sciences
Chul-Su Shin, Paul A. Dirmeyer, Bohua Huang
Summary: This study presents a joint approach combining correlation and NMI to examine land and ocean surface forcing of U.S. drought at varying lead times. The proposed method can discriminate linear and nonlinear relationships more intuitively and identify non-linear relationships, particularly in cases where there are clusters and blank areas in the joint probability distributions between source and target variables. Therefore, this joint approach is a potentially powerful tool to reveal complex and heretofore undetected relationships.
JOURNAL OF CLIMATE
(2023)
Article
Meteorology & Atmospheric Sciences
Md Wahiduzzaman, Md Arfan Ali, Kevin Cheung, Jing-Jia Luo, Tang Shaolei, Prasad K. Bhaskaran, Chaoxia Yuan, Muhammad Bilal, Zhongfeng Qiu, Mansour Almazroui
Summary: This study evaluated the impact of aerosols and climate modes on tropical cyclone frequency in the North Indian Ocean. It found strong linkages between TC activity and the Atlantic meridional mode, Indian Ocean dipole, and El Nino-Southern Oscillation. Certain aerosols, such as black carbon, organic carbon, sea salt, and sulfate, had a significant impact on cyclone frequency.
JOURNAL OF CLIMATE
(2022)
Article
Acoustics
Luis Andrade, Robin S. Langley, Tore Butlin
Summary: This paper presents an improved hybrid Finite Element-Statistical Energy Analysis (FE-SEA) method for analyzing complex vibro-acoustic built-up systems. The generalized set of FE-SEA equations is derived to estimate the response of a system when prescribed displacements contribute to the power input. The study finds that the equations may not be reversible, leading to altered responses when using the same random structure. Validation against numerical data shows the effectiveness of the generalized FE-SEA equations.
JOURNAL OF SOUND AND VIBRATION
(2022)
Article
Mathematics, Applied
N. C. Pati, Paulo C. Rech, G. C. Layek
Summary: The study investigates the multistable states of low-frequency, short-wavelength nonlinear acoustic-gravity waves propagating in a small slope in a rotating atmosphere. It highlights the connections between the air Prandtl number and the slope parameter on the stabilities of the system, and the transition to unsteady motion due to Earth's rotation. The model system exhibits hysteresis-induced multistability with unpredictable dynamics in certain parameter spaces.
Article
Astronomy & Astrophysics
Patricio E. Cubillos, Jasmina Blecic
Summary: The pyrat bay framework is an open-source python tool for exoplanet atmospheric modeling, spectral synthesis, and Bayesian retrieval. It allows users to generate atmospheric parametric models, sample line-by-line cross-sections, compute emission or transmission spectra, and perform atmospheric retrievals using Markov chain Monte Carlo. The framework has been benchmarked and proven to be reliable, with the code readily available for the community to use.
MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY
(2021)
Article
Computer Science, Interdisciplinary Applications
K. Mahesh, S. Kumar Ranjith, R. S. Mini
Summary: This paper proposes an algorithm based on deep convolutional autoencoder network for the inverse design of a low-frequency acoustic absorber. A hybrid sound-absorber configuration with Helmholtz resonators, curvy neck, and microperforated panel is suggested and its geometrical properties are inversely forecasted. By using the effective medium theory and the electro-acoustic analogy, a mathematical model is established to evaluate the absorption characteristics of the introduced geometry. The proposed inverse technique is successfully applied to both standard and complex geometrical setups, achieving high accuracy without pre-design information on absorber geometry. The developed absorber models with deep sub-wavelength thickness and wide absorption spectra have great potential in noise reduction applications.
ENGINEERING WITH COMPUTERS
(2023)
Article
Meteorology & Atmospheric Sciences
Zhuolin Xuan, Wenjun Zhang, Feng Jiang, Fei-Fei Jin
Summary: Current climate models have high skills in predicting the phase of El Nino-Southern Oscillation (ENSO), but face challenges in forecasting the amplitude. Accumulated westerly wind events (WWEs)/easterly wind surges (EWSs) and oceanic recharged/discharged states are found to be important for accurate ENSO amplitude forecasts.
JOURNAL OF CLIMATE
(2022)
Article
Multidisciplinary Sciences
Zhike Xu, Ling Qin, Wei Xu, Shuhua Fang, Jiyao Wang
Summary: This paper introduces a metasurface design approach using a perforated labyrinthine path coil structure to manipulate acoustic transmission with adjustable resonance peak frequencies and bandgap width for acoustic metamaterials. The theory is validated through simulations and experiments, demonstrating the accuracy of the proposed design method.
SCIENTIFIC REPORTS
(2021)
Article
Engineering, Multidisciplinary
Si-Xin Chen, Lu Zhou, Yi-Qing Ni, Xiao-Zhou Liu
Summary: This article introduces a novel transfer learning approach for evaluating rail structural conditions progressively, utilizing acoustic emission monitoring data and knowledge transferred from an acoustic-related database. The results demonstrate that the proposed method successfully predicts the evolving stages of rail conditions with high accuracy and computational efficiency. Additionally, the study suggests the importance of selecting appropriate source data in maximizing the benefits of transfer learning in the structural health monitoring field.
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2021)
Article
Engineering, Mechanical
Rih-Teng Wu, Mehdi Jokar, Mohammad R. Jahanshahi, Fabio Semperlotti
Summary: This study proposes a novel approach based on deep auto-encoder to solve the inverse problem of designing assemblies of acoustic scattering elements, achieving more efficient solution methodologies. The proposed network is validated numerically through three design scenarios, demonstrating its feasibility and performance.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2022)
Article
Meteorology & Atmospheric Sciences
Jingfang Fan, Jun Meng, Josef Ludescher, Zhaoyuan Li, Elena Surovyatkina, Xiaosong Chen, Juergen Kurths, Hans Joachim Schellnhuber
Summary: In this study, a series of dynamical and physical climate networks were constructed, and their characteristics were used to successfully predict the Indian summer monsoon rainfall. The findings suggest that global warming has significant impacts on both the climate network and precipitation in India.
JOURNAL OF CLIMATE
(2022)
Article
Construction & Building Technology
Fausto Molina-Gomez, Lenin Alexander Bulla-Cruz, Aquiles Enrique Darghan Contreras
Summary: This study presents an approach to validate the grain size distribution of granular materials for road construction, applicable for both unbound and bound layers, and allows compliance validation based on international regulations. The approach includes statistical analysis and comparisons against boundary curves, providing a comprehensive control and management of such materials used for infrastructure construction.
CONSTRUCTION AND BUILDING MATERIALS
(2021)
Article
Engineering, Environmental
Ester Piegari, Giorgio De Donno, Davide Melegari, Valeria Paoletti
Summary: In this study, a machine learning-based approach is proposed for mapping leachate contamination by integrating geoelectrical tomographic data effectively. Multivariate analysis is performed on datasets consisting of electrical resistivity, chargeability, and normalized chargeability data, resulting in the identification of the best data partition and less ambiguous detection of leachate accumulation zones. The combination of geophysical imaging and unsupervised machine learning shows promising results in characterizing leachate distribution and assessing pollution in landfills.
Article
Computer Science, Interdisciplinary Applications
Meghdoot Mozumder, Andreas Hauptmann, Ilkka Nissila, Simon R. Arridge, Tanja Tarvainen
Summary: Diffuse optical tomography (DOT) utilizes near-infrared light to image optical parameters, but faces ill-posedness. Bayesian approach and deep learning can improve image reconstruction. The proposed approach provides accurate and computationally efficient solutions.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2022)
Article
Environmental Sciences
Mohammad Rostami, Soheil Kolouri, Eric Eaton, Kyungnam Kim
Article
Computer Science, Artificial Intelligence
Xinyun Zou, Soheil Kolouri, Praveen K. Pilly, Jeffrey L. Krichmar
Editorial Material
Engineering, Electrical & Electronic
Soheil Kolouri, Xuwang Yin, Gustavo K. Rohde
IEEE SIGNAL PROCESSING MAGAZINE
(2020)
Article
Computer Science, Artificial Intelligence
Jeffery Dick, Pawel Ladosz, Eseoghene Ben-Iwhiwhu, Hideyasu Shimadzu, Peter Kinnell, Praveen K. Pilly, Soheil Kolouri, Andrea Soltoggio
FRONTIERS IN NEUROROBOTICS
(2020)
Article
Computer Science, Artificial Intelligence
Mohammad Shifat-E-Rabbi, Xuwang Yin, Abu Hasnat Mohammad Rubaiyat, Shiying Li, Soheil Kolouri, Akram Aldroubi, Jonathan M. Nichols, Gustavo K. Rohde
Summary: A new supervised image classification method utilizing Radon Cumulative Distribution Transform (R-CDT) is proposed for a broad class of image deformation models, showing improvements in computational efficiency and training sample requirements compared to neural network-based methods. The method, utilizing a nearest-subspace algorithm in the R-CDT space, is simple, non-iterative, and provides competitive accuracies to state-of-the-art neural networks for various classification problems.
JOURNAL OF MATHEMATICAL IMAGING AND VISION
(2021)
Article
Computer Science, Artificial Intelligence
Pawel Ladosz, Eseoghene Ben-Iwhiwhu, Jeffery Dick, Nicholas Ketz, Soheil Kolouri, Jeffrey L. Krichmar, Praveen K. Pilly, Andrea Soltoggio
Summary: The article discusses a new bio-inspired neural architecture called modulated Hebbian plus Q-network architecture (MOHQA) for solving confounding POMDP problems. MOHQA combines a Hebbian network with a DQN, utilizing the advantages of both different learning algorithms to improve DQN's results and performance.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Megan M. Baker, Alexander New, Mario Aguilar-Simon, Ziad Al-Halah, Sebastien M. R. Arnold, Ese Ben-Iwhiwhu, Andrew P. Brna, Ethan Brooks, Ryan C. Brown, Zachary Daniels, Anurag Daram, Fabien Delattre, Ryan Dellana, Eric Eaton, Haotian Fu, Kristen Grauman, Jesse Hostetler, Shariq Iqbal, Cassandra Kent, Nicholas Ketz, Soheil Kolouri, George Konidaris, Dhireesha Kudithipudi, Erik Learned-Miller, Seungwon Lee, Michael L. Littman, Sandeep Madireddy, Jorge A. Mendez, Eric Q. Nguyen, Christine Piatko, Praveen K. Pilly, Aswin Raghavan, Abrar Rahman, Santhosh Kumar Ramakrishnan, Neale Ratzlaff, Andrea Soltoggio, Peter Stone, Indranil Sur, Zhipeng Tang, Saket Tiwari, Kyle Vedder, Felix Wang, Zifan Xu, Angel Yanguas-Gil, Harel Yedidsion, Shangqun Yu, Gautam K. Vallabha
Summary: Despite the advancement of machine learning techniques, state-of-the-art systems lack robustness to real world events and the ability to adapt to novel distributions and tasks. Lifelong Learning systems with continuous learning, transfer and adaptation, and scalability capabilities are proposed to address this critical gap. A suite of metrics and an evaluation framework are used to assess Lifelong Learning in a principled way, informing the development and progress of varied and complex systems.
Article
Computer Science, Information Systems
Meiyi Li, Soheil Kolouri, Javad Mohammadi
Summary: In this paper, a neural approximator is proposed to solve constrained optimization problems, providing rapid solutions without iterations. The method ensures feasibility through a sequence of steps and demonstrates superior performance in optimal power dispatch and image registration.
Proceedings Paper
Acoustics
Soheil Kolouri, Kimia Nadjahi, Shahin Shahrampour, Umut Simsekli
Summary: This paper introduces a new family of sliced probability metrics called Generalized Sliced Probability Metrics (GSPMs), which are related to the Maximum Mean Discrepancy (MMD). The paper shows that gradient flows based on GSPMs converge to the global optimum under mild assumptions. Additionally, various choices of GSPMs lead to new positive definite kernels that can be used in the MMD formulation while providing a unique integral geometric interpretation.
2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
(2022)
Review
Computer Science, Artificial Intelligence
Dhireesha Kudithipudi, Mario Aguilar-Simon, Jonathan Babb, Maxim Bazhenov, Douglas Blackiston, Josh Bongard, Andrew P. Brna, Suraj Chakravarthi Raja, Nick Cheney, Jeff Clune, Anurag Daram, Stefano Fusi, Peter Helfer, Leslie Kay, Nicholas Ketz, Zsolt Kira, Soheil Kolouri, Jeffrey L. Krichmar, Sam Kriegman, Michael Levin, Sandeep Madireddy, Santosh Manicka, Ali Marjaninejad, Bruce McNaughton, Risto Miikkulainen, Zaneta Navratilova, Tej Pandit, Alice Parker, Praveen K. Pilly, Sebastian Risi, Terrence J. Sejnowski, Andrea Soltoggio, Nicholas Soures, Andreas S. Tolias, Dario Urbina-Melendez, Francisco J. Valero-Cuevas, Gido M. van de Ven, Joshua T. Vogelstein, Felix Wang, Ron Weiss, Angel Yanguas-Gil, Xinyun Zou, Hava Siegelmann
Summary: Biological organisms learn from interactions with their environment, and artificial systems also need the ability to learn throughout their lifetime. This article introduces biological mechanisms and artificial models and mechanisms for lifelong learning, and discusses opportunities to bridge the gap between natural and artificial intelligence.
NATURE MACHINE INTELLIGENCE
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Joseph F. Comer, Reed W. Andrews, Navid Naderializadeh, Soheil Kolouri, Heiko Hoffmann
AUTOMATIC TARGET RECOGNITION XXX
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Phillip E. Pope, Soheil Kolouri, Mohammad Rostami, Charles E. Martin, Heiko Hoffmann
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Soheil Kolouri, Kimia Nadjahi, Umut Simsekli, Roland Badeau, Gustavo K. Rohde
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019)
(2019)
Proceedings Paper
Automation & Control Systems
Alexander J. Gabourie, Mohammad Rostami, Philip E. Pope, Soheil Kolouri, Kyungnam Kim
2019 57TH ANNUAL ALLERTON CONFERENCE ON COMMUNICATION, CONTROL, AND COMPUTING (ALLERTON)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Javad Mohammadi, Soheil Kolouri
2019 IEEE 29TH INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING (MLSP)
(2019)