检索结果-内蒙古大学图书馆

An efficient multi-objective evolutionary approach for solving the operation of multi-reservoir system scheduling in hydro-power plants

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Marcelino, Carolina Gil Leite, G.M.C. Delgado, C.A.D.M. De Oliveira, L.B. Wanner, E.F. Jiménez-Fernández, S. Salcedo-Sanz, S. Department of Signal Processing and Communications Universidad de Alcalá Spain Institute of Computing Federal University of Rio de Janeiro Brazil Post-Graduate Program in Systems Engineering and Computer Science Federal University of Rio de Janeiro Brazil Computing Department Federal Center of Technology Education of Minas Gerais Brazil

This paper tackles the short-term hydro-power unit commitment problem in a multi-reservoir system - a cascade-based operation scenario. For this, we propose a new mathematical modelling in which the goal is to maximize the total energy production of the hydro-power plant in a sub-daily operation, and, simultaneously, to maximize the total water content (volume) of reservoirs. For solving the problem, we discuss the Multi-objective Evolutionary Swarm Hybridization (MESH) algorithm, a recently proposed multiobjective swarm intelligence-based optimization method which has obtained very competitive results when compared to existing evolutionary algorithms in specific applications. The MESH approach has been applied to find the optimal water discharge and the power produced at the maximum reservoir volume for all possible combinations of turbines in a hydro-power plant. The performance of MESH has been compared with that of well-known evolutionary approaches such as NSGA-II, NSGA-III, SPEA2, and MOEA/D in a realistic problem considering data from a hydro-power energy system with two cascaded hydro-power plants in Brazil. Results indicate that MESH showed a superior performance than alternative multi-objective approaches in terms of efficiency and accuracy, providing a profit of $412,500 per month in a projection analysis carried out. © 2021, CC BY-NC-ND.

关键词： Multiobjective optimization

Exploration of Dark Chemical Genomics Space via Portal Learning: Applied to Targeting the Undruggable Genome and COVID-19 Anti-Infective Polypharmacology

学校读者我要写书评

暂无评论

Research Square

Research Square 2021年

作者： Cai, Tian Xie, Li Chen, Muge Liu, Yang He, Di Zhang, Shuo Mura, Cameron Bourne, Philip E. Xie, Lei Ph.D. Program in Computer Science The Graduate Center The City University of New York New York10016 United States Department of Computer Science Hunter College The City University of New York New York10065 United States Master Program in Computer Science Courant Institute of Mathematical Sciences New York University United States School of Data Science Department of Biomedical Engineering University of Virginia VA22903 United States Helen and Robert Appel Alzheimer’s Disease Research Institute Feil Family Brain & Mind Research Institute Weill Cornell Medicine Cornell University New York10021 United States

Advances in biomedicine are largely fueled by exploring uncharted territories of human biology. Machine learning can both enable and accelerate discovery, but faces a fundamental hurdle when applied to unseen data with distributions that differ from previously observed ones—a common dilemma in scientific inquiry. We have developed a new deep learning framework, called Portal Learning, to explore dark chemical and biological space. Three key, novel components of our approach include: (i) end-to-end, step-wise transfer learning, in recognition of biology’s sequence-structure-function paradigm, (ii) out-of-cluster meta-learning, and (iii) stress model selection. Portal Learning provides a practical solution to the out-of-distribution (OOD) problem in statistical machine learning. Here, we have implemented Portal Learning to predict chemical-protein interactions on a genome-wide scale. Systematic studies demonstrate that Portal Learning can effectively assign ligands to unexplored gene families (unknown functions), versus existing state-of-the-art methods. Compared with AlphaFold2-based protein-ligand docking, Portal Learning significantly improved the performance by 79% in PR-AUC and 27% in ROC-AUC, respectively. The superior performance of Portal Learning allowed us to target previously "undruggable" proteins and design novel polypharmacological agents for disrupting interactions between SARS-CoV-2 and human proteins. Portal Learning is general-purpose and can be further applied to other areas of scientific inquiry. © 2021, CC BY.

关键词： Coronavirus

Exploration of dark chemical genomics space via portal learning: Applied to targeting the undruggable genome and COVID-19 anti-infective polypharmacology

学校读者我要写书评

暂无评论

arXiv 2021年

Advances in biomedicine are largely fueled by exploring uncharted territories of human biology. Machine learning can both enable and accelerate discovery, but faces a fundamental hurdle when applied to unseen data with distributions that differ from previously observed ones—a common dilemma in scientific inquiry. We have developed a new deep learning framework, called Portal Learning, to explore dark chemical and biological space. Three key, novel components of our approach include: (i) end-to-end, step-wise transfer learning, in recognition of biology’s sequence-structure-function paradigm, (ii) out-of-cluster meta-learning, and (iii) stress model selection. Portal Learning provides a practical solution to the out-of-distribution (OOD) problem in statistical machine learning. Here, we have implemented Portal Learning to predict chemical-protein interactions on a genome-wide scale. Systematic studies demonstrate that Portal Learning can effectively assign ligands to unexplored gene families (unknown functions), versus existing state-of-the-art methods, thereby allowing us to target previously "undruggable" proteins and design novel polypharmacological agents for disrupting interactions between SARS-CoV-2 and human proteins. Portal Learning is general-purpose and can be further applied to other areas of scientific *** Codes 68T07 © 2021, CC BY.

关键词： Genes

Multimodal Whole Slide Foundation Model for Pathology

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ding, Tong Wagner, Sophia J. Song, Andrew H. Chen, Richard J. Lu, Ming Y. Zhang, Andrew Vaidya, Anurag J. Jaume, Guillaume Shaban, Muhammad Kim, Ahrong Williamson, Drew F.K. Chen, Bowen Almagro-Perez, Cristina Doucet, Paul Sahai, Sharifa Chen, Chengkuan Komura, Daisuke Kawabe, Akihiro Ishikawa, Shumpei Gerber, Georg Peng, Tingying Le, Long Phi Mahmood, Faisal Department of Pathology Mass General Brigham Harvard Medical School BostonMA United States Data Science Program Dana-Farber Cancer Institute BostonMA United States Cancer Program Broad Institute of Harvard and MIT CambridgeMA United States John A. Paulson School of Engineering and Applied Sciences Harvard University CambridgeMA United States Helmholtz Munich German Research Center for Environment and Health Munich Germany School of Computation Information and Technology Technical University of Munich Munich Germany Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA United States Harvard-MIT Division of Health Sciences and Technology Massachusetts Institute of Technology CambridgeMA United States Department of Pathology Pusan National University Busan Korea Republic of Department of Pathology and Laboratory Medicine Emory University School of Medicine AtlantaGA United States Harvard Data Science Initiative Harvard University CambridgeMA United States Department of Systems Biology Harvard Medical School BostonMA United States Department of Preventive Medicine Graduate School of Medicine The University of Tokyo Tokyo Japan Division of Pathology National Cancer Center Exploratory Oncology Research & Clinical Trial Center Chiba Japan

The field of computational pathology has been transformed with recent advances in foundation models that encode histopathology region-of-interests (ROIs) into versatile and transferable feature representations via self-supervised learning (SSL). However, translating these advancements to address complex clinical challenges at the patient and slide level remains constrained by limited clinical data in disease-specific cohorts, especially for rare clinical conditions. We propose TITAN, a multimodal whole slide foundation model pretrained using 335,645 WSIs via visual self-supervised learning and vision-language alignment with corresponding pathology reports and 423,122 synthetic captions generated from a multimodal generative AI copilot for pathology. Without any finetuning or requiring clinical labels, TITAN can extract general-purpose slide representations and generate pathology reports that generalize to resource-limited clinical scenarios such as rare disease retrieval and cancer prognosis. We evaluate TITAN on diverse clinical tasks and find that TITAN outperforms both ROI and slide foundation models across machine learning settings such as linear probing, few-shot and zero-shot classification, rare cancer retrieval and cross-modal retrieval, and pathology report generation. The model is publicly accessible at https://***/mahmoodlab/TITAN © 2024, CC BY-NC-ND.

关键词： Self-supervised learning

Extreme electrodynamics in time-varying media

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Scalora, M. Vincenti, M.A. de Ceglia, D. Akozbek, N. Ferrera, M. Rizza, C. Alù, A. Litchinitser, N. Cojocaru, C. Trull, J. FCDD-AMT-MGR DEVCOM AvMC C. M. Bowden Research Center Redstone ArsenalAL35898-5000 United States Department of Information Engineering University of Brescia Brescia25123 Italy US Army Space & Missile Defense Command Tech Center Redstone ArsenalAL35898 United States Institute of Photonics and Quantum Sciences Heriot-Watt University SUPA EdinburghEH14 4AS United Kingdom Department of Physical and Chemical Sciences University of L’Aquila L’AquilaI-67100 Italy Photonics Initiative Advanced Science Research Center City University of New York New YorkNY10031 United States Physics Program Graduate Center City University of New York New YorkNY10016 United States Department of Electrical and Computer Engineering Duke University DurhamNC27708 United States Department of Physics Universitat Politècnica de Catalunya Barcelona Terrassa08222 Spain

Abrupt time variations of the properties of optical materials have been at the center of intense research efforts in recent years, with the prospect of enabling extreme wave transformations and of leveraging time as a degree of freedom for wave control. While the most viable approach to yield ultrafast variations of the optical material response is through optical pumping of nonlinear media, the complex dynamics in these systems are not yet fully understood. Here, as a relevant case study, we rigorously investigate the pump-probe dynamics in a 310nm-thick transparent conductive oxide etalon, using a weak 40 femtosecond probe and a pump that displays peak power densities in the TW/cm2 range with a duration of a few femtoseconds. We examine the pump-probe interaction using a hydrodynamic-Maxwell approach that accounts for diffraction, self-focusing and -defocusing, self- and cross-phase modulation, probe gain, and linear and nonlinear material dispersion expanded in the perturbative regime up to 9th order for both pump and probe. By allowing the intricacies of the pump-probe interaction to proceed in time, we can also define an effective spatio-temporal permittivity for a more direct evaluation of the material ultra-broadband optical behavior. The reported results challenge the conventional modeling of this kind of problem, which has so far overlooked pump dynamics, simplistically assigning a local time-dependent refractive index to the probe that may be designed to fit the experimental data, but has no physical connection to the complex pump-probe interaction. Our approach unveils new dynamics, pointing towards the possibility to achieve extreme pulse compression into the attosecond range and nonlinear diffraction over deeply subwavelength propagation distances, thus opening a possible new path towards novel and cost-effective tools for integrated photonics and attosecond science. © 2025, CC BY-NC-ND.

关键词： Probes

Landau Polaritons in a Full-Dielectric Three-Dimensional Photonic-Crystal Cavity

学校读者我要写书评

暂无评论

Landau Polaritons in a Full-Dielectric Three-Dimensional Pho...

CLEO: science and Innovations, S and I 2022

作者： Tay, Fuyang Mojibpour, Ali Liang, Shuang Baydin, Andrey Ahmadivand, Arash Peraca, Nicolas Marquez Xu, Hongjing Gardner, Geoff C. Manfra, Michael J. Hagenmüller, David Kono, Junichiro Department of Electrical and Computer Engineering Rice University HoustonTX77005 United States Applied Physics Graduate Program Smalley-Curl Institute Rice University HoustonTX77005 United States Department of Physics and Astronomy Purdue University West LafayetteIN47907 United States Birck Nanotechnology Center Purdue University West LafayetteIN47907 United States Smalley-Curl Institute Rice University HoustonTX77005 United States Department of Physics and Astronomy Rice University HoustonTX77005 United States Microsoft Quantum Purdue Purdue University West LafayetteIN47907 United States School of Electrical and Computer Engineering Purdue University West LafayetteIN47907 United States School of Materials Engineering Purdue University West LafayetteIN47907 United States Université de Strasbourg CNRS Strasbourg67000 France Department of Materials Science and NanoEngineering Rice University HoustonTX77005 United States

ISBN: (纸本)9781557528209

We fabricated a full-dielectric three-dimensional photonic-crystal cavity containing an ultrahigh-mobility two-dimensional electron gas. By applying a strong perpendicular magnetic field, we created Landau polaritons originating from the ultrastrong coupling of electrons with cavity modes. © Optica Publishing Group 2022, © 2022 The Author(s)

关键词： Polariton

Data Mining for Predicting Customer Satisfaction Using Clustering Techniques

学校读者我要写书评

暂无评论

Data Mining for Predicting Customer Satisfaction Using Clust...

International Conference on Information Management and Technology (ICIMTech)

作者： Kartika Purwandari Join W. C. Sigalingging Muhammad Fhadli Shinta Nur Arizky Bens Pardamean Bioinformatics & Data Science Research Center Bina Nusantara University Jakarta Indonesia National Central University Taoyuan Taiwan BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9781728170718

ISBN: (纸本)9781728170725

Managing customer satisfaction has become an important business trend, including restaurants business. This study aims to determine the application of the K-means, Spectral Clustering (SC), and Agglomerative Clustering (AC) method for measuring customer satisfaction on a family restaurant in Taiwan. We contribute the data collection process and application of data mining in a family restaurant. The clustering analysis based on agglomerative clustering approach performs as well as the K-means approach to cluster the same characteristics of the customers. At last, this study shows the measurement result of customer satisfaction and provides improvement suggestion to the restaurant concerned.

关键词： Data mining Customer satisfaction Principal component analysis computer science Reliability Data visualization

Smart IoT CPO Storage Tank

学校读者我要写书评

暂无评论

IOP Conference Series: Earth and Environmental science 2022年第1期998卷

作者： Rengga Arnalis Renjani Hermantoro Prima Okta Adi Nugraha Kartika Purwandari Teddy Suparyanto Bens Pardamean Department of Agricultural Engineering Institute of Agriculture STIPER Yogyakarta Indonesia 55281 Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia 11480

Indonesia's crude palm oil (CPO) production from year to year continues to increase, at the end of 2020 it reached 17.35 million tons, up 3.6% from the previous year. Increasing production will result in more CPO stock and require good storage. The storage process that occurs is to maintain the temperature of the CPO so that the quality is not damaged. This temperature regulation is still done manually and raises the risk of work accidents. The purpose of this research is to create a temperature control system and automatic volume measurement that can be monitored from a smartphone. The manufacture of a control system used ESP8266 NodeMCu microcontroller, temperature sensor, proximity sensor, and 1000-Watt heater. programming used the Arduino IDE and C++. The result of this study was an IoT CPO Storage Tank design equipped with sensors and microcontrollers. The temperature was measured with the DS18B20 sensor had a data accuracy of 99.19% while the volume measured with the HC-SR04 sensor had an accuracy of 99.78%. Data obtained from the sensor could be seen through the Thingspeak application from a computer or smartphone.

关键词：

Reply to “Comment on ‘Scattering Cancellation-Based Cloaking for the Maxwell-Cattaneo Heat Waves’”

学校读者我要写书评

暂无评论

Physical Review Applied 2021年第5期15卷 058002-058002页

作者： M. Farhat S. Guenneau P.-Y. Chen A. Alù K.N. Salama Computer Electrical and Mathematical Science and Engineering (CEMSE) Division King Abdullah University of Science and Technology (KAUST) Thuwal 23955-6900 Saudi Arabia UMI 2004 Abraham de Moivre-CNRS Imperial College London London SW7 2AZ United Kingdom Department of Electrical and Computer Engineering University of Illinois at Chicago Chicago Illinois 60607 USA Photonics Initiative Advanced Science Research Center City University of New York New York New York 10031 USA Physics Program Graduate Center City University of New York New York New York 10016 USA