检索结果-内蒙古大学图书馆

Enhancing Diagnostic Accuracy for Knee Osteoarthritis Using a Deep Learning Approach

学校读者我要写书评

暂无评论

Enhancing Diagnostic Accuracy for Knee Osteoarthritis Using ...

International Symposium on applied science 2024, ISAS 2024

作者： Raza, Aquib Ching, Congo Tak Shing Liu, Peng-Ta Phan, Thien-Luan Tran, Ngoc-Luan Nguyen, Ha Anh T. Rameez, Mohammad Li, Hung-Chung Linh, Dao Nguyen Phuong Van Hieu, Nguyen Tran, Trung Nghia National Taiwan University Taipei City10673 Taiwan Research Center for Information Technology Academia Sinica Taipei City11529 Taiwan Graduate Institute of Biomedical Engineering National Chung Hsing University Taichung402 Taiwan Department of Electrical Engineering National Chi Nan University Nantou County Taiwan Advanced Plant and Food Crop Biotechnology Center National Chung Hsing University Taichung402 Taiwan International Doctoral Program in Agriculture National Chung Hsing University Taichung402 Taiwan Fall Prevention Center Department of Physical Medicine & Rehabilitation Changhua Christian Hospital Changhua500 Taiwan Department of Physics and Electronic Engineering University of Science Vietnam National University - Ho Chi Minh City Ho Chi Minh City70000 Viet Nam Department of Computer Science University of York York HeslingtonYO10 5DD United Kingdom Undergraduate Program of Intellectual Creativity Engineering National Chung Hsing University Taichung402 Taiwan Ho Chi Minh City72409 Viet Nam HCMUT Vietnam National University Ho Chi Minh City Thu Duc Ho Chi Minh City71308 Viet Nam

This research introduces a deep learning framework that combines convolutional neural networks with autoencoders to improve the diagnostic accuracy of knee osteoarthritis. The study utilized a publicly available dataset from the Mendeley Data repository, where knee joint images were preprocessed using Contrast Limited Adaptive Histogram Equalization to enhance contrast and ensure consistent image sizing. Initially, an autoencoder was employed in an unsupervised manner to learn compressed representations of the data. These representations were then used to train a CNN to classify knee images into 'healthy' and 'osteoarthritic' categories. The model was trained using an 80:20 split for training and testing data, incorporating early stopping and data augmentation techniques to prevent overfitting and enhance generalization. Performance metrics such as accuracy, precision, recall, and the area under the Receiver Operating Characteristic curve (ROCAUC) were used to evaluate the model, resulting in a high test accuracy of 98.95%. The high precision and recall rates further confirmed the model's robustness in diagnosing KOA. To enhance interpretability, Gradient-weighted Class Activation Mapping (Grad-CAM) was applied to identify critical regions in the images that influenced the model's decisions. Additionally, t-Distributed Stochastic Neighbor Embedding (t-SNE) was used to visualize the high-dimensional encoded features in a two-dimensional space, providing deeper insights into how the model differentiates between classes. The promising results of this deep learning approach suggest its potential for broader applications in medical imaging diagnostics. By providing healthcare professionals with a tool that enhances diagnostic accuracy and operational efficiency, this framework lays the foundation for developing scalable, AI-driven diagnostic systems for various complex medical conditions. © 2025 Institute of physics Publishing. All rights reserved.

关键词： Joints (anatomy)

Enhanced Superconducting Qubit Performance Through Ammonium Fluoride Etch

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Kopas, Cameron J. Goronzy, Dominic P. Pham, Thang Torres Castanedo, Carlos G. Cheng, Matthew Cochrane, Rory Nast, Patrick Lachman, Ella Zhelev, Nikolay Z. Vallières, André Murthy, Akshay A. Oh, Jin-Su Zhou, Lin Kramer, Matthew J. Cansizoglu, Hilal Bedzyk, Michael J. Dravid, Vinayak P. Romanenko, Alexander Grassellino, Anna Mutus, Josh Y. Hersam, Mark C. Yadavalli, Kameshwar Rigetti Computing BerkeleyCA United States Department of Materials Science and Engineering Northwestern University EvanstonIL United States Center for Applied Physics and Superconducting Technologies Northwestern University EvanstonIL United States Department of Physics and Astronomy Northwestern University EvanstonIL United States Department of Physics University of Oregon EugeneOR United States Graduate Program in Applied Physics Northwestern University EvanstonIL60208 United States Fermi National Accelerator Laboratory BataviaIL United States Ames Laboratory U.S. Department of Energy AmesIA United States Northwestern University EvanstonIL United States Department of Chemistry Northwestern University EvanstonIL United States Department of Electrical and Computer Engineering Northwestern University EvanstonIL United States

The performance of superconducting qubits is often limited by dissipation and two-level systems (TLS) losses. The dominant sources of these losses are believed to originate from amorphous materials and defects at interfaces and surfaces, likely as a result of fabrication processes or ambient exposure. Here, we explore a novel wet chemical surface treatment at the Josephson junction-substrate and the substrate-air interfaces by replacing a buffered oxide etch (BOE) cleaning process with one that uses hydrofluoric acid followed by aqueous ammonium fluoride. We show that the ammonium fluoride etch process results in a statistically significant improvement in median T1 by ∼ 22% (p = 0.002), and a reduction in the number of strongly-coupled TLS in the tunable frequency range. Microwave resonator measurements on samples treated with the ammonium fluoride etch prior to niobium deposition also show ∼ 33% lower TLS-induced loss tangent compared to the BOE treated samples. As the chemical treatment primarily modifies the Josephson junction-substrate interface and substrate-air interface, we perform targeted chemical and structural characterizations to examine materials’ differences at these interfaces and identify multiple microscopic changes that could contribute to decreased TLS. © 2024, CC BY-NC-ND.

关键词： Fluorine compounds

Instruction Multi-Constraint Molecular Generation Using a Teacher-Student Large Language Model

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhou, Peng Wang, Jianmin Li, Chunyan Wang, Zixu Liu, Yiping Sun, Siqi Lin, Jianxin Wei, Leyi Cai, Xibao Lai, Houtim Liu, Wei Wang, Longyue Liu, Yuansheng Zeng, Xiangxiang College of Information Science and Engineering Hunan University Changsha China The Interdisciplinary Graduate Program in Integrative Biotechnology Yonsei University Incheon21983 Korea Republic of School of Informatics Yunnan Normal University Kunming650500 China Department of Computer Science University of Tsukuba Tsukuba3058577 Japan Research Institute of Intelligent Complex Systems Fudan University Shanghai200433 China Shanghai AI Laboratory Shanghai200232 China Centre for Artificial Intelligence driven Drug Discovery Faculty of Applied Science Macao Polytechnic University China School of Informatics Xiamen University Xiamen China Tencent AI Lab China

While various models and computational tools have been proposed for structure and property analysis of molecules, generating molecules that conform to all desired structures and properties remains a challenge. Here, we introduce a multi-constraint molecular generation large language model, TSMMG, which, akin to a student, incorporates knowledge from various small models and tools, namely, the 'teachers'. To train TSMMG, we construct a large set of text-molecule pairs by extracting molecular knowledge from these 'teachers', enabling it to generate novel molecules that conform to the descriptions through various text prompts. We experimentally show that TSMMG remarkably performs in generating molecules meeting complex, natural language-described property requirements across two-, three-, and four-constraint tasks, with an average molecular validity of over 99% and success ratio of 82.58%, 68.03%, and 67.48%, respectively. The model also exhibits adaptability through zero-shot testing, creating molecules that satisfy combinations of properties that have not been encountered. It can comprehend text inputs with various language styles, extending beyond the confines of outlined prompts, as confirmed through empirical validation. Additionally, the knowledge distillation feature of TSMMG contributes to the continuous enhancement of small models, while the innovative approach to dataset construction effectively addresses the issues of data scarcity and quality, which positions TSMMG as a promising tool in the domains of drug discovery and materials science. Copyright © 2024, The Authors. All rights reserved.

关键词： Students

Quantum Nonlocality: Multi-copy Resource Inter-convertibility & Their Asymptotic Inequivalence

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ghosh, Subhendu B. Chowdhury, Snehasish Roy Kar, Guruprasad Roy, Arup Guha, Tamal Banik, Manik Physics and Applied Mathematics Unit Indian Statistical Institute 203 B.T. Road Kolkata700108 India Department of Physics A B N Seal College West Bengal Cooch Behar736101 India QICI Quantum Information and Computation Initiative Department of Computer Science The University of Hong Kong Pokfulam Road Hong Kong Department of Physics of Complex Systems S.N. Bose National Center for Basic Sciences Block JD Sector III Salt Lake Kolkata700106 India

Quantum nonlocality, pioneered in Bell's seminal work and subsequently verified through a series of experiments, has drawn substantial attention due to its practical applications in various protocols. Evaluating and comparing the extent of nonlocality within distinct quantum correlations holds significant practical relevance. Within the resource theoretic framework this can be achieved by assessing the inter-conversion rate among different nonlocal correlations under free local operations and shared randomness. In this study we, however, present instances of quantum nonlocal correlations that are incomparable in the strongest sense. Specifically, when starting with an arbitrary many copies of one nonlocal correlation, it becomes impossible to obtain even a single copy of the other correlation, and this incomparability holds in both directions. Such incomparable quantum correlations can be obtained even in the simplest Bell scenario, which involves two parties, each having two dichotomic measurements setups. Notably, there exist an uncountable number of such incomparable correlations. Our result challenges the notion of a 'unique gold coin', often referred to as the 'maximally resourceful state', within the framework of the resource theory of quantum nonlocality. To this end, we provide examples of isotropic quantum correlations that cannot be distilled up-to Tsirelson point,and thus partially answer a long standing open question in nonlocality distillation. © 2023, CC BY.

关键词： Bells

Loss tangent fluctuations due to two-level systems in superconducting microwave resonators

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Vallières, André Russell, Megan E. You, Xinyuan Garcia-Wetten, David A. Goronzy, Dominic P. Walker, Mitchell J. Bedzyk, Michael J. Hersam, Mark C. Romanenko, Alexander Lu, Yao Grassellino, Anna Koch, Jens McRae, Corey Rae H. Graduate Program in Applied Physics Northwestern University EvanstonIL60208 United States Fermi National Accelerator Laboratory BataviaIL60510 United States Department of Physics and Astronomy Northwestern University EvanstonIL60208 United States Department of Materials Science and Engineering Northwestern University EvanstonIL60208 United States Department of Chemistry Northwestern University EvanstonIL60208 United States Department of Electrical and Computer Engineering Northwestern University EvanstonIL60208 United States Center for Applied Physics and Superconducting Technologies Northwestern University EvanstonIL60208 United States Electrical Computing and Energy Engineering Department University of Colorado BoulderCO80309 United States Department of Physics University of Colorado BoulderCO80309 United States National Institute of Standards and Technology BoulderCO80305 United States

Superconducting microwave resonators are critical to quantum computing and sensing technologies. Additionally, they are common proxies for superconducting qubits when determining the effects of performance-limiting loss mechanisms such as from two-level systems (TLS). The extraction of these loss mechanisms is often performed by measuring the internal quality factor Qi as a function of power or temperature. In this work, we investigate large temporal fluctuations of Qi at low powers over periods of 12 to 16 hours (relative standard deviation σQi/Qi = 13%). These fluctuations are ubiquitous across multiple resonators, chips and cooldowns. We are able to attribute these fluctuations to variations in the TLS loss tangent due to two main indicators. First, measured fluctuations decrease as power and temperature increase. Second, for interleaved measurements, we observe correlations between low- and medium-power Qi fluctuations and an absence of correlations with high-power fluctuations. Agreement with the TLS loss tangent mean is obtained by performing measurements over a time span of a few hours. We hypothesize that, in addition to decoherence due to coupling to individual near-resonant TLS, superconducting qubits are affected by these observed TLS loss tangent fluctuations. © 2024, CC BY.

关键词： Qubits

Multi-Tap Canceller for Wi-Fi Communication in Band with Fill Duplex

学校读者我要写书评

暂无评论

Multi-Tap Canceller for Wi-Fi Communication in Band with Fil...

International Conference on Contemporary Computing and Informatics (IC3I)

作者： Supratim Saha Rajni Gautam Pravesh Belwal S. Hemelatha S. Kannimuthu Vijaya N. Aher Electronics and Communication Engineering Swami Vivekanand Subharti University Meerut India Department of Physics School of Basic & Applied Sciences K. R. Mangalam University Gurugram India Electronics and Communications Engineering Dev Bhoomi Uttarakhand University Uttarakhand India Department of Computer Science Engineering Karpagam Academy of Higher Education Coimbatore India Department of Information Technology Karpagam College of Engineering Coimbatore India E&TC Vishwakarma Institute of Information Technology Pune India

Since they involve the appropriate reduction of self-interference induced by the co-located transmitters, in-band full-duplex wirelessly network is difficult to implement. In order to increase system separation, the straight antennas coupling and multichip effects that make up a normal disturbance channel are both cancelled using a novel input time line RF recycled content structure shown in this work. A four-tap recycled content prototype had been evaluated under various settings and discovered to provide, in isolation situations, an average of 30 dB of signal cancelation above a 30 MHz band centered at 2.45 GHz. The canceller increased the overall analog seclusion to 90 dB for such cases when used in conjunction with only Omni-directional high-isolation antennas. The canceller reduced a +30 dbm OFDM in an enclosed environment. Along a 20 MHz band with a 2.45 GHz center, the device reduced the noise by 22 dB and generated 78 dB of overall analog seclusion. This thorough evaluation establishes the degree of analogue interference cancellation that may be anticipated for the various situations taken into account, as well as the effectiveness constraints of an optimized multi RF attenuator.

关键词：

Dose Requirements for Fused Multi-Modal Electron Tomography

学校读者我要写书评

暂无评论

Microscopy and microanalysis : the official journal of Microscopy Society of America, Microbeam Analysis Society, Microscopical Society of Canada 2023年第1期29卷 1968-1969页

作者： Manassa, Jason Schwartz, Jonathan Jiang, Yi Zheng, Huihuo Fessler, Jeffrey A. Wendy Di, Zichao Hovden, Robert Department of Materials Science and Engineering University of Michigan Ann Arbor MI United States Advanced Photon Source Facility Argonne National Laboratory Lemont IL United States Argonne Leadership Computing Facility Argonne National Laboratory Lemont IL United States Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor MI United States Mathematics and Computer Science Division Argonne National Laboratory Lemont IL United States Applied Physics Program University of Michigan Ann Arbor MI United States

Developing a medical artificial intelligence course for high school students

学校读者我要写书评

暂无评论

Developing a medical artificial intelligence course for high...

International Forum on Medical Imaging in Asia 2021, IFMIA 2021

作者： Huang, Chao-Jung Wu, Tinghui Lu, Jui-Ting Lin, Beatrice Chang, Dawei Wang, Pochuan Wang, Mei-Chi Lee, Peijung Wang, Weichung National Taiwan University-Stanford Joint Program Office of AI in Biotechnology Ministry of Science and Technology Joint Research Center for Artificial Intelligence Technology and All Vista Healthcare Taipei Taiwan Institute of Applied Mathematical Sciences National Taiwan University Taipei Taiwan Department of Mathematics Ecole Normale Supérieure de Lyon Lyon France Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan Department of Electronic and Computer Engineering National Taiwan University of Science and Technology Taipei Taiwan Department of Mathematics National Taiwan University Taipei Taiwan

ISBN: (数字)9781510644212

ISBN: (纸本)9781510644205

Artificial intelligence (AI) training courses often require prerequisites such as calculus or statistics. It is hence challenging to design and develop an introductory AI course for students of secondary education. This research intends to develop a medical AI course, provide high school students with an overview of deep learning applications in medical image analysis, and inspire them to pursue careers in the field of medical AI. We designed a 20-hour course, including lectures and two hands-on projects based on medical image classification. The proposed courses provided medical AI disciplines and built up their knowledge from basic to advanced levels. During the ten-day online courses, all the students were fully engaged and gave us positive feedback. The students endeavored to complete the experimental study in training, testing, and hypothesis of medical images application in the course. Their performance exceeded all expectations, for they did further analysis by tuning different hyperparameters. We designed a course evaluation form, which suggested that the students found it essential and expected to interact with the instructors. The results indicate that combining lectures with hands-on sessions would lead to evidently better achievement in terms of high school students' medical AI knowledge and positive attitudes while addressing real-world problems in the projects. Through this innovative education model, high school students regained their enthusiasm and were encouraged to cultivate their medical AI skills through self-learning while finishing the project. We conclude that this course could be successfully applied to interdisciplinary education in high school. © 2021 SPIE.

关键词： Students

Quantum Computing Universal Thermalization Dynamics in a (2+1)D Lattice Gauge Theory

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Mueller, Niklas Wang, Tianyi Katz, Or Davoudi, Zohreh Cetina, Marko Department of Physics University of Washington SeattleWA98195 United States Department of Physics Duke University DurhamNC27708 United States Duke Quantum Center Duke University DurhamNC27701 United States The NSF Institute for Robust Quantum Simulation University of Maryland College ParkMD20742 United States Department of Electrical and Computer Engineering Duke University DurhamNC27708 United States School of Applied and Engineering Physics Cornell University IthacaNY14853 United States Department of Physics Maryland Center for Fundamental Physics University of Maryland College ParkMD20742 United States Joint Center for Quantum Information and Computer Science NIST University of Maryland College ParkMD20742 United States University of Maryland College ParkMD20742 United States

Simulating non-equilibrium phenomena in strongly-interacting quantum many-body systems, including thermalization, is a promising application of near-term and future quantum computation. By performing experiments on a digital quantum computer consisting of fully-connected optically-controlled trapped ions, we study the role of entanglement in the thermalization dynamics of a Z2 lattice gauge theory in 2+1 spacetime dimensions. Using randomized-measurement protocols, we efficiently learn a classical approximation of non-equilibrium states that yields the gap-ratio distribution and the spectral form factor of the entanglement Hamiltonian. These observables exhibit universal early-time signals for quantum chaos, a prerequisite for thermalization. Our work, therefore, establishes quantum computers as robust tools for studying universal features of thermalization in complex many-body systems, including in gauge theories. Copyright © 2024, The Authors. All rights reserved.

关键词： Quantum computers