检索结果-内蒙古大学图书馆

TextAI 3.0 (Multimodal): multimodal sentiment analysis using attention-enabled ensemble-based deep learning in hyperbolic space

引用

international Journal of Information Technology (Singapore) 2025年 1-16页

作者： Singh, Jaskaran Sanga, Prabhav Khanna, Narendra N. Laird, John R. Singh, Inder M. Kalra, Mannudeep K. Mantella, Laura E. Johri, Amer M. Faa, Gavino Tiwari, Ekta Singh, Rajesh Abbas, Mohamed Saba, Luca Suri, Jasjit S. Stroke Monitoring and Diagnostic Division AtheroPoint™ Roseville 95661 CA United States Bharati Vidyapeeth’s College of Engineering New Delhi India Department of Cardiology Indraprastha APOLLO Hospitals New Delhi 110001 India Department of Neurology and Stroke Program University of Maryland School of Medicine Baltimore United States Department of Radiology Harvard Medical School Boston 02115 MA United States Department of Biomedical and Molecular Sciences Queen’s University Kingston ON Canada Division of Cardiology Department of Medicine Queen’s University Kingston ON Canada Department of Pathology University of Cagliari Cagliari Italy Department of Computer Science Visvesvaraya National Institute of Technology (VNIT) Nagpur 440010 India Department of Research and Innovation Uttaranchal Institute of Technology Uttaranchal University Dehradun 248007 India Central Labs King Khalid University P.O. Box 960 AlQura’a Abha Saudi Arabia Electrical Engineering Department College of Engineering King Khalid University Abha 61421 Saudi Arabia Department of Neurology University of Cagliari Cagliari Italy Department of ECE Idaho State University Pocatello 83209 ID United States Department of CE Graphic Era Deemed to Be University Dehradun 248002 India University Center for Research and Development Chandigarh University Mohali India Symbiosis Institute of Technology Symbiosis International (Deemed University) Nagpur Campus Pune India Department of Innovation Global Biomedical Technologies Inc. Roseville 95661 CA United States

The rising prevalence of depression presents a significant global health challenge, underscoring the need for effective early detection through sentiment analysis. Traditional multimodal sentiment analysis methods, which rely on Euclidean space for data representation, often fail to capture the complex hierarchical relationships and non-linear structures inherent in multimodal data. To address this limitation, we propose a novel multimodal architecture that operates in hyperbolic space and incorporates attention-based ensemble learning to enhance feature representation and model performance. We developed and evaluated ten AI models—five utilizing Euclidean space and five leveraging hyperbolic space—on the Spoken Language Understanding Evaluation (SLUE) benchmark dataset. The models were assessed using cross-validation techniques to ensure robustness, and statistical analyses were conducted to validate the findings. Our results indicate that hyperbolic-based multimodal models achieve a 2.32% improvement in accuracy compared to their Euclidean counterparts, while the integration of self-attention mechanisms further contributes an average accuracy gain of 0.96%. Additionally, we observed a 3.76% decline in performance when reducing the training-to-test data ratio from 90:10 to 50:50, highlighting the importance of data distribution in model training. These findings confirm that attention-enhanced multimodal models in hyperbolic space offer superior representations for sentiment analysis. © Bharati Vidyapeeth's Institute of computer Applications and Management 2025.

关键词： Attention-enabled Deep learning Euclidean space Hyperbolic space Multimodal Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Voltage Levels and Reactive Power in Distribution Networks with High Integration of Distributed Photovoltaic Generation

Voltage Levels and Reactive Power in Distribution Networks w...

引用

2019 IEEE PES Conference on Innovative Smart Grid Technologies, ISGT Latin America 2019

作者： Darui, Caroline B. F. Lucca, Tiago G. Abaide, Alzenira Da R. Da Veiga, Matheus F. Da Cruz, Matheus S. Knak Neto, Nelson Wüst, Lucas L. Figueiró, Iuri C. Federal University of Santa Maria Graduate Program in Electrical Engineering Santa Maria Brazil URI Santo Ângelo Department of Engineering and Computer Science Santo Ângelo Brazil

ISBN: (纸本)9781538695678

The Brazilian electrical system is undergoing many changes due to the exponential growth of photovoltaic systems connected to the grid (PV). This increase may affect power quality parameters, such as reduction of power factor and increase of voltage levels. This work aims to model and simulate a low voltage distribution network with high levels of integration of PV systems in order to verify how the voltage and reactive parameters behave in these cases. It was used new load curve models, the Monte Carlo method and the OpenDSS software. © 2019 IEEE.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

Development of a Selective Wet-Chemical Etchant for 3D Structuring of Silicon via Nonlinear Laser Lithography

arXiv

引用

arXiv 2023年

作者： Borra, Mona Zolfaghari Radfar, Behrad Nasser, Hisham Çolakoğlu, Tahir Tokel, Onur Turnalı, Ahmet Demirtaş, Merve Ustunel, Hande Toffoli, Daniele Ömer İlday, F. Turan, Raşit Pavlov, Ihor Bek, Alpan ODTÜ-GÜNAM Middle East Technical University Ankara06800 Turkey Ankara06800 Turkey Department of Electronics and Nanoengineering Aalto University Tietotie 3 EspooFI-02150 Finland Department of Physics Engineering Ankara University Ankara06100 Turkey Department of Physics Bilkent University Ankara06800 Turkey UNAM National Nanotechnology Research Center Institute of Materials Science and Nanotechnology Bilkent University Ankara06800 Turkey Department of Electrical and Electronics Engineering Bilkent University Ankara06800 Turkey Department of Electrical and Computer Engineering Boston University 8 Saint Mary’s Street BostonMA02215 United States Ankara06800 Turkey Network Technologies Department TUBITAK ULAKBIM Ankara06800 Turkey Department of Chemical and Pharmaceutical Sciences Trieste University Trieste Italy IOM-CNR Istituto Officina dei Materiali Trieste34149 Italy Micro and Nanotechnology Graduate Program of Natural and Applied Sciences Middle East Technical Turkey

Recently-demonstrated high-quality three-dimensional (3D) subsurface laser processing inside crystalline silicon (c-Si) wafers opens a door to a wide range of novel applications in multidisciplinary research areas. Using this technique, a novel maskless micro-pillars with precise control on the surface reflection and coverage are successfully fabricated by etching the laser processed region of c-Si wafer. To achieve this, a particular selective wet chemical etching is developed to follow subsurface laser processing of c-Si to reveal the desired 3D structures with smooth surfaces. Here, we report the development of a novel chromium-free chemical etching recipe based on copper nitrate, which yields substantially smooth surfaces at high etch rate and selectivity on the both laser-processed Si surface and subsurface, i.e., without significant etching of the unmodified Si. Our results show that the etch rate and surface morphology are interrelated and strongly influenced by the composition of the adopted etching solution. After an extensive compositional study performed at room temperature, we identify an etchant with a selectivity of over 1600 times for laser-modified Si with respect to unmodified Si. We also support our findings using density functional theory calculations of HF and Cu adsorption energies, indicating significant diversity on the c-Si and laser-modified surfaces. Copyright © 2023, The Authors. All rights reserved.

关键词： Morphology

来源：评论

学校读者我要写书评

暂无评论

Cavity-mediated superthermal phonon correlations in the ultrastrong coupling regime

arXiv

引用

arXiv 2024年

作者： Kim, Dasom Hou, Jin Lee, Geon Agrawal, Ayush Kim, Sunghwan Zhang, Hao Bao, Di Baydin, Andrey Wu, Wenjing Tay, Fuyang Huang, Shengxi Chia, Elbert E.M. Kim, Dai-Sik Seo, Minah Mohite, Aditya D. Hagenmüller, David Kono, Junichiro Applied Physics Graduate Program Smalley–Curl Institute Rice University HoustonTX77005 United States Department of Electrical and Computer Engineering Rice University HoustonTX77005 United States Department of Materials Science and NanoEngineering Rice University HoustonTX77005 United States Sensor System Research Center Korea Institute of Science and Technology Seoul02792 Korea Republic of Department of Physics and Astronomy Seoul National University Seoul08826 Korea Republic of Department of Chemical and Biomolecular Engineering Rice University Houston77005 United States Ulsan44919 Korea Republic of Division of Physics and Applied Physics School of Physical and Mathematical Sciences Nanyang Technological University Singapore637371 Singapore Smalley–Curl Institute Rice University HoustonTX77005 United States Rice Advanced Materials Institute Rice University HoustonTX77005 United States KU–KIST Graduate School of Converging Science and Technology Korea University Seoul02841 Korea Republic of Université de Strasbourg CNRS Strasbourg67200 France Department of Physics and Astronomy Rice University HoustonTX77005 United States

Phonons, or vibrational quanta, are behind some of the most fundamental physical phenomena in solids, including superconductivity, Raman processes, and broken-symmetry phases. It is therefore of fundamental importance to find ways to harness phonons for controlling these phenomena and developing novel quantum technologies. However, the majority of current phonon control techniques rely on the use of intense external driving fields or strong anharmonicities, which restricts their range of applications. Here, we present a scheme for controlling the intensity fluctuations in phonon emission at room temperature based on multimode ultrastrong light–matter coupling. The multimode ultrastrong coupling regime is achieved by coupling two optical phonon modes in lead halide perovskites to an array of nanoslots, which operates as a single-mode cavity. The extremely small mode volume of the nanoslots enables unprecedented coupling strengths in a cavity phonon-polariton system. In the far-detuned, low-cavity-frequency regime, we demonstrate that the nanoslot resonator mediates an effective coupling between the phonon modes, resulting in superthermal phonon bunching in thermal equilibrium, both within the same mode and between different modes. Experimental results are in good agreement with a multimode Hopfield model. Our work paves the way for the tailoring of phonons to modify charge and energy transport in perovskite materials, with potential applications in light-collecting or emitting devices. Copyright © 2024, The Authors. All rights reserved.

关键词： Perovskite

来源：评论

学校读者我要写书评

暂无评论

Electrochemical biosensor based on an atomic layered composite of graphene oxide/graphene as an electrode material towards selective and sensitive detection of miRNA-21

引用

Microchemical Journal 2024年 199卷

作者： Huang, Min-Shin Govindasamy, Mani Chinnapaiyan, Sathishkumar Lin, Yi-Ting Lu, Shao-Yang Samukawa, Seiji Huang, Chi-Hsien Department of Materials Engineering Ming Chi University of Technology New Taipei City 243303 Taiwan International Ph.D. Program in Innovative Technology of Biomedical Engineering and Medical Devices Ming Chi University of Technology New Taipei City 24303 Taiwan Centre for Applied Research Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Chennai-602105 Tamil Nadu India Institute of Fluid Science Tohoku University Sendai 980-8577 Japan College of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu 300093 Taiwan Division of Rheumatology Allergy and Immunology Chang Gung Memorial Hospital Taoyuan City 33305 Taiwan College of Engineering Chang Gung University Taoyuan City 33302 Taiwan

Development of an efficient technique towards the detection of miRNAs is highly significant for the timely diagnosis and prognosis of cancers. In this study, we utilized the chemical vapor deposition (CVD) technique to grow bilayer graphene (BLG) on copper foil and subsequently transferred the BLG to fluorine doped tin oxide (FTO) substrate via a facile wet transfer technique. The upper layer of the BLG was modified to graphene oxide (GO) with a low damage plasma treatment (LDPT) process to serve as a biomolecule receiving layer and the lower graphene layer (G) serves as an electron transport layer. The developed GO/G/FTO platform offers superior sensing ability towards the miRNA-21. The results demonstrated that the proposed GO/G/FTO substrate detect the miRNA-21 with a wide linear range (10 fM ∼ 1 nM), low limit of detection (3.18 fM), high sensitivity (0.6 mApM⁻¹cm⁻²), selectivity and stability via the differential pulse voltammetry method. Additionally, the sensors can efficiently discriminate the target miRNA-21 from its complementary base mismatched counterparts. The proposed approach serves as an excellent tool for the early diagnosis of diseases. © 2024 Elsevier B.V.

关键词： Atomic layer oxidation Biosensor Cancer biomarkers Electrochemical Graphene oxide Plasma treatment

来源：评论

学校读者我要写书评

暂无评论

Homogenization and design of acoustic Willis metasurfaces

引用

Physical Review B 2021年第5期103卷 054306-054306页

作者： Hussein Esfahlani Yarden Mazor Andrea Alù Photonics Initiative Advanced Science Research Center City University of New York New York New York 10031 USA Kymeta Corporation Redmond Washington 98052 USA Department of Electrical and Computer Engineering The University of Texas at Austin Austin Texas 78712 USA Physics Program Graduate Center of the City University of New York New York New York 10016 USA

Metasurfaces are ultrathin planar arrays of carefully tailored subwavelength particles that enable agile and flexible manipulation of the impinging waves. Originally introduced in optics, their application to acoustic waves has recently opened exciting opportunities for exotic sound control. In conventional acoustic inclusions, the interactions with the impinging pressure and velocity are decoupled, limiting the functionalities that arrays of them can achieve. While the coupling between these two quantities in symmetry-breaking inclusions, known as Willis coupling, has been discussed for several years, only recently has it been realized that these phenomena can become nonperturbative in suitably tailored resonant scatterers. Here, we explore the opportunities that these Willis meta-atoms open in the context of acoustic metasurfaces, offering additional knobs to manipulate and tailor sound. The general response of Willis metasurface is analytically derived, yielding fundamental bounds and optimal surface responses enabling full control of the impinging acoustic wave front.

关键词： Acoustic metamaterials Acoustic wave phenomena Polarizability

来源：评论

学校读者我要写书评

暂无评论

Emergence of Interlayer Coherence in Twist-Controlled Graphene Double Layers

arXiv

引用

arXiv 2022年

作者： Lin, Kenneth A. Prasad, Nitin Burg, G. William Zou, Bo Ueno, Keiji Watanabe, Kenji Taniguchi, Takashi MacDonald, Allan H. Tutuc, Emanuel Microelectronics Research Center Department of Electrical and Computer Engineering The University of Texas at Austin AustinTX78758 United States Department of Chemistry and Biochemistry University of Maryland College ParkMD20742 United States Department of Physics The University of Texas at Austin AustinTX78712 United States Department of Chemistry Graduate School of Science and Engineering Saitama University Saitama338-8570 Japan Research Center for Functional Materials National Institute of Materials Science 1-1 Namiki Tsukuba Ibaraki305-0044 Japan International Center for Materials Nanoarchitectonics National Institute of Materials Science 1-1 Namiki Tsukuba Ibaraki305-0044 Japan

We report enhanced interlayer tunneling with reduced linewidth at zero interlayer bias in a twistcontrolled double monolayer graphene heterostructure in the quantum Hall regime, when the top (νT) and bottom (νB) layer filling factors are near νT= ±1/2, ±3/2 and νB= ±1/2, ±3/2, and the total filling factor ν = ±1 or ±3. The zero-bias interlayer conductance peaks are stable against variations of layer filling factor, and signal the emergence of interlayer phase coherence. Our results highlight twist control as a key attribute in revealing interlayer coherence using tunneling. Copyright © 2022, The Authors. All rights reserved.

关键词： Graphene

来源：评论

学校读者我要写书评

暂无评论

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

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

引用

Conference on Lasers and Electro-Optics (CLEO)

作者： Fuyang Tay Ali Mojibpour Shuang Liang Andrey Baydin Arash Ahmadivand Nicolas Marquez Peraca Hongjing Xu Geoff C. Gardner Michael J. Manfra David Hagenmüller Junichiro Kono Department of Electrical and Computer Engineering Rice University Houston Texas USA Applied Physics Graduate Program Smalley-Curl Institute Rice University Houston Texas USA Department of Physics and Astronomy Purdue University West Lafayette IN USA Birck Nanotechnology Center Purdue University West Lafayette IN USA Smalley-Curl Institute Rice University Houston Texas USA Department of Physics and Astronomy Rice University Houston Texas USA Microsoft Quantum Purdue Purdue University West Lafayette IN USA School of Electrical and Computer Engineering Purdue University West Lafayette IN USA School of Materials Engineering Purdue University West Lafayette IN USA ISIS (UMR 7006) Université de Strasbourg and CNRS Strasbourg France Department of Materials Science and Nano Engineering Rice University Houston Texas USA

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 ... 详细信息

ISBN: (数字)9781957171050

ISBN: (纸本)9781665466660

关键词： Couplings HEMTs Laser modes Polaritons Magnetic fields Gas lasers MODFETs

来源：评论

学校读者我要写书评

暂无评论

Terahertz chiral photonic-crystal cavities with broken time-reversal symmetry

arXiv

引用

arXiv 2024年

作者： Tay, Fuyang Sanders, Stephen Baydin, Andrey Song, Zhigang Welakuh, Davis M. Alabastri, Alessandro Rokaj, Vasil Dag, Ceren B. 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 Smalley–Curl Institute Rice University HoustonTX77005 United States John A. Paulson School of Engineering and Applied Sciences Harvard University CambridgeMA02139 United States Max Planck Institute for The Structure and Dynamics of Matter Luruper Chaussee 149 Hamburg22761 Germany ITAMP Harvard-Smithsonian Center for Astrophysics CambridgeMA02138 United States Department of Physics Harvard University CambridgeMA02138 United States Department of Physics Villanova University VillanovaPA19085 United States Department of Physics and Astronomy Rice University HoustonTX77005 United States Department of Materials Science and NanoEngineering Rice University HoustonTX77005 United States

Strong coupling between matter and vacuum electromagnetic fields in a cavity can induce novel quantum phases in thermal equilibrium via symmetry breaking. Particularly, coupling with circularly polarized fields can break time-reversal symmetry, leading to topological modifications in the band structure. Therefore, chiral optical cavities that host chiral vacuum fields are being sought, especially in the terahertz (THz) frequency range, where various large-oscillator-strength resonances exist. Here, we present a novel approach to achieving THz chiral photonic-crystal cavities (PCCs) with high-quality factors (>400) using a magnetoplasma in a lightly doped semiconductor. Numerical simulations of an optimized structure based on InSb in a small perpendicular magnetic field (∼0.2 T) show chiral cavity resonances with near-perfect ellipticity at the surfaces of the central dielectric layer, where one can place atomically thin materials like monolayer graphene. We theoretically estimate an energy gap on the order of 1 meV in graphene when coupled to our proposed chiral cavity, which is potentially measurable in experiments. These THz chiral PCCs offer a promising platform for exploring new phases in cavity-dressed condensed matter with broken time-reversal symmetry. Copyright © 2024, The Authors. All rights reserved.

关键词： Crystal symmetry

来源：评论

学校读者我要写书评

暂无评论

Accurately predicting anticancer peptide using an ensemble of heterogeneously trained classifiers

引用

Informatics in Medicine Unlocked 2023年 42卷

作者： Azim, Sayed Mehedi Sabab, Noor Hossain Nuri Noshadi, Iman Alinejad-Rokny, Hamid Sharma, Alok Shatabda, Swakkhar Dehzangi, Iman Center for Computational and Integrative Biology Rutgers University Camden 08102 NJ United States Department of Computer Science and Engineering United International University Plot 2 United City Madani Avenue BaddaDhaka 1212 Bangladesh Department of Bioengineering University of California Riverside 92507 CA United States BioMedical Machine Learning Lab The Graduate School of Biomedical Engineering The University of New South Wales (UNSW Sydney) Sydney NSW 2052 Australia UNSW Data Science Hub UNSW Sydney Sydney NSW 2052 Australia Health Data Analytics Program AI-enabled Processes Research Centre Macquarie University Sydney 2109 Australia Institute for Integrated and Intelligent Systems Griffith University Brisbane Australia Laboratory for Medical Science Mathematics RIKEN Center for Integrative Medical Sciences Yokohama 230-0045 Japan Department of Computer Science Rutgers University Camden 08102 NJ United States

The use of therapeutic peptides for the treatment of cancer has received tremendous attention in recent years. Anticancer peptides (ACPs) are considered new anticancer drugs which have several advantages over chemistry-based drugs including high specificity, strong tumor penetration capacity, and low toxicity level for normal cells. Due to the rise of experimentally verified bioactive peptides, several in silico approaches became imperative for the investigation of the characteristics of ACPs. In this paper, we proposed a new machine learning tool named iACP-RF that uses a combination of several sequence-based features and an ensemble of three heterogeneously trained Random Forest classifiers to accurately predict anticancer peptides. Experimental results show that our proposed model achieves an accuracy of 75.9% which outperforms other state-of-the-art methods by a significant margin. We also achieve 0.52, 75.6%, and 76.2% in terms of Matthews Correlation Coefficient (MCC), Sensitivity, and Specificity, respectively. iACP-RF as a standalone tool and its source code are publicly available at: https://***/MLBC-lab/iACP-RF. © 2023 The Authors

关键词： Anticancer peptides Ensemble learning Feature extraction Heterogeneous classifiers Machine learning Random Forest

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：