检索结果-内蒙古大学图书馆

6th International Conference on Applied Computational Intelligence in Information Systems, ACIIS 2023

作者： Zariful, Wafiq Tashim, Najeebah Az-Zahra Lim, Tiong Hoo Basri, Aida Maryam Chuprat, Suriayati Putra, Seno Adi Liu, Pengcheng Fakhrurroja, Hanif Universiti Teknologi Brunei Electrical and Electronic Engineering Bandar Seri Begawan Brunei Universiti Teknologi Brunei School of Applied Sciences and Mathematics Bandar Seri Begawan Brunei Universiti Teknologi Malaysia Razak Faculty of Technology and Informatics Johor Bahru Malaysia Telkom Universiti School of Industrial and System Engineering Bandung Indonesia University of York Department of Computer Science York United Kingdom Telkom University Research Center for Smart Mechatronics National Research and Innovation Agency Bandung Indonesia

ISBN: (纸本)9798350317428

Deep Learning plays a vital role in various domains, spanning surveillance, agriculture, and healthcare. However, the current landscape lacks comprehensive comparative studies, underscoring the needs to explore various convolutional neural networks (CNNs) for aquaculture industries. This study conducts a comprehensive comparative analysis on state-of-the-art object detection models to identify the most suitable approach for detecting freshwater prawns, specifically in challenging turbid and murky water conditions as there is a lack of comparison studies for underwater images of freshwater prawns. The evaluated models, including YOLOv8, Faster R-CNN (FRCNN), Single Shot Detector (SSD), and EfficientDet, are assessed based on the following metrics namely inference time, accuracy, image cropping size, and model memory footprint. Using a dataset comprising 2976 manually collected images of freshwater prawns, augmented to a total of 7148 images, our results demonstrate that YOLOv8 outperforms its counterparts, achieving an impressive mean Average Precision (mAP) accuracy of 83.71% with an inference time of 32.9 milliseconds. This positions YOLOv8 as a dependable choice for real-time object detection in challenging underwater environments and contributes to addressing the limited research comparing YOLOv8 with other popular object detection algorithms, thereby aiding model selection for similar object detection applications. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Electrochemical hydrogen charging treatment for hydrogenated 316 L stainless steel induced hydrogen therapy for orthopedic implantation

引用

Surface and Coatings Technology 2024年 479卷

作者： Lin, Yu-Chien Dhawan, Udesh Liu, Yen-Chen Lee, Yueh-Lien Liu, Xinke Yen, Hung-Wei Hu, Chih-Chien Chung, Ren-Jei Department of Chemical Engineering and Biotechnology National Taipei University of Technology Taipei Taiwan School of Materials Science and Engineering Nanyang Technological University Singapore Centre for the Cellular Microenvironment Division of Biomedical Engineering James Watt School of Engineering Mazumdar-Shaw Advanced Research Centre University of Glasgow Glasgow United Kingdom Department of Engineering Science and Ocean Engineering National Taiwan University Taipei Taiwan College of Materials Science and Engineering Chinese Engineering and Research Institute of Microelectronics Shenzhen University Shenzhe China Department of Electrical and Computer Engineering National University of Singapore Singapore Department of Materials Science and Engineering National Taiwan University Taipei Taiwan Bone and Joint Research Center Chang Gung Memorial Hospital Linko Taiwan Department of Orthopaedic Surgery Chang Gung Memorial Hospital Linko Taiwan College of Medicine Chang Gung University Taoyuan Taiwan Taipei Taiwan

Post-implant inflammation is a leading factor in the failure of orthopedic implant surgery. Hydrogen therapy is viewed as a medium capable of reducing reactive oxygen species (ROS) to alleviate inflammatory responses. However, existing hydrogen therapy methods have limitations, often involving undesired inhalation, injection, or non-targeted exposure of hydrogen to the body. To address this, the concept of delivering hydrogen precisely using the implant itself has been conducted in this study. Traditional hydrogen treatments for metallic implant materials, such as 316 L stainless steel (316 L SS), can induce hydrogen embrittlement (HE), significantly restricting the potential applications of hydrogenated implants in the biomedical field. Therefore, in this study, the electrochemical cathodic hydrogen charging method was employed to diffuse a hydrogenated layer of approximately 216 ± 31 nm on the surface of 316 L SS. This renders the material minimized by HE and alters its surface properties. Through in vitro and in vivo experiments, an approximately 80 % free radical scavenging rate was achieved. Additionally, significant anti-inflammatory effects were observed in the histological analysis of Femur implantation. This demonstrates that the surface hydrogenation treatment can impart anti-inflammatory properties to metallic implant materials without compromising their inherent material properties, thereby enhancing the success rate of surgical procedures. © 2024

关键词： Hydrogen

来源：评论

学校读者我要写书评

暂无评论

RETRACTION: Luminescent solar concentrator efficiency enhanced via nearly lossless propagation pathways

引用

NATURE PHOTONICS 2024年第9期18卷 998-998页

作者： Park, Kyoungwon Yi, Jeongmin Yoon, Suk-Young Park, Seong Min Kim, Jiyong Shin, Hyun-Beom Biswas, Swarup Yoo, Gang Yeol Moon, Sang-Hwa Kim, Jiwan Oh, Min Suk Wedel, Armin Jeong, Sohee Kim, Hyeok Oh, Soong Ju Kang, Ho Kwan Yang, Heesun Han, Chul Jong Display Research Center Korea Electronics Technology Institute Seongnam-si Republic of Korea Department of Materials Science and Engineering Korea University Seoul Republic of Korea Department of Materials Science and Engineering Hongik University Seoul Republic of Korea Functional Materials and Devices Fraunhofer Institute for Applied Polymer Research Potsdam Germany Device Technology Division Korea Advanced Nano Fab Center Suwon-si Republic of Korea School of Electrical and Computer Engineering Center for Smart Sensor System of Seoul (CS4) University of Seoul Seoul Republic of Korea Department of Advanced Materials Engineering Kyonggi University Suwon-si Republic of Korea Department of Energy Science Sungkyunkwan Institute of Energy Science and Technology (SIEST) Artificial Atom and Quantum Materials Center Sungkyunkwan University (SKKU) Suwon Republic of Korea

来源：评论

学校读者我要写书评

暂无评论

The growing memristor industry

引用

Nature 2025年第8059期640卷 613-622页

作者： Lanza, Mario Pazos, Sebastian Aguirre, Fernando Sebastian, Abu Le Gallo, Manuel Alam, Syed M. Ikegawa, Sumio Yang, J. Joshua Vianello, Elisa Chang, Meng-Fan Molas, Gabriel Naveh, Ishai Ielmini, Daniele Liu, Ming Roldan, Juan B. Department of Materials Science and Engineering National University of Singapore Singapore Singapore Institute for Functional Intelligent Materials National University of Singapore Singapore Singapore Centre for Advanced 2D Materials (CA2DM) National University of Singapore Singapore Singapore Materials Science and Engineering Program Physical Science and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal Saudi Arabia Intrinsic Semiconductor Technologies London United Kingdom IBM Research – Zurich Rüschlikon Switzerland Everspin Technologies Chandler AZ United States Department of Electrical and Computer Engineering University of Southern California Los Angeles CA United States CEA-Leti Université Grenoble Alpes Grenoble France Department of Electrical Engineering National Tsing Hua University Hsinchu Taiwan Weebit Nano Hod Hasharon Israel Dipartimento di Elettronica Informazione e Bioingegneria (DEIB) Politecnico di Milano and *** Milano Italy Key Laboratory of Microelectronic Devices and Integrated Technology Institute of Microelectronics Chinese Academy of Sciences Beijing China Departamento de Electrónica y Tecnología de Computadores Universidad de Granada Facultad de Ciencias Granada Spain

The semiconductor industry is experiencing an accelerated transformation to overcome the scaling limits of the transistor and to adapt to new requirements in terms of data storage and computation, especially driven by artificial intelligence applications and the Internet of Things. In this process, new materials, devices, integration strategies and system architectures are being developed and optimized. Among them, memristive devices and circuits—memristors are two-terminal memory devices that can also mimic some basic bioelectronic functions—offer a potential approach to create more compact, energy-efficient or better-performing systems. The memristor industry is growing quickly, raising abundant capital investment, creating new jobs and placing advanced products in the market. Here we analyse the status and prospects of the memristor industry, focusing on memristor-based products that are already commercially available, prototypes with a high technological readiness level that might affect the market in the near future, and discuss obstacles and pathways to their implementation. © Springer Nature Limited 2025.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimized MARL for Latency-Sensitive Collaborative Service Placement in Edge Computing

Optimized MARL for Latency-Sensitive Collaborative Service P...

引用

IEEE International Conference on Web Services (ICWS)

作者： Guoqiang Liu Xiaolong Xu Xiyuan Xu Xinyue Ji Lianyong Qi Xuyun Zhang School of Software Nanjing University of Information Science and Technology Nanjing China Jiangsu Province Engineering Research Center of Advanced Computing and Intelligent Services Nanjing University of Information Science and Technology Nanjing China College of Computer Science and Technology China University of Petroleum (East China) Qingdao China School of Computing Macquarie University Sydney Australia

ISBN: (数字)9798350368550

ISBN: (纸本)9798350368567

By distributing computing and storage resources to edge servers (ESs), edge computing enables service execution closer to requests, alleviating high latency caused by long-distance data transmission. The communication between ESs facilitates collaborative service placement (CSP) on multiple ESs, leading to latency reduction and thereby improving the quality of service. However, the discrepancies in service request distributions among ESs pose challenge to effective CSP, while limited prior knowledge further increases the difficulty in policy formation. Additionally, the delayed awareness of placement strategies among other ESs exacerbates the influence of non-Markovian nature. To overcome above challenges, a leader-follower based multi-agent reinforcement learning for CSP scheme, named LFMCSP, is proposed in this paper. Specifically, a CSP model is formulated, with ESs abstracted as intelligent agents within it. Then, the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm is utilized to explore potential patterns in complex requests by experience sharing. To achieve transparency of global states for all agents, the leader-follower architecture is integrated into MADDPG. Through rigorous experiments and comparisons with various baseline schemes, LFMCSP demonstrates effectiveness in reducing service execution delays.

关键词： Collaboration computer architecture Quality of service Reinforcement learning Space exploration Service-oriented architecture Delays Servers Intelligent agents Edge computing

来源：评论

学校读者我要写书评

暂无评论

CroPrompt: Cross-task Interactive Prompting for Zero-shot Spoken Language Understanding

CroPrompt: Cross-task Interactive Prompting for Zero-shot Sp...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Qin, Libo Wei, Fuxuan Chen, Qiguang Zhou, Jingxuan Huang, Shijue Si, Jiasheng Lu, Wenpeng Che, Wanxiang School of Computer Science and Engineering Central South University China Key Laboratory of Data Intelligence and Advanced Computing in Provincial Universities Soochow University China Research Center for Social Computing and Information Retrieval Harbin Institute of Technology China Harbin Institute of Technology Shenzhen China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology Shandong Academy of Sciences China

ISBN: (纸本)9798350368741

Slot filling and intent detection are two highly correlated tasks in spoken language understanding (SLU). Recent SLU research attempts to explore zero-shot prompting techniques in large language models to alleviate the data scarcity problem. Nevertheless, the existing prompting work ignores the cross-task interaction information for SLU, which leads to sub-optimal performance. To solve this problem, we present the pioneering work of Cross-task Interactive Prompting (CroPrompt) for SLU, which enables the model to interactively leverage the information exchange across the correlated tasks in SLU. Additionally, we further introduce a multi-task self-consistency mechanism to mitigate the error propagation caused by the intent information injection. We conduct extensive experiments on the standard SLU benchmark and the results reveal that CroPrompt consistently outperforms the existing prompting approaches. In addition, the multi-task self-consistency mechanism can effectively ease the error propagation issue, thereby enhancing the performance. We hope this work can inspire more research on cross-task prompting for SLU. © 2025 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Influence of Microstructure on the Magnetic Properties of Li-Cu-Mg-Zn Ferrites: Role of Bi2O3 Addition

SSRN

引用

SSRN 2024年

作者： Ahammed, Faruque Khan, M.N.I. Ullah, Muhammad Samir Badhan, M.A.H. Sajjad, Redwan N. Jamil, A.T.M. Kaosar Department of Physics Dhaka University of Engineering and Technology Gazipur1707 Bangladesh Materials Science Division Atomic Energy Center Dhaka1000 Bangladesh Department of Physics Bangladesh University of Engineering and Technology Dhaka1000 Bangladesh Bose Center for Advanced Study and Research in Natural Science University of Dhaka Dhaka1000 Bangladesh Department of Nanomaterials and Ceramic Engineering Bangladesh University of Engineering and Technology Dhaka1000 Bangladesh

Influence of Bi2O3 addition on the microstructure and magnetic properties of Li-Cu-Mg-Zn ferrites having the compositions Li0.25Cu0.10Mg0.10Zn0.30Fe2.25O4 + xBi2O3 (where x = 0.0, 0.3, 0.4, 0.6 and 0.8 wt %) have been reported in this study The structural property has been studied with the x-ray diffraction technique, which reveals that all the samples have shown the cubic spinel phase without any impurity peak. A microstructural analysis demonstrates that the grain growth of the samples is influenced by the amount of Bi2O3 addition and the average grain size increases from 0.84 (for x= 0.0 wt %) to 2.74 µm (for x = 0.6 wt %). The increase of the grain size could be attributed to the densification of sample due to the role of Bi2O3 as the sintering aid. The magnetic hysteresis measurement shows that the saturation magnetization increases from 72.1 (for x= 0.0 wt %) to 77.6 emu/g (for x = 0.6 wt % ). However, it deteriorated at x = 0.8 wt %, which may be ascribed to the dilution effect. The complex magnetic permeability measurement shows an enhancement of the initial permeability as the content of Bi2O3 increases from x = 0.0 to x = 0.6 wt %. It is inferred that a correlation has been found between the grain growth and the magnetic properties of the investigated samples. Fourier transforms infrared absorption reveals that the frequency band appears in the high frequency (539-555) range which can be attributed to the stretching vibrations at the tetrahedral site. The band appearing in the low frequency (359-370) range is for the octahedral site, which is related to bending vibration. The elastic constants such as bulk modulus, Young’s modulus, rigidity modulus, Poisson’s ratio and Pugh’s ratio have been calculated for all the studied samples. It shows that all synthesized samples are in ductile nature. © 2024, The Authors. All rights reserved.

关键词： Bismuth compounds

来源：评论

学校读者我要写书评

暂无评论

GRAS transcription factors regulate cell division planes in moss overriding the default rule (vol 120, e2210632120, 2023)

引用

PROCEEDINGS OF THE NATIONAL ACADEMY OF scienceS OF THE UNITED STATES OF AMERICA 2023年第10期120卷 e2210632120-e2210632120页

作者： Ishikawa, Masaki Fujiwara, Ayaka Kosetsu, Ken Horiuchi, Yuta Kamamoto, Naoya Umakawa, Naoyuki Tamada, Yosuke Zhang, Liechi Matsushita, Katsuyoshi Palfalvi, Gergo Nishiyama, Tomoaki Kitasaki, Sota Masuda, Yuri Shiroza, Yoshiki Kitagawa, Munenori Nakamura, Toru Cui, Hongchang Hiwatashi, Yuji Kabeya, Yukiko Shigenobu, Shuji Aoyama, Tsuyoshi Kato, Kagayaki Murata, Takashi Fujimoto, Koichi Benfey, Philip N. Hasebe, Mitsuyasu Kofuji, Rumiko Division of Evolutionary Biology National Institute for Basic Biology Okazaki 444-8585 Japan Department of Basic Biology The Graduate School for Advanced Studies (SOKENDAI) Okazaki 444-8585 Japan Graduate School of Natural Science and Technology Kanazawa University Kanazawa 920-1192 Japan Department of Biological Sciences Graduate School of Science Osaka University Toyonaka 560-0043 Japan School of Engineering Utsunomiya University Utsunomiya 321-8585 Japan Division of Integrated Omics Research Research Center for Experimental Modeling of Human Disease Kanazawa University Kanazawa 920-0934 Japan Department of Biology Kanazawa University Kanazawa 920-1192 Japan Present Address: National Key Laboratory for Germplasm Innovation and Utilization for Fruit and Vegetable Horticultural Crops Huazhong Agricultural University Wuhan 430070 China. Department of Biology Duke University Durham NC 27516 HHMI Duke University Durham NC 27516 Department of Biological Science Florida State University Tallahassee FL 32306-4295 School of Food Industrial Sciences Miyagi University Sendai 982-0215 Japan Present address: Live Imaging Center Institute of Transformative Bio-Molecules Nagoya University Nagoya 466-8601 Japan Bioimage Informatics Group Exploratory Research Center on Life and Living Systems (ExCELLS) National Institutes of Natural Sciences Okazaki 444-8585 Japan Interdisciplinary Research Unit National Institute for Basic Biology Okazaki 444-8585 Japan Department of Applied Bioscience Kanagawa Institute of Technology Atsugi 243-0292 Japan Faculty of Biological Science and Technology Institute of Science and Engineering Kanazawa University Kanazawa 920-1192 Japan

Plant cells are surrounded by a cell wall and do not migrate, which makes the regulation of cell division orientation crucial for development. Regulatory mechanisms controlling cell division orientation may have contributed to the evolution of body organization in land plants. The GRAS family of transcription factors was transferred horizontally from soil bacteria to an algal common ancestor of land plants. SHORTROOT (SHR) and SCARECROW (SCR) genes in this family regulate formative periclinal cell divisions in the roots of flowering plants, but their roles in nonflowering plants and their evolution have not been studied in relation to body organization. Here, we show that SHR cell autonomously inhibits formative periclinal cell divisions indispensable for leaf vein formation in the moss Physcomitrium patens, and SHR expression is positively and negatively regulated by SCR and the GRAS member LATERAL SUPPRESSOR, respectively. While precursor cells of a leaf vein lacking SHR usually follow the geometry rule of dividing along the division plane with the minimum surface area, SHR overrides this rule and forces cells to divide nonpericlinally. Together, these results imply that these bacterially derived GRAS transcription factors were involved in the establishment of the genetic regulatory networks modulating cell division orientation in the common ancestor of land plants and were later adapted to function in flowering plant and moss lineages for their specific body organizations.

关键词： GRAS TFs geometry rule cell division orientation horizontal gene transfer

来源：评论

学校读者我要写书评

暂无评论

Unveiling interatomic distances influencing the reaction coordinates in alanine dipeptide isomerization: An explainable deep learning approach

arXiv

引用

arXiv 2024年

作者： Okada, Kazushi Kikutsuji, Takuma Okazaki, Kei-Ichi Mori, Toshifumi Kim, Kang Matubayasi, Nobuyuki Division of Chemical Engineering Department of Materials Engineering Science Graduate School of Engineering Science Osaka University Osaka Toyonaka560-8531 Japan Research Center for Computational Science Institute for Molecular Science Aichi Okazaki444-8585 Japan Graduate Institute for Advanced Studies SOKENDAI Aichi Okazaki444-8585 Japan Institute for Materials Chemistry and Engineering Kyushu University Fukuoka Kasuga816-8580 Japan Interdisciplinary Graduate School of Engineering Sciences Kyushu University Fukuoka Kasuga816-8580 Japan

The present work shows that the free energy landscape associated with alanine dipeptide isomerization can be effectively represented by specific interatomic distances without explicit reference to dihedral angles. Conventionally, two stable states of alanine dipeptide in vacuum, i.e., C7eq (β-sheet structure) and C7ax (left handed α-helix structure), have been primarily characterized using the main chain dihedral angles, φ (C-N-Cα-C) and ψ (N-Cα-C-N). However, our recent deep learning combined with "Explainable AI" (XAI) framework has shown that the transition state can be adequately captured by a free energy landscape using φ and θ (O-C-N-Cα) [T. Kikutsuji, et al. J. Chem. Phys. 156, 154108 (2022)]. In perspective of extending these insights to other collective variables, a more detailed characterization of transition state is required. In this work, we employ the interatomic distances and bond angles as input variables for deep learning, rather than the conventional and more elaborate dihedral angles. Our approach utilizes deep learning to investigate whether changes in the main chain dihedral angle can be expressed in terms of interatomic distances and bond angles. Furthermore, by incorporating XAI into our predictive analysis, we quantified the importance of each input variable and succeeded in clarifying the specific interatomic distance that affects the transition state. The results indicate that constructing a free energy landscape based on using the identified interatomic distance can clearly distinguish between the two stable states and provide a comprehensive explanation for the energy barrier crossing. Copyright © 2024, The Authors. All rights reserved.

关键词： Isomerization

来源：评论

学校读者我要写书评

暂无评论

EC2Seq2Sql: Patient-Trial Matching with LLM Agents

SSRN

引用

SSRN 2025年

作者： Yang, Liu Han, Yongzhong Liu, Liang Jiang, Xiaoyan Li, Ying Jihan, Huang Su, Qianmin School of Electronic and Electrical Engineering Shanghai University of Engineering Science Shanghai201620 China Clinical Research Unit Institute of Clinical Science Zhongshan Hospital Fudan University Shanghai China Department of Hepatology Longhua Hospital Shanghai University of Traditional Chinese Medicine Shanghai China Center for Drug Clinical Research Shanghai University of Traditional Chinese Medicine Shanghai China Leiden Institute of Advanced Computer Science Leiden University Leiden Netherlands

Objective: The success of clinical trials hinges upon the timely identification of patients who satisfy the stipulated eligibility criteria. However, eligibility criteria are frequently articulated in natural language, and their complexity and flexibility render traditional manual screening methods not only inefficient but also susceptible to errors. Nevertheless, eligibility criteria are commonly articulated in natural language, and their complexity and flexibility render traditional manual screening methods not only inefficient but also prone to errors. To address this challenge, we propose the EC2Seq2Sql method, which is designed to automatically translate complex eligibility criteria into SQL queries, thereby facilitating efficient and accurate patient screening. Materials and Methods: EC2Seq2Sql consists of two stages. In the first stage, employing the BART model to perform semantic parsing on the natural language text of clinical trial eligibility criteria, converting the complex text into lightweight and structured pattern sequences. In the second stage, by employing an agent to handle these lightweight structured sequences, the model is further guided to transform the structured sequences into SQL statements through the integration of system-designed and human-curated prompts. Finally, the generated SQL queries can be applied to the EHR database to identify patients who meet the eligibility criteria. This approach also offers valuable insights into the future structuring of clinical trial eligibility criteria and the development of systems that align these criteria with EHR data. Results: The experimental results demonstrate that the BART model achieved scores of 0.8105 and 0.8427 on the ROUGE and BLEU evaluation metrics, respectively, significantly outperforming the comparison models, including T5-base, T5-small, and GPT-2. During the SQL generation process, the agent, guided by prompt engineering, transforms the lightweight and structured information extra

关键词： Semantics

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：