检索结果-内蒙古大学图书馆

High throughput analysis of rare nanoparticles with deep-enhanced sensitivity via unsupervised denoising

Nature Communications 2025年第1期16卷 1-14页

作者： Iwamoto, Yuichiro Salmon, Benjamin Yoshioka, Yusuke Kojima, Ryosuke Krull, Alexander Ota, Sadao Research Center for Advanced Science and Technology The University of Tokyo Meguro 4-6-1 Shibuya Tokyo Japan School of Computer Science University of Birmingham Birmingham United Kingdom Department of Molecular and Cellular Medicine Institute of Medical Science Tokyo Medical University Nishishinjuku 6-7-1 Shinjuku Tokyo Japan Graduate School of Medicine The University of Tokyo Hongo 7-3-1 Bunkyo Tokyo Japan

The large-scale multiparametric analysis of individual nanoparticles is increasingly vital in the diverse fields of biology, medicine, and materials science. However, the current methods struggle with the tradeoff between measurement scalability and sensitivity, especially when identifying rare nanoparticles in heterogeneous mixtures. By developing and combining an unsupervised deep learning-based denoising method and an optofluidic device tuned for nanoparticle detection, we realize a nanoparticle analyzer that simultaneously achieves high scalability, throughput, and sensitivity levels;we name this approach “Deep Nanometry” (DNM). DNM detects polystyrene beads with a detection of limit of 30 nm at a throughput of over 100,000 events/second. The sensitive and scalable DNM directly detects rare target extracellular vesicles (EVs) in non-purified serum, making up as little as 0.002% of the 1,214,392 total particles. Moreover, DNM accurately and sufficiently counts diagnostic marker EVs present in only 0.93% and 0.17% of particle detections in sera of colorectal cancer patients and healthy controls, demonstrating its potential application to the early detection of colorectal cancer. © The Author(s) 2025.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adversarial Medical Image with Hierarchical Feature Hiding

arXiv

引用

arXiv 2023年

作者： Yao, Qingsong He, Zecheng Li, Yuexiang Lin, Yi Ma, Kai Zheng, Yefeng Zhou, S. Kevin School of Biomedical Engineering Suzhou Institute for Advanced Research University of Science and Technology of China Institute of Computing Technology Chinese Academy of Sciences China Institute of Computing Technology Chinese Academy of Science China Jarvis Research Center Ten-cent YouTu Lab Shenzhen China Group Guangxi Key Laboratory for Genomic and Personalized Medicine Guangxi Medical University Nanning China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Meta Reality Labs United States

Deep learning based methods for medical images can be easily compromised by adversarial examples (AEs), posing a great security flaw in clinical decision-making. It has been discovered that conventional adversarial attacks like PGD which optimize the classification logits, are easy to distinguish in the feature space, resulting in accurate reactive defenses. To better understand this phenomenon and reassess the reliability of the reactive defenses for medical AEs, we thoroughly investigate the characteristic of conventional medical AEs. Specifically, we first theoretically prove that conventional adversarial attacks change the outputs by continuously optimizing vulnerable features in a fixed direction, thereby leading to outlier representations in the feature space. Then, a stress test is conducted to reveal the vulnerability of medical images, by comparing with natural images. Interestingly, this vulnerability is a double-edged sword, which can be exploited to hide AEs. We then propose a simple-yet-effective hierarchical feature constraint (HFC), a novel add-on to conventional white-box attacks, which assists to hide the adversarial feature in the target feature distribution. The proposed method is evaluated on three medical datasets, both 2D and 3D, with different modalities. The experimental results demonstrate the superiority of HFC, i.e., it bypasses an array of state-of-the-art adversarial medical AE detectors more efficiently than competing adaptive attacks1, which reveals the deficiencies of medical reactive defense and allows to develop more robust defenses in future. © 2023, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Goal-Aware RSS for Complex Scenarios via Program Logic

Goal-Aware RSS for Complex Scenarios via Program Logic

引用

IEEE Symposium on Intelligent Vehicle

作者： Ichiro Hasuo Clovis Eberhart James Haydon Jérémy Dubut Rose Bohrer Tsutomu Kobayashi Sasinee Pruekprasert Xiao-Yi Zhang Erik André Pallas Akihisa Yamada Kohei Suenaga Fuyuki Ishikawa Kenji Kamijo Yoshiyuki Shinya Takamasa Suetomi National Institute of Informatics (NII) Tokyo Japan SOKENDAI (The Graduate University for Advanced Studies) Japan Japanese-French Laboratory for Informatics (IRL 3527) Tokyo Japan Dept. Computer Science Worcester Polytechnic Institute Worcester MA USA Inst. Software & Systems Engineering University of Augsburg Augsburg Germany Cyber Physical Security Research Center AIST Tokyo Japan Graduate School of Informatics Kyoto University Kyoto Japan Mazda Motor Corporation Fuchu Japan

ISBN: (数字)9798350348811

ISBN: (纸本)9798350348828

We introduce a goal-aware extension of responsibility-sensitive safety (RSS), a recent methodology for rule-based safety guarantee for automated driving systems (ADS). Making RSS rules guarantee goal achievement—in addition to collision avoidance as in the original RSS—requires complex planning over long sequences of manoeuvres. To deal with the complexity, we introduce a compositional reasoning framework based on program logic, in which one can systematically develop RSS rules for smaller subscenarios and combine them to obtain RSS rules for bigger scenarios. As the basis of the framework, we introduce a program logic dFHL that accommodates continuous dynamics and safety conditions. Our framework presents a dFHL-based workflow for deriving goal-aware RSS rules; we discuss its software support, too. We conducted experimental evaluation using RSS rules in a safety architecture. Its results show that goal-aware RSS is indeed effective in realising both collision avoidance and goal achievement.

关键词： Intelligent vehicles computer architecture Software Cognition Safety Planning Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Trust aware secure energy efficient hybrid protocol for MANET

Trust aware secure energy efficient hybrid protocol for MANE...

引用

Artificial Intelligence and Smart Communication (AISC), International Conference on

作者： Anuradha Jha V. Vivek Poonam Gupta Rutvij Joshi Prabhdeep Singh N.Ch.Sriman Narayana Iyengar GGSIP University University School of Law and Legal Studies USLLS Dwarka India Department of Computer Science and Engineering Faculty of Engineering and Technology JAIN (Deemed-to-be University) Bengaluru India Department of Management Sanskriti University Mathura India Department of ECE PIET Parul University Vadodara India Department of CSE Graphic Era Deemed to be University Dehradun India Department of Information Technology Sreenidhi Institute of Science and Technology Hyderabad India

Transmitters (MANETs) are particularly appropriate for uses like special outings, satellite communications in regions with no radio electric grid, crises and things in the environment, as well as diagnostic interventions for the armed forces. Despite the fact that MANETs have evolved into infrastructure-free, soul, and quickly moveable wireless technologies. Privacy may be the key IoT weak point due to the frameworks' flexibility and the constantly changing node mobility. Due to this, it is especially susceptible to numerous assaults, such as software modification, tunneling, and espionage. On MANET, security threats are more serious than problems with the quality of service (QoS). Invasion monitoring, which alters your system to identify further breach holes, is therefore the best way to protect MANET privacy. The ability to detect intrusions is essential for providing protection and acting as an extra layer of restrictions. The loss of the node's energy source might also affect the cellular station's capacity to send messages, which is solely dependent on system life. As a result, the protocol was created and this connection was chosen as the best, most dependable way to extend the MANETs for travel. It is challenging to provide secure and energy-efficient routing in this sort of network due to its dynamic topology and resource limitations. To address the problems of energy safety and security, we provide a hybrid technique of cat slapped solo algorithms (C-SSA), which selects the finest leaps in route advancement. This approach would enable confidence secure efficient energy traveling in MANETs. Fuzzy clustering is utilized initially, and number of clusters (CHs) are selected according to the importance of recent, implicit, and direct trust. Also discovered were nodes depending on the trust threshold value. Even the CHs participate in wireless multi-hop routing, and the best routes are selected here based on lag, throughput, and connection throughout this context

关键词： Wireless communication Privacy Protocols Quality of service Routing Ad hoc networks Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Development of Intelligent Power Quality Management in Renewable Energy System in Smart Grid using Deep Learning

Development of Intelligent Power Quality Management in Renew...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： P Rajendran Jarabala Ranga P. Venkata Prasad Balasubbareddy Mallala G. Senthilkumar Natrayan L Department of Management Studies Chinmaya Vishwa Vidyapeeth Deemed to be University Ernakulam Kerala India Department of Electrical and Electronics Engineering Ramachandra College of Engineering Eluru Andhra Pradesh India Department of Electrical and Electronics Engineering Chaitanya Bharathi Institute of Technology Hyderabad Telangana India Department of Computer Science and Engineering Panimalar Engineering College Chennai Tamil Nadu India Department of Mechanical Engineering Saveetha School of Engineering SIMATS Chennai Tamil Nadu India

ISBN: (数字)9798350359299

ISBN: (纸本)9798350359305

The present research addresses the crucial issues in intelligent power quality management inside smart grids by merging machine learning models with an Internet of Things (IoT) infrastructure. The research focuses on renewable energy sources, notably solar and wind, employing multiple sensors such as temperature, wind speed, and windmill rotation speed to obtain complete environmental data. A microcontroller records the sensor readings and related power production, generating a dataset of 20,223 entries over a month. Four machine learning models—the Recurrent Neural Network (RNN), Decision Tree (DT), Support Vector Machine (SVM), and Artificial Neural Network (ANN)—are evaluated on 20% of the dataset after being trained on 80% of it. Thesse trained ML model predicts the electricity that can be produced in future based on the information collected from the sensor. Also if the climatic condition is known then the electricity produced in future can be predicted in future. From the experimental result it is seen that the ANN emerges as the top-performing model with an accuracy of 93.5%, displaying its ability to predict electricity. SVM closely follows with 92.3%, while DT exhibits a balanced performance at 89.7%. The RNN, specialized in handling sequential data, achieves an accuracy of 86.22%. The findings underline the usefulness of the integrated system for forecasting electricity production based on real-time environmental conditions, supporting informed decision-making for smart grid stability. This work advances the field of intelligent power quality management and offers a roadmap for maximising the integration of renewable energy sources through the use of machine learning and Internet of Things technology. As the study seek for sustainable energy solutions, this research moves the sector ahead by giving practical insights for robust and efficient smart grid operations.

关键词： Support vector machines Temperature sensors Renewable energy sources Recurrent neural networks Electricity Power quality Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

Space-Air-Ground Integrated Multi-domain Network Resource Orchestration based on Virtual Network Architecture: a DRL Method

arXiv

引用

arXiv 2022年

作者： Zhang, Peiying Wang, Chao Kumar, Neeraj Liu, Lei Qingdao266580 China State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China Qingdao266580 China Department of Computer Science and Engineering Thapar Institute of Engineering and Technology Deemed to be University Patiala147004 India Department of Computer Science and Information Engineering Asia University Taichung41354 Taiwan School of Computer Science University of Petroleum and Energy Studies Dehradun248007 India State Key Laboratory of Integrated Services Networks Xidian University Xi’an710071 China

Traditional ground wireless communication networks cannot provide high-quality services for artificial intelligence (AI) applications such as intelligent transportation systems (ITS) due to deployment, coverage and capacity issues. The space-air-ground integrated network (SAGIN) has become a research focus in the industry. Compared with traditional wireless communication networks, SAGIN is more flexible and reliable, and it has wider coverage and higher quality of seamless connection. However, due to its inherent heterogeneity, time-varying and self-organizing characteristics, the deployment and use of SAGIN still faces huge challenges, among which the orchestration of heterogeneous resources is a key issue. Based on virtual network architecture and deep reinforcement learning (DRL), we model SAGIN’s heterogeneous resource orchestration as a multi-domain virtual network embedding (VNE) problem, and propose a SAGIN cross-domain VNE algorithm. We model the different network segments of SAGIN, and set the network attributes according to the actual situation of SAGIN and user needs. In DRL, the agent is acted by a five-layer policy network. We build a feature matrix based on network attributes extracted from SAGIN and use it as the agent training environment. Through training, the probability of each underlying node being embedded can be derived. In test phase, we complete the embedding process of virtual nodes and links in turn based on this probability. Finally, we verify the effectiveness of the algorithm from both training and testing. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

TraSeTR: Track-to-Segment Transformer with Contrastive Query for Instance-level Instrument Segmentation in Robotic Surgery

TraSeTR: Track-to-Segment Transformer with Contrastive Query...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Zixu Zhao Yueming Jin Pheng– Ann Heng Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Department of Comouter Science University College London UK Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Chinese Academy of Sciences

Surgical instrument segmentation - in general a pixel classification task - is fundamentally crucial for promoting cognitive intelligence in robot-assisted surgery (RAS). However, previous methods are struggling with discriminating instrument types and instances. To address above issues, we explore a mask classification paradigm that produces per-segment predictions. We propose TraSeTR, a novel Track-to-Segment Transformer that wisely exploits tracking cues to assist surgical instrument segmentation. TraSeTR jointly reasons about the instrument type, location, and identity with instance-level predictions i.e., a set of class-bbox-mask pairs, by decoding query embeddings. Specifically, we introduce the prior query that encoded with previous temporal knowledge, to transfer tracking signals to current instances via identity matching. A contrastive query learning strategy is further applied to reshape the query feature space, which greatly alleviates the tracking difficulty caused by large temporal variations. The effectiveness of our method is demonstrated with state-of-the-art instrument type segmentation results on three public datasets, including two RAS benchmarks from EndoVis Challenges and one cataract surgery dataset CaDIs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Investigating the Strength and Hardness of AL7075 Composite Reinforced with Natural Fibers

Investigating the Strength and Hardness of AL7075 Composite ...

引用

Computational Modelling, Simulation and Optimization (ICCMSO), International Conference on

作者： Dinesh Kumar Vineet Singla Ravinder Kundu Neha Arun Kumar Sunil Kumar Sharma Department of Mechanical Engineering M.D.U University Institute of Engineering and Technology Rohtak India Department of Computer Science and Engineering Jamia Hamdard University New Delhi India Department of automotive studies Skill faculty of engineering and technology shri vishwakarma skill university Palwal India Department of Green Technology shri vishwakarma skill university Palwal India

Stir casting is the easiest way to melt and combine reinforcement in metal matrix composites made from low-melting metals like aluminium. The stir cast process was used to make Aluminium 7075 hybrid composites by reinforcing sugarcane and bamboo leaf ash at 2%, 4%, 6%, and 8% by weight and retaining AL7075-T651 concentration. Tensile testing was performed on standard-sized samples using Universal Testing Machine UNITEK-94100. Results were tabulated and compared to pure AL7075-T651. The tensile test indicates that the reinforcing percentage enhances strength up to a point, then decreases. Rockwell hardness was used to compare hybrid composite hardness to pure AL7075-T651 alloy. The results showed that adding SLA+BLA reinforcement enhances the hardness of the manufactured AL7075-T651 composite compared to the base matrix alloy up to a certain extent, thereafter it decreases. The results were compared to pure AL7075-T651 alloy using graphical methods, showing that reinforcing improved mechanical properties.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Uncovering the influence of public awareness on dengue population dynamics: a mathematical model approach

引用

Boletín de la Sociedad Matemática Mexicana 2025年第2期31卷 1-31页

作者： Bitrus, Kefas Abdullah, Farah Aini Adewole, Matthew O. Andrawus, James Qureshi, Sania Soomro, Amanullah Yusuf, Abdullahi Department of Mathematics Federal University Lokoja Kogi Nigeria School of Mathematical Sciences Universiti Sains Malaysia (USM) Penang Malaysia Department of Computer Science and Mathematics Mountain Top University Prayer City Nigeria Department of Mathematics Federal University Dutse Jigawa Nigeria Department of Basic Sciences and Related Studies Mehran University of Engineering and Technology Jamshoro Pakistan Department of Mathematics Mathematics Research Center Near East University Nicosia Mersin 10 Turkey Department of Mathematics Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai India Department of Mathematics Firat University Elazig Turkey

An arbovirus belonging to the Flaviviridae family is the cause of the infectious disease called dengue fever. In this work, the human population is divided into eight compartments, which are $$(S_h)$$ indicates susceptible people, $$(E_h)$$ indicates dengue virus-exposed humans, Controlled humans $$(C_h)$$ are those who are aware of the dengue virus and how humans can get infected with it. People infected with the dengue virus are known as infectious humans $$(I_h)$$ , and they can spread the illness to others by being bitten by mosquitoes. Treated individuals $$(T_h)$$ these are humans that are undergoing treatment, Recovered individuals (R);These are individuals that are recovered from the disease, Susceptible vectors $$(S_v)$$ ;these are susceptible mosquitoes that can be contracted with virus by biting infected humans, Infected vectors $$(I_v)$$ these are infected mosquitoes that are capable of transmitting the virus to human by bite. Among the other things done: the boundedness of the model has been ascertained, and the threshold called reproduction number $${\mathcal {R}}_c$$ has been obtained using a new generation matrix. The existence of equilibria has been ascertained, which showed that the model consists of two equilibria, the disease-free equilibrium point (DFE) and endemic equilibrium point. Local stability of disease-free equilibrium has been ascertained, which showed that the DFE is locally asymptotically stable if $${\mathcal {R}}_c<1$$ and unstable otherwise. The global stability of disease-free equilibrium has been ascertained using the comparison theorem, the significance of this method is that is easier to access the global stability of disease-free equilibrium with it and it is faster. The global stability of the endemic equilibrium point has been ascertained using the non-linear Lyapunov function of the Go-Volterra type, the result shows that the endemic equilibrium point is globally asymptotically stable if $${\mathcal {R}}_c>1$$ , when

关键词：

来源：评论

学校读者我要写书评

暂无评论

Introducing Shape Prior Module in Diffusion Model for Medical Image Segmentation

arXiv

引用

arXiv 2023年

作者： Zhang, Zhiqing Fan, Guojia Liu, Tianyong Li, Nan Liu, Yuyang Liu, Ziyu Dong, Canwei Zhou, Shoujun Shenzhen Institute of Advanced Technology University of Chinese Academy of Sciences Shenzhen China Shenzhen China College Of Geosciences Northeast Petroleum University Shenzhen China Department of Computer Science City University of Hong Kong Shenzhen China Shenyang Institute of Automation University of Chinese Academy of Sciences Shenzhen China Faculty of Science and Engineering Chinese Academy of Sciences University of Nottingham Ningbo China Ningbo China

Medical image segmentation is critical for diagnosing and treating spinal disorders. However, the presence of high noise, ambiguity, and uncertainty makes this task highly challenging. Factors such as unclear anatomical boundaries, interclass similarities, and irrational annotations contribute to this challenge. Achieving both accurate and diverse segmentation templates is essential to support radiologists in clinical practice. In recent years, denoising diffusion probabilistic modeling (DDPM) has emerged as a prominent research topic in computer vision. It has demonstrated effectiveness in various vision tasks, including image deblurring, super-resolution, anomaly detection, and even semantic representation generation at the pixel level. Despite the robustness of existing diffusion models in visual generation tasks, they still struggle with discrete masks and their various effects. To address the need for accurate and diverse spine medical image segmentation templates, we propose an end-to-end framework called VerseDiff-UNet, which leverages the denoising diffusion probabilistic model (DDPM). Our approach integrates the diffusion model into a standard U-shaped architecture. At each step, we combine the noise-added image with the labeled mask to guide the diffusion direction accurately towards the target region. Furthermore, to capture specific anatomical a priori information in medical images, we incorporate a shape a priori module. This module efficiently extracts structural semantic information from the input spine images. We evaluate our method on a single dataset of spine images acquired through X-ray imaging. Our results demonstrate that VerseDiff-UNet significantly outperforms other state-of-the-art methods in terms of accuracy while preserving the natural features and variations of anatomy. The generality and validity of our proposed model are confirmed through extensive experiments. By enabling more precise segmentation of anatomical structures, our framewo

关键词： Anomaly detection

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：