检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2021年第4期2卷 372-380页

作者： Yang, Jianfei Zeng, Zhaoyang Wang, Kai Zou, Han Xie, Lihua The School of Electrical and Electronics Engineering Nanyang Technological University Singapore639798 Singapore The School of Data and Computer Science Sun Yat-sen University Guangzhou510006 China The Institutes of Data Science School of Computing National University of Singapore Singapore119077 Singapore The Department of Electrical Engineering and Computer Sciences University of California BerkeleyCA94720 United States

The recyclability of domestic waste plays a crucial role in the modern society, which helps reduce multiple types of pollution and brings economic effect. To achieve this goal, garbage classification is one of the most important steps during the recycling process. Prevailing deep learning techniques empower high-performance visual recognition models and can benefit the automation of garbage classification task. Nevertheless, there exist three challenges when directly leveraging deep recognition models for this task, referring to lack of sufficient data, high cost of category increment, and noisy data quality. In this article, we present a novel incremental learning framework, GarbageNet, to address the aforementioned challenges. First, weakly-supervised transfer learning guarantees the capacity of feature extractor. Second, for new categories of garbages, GarbageNet embeds them as anchors for reference and classifies the test samples by finding their nearest neighbors in the latent space. Third, an attentive mixup of training data is utilized for suppressing the negative effect of mislabeled data. We evaluate our method on real-world datasets, and the empirical results demonstrate that GarbageNet achieves the state-of-the-art performance with regard to accuracy, robustness, and extendability. The proposed method won the first place in the HUAWEI Cloud Garbage Classification Challenge in 2019. Impact Statement-This article contributes to a vision-based garbage recognition system for the recyclability of domestic waste. To the best of our knowledge, it is the first article that explores a realistic vision-based solution for the garbage recognition with a real-world dataset and a comprehensive benchmark on current state-of-the-art visual recognition models. The proposed method addresses several challenges and achieves state-of-the-art performance. We believe that this interdisciplinary research contributes to the AI for the environment, which helps promote environmenta

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

High-Performance Magnetic-core Coils for Targeted Rodent Brain Stimulations

引用

Biomedical engineering Frontiers 2022年第1期3卷 82-92页

作者： Hedyeh Bagherzadeh Qinglei Meng Hanbing Lu Elliott Hong Yihong Yang Fow-Sen Choa Department of Computer Science and Electrical Engineering University of MarylandBaltimore CountyBaltimoreMD 21250USA Neuroimaging Research Branch National Institute on Drug AbuseNational Institutes of HealthBaltimoreMD 21224USA Maryland Psychiatric Research Center Department of PsychiatryUniversity of Maryland School of MedicineBaltimoreMD 21201USA

Objective and Impact *** is a need to develop rodent coils capable of targeted brain stimulation for treating neuropsychiatric disorders and understanding brain *** describe a novel rodent coil design to improve the focality for targeted stimulations in small rodent *** magnetic stimulation(TMS)is becoming increasingly important for treating neuropsychiatric disorders and understanding brain *** studies permit invasive manipulations and are essential for the mechanistic understanding of TMS effects and explorations of therapeutic outcomes in disease ***,existing TMS tools lack focality for targeted ***,there has been limited fundamental research on developing coils capable of focal stimulation at deep brain regions on small animals like *** this study,ferromagnetic cores are added to a novel angle-tuned coil design to enhance the coil performance regarding penetration depth and *** simulations and experimental electric field measurements were conducted to optimize the coil *** proposed coil system demonstrated a significantly smaller stimulation spot size and enhanced electric field decay rate in comparison to existing *** the ferromagnetic core reduces the energy requirements up to 60%for rodent brain *** simulated results are validated with experimental measurements and demonstration of suprathreshold rodent limb excitation through targeted motor cortex *** newly developed coils are suitable tools for focal stimulations of the rodent brain due to their smaller stimulation spot size and improved electric field decay rate.

关键词： stimulation manipulation becoming

来源：评论

学校读者我要写书评

暂无评论

Lung Cancer Detection: A Machine Learning Approach for Early Diagnosis

Lung Cancer Detection: A Machine Learning Approach for Early...

引用

International conference of Electronics, Communication and Aerospace Technology (ICECA)

作者： Praveen Kumar Joshi Rahul Prakash Devendra Singh Saurabh Dhanik Abhishek Tamta Vaibhav Kumar Sharma School of Computing Department Graphic Era Hill University Bhimtal India Department of Electronics Engineering National Institutes of Technology Srinagar India Department of Computer Science and Engineering Graphic Era Hill University Bhimtal India

ISBN: (数字)9798350367904

ISBN: (纸本)9798350367911

Lung cancer poses a significant health challenge, with early detection being crucial for better outcomes. Traditional diagnostic methods have limitations, leading to missed diagnoses. Machine learning offers promise in revolutionizing disease detection by leveraging data and advanced algorithms. This paper explores using machine learning for early lung cancer detection. Sophisticated algorithms enable accurate diagnostic systems, improving efficiency and scalability. Challenges like data quality and interpretability also need to be addressed. This study evaluates machine learning algorithms on real datasets to assess their effectiveness in clinical practice, contributing to the field of healthcare applications. We have found highest accuracy (96.77%), precision (98.33%), recall (98.33%) and F1-score (98.33%) in the Random Forest classifier.

关键词： Training Accuracy Machine learning algorithms Scalability Neural networks Lung cancer Nearest neighbor methods Boosting Reliability Random forests

来源：评论

学校读者我要写书评

暂无评论

Topological Heart Rate Variability Dynamics Analysis toward Sleep Apnea Detection with Persistent Shannon Entropy

Topological Heart Rate Variability Dynamics Analysis toward ...

引用

2022 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2022

作者： Zhao, Rui-Qi Ren, Xu-Chao Liang, Duan Liu, Guan-Zheng Li, Ying-Tian Jia, Zhen-Hua Yan, Yan Department of Computer Science North China Institute of Aerospace Engineering 065000 China Xi'an Shiyou University 710065 China Department of Biomedical Engineering Sun Yat-sen University 84112828 China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences 518055 China

ISBN: (数字)9781665469838

ISBN: (纸本)9781665469838

Sleep is a necessary process to maintain the normal physiological function of the human body and an important guarantee to improve people's quality of life. Obstructive sleep apnea (OSA) is a common sleep disorder seriously affecting human healthcare, which is also considered to be a potential risk factor for cardiovascular disease. This work investigates sleep state monitoring and OSA recognition from the heart rate variability dynamics. By investigating the topological properties of the state point clouds in the reconstructed phase space, the nonlinear dynamics pattern is well distinguished when the sleeping state changes. We proposed a Shannon entropy analysis and feature learning framework developed with the topological summaries, which shows good classification ability in the OSA detection experiments. The proposed approach is a promising solution for the clinical use of sleep state monitoring in real-Time computing occasions. © 2022 IEEE.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

RoboFold: A platform for Protein-folding Inspired Robot Swarms ∗ 5

RoboFold: A platform for Protein-folding Inspired Robot Swar...

引用

5th World Robot Conference Symposium on Advanced Robotics and Automation, WRC SARA 2023

作者： Zhang, Feng Gu, Yuping Yuan, Shuai Yang, Yongliang Shenyang Jianzhu University School of Electrical and Control Engineering Liaoning Shenyang110168 China Shenyang Institute of Automation Chinese Academy of Sciences State Key Laboratory of Robotics Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Liaoning Shenyang110016 China Shenyang Jianzhu University School of Computer Science and Engineering School of Electrical and Control Engineering Liaoning Shenyang110168 China

ISBN: (纸本)9798350307320

Natural swarms have inspired various controlling algorithms for swarm robotics, while few of them were programmed in a similar way as the natural swarms. Defining a reliable programming method is still a daunting challenge in swarm robotics. In nature, the information of 3D protein structure is programmed in the sequence of amino acids of the protein. To mimic the programming method of protein folding, we present a platform for investigating protein-folding inspired programming method for robot swarms. This platform includes three parts: a vibration machine, protein-like robot sequences, and recording devices. The preliminary results presented here demonstrated the effectiveness of this platform and the feasibility of protein-folding inspired programming method for robot swarms. © 2023 IEEE.

关键词： Protein folding

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Logic in computer Technology: Applications and Advancements

Fuzzy Logic in Computer Technology: Applications and Advance...

引用

Pervasive Computing and Social Networking (ICPCSN), International Conference on

作者： Shashank Pareek Hemant Gupta Jaspreet Kaur Raman Kumar Jasgurpreet Singh Chohan Department of Computer Science and Engineering Chandigarh University Mohali India Department of Electrical Engineering GLA University Mathura India Computer Science and Engineering Department Gulzar Group of Institutes Khanna India Department of Mechanical Engineering Chandigarh University Mohali India University Centre for Research and Development Chandigarh University Mohali India

The development of Fuzzy Logic has had a profound impact on the field of computing. A crucial part of any decision-making process is the use of this mathematical method for dealing with uncertainty and imprecision. In this article, it will go over what Fuzzy Logic is, how it may be used in computing, and what recent developments have been achieved in the field. The strengths and weaknesses of using Fuzzy Logic in IT are also discussed. The introduction of Fuzzy Logic into the realm of computer science was a game-changer, since it provided a robust mathematical strategy for addressing uncertainty and imprecision in decision-making. This article introduces readers to Fuzzy Logic by discussing its background, basic ideas, and potential uses in the field of information technology. Artificial intelligence, control systems, decision-making, data analysis, and image processing are just some of the many areas where Fuzzy Logic has been put to use. In addition, this article discusses contemporary developments in Fuzzy Logic, such as those in machine learning, control systems, and robotics. Although this study extols Fuzzy Logic's numerous benefits, it also addresses the method's drawbacks. Workers in the IT industry would do well to familiarize themselves with the merits and drawbacks of Fuzzy Logic, as this knowledge may inform the development of superior products. This study's overarching goal is to introduce readers to Fuzzy Logic in the context of computer technology, including its advantages and disadvantages. Fuzzy logic has been more useful in many areas of computer science and technology. Used in areas such as control systems, image processing, robotics, and decision making, fuzzy logic allows for the processing of imprecise or uncertain input. This study gives a thorough introduction to fuzzy logic in computer technology, including its history, current developments, and potential future uses. The first section of the study provides a foundational understanding of fu

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Power Electronics and Control Techniques for Renewable Energy Integration in Smart Grids

A Comparative Study of Power Electronics and Control Techniq...

引用

Pervasive Computing and Social Networking (ICPCSN), International Conference on

作者： Shashank Pareek Yogendra Kumar Harpreet Kaur Raman Kumar Jasgurpreet Singh Chohan Department of Computer Science and Engineering Chandigarh University Mohali India Department of Electrical Engineering GLA University Mathura India Computer Science and Engineering Department Gulzar Group of Institutes Khanna India Department of Mechanical Engineering Chandigarh University Mohali India University Centre for Research and Development Chandigarh University Mohali India

The development of smart grid technology for more effective and sustainable energy management has been prompted by the growing use of renewable energy sources like solar and wind power. In order to integrate renewable energy sources into the grid, power electronics and control approaches are essential. The purpose of this study is to examine the pros and cons of the various power electronics and control approaches now in use for integrating renewable energy sources into smart grids. The development of smart grid technology for more effective and sustainable energy management has been facilitated by the use of renewable energy sources like solar and wind power. When it comes to incorporating renewable energy sources into the grid, power electronics and control approaches play a crucial role. This article provides a comprehensive analysis of the literature on the topic of renewable energy integration in smart grids, with a particular focus on power electronics and control strategies. The study is based on a review of relevant literature and an analysis of the benefits and drawbacks of each method. Efficiency, dependability, cost-effectiveness, scalability, and compatibility with various renewable energy sources are some of the characteristics included in the comparison study. The research shows that each method has advantages and disadvantages, and that the choice of method is context-specific. The work has significant significance for the field of electrical and computer engineering and aids in the development of more efficient and sustainable energy management systems for the future smart grid.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Internet Security Impact on E-Banking Users

Internet Security Impact on E-Banking Users

引用

2022 Workshop on Emerging Technology Trends on the Smart Industry and the Internet of Things, TTSIIT 2022

作者： Hassan, Mohammed Khodayer Hassan, Ali Khodayer, Aymen Mohammed Khodayer, Omer Mohammed Al-Rafidan University Department of Computer Science Baghdad Iraq Institutes for post graduate studies Iraqi commission for Computers and Informatics Baghdad Iraq Al-Farhidai University Department of Communication Engineering Baghdad Iraq Polteckina University of Bucharest Department of Telecommunication Engineering Bucharest Romania

Information technology has been used widely in different sectors in daily task to fulfill Customers and organization’s needs. Banking business is one of the main trends that use information technology in wide range. Customers can deal with banks through Websites which E-banking or using a credit card at an ATM what it is called. One of the most important factors in the success of electronic banking services is security. A strong security system is critical for a safe banking system in order to prevent hacking of the client's banking account and any private information of the customers in the bank system's databases. Any of the tasks can only be performed by legal or authorized personnel. As a result, bank systems must ensure that their transactions run as they should, in a secure manner, and that no activities occur that could result in a loss to the bank organization and its clients or customers. Banking account hacking has resulted in millions of dollars in losses in the wild world due to security system vulnerabilities. That kind of paper discusses the attacks on the banking system, the importance of the robust security system and the security measures that have been taken to prevent a great lost to the financial institution. Recommendations have been made to prevent any intrusion in the future. This paper shows the security trends to word helping customer and banks in their works to get better performance in doing their jobs by using electronic banking system. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： authentication confidentiality E-banking systems intrusions of banking system

来源：评论

学校读者我要写书评

暂无评论

Locality-sensitive bucketing functions

arXiv

引用

arXiv 2022年

作者： Chen, Ke Shao, Mingfu Department of Computer Science and Engineering School of Electronic Engineering and Computer Science The Pennsylvania State University United States Huck Institutes of the Life Sciences The Pennsylvania State University United States

Many bioinformatics applications involve bucketing a set of sequences where each sequence is allowed to be assigned into multiple buckets. To achieve both high sensitivity and precision, bucketing methods are desired to assign similar sequences into the same buckets while assigning dissimilar sequences into distinct buckets. Existing k-mer-based bucketing methods have been efficient in processing sequencing data with low-error rate, but encounter much reduced sensitivity on data with high-error rate. Locality-sensitive hashing (LSH) schemes are able to mitigate this issue through tolerating the edits in similar sequences, but state-of-the-art methods still have large gap. Here we generalize the LSH function by allowing it to hash one sequence into multiple buckets. Formally, a bucketing function, which maps a sequence (of fixed length) into a subset of buckets, is defined to be (d1, d2)-sensitive if any two sequences within an edit distance of d1 are mapped into at least one shared bucket, and any two sequences with distance at least d2 are mapped into disjoint subsets of buckets. We construct LSB functions with a variety of values of (d1, d2) and analyze their efficiency with respect to the total number of buckets needed as well as the number of buckets that a specific sequence is mapped to. We also prove lower bounds of these two parameters in different settings and show that some of our constructed LSB functions are optimal. These results provide theoretical foundations for their practical use in analyzing sequencing data with high error rate while also providing insights for the hardness of designing ungapped LSH functions. Copyright © 2022, The Authors. All rights reserved.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

MiM: Mask in Mask Self-Supervised Pre-Training for 3D Medical Image Analysis

引用

IEEE Transactions on Medical Imaging 2025年

作者： Zhuang, Jiaxin Wu, Linshan Wang, Qiong Fei, Peng Vardhanabhuti, Varut Luo, Lin Chen, Hao Hong Kong University of Science and Technology Departments of Computer Science and Engineering Hong Kong Chinese Academy of Sciences Shenzhen Institutes of Advanced Technology China Huazhong University of Science and Technology School of Optical and Electronic Information Wuhan National Laboratory for Optoelectronics Wuhan430074 China The University of Hong Kong Department of Diagnostic Radiology Hong Kong Peking University College of Engineering Beijing China Hong Kong University of Science and Technology Department of Computer Science and Engineering Department of Chemical and Biological Engineering State Key Laboratory of Molecular Neuroscience Hong Kong HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute Futian Shenzhen China

The Vision Transformer (ViT) has demonstrated remarkable performance in Self-Supervised Learning (SSL) for 3D medical image analysis. Masked AutoEncoder (MAE) for feature pre-training can further unleash the potential of ViT on various medical vision tasks. However, due to large spatial sizes with much higher dimensions of 3D medical images, the lack of hierarchical design for MAE may hinder the performance of downstream tasks. In this paper, we propose a novel Mask in Mask (MiM) pre-training framework for 3D medical images, which aims to advance MAE by learning discriminative representation from hierarchical visual tokens across varying scales. We introduce multiple levels of granularity for masked inputs from the volume, which are then reconstructed simultaneously ranging at both fine and coarse levels. Additionally, a cross-level alignment mechanism is applied to adjacent level volumes to enforce anatomical similarity hierarchically. Furthermore, we adopt a hybrid backbone to enhance the hierarchical representation learning efficiently during the pre-training. MiM was pre-trained on a large scale of available 3D volumetric images, i.e., Computed Tomography (CT) images containing various body parts. Extensive experiments on twelve public datasets demonstrate the superiority of MiM over other SSL methods in organ/tumor segmentation and disease classification. We further scale up the MiM to large pre-training datasets with more than 10k volumes, showing that large-scale pre-training can further enhance the performance of downstream tasks. © 1982-2012 IEEE.

关键词： Image segmentation

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：