检索结果-内蒙古大学图书馆

DFD-Net:lung cancer detection from denoised CT scan image using deep learning

Frontiers of Computer science 2021年第2期15卷 119-131页

作者： Worku J.SORI Jiang FENG Arero W.GODANA Shaohui LIU Demissie J.GELMECHA School of Electrical Engineering and Computing Department of Computer Science and EngineeringAdama Science and Technology UniversityAdama1888Ethiopia Faculty of Natural Computational Science Department of Mathematics Bule Hora UniversityBule HoraHagere Maryam144Ethiopia School of Computer Science and Technology Harbin Institute of TechnologyHarbin150001China Peng Cheng Laboratory Shenzhen518052China School of Electrical Engineering and Computing Department of Electronics and Communications EngineeringAdama Science and Technology UniversityAdama1888Ethiopia

The availability of pulmonary nodules in CT scan image of lung does not completely specify *** noise in an image and morphology of nodules,like shape and size has an implicit and complex association with cancer,and thus,a careful analysis should be mandatory on every suspected nodules and the combination of information of every *** this paper,we introduce a“denoising first”two-path convolutional neural network(DFD-Net)to address this *** introduced model is composed of denoising and detection part in an end to end ***,a residual learning denoising model(DR-Net)is employed to remove noise during the preprocessing ***,a two-path convolutional neural network which takes the denoised image by DR-Net as an input to detect lung cancer is *** two paths focus on the joint integration of local and global *** this end,each path employs different receptive field size which aids to model local and global *** further polish our model performance,in different way from the conventional feature concatenation approaches which directly concatenate two sets of features from different CNN layers,we introduce discriminant correlation analysis to concatenate more representative ***,we also propose a retraining technique that allows us to overcome difficulties associated to the image labels *** found that this type of model easily first reduce noise in an image,balances the receptive field size effect,affords more representative features,and easily adaptable to the inconsistency among nodule shape and *** intensive experimental results achieved competitive results.

关键词： medical image discriminant correlation analysis features fusion image detection denoising

来源：评论

学校读者我要写书评

暂无评论

Brain-inspired artificial intelligence research: A review

引用

science China(Technological sciences) 2024年第8期67卷 2282-2296页

作者： WANG GuoYin BAO HuaNan LIU Qun ZHOU TianGang WU Si HUANG TieJun YU ZhaoFei LU CeWu GONG YiHong ZHANG ZhaoXiang HE Sheng Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and TelecommunicationsChongqing 400065China Key Laboratory of Cyberspace Big Data Intelligent Security Chongqing University of Posts and TelecommunicationsChongqing 400065China College of Computer and Information Science Chongqing Normal UniversityChongqing 401331China State Key Laboratory of Brain and Cognitive Science Institute of BiophysicsChinese Academy of SciencesBeijing 100101China School of Psychological and Cognitive Sciences Peking UniversityBeijing 100871China State Key Laboratory of Multimedia Information Processing School of Computer SciencePeking UniversityBeijing 100871China Department of Computer Science School of ElectronicsInformation and Electrical EngineeringShanghai Jiao Tong UniversityShanghai 200240China Faculty of Electronic and Information Engineering Xi’an Jiaotong UniversityXi’an 710049China The Center for Research on Intelligent Perception and Computing Institute of AutomationChinese Academy of SciencesBeijing 100190China Institute of Biophysics Chinese Academy of SciencesBeijing 100101China

Artificial intelligence(AI) systems surpass certain human intelligence abilities in a statistical sense as a whole, but are not yet the true realization of these human intelligence abilities and behaviors. There are differences, and even contradictions, between the cognition and behavior of AI systems and humans. With the goal of achieving general AI, this study contains a review of the role of cognitive science in inspiring the development of the three mainstream academic branches of AI based on the three-layer framework proposed by David Marr, and the limitations of the current development of AI are explored and analyzed. The differences and inconsistencies between the cognition mechanisms of the human brain and the computation mechanisms of AI systems are analyzed. They are found to be the cause of the differences and contradictions between the cognition and behavior of AI systems and humans. Additionally, eight important research directions and their scientific issues that need to focus on braininspired AI research are proposed: highly imitated bionic information processing, a large-scale deep learning model that balances structure and function, multi-granularity joint problem solving bidirectionally driven by data and knowledge, AI models that simulate specific brain structures, a collaborative processing mechanism with the physical separation of perceptual processing and interpretive analysis, embodied intelligence that integrates the brain cognitive mechanism and AI computation mechanisms,intelligence simulation from individual intelligence to group intelligence(social intelligence), and AI-assisted brain cognitive intelligence.

关键词： artificial intelligence cognitive science brain science intelligence science large language model

来源：评论

学校读者我要写书评

暂无评论

Robust Sensor Fusion Algorithms for IoT

Robust Sensor Fusion Algorithms for IoT

引用

2024 International Conference on Innovative computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Subramanian, Sakthitharan Lokeshwari, Gandrakoti Jagadeesan, S. Leela, S. Pratheep, V.G. Venkatasudhahar, Murugesan School of Computing Faculty of Engineering and Technology Srm Institute of Science and Technology Department of Computational Intelligence Tamil Nadu Chennai603203 India Geethanjali College of Engineering and Technology Department of Cybersecurity Telangana Hyderabad501301 India Department of Computer Science and Engineering Tamil Nadu Erode638052 India Sri Eshwar College of Engineering Department of Computer Science and Business Systems Tamil Nadu Coimbatore641202 India Kongu Engineering College Department of Mechatronics Engineering Tamil Nadu Perundurai638060 India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Mechanical Engineering Tamil Nadu Chennai600062 India

ISBN: (纸本)9798331543617

Sensor fusion is a critical component of the IoT ecosystem, as it combines a variety of data streams from multiple sensors to enhance the accuracy, reliability, and real-time decision-making. This research concentrates on the development of robust sensor fusion algorithms that are capable of effectively managing the heterogeneity, noise, and uncertainty that are inherent in data from Internet of Things (IoT) sensors. Our primary focus is on the ability of these algorithmic methodologies to manage data from multi-modal sensors. We investigate algorithms that are based on deep learning, Bayesian inference, and Kalman filtering. The proposed solutions aim to improve the performance of systems in sectors that are influenced by the Internet of Things (IoT), including healthcare, smart cities, industrial automation, and autonomous cars. This investigation investigates the scalability, energy efficiency, and computational burden of the Internet of Things (IoT) in the context of limited resources. Through simulations and practical applications, we demonstrate the enhancement of data precision, defect tolerance, and overall system dependability by these robust sensor fusion techniques. © 2024 IEEE.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Automatic Title Generation with Attention-Based LSTM 3rd

Automatic Title Generation with Attention-Based LSTM

引用

3rd International Conference on Information Technology, InCITe 2023

作者： Dhilsath Fathima, M. Seeni Syed Raviyathu Ammal, M. Singh, Prashant Kumar Shome, Sachi Kharsyienlieh, Manbha Hariharan, R. Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Tamil Nadu Kattankulathur India Department of Information Technology Mohamed Sathak Engineering College Tamil Nadu Kilakarai India Department of Information Technology Veltech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India

ISBN: (纸本)9789819959969

The objective of this article is to develop a generalised architecture that can generate headings for any type of document, including articles, book paragraphs, newspaper articles, and legal documents. The title of a document provides a concise overview of its content, allowing readers to quickly understand the main idea without focusing on the specifics. The more attractive the title is, the more the reader is bound to read it. Title generation will be helpful to the editors of newspapers or technical writers to easily find the central theme of the whole article. The Sequence-to-Sequence (Seq-to-Seq) model is implemented in this proposed work for generating the title for the project, article, and research articles. The Seq-to-Seq model utilizes an encoder-decoder recurrent neural network that has an attention layer and Long Short-Term Memory (LSTM). The main strength of the developed framework is the adoption of an attention layers to the encoder-decoder architecture, which assigns more weightage to background words. This proposed model achieves 90% prediction accuracy by including an attention layer into the LSTM. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

A Fertilizer Recommendation System for Rice Leaf Plant

A Fertilizer Recommendation System for Rice Leaf Plant

引用

International Conference on Communication and Electronics Systems (ICCES)

作者： Subhiksha Murugan A. Manikandan S. Hariprasad Department of Electronics and Communication Engineering College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chennai India Department of Computational Intelligence School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chennai India

ISBN: (数字)9798350377972

ISBN: (纸本)9798350377989

The secret to increasing crop productivity and sustainability is precision farming. Optimizing fertilizer use is essential in rice cultivation to satisfy the unique nutrient requirements of crops while reducing environmental effect. Conventional techniques focus on general principles, which frequently result in reduced yields, deteriorated soil, and inefficient nutrient usage. The AI-based fertilizer recommendation system RiceFert, created for rice leaf plants, is presented in this work. The system examines crop-specific information, soil characteristics (such as type and nutrient levels), and environmental data (temperature, humidity, and wetness) using a Random Forest (RF) model and deep learning techniques. Data preparation, feature extraction, and model training are all part of the process, which compares classifiers such as Random Forest, SVM, Gradient Boosting, and Naive Bayes. The Random Forest model is superior at recommending fertilizer based on performance criteria like accuracy, precision, recall, and F1-score. This focused strategy reduces excessive or inadequate fertilizer use, increasing rice output and promoting sustainable farming. RiceFert demonstrates the potential of AI in precision agriculture by offering farmers personalized guidance that improves crop output, lowers costs, encourages environmental conservation, and helps farmers make better decisions.

关键词： Training Temperature distribution Crops Soil Nutrients Data models Random forests Recommender systems Fertilizers Farming

来源：评论

学校读者我要写书评

暂无评论

QoS-Based Beamforming and Compression Design for Cooperative Cellular Networks via Lagrangian Duality

引用

IEEE Transactions on Signal Processing 2025年

作者： Fan, Xilai Liu, Ya-Feng Liu, Liang Chang, Tsung-Hui Chinese Academy of Sciences State Key Laboratory of Scientific and Engineering Computing Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Beijing100190 China The Hong Kong Polytechnic University Department of Electronic and Information Engineering Hong Kong Hong Kong The Chinese University of HongKong School of Science and Engineering Shenzhen Shenzhen China Shenzhen Research Institute of Big Data China

This paper considers the quality-of-service (QoS)-based joint beamforming and compression design problem in the downlink cooperative cellular network, where multiple relay-like base stations (BSs), connected to the central processor via ratelimited fronthaul links, cooperatively transmit messages to the users. The problem of interest is formulated as the minimization of the total transmit power of the BSs, subject to all users' signal-to-interference-plus-noise ratio (SINR) constraints and all BSs' fronthaul rate constraints. In this paper, we first show that there is no duality gap between the considered joint optimization problem and its Lagrangian dual by showing the tightness of its semidefinite relaxation (SDR). Then, we propose an efficient algorithm based on the above duality result for solving the considered problem. The proposed algorithm judiciously exploits the special structure of an enhanced Karush-Kuhn-Tucker (KKT) conditions of the considered problem and approaches the solution that satisfies the enhanced KKT conditions via two fixed point iterations. Two key features of the proposed algorithm are: (1) it is able to detect whether the considered problem is feasible or not and find its globally optimal solution when it is feasible;(2) it is highly efficient because both of the fixed point iterations in the proposed algorithm are linearly convergent and function evaluations in the fixed point iterations are computationally cheap. Numerical results show the global optimality and efficiency of the proposed algorithm. © 1991-2012 IEEE.

关键词： Lagrange multipliers

来源：评论

学校读者我要写书评

暂无评论

An Extensive Machine Learning Framework Employing Ensemble Classifiers for Heart Disease Detection 3

An Extensive Machine Learning Framework Employing Ensemble C...

引用

3rd International Conference on Innovative Mechanisms for Industry Applications, ICIMIA 2023

作者： Chandralekha, E. Vinodhini, S. Kandasamy, V. Rama, P. Ravikumar, S. Saravanan, T.R. Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Dept.of CSE Chennai India Velammal Engineering College Dept. of Information Technology Chennai India Panimalar Engineering College Dept. of Information Technology Chennai India College of Engineering and Technology Faculty of Engineering and Technology SRM Institute of Science and Technology Dept. of Computing Technologies Chennai India SRM Institute of Science and Technology Dept. of Computational Intelligence Chennai India

ISBN: (纸本)9798350343632

Heart disease is a significant global health challenge, impacting many lives and often being a leading cause of mortality and illness. Detecting heart disease accurately and promptly is essential for effective medical care. Due to the complex interplay of risk factors and the intricate nature of diagnosis, advanced technologies like machine learning are being explored. This study introduces a comprehensive framework that employs machine learning techniques for heart disease detection. The framework involves critical stages such as data preprocessing, feature selection, and training ensemble classifiers. Experimental results highlight the importance of specific attributes in each classifier, offering insights into predictions. Notably, attributes like oldpeak, thalach, ca, cp, and thal are key features in the Random Forest classifier, while Gradient Boosting underscores ca, cp, thal, oldpeak, and age. AdaBoost and the Extra Trees Classifier reveal similar significant attributes. Evaluation metrics emphasize the models' robust performance, with the Extra Trees Classifier achieving the highest accuracy. This research contributes to a practical heart disease detection framework with potential for improving medical decision-making. © 2023 IEEE.

关键词： AdaBoost Extra Trees Classifier Gradient Boosting Machine Learning Random Forest

来源：评论

学校读者我要写书评

暂无评论

Leveraging Internet of Things (IoT) Sensors and Deep Learning Techniques for Precision Agriculture 1

Leveraging Internet of Things (IoT) Sensors and Deep Learnin...

引用

1st International Conference on Innovative engineering sciences and Technological Research, ICIESTR 2024

作者： Wilfred Blessing, N.R. Pyingkodi, M. Wasim Haidar, S.K. Palarimath, Suresh Paravathavarthini, S. Balakumar, C. Sheeja Kumari, V. Sutherlin Subitha, G. Seldev Christopher, S. University of Technology and Applied Sciences-Ibri College of Computing and Information Sciences Ibri Oman Kongu Engineering College Department of Computer Applications Erode India University of Technology and Applied Sciences-Salalah College of Computing and Information Sciences Salalah Oman Kongu Engineering College Department of Computer Technology Erode India Karpagam Academy of Higher Education Department of Computer Science Coimbatore India Saveetha Institute of Medical and Technical Sciences Department of Computational Intelligence Chennai India Stella Mary's College of Engineering Department of Computer Science and Engineering Aruthenganvilai India St. Xavier's Catholic College of Engineering Department of Computer Science and Engineering Nagercoil India

ISBN: (纸本)9798350348637

Precision agriculture, driven by advancements in technology, aims to optimize farming practices by utilizing data and technology to enhance efficiency, productivity, and sustainability This research introduces an innovative pilot investigation centered on the convergence of two revolutionary technologies are the Internet of Things (IoT) and Deep Learning. With a specific focus on advancing precision agriculture, the primary objective of this study is to evaluate the combined effects of data collection facilitated by IoT and analytical capabilities of deep learning in enhancing and optimizing various agricultural processes. The integration of IoT in agriculture has revolutionized data acquisition, employing an array of sensors to monitor critical parameters such as soil moisture, temperature, and crop health. Concurrently, Deep Learning, a subset of artificial intelligence, exhibits the potential to glean actionable insights from voluminous datasets, offering advanced analytics and predictive capabilities. This study investigates the practical implementation and efficacy of this integration in a controlled agricultural setting. Sensors strategically positioned in the pilot study capture real-time data, while deep learning algorithms process and analyze this information. The primary objectives include evaluating the effectiveness of this combined technology in optimizing irrigation schedules, predicting crop yields, and identifying anomalies in crop health. Preliminary findings underscore the transformative potential of IoT and Deep Learning, empowering farmers with real-time data for informed decision-making. Key considerations encompassed in the study include IoT Sensors, Deep learning algorithms, and user adoption. The research not only sheds light on the technical intricacies of the integration but also delves into the challenges and opportunities inherent in merging these technologies within the agricultural landscape. As agriculture transitions towards the next

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

AI-Powered Diagnostic Tool for Retinal Disease Detection Using Convolutional Neural Networks

AI-Powered Diagnostic Tool for Retinal Disease Detection Usi...

引用

Data Intelligence and Cognitive Informatics (ICDICI), International Conference on

作者： Manikandan Moovendran K. K. Dhanush Kumar J. M. Sashanth Department of Computational Intelligence Faculty of Engineering and Technology School of Computing SRM Institute of Science and Technology Chennai CINTEL Department(B.Tech AI) SRM Institute of Science and Technology Chennai

ISBN: (数字)9798350389609

ISBN: (纸本)9798350389616

Accurate and timely detection of retinal disease helps prevent severe vision impairment, although traditional diagnostics take plenty of time and are demanding to perform. This led to the design of the advanced diagnostic tool, in which AI and Convolutional Neural Networks (CNNs) will enhance the identification of retinal disorders. This system will analyze a retina image to detect among others, diabetic retinopathy and age-related macular degeneration, among others. Advanced deep learning algorithms enable the tool to rapidly identify the subtle patterns and anomalies in retinal scans, which even an astute human analyst might not identify, providing insightful and diagnostic support to healthcare experts. This AI-based approach leads to the acceleration of the diagnostic workflow and the minimization of errors, which elevates overall diagnostic accuracy and allows earlier intervention. This technology will contribute to making high-quality retinal care more accessible and efficient, finally arriving at the benefit of a patient at an earlier time of early detection and treatment.

关键词： Macular degeneration Diabetic retinopathy Accuracy Sensitivity Transfer learning Medical services Retina Minimization Convolutional neural networks Diseases

来源：评论

学校读者我要写书评

暂无评论

HPE Transformer: Learning to Optimize Multi-Group Multicast Beamforming Under Nonconvex QoS Constraints

arXiv

引用

arXiv 2024年

作者： Li, Yang Liu, Ya-Feng The Shenzhen Research Institute of Big Data Shenzhen518172 China The State Key Laboratory of Scientific and Engineering Computing Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China

This paper studies the quality-of-service (QoS) constrained multi-group multicast beamforming design problem, where each multicast group is composed of a number of users requiring the same content. Due to the nonconvex QoS constraints, this problem is nonconvex and NP-hard. While existing optimization-based iterative algorithms can obtain a suboptimal solution, their iterative nature results in large computational complexity and delay. To facilitate real-time implementations, this paper proposes a deep learning-based approach, which consists of a beamforming structure assisted problem transformation and a customized neural network architecture named hierarchical permutation equivariance (HPE) transformer. The proposed HPE transformer is proved to be permutation equivariant with respect to the users within each multicast group, and also permutation equivariant with respect to different multicast groups. Simulation results demonstrate that the proposed HPE transformer outperforms state-of-the-art optimization-based and deep learning-based approaches for multi-group multicast beamforming design in terms of the total transmit power, the constraint violation, and the computational time. In addition, the proposed HPE transformer achieves pretty good generalization performance on different numbers of users, different numbers of multicast groups, and different signal-to-interference-plus-noise ratio targets. Copyright © 2024, The Authors. All rights reserved.

关键词： Beamforming

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：