检索结果-内蒙古大学图书馆

Panoptic Region Slicing Segmentation and Optimized Alexnet-Based CNN for Early Melanoma Diagnosis

SN computer science 2024年第6期5卷 756页

作者： Ganesh, V.N. Gulappagol, Laxmi Pushparani, M.K. Ganesh, K. Department of Electronics and Communication Engineering Alvas Institute of Engineering and Technology Department of Internet of Things and Cyber Security including Block chain Technology A J Institute of Engineering and Technology Department of Computer Science & amp Design Alvas Institute of Engineering and Technology

Early and accurate diagnosis of melanoma, a potentially life-threatening skin cancer, is crucial for improving patient outcomes. In this study, we propose a novel approach for melanoma detection, termed Panoptic Region Slicing Segmentation (PRS2) using an optimized convolution neural network (PRS2-OCNN) based on AlexNet. The proposed system integrates several advanced methods to enhance the accuracy and efficiency of melanoma identification. The initial step involves preprocessing the dermoscopic image using a 2D Fusion Filter, which enhances the image quality and prepares it for subsequent analysis. Next, the Panoptic Region Slicing Segmentation (PRS2) method is applied to emphasize the boundary regions, allowing for precise localization of melanoma-affected areas. To assess color variations within the segmented regions, we employ Threshold Histogram Evaluation (THE), which effectively characterizes melanoma-specific color patterns. The features extracted using Spread Spectral Menzies’s Feature Selection (SSMFS), reducing the dimensionality and improving the efficiency of the subsequent analysis. The core of our proposed approach lies in the optimized convolution neural network, derived from the influential AlexNet architecture. By fine-tuning the AlexNet-OCNN on the reduced feature set, we maximize its ability to accurately classify melanoma lesions based on their risk level. The PRS2-OCNN identifies melanoma classes according to their risk severity, aiding dermatologists in making informed decisions for timely and appropriate *** evaluations were conducted on a diverse and extensive dataset of dermoscopic images. The proposed system demonstrated superior performance compared to existing methods, exhibiting heightened detection accuracy by deeply analyzing the melanoma-affected regions. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： 2D fusion filter AlexNet Early diagnosis Melanoma Panoptic region slicing segmentation PRS2-OCNN

来源：评论

学校读者我要写书评

暂无评论

Detection of Parkinson disease for handwriting dataset using deep learning algorithms 3

Detection of Parkinson disease for handwriting dataset using...

引用

3rd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2023

作者： Malathi, A. Ramalakshmi, R. Gandhi, Vaibhav Anand Institute of Higher Technology Department of Computer Science and Engineering Chennai India Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Srivilliputhur India Middlesex University Department of Design Engineering London United Kingdom

ISBN: (纸本)9798350399264

The most common neurodegenerative diseases are Parkinson's disease. People who have reached the age of 70 or older are affected. Parkinson's disease is the second incurable illness after Almeria's disease. The numerous characteristics that distinguish between people with Parkinson's disease and those who are healthy, and earlier diagnosis of the disease results in reduced disease severity. These are the typical signs of Parkinson's disease, which include both motor and non-motor deficiency in patients. The handwritten data set, which includes spiral and wave drawings, was retrieved from UCI equipment. EfficientnetB3 provides high accuracy in comparison to the current CNN model. To increase efficiency, EfflcientnetB3 shrinks the parameter size and equally scales each dimension using a predetermined set of scaling dimensions. The proposed model Adam -EfficientNet achieves 98.3 % which is the best accuracy compared to all other existing CNN models. © 2023 IEEE.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

design & analysis of Optical Ring Resonator with Circular Cavity as Add-drop Multiplexer 7

Design & analysis of Optical Ring Resonator with Circular Ca...

引用

7th IEEE Pune Section International Conference, PuneCon 2024

作者： Patil, Prasenjeet Damodar Bahadure, Nilesh Bhaskarrao Selokar, Pradip Ram Govind Sarate, Gajanan Mit Art Design & Technology University Department of Computer Science and Engineering Maharashtra Pune India Gsfc University Department of Computer Science and Engineering Gujarat Vadodara India Ramdeobaba University Department of Electronics and Communication Engineering Maharashtra Nagpur India Government Polytechnic Department of Electronics Engineering Maharashtra Amaravati India

ISBN: (纸本)9798331527822

From the last decade, there has been immense interest in development of optical components. Optical components can be broadly classified into two types viz. active and passive components. These components are used for purpose of splitting, multiplexing, filtering etc. In order to investigate performance of these components, computationally complex Maxwell's equations are solved either in time or frequency domain. Numerous mathematical methods are developed to solve these equations for analysis of wave propagation inside optical components. The effectiveness of these method depends on the dimensions of the component, wavelength and step size used in the problem. Optical ring resonators are passive components, which are used as channel dropping filters in dense wavelength division multiplexing(DWDM). Filtering performance of ring resonators depends upon various parameters such as size and shape of cavity, coupling length, separation gap from adjacent waveguides etc. In this paper, finite difference beam propagation method(FDBPM) is used to analyze the filtering performance of optical ring resonator with circular cavity. The filtering performance is determined by selecting circular cavities with different diameters and its separation distance for adjacent parallel waveguide. Simulation results shows that maximum optical power can be dropped for circular cavity with smaller diameters with lesser separation gaps, which are consistent with theoretical results. This paper also investigates effect of negative separation gap on filtering performance of ring resonator. © 2024 IEEE.

关键词： Maxwell equations

来源：评论

学校读者我要写书评

暂无评论

Secure-by-Construction Synthesis for Control Systems

引用

IEEE Transactions on Automatic Control 2025年第6期70卷 4170-4177页

作者： Zhong, Bingzhuo Liu, Siyuan Caccamo, Marco Zamani, Majid Thrust of Artificial Intelligence Information Hub The Thrust of Intelligent Transportation System Hub China KTH Royal Institute of Technology Division of Decision and Control Systems Stockholm Sweden Technical University of Munich TUM School of Engineering and Design Germany University of Colorado Boulder Department of Computer Science United States Ludwig Maximilian University Department of Computer Science Munich Germany

In this note, we present the synthesis of secure-by-construction controllers that address safety and security properties simultaneously in cyber-physical systems. Our focus is on studying a specific security property called opacity, which characterizes the system's ability to maintain plausible deniability of its secret behavior in the presence of an intruder. These controllers are synthesized based on a concept of so-called (augmented) control barrier functions. We propose conditions that facilitate the construction of the desired (augmented) control barrier functions and their corresponding secure-by-construction controllers. To compute these functions, we propose an iterative scheme that leverages iterative sum-of-square programming techniques. This approach enables efficient computation of these functions, particularly for polynomial systems. Finally, we validate the effectiveness of our results through a case study of a vehicle. © 1963-2012 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Diet and Exercise Tracking for Daily Requirements Using Artificial Intelligence Technique

Diet and Exercise Tracking for Daily Requirements Using Arti...

引用

2023 International Conference on New Frontiers in Communication, Automation, Management and Security, ICCAMS 2023

作者： Annapureddy, Vasavi Keerthana Kumar, Mohit Hemanth Alliance University Alliance College of Engineering and Design Department of Computer Science and Engineering Karnataka Bengaluru562106 India Alliance University Alliance College of Engineering and Design Department of Mechanical Engineering Karnataka Bengaluru562106 India

ISBN: (纸本)9798350317060

Recently, there has been a concern about our looks and fitness freaks in today's world. The consumption of more food leads to gaining weight in the long run if it exceeds the daily requirement. The present investigation presents the control of calories consumption using the artificial intelligence (AI) model. Based on the AI model, the correct quantity of food is recommended and suggests the necessary workouts to reduce the extra calories. From this investigation, it can be concluded that people can still eat any food and do essential exercises needed for daily requirements to maintain proper health. © 2023 IEEE.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Grammar Error Correction Using Natural Language Processing

Grammar Error Correction Using Natural Language Processing

引用

2023 International Conference on Sustainable Communication Networks and Application, ICSCNA 2023

作者： Geetha, M. Vijaya, K. Subramanian, K.M. Rajesh Kanna, P. Rajeshkumar, G. Karthika, S. M. Kumarasamy College of Engineering Department of Computer Science and Engineering Karur India Kongu Engineering College Department of Computer Science and Design Erode India Shadan College of Engineering and Technology Department of Computer Science and Engineering Hyderabad India Bannari Amman Institute of Technology Department of Computer Science and Engineering Sathyamangalam India Bannari Amman Institue of Technology Department of Artificial Intelligence and Machine Learning Sathyamangalam India

ISBN: (纸本)9798350313987

In the digital era, mos t of the communication is happening through online platforms. English plays a vital role for better understanding. Good grammar helps in framing a better sentence. This demands for the development of an automatic Grammar Error Correction (GEC) tool. Many research works have been initiated to make Grammar Error Correction possible by using various machine learning algorithms. Some of the algorithms are Naive Bayes, BERT, Support Vector Machine, and ULMFIT. Among these algorithms BERT gives a comparatively best accuracy rate. The fundamental goal of this research work is to compare these algorithms with respect to accuracy Here, NLP is used for analyzing the grammatical corrections in the sentence. Further, this study can be extended to overcome the drawbacks faced by the BERT algorithm such as increase in time cons umption for training and cos t. © 2023 IEEE.

关键词： Bidirectional Encipher Representations from Instruments Grammar Error Correction Natural Language Processing Universal Language Model Fine-Tuning

来源：评论

学校读者我要写书评

暂无评论

Real-Time 4-Mode MDM Transmission Using Commercial 400G OTN Transceivers and All-Fiber Mode Multiplexers

引用

ZTE Communications 2024年第1期22卷 106-110页

作者： REN Fang LI Yidan YE Bing LIU Jianguo CHEN Weizhang School of Computer and Communication Engineering University of Science and Technology BeijingBeijing 100083China Department of WDM System Design ZTE CorporationBeijing 100029China

Weakly-coupled mode division multiplexing(MDM)technique is considered a promising candidate to enhance the capacity of an optical transmission system,in which mode multiplexers/demultiplexers(MMUX/MDEMUX)with low insertion loss and modal crosstalk are the key *** this paper,a low-modal-crosstalk 4-mode MMUX/MDEMUX for the weakly-coupled triple-ring-core few-mode fiber(TRC-FMF)is designed and fabricated with side-polishing *** measurement results show that a pair of MMUX/MDEMUX and 25 km weakly-coupled TRC-FMF MDM link achieve low modal crosstalk of lower than−17.5 dB and insertion loss of lower than 11.56 dB for all the four *** on the TRC-FMF and all-fiber MMUX/MDEMUX,an experiment for 25 km real-time 4-mode 3-λwavelength division multiplexing(WDM)-MDM transmission is conducted using commercial 400G optical transport network(OTN)*** experimental results prove weakly-coupled MDM techniques facilitate a smooth upgrade of the optical transmission system.

关键词： optical fiber couplers mode(de)multiplexers mode division multiplexing transmission

来源：评论

学校读者我要写书评

暂无评论

Skeleton-Based Volumetric Parameterizations for Lattice Structures

引用

computer Modeling in engineering & sciences 2023年第4期135卷 687-709页

作者： Long Chen Shuxun Liang Nan Yan Xiangqian Yang Baotong Li School of Mechanical Engineering University of Shanghai for Science and TechnologyShanghai200093China School of Optical-Electrical and Computer Engineering University of Shanghai for Science and TechnologyShanghai200093China Key Laboratory of EducationMinistry for Modern Design&Rotor-Bearing System Xi’an Jiaotong UniversityXi’an710049China

Lattice structures with excellent physical properties have attracted great research *** this paper,a novel volume parametric modeling method based on the skeleton model is proposed for the construction of threedimensional lattice *** skeleton model is divided into three types of *** the corresponding algorithms are utilized to construct diverse types of volume parametric *** unit-cell is assembled with distinct nodes according to the geometric *** final lattice structure is created by the periodic arrangement of *** different types of volume parametric lattice structures are constructed to prove the stability and applicability of the proposed *** quality is assessed in terms of the value of the Jacobian ***,the volume parametric lattice structures are tested with the isogeometric analysis to verify the feasibility of integration of modeling and simulation.

关键词： Lattice structure volumetric parameterization skeleton model node modeling

来源：评论

学校读者我要写书评

暂无评论

Application of computer Vision and Deep Learning Neural Network in Multi-Modal Information Fusion 2

Application of Computer Vision and Deep Learning Neural Netw...

引用

2nd IEEE International Conference on Data science and Network Security, ICDSNS 2024

作者： Wu, Qiongfei Xie, Qubo Xia, Dingchun Wuhan Institute of Design and Science Department of Information Engineering Hubei Wuhan China School of Computer Science&Technology Huazhong University of Science and Technology Hubei Wuhan China School of Computer Science and Artificial Intelligence Wuhan Textile University Hubei Wuhan China

ISBN: (纸本)9798350373110

Multimodal data often requires manual annotation for training, and the annotation process is tedious and time-consuming. The lack of labels makes it difficult to build large-scale labeled multi-modal datasets. In response to the current problems, this article proposes a solution based on a deep neural network algorithm to classify and identify multi-modal data and realize mutual conversion between different features. It can be seen from the experimental results that when the sample error is less than 5%, using deep model training can significantly reduce the difference between the original sample linearity and the local maximum likelihood. This article adopts a multi-layered structure of hyper-realization method to achieve higher accuracy than traditional artificial prediction values. Through verification, it was found that the average coefficients of the hidden layer and additive features were 0.53 and 0.67 respectively, there were multiple correlations between these two data, the closer the correlation coefficient was to 1, then they were positively correlated;the average data input convergence was 64%, and the average output convergence was 72.3%;the matching efficiency of this fusion model could reach up to 97%. © 2024 IEEE.

关键词： Information fusion

来源：评论

学校读者我要写书评

暂无评论

Novel soft robotic finger model driven by electrohydrodynamic(EHD)pump

引用

Journal of Zhejiang University-science A(Applied Physics & engineering) 2024年第7期25卷 596-604页

作者： Xuehang BAI Yanhong PENG Dongze LI Zhuochao LIU Zebing MAO Department of Mechanical Automotive and Materials EngineeringFaculty of EngineeringUniversity of WindsorWindsorN9B 3P4Canada Department of Information and Communication Engineering Graduate School of EngineeringNagoya UniversityNagoya464-8601Japan Department of Intelligent Science and Technology College of Computer Science and TechnologyQingdao UniversityQingdao266071China Design and Research Institute of University of Science and Technology Beijing Co.Ltd. Beijing100083China Faculty of Engineering Yamaguchi UniversityYamaguchi755-8611Japan

1Introduction In the field of robotic-human interactions,soft robotics offers enhanced safety and adaptability.A major challenge in this area is the integration of soft actuators with pump systems,which often increases the system volume and *** study presents the development and testing of a robotic finger powered by electrohydrodynamic(EHD)*** leveraging the electric field-induced flow of dielectric fluids.

关键词： robotic complexity. pump

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：