检索结果-内蒙古大学图书馆

2024 Asia Pacific Conference on Innovation in technology, APCIT 2024

作者： Priyanka, S. Selvam, Prabu Vellore Institute of Technology School of Computer Science and Engineering Chennai India SRM Institute of Science and Technology Department of Computer Science and Engineering Tiruchirappalli India

ISBN: (纸本)9798350361537

Ophthalmic diagnostics play a critical role in the early detection and management of various ocular diseases. Among the advanced imaging modalities employed in ophthalmology, Optical Coherence Tomography (OCT) has emerged as a cornerstone technology for non-invasive, high-resolution imaging of ocular structures. This paper analyzes the efficiency of three deep learning models such as VGG16, ResNet50, and InceptionV3, in Optical Coherence Tomography (OCT) images. This study compares the efficiency of these deep learning models in classifying four different pathological retinal conditions: Normal Retina (NR), Choroidal NeoVascularization (CNV), Diabetic Macular Edema (DME), and Early Age-Related Macular Degeneration (EAMD). In addition, we have performed two preprocessing operations, image enhancement and data augmentation, to improve the image quality and to over the data imbalance, respectively. We assessed the performance of these deep learning models using a benchmark dataset. After the experiments, we found that the VGG16 outperforms ResNet50 and InceptionV3 by accomplishing an accuracy of 98.7%. © 2024 IEEE.

关键词： Optical coherence tomography

来源：评论

学校读者我要写书评

暂无评论

3D-printed shoulder and elbow exercise device for stroke patients-A pilot study

引用

Medicine in Novel technology and Devices 2024年第4期24卷 85-92页

作者： Porkodi Jayavel Varshini Karthik Jaison Jacob Mathunny Suresh Jothi Ashokkumar Devaraj Department of Biomedical Engineering College of Engineering and TechnologySRM Institute of Science and TechnologyKattankulathurIndia SRM College of Physiotherapy SRM Institute of Science and TechnologyKattankulathurIndia

Upper limb movements are essential in everyday life;hand paralysis caused by post-stroke affects the regular lives of *** regain hand mobility and motor function,we must perform repetitive ***,rehabilitation devices are essential to help post-stroke victims exercise and recover from paralysis more *** proposed research developed a 3D-printed portable rehabilitative device for elbow and shoulder *** device assists patients with hand impairments in performing repetitive elbow flexion and internal/external rotation of the *** post-stroke patients(each group of 10)were randomly assigned to the traditional training group or rehabilitation device training *** study compared the outcomes of the two groups before and after eight weeks of *** the therapy,the patient's performance was evaluated using standard clinical tests such as the Fugl-Meyer Assessment(FMA)and Active Range of Motion(AROM)of the elbow and *** results of the RDT(Rehabilitation Device Training)group were greater than those of the TT(Traditional Training)group,and the p values(p<0.05)show a significant *** proposed device is a simple,low-cost,portable structure that improves muscular strength and mobility in the shoulder and elbow.

关键词： Exercise Rehabilitation Stroke Portable Strength

来源：评论

学校读者我要写书评

暂无评论

Computational Investigation on Flow of Nanofluid past an Exponentially Stretching Surface using VHPM

引用

IAENG International Journal of Applied Mathematics 2024年第5期54卷 902-909页

作者： Mahalakshmi, D. Vennila, B. Department of Mathematics College of Engineering and Technology SRM Institute of Science and Technology SRM Nagar Tamil Nadu Kattankulathur Chengalpattu603 203 India Department of Mathematics College of Engineering and Technology SRM Institute of Science and Technology SRM Nagar Tamil Nadu Kattankulathur Chengalpattu603 203 India

The theory of nanoliquids has revealed several fundamental properties, including a significant increase in thermal conductivity over the base fluid. In this study, we analyzed the nanoliquids two-dimensional laminar boundary layer flow over an exponentially stretching surface. Suitable variables are applied to simplify the nonlinear partial differential equations (PDEs) into ordinary differential equations (ODEs). The resulting equations are analytically solved by using the variational homotopy perturbation method (VPHM),and the graphical representation obtained with the help of the expressions for momentum, temperature, and concentration are evaluated for specific estimates of the dimensionless parameters, specifically the Lewis number(Le), Brownian motion parameter (Nb), thermophoresis parameter (Nt), Prandtl number (Pr), of suction and injection parameters. © (2024), (International Association of Engineers). All Rights Reserved.

关键词： Brownian movement

来源：评论

学校读者我要写书评

暂无评论

Automated Pneumonia Detection Using Manta Ray Optimizer with Deep Learning Approaches 2

Automated Pneumonia Detection Using Manta Ray Optimizer with...

引用

2nd IEEE International Conference on IoT, Communication and Automation technology, ICICAT 2024

作者： Sabaresh, M.M. Shahin, Fidin Sabri Raja, M Senthil SRM Institute of Science and Technology Computer Science and Engineering CTech Department Chennai India SRM Institute of Science and Technology CTech Department Chennai India

ISBN: (纸本)9798350368109

This new method merging various disciplines into each stage, introduces a novel integration of state-of-the-art neural networks (MobileNet, ResNet, and VGG19) with an adaptive nature based on the Manta Ray scheme within the framework approaches helped by Adam optimizer to significantly improve accuracy across chest X-ray images. Integrating physics-motivated model parameter adaptation, based on the fluid-inspired lenticular lens architecture of manta rays (7), into MRO encourages more rapid convergence during training and allows for flexible manipulation in response to distributed behaviors inherent to medical imaging. This combined action not only accelerates convergence but also enhances the global stability of the model, improving classification accuracy and increasing reliability in diagnostics. Furthermore, the interoperability of these approaches highlights how cross-disciplinary research in healthcare technology can not only be transformational but also provide invaluable adjuncts to clinical practice for high-throughput targeted analyses. In an entirely new way, we want to transform traditional medical imaging analysis by bringing pervasively accurate diagnosis into everyday clinical practice while providing better outcomes for patients and leading "the cutting edge"of healthcare delivery. This ultimate workflow does seem to hold the key which can result in far-reaching improvements in health care, especially after making important progress upon the currently existing slower and less efficient healthcare systems. This approach is interdisciplinary and promises revolutionary progress in medical diagnostics. © 2024 IEEE.

关键词： Clinical research

来源：评论

学校读者我要写书评

暂无评论

Automata Field Analysis: Operations, Substructures, and Homomorphisms

引用

IAENG International Journal of Applied Mathematics 2024年第3期54卷 350-364页

作者： Sathiyasorubini, G. Venkatesan, R. Department of Mathematics College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamilnadu Chengalpattu603203 India Department of Mathematics College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamilnadu Chengalpattu603203 India

This paper introduced the automata field concept and studied its characteristics. In particular, we define new operations by converting finite automata to finite automata field. Additionally, we examine the properties of finite automata field and their relation to field. We also define substructures of the automata field, including sub-automata field and automata field homomorphism. © (2024), (International Association of Engineers). All Rights Reserved.

关键词： Finite automata

来源：评论

学校读者我要写书评

暂无评论

The Fuzzy Sumudu Decomposition Method for Solving Differential Equations in an Imprecise Context

引用

IAENG International Journal of Applied Mathematics 2024年第12期54卷 2523-2528页

作者： Divya, B. Ganesan, K. Department of Mathematics College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamilnadu Chengalpattu603203 India Department of Mathematics College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamilnadu Chengalpattu603203 India

This paper presents the fuzzy Sumudu decomposition technique (FSDM) as a novel method for dealing with differential equations that contain uncertainty. The FSDM method allows for the direct solution of fuzzy differential equations, eliminating the need to convert them into their classical counterparts, which is a need in conventional methodologies. This is achieved by analysing the equations using a novel fuzzy arithmetic approach. By employing FSDM, we generate solutions using infinite series that gradually converge towards the exact solutions for the specific problems being studied. This approach offers a reliable and powerful tool for dealing with differential equations in a fuzzy setting, enabling us to understand and handle the inherent uncertainty inside the system. An illustrative numerical example is presented to showcase the potential and practicality of the FSDM. This case serves as an illustration of how the technique can be employed to tackle realworld difficulties. This illustration showcases the efficacy of the FSDM (Fuzzy Set Differential Method) in effectively solving fuzzy differential equations and generating accurate results. This study contributes to the subject of differential equations by introducing the fuzzy Sumudu decomposition methodology as an alternative strategy for dealing with uncertainty. The FSDM approach offers a novel and efficient technique for resolving fuzzy differential equations through the redefinition of the issue and the use of fuzzy arithmetic. This is illustrated with a numerical example. © (2024), (International Association of Engineers). All Rights Reserved.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Customized Movie Recommendation for Enhanced Entertainment

Customized Movie Recommendation for Enhanced Entertainment

引用

2024 International Conference on Cybernation and Computation, CYBERCOM 2024

作者： Minu, M.S. Talapalli, Srikar Chevuri, Saahithi Medhasri, T.S. SRM Institute of Science and Technology Department of Computer Science Engineering Ramapuram Chennai India SRM Institute of Science and Technology Department of Computer Science Engineering with Specialization in Big Data Analytics Ramapuram Chennai India

ISBN: (纸本)9798331542344

The surging popularity of online movie databases has created a challenge for viewers: choosing a film from a massive library can be overwhelming. In this paper, it proposes to design a new hybrid movie recommendation powered by machine learning techniques as a solution to improve user experience. Among those techniques, two are combined into this paper: content-based filtering, using the real features of a movie such as genre and a director, and collaborative filtering, which uses the rating provided by users. This hybrid approach thus improves the intrinsic weaknesses that reside in both these methods individually. On the other hand, content-based filtering tends to reduce exploration to movies of the exact type one is doing well at, whereas, inversely, collaborative filtering settings often mean that a user will be exposed only to films within his or her already-recognized taste profile. It is expected that the proposed hybrid system will solve both problems by balancing this line between exploring familiar cinematic territory and making new recommendations based on both user preferences and the entire collective intelligence of the user base. The approach would aim to enrich user satisfaction by facilitating the selection of movies and providing a richer and more diversified movie-viewing experience. © 2024 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Trapezoidal Neutrosophic Program Evaluation and Review Technique Using Interval Arithmetic Operations

引用

IAENG International Journal of Applied Mathematics 2024年第3期54卷 324-341页

作者： Sinika, S. Ramesh, G. Department of Mathematics College of Engineering and Technology SRM Institute of Science and Technology Tamilnadu Kattankulathur Chengalpattu603203 India Department of Mathematics College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chengalpattu Tamilnadu603203 India

In the discipline of project management, the occurence of ambiguity and vagueness are the major hurdles for its accomplishment. Neutrosophic sets can be a great solution to overcome such situations leading to improved decision-making, better communication and enhanced problem-solving in project management. By incorporating neutrosophic sets into the PERT, one can handle uncertainty in the project schedule and improve the accuracy of critical path analysis. This manuscript instigates an interval-based de-neutrosophication methodology and utilizes PERT problem in a neutrosophic environment. Trapezoidal neutrosophic forward and backward pass are employed to determine each activity’s neutrosophic slack time and criticality. It uses the proposed interval-based ranking technique as a tool to ease the analysis. To validate the critical path, we develop a trapezoidal neutrosophic criticality degree for all the activities and further the efficiency of the proposed technique is analyzed using illustrations. Additionally, interval-valued trapezoidal neutrosophic fuzzy PERT is discussed by constructing the criticality degree using the interval-based de-neutrosophication technique and finally deliberated with examples. © (2024), (International Association of Engineers). All Rights Reserved.

关键词： Criticality (nuclear fission)

来源：评论

学校读者我要写书评

暂无评论

Ensuring Trust in Blockchain-Based E-commerce Using Smart Contracts 5th

Ensuring Trust in Blockchain-Based E-commerce Using Smart Co...

引用

5th International Conference on Computing, Communications, and Cyber Security, IC4S 2023

作者： Surendar, P.D. Kumar, Adhithi Satish Pavani, Venkata Azhagiri, M. Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai600089 India

ISBN: (纸本)9789819773701

In the ever-changing realm of e-commerce, building trust is crucial for both customers and sellers. Reputation systems play a vital role in enabling informed decision-making by providing vendor ratings and reviews. Conventional reputation systems are typically inadequate in dealing with contemporary issues including privacy, identity theft, and feedback fraud. In order to address these challenges, we suggest implementing a decentralized reputation system that places a high value on privacy and effectively counters existing risks. Our architecture utilizes two permissioned blockchains, Hyperledger Indy for decentralized identity management through verifiable credentials and Zero Knowledge Proof (ZKP) technology, guaranteeing anonymity and authenticity, and Hyperledger Fabric for executing smart contracts, facilitating intricate business logic. The system incorporates verified vendor identities, transaction feedback tokens, and discount tokens to encourage genuine evaluations. Smart contracts implemented on the Hyperledger Fabric platform provide the security and transparency of the feedback process, hence reducing the occurrence of biased feedback and identity assaults. This technique provides a strong and reliable answer to the issues faced in e-commerce. It ensures the protection of private information and enables the verification of digital identities while maintaining privacy. The implementation of feedback and discount tokens promotes the provision of precise input, mitigating unjust practices and bolstering the dependability and confidence in the system. We demonstrate the effectiveness of our methodology using Zero Knowledge Proofs (ZKP), highlighting its importance in establishing confidence within the context of blockchain. Our system represents a notable advancement in creating a safe, transparent, and reliable e-commerce environment. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Audio Assistive System for Visually Impaired People

引用

computers, Materials & Continua 2022年第4期71卷 1205-1219页

作者： S.Kiruthika Devi C.N.Subalalitha Department of Computer Science and Engineering SRM Institute of Science and TechnologyKattankulathur603203India

Vision impairment is a latent problem that affects numerous people across the *** advancements,particularly the rise of computer processing abilities like Deep Learning(DL)models and emergence of wearables pave a way for assisting visually-impaired *** models developed earlier specifically for visually-impaired people work effectually on single object detection in unconstrained ***,in real-time scenarios,these systems are inconsistent in providing effective guidance for visually-impaired *** addition to object detection,extra information about the location of objects in the scene is essential for visually-impaired *** this in mind,the current research work presents an Efficient Object Detection Model with Audio Assistive System(EODM-AAS)using DL-based YOLO v3 model for visually-impaired *** aim of the research article is to construct a model that can provide a detailed description of the objects around visually-impaired *** presented model involves a DL-based YOLO v3 model for multi-label object ***,the presented model determines the position of object in the scene and finally generates an audio signal to notify the visually-impaired *** order to validate the detection performance of the presented method,a detailed simulation analysis was conducted on four *** simulation results established that the presented model produces effectual outcome over existing methods.

关键词： Deep learning visually impaired people object detection YOLO v3

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：