检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Recent Advances in science and engineering Technology, ICRASET 2024

作者： Rekha, V. Sharmila, N. Komala, M. Pavithra, G.S. Mallikarjunaswamy, S. Naveen, K.B. Shilpa, M. Sheela, S. Department of Computer Science and Engineering Bangalore India Jss Science and Technology University Dept of Electronics and Electrical Engineering Mysuru India Sjb Institute of Technology Dept of Electronics and Communication Engineering Bengaluru India Jss Academy of Technical Eduction Dept of Computer Science and Engineering Bengaluru India Jss Academy of Technical Eduction Dept of Electronics and Communication Engineering Bengaluru India Bgs Institute of Technology Adichunchanagiri University Dept of Electronics and Electrical Engineering BG Nagara India Bengaluru Institute of Technology Dept of Information Science and Engineering Bengaluru India Global Academy of Technology Dept of Computer Sceinec and Engineering Bengaluru India

ISBN: (纸本)9798350388602

The integration of renewable energy sources into smart grids requires advanced management systems to optimize energy production, storage, and distribution. Conventional methods like Static Energy Allocation (SEA) and Rule-Based Control (RBC) struggle with real-time adaptability, leading to inefficiencies in handling the variable nature of renewable energy. SEA and RBC lack the predictive capabilities needed to effectively manage dynamic energy generation, resulting in increased energy losses and operational *** paper proposes a Hybrid Edge-Cloud Renewable Energy Management System (HECREMS) using Deep Learning with Predictive Analytics (DLPA). HECREMS integrates edge computing for real-time data processing with cloud computing for enhanced predictive analytics, providing a robust framework for efficient energy management. The proposed system leverages the low latency of edge devices and the computational power of the cloud to improve energy forecasting and decision-making. HECREMS outperforms traditional SEA and RBC methods, achieving a 0.25% improvement in energy utilization efficiency, a 0.20% reduction in operational costs, and a 0.30% increase in system responsiveness. By addressing the drawbacks of conventional approaches, HECREMS demonstrates significant advancements in the efficient and sustainable management of renewable energy within smart grids. © 2024 IEEE.

关键词： Cloud analytics

来源：评论

学校读者我要写书评

暂无评论

Deep Transfer Learning Models for Mobile-Based Ocular Disorder Identification on Retinal Images

引用

computers, Materials & Continua 2024年第7期80卷 139-161页

作者： Roseline Oluwaseun Ogundokun Joseph Bamidele Awotunde Hakeem Babalola Akande Cheng-Chi Lee Agbotiname Lucky Imoize Department of Multimedia Engineering Kaunas University of TechnologyKaunas44249Lithuania Department of Computer Science Landmark UniversityOmu Aran251103Nigeria Department of Computer Science Faculty of Information and Communication SciencesUniversity of IlorinIlorin240003Nigeria Department of Telecommunication Science University of IlorinIlorin230003Nigeria Department of Library and Information Science Fu Jen Catholic UniversityNew Taipei City24205TaiwanChina Department of Computer Science and Information Engineering Fintech and Blockchain Research CenterAsia UniversityTaichung City41354TaiwanChina Department of Electrical and Electronics Engineering Faculty of EngineeringUniversity of LagosAkokaLagos100213Nigeria Department of Electrical Engineering and Information Technology Institute of Digital CommunicationRuhr UniversityBochum44801Germany

Mobile technology is developing *** phone technologies have been integrated into the healthcare industry to help medical ***,computer vision models focus on image detection and classification ***2 is a computer vision model that performs well on mobile devices,but it requires cloud services to process biometric image information and provide predictions to *** leads to increased *** biometrics image datasets on mobile devices will make the prediction faster,but mobiles are resource-restricted devices in terms of storage,power,and computational ***,a model that is small in size,efficient,and has good prediction quality for biometrics image classification problems is *** pre-trained CNN(PCNN)MobileNetV2 architecture combined with a Support Vector Machine(SVM)compacts the model representation and reduces the computational cost and memory *** proposed novel approach combines quantized pre-trained CNN(PCNN)MobileNetV2 architecture with a Support Vector Machine(SVM)to represent models efficiently with low computational cost and *** contributions include evaluating three CNN models for ocular disease identification in transfer learning and deep feature plus SVM approaches,showing the superiority of deep features from MobileNetV2 and SVM classification models,comparing traditional methods,exploring six ocular diseases and normal classification with 20,111 images postdata augmentation,and reducing the number of trainable *** model is trained on ocular disorder retinal fundus image datasets according to the severity of six age-related macular degeneration(AMD),one of the most common eye illnesses,Cataract,Diabetes,Glaucoma,Hypertension,andMyopia with one class *** the experiment outcomes,it is observed that the suggested MobileNetV2-SVM model size is *** testing accuracy for MobileNetV2-SVM,InceptionV3,and MobileNetV2 is 90.11%,86.88%,a

关键词： Retinal images ocular disorder deep transfer learning disease identification mobile device

来源：评论

学校读者我要写书评

暂无评论

Wireless Gesture-Driven Navigation for Autonomous Robots: An Innovative Human-Machine Interface Approach

Wireless Gesture-Driven Navigation for Autonomous Robots: An...

引用

2024 International Conference on System, Computation, Automation and Networking, ICSCAN 2024

作者： Zarina Begum, M. Gowthami, V. Ramya, M. Vijaya Shanthi, V. Manakula Vinayagar Institute of Technology Department of Electronics and Communication Engineering Puducherry India Christ Institute of Technology Department of Computer Science Engineering Puducherry India

ISBN: (数字)9798331510022

ISBN: (纸本)9798331510022

As more and more features are added to the car's Human- Machine Interface (HMI), device management becomes increasingly difficult. Making the most of the many human senses is consequently a tactic to facilitate using in-car technologies. With the use of an Arduino Uno and this concept, a car robot with wireless navigation can be built. The robot chassis's direction is altered in accordance with the statement specified in the Arduino code, which is run when the position of the hand is monitored and the designed coordinates are taken into consideration as the parameter. in order for it to carry out the necessary actions, such as going ahead, backward, turning left, turning right, and stopping. © 2024 IEEE.

关键词： DC motors

来源：评论

学校读者我要写书评

暂无评论

Improved UNet for Semi-Supervised Multi-Scale CMRI Right Ventricular Segmentation Method 9

Improved UNet for Semi-Supervised Multi-Scale CMRI Right Ven...

引用

9th International Conference on Intelligent Computing and Signal Processing, ICSP 2024

作者： Cui, Hongzhen Wang, Shichao Zhu, Xiaoyue Peng, Yunfeng School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China School of Electronics and Information Engineering Liaoning University of Technology Liaoning China

ISBN: (纸本)9798350376548

Segmentation of the right ventricle (RV) holds significant clinical implications for the assessment of cardiac function in conditions such as pulmonary hypertension. Precise delineation of the right ventricle from cardiac magnetic resonance images (CMRI) is crucial in the diagnosis of various cardiac conditions. It provides clinicians with essential information for patient evaluation, treatment planning, and subsequent rehabilitation strategies. Currently, the development of fully automated segmentation models for the right ventricle heavily relies on deep learning techniques, necessitating meticulous manual annotation of CMRI data to achieve optimal segmentation results. However, the labor-intensive nature of labeling CMRI data requires significant medical expertise and consumes considerable time and resources. In response to these challenges, this study proposes a semi-supervised multi-scale segmentation approach for the right ventricle in CMRI. The method leverages unlabeled data to enhance segmentation accuracy while minimizing the reliance on annotated data. Experimental findings demonstrate the effectiveness of the proposed method in accurately delineating the right ventricle from CMRI datasets. © 2024 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Development of a CNN Model for Efficient Leaf Disease Detection

Development of a CNN Model for Efficient Leaf Disease Detect...

引用

2024 OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Dagar, Ishant Sharma, Harsh Gusain, Raj Vidyarthi, Anurag Prakash, Rishi Gowri, R. Propagation Research Lab Department of Electronics & Communication Engineering Dehradun India Graphic Era Hill University Department of Computer Science Engineering Dehradun India

ISBN: (纸本)9798350373783

In order to mitigate financial losses for producers and safeguard crops against diseases, the proposed solution presents a CNN model that enables early detection of leaf issues. In the agriculturally dominant nation of India, foliage maladies annually reduce agricultural output by 35%. The process of manually identifying diseases in foliage is time-consuming due to the lack of apparatus and expertise in laboratories required to identify early indicators of such conditions. The following are examples of such diseases: late blight, early blight, black root, bacterial mark, infected leaf, healthy leaf, and so forth. The importance of developing self-governing algorithms to diagnose diseases in leaves through the analysis of visual symptoms has been underscored by recent developments in deep learning and computer vision models. The main aim of the proposed model is to address the challenge of leaf disease diagnosis through the implementation of a straightforward method that minimizes the demand for computational resources. We implemented the multi-layered architecture of convolutional neural networks (CNN) in order to identify and eradicate leaf diseases. A model for image classification is trained utilizing our proposed approach, and it attains an accuracy of 91.5%, surpassing the performance of existing methodologies. © 2024 IEEE.

关键词： Multilayer neural networks

来源：评论

学校读者我要写书评

暂无评论

Unleashing the Power of STAR-RIS for Enhanced Connectivity in Counteracting Random Blockages

Unleashing the Power of STAR-RIS for Enhanced Connectivity i...

引用

2024 IEEE Global communications Conference, GLOBECOM 2024

作者： Zhu, Zengjie Huang, Xiaoxia Li, Pan Lin, Phone Sun Yat-sen University School of Electronics and Communication Engineering China Hangzhou Dianzi University School of Computer Science China National Taiwan University Department of Computer Science and Information Engineering Taiwan

ISBN: (纸本)9798350351255

Reconfigurable Intelligent Surfaces (RISs) have emerged as a promising technology for network performance enhancement by intelligently manipulating the propagation environment. In contrast to conventional reflecting-only RIS, the simultaneous transmitting and reflecting RIS (STAR-RIS) extends coverage to 360 degrees through transmission and reflection, offering more flexibility in channel reconfiguration. The application of STAR-RIS in wireless networks holds tremendous potential for significantly improving network connectivity by fostering cascaded paths. However, it remains open on the deployment strategy for STAR-RIS to guarantee network connectivity cost-effectively, especially when considering random blockages. In this paper, we focus on investigating the impact of STAR-RIS on network connectivity in blockage-prone scenarios. Leveraging percolation theory, we derive upper and lower bounds for the critical density of nodes in both no-STAR-RIS and STAR-RIS-aided networks. Our results quantify the impact of STAR-RIS on network connectivity, demonstrating its significant enhancement on network connectivity and providing valuable insights into cost-effective deployment schemes for STAR-RIS. © 2024 IEEE.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

Progressive Learning Framework for Speech Enhancement using Multi-scale Convolution and S-TCN 8

Progressive Learning Framework for Speech Enhancement using ...

引用

8th International Conference on Inventive Systems and Control, ICISC 202

作者： Parisae, Veeraswamy Bhavanam, S Nagakishore Devi, M Vasuja Acharya Nagarjuna University Electronics and Communication Engineering Andhra Pradesh Guntur India Department of Computer Science & Engineering Jabalpur Madhya Pradesh Barela India

ISBN: (纸本)9798350386578

In recent years, there has been a growing prevalence of deep-learning methods for enhancing speech. Recent research has focused on capturing speech's long-range dependencies efficiently to enhance performance. However, many studies on speech enhancement typically overlook the distributions of speech signal's energy in the time-frequency (T-F) domain, a crucial factor for accurately predicting masks. An enhancement model of target speech based on long-term and T-F distributions is presented in this paper. The Feature extraction and reconstruction make up the system. There is a significant limitation to traditional CNNs, which is the use of a fixed-sized kernel, which compromises local as well as contextual data. It is overcomed using multiscale convolution-based feature extractor blocks (MSCFEB) in the extractor. Different kernel sizes are used in a single layer for capturing the interaction of both local as well as contextual information in the signal. There is a time-frequency attention (TFA) module following each MSCFEB in the feature extractor. By usingTFA, varying attention weights are allocated to each time-frequency spectral component. This allows model to focus on specific time frames and frequency channels. By stacking several filtering modules (FMs), the spectrum reconstruction module(SRM) facilitates reconstruction of a spectrum in a progressive manner to reduce magnitude noise. Furthermore, spectrum estimation is ultimately achieved by unfolding the filtering modules repeatedly, gradually improving the intermediate outcome across stages. Tests are conducted with the common voice dataset to validate the proposed approach. The results demonstrate that this model outperformed previous baseline systems. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

AI-Powered Smart Glasses and Shoes for the Visually Impaired 6

AI-Powered Smart Glasses and Shoes for the Visually Impaired

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Makanyadevi, K. Avinash, M.V. Chandhrakiran, S.V. Kavitha, S. Bhalaram Krishna, S.A. Dhiyanesh, S. Department of Computer Science and Engineering M.Kumarasamy College of Engineering Thalavapalayam Tamilnadu Karur India Department of Electronics and Communication Engineering M.Kumarasamy College of Engineering Thalavapalayam Tamilnadu Karur India

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522667

This project proposes a wearable assistive system aimed at improving navigation for visually impaired individuals. The system integrates AI-powered smart glasses and specially designed shoes, working together to enhance the user’s ability to detect and avoid obstacles in their surroundings. Central to the system is the YOLO v8 (You Only Look Once) algorithm, a state-of-the-art deep learning model that enables real-time object recognition. The smart glasses use this model to detect and classify objects such as people, vehicles, and potential obstacles, providing immediate feedback to the user regarding their environment. In addition to the object recognition capabilities of the glasses, the system employs ultrasonic sensors in both the glasses and shoes to detect nearby objects or obstacles. These sensors measure the distance to obstacles and provide critical information on the proximity of objects. When an obstacle is detected within a dangerous range, the system alerts the user using a buzzer and a vibration sensor, enhancing their spatial awareness. The smart glasses are responsible for detecting forward-facing objects, while the shoes focus on ground-level obstacles, such as uneven surfaces or stairs, which are crucial for safe navigation. The system is controlled by an Arduino Uno microcontroller that processes data from the sensors and manages the alerts in real-time. Designed for cost-effectiveness, energy efficiency, and ease of maintenance, this wearable assistive system offers an innovative solution for visually impaired individuals, providing them with greater independence and safety in everyday navigation. Ultimately, this project aims to improve the quality of life for users by fostering increased mobility and confidence in navigating their environment. © 2025 IEEE.

关键词： Ultrasonic sensors

来源：评论

学校读者我要写书评

暂无评论

PERFORMANCE ANALYSIS OF VLC-BASED LI-FI NLOS UNDERWATER CHANNEL USING ASK MODULATION SCHEME OVER WDM UNDER THE INFLUENCE OF AMBIENT LIGHT

PERFORMANCE ANALYSIS OF VLC-BASED LI-FI NLOS UNDERWATER CHAN...

引用

2025 International Conference on Energy, Power, Environment, Control and Computing, ICEPECC 2025

作者： Umer, Rao Behram Mushtaq, Farhan Khan, Faisal Hammad Nouman, Muhammad Hassan, Usman Amanullah Adnan, Muhammad Photonics And Communication Lab Department of Electrical Engineering University of Engineering & Technology Taxila Pakistan Electronics and Communication Systems Lab Department of Telecommunication Engineering University of Engineering & Technology Taxila Pakistan School of Electrical Engineering and Computer Science National University of Sciences and Technology Islamabad Pakistan

ISBN: (纸本)9781837243235

Li-Fi is another term for Visible light communication (VLC) which operates by transmitting data through free space by using either Light Emitting Diodes (LEDs) or Laser Diodes (LDs). The technique finds substantial applications in scientific research as well as military applications when used underwater. VLC technology helps eliminate radio interference alongside providing replacement solutions for traditional underwater communication systems. The research develops and models a visible light wireless communication system through ambient light testing with two 550 nm and 450 nm LD light sources and Pin photodetector over 10 meters using Opti System software. The system uses Non-Return-to-Zero On-Off Keying (NRZ OOK) also known as Amplitude Shift Keying (ASK) modulation through Mach-Zehnder Modulator with WDM technology in NLOS environment. A 10 Gbps data transmission occurs through the clear ocean environment along a 10-meter channel with 0.0405 1/m absorption and 0.0025 1/m scattering. The 550 nm transmitted source emits its maximum Quality factor as 8.35 when BER analyzers operate under ambient light conditions and produce its minimum BER as 4.89e-11 under the same conditions. Examining similar ambient light influences reveals the BER analyzers demonstrate a maximum Quality factor of 8.62 and minimum BER of 18.11e-12 when operating under 450 nm transmitted light. © The Institution of engineering & Technology 2025.

关键词： Amplitude shift keying

来源：评论

学校读者我要写书评

暂无评论

Novel System based on Amalgamation of Embedded Systems and Edge AI for Hand Gesture Recognition 2024

Novel System based on Amalgamation of Embedded Systems and E...

引用

16th International Conference on Contemporary Computing, IC3 2024

作者： Singh, Gargi Gautam, Saanika Puri, Yugnanda Parikh, Jolly Mishra, Gargi Department of Electronics and Communication Engineering Bharati Vidyapeeth's College of Engineering New Delhi India Department of Computer Science and Engineering Bharati Vidyapeeth's College of Engineering New Delhi India

ISBN: (纸本)9798400709722

Hand gesture recognition is highly significant and a natural means of human-computer interaction. This detection is carried out by using the MPU- 6050 sensor, a widely available Inertial Measurement Unit (IMU). MPU-6050 sensor measures the orientation and objects acceleration and is a low-cost, high-performance sensor. NanoEdgeAI studio, a low-power edge computing framework known to process data efficiently, has been employed to implement the accurate machine learning model. In addition to that, the usage of a microprocessor, Nucleo-F401RE, demonstrates the feasibility of deploying robust and responsive hand gesture recognition systems in edge computing scenarios, showcasing the potential for enhanced human-machine interaction. The selected model used for the research is MLP (multilayer perceptron) which is also known for its flexibility and ability. A balanced accuracy a percentage measure of signals correctly identified by the model was found out to be of 84.27%. © 2024 Copyright held by the owner/author(s).

关键词： Embedded systems

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：