检索结果-内蒙古大学图书馆

1st International Conference on Software, Systems and Information Technology, SSITCON 2024

作者： Shankari, S. Uma Ali, Hassan Mohamed Durga, Boya Vijaya Vadivu, M. Senthil Mangaiyarkarasi, V. Srm Institute of Science and Technology Ramapuram Department of Computer Science and Applications Chennai India College of Technical Engineering the Islamic University Department of Computers Techniques Engineering Najaf Iraq Maisammaguda School of Computer Science and Engineering Hyderabad India Sona College of Technology Department of Electronics and Communication Engineering Salem India New Prince Shri Bhavani College of Engineering and Technology Department of Electronics and Communication Engineering Chennai India

ISBN: (纸本)9798350352931

Nowadays, most of the people are getting affected with various health issues such as typhoid, diabetes and cancer. A human immune system plays a crucial role in maintaining and balancing human health and reduces the risk of getting ill. Immunotherapy is a treatment which utilizes human body immunity power to fight cancer. There are many challenges in the existing models such as imbalance data, heterogenic data, uncertainties, and lack of temporal data. These challenges are resolved by imposing deep learning techniques and generating a valid information with the clinical details of patient health conditions. Therefore, a hybrid model name called Multi-Scale Feature Fusion Semantic Segmentation Network (MSSNet) and You Look Only Once (MedYOLO) for feature extraction and detection. Initially, Synthetic Minority Over-sampling Technique (SMOTE) is employed to overcome the issue of imbalanced data;further MSSNet is imposed for extracting the optimal features and detected using MedYOLO. Also, to get detailed information and generate cohort, the data collected from GSC hospital with overall details that are essential to predict the patient response to immunotherapy in cancer treatment. In the end, MSSNet-MedYOLO obtained higher accuracy of 98.16% for an effective prediction of patient response which is better than existing Convolutional Neural Network (CNN). © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Reliable Smart Wrist Pulse Oximeter for Hypoxemia and COVID-19 Patients 8th

Reliable Smart Wrist Pulse Oximeter for Hypoxemia and COVID-...

引用

8th International Conference on Inventive communication and Computational Technologies, ICICCT 2024

作者： Ramamoorthy, Raghu Smitha, J.A. Velu, Anitha Department of Computer Science and Engineering The Oxford College of Engineering Karnataka Bengaluru India Department of Computer and Engineering Sri Sairam College of Engineering Karnataka Bengaluru India Department of Electronics and Communication Engineering Sri Sairam College of Engineering Karnataka Bengaluru India

ISBN: (纸本)9789819777099

In the present day, the people are living with the COVID-19. The catastrophic virus of COVID-19 causes hypoxemia (shortness of breath), sometimes even severe cases. Hypoxemia is caused due to low oxygen saturation (SpO2) levels and to monitor SpO2 levels this work proposes a reliable smart wrist pulse oximeter. Patients who are diagnosed during the early stages of the virus are able to monitor their SpO2 levels at home and take the prescribed medicines. Oximetry follows the principle of light reflection. The fingertip model is the most common technique used to display the blood oxygenation level. However, the finger model is not as comfortable and does not promote continuous monitoring of SpO2 levels. Factors such as nail polish can play a role in the accuracy of the reading. The proposed design is a non-invasive medical device that can measure the oxygen saturation level in a person’s blood. The wrist wearable devices are more convenient for continuous monitoring of oxygen saturation levels than finger models. Most devices in application today are inaccurate and used for non-clinical use. Therefore, it is aimed to achieve better accuracy by avoiding readings that are influenced by factors such as motion artifacts by utilizing sensors that are appropriate through an accelerometer and gyroscope. The proposed oximeter can initiate notifications to alert an individual of the levels of oxygen saturation, fall detection, and heart rate levels. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Oximeters

来源：评论

学校读者我要写书评

暂无评论

Land Cover Segmentation for Agricultural Monitoring Using Synthetic Aperture Radar (SAR) Imagery with Convolutional Neural Networks and Attention-Based Transformer Models

Land Cover Segmentation for Agricultural Monitoring Using Sy...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Prakash, E.P. Sathiya, K.G. Manoranjitham, S. Sekar, G. Munaf, S. Santhia, R.K. Dr. N.G.P. Institute of Technology Department of Computer Science and Engineering Coimbatore641048 India Arunai Engineering College Department of Electronics and Communication Engineering Tiruvannamalai606604 India Agni college of Technology Department of Information Technology Chennai600130 India Vsb College Of Engineering Department of Electronics and Communication Engineering Technical Campus Coimbatore642109 India Sri Ramakrishna Institute of Technology Department of Electronics and Communication Engineering Coimbatore641010 India Pondicherry University Department of Computer Science and Engineering 605014 India

ISBN: (纸本)9798331509828

Automated classification of land cover types is one of the most crucial aspects within many remote sensing applications, including the monitoring of agricultural land and territories. This work proposes a novel approach for division of land covers using a hybrid of CNNs and Attention-based Transformer networks. CNNs are adopted to extract the spatial features from different levels of the SAR image, while Transformer Model Arch applies self-attention functions to explore the long-range dependency and contextual relation of the entire image. The model learning process is performed end-to-end from multi-temporal SAR data to differentiate different types of land covers, including crops, vegetation, water, and urban surfaces. In this case, we apply the proposed approach to different agricultural areas to show that it outperforms traditional methods, such as thresholding and other machine learning approaches. The results highlight the viability of this mixed form to solve the noise and changeable nature of SAR imagery, in terms of enhancing the use of the agricultural monitoring application. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Emotion-driven Activity Detection: Detecting Activities Perception through Facial Feature Analysis in Educational Environments 18

Emotion-driven Activity Detection: Detecting Activities Perc...

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Balasubramanian, K. Mariadass, Emmanuel Peo Akalya, L. Cinthuja, K. Murali, N. Rajangam, Balamurugan E. G. S. Pillay Engineering College Department of Computer Science and Engineering Nagapattinam India Panimalar Engineering College Department of Computer Science and Engineering Chennai India K. Ramakrishnan College of Engineering Department of Electronics and Communication Engineering Trichy India

ISBN: (纸本)9789380544519

Understanding and categorizing student activities within educational settings is a critical component of enhancing learning outcomes and well-being. This study introduces an innovative approach to student activity classification by leveraging facial emotion recognition technology. The system is designed to capture and analyze students' facial expressions, interpret their emotional states, and subsequently categorize their activities. By deploying a dataset encompassing a wide range of academic and non - academic activities, this research explores the purpose of deep learning models for recognition of facial emotion. The system is capable of identifying emotions such as sadness, surprise, happiness and anger. Extracted emotion features are then utilized to classify student activities, shedding light on whether a student is engaged, attentive, confused, or disinterested, among other states. This approach holds the potential to enhance educational environments by providing real-time insights into student behaviour and facilitating timely interventions to improve learning experiences and outcomes. Additionally, it opens up avenues for personalized educational support and the development of intelligent learning systems. In this paper we could implement the system to extract the facial features using Grassmann algorithm. And identify the emotions of student at predefined time intervals. Based on emotion classification, predict the active status and send reports to admin. Furthermore, this technology holds promise for the development of intelligent learning systems that adapt to students' emotional states, providing additional support or challenges when needed. For instance, a virtual tutor could adjust the difficulty of exercises based on a student's emotional responses, creating a dynamic and responsive learning experience. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Deep learning Face recognition system Features based matching Slot allocation Smart parking system

来源：评论

学校读者我要写书评

暂无评论

Leveraging Machine Learning for Enhanced SensorPowered Green IoT with Federated Learning 15

Leveraging Machine Learning for Enhanced SensorPowered Green...

引用

15th International Conference on Computing communication and Networking Technologies, ICCCNT 2024

作者： Devrani, Rekha Premkumar, R. Kumar, Shyam Vivekananda Global University Department of Computer Science & Engineering Jaipur India School of Engineering and Technology Department of Electronics and Communication Engineering Karnataka Bangalore India Arka Jain University Department of Computer Science & It Jharkhand Jamshedpur India

ISBN: (纸本)9798350370249

Federated getting to know (FL) is a gadget studying generation which allows a user to train a single model across more than one dispensed system, with none of the person systems having to transfer the statistics sets, nor the version, to a vital device for education. It allows disbursed schooling of an unmarried model throughout more than one disbursed net of things (IoT) gadgets or users. It makes it feasible to improve the accuracy and scalability of our Sensor-Powered inexperienced IoT applications. FL can consequently be instrumental in taking inexperienced IoT answers towards the character sources of environmental records, like air firstclass sensors, as opposed to amassing facts *** permits us to leverage powerful gadget learning models to enhance the accuracy and scalability of our Sensor-Powered green IoT systems. By using federated models throughout education, we will grow the accuracy of our predictions and decrease the amount of effort and time we have to acquire and store sensor facts centrally. Moreover, FL lets us improve the version overall performance of green IoT packages by dispensing schooling and predictions to a disbursed community of sensor-based totally IoT devices. We also can, in addition, reduce the reliance on central systems with the aid of transferring the middle of our Sensor-Powered inexperienced IoT packages from the cloud to allotted nodes. © 2024 IEEE.

关键词： Generation Predictions Scalability Sensor Statistics Throughout Unmarried

来源：评论

学校读者我要写书评

暂无评论

Modeling of metaheuristic-based dual cluster head selection with routing protocol for energy-efficient wireless sensor networks

引用

Soft Computing 2025年第6期29卷 2999-3020页

作者： Reddy, Maddikera Krishna Veluswamy, Anusha Sowbarnika Selvanayaki, S. Harini, C. Kumar, Pavan Shameem, Syed Department of Electronics and Communication Engineering Rajeev Gandhi Memorial College of Engineering and Technology Andhra Pradesh Nandyal India Department of Mathematics and Computer Science Susquehanna University Pennsylvania SelinsgrovePA United States Department of Artificial Intelligence and Data Science Saveetha Engineering College Chennai India Maisamma Guda Secunderabad India Department of Computer Science and Engineering Raghu Engineering College Andhra Pradesh Dakamarri Vizayanagaram India Department of ECE Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India

Wireless Sensor Networks (WSN) are decentralized networks of spatially distributed sensors that gather and monitor environmental information for various applications, including industrial automation and environmental monitoring. This enables real-time information gathering without relying upon wired connections. In WSN, clustering and routing are essential techniques for improving data transmission. Clustering comprises grouping sensor nodes (SN) into clusters to optimize energy efficacy and extend the network's lifetime. However, selecting suitable and efficient cluster head (CH) components is crucial to harness their benefits. Selecting appropriate CHs and finding optimum coefficients for all the parameters of applicable fitness function (FF) in CH selection is a non-deterministic polynomial-time (NP-hard) problem that needs additional processing. In contrast, routing focuses on defining the most effective path for data to traverse through the network, ensuring timely and reliable data delivery and reducing energy consumption. Therefore, this study proposes a new Metaheuristic-Based Dual Cluster Head Selection with Routing Protocol (MBDCHS-RP) method for energy-efficient WSNs. The MBDCHS-RP method aims to cluster the nodes and select optimum routes for transmitting information in the WSN. To achieve this, the MBDCHS-RP method follows a two-stage clustering process, including tentative CH (TCH) and final CH (FCH) selection. The MBDCHS-RP technique utilizes a cheetah optimization algorithm (COA) with FF comprising residual energy (RE) and average node distance as input parameters for the TCH selection process. In addition, the flower pollination algorithm (FPA) is used to select final CHs with multiple input parameters, namely average intra-cluster distance, RE, and average sink distance. A carnivorous plant algorithm (CPA) is employed for the optimal route selection process with two parameters, RE and distance to the base station, to enable an effective data transm

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

MULTI-FREQUENCY POLSAR IMAGE CLASSIFICATION BASED ON CROSS ATTENTION VIT

MULTI-FREQUENCY POLSAR IMAGE CLASSIFICATION BASED ON CROSS A...

引用

IET International Radar Conference 2023, IRC 2023

作者： Wang, Hongmiao Ren, Dawei Yin, Junjun Yang, Jian Departments of Electronic Engineering Tsinghua University Beijing China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China

ISBN: (纸本)9781839539954

In the land cover classification of multi-frequency Polarimetric SAR (PolSAR) images, the classification performance highly depends on the effectiveness of feature fusion. Currently, linear fusion methods are widely employed in multi-frequency PolSAR land cover classification. However, linear fusion methods do not introduce extra interactions between the features from different bands, thus failing to fully exploit the advantages of fused features. To address this issue, a feature fusion method based on cross-attention is proposed. The proposed method is based on the Vision Transformer architecture. We enhance the model's capability to extract multi-frequency fusion features by introducing additional cross-frequency feature interactions within the self-attention module. Experimental results demonstrate that using the proposed cross-attention module significantly improves the model's performance in multi-frequency PolSAR image classification without introducing extra parameters or computational costs. © The Institution of engineering & Technology 2023.

关键词： Polarimeters

来源：评论

学校读者我要写书评

暂无评论

Effectiveness of Almost Sub Frame Approach as Inter Cell Interference Management in LTE-A Macro - Pico Scenario 9

Effectiveness of Almost Sub Frame Approach as Inter Cell Int...

引用

9th IEEE International Conference for Convergence in Technology, I2CT 2024

作者： Jember, Kehali A. Abose, Tadele A. Kassahun, Ermias Madhav, T. Venu Adama Science And Technology University Department Electronics And Communication Engineering Adama Ethiopia Mettu University Department Electrical And Computer Engineering Ethiopia Gondar University Department Electrical And Computer Engineering Gondar Ethiopia

ISBN: (纸本)9798350394474

Heterogeneous networks are promising solutions for enhancing network performance of LTE-A mobile networks by deploying small cells within the area of the serving macro cells. The goal of deploying such networks is to offload data from the congested macro cells towards the small cells. However, cross tier interference is a serious issue, which is introduced due to the transmitted power difference between Macro cell node and small cell node. Hence, cell age users are mainly affected by high power interference originated from Macro node. The paper develops enhanced inter-cell interference coordination using Almost Blank Sub-Frame (ABS) to improve user throughput. This can be achieved by stopping data transmission on in certain sub frame of macro cell while Pico users are scheduled at the same frame. computer simulation results depict that the performance of Pico cell users is highly degraded, especially for cell edge users. The ABS technique improves cell edge user throughput of Pico cell by 95% and center cell user throughput by 75.25%. © 2024 IEEE.

关键词： Heterogeneous networks

来源：评论

学校读者我要写书评

暂无评论

Internet of Things (IoT) based Watercraft for Environmental Surveillance and Maintenance 5

Internet of Things (IoT) based Watercraft for Environmental ...

引用

5th International Conference on Image Processing and Capsule Networks, ICIPCN 2024

作者： Sushmitha, S. Jebaraj, Bharath Singh Vivekrabinson, K. Azarudeen, K. Priyadharshini, S. Gnanasekaran, T. Rajalakshmi Institute of Technology Department of Electronics and Communication Engineering Tamil Nadu India Kalasalingam Academy of Research and Educatuion Department of Computer Science and Engineeing Sriviliputhur India Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Tamil Nadu India Velammal College of Engineering and Technology Department of Computer Science and Engineering Madurai India R.M.K. Engineering College Department of Electronics and Communication Engineering Thiruvallur India R.M.K. Engineering College Department of Electronics and Instrumentation Engineering Thiruvallur India

ISBN: (纸本)9798350367171

Water is the topmost priority for all human and industry needs in the universe. This proposed work creates awareness about the conservation of water bodies. Here, a garbage collector is designed to clean the lake and river automatically. The client can supervise the boat from any remote place. The developed model has a live camera that uses image processing technology for detecting the garbage, and the distance between the boat and the garbage is calculated, and the cleaning of plastic and other spills will happen. The values of pH and temperature are continuously monitored and the results are displayed on the web page using IoT. The proposed prototype has been experimented with in a small swimming pool. The proposed watercraft model is made up of heavy-duty material. The movement of the model is controlled using wireless Bluetooth communication from a smartphone application. The exact values of pH and temperature are displayed on the smartphone via an application. The mobile application has switches and can be used to control the boat. © 2024 IEEE.

关键词： Boats

来源：评论

学校读者我要写书评

暂无评论

A Hyb-WGWO and Deep EMC–based Intelligent E-healthcare monitoring model for patient condition diagnosis in internet of things connected applications

引用

Research on Biomedical engineering 2023年第1期39卷 37-49页

作者： Mojjada, Ramesh Kumar Ashok Kumar, K. Tamizhselvan, C. Melingi, Sunil Babu Surender, R. RNTBCI Chennai Tamil Nadu Chengalpattu603 002 India Department of Electronics and Communication Engineering Matrusri Engineering College Hyderabad Telangana Saidabad500 059 India Department of Electronics and Communication Engineering Saveetha School of Engineering Saveetha Nagar Thandalam Tamil Nadu Chennai602 105 India Department of Electronics and Communication Engineering SRM Institute of Science and Technology Ramapuram campus Tamil Nadu Chennai500 089 India Department of Computer Science and Engineering Dhanekula Institute of Engineering and Technology Krishna District Andhra Pradesh Vijayawada521 139 India

Purpose: This manuscript proposes an IoT-based E-healthcare monitoring method for constantly monitoring the important signs of patient and diagnoses biological and behavioral changes through the technologies of smart healthcare. Method: Patient health monitoring system is used to deep learning techniques for the performance of patient categorization. Here, Hybrid whale and grey wolf optimization approach (Hyb-WGWO) is proposed to the selection of cluster head with various internet of things (IoTs) devices. These devices are utilized to sense the healthcare data into clusters form. In this, the cluster head is chosen by using the proposed Hyb-WGWO approach. Data in the cloud server are transmitted to the cluster head. Then deep ensemble multitask classification (DEMC) model is proposed for identifying patient disease conditions, such as low, normal, abnormal and critical. Results: The experimental outcomes of the proposed Hyb-WGWO-DEMC approach show 25.98% and 31.86% improved accuracy, 28.08%, 26.87% better specificity than the existing methods, such as Elliptic Decryption Algorithm in Elman Neural Network (EDA-ENN) and Grasshopper Optimization and Particle Swarm Optimization with cryptographic encryption (GOPSO-CE) respectively. Conclusion: IoT-based E-healthcare monitoring method achieves higher accuracy and lower error rate through the technologies of smart healthcare. © 2022, The Author(s), under exclusive licence to The Brazilian Society of Biomedical engineering.

关键词： Internet of things

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：