检索结果-内蒙古大学图书馆

5th International Conference on Data Intelligence and Cognitive informatics, ICDICI 2024

作者： Kaviya, R. Prasad, Mridula Pavithra, S. Kapali, B. Suresh Chander Vellore Institute of Technology School of Computer Science and Engineering Chennai India Easwari Engineering College Department of Biomedical Engineering Chennai India

ISBN: (纸本)9798350389609

Ureteropelvic junction obstruction (UPJO) is a medical condition characterized by a blockage at the junction between the ureter and the kidney, leading to impaired urine flow and increased fluid pressure. If left untreated, UPJO can progress to hydronephrosis and potentially result in irreversible kidney damage. This paper presents a novel system for the early detection and severity grading of UPJO using Deep Learning computer-Aided Diagnosis (DL-CAD) techniques. The proposed approach leverages ultrasound imaging as a primary diagnostic tool, noted for its cost-effectiveness, absence of radiation, and non-invasive nature. To enhance the security and integrity of medical data transmission, we integrate blockchain technology into our framework. Our solution combines a DL- CAD model featuring an attention-based pyramid semantic segmentation network with a discrete wavelet transformation- processed residual classification network. An IoT device is employed to detect patient abnormalities and transmit this data to the diagnosis model via an InterPlanetary File System (IPFS). This decentralized storage solution facilitates secure data management across a peer-to-peer network. Ultimately, the proposed framework not only identifies the presence of UPJO but also assesses its severity, ensuring that patient data remains protected throughout the diagnostic process. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Machine Learning Models for Diabetes Prediction 13

Comparative Analysis of Machine Learning Models for Diabetes...

引用

13th International Conference on System Modeling and Advancement in Research Trends, SMART 2024

作者： Shukla, Anshita Kumar, Rahul Chole, Vikrant Moolchandani, Jhankar Sahu, Santosh Kumar, Ashok Amity School of Engineering and Technology Amity University Department of Computer Science and Engineering Madhya Pradesh Gwalior India

ISBN: (纸本)9798350380583

This paper aims at comparing performance of various machine learning models for the task of predicting diabetes using one of the public datasets. The research assesses the big data analysis in the determination of the possibilities of risk of diabetes and the preferred models of Logistic Regression and KNearest Neighbors (KNN). Performance measures including accuracy, precision and recall were used in assessing the performance of the two models. The study do reveals the high level of potential of both the models yet reveals that Logistic Regression just edges a bit ahead of KNN in terms of accuracy and precision. These results show the potential of using machine learning in hospital diagnosis and specifically in diagnosis of Chronic diseases such as diabetics. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Deep Spectral Learning Features in an Adaptive Dense Net Convolution Neural Network for Macular Degeneration

Deep Spectral Learning Features in an Adaptive Dense Net Con...

引用

2024 IEEE International Conference on Electronic Systems and Intelligent Computing, ICESIC 2024

作者： Mahalakshmi, D. John Justin Thangaraj, S. Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331522988

Age-related macular degeneration (AMD) and diabetic retinopathy (DR) are vision-impairing ocular disorders that impact the elderly. The macula is a special area of the retina at the center of vision. In serious situations, emergency care is needed and the treatment regimen will vary with a case-to-case basis. Deep convolutional neural networks are proposed here to automate the fast classification of dry and wet Age-related Macular Degeneration (AMD). We leverage convolutional neural networks (CNN) spectrum learning capabilities, to introduce a novel approach to detect age-related macular degeneration (ARMD). The treatment should be guided by the precise differentiation between dry and moist types. to present an ADCNN-invasive spectral learning feature. Deep neural networks performance results reveal that dry vision loss can be identified with high precision, but not wet visual impairment. Afterward, by means of a dense net layer features are selected and tune before being operated into a deep neural network. The objective of this research is to define the type of transfer learning used for assessing at-risk individuals, specifically with structural analysis from deep convolutional neural networks. The model represent an authentication of 99.56%, a uniqueness and sensitivity of 98.51% in the AMD database indicating that deep learning is a well-suited approach for intelligent health monitoring. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

EnCR-XGBoost: Ensemble Convolutional Recurrent Based XGBoost for Autism Detection Using MRI 9

EnCR-XGBoost: Ensemble Convolutional Recurrent Based XGBoost...

引用

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Balasubramani, Jagadesh Surendran, R. Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350377972

The Autism detection is crucial for enhancing the social behavior and interaction of the people because the autism is a complex neurodevelopmental disorder. The deep learning based autism detection is employed for obtaining the accurate detection of disease. Still, inaccurate detection, computation complexity and over-fitting issues limit the performance. Thus, deep learning based autism detection is introduced in this research for solving the issues faced by the existing models. The input obtained from the MRI image is pre-processed using the median filter to enhance the quality of the image. Then, the appropriate features are extracted using proposed Ensemble Convolutional Recurrent (EnCR) model designed with the ensemble of convolutional and recurrent model for extracting both spatial and temporal features for enhancing the detection accuracy. Finally, XGBoost method is utilized for performing the autism detection task using the EnCR based features. The designed EnCR+XGBoost model is evaluated based on Accuracy, Precision, Recall, and F-score and obtained the values of 98.1500,98.4320,98.0320, and 98.2316 respectively. © 2024 IEEE.

关键词： Median filters

来源：评论

学校读者我要写书评

暂无评论

Non-Contact Vital Prediction Using rPPG Signals 1

Non-Contact Vital Prediction Using rPPG Signals

引用

1st IEEE International Conference on Contemporary Computing and Communications, InC4 2023

作者： Madhu, Meghna Gurudas, V.R. Manjunath, Chinthakunta Naik, Praveen Kulkarni, Praveen School of Engineering and Technology Department of Computer Science and Engineering Bangalore India Dayananda Sagar University Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350335774

In this paper, we present the clinical significance of various cardiac symptoms with the use of heart rate detection, ongoing monitoring and present emotions. The development of algorithms for remote photoplethysmography has drawn a lot of interest during the past decade (rPPG). As a result, using data gathered from the video feed, we can now precisely follow the heart rate of individuals who are still seated. rPPG algorithms have also been developed, in addition to technique based on hand-crafted characteristics. Deep learning techniques often need a lot of data to train on, but biomedical data frequently lacks real-world examples. The experiment described in this work, we looked at how illumination affected the rPPG signals' SNR. The findings show that the SNR in each RGB channel varies depending on the colour of the light source. Paper describes development in video filtering for recognising the comprehending human face emotions. In our method, emotions are deduced by identifying facial landmarks and analysing their placement. © 2023 IEEE.

关键词： Photoplethysmography

来源：评论

学校读者我要写书评

暂无评论

A Review of Deep Convolutional Neural Networks in Mobile Face Recognition

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2023年第23期17卷 4-19页

作者： Chi, Jing On, Chin Kim Zhang, Haopeng Chai, Soo See Faculty of Computing and Informatics University Malaysia Sabah Sabah Malaysia School Information and Electrical Engineering Hebei University of Engineering Hebei China Faculty of Computer Science and Information Technology Universiti Malaysia Sarawak Sarawak Malaysia

With the emergence of deep learning, Convolutional Neural Network (CNN) models have been proposed to advance the progress of various applications, including face recognition, object detection, pattern recognition, and number plate recognition. The utilization of CNNs in these areas has considerably improved security and surveillance capabilities by providing automated recognition solutions, such as traffic surveillance, access control devices, biometric security systems, and attendance systems. However, there is still room for improvement in this field. This paper discusses several classic CNN models, such as LeNet-5, AlexNet, VGGNet, GoogLeNet, and ResNet, as well as lightweight models for mobile-based applications, such as MobileNet, ShuffleNet, and EfficientNet. Additionally, deep CNN-based face recognition models, such as DeepFace, DeepID, FaceNet, and SphereFace, are explored, along with their architectural characteristics, advantages, disadvantages, and recognition accuracy. The results indicate that many scholars are researching lightweight face recognition, but applying it to mobile devices is impractical due to high computational costs. Furthermore, noise label learning is not robust in actual scenarios, and unlabeled face learning is expensive in manual labeling. Finally, this paper concludes with a discussion of the current problems faced by face recognition technology and its potential future directions for development. © 2023 by the authors of this article. Published under CC-BY. All Rights Reserved.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Predicting Student Academic Performance using Machine Learning: Analyzing Socio-Economic and Personal Factors from Secondary Education in Portugal 4

Predicting Student Academic Performance using Machine Learni...

引用

4th International Conference on Technological Advancements in Computational Sciences, ICTACS 2024

作者： Sahu, Santosh Kumar, Ashok Kumar, Rahul Shukla, Anshita Chole, Vikrant Moolchandani, Jhankar Amity School of Engineering and Technology Amity University Department of Computer Science and Engineering Madhya Pradesh Gwalior India

ISBN: (纸本)9798350387490

This paper aims to predict student academic performance using machine learning algorithms by analyzing socioeconomic and personal factors from secondary education in Portugal. The study utilizes a dataset containing demographics, family background, educational support, extra-curricular activities, and academic records to evaluate their impact on students' success in Mathematics and Portuguese courses. Machine learning models such as Logistic Regression, Decision Trees, and Random Forests were employed to analyze the data. The Random Forest model outperformed others with an accuracy of 85 %, indicating significant potential in predicting student performance using the selected features. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Real-Time Monitoring and Optimization of Recycled Water Irrigation in Coffee Plantations using Bi-directional RNNs and IoT Sensors

Real-Time Monitoring and Optimization of Recycled Water Irri...

引用

2024 International Conference on Innovation and Intelligence for informatics, Computing, and Technologies, 3ICT 2024

作者： Raveena, S. Surendran, R. Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India

ISBN: (数字)9798331533137

ISBN: (纸本)9798331533137

The coffee firms relies heavily on sustainable water management measures due to water scarcity. Present study investigates the utilization of Bi-directional Recurrent Neural Networks (Bi-directional RNNs) combined with Internet of Things (IoT) sensors to monitor and optimize the irrigation of reclaimed water in coffee plants in real-time. The suggested system utilizes a range of IoT sensors to gather up-to-the-minute information on soil moisture, temperature, humidity, pH value, nutrient value, water quality, and potentially weather conditions. Data collected is transmitted through the IoT Lora WAN wireless network, which facilitates long-distance communication for plantations. Bi-directional recurrent neural networks (RNNs) examine the sequential sensor data to detect temporal relationships and determine the best watering schedules and possible irregularities. The proposed model suggests modifications accuracy of 95.66% to irrigation practices based use of water in a more effective manner. ©2024 IEEE.

关键词： Soil moisture

来源：评论

学校读者我要写书评

暂无评论

The OCPT Mechanism: An Innovative Methodology to Erect the Language Understanding to Build the Enhanced STT Model 4

The OCPT Mechanism: An Innovative Methodology to Erect the L...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Saranya, V. Devi, T. Deepa, N. Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331529635

Generative Pretrained Transformers (GPT) predict the sequence of words when building the language model in speech recognition. The traditional model inherits the high range biases during training the data, this issue leads to inappropriate outputs, the proposed research, the Optimized Constructive Pretrained Transformers(OCPT) mechanism emphasizes tuning GPT models specific to domain language modeling, accentuating the value of an organized approach that involves data preprocessing, model initialization, fine-tuning, and assessment. This model helps to build a more efficient and effective Speech-to-text model. The model obtained 97.12% accuracy on the validation set, compared with the AuGPT model which produces 91% accuracy, indicating the proposed model's ability to understand and generate contextually relevant text. During the training phase, the model was hyperparameter-tuned to improve performance metrics including learning rate, batch size, and training epochs. The Adam optimizer was important in accurately adjusting the model parameters to ensure convergence and stability. To avoid overfitting and ensure the model's generalizability, accuracy, and loss have been evaluated throughout the training and validation phases. The findings assessed the model's learning trajectories and performance indicators, demonstrating its efficacy. © 2024 IEEE.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of IoT and Blockchain Technologies in Enhancing Security and Efficiency in Healthcare Systems 4

Comparative Analysis of IoT and Blockchain Technologies in E...

引用

4th International Conference on Technological Advancements in Computational Sciences, ICTACS 2024

作者： Kumar, Ashok Shukla, Anshita Thada, Vikas Chole, Vikrant Moolchandani, Jhankar Sahu, Santosh Amity School of Engineering and Technology Amity University Department of Computer Science and Engineering Madhya Pradesh Gwalior India

ISBN: (纸本)9798350387490

This paper presents an extensive comparison of the IoT and blockchain technologies in the improvement of security, privacy, and interoperability, as well as energy efficiency in healthcare systems. This is because IoT allows for constant tracking and gathering of data from medical devices and this enhances the welfare of the patients as well as the management of the health facilities. However, this has exposed the Internet of Things (loT) technology with multiple risks in data security and privacy since it uses wireless communication and has limited computational power. Such issues can be addressed through the use of blockchain technology because of its distributed and tamper proof ledger. This research work presents a case of how the integration of IoT with blockchain will lead to a middle of the two worlds, where IoT will be useful for handling real time data while blockchain will handle the issue of security. The study concludes that the integration of blockchains with the IoT offers superior results than the individual implementations in several aspects, thus offering a more secure, efficient, and interoperable environment for today's healthcare applications. Possible future work includes improving the integration of these technologies to minimize the energy consumption, improve the scalability of the system and establish feasible implementation models in actual health care systems. © 2024 IEEE.

关键词：

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：