检索结果-内蒙古大学图书馆

7th International Conference on Intelligent computing and Control Systems, ICICCS 2023

作者： Sharmili, K.C. Suja, G.P. Pandian, E. Walid, Md. Abul Ala Arunachalam, Sripriya Babu, G.Charles Computer Science Stella Maris College 17 Cathedral Road Chennai India Computer Science Muslim Arts College Thiruvithancode629174 India Sri Muthukumaran Institute of Technology Mangadu Master of Computer Application Chennai69 India Department of Computer Science and Engineering Khulna9203 Bangladesh Computer Applications-PG School of Computing Sciences VELS Institute of Science Technology & Advanced Studies - VISTAS Velan Nagar P.V. Vaithiyalingam Road Pallavaram Chennai600 117 India GRIET Department of Computer Science and Engineering Hyderabad India

ISBN: (纸本)9798350397253

In recent years, Alzheimer's disease has become a major health concern. Over 45 million individuals worldwide suffer from this illness. Alzheimer's disease is a neurodegenerative illness of unidentified etiology and process that causes cognitive deterioration, and it mostly affects the elderly. Dementia, the gradual and irreversible loss of brain cells, is the leading cause of Alzheimer's disease. Those with this illness lost the ability to think, read, and do other basic tasks. A machine learning system may aid in this situation by making accurate predictions about the onset of illness. Dementia diagnosis in a broad patient population is the major objective. This research presents the findings and analysis of many Machine Learning models for identifying dementia. To alleviate this obstacle and help in the diagnosis of AD will create a deep-learning architecture that uses stacked auto-encoders and a softmax output layer. The proposed technique can analyze numerous classes in a single setting, unlike earlier procedures, and only needs a small number of labeled training samples and basic domain expertise to get started. In the present studies, a substantial improvement in performance when it came to classifying all diagnostic subgroups. Using the proposed technique can run these time series through a Convolutional Neural Network (CNN) and ResNet50 model to extract the distinguishing patterns across stages. With an F1-score of 0.99 and an accuracy of 99.91 percent, the CNN-based technique outperformed the standard feature-based classifiers by a significant margin. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Detecting entanglement of quantum channels

引用

Communications in Theoretical Physics 2021年第11期73卷 77-84页

作者： Chaojian Li Bang-Hai Wang Bujiao Wu Xiao Yuan School of Computer Science and Technology Guangdong University of TechnologyGuangzhou 510006China Advanced Institute of Information Technology Peking UniversityChina Center on Frontiers of Computing Studies Department of Computer SciencePeking UniversityBeijing 100871China

Entanglement is the crucial resource for different quantum information processing *** conventional studies focus on the entanglement of bipartite or multipartite quantum states,recent works have extended the scenario to the entanglement of quantum channels,an operational quantification of the channel entanglement manipulation *** on the recently proposed channel entanglement resource framework,here we study a further task of resource detection—witnessing entanglement of quantum *** first introduce the general framework and show how channel entanglement detection is related to the Choi state of the channel,enabling channel entanglement detection via conventional state entanglement detection *** also consider entanglement of multipartite quantum channels and use the stabilizer formalism to construct entanglement witnesses for circuits consisting of controlled-Z *** study the effectiveness of the proposed detection methods and compare their performance for several typical *** work paves the way for systematic theoretical studies of channel entanglement and practical benchmarking of noisy intermediate scaled quantum devices.

关键词： quantum entanglement quantum channel entanglement detection entanglement witness

来源：评论

学校读者我要写书评

暂无评论

IOT Based Health Tracking Shoe for Elderly People Using Gait Monitoring System 7

IOT Based Health Tracking Shoe for Elderly People Using Gait...

引用

7th International Conference on advanced computing and Communication Systems, ICACCS 2021

作者： Jose Reena, K. Parameswari, R. Vels Institute of Science Technology Advanced Studies School of Computing Science Department of Computer Science Chennai India

ISBN: (纸本)9781665405201

Modern Technology increases the economic needs of each person in their machine life. This Machine life reduces the time to take care of their elderly parents in the real world. This paper proposed techniques to monitor and track their elderly parents from their shoe embedded with sensors. Proposed Techniques that track their gait structure and blood pressure, heart rate, and information passed to the responsible person of the elderly parents through SMS. This Paper consists of strategies to implement the gait monitoring system through the wireless sensor with a mobile application using the GSM Sim module. © 2021 IEEE.

关键词： Blood pressure

来源：评论

学校读者我要写书评

暂无评论

Fidelity and diversity metrics for validating hierarchical synthetic data: Application to residential energy demand

Fidelity and diversity metrics for validating hierarchical s...

引用

2022 IEEE International Conference on Big Data, Big Data 2022

作者： Thorve, Swapna Vullikanti, Anil Mortveit, Henning S Swarup, Samarth Marathe, Madhav V. Department of Computer Science Biocomplexity Institute University of Virginia United States Department of Engineering Systems and Environment Biocomplexity Institute University of Virginia United States Network Systems Science and Advanced Computing Biocomplexity Institute University of Virginia United States

ISBN: (纸本)9781665480451

Synthetic data is gaining rapid importance in many application domains due to privacy issues, bias, lack, or simply unavailability of real data. It is important that the synthetic data be a good representation of real data for successfully completing the task at hand. Thus, devising characteristic validation metrics is crucial and remains an open problem in many domains (e.g., image generation). Good validation metrics must be able to disentangle the differences between the quality and the variability coverage of the synthetic data. We propose to use a 3-dimensional metric (precision α, recall β, coverage γ) to describe the fidelity and diversity of the synthetic data. In this paper, we improve on existing definitions of precision, recall, and coverage to extend to large scale time series data. Traditional nearest neighbor manifolds from the literature are replaced by unsupervised learning techniques such as clustering to deal with large scale fine resolution time series while computing the validation metrics. The proposed metrics are employed to validate synthetic data in the domain of residential energy demand. In addition, we extend these definitions to datasets that have a natural hierarchical structure. We propose a hierarchical data-tree model in which precision, recall, and coverage can be computed at multiple inherent (and/or custom) levels of groupings of the data. © 2022 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Meta Learning Gradient Boosted Neural Network Model Based Diabetes Risk Prediction with Bias Reduction Using OCT Image Attributes 6

Meta Learning Gradient Boosted Neural Network Model Based Di...

引用

6th IEEE International Conference on Communication and Electronics Systems, ICCES 2021

作者： Vidhyasree, M. Parameswari, R. School of Computing Science Vels Institute of Science Technology and Advanced Studies Department of Computer Science Chennai India

ISBN: (纸本)9781665435871

Ensemble learning is defined as technique used to combine feeble techniques to develop a robust technique to maximize the algorithm efficiency. Ensemble boosting technique is combined with neural network to improve the prediction accuracy. The combined technique is optimized with fine-tuned hyper parameters, and it is cross validated to avoid overfitting. Neural network is defined as the technique used to imitate human memory that consists of number of perceptrons to accept input data from user. Input layer consists of number of input nodes based on input data given by user. The weight calculation and parameter calculation are performed in hidden layer. The output layer consists of output nodes to display the required output. This work consists of OCT retinal parameters of Myopic, CSR and normal data of to predict diabetic risk. This work discusses about optimized and cross validated gradient boosted neural network with 98% prediction accuracy. © 2021 IEEE.

关键词： Input output programs

来源：评论

学校读者我要写书评

暂无评论

Adaptive energy-preserving algorithms for guiding center system

引用

Plasma science and Technology 2023年第4期25卷 11-22页

作者：朱贝贝刘健张嘉炜祝爱卿唐贻发 Department of Applied Mathematics School of Mathematics and PhysicsUniversity of Science and Technology BeijingBeijing 100083Peopleʼs Republic of China School of Nuclear Science and Technology University of Science and Technology of ChinaHefei 230026Peopleʼs Republic of China Advanced algorithm Joint Lab Shandong Computer Science CenterQilu University of TechnologyJinan 250014Peopleʼs Republic of China The State Key Laboratory of Scientific and Engineering Computing The Institute of Computational Mathematics and Scientific/Engineering ComputingAcademy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190Peopleʼs Republic of China School of Mathematical Sciences University of Chinese Academy of SciencesBeijing 100049Peopleʼs Republic of China

We develop two types of adaptive energy preserving algorithms based on the averaged vector field for the guiding center dynamics,which plays a key role in magnetized *** adaptive scheme is applied to the Gauss Legendre’s quadrature rules and time stepsize respectively to overcome the energy drift problem in traditional energy-preserving *** new adaptive algorithms are second order,and their algebraic order is carefully *** results show that the global energy errors are bounded to the machine precision over long time using these adaptive algorithms without massive extra computation cost.

关键词： guiding center system energy-preserving methods adaptive energy conservation

来源：评论

学校读者我要写书评

暂无评论

Improving Energy Efficiency using Colliding Bodies Optimization based Routing Protocol for Wireless Sensor Networks 2

Improving Energy Efficiency using Colliding Bodies Optimizat...

引用

2nd International Conference on Electronics and Renewable Systems, ICEARS 2023

作者： Prabakaran, P. Shalini, R. Hariharan, N. Marieswari, S. Kumar, Kallakunta Ravi Apoorva, Maturi Gayatri Lakshmi Vels Institute of Science Technology and Advanced Studies School of Computing Sciences Department of Computer Applications Chennai India Vels Institute of Science Technology and Advanced Studies School of Computing Sciences Department of Bca and It Chennai India R.M.K. College of Engineering and Technology Science and Humanities - Eee Thiruvallur601206 India P. S. R. Engineering College Biomedical Engineering India Koneru Lakshmaiah Education Foundation Department of Ece Vaddeswaram India Amrita School of Engineering Ece Department India

ISBN: (纸本)9798350346640

Wireless sensor network (WSN) contains millions of small, low-power gadgets with a lack of resources are memory and battery power. Such gadgets were deployed in a dispersed manner and were often utilized to monitor and sense applications. Owing to constraints and limited resources of WSNs, routing can be a great difficulty. Routing in WSN was the process of choosing the optimal path for data to travel from a source node to a destination node. The goal of routing in WSN offer dependable and effective transmission while minimizing network overhead and energy consumption. This study designs an Energy Efficient Colliding Bodies Optimization based Routing Protocol (EECBO-RP) for WSN. The end goal of the EECBO-RP algorithm lies in the optimal election of routes to a destination. For achieving reasonable results for the minimization of energy exploitation, the EECBO-RP system derives the fitness function using the following variables: residual energy, distance to BS, and node degree. The EECBO-RP technique chooses the relay nodes so that a way that the overall efficiency of the WSN gets maximized. The simulation values of the EECBO-RP system are tested under several dimensions and the outcomes pointed out the betterment of the EECBO-RP technique. © 2023 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Early detection of DR with an Effective Optimal Stochastic Deep Network in fundus images using the Monte Carlo Method

Early detection of DR with an Effective Optimal Stochastic D...

引用

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

作者： B Padmini Y Kalpana Department of Computer Science School of Computing Sciences Vels Institute of Science Technology and Advanced studies (VISTAS) Chennai TamilNadu India Department of Computer Application School of Computing Sciences Vels Institute of Science Technology and Advanced studies (VISTAS) Chennai TamilNadu India

ISBN: (数字)9798350317060

ISBN: (纸本)9798350317077

Diabetes mellitus often causes diabetic retinopathy (DR), which damages the retina and makes it hard to see. If it is forced to treat, the possibility of losing sight is much less likely. It can cause hallucinations if not diagnosed early. Manually examining DR retina fundus pictures is a time-consuming, labor-intensive process that is also prone to error for ophthalmologists, making it preferable to CAD technology. Deep learning (DL) has notably become one of the most prominent ways to improve effectiveness, especially when it comes to putting clinical data into categories and evaluating them. On the other hand, reliability limits the incorporation of DL into real-world medical processes since traditional DL frameworks cannot objectively evaluate model uncertainty. The Enriched Squawk Optimization Algorithm (ESOA) is utilized to fine-tune the hyperparameters of SDNMC and is referred to as OSDNMC in this study. This method, which can estimate uncertainties to assess tumor image classification reliability, is proposed as a solution to this problem. This model analyses the concept using fundus image datasets collected with the customized device from high-risk populations to demonstrate that actionable uncertainty information may be generated. The tests also demonstrate better accuracy using uncertainty-informed recommendations. By employing color fundus images and the OSDNMC technique, our work was able to classify DR automatically with 96.5% accuracy on our dataset, exceeding findings from more traditional methods like Ar-HGSO, CNN, and DCNN.

关键词： Solid modeling Uncertainty Monte Carlo methods Sociology Stochastic processes Retina Reliability

来源：评论

学校读者我要写书评

暂无评论

TPU-Accelerated Deep Learning for Accurate Satellite Land Classification

TPU-Accelerated Deep Learning for Accurate Satellite Land Cl...

引用

3rd International Conference on Machine Learning and Data Engineering, ICMLDE 2024

作者： Babu, Tina Nair, Rekha R. Kishore, S. Department of Computer Science and Engineering School of Advanced Computing Alliance University Bengaluru India Nitte Institute of Professional Education Karnataka Mangalore India

Tensor Processing Units (TPUs) offer significant computational advantages for deep learning tasks, particularly in processing high-dimensional satellite imagery. This study presents a systematic approach to land classification using Convolutional Neural Networks (ConvNets) accelerated by TPUs. The implemented ConvNet architecture achieved 94.5% classification accuracy across ten land cover categories, outperforming traditional machine learning methods by 6-9% and standard CNN implementations by 4%. The model demonstrated high precision (93.8%), recall (94.2%), and F1-score (94.0%) across diverse land cover types, with particularly strong performance in identifying water bodies (95.1% F1-score) and forest regions (94.9% F1-score). Through ex- tensive hyperparameter optimization enabled by TPU acceleration, training time was reduced by 60% compared to GPU-based implementations. The study utilized a dataset of 27,000 labeled satellite images across 10 land cover categories, with robust validation through 5-fold cross-validation. The improved performance and computational efficiency demonstrate the viability of TPU-accelerated deep learning for large-scale geospatial analysis applications. © 2025 The Author(s).

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Cloud-Enabled Predictive Vehicle Health Monitoring and Maintenance with LSTM Networks for Time-Series Analysis 1

Cloud-Enabled Predictive Vehicle Health Monitoring and Maint...

引用

1st International Conference on Innovations in Communications, Electrical and computer Engineering, ICICEC 2024

作者： Vinya, Viyyapu Lokeshwari Manivannan, K.K. Manivannan, S.K. Sathiyamoorthy, C. Jagadeeswaran, M. Meenakshi, B. SRM Institute of Science and Technology Department of Computing Technologies School of Computing Kattankulathur Tamil Nadu Chennai India Easwari Engineering College Department of Electrical and Electronics Engineering Tamil Nadu Chennai India Vit Bhopal University Department of Physics School of Advanced Sciences and Languages Madhya Pradesh Bhopal India J.J College of Engineering and Technology Department of Information Technology Tamil Nadu Tiruchirappalli India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Saveetha University Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Saveetha School of Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350376517

Maximizing operational efficiency and customer satisfaction in the automobile sector depends on maintaining vehicle health and avoiding maintenance downtime. Vehicle Internet of Things (IoT) devices capture massive volumes of sensor data, enabling predictive maintenance. This research offers cloud-based predictive vehicle health monitoring and maintenance systems using Long Short-Term Memory (LSTM) networks for time-series analysis. System architecture uses IoT sensors in automobiles to gather real-time data on engine temperature, oil pressure, and vibration. This data is stored, analyzed, and predicted on clouds. To assess time-series sensor data and forecast failures or maintenance requirements, LSTM networks, a form of recurrent neural network, are used. The proposed system uses data preprocessing to manage missing values and outliers, feature extraction to find significant sensor data patterns, and LSTM-based predictive modeling to predict vehicle health conditions. Technology may predict future faults by continually monitoring and evaluating the vehicle's state, allowing proactive maintenance to avoid expensive breakdowns and downtime. The cloud-based architecture is scalable and flexible, providing smooth connection with fleet management systems and remote vehicle health monitoring across scattered sites. The suggested method optimizes maintenance schedules and resource allocation using predictive insights from real-time sensor data to improve operational efficiency and save costs. It may improve predictive vehicle health monitoring and maintenance in the automobile sector, improving dependability, safety, and cost. © 2024 IEEE.

关键词： Customer satisfaction

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：