检索结果-内蒙古大学图书馆

Improving Multiple Sclerosis Disease Prediction Using Hybrid Deep Learning Model

computers, Materials & Continua 2024年第10期81卷 643-661页

作者： Stephen Ojo Moez Krichen Meznah A.Alamro Alaeddine Mihoub Gabriel Avelino Sampedro Jaroslava Kniezova Department of Electrical and Computer Engineering College of EngineeringAnderson UniversityAndersonSC 29621USA Faculty of Computing and Information Al-Baha UniversityAl-Baha65528Saudi Arabia ReDCAD Laboratory University of SfaxSfax3038Tunisia Department of Information Technology College of Computer&Information SciencePrincess Nourah Bint Abdul Rahman UniversityRiyadh11564Saudi Arabia Department of Management Information Systems College of Business and EconomicsQassim UniversityP.O.Box 6640Buraidah51452Saudi Arabia School of Management and Information Technology De La Salle-College of Saint BenildeManila1004Philippines Department of Information Management and Business Systems Faculty of ManagementComenius University BratislavaBratislava 2582005Slovakia

Myelin damage and a wide range of symptoms are caused by the immune system targeting the central nervous system in Multiple Sclerosis(MS),a chronic autoimmune neurological *** disrupts signals between the brain and body,causing symptoms including tiredness,muscle weakness,and difficulty with memory and *** methods for detecting MS are less precise and time-consuming,which is a major gap in addressing this *** gap has motivated the investigation of new methods to improve MS detection consistency and *** paper proposed a novel approach named FAD consisting of Deep Neural Network(DNN)fused with an Artificial Neural Network(ANN)to detect MS with more efficiency and accuracy,utilizing regularization and combat *** use gene expression data for MS research in the GEO GSE17048 *** dataset is preprocessed by performing encoding,standardization using min-max-scaler,and feature selection using Recursive Feature Elimination with Cross-Validation(RFECV)to optimize and refine the ***,for experimenting with the dataset,another deep-learning hybrid model is integrated with different ML models,including Random Forest(RF),Gradient Boosting(GB),XGBoost(XGB),K-Nearest Neighbors(KNN)and Decision Tree(DT).Results reveal that FAD performed exceptionally well on the dataset,which was evident with an accuracy of 96.55%and an F1-score of 96.71%.The use of the proposed FAD approach helps in achieving remarkable results with better accuracy than previous studies.

关键词： Multi Sclerosis(MS) machine learning deep learning artificial neural network healthcare

来源：评论

学校读者我要写书评

暂无评论

Energy Management System for Photovoltaic-Battery-Fuel Cell using Arduino Board and Matlab Simulink

Energy Management System for Photovoltaic-Battery-Fuel Cell ...

引用

2022 IEEE Delhi Section Conference, DELCON 2022

作者： Barhoumi, El Manaa Zghaibeh, Manaf Okonkwo, Paul C. Hasan, Najam Ul Farhani, Slah Bacha, Faouzi College of Engineering Dhofar University Electrical and Computer Engineering Department Salalah Oman College of Engineering Dhofar University Mechanical and Mechatronic Engineering Department Salalah Oman Insat University of Carthage Laboratory of Computer and Industrial Systems Tunis Tunisia Ensit University of Tunis Department of Electrical Engineering Tunis Tunisia

ISBN: (纸本)9781665458832

This paper presents the design and implementation of an energy management system (EMS) for a renewable energy system using Matlab Simulink and Arduino Mega. The proposed renewable energy system is composed of an electrolyzer, a battery, photovoltaic modules, and fuel cells. The developed energy management is implemented on the Arduino board to control the connection of the different components to the load based on the load power consumption, the battery's charge state, and the energy produced by the photovoltaic modules. The energy management system inputs include the information on the amount of energy produced by the photovoltaic modules, the power used by the load, and the battery's charge state. When the produced energy exceeds the energy used by the load and the batteries are fully charged, the system allows the electrolyzer to connect to the photovoltaic modules to produce the hydrogen. Our proposed system is based on low cost technology that intends to extend the life of the batteries and enhance the efficiency of the renewable energy system by the production and using the hydrogen. The obtained experimental results show the effectiveness of the EMS in controlling the connection of the different components. © 2022 IEEE.

关键词： Energy management systems

来源：评论

学校读者我要写书评

暂无评论

Simulation to Reality Semantic Segmentation for Humanoid Soccer Robots 10

Simulation to Reality Semantic Segmentation for Humanoid Soc...

引用

10th International Conference on Artificial Intelligence and Robotics, QICAR 2024

作者： Gholami, Amir Nazari, Ahmadreza Rashnozadeh, Fatemeh Behvarmanesh, Pegah Rahmani, Arash Ramirez-Serrano, Alejandro Department of Mechanical and Manufacturing Engineering University of Calgary CalgaryAB Canada Department of Electrical and Computer Engineering University of Calgary CalgaryAB Canada Mechatronics Research Laboratory Qazvin Islamic Azad University Qazvin Iran

ISBN: (纸本)9798350348873

Deep learning methods like semantic segmentation have gained popularity in computer vision, but challenges remain, particularly in the lack of relevant datasets, such as for humanoid soccer robots. Manually annotating these datasets for segmentation is time-consuming and error-prone. To overcome this, we utilized realistic simulation to quickly generate large datasets and corresponding masks. This paper focuses on applying the u-net architecture on low-end hardware, using a synthetic dataset for training. To evaluate the model, a real annotated dataset was created. Although our Sim-to-Real approach produced a dataset close to reality, the results were unsatisfactory. To address this, transfer learning was employed to fine-tune the network and achieve better accuracy in a real environment. ©2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Tackling the Qubit Mapping Problem with Permutation-Aware Synthesis 4

Tackling the Qubit Mapping Problem with Permutation-Aware Sy...

引用

4th IEEE International Conference on Quantum Computing and engineering, QCE 2023

作者： Liu, Ji Younis, Ed Weiden, Mathias Hovland, Paul Kubiatowicz, John Iancu, Costin Argonne National Laboratory Mathematics and Computer Science Division United States Lawrence Berkeley National Laboratory Computational Research Division United States University of California Department of Electrical Engineering and Computer Science Berkeley United States

ISBN: (纸本)9798350343236

We propose a scalable, hierarchical qubit mapping and routing algorithm that harnesses the power of circuit synthesis. First, we decompose large circuits into subcircuits small enough to be directly resynthesized. For each block, we pre-synthesize them for all permutations of its input and output qubits. Following this offline step, we employ a permutation-aware, block-based generalization of the popular SABRE mapping algorithm. This mapping step stitches together blocks by choosing an input-output permutation that minimizes intrablock gate count and required inter-block communication (SWAP and bridge gates). Our approach has a twofold advantage: 1) circuit synthesis may eliminate more two-qubit gates than other optimizing compilers;2) considering all permutations of input and output qubits eliminates communication operations transparently. In contrast, other mapping algorithms can only introduce communication operations. We show that we can produce better-quality circuits than commercial compilers: shorter by up to 68% (18% on average) fewer gates than Qiskit, up to 36% (9% on average) fewer gates than Tket. We outperform BQSkit, a permutation-unaware, synthesis-based compiler, by up to 67% (21% on average) fewer gates. We also exceed experimental optimal mappers such as OLSQ in quality (10.7% shorter circuits) and time to solution. Our scalable, heuristic approach can be seamlessly integrated into any quantum circuit compiler or optimization infrastructure, and it applies well to any qubit technology, such as superconducting and trapped ions. © 2023 IEEE.

关键词： Conformal mapping

来源：评论

学校读者我要写书评

暂无评论

Application of Impact-Driven Vibrations to Estimate Axial Stress in Continuous Welded Rails 41st

Application of Impact-Driven Vibrations to Estimate Axial St...

引用

41st IMAC, A Conference and Exposition on Structural Dynamics, 2023

作者： Enshaeian, Alireza Belding, Matthew Rizzo, Piervincenzo Laboratory for Nondestructive Evaluation and Structural Health Monitoring Studies Department of Civil and Environmental Engineering University of Pittsburgh PittsburghPA United States Department of Electrical and Computer Engineering University of Pittsburgh PittsburghPA United States

ISBN: (纸本)9783031366628

Track segments welded together form a continuous welded rail (CWR). Although CWRs are widely used, they are prone to buckling in warm seasons. To prevent rail buckles, accurate estimates of the axial stress and rail neutral temperature (i.e., the temperature at which the axial stress is zero) are needed. This study proposes a noninvasive method to determine the axial load in CWRs using numeric models and field test data. A general finite element model under varying boundary conditions and axial stresses was formulated. The model was then validated experimentally by testing a real track in the field. During the experiment, the rail was subjected to the impact of an instrumented hammer, and the triggered vibrations were recorded with conventional accelerometers. These vibration frequencies were compared with numerical predictions to estimate the neutral temperature of the rail using a machine learning algorithm. The estimates showed good agreement with the measurements conducted by a third independent party that used a very cumbersome approach based on strain gages. © 2024, The Society for Experimental Mechanics, Inc.

关键词： Finite element method

来源：评论

学校读者我要写书评

暂无评论

Secure and Efficient Color Image Cryptography Using Two Secret Keys 8th

Secure and Efficient Color Image Cryptography Using Two Sec...

引用

8th International Conference on Smart City Applications, SCA 2023

作者： Abu-Faraj, Mua’ad Al-Hyari, Abeer Alqadi, Ziad Department of Computer Information Systems The University of Jordan Aqaba77110 Jordan Electrical Engineering Department Al-Balqa Applied University As Salt19117 Jordan Computers and Networks Engineering Department Al-Balqa Applied University Amman15008 Jordan

ISBN: (纸本)9783031538230

The significance of digital color images in various applications necessitates the development of secure and efficient color image encryption techniques. This study presents a simple yet highly secure method for encrypting color images using dual secret keys, enhancing overall image security and safeguarding against hacking attempts. The first key generates index keys for encrypting and decrypting image segments, while the second key determines the starting point in the image_key and divides the unencrypted image into segments. These index keys are then employed to encrypt and decrypt the segments. Encryption and decryption of segments involve a straightforward process, distributing plain data based on the index key and retrieving decrypted data from encrypted data following the index key’s indices. The proposed method will be assessed and applied to various color images, with the results analyzed to demonstrate improvements in quality, sensitivity, and speed. The method’s speed will be compared with other techniques to highlight the acceleration offered by the proposed approach. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Power Dispatch Estimation from Electric Vehicles in a Distribution System

Power Dispatch Estimation from Electric Vehicles in a Distri...

引用

International Conference on Electric Power and Energy Conversion systems (EPECS)

作者： Ganesh K. Venayagamoorthy Imanthi Kalanika Subasinghe Raj Naidoo Holcombe Department of Electrical and Computer Engineering Real-Time Power and Intelligent Systems Laboratory Clemson University Clemson SC USA Department of Electrical Electronic and Computer Engineering University of Pretoria South Africa

ISBN: (数字)9798331516963

ISBN: (纸本)9798331516970

The integration of electric vehicles (EVs) into the electric power distribution system poses numerous challenges and opportunities for optimizing energy management and system operations. Electric vehicle grid interfaces (EVGIs), essentially bidirectional power converters, allow for charging/grid-to-vehicle (G2V) and discharging/vehicle-to-grid (V2G) power transfers. A power dispatch estimation (PDE) model for V2G, based on availability of EVs in a distribution system and capabilities of the distribution system, is needed to assist in grid operations. This paper presents the development of a PDE model based on nodal power flows to capture the complex spatiotemporal dependencies inherent in G2V and V2G patterns. The hierarchical structure of a distribution system, feeder to EVGI node, is taken into consideration for PDE. Typical PDE estimation results are presented for the IEEE 34 test node feeder distribution system allocated with EVGIs.

关键词： Partial discharges Vehicle-to-grid systems operation Estimation Spatiotemporal phenomena Resource management Energy management Voltage control Vehicle dynamics Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Pediatric Bone Age Prediction Using Deep Learning 26

Pediatric Bone Age Prediction Using Deep Learning

引用

26th International Conference on computer and Information Technology, ICCIT 2023

作者： Bin Habib, Al Zadid Sultan Islam, Md. Ekramul Bin Syed, Md Asif Ahamed, Md Younus Tasnim, Tanpia West Virginia University Lane Department of Computer Science and Electrical Engineering MorgantownWV26506 United States Stamford University Bangladesh Department of Computer Science & Engineering Dhaka1217 Bangladesh West Virginia University Department of Industrial and Management Systems Engineering MorgantownWV26506 United States Green University of Bangladesh Department of Computer Science and Engineering Dhaka1461 Bangladesh

ISBN: (纸本)9798350359015

Pediatric bone age prediction is a crucial task in clinical practice that can help diagnose endocrine disorders and provide insight into a child's growth and development. However, conventional bone age prediction methods are often labor-intensive and require specialized radiological expertise. This paper presents a Deep Learning (DL)-based approach to pediatric bone age prediction using EfficientNet with Additive Attention, a state-of-the-art neural network architecture for image classification and regression tasks. The method utilizes over 12,000 X-ray images from the RSNA bone age dataset. It involves image preprocessing, transforming them into three-channel images, and training a Convolutional Neural Network (CNN) to automatically learn the features of hand bone images. This approach provides a more effective and accurate solution for predicting bone age, which is critical in diagnosing pediatric endocrine diseases. This work uses two variations of the EfficientNet model (B0 and B4), where EfficientNetB4 is also finetuned with the Additive Attention mechanism. These three models predict the age for the original age, and their comparison is shown in curves. The predicted ages depict that in most cases, EfficientNetB4 and EfficientNetB4 with Additive Attention (EN-AA) successfully predicted the bone ages more accurately regarding the original age, and their performance was better than the EfficientNetB0. Specific performance metrics are provided to underscore this improvement. Learning curves for training and validation loss confirm effective learning without overfitting or underfitting, further validating our approach's efficacy in pediatric endocrine disease diagnosis. © 2023 IEEE.

关键词： Additive Attention Deep Learning EfficientNet Image Regression Pediatrics RSNA Bone Age

来源：评论

学校读者我要写书评

暂无评论

Statistical Delay and Error-Rate Bounded QoS Provisioning for RSMA Based 6G Mobile Wireless Networks in the Non-Asymptotic Regime

Statistical Delay and Error-Rate Bounded QoS Provisioning fo...

引用

IEEE International Conference on Communications (ICC)

作者： Xi Zhang Qixuan Zhu H. Vincent Poor Department of Electrical and Computer Engineering Networking and Information Systems Laboratory Texas A&M University College Station TX USA Department of Electrical and Computer Engineering Princeton University Princeton NJ USA

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

The upcoming 6G mobile wireless networks are expected to support massive ultra-reliable and low-latency communications (mURLLC), which is an emerging service that demands more stringent requirements than the fifth generation (5G) wireless networks on delay and error-rate bounded quality-of-services (QoS) with massive connectivity. Finite blocklength coding (FBC) techniques based short packets communication techniques have been shown to be able to support both the statistical delay and error-rate bounded QoS provisioning. Rate splitting (RS) multiple access schemes have been proposed to address the sum degree-of-freedom loss problem over massive multiple-input and multiple-output channels when massive mobile users request to access the network. However, how to support the statistical delay and error-rate bounded QoS provisioning using FBC among massive mobile users to enable the massive access has not been sufficiently studied. In this paper, we propose to integrate FBC with RS techniques to achieve mURLLC transmissions. First, we define the ∊-effective capacity to measure the performance of statistical delay and error-rate bounded provisioning, and obtain a closed-form ∊-effective capacity under the RS scheme. Then, we maximize the aggregate ∊-effective capacity over all mobile users by deriving an optimal transmit power allocation strategy for the RS scheme. Finally, using numerical analyses, we validate and evaluate our proposed RS schemes to support statistical delay and error-rate bounded QoS provisioning over 6G communication networks in the non-asymptotic regime.

关键词： 6G mobile communication Numerical analysis Error probability Wireless networks Aggregates Measurement uncertainty Quality of service

来源：评论

学校读者我要写书评

暂无评论

Quantum Assisted Combinatorial Benders' Algorithm for the Synergy of Hydrogen and Power Distribution systems with Mobile Storage

引用

IEEE Transactions on Power systems 2025年

作者： Li, Mingze Wang, Siyuan Fan, Lei Han, Zhu University of Houston Department of Electrical and Computer Engineering The Department of Engineering Technology HoustonTX77204 United States Argonne National Laboratory Energy Systems and Infrastructure Analysis Division LemontIL60439 United States University of Houston Department of Engineering Technology The Department of Electrical and Computer Engineering HoustonTX77204 United States The University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States

The growth of hydrogen infrastructure is expected to aid in the integration of fluctuating renewable energy in distribution systems. To leverage the hydrogen system flexibility, this work presents a mixed-binary quadratic program (MBQP) model for synergistic operations of hydrogen and power distribution systems, wherein truck-mounted mobile hydrogen storage facilities are modeled for the schedule of their routes and loading/unloading quantities. A quantum-assisted combinatorial Benders' decomposition algorithm is designed for our MBQP model to deploy the solving of master and sub-problems on a quantum processing unit (QPU) and a classical CPU, respectively. The master problem is reformulated as a quadratic unconstrained binary optimization (QUBO) problem, which can be efficiently solved by quantum annealers. The proposed approach was tested on a hybrid quantum annealing and classical computing platform. Results show a trend to outperform the CPU-based commercial solvers as the problem scale increases. © 1969-2012 IEEE.

关键词： Quantum computers

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：