检索结果-内蒙古大学图书馆

A Multi-phase Deep Learning Approach for Predicting HCC Response to TACE using Complete Computed Tomography

A Multi-phase Deep Learning Approach for Predicting HCC Resp...

2023 IEEE EMBS Special Topic Conference on Data Science and engineering in Healthcare, Medicine and Biology, IEEECONF 2023

作者： Chang, Shun Cheng Liu, Chien Fu Misztal, Marta Hsieh, Yi Hsien Lin, Che Taiwan School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom Department of Electrical Engineering Ntu Taiwan Center for Computational and Systems Biology Center for Biotechnology Ntu Taiwan Smart Medicine and Health Informatics Program Ntu Taiwan

ISBN: (纸本)9798350383386

In this research study, we compare the predictive performance of two advanced deep learning-based models in order to provide a solution to TACE (Transarterial Chemoembolization) response prediction in HCC (Hepatocellular Carcinoma) patients. Using entire abdominal CT scans enabled a broader perspective available for the model, eliminating the need for segmentation during the preprocessing. Making use of both single-phase and multi-phase CT imaging, we have used DenseNet121 and have obtained an accuracy of 80% for the multi-phase *** Relevance: The ability to predict the effectiveness of TACE treatment prior to its administration makes it possible to provide a better decision-making aid for physicians and patients. © 2023 IEEE.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Enhancing Local Area Power Stability: Integrative Oscillation Damping with PV Systems and BESS

Enhancing Local Area Power Stability: Integrative Oscillatio...

引用

Technology and Policy in Energy and Electric Power (ICT-PEP), International Conference on

作者： Ilham Akbar Ariesa Budi Zakaria Eduard Muljadi Graduate Program PLN-ITB PLN Corporate University Auburn USA Electrical and Computer Engineering Auburn University Auburn USA

ISBN: (数字)9798331518646

ISBN: (纸本)9798331518653

This research delves into enhancing local area power stability by integrating battery energy storage systems (BESS) with photovoltaic (PV) systems to address and accelerate the damping of post-fault oscillations following short-circuit disturbances within power grids incorporating variable renewable energy sources. Focused on implementing a power oscillation damping (POD) mechanism within PV plants, this study aims to mitigate post-fault oscillations effectively within a specified timeframe. The proposed POD within the PV plant is strategically designed to augment the grid's resilience by supplying additional active and reactive power in response to system demands post-disturbance. The integration of a 25 MW BESS has demonstrated a significant enhancement in the system's recovery speed, reducing oscillation duration from 60 seconds to 45 seconds. Moreover, a configuration with double PV systems and a 50 MW BESS further reduced the oscillation duration to 42 seconds. Utilizing PSCAD software, this study presents an innovative approach to visualize the system's behavior post-short-circuit disturbances, confirming the efficacy of BESS integration in improving system stability and reliability. These results pave the way for further exploration of optimal BESS sizing and placement strategies to maximize grid resilience.

关键词： Damping Reactive power Battery energy storage system Simulation Power system stability Stability analysis Circuit stability Oscillators Frequency control Resilience

来源：评论

学校读者我要写书评

暂无评论

SODIUM-ION BATTERY CYCLE LIFE PREDICTION USING MACHINE LEARNING

SODIUM-ION BATTERY CYCLE LIFE PREDICTION USING MACHINE LEARN...

引用

International Conference on Green Energy, Computing and Intelligent Technology 2024, GEn-CITy 2024

作者： Liu, Linfeng Juwono, Filbert H. Wong, W.K. Purwanto, Erick Jin, Tingyan Zhen, Yuyang Sustainable Energy Technology Program Xi'an Jiaotong-Liverpool University Suzhou China Department of Electrical and Electronic Engineering Xi'an Jiaotong-Liverpool University Suzhou China Department of Electrical and Computer Engineering Curtin University Malaysia Miri Malaysia Department of Computing Xi'an Jiaotong-Liverpool University Suzhou China School of Mechanical and Electrical Engineering Beijing Information Science and Technology University Beijing China School of Instrument Science and Technology Beijing University of Technology Beijing China

ISBN: (纸本)9781837242689

In this study, we explore the classification and prediction capabilities of three models-Genetic program.ing (GP), Logistic Regression (LR), and the Kolmogorov-Arnold Network (KAN)-on the task of sodium-ion battery life prediction. By leveraging a dataset composed of multiple battery characteristics, we aim to determine the remaining power of sodium-ion batteries using these machine learning models. The KAN model, being a novel approach, demonstrates superior performance across various metrics, including accuracy, precision, recall, and F1 score, when compared to the other two models. This highlights the potential of KAN as a robust model for complex classification tasks in the field of battery life prediction. © The Institution of engineering & Technology 2024.

关键词： Genetic program.ing

来源：评论

学校读者我要写书评

暂无评论

MAZENET: AN ACCURATE, FAST, & SCALABLE DEEP LEARNING SOLUTION FOR STEINER MINIMUM TREES

arXiv

引用

arXiv 2024年

作者： Ramos, Gabriel Díaz Arikan, Toros Baraniuk, Richard G. Rice University United States Department of Electrical and Computer Engineering Smalley-Curl Institute Applied Physics Program United States

The Obstacle Avoiding Rectilinear Steiner Minimum Tree (OARSMT) problem, which seeks the shortest interconnection of a given number of terminals in a rectilinear plane while avoiding obstacles, is a critical task in integrated circuit design, network optimization, and robot path planning. Since OARSMT is NP-hard, exact algorithms scale poorly with the number of terminals, and so practical solvers sacrifice accuracy for large problems. We propose and study MazeNet, a deep learning-based method that learns to solve the OARSMT from data. MazeNet re-frames OARSMT as a maze-solving task that can be addresssed with a recurrent convolutional neural network (RCNN). A key hallmark of MazeNet is its scalability: we only need to train the RCNN blocks on mazes with a small number of terminals;mazes with a larger number of terminals can be solved simply by replicating the same pre-trained blocks to create a larger network. Across a wide range of experiments, MazeNet achieves perfect OARSMT-solving accuracy, with significantly reduced runtime compared to classical exact algorithms, and with the ability to handle larger numbers of terminals than state-of-the-art approximate algorithms. © 2024, CC BY.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Diabetes Classification Problem with CatBoost Method and Optuna Gradient Boosting Optimization 6

Diabetes Classification Problem with CatBoost Method and Opt...

引用

6th International Conference on Information and Communications Technology, ICOIACT 2023

作者： Kurniawan, Safar Dwi Purwono, Purwono Ma'arif, Alfian Suwarno, Iswanto Politeknik Harapan Bersama Department of Computer Engineering Tegal Indonesia Universitas Harapan Bangsa Department of Informatics Purwokerto Indonesia Universitas Ahmad Dahlan Department of Electrical Engineering Yogyakarta Indonesia Universitas Muhammadiyah Yogyakarta Department of Engineer Professional Program Yogyakarta Indonesia

ISBN: (纸本)9798350315639

Diabetes mellitus is a dangerous global epidemic that can cause kidney failure, heart attack, blindness, and death. The main cause of this disease is too high blood sugar levels due to the irrelevant work of pancreatic beta cells. Rapid computer technology advances and implementations based on artificial intelligence have penetrated various fields, especially the health sector. Data mining and machine learning are technologies that continue to grow, are reliable, and can be used as research support tools in the medical field. This technology is considered capable of helping to automate diabetes prediction. Based on related research, our contribution to this research is to utilize the CatBoost method with Optuna optimization. In the data preprocessing stage, all 768 data sets have gone through removing outliers, normalizing features to reducing dimensions. The dataset is divided into 85\% composition for training data and 15\% for test data. At the feature selection stage with Correlation Pearson's, we found that Glucose correlated with diabetes outcome or disease because it had a value range of 0.47. The results' accuracy is considered less than optimal because it only produces an accuracy value below 80%, even after optimization with Optuna. It can be seen that there was only an increase of 7\% after optimizing with Optuna. © 2023 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Performance of E-Mode AlGaN/GaN HEMTs With Recessed Gates Through Low-Damage Neutral Beam Etching and Post-Metallization Annealing

IEEE Open Journal of Nanotechnology

引用

IEEE Open Journal of Nanotechnology 2023年 4卷 150-155页

作者： Chen, Yi-Ho Ohori, Daisuke Aslam, Muhammad Lee, Yao-Jen Li, Yiming Samukawa, Seiji National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Graduate Degree Program of College of Electrical and Computer Engineering Hsinchu300093 Taiwan Tohoku University Institute of Fluid Science Sendai980-8577 Japan National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Electrical Engineering and Computer Science International Graduate Program Hsinchu300093 Taiwan National Yang Ming Chiao Tung University Institute of Pioneer Semiconductor Innovation Hsinchu300093 Taiwan National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Institute of Communications Engineering Institute of Biomedical Engineering Hsinchu300093 Taiwan National Yang Ming Chiao Tung University Department of Electronics and Electrical Engineering Hsinchu300093 Taiwan National Yang Ming Chiao Tung University Institute of Communications Engineering Hsinchu300093 Taiwan

This study investigated the electrical properties of AlGaN/GaN high-electron-mobility transistors (HEMTs) with varied recess depths under the gate electrode. We demonstrated a recess depth of approximately 6 nm, which was achieved through neutral beam etching (NBE) technique with a low etch rate of 1.8 nm/min, resulting in device enhancement-mode (E-mode) behavior with threshold voltage (Vth) of 0.49 V. The effects of post-metallization annealing (PMA) on the device performance were also examined. The results revealed that PMA treatment improves the DC characteristics of the devices, including maximum drain current (IDMAX), transconductance (gm), subthreshold swing (SS), on-off ratio, and off-state leakage current, with maximum enhancement percentage of 18.3% for IDMAX, 3758% for on-off ratio, and 54.3% for SS. Moreover, this study compared the recess depths of metal-insulator-semiconductor high-electron-mobility transistors (MIS-HEMTs) with the SiN dielectric layer. The results showed that MIS-HEMTs exhibit more negative Vth values, which can be attributed to the controlled surface states achieved through passivation. © 2020 IEEE.

关键词： Etching

来源：评论

学校读者我要写书评

暂无评论

Analysis of Selective Emitter Formation Technology of n-TOPCon Solar Cell

引用

Transactions of the Korean Institute of electrical Engineers 2022年第1期71卷 114-120页

作者： Jeong, Sungjin Cha, Yewon Kim, Sungheon Kim, Hongrae Park, Somin Kim, Taeyong Park, Jinjoo Ju, Minkyu Yi, Junsin Dept. of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of Interdisciplinary Program in Photovoltaic System Engineering Sungkyunkwan University Korea Republic of Dept. of Energy Convergence Engineering Division of Energy & Optical Technology Convergence Cheongju University Korea Republic of College of Information and Communication Engineering Sungkyunkwan University Korea Republic of

The main efficiency limiting factors for homogeneous emitter solar cells are resistance loss through metal contact on the front side and recombination loss at the surface. Herein, a selective emitter technology is introduced to solve the above problem, and it is currently commercialized in the mainstream p-PERC (Passivated Emitter Rear Contact) solar cell. The selective emitter boosts efficiency by 0.3-0.4% when compared to a homogeneous emitter, and when applied to the n-TOPCon (Tunnel Oxide Passivated Contact) solar cell, high efficiency of 26% or higher may be predicted. The most widely utilized selective emitter technologies are laser and etch-back. The One-Step Technology, which is suited to the n-TOPCon solar cell process, a laser is suitable for mass manufacturing with high yield. Because selective emitters increase electrical characteristics, which impact cell efficiency, it is required to study and create a technology that is optimal for the n-TOPCon manufacturing process. © 2022 Korean Institute of electrical Engineers. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Resilience of Data-Driven Cyberattack Detection Systems in Smart Power Grids

Resilience of Data-Driven Cyberattack Detection Systems in S...

引用

European Signal Processing Conference (EUSIPCO)

作者： Abdulrahman Takiddin Rachad Atat Hayat Mbayed Muhammad Ismail Erchin Serpedin Department of Electrical and Computer Engineering Florida State University Tallahassee FL USA Electrical and Computer Engineering Program Texas A&M University at Qatar Doha Qatar Center for Advanced Power Systems Florida State University Tallahassee FL USA Department of Computer Science Tennessee Technological University Cookeville TN USA Department of Electrical and Computer Engineering Texas A&M University College Station TX USA

ISBN: (数字)9789464593617

ISBN: (纸本)9798331519773

Data communications within the smart power grid components are susceptible to cyberattacks due to the inter-connected nature of the grid and reliance on communication networks. Such cyberattacks can exploit the integrity of the exchanged data and result in operational instability. Existing data-driven cyberattack detection systems (CDSs) are proposed in the literature but their effectiveness is only verified against one type of cyberattacks. In reality, a smart grid system could encounter more than one attack type at once. Thus, in this paper, we investigate the resilience of state-of-the-art data-driven CDSs against replay false data injection, adversarial evasion, and adversarial data poisoning attacks on a realistic IEEE 118-bus system model. It turns out that a convolutional recurrent graph autoencoder-based CDS offers an attack detection rate of 96 – 97.5%, which outperforms other machine learning and deep learning-based data-driven CDSs by 16 – 54% since it captures the recurrent and spatial aspects of the data without being trained on attack data.

关键词： Deep learning Europe Feature extraction Graph neural networks Data models Smart grids Reliability computer crime Unsupervised learning Resilience

来源：评论

学校读者我要写书评

暂无评论

Adaptive Neuro-Fuzzy Inference System As New Real-Time Approach for Parkinson Seizures Prediction 4

Adaptive Neuro-Fuzzy Inference System As New Real-Time Appro...

引用

4th International Conference on Bio-engineering for Smart Technologies, BioSMART 2021

作者： Daher, Alaa Yassin, Sally Alsamra, Hadi Ali, Hassan Abou Beirut Arab University Biomedical Engineering Program Faculty of Engineering Electrical and Computer Engineering Department Debbieh Lebanon

ISBN: (纸本)9781665408103

Parkinson's disease, as a definition, is a neurological condition that affects the brain and causes tremors, stiffness, and difficulties walking, balancing, and coordinating. Symptoms of Parkinson's disease normally appear gradually and worsen with time. People with Parkinson's disease may have difficulties walking and speaking as the condition develops. Numerous recent studies have shown a direct association between Parkinson's disease and the incident of having epileptic seizures, which is defined to be a burst of the uncontrollable electrical activity of the brain cells, that is associated with an increased risk of sudden unexplained deaths. This project aims to obtain a real-time seizure prediction system for Parkinson's disease patients based on the electroencephalogram (EEG) signals, enabling the detection of a seizure before it happens. This will hopefully save them from risky situations or sudden death, as they will be alerted and have the time enabling them to be prepared and take the needed precautions and steps to prevent the seizure from happening. For this project, we've used the Neural Network and the ANFIS ('udaptive neuro-fuzzy inference system '') to process and analyze the electroencephalogram (EEG) data signals of the Parkinson patients to detect seizures starting point. © 2021 IEEE.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

A Novel Resource Allocation in Software-Defined Networks for IoT Application 31

A Novel Resource Allocation in Software-Defined Networks for...

引用

31st International Conference on Software, Telecommunications and computer Networks, SoftCOM 2023

作者： De Sousa, Alexandre Ladeira Okey, Ogobuchi Daniel Rosa, Renata Lopes Saadi, Muhammad Rodriguez, Demostenes Zegarra Federal University of Lavras Department of Computer Science Minas Gerais Lavras Brazil Federal University of ABC Santo Andre Graduate Program in Information Engineering Sao Paulo Brazil University of Central Punjab Department of Electrical Enginnering Punjab Pakistan Federal University of Lavras Computer Science Department Minas Gerais Lavras Brazil

ISBN: (纸本)9798350301076

The rapid proliferation of Internet of Things (IoT) devices has posed significant challenges for network resource allocation and management. In this paper, we propose a novel methodology for efficient resource allocation in Software-Defined Networks (SDNs) to meet the unique requirements of IoT applications. Our approach leverages the flexibility and program.ability of SDN to dynamically allocate network resources based on the specific needs of IoT devices. Our proposal combines reinforcement learning with dynamic resource allocation, demonstrating its effectiveness in optimizing resource allocation and enhancing network performance. The results highlight the potential of our approach to addressing the resource challenges in SDN-based IoT environments. The proposed method obtains results superior to 30% of throughput in comparison to a traditional resource allocation in SDN to IoT applications. © 2023 University of Split, FESB.

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：