检索结果-内蒙古大学图书馆

IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT Europe)

作者： Abiodun E. Onile Juri Belikov Eduard Petlenkov Yoash Levron Department of Software Science Tallinn University of Technology Akadeemia tee 15a Tallinn Department of Computer Systems Tallinn University of Technology Akadeemia tee 15a Tallinn Faculty of Electrical & Computer Engineering Technion—Israel Institute of Technology Haifa Israel

The next evolution of traditional energy systems towards smart grid will require end-consumers to actively participate and make informed decisions regarding their energy usage. Industry 4.0 facilitates such progress by allowing more advanced analytics and creating means for end-consumers and distributed grid assets to be modelled as their Digital twins (DT) equivalents, paving the way for asset-level analytics. Note-worthily, consumers’ comfort is crucial towards promotion of easy adoption of such models from consumers’ perspectives. This study presents the application of hybrid DT and multiagent reinforcement learning models for real-time estimation of end-consumers future energy behaviors while generating actionable recommendation feedback for improving their energy efficiency and enhancing end-user comfort.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Visual SLAM System for Autonomous Vehicles in Dynamic Environments

A Novel Visual SLAM System for Autonomous Vehicles in Dynami...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Xinyu Zeng Ying He F. Richard Yu Guang Zhou Shenzhen Key Lab of Digital & Intelligent Technologies & Systems College of Computer Science and Software Engineering Shenzhen University China Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) Shenzhen China Deeproute Inc

With the development of autonomous vehicles and intelligent robots, visual simultaneous localization and mapping (SLAM) has attracted great attentions. Most existing visual SLAM systems assume that the objects are stationary in static environments. However, in the real world, there are many objects that are non-stationary in dynamic environments, which will cause performance degradation of visual SLAM systems. In this paper, to address this issue, we propose a novel visual SLAM system based on multi-task deep neural networks. Specifically, we apply multi-task deep neural networks to extract oriented keypoints and perceive dynamic semantic regions, which are used to perform outlier rejection in the SLAM system. We evaluate our method on public datasets, and the results show that our method outperforms existing visual SLAM systems. The presentation video url is: https://***/qGE1OvaJvV0.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Day-ahead PV Output Power Forecasting Utilizing Boosting Recursive LightGBM-LSTM Framework

Day-ahead PV Output Power Forecasting Utilizing Boosting Rec...

引用

IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT Europe)

作者： Hossein Nourollahi Hokmabad Oleksandr Husev Dmitri Vinnikov Juri Belikov Eduard Petlenkov Department of Electrical Power Engineering and Mechatronics Tallinn University of Technology Tallinn Estonia Department of Software Science Tallinn University of Technology Tallinn Estonia Department of Computer Systems Tallinn University of Technology Tallinn Estonia

Recently, global photovoltaic (PV) system installations have surged. Precise forecasting is vital for their grid integration and carbon emission cuts. However, due to fluctuating solar radiation, predicting PV output is difficult. Machine learning models, notably Long Short-Term Memory (LSTM) networks, offer a solution. This study presents a novel framework using a boosted recursive Light Gradient Boosting Machine (LightGBM)-LSTM network to forecast daily PV output at hourly intervals. Conducted in Northern Europe—a region with significant solar radiation variability—the models trained on meteorological and historical data showed a 12% improvement in RMSE, a 13% reduction in MAPE, and a 5% increase in the R 2 score compared to standalone LSTM models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Emerging Role of Industry 5.0 Digital Twins in Demand Response Electricity Market and Applications

Emerging Role of Industry 5.0 Digital Twins in Demand Respon...

引用

IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT Europe)

Traditional power system is facing challenges demanding new operational requirements to meet targets of Net Zero Emissions by 2050. Aggregators are playing progressively important role in the demand response (DR) electricity market but are often riddled with deep level of market monopoly and lack of transparency/secrecy. Emerging real-time information technology (IT) applications and novel modelling of digital twins (DT) of individual electricity assets are challenging this position by promising improvements and openness that allows TSO direct access to available demand side flexibility. Additionally, DT technologies are facilitating how demand response services are delivered to end-users by allowing individual assets participation at the atomic level. In this study, the application potentials of assets’ DT in participating in the demand response electricity market was examined. Again, an overview of DT applications for DR was conducted. The novelty of this study is highlighted in development of new approach that facilitates individual end-user assets’ contribution to demand response efforts. The research identifies key useful questions that might serve as inspiration for stakeholders and policy-makers to further close existing gaps in the field of DT, smart-grid and demand response.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Interactive 3D Medical Image Segmentation with SAM 2

arXiv

引用

arXiv 2024年

作者： Shen, Chuyun Li, Wenhao Shi, Yuhang Wang, Xiangfeng Huang, Yifei School of Computer Science and Technology East China Normal University Shanghai200062 China School of Software Engineering Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai200092 China Shanghai United Imaging Healthcare Advanced Technology Research Institute Co. Ltd Shanghai201807 China School of Software Engineering East China Normal University Shanghai200062 China

Interactive medical image segmentation (IMIS) has shown significant potential in enhancing segmentation accuracy by integrating iterative feedback from medical professionals. However, the limited availability of enough 3D medical data restricts the generalization and robustness of most IMIS methods. The Segment Anything Model (SAM), though effective for 2D images, requires expensive semi-auto slice-by-slice annotations for 3D medical images. In this paper, we explore the zero-shot capabilities of SAM 2, the next-generation Meta SAM model trained on videos, for 3D medical image segmentation. By treating sequential 2D slices of 3D images as video frames, SAM 2 can fully automatically propagate annotations from a single frame to the entire 3D volume. We propose a practical pipeline for using SAM 2 in 3D medical image segmentation and present key findings highlighting its efficiency and potential for further optimization. Concretely, numerical experiments on the BraTS2020 and the medical segmentation decathlon datasets demonstrate that SAM 2 still has a gap with supervised methods but can narrow the gap in specific settings and organ types, significantly reducing the annotation burden on medical professionals. Our code will be open-sourced and available at https://***/Chuyun-Shen/SAM_2_Medical_3D. Copyright © 2024, The Authors. All rights reserved.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Energy Storage and Forecasting Error Impact Analysis In Photovoltaic Equipped Residential Nano-Grids

Energy Storage and Forecasting Error Impact Analysis In Phot...

引用

Compatibility in Power Electronics (CPE)

作者： Hossein Nourollahi Hokmabad Oleksandr Husev Juri Belikov Dmitri Vinnikov Eduard Petlenkov Department of Electrical Power Engineering and Mechatronics Tallinn University of Technology Tallinn Estonia Department of Software Science Tallinn University of Technology Tallinn Estonia Department of Computer Systems Tallinn University of Technology Tallinn Estonia

Battery energy storage systems (BESS) enable many applications for photovoltaic (PV) equipped nano-grids. Stored excessive energy is utilized for energy arbitrage, demand response during blackouts, and peak shaving. This technology helped utility service providers deal with the duck-curve-effect and intermittency of renewable energy systems. In this paper, we investigate the benefits of using energy storage systems in PV nano-grids for residential sectors and evaluate the relationship between battery presence and system performance. We also analyze the effects of battery degradation on energy independence and self-sufficiency and investigate the relationship between simple payback time and state of health (SoH) levels of nano-grid components. Additionally, we propose a simple rule-based energy supervision strategy and evaluate its performance under various forecasting error levels, highlighting the importance of high-performance forecasting methods for proper energy management systems. Our contributions will help select and optimize PV-battery solutions and energy management algorithms to achieve the highest benefit and minimize investment risks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Content-Based Image Retrieval for Lung Cancer Diagnosis: Leveraging Texture Analysis and Ensemble Models 7

Enhancing Content-Based Image Retrieval for Lung Cancer Diag...

引用

7th International Conference on Image Information Processing, ICIIP 2023

作者： Jayabalaji, K.A. Laxmaiah, Bagam Thatipudi, Jayendra Gopal Chandraprabha, K. Badhe, Pravin Balaram, Allam Sri Krishna Arts And Science College Department of Software Systems Tamilnadu Coimbatore India Cmr Technical Campus Department of Cse Telangana Kandlakoya India University of North Texas Department of Computer Science DentonTX76203 United States Bannari Amman Institute of Technology Department of Information Technology Tamilnadu Sathyamangalam India Sinhgad College of Pharmacy Swalife Biotech Department of Pharmacology Pune India Mlr Institute of Technology Department of Computer Science And Engineering Telangana Hyderabad500043 India

ISBN: (纸本)9798350371406

In image retrieval systems, many search engines rely on text-based methods, extracting information from descriptions and tags to retrieve relevant images. However, this conventional approach often overlooks the optical or semantic information present in photographs, leading to errors in the retrieved results. To address this issue, it is essential to consider content-based information such as intensities, edges, and pixel values when designing image retrieval systems, especially in domains like medicine. This study focuses on developing a Content-Based Image Retrieval (CBIR) system for the domain of medicine, with a particular emphasis on lung cancer detection. Early identification and treatment of lung cancer are critical for patient outcomes, making suitable computer-Aided Diagnosis (CAD) systems essential for assisting clinicians. The proposed ensemble model incorporates various feature extraction methods, including image processing techniques and wavelet transform, to harness the valuable information from images. These features are then fed into a deep learning model to assess their effectiveness in image retrieval tasks. By combining machine learning and image processing techniques, this work presents a comprehensive CBIR system capable of efficiently retrieving relevant medical images. Such advancements in image retrieval technology hold significant promise for aiding medical professionals in diagnosing and treating diseases like lung cancer promptly. © 2023 IEEE.

关键词： computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Pretrained Model with CNN for Lung Cancer Identification and Classification

Pretrained Model with CNN for Lung Cancer Identification and...

引用

Pattern Recognition and Artificial Intelligence (PRAI), International Conference on

作者： Shaista Kanwal Sajid Ali Tahani Jaser Alahmadi Muhammad Assam Ghulam Jillani Ansari Uzair Aslam Bhatti Department of Information Sciences University of Education Lahore Pakistan Department of Information Systems College of Computer and Information Sciences Princess Nourah bint Abdulrahman University Riyadh Saudi Arabia Department of Software Engineering University of Science and Technology Bannu KPK Pakistan School of information and communication engineering Hainan University

ISBN: (数字)9798350350890

ISBN: (纸本)9798350350906

Lung cancer impacts both genders, and its early detection is key to lowering death rates. Current deep learning techniques for automated identification and classification of lung carcinoma face issues with interpretability, data variability handling, and broader applicability. In our research, we propose a novel method that merges a convolutional neural network (CNN) with a streamlined RESNET18 framework. This approach is designed for lung cancer detection and categorization from CT scans, involving image preprocessing like resizing and rescaling. It effectively differentiates between healthy and cancerous tissues, further classifying them as either Normal, Benign, or Malignant, including variants such as adenocarcinoma and squamous cell carcinoma. Our CNN+RESNET18 model boasts an impressive 99% accuracy, supporting radiologists in the intricate task of image analysis, reducing risks of incorrect or delayed diagnosis, and fostering prompt treatment for improved patient outcomes.

关键词： Accuracy Squamous cell carcinoma Computed tomography Scalability Lung cancer Mortality Streaming media Feature extraction Convolutional neural networks Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Application of Artificial Intelligence in Rock Tunnel engineering: A Survey on Where and How

引用

Expert systems 2025年第7期42卷

作者： Yu, Xiaojie He, Ben-Guo Xu, Xu Zhou, Yicong Diaz, Miguel A. Chen, Junxin Camacho, David School of Software Dalian University of Technology Dalian China Key Laboratory of Ministry of Education on Safe Mining of Deep Metal Mines Northeastern University Shenyang China School of Computer Science and Engineering Northeastern University Shenyang China Department of Computer and Information Science University of Macau China Department of Computer Systems Engineering Universidad Politécnica de Madrid Madrid Spain

Rock tunnel engineering (RTE) plays a crucial role in modern infrastructure development. The development of artificial intelligence (AI) is able to drive transformative advances in RTE. This review provides an in-depth analysis of the AI application in RTE. Through a comprehensive examination of existing literature, we explore how AI technologies have revolutionised various aspects of RTE, including construction methodology, rock parameter estimation, hazard disaster management during construction, and tunnel operation. In addition, we provide an in-depth study of the synergies between various AI algorithms and related open datasets. This work also outlines promising future research directions for the AI application in RTE, aiming to inspire further advancements in this emerging field. In conclusion, this review underscores the positive influence of AI on RTE, emphasising its capacity to elevate efficiency, accuracy, and safety standards throughout various phases of tunnel projects. The convergence of AI with RTE holds immense promise for advancing the field and ensuring the success and sustainability of future tunnel infrastructure endeavours. © 2025 John Wiley & Sons Ltd.

关键词： Disaster prevention

来源：评论

学校读者我要写书评

暂无评论

A Method for Reducing Speech Distortion in Minimum Variance Distortionless Response Beamformer

A Method for Reducing Speech Distortion in Minimum Variance ...

引用

Seminar on Signal Processing

作者： Quan Trong The Nguyen Ba Huy Pham Tuan Anh Falculty of Information Technology Ha Noi University of Science and Technology Ha Noi Viet Nam Falculty of Control Systems and Robotics University ITMO Saint - Petersburg Russia Federation Falculty of Software Engineering and Computer Systems University ITMO Saint - Petersburg Russian Federation

Speech processing devices such as mobile telephone, hearing aid, cochlear implant is commonly equipped with a designed microphone array (MA) to capture the acoustic environment. The MA signals often contain a mixture of desired speech component and unwanted surrounding noise (a combination of reverberation, different interferences, complex recording environment, third-party speaker). Minimum Distortionless Variance Response (MVDR) beamformer is one the most useful methods for reducing background noise and improving speech enhancement has been recently studied. MVDR beamformer merges the predefined constraints of response from a priori relative transfer function and the criteria of minimum total output noise power. Because of the microphone mismatches, the different microphone sensitivities, or the error of the direction of arrival of the interest signal, the output final signal of MVDR beamformer often corrupted. In this paper, the authors proposed an additive gain function for reducing speech distortion and enhancing MVDR beamformer's performance.

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：