检索结果-内蒙古大学图书馆

Advanced Research in Computing (ICARC), International Conference on

作者： Sarith Wijesundera Suresh Michael Peiris Department of Computer Science and Engineering University of Westminster London UK School of Computing Informatics Institute of Technology Colombo Sri Lanka

ISBN: (数字)9798331530983

ISBN: (纸本)9798331530990

Data Augmentation (DA) is an effective strategy to increase model generalisation. In Natural Language Processing (NLP), DA remains in its early stages, primarily due to the inherent sensitivity of textual data, which complicates the augmentation process. These complexities are further increased in multilingual contexts, as DA techniques effective in one language may not yield comparable results in others. As a result, manually identifying optimal DA techniques that preserve semantic integrity and are language agnostic remains a significant challenge. It emphasises the necessity for automating the text DA process with Explainable Artificial Intelligence (XAI), which offers a promising approach by calculating word importance scores to effectively guide the augmentation. In this paper, a comprehensive review of existing approaches in auto-text DA is presented, beginning with an exploration of the concept of auto-text DA, followed by a discussion on its cross-lingual applications, and concluding with the integration of XAI for semantic preservation. The paper highlights the critical need for further research to enhance the effectiveness and applicability of XAI in auto-text DA, enabling its use across diverse languages.

关键词： Sensitivity Explainable AI Reviews Semantics Transfer learning Data augmentation Search problems Natural language processing Multilingual Optimization

来源：评论

学校读者我要写书评

暂无评论

ACDV: Adaptive Content Delivery for Vehicular Digital Twin Networks

引用

IEEE Transactions on Vehicular technology 2025年第5期74卷 7084-7098页

作者： Zheng, Jinkai Luan, Tom H. Li, Guanjie Yin, Zhisheng Wu, Yuan Dong, Mianxiong Dongguan University of Technology School of Electrical Engineering and Intelligentization Dongguan523808 China Xi'an Jiaotong University School of Cyber Science and Engineering Xi'an710049 China Xidian University School of Cyber Engineering Xi'an710071 China Singapore University of Technology and Design Information Systems Technology and Design Pillar 487372 Singapore Xidian University State Key Laboratory of Isn Xi'an710071 China University of Macau State Key Laboratory of Internet of Things for Smart City 999078 China University of Macau Department of Computer Information Science 999078 China Muroran Institute of Technology Department of Sciences and Informatics Muroran05-08585 Japan

Digital Twins (DTs), serving personalized cloud-based digital assistants, hold great promise for supporting infotainment applications of the Internet of Vehicles (IoVs), in which personalized content such as high-definition maps, system updates, and social video streaming can be delivered from individualized DTs to vehicular users (VUEs) to enhance the intelligence of IoV services and improve their driving experience. This paper proposes a novel content caching framework tailored to DT-enabled IoVs, where DTs selectively cache on-demand contents on edge devices (i.e., cellular base stations and roadside units) managed by the edge service manager (ESM) along the VUE's trip to avoid backbone congestion yet save download time. However, ESMs are inherently selfish and reluctant to contribute resources to cache contents without benefits. Furthermore, considering the diverse trajectories of vehicles, it is inefficient to cache data along a single path. To address these challenges, we propose ACDV, which first models the interactions between the ESMs and DTs as a Stackelberg game to incentivize ESMs to actively participate in the content caching process. We then deploy a Markov model to predict the VUE distribution, which enables DTs to cache contents with a focus on predicted trajectories. To save storage costs, we derive an upper bound of content sizes that the VUE can download within a limited network connection time. Considering the lack of network information and users' private utility model in practical scenarios, we further develop a learning-based algorithm to find the optimal pricing scheme and content size strategies of ESMs and DTs. Through extensive simulations, we show that our proposal can effectively find the optimal strategy and achieve a fast convergence speed and high-level performance compared to the baselines. © 1967-2012 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Dual Approach in Autonomous Directional Drilling: Innovations with Drillbotics 1.5 Inch Automated RSS and Virtual Rig Platforms

Dual Approach in Autonomous Directional Drilling: Innovation...

引用

2025 SPE/IADC International Drilling Conference and Exhibition, DC 2025

作者： Soilemezidis, C. Mensah, J.S. Hollstein, W. Al Maasarani, K. Alkhawaja, A. Jamali, F. Dörfler, G. Hölzner, N. Jarbouh, K.A. Ustaoglu, D. Alukkal, A.T. Gudhane, L.A.Y. Jaeger, P. Feldmann, E. Carvajal, C.A.P. Yin, A.O. Sinkuu, L. Quayson, J. Amoah, F.B. Yahaya, H.S. Owusu, K.A. Dongoyo, C.K.N. Owusu, A. Amorin, R. Florence, F. Institute of Subsurface Energy Systems Clausthal University of Technology Lower Saxony Clausthal-Zellerfeld Germany Department of Petroleum and Natural Gas Engineering University of Mines and Technology Tarkwa Ghana Institute of Mechanical Engineering Clausthal University of Technology Lower Saxony Clausthal-Zellerfeld Germany Institute of Economics Clausthal University of Technology Lower Saxony Clausthal-Zellerfeld Germany Institute of Informatics Clausthal University of Technology Lower Saxony Clausthal-Zellerfeld Germany Department of Electrical and Electronics Engineering University of Mines and Technology Tarkwa Ghana Department of Computer Science and Engineering University of Mines and Technology Tarkwa Ghana Department of Petroleum Geoscience University of Mines and Technology Tarkwa Ghana Rig Operations AustinTX United States

ISBN: (纸本)9781959025641

SPE’s Drilling Systems Automation Technical Section (DSATS) sponsors the Drillbotics® autonomous drilling contest to promote advanced learning at participating universities. Two groups worked separately to drill a directional well hands-free and to connect to a well model to detect/close in a kick. This paper consolidates the efforts of both teams. Team A, the directional drilling team from the University of Mines and technology (UMaT) in Ghana, developed a virtual model that replicated full-scale directional drilling operations, facilitating the development and testing of innovative control schemes and automation strategies. Leveraging state-of-the-art drilling software, real-time data analytics, and advanced control systems, the project demonstrated the potential of automated drilling technologies across both the planning and execution phases of drilling projects. Team B, from Technical University Clausthal (TUC) in Germany, designed and built a mini-rig that included a working scaled version of a rotary steerable system (RSS) tool to steer a wellbore through a block of sandstone to reach two non-planer targets. The work incorporates machine learning techniques to evaluate downhole sensor data and improve steering signal input. The modular design of the second-generation surface actuation system offers a more compact and efficient solution than its predecessor. The control architecture and network protocols are analyzed, demonstrating network delays of under 2 msec using a refined second-generation translator setup. The achievements of both teams are important to the future of drilling automation, as their approaches could be used to verify and validate third-party app’s communications prior to field release on full-scale rigs. Copyright 2025, SPE/IADC International Drilling Conference and Exhibition.

关键词： Directional drilling

来源：评论

学校读者我要写书评

暂无评论

Enhanced Speech Emotion and Gender Recognition Using Hybrid CNN-LSTM Models

Enhanced Speech Emotion and Gender Recognition Using Hybrid ...

引用

Sentiment Analysis and Deep Learning (ICSADL), International Conference on

作者： S Priyadharshini G. Naveen Sundar D. Narmadha Senthil Kumar Thangavel Adeyemi Abel Ajibesin Selvanayaki Kolandapalayam Shanmugam Department of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India Department of Computer Science and Engineering Amrita School of Computing Coimbatore India Department of Information Technology Faculty of Informatics and Design Cape Peninsula University of Technology South Africa Department of Mathematics and Computer Science Ashland University USA

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

The current paper proposes a new approach for peripheral speech emotion analysis and gender estimation incorporating the best machine learning architectures such as CNNs and LSTMs. Its correct depiction of emotions and the variation of the gendered speech to indicate manifold signal-to-noise ratio make the approach accommodate the difficulty inherent in recognizing emotions from the recording of voices as well as predicting the gender of a speaker. It is then able to ally with preprocessing and collection of a vast range of different speech samples, feature extraction of pitch, tone and spectral data. These features serve as input to the CNNs and LSTMs: LSTMs work well at temporal regular features and the CNNs work well in feature extraction by location (spatio feature). The approach is tested on the RAVDESS and IEMOCAP datasets and establishes a near perfect match to prior approaches with reference to recognition accuracy of emotion analysis and gender prediction. Thus, applying the identified dual method approach, which could be described by such characteristics as highly accurate data pre-preprocessing, clear indication of the features of interest, a different CNN-LSTM model joint training, it offers a reasonably good platform to gain certain insights into such characteristics of the speech as our experiment demonstrates. This work offers satisfactory configurations on concerns such as human computer relation, customer relation and mental health surveillance to suggest that other applications could be achieved in future.

关键词： Training Emotion recognition Accuracy Computational modeling Speech recognition Speech enhancement Predictive models Feature extraction Data models Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

MRI Prostate and Tumor Segmentation with Fine-tuned SAM: A Path to Enhanced Treatment Planning

MRI Prostate and Tumor Segmentation with Fine-tuned SAM: A P...

引用

Medical Imaging 2025: Clinical and Biomedical Imaging

作者： Chen, Jingchu Hu, Mingzhe Safari, Mojtaba Yang, Xiaofeng Department of Radiation Oncology Winship Cancer Institute Emory University AtlantaGA30322 United States School of Mechanical Engineering Georgia Institute of Technology AtlantaGA30322 United States Department of Computer Science and Informatics Emory University AtlantaGA30322 United States

ISBN: (纸本)9781510685987

Magnetic resonance imaging (MRI) provides high spatial resolution and soft tissue contrast, which is crucial in diagnosing prostate cancer. Accurate segmentation of the prostate and dominant intraprostatic lesions on MRI is essential for guiding dose boost in radiation therapy planning. However, manual segmentation is labor-intensive and time-consuming. While current deep learning models offer automatic segmentation, they often struggle with accurately contouring the smaller, irregularly shaped DILs due to limited patient data. The Segment Anything Model (SAM), a foundation model pre-trained on a large and diverse dataset, has the potential to address these challenges and improve prostate and DIL segmentation on MRI. Studies suggest fine-tuning SAM can help SAM adapt to medical images and improve segmentation outcomes. We obtained T2-weighted MRI slices with manual contours from the Cancer Imaging Archive (TCIA) for training and evaluation. The bounding box method was employed to generate prompts for its intuitive approach and effectiveness in achieving optimal segmentation results. We trained a fine-tuned SAM model to segment the prostate and DIL. The results were compared to the segmentation results of the baseline metrics established by the SAM-only model. The fine-tuned SAM produced the best segmentation results, achieving mean Dice Similarity Coefficients (DSCs) of 0.911±0.044, 95th Percentile Hausdorff Distance (HD95) of 3.58±2.078 mm, and an Intersection over Union (IoU) of 0.862±0.059 for the prostate, and a mean DSC of 0.800±0.088, HD95 of 2.987±3.016 mm, and IoU of 0.708±0.105 for the DIL. © 2025 SPIE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Brain Magnetic Resonance Imaging Segmentation System in MS with Deep Neural Networks 18th

Brain Magnetic Resonance Imaging Segmentation System in MS w...

引用

18th EAI International Conference on Pervasive Computing Technologies for Healthcare, PervasiveHealth 2024

作者： Adamides, Giorgos Panayides, Andreas Loizou, Christos P. Nicolaou, Andria Pantzaris, Marios Pattichis, Constantinos Department of Computer Science University of Cyprus Nicosia Cyprus 3AE HEALTH LTD Nicosia Cyprus CYENS CoE Nicosia Cyprus Department of Electrical Engineering and Computer Engineering and Informatics Cyprus University of Technology Limassol Cyprus School of Molecular Medicine The Cyprus Institute of Neurology and Genetics University of Cyprus Nicosia Cyprus

ISBN: (纸本)9783031855719

Multiple Sclerosis (MS) is a chronic autoimmune disease that affects the central nervous system. Nerves are covered by a layer called myelin, which is responsible for protecting and maintaining their functionality. In the case of MS, the myelin becomes damaged, resulting in the nerves functioning unpredictably. MS is a disease characterized by relapses, which can cause permanent and irreversible damage to the patient's mobility, vision, and sensations, unless appropriate medical treatment is administered in time. This highlights the importance of the early detection of the presence or differentiation of MS using computer assisted diagnosis (CAD) systems. This study proposes an automatic segmentation approach of MS damaged regions using deep neural networks that can be integrated with any 3rd party CAD system. The data utilized comprised of a total of 1838 T2-type Magnetic Resonance Imaging (MRI) images collected from a cohort of 38 patients who underwent imaging at two distinct time points. Each MRI image was accompanied by meta-data, detailing the specific locations of the observed damage attributed to MS. The experimental setup investigated and optimized a comprehensive combination of different data preprocessing and augmentation steps, using several variations of the U-Net convolutional neural network (CNN), like U-Net++, Attention U-Net, ResUNet-a and TransUNet. The proposed methods achieved a segmentation accuracy of 0.70 based on the Dice Similarity Coefficient (DSC), a performance comparable to 2D and 3D state-of-the-art approaches in literature. A software framework encapsulating the automated model was also developed to facilitate the clinical practice workflow and underpin adoption by medical practitioners. © ICST institute for computer Sciences, Social informatics and Telecommunications engineering 2025.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Virtual Network Embedding: Literature Assessment, Recent Advancements, Opportunities, and Challenges

引用

IEEE Communications Surveys and Tutorials 2025年

作者： Satpathy, Anurag Sahoo, Manmath Narayan Swain, Chittaranjan Bellavista, Paolo Guizani, Mohsen Muhammad, Khan Bakshi, Sambit Missouri University of Science and Technology Department of Computer Science RollaMO United States National Institute of Technology Visual Surveillance Laboratory Department of Computer Science and Engineering Odisha Rourkela769008 India Atal Bihari Vajpayee Indian Institute of Information Technology and Management Department of Computer Science and Engineering Gwalior India Department of Computer Science and Engineering Italy Machine Learning Department Abu Dhabi United Arab Emirates Department of Applied Artificial Intelligence School of Convergence College of Computing and Informatics Seoul03063 Korea Republic of

Network virtualization (NV) allows service providers (SPs) to instantiate logically isolated entities called virtual networks (VNs) on top of a substrate network (SN). Though VNs bring about multiple benefits, particularly in terms of economic costs and elasticity, they also force various technical challenges to be addressed. The primary one is the issue of optimally allocating resources to VNs, also termed virtual network embedding (VNE). This paper presents an exhaustive survey of VNE by extensively covering the state-of-the-art research field in this very active field and focusing on the emerging research trends in industry and academia over the last decade. In addition, this survey originally contributes to the literature by proposing a novel taxonomy for existing VNE solutions and providing a thorough comparative study of their strategies. © 1998-2012 IEEE.

关键词： Virtual machine

来源：评论

学校读者我要写书评

暂无评论

Optimizing Logistics in E-Commerce Using Deep Random Forest for Enhanced User Satisfaction 3

Optimizing Logistics in E-Commerce Using Deep Random Forest ...

引用

3rd IEEE International Conference on Automation and Computation, AUTOCOM 2025

作者： Nisha, G.Anne Sreetha, P. Seetha, A. Manickam, K. Jagannathan, Sharath Kumar Sekar, S.D. Kyoto Computer Gakuin Department of Informatics Kyoto Japan Kpr Institute of Engineering and Technology Department of Biomedical Engineering Tamil Nadu India S. A. Engineering College Department of Information Technology Thiruverkadu Chennai India Sona College of Technology Department of Mathematics Tamil Nadu India Data Science Institute Saint Peter's University NJ United States R.M.K.Engineering College Department of Mechanical Engineering TamilNadu Chennai India

ISBN: (纸本)9798331542375

Operational efficiency is one of the most important factors affecting customer satisfaction directly in e-commerce. Still, constant addressing of timely delivery, path simplification, and reduction of delays remains challenging problems. Deep Random Forest (DRF) is a new approach presented in this work to examine and forecast significant logistics metrics including delivery times and satisfaction scores. Development of this approach targeted to solve these issues. The model makes use of e-commerce past performance including order volumes, customer comments, and delivery times. Findings: The suggested approach achieves 10% increase in user satisfaction, 12% cost reduction, and 15% faster delivery times than baseline methods. This is accomplished by means of DRF, applied to examine trends and carry out predictive modifications. Results and Methodology: These results outperform those of the benchmarks established by Gradient Boosting and XGBoost, which displayed respective rises in satisfaction of 9% and 8%. Apart from improving the quality of service, the use of DRF not only strengthened user loyalty but also contributed to improve the transportation efficiency. This approach exposes the transforming opportunities of artificial intelligence in logistics management for e-commerce systems. This approach guarantees operations with a customer-centric concentration benefiting from measurable advantages. © 2025 IEEE.

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Utilization of Distribution System Flexibility for Enhanced TSO-DSO Interoperability: A Novel Machine Learning-Based Optimal Power Flow Approach

arXiv

引用

arXiv 2025年

作者： Dindar, Burak Saner, Can Berk Çakmak, Hüseyin K. Hagenmeyer, Veit Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Karlsruhe76131 Germany Department of Electrical and Computer Engineering National University of Singapore Singapore117581 Singapore

Due to the transformation of the power system, the effective use of flexibility from the distribution system (DS) is becoming crucial for efficient network management. Leveraging this flexibility requires interoperability among stakeholders, including Transmission System Operators (TSOs) and Distribution System Operators (DSOs). However, data privacy concerns among stakeholders present significant challenges for utilizing this flexibility effectively. To address these challenges, we propose a machine learning (ML)-based method in which the technical constraints of the DSs are represented by ML models trained exclusively on non-sensitive data. Using these models, the TSO can solve the optimal power flow (OPF) problem and directly determine the dispatch of flexibility-providing units (FPUs)—in our case, distributed generators (DGs)-in a single round of communication. To achieve this, we introduce a novel neural network (NN) architecture specifically designed to efficiently represent the feasible region of the DSs, ensuring computational effectiveness. Furthermore, we incorporate various PQ charts rather than idealized ones, demonstrating that the proposed method is adaptable to a wide range of FPU characteristics. To assess the effectiveness of the proposed method, we benchmark it against the standard AC-OPF on multiple DSs with meshed connections and multiple points of common coupling (PCCs) with varying voltage magnitudes. The numerical results indicate that the proposed method achieves performant results while prioritizing data privacy. Additionally, since this method directly determines the dispatch of FPUs, it eliminates the need for an additional disaggregation step. By representing the DSs technical constraints through ML models trained exclusively on nonsensitive data, the transfer of sensitive information between stakeholders is prevented. Consequently, even if reverse engineering is applied to these ML models, no sensitive data can be extracted. This allows

关键词： Reverse engineering

来源：评论

学校读者我要写书评

暂无评论

DIPLI: Deep Image Prior Lucky Imaging for Blind Astronomical Image Restoration

arXiv

引用

arXiv 2025年

作者： Singh, Suraj Batsheva, Anastasia Rogov, Oleg Y. Bouridane, Ahmed Skolkovo Institute of Science and Technology Russia College of Computing and Informatics Computer Engineering Department University of Sharjah United Arab Emirates AIRI Russia

Contemporary image restoration and super-resolution techniques effectively harness deep neural networks, markedly outperforming traditional methods. However, astrophotography presents unique challenges for deep learning due to limited training data. This work explores hybrid strategies, such as the Deep Image Prior (DIP) model, which facilitates blind training but is susceptible to overfitting, artifact generation, and instability when handling noisy images. We propose enhancements to the DIP model’s baseline performance through several advanced techniques. First, we refine the model to process multiple frames concurrently, employing the Back Projection method and the TVNet model. Next, we adopt a Markov approach incorporating Monte Carlo estimation, Langevin dynamics, and a variational input technique to achieve unbiased estimates with minimal variance and counteract overfitting effectively. Collectively, these modifications reduce the likelihood of noise learning and mitigate loss function fluctuations during training, enhancing result stability. We validated our algorithm across multiple image sets of astronomical and celestial objects, achieving performance that not only mitigates limitations of Lucky Imaging, a classical computer vision technique that remains a standard in astronomical image reconstruction but surpasses the original DIP model, state of the art transformer- and diffusion-based models, underscoring the significance of our improvements. © 2025, CC BY-NC-SA.

关键词： Markov processes

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：