检索结果-内蒙古大学图书馆

Development and Validation of a Preoperative Ct-Based Signature Using Automatically Segmented Tumor and Perirenal Adipose Tissue to Predict Pathological Grading of Clear Cell Renal Cell Carcinoma

SSRN

引用

SSRN 2023年

作者： Li, Shichao Zhou, Ziling Gao, Mengmeng Liao, Zhouyan He, Kangwen Qu, Weinuo Kemal, Ihab R. Zhang, Qingpeng Li, Zhen Department of Radiology Tongji Hospital Tongji Medical College Huazhong University of Science and Technology Hubei Wuhan China Department of Pharmacology and Pharmacy LKS Faculty of Medicine The Musketeers Foundation Institute of Data Science The University of Hong Kong Hong Kong Department of Radiology University of Colorado Denver Anschutz Medical Campus AuroraCO United States

Background: Accurate preoperative prediction of the pathological grade of clear cell renal cell carcinoma (ccRCC) is crucial for optimal treatment planning and patient outcomes. This study aims to develop and validate a deep learning (DL) algorithm to automatically segment renal tumors, kidneys, and perirenal adipose tissue (PRAT) from CT images, and extract radiomics features to predict the pathological grade of ***: A two-dimensional TransUNet-based DL model combined with the train-while-annotation method was trained for automatic volumetric segmentation of renal tumors, kidneys, and visceral adipose tissue (VAT) on images from two groups of datasets. PRAT was extracted using a dilation algorithm by calculating voxels of VAT surrounding the kidneys. Radiomics features were subsequently extracted from three regions of interest of CT images adopting multiple filtering strategies. The least absolute shrinkage and selection operator (LASSO) regression was used for feature selection, and the support vector machine (SVM) for developing the pathological grading model. Ensemble learning was used for imbalanced data classification. Performance evaluation included the Dice coefficient for segmentation and metrics such as accuracy and AUC for classification. The WHO/ISUP grading models were finally interpreted and visualized using the SHapley Additive exPlanations (SHAP) ***: For automatic segmentation, the mean Dice coefficient achieved 0.836 for renal tumors and 0.967 for VAT on the internal validation dataset. For WHO/ISUP grading, a model built with features of PRAT showed moderate predictive value, with an AUC of 0.711 (95% CI, 0.604-0.802) in the internal validation set. While model built with combination features of renal tumor, kidney, and PRAT showed an AUC of 0.814 (95% CI, 0.717-0.889) in the internal validation set, significantly higher than the model built with features solely from tumor lesion (0.760;95% CI, 0.657-0.845).Interpretation: By

关键词： Cells

来源：评论

学校读者我要写书评

暂无评论

RIS-Assisted Passive Localization (RAPL): An Efficient Zero-Overhead Framework Using Conditional Sample Mean

arXiv

引用

arXiv 2025年

作者： Yao, Jiawei Mao, Yijie Chen, Mingzhe Hu, Ye School of Information Science and Technology ShanghaiTech University Shanghai201210 China Department of Electrical and Computer Engineering Frost Institute for Data Science and Computing University of Miami Coral GablesFL33146 United States Department of Industrial and Systems Engineering University of Miami Coral GablesFL33146 United States

Reconfigurable Intelligent Surface (RIS) has been recognized as a promising solution for enhancing localization accuracy. Traditional RIS-based localization methods typically rely on prior channel knowledge, beam scanning, and pilot-based assistance. These approaches often result in substantial energy and computational overhead, and require real-time coordination between the base station (BS) and the RIS. To address these challenges, in this work, we move beyond conventional methods and introduce a novel data-driven, multiple RISs-assisted passive localization approach (RAPL). The proposed method includes two stages, the angle-of-directions (AoDs) between the RISs and the user is estimated by using the conditional sample mean in the first stage, and then the user’s position is determined based on the estimated multiple AoD pairs in the second stage. This approach only utilizes the existing communication signals between the user and the BS, relying solely on the measurement of received signal power at each BS antenna for a set of randomly generated phase shifts across all RISs. Moreover, by obviating the need for real-time RIS phase shift optimization or user-to-BS pilot transmissions, the method introduces no additional communication overhead, making it highly suitable for deployment in real-world networks. The proposed scheme is then extended to multi-RIS scenarios considering both parallel and cascaded RIS topologies. Numerical results show that the proposed RAPL improves localization accuracy while significantly reducing energy and signaling overhead compared to conventional methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

Speech Separation for Low-Resource Languages

Speech Separation for Low-Resource Languages

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Marvin Borsdorf Zexu Pan Pascal Himmelmann Haizhou Li Tanja Schultz Machine Listening Lab University of Bremen Bremen Germany Alibaba Group Singapore Department of Mathematics and Computer Science FernUniversität in Hagen Hagen Germany School of Data Science Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China Department of Electrical and Computer Engineering National University of Singapore Singapore Cognitive Systems Lab University of Bremen Bremen Germany

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Speech separation aims to equip machines with the human ability of selective listening, i.e. to focus attention on specific information in spoken communication. Studies have shown that the language spoken in a cocktail party scenario matters. While the development of speech separation models can leverage extensive databases, for the majority of languages only very limited data is available. This work presents the very first study on speech separation for low-resource languages. We choose blind source separation as the task to be studied and analyze three strategies to overcome the data scarcity of two low-resource languages from the GlobalPhoneMS2 database. We show that data from other languages can be used to develop models that work for low-resource languages. Finetuning additionally boosts the performance, and training on multiple languages increases both performance and robustness. We show that dynamic mixing in the development helps to find a trade-off between performance and development time.

关键词： Training Measurement databases Signal processing data models Blind source separation Robustness Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

Context-aware Inductive Graph Matrix Completion with Sentence BERT

Context-aware Inductive Graph Matrix Completion with Sentenc...

引用

IEEE International Conference on Web Services (ICWS)

作者： Donghee Han Daehee Kim Keejun Han Mun Yong Yi Graduate School of Data Science Korea Advanced Institute of Science and Technology Daejeon Republic of Korea School of Computer Engineering Hansung University Seoul Republic of Korea Department of Industrial and Systems Engineering Korea Advanced Institute of Science and Technology Daejeon Republic of Korea

Existing graph neural network (GNN) based recommendation models depend highly on initial node features and graph structures. Most prior studies do not support the use of additional information on user-item interactions and adopt a transductive method, which has limitations for actual web service. To overcome these problems, we propose Context-aware Inductive Graph Matrix Completion (CGMC), which utilizes context vectors that represent user-item interactions and user-item bipartite graph structures in an inductive manner. Our method constructs context vectors from the review, timestamp, and rating and uses them as edge features of the user-item bipartite graph. Relations between homogeneous nodes are also constructed based on common neighbors. Our model combines context vectors and relational information using Context-aware Graph Attention Networks and Edge Fusion Graph Convolutional Networks. We conducted extensive experiments using six real-world datasets, and the results show that the proposed model achieves superior performances over other competing models. Furthermore, we analyzed the inductive characteristics of CGMC through the cross-domain transferability. The source code is available in the repository at [https://***/venzino-han/CGMC_SBERT].

关键词：

来源：评论

学校读者我要写书评

暂无评论

Label-Free Biomolecule Detection with InP/AlGaAs Charge Plasma Dielectric-Modulated Vertical TFET Using TaN as Metal Gate

引用

IEEE Access 2025年 13卷 89667-89684页

作者： Elshafie, Hashim Alqahtani, Abdulrahman Saad Mubarakali, Azath Adarsh Rag, S. Venkatesh, M. Parthasarathy, P. King Khalid University College of Computer Science Department of Computer Engineering Abha61421 Saudi Arabia University of Bisha College of Computing and Information Technology Bisha67714 Saudi Arabia King Khalid University College of Computer Science Department of Informatics and Computer Systems Abha61421 Saudi Arabia Manipal Institute of Technology Department of Data Science and Computer Applications Manipal Academy of Higher Education Manipal576104 India CMR Institute of Technology Department of Electronics and Communication Engineering Karnataka Bengaluru560037 India

This study introduces a label-free biosensing method for biomolecule detection utilizing an InP/AlGaAs charge plasma dielectric-modulated vertical tunnel field-effect transistor (InP/AlGaAs VTFET) featuring TaN as the metal gate. The device comprises a nanocavity beneath the gate metal adjacent to the tunnelling junction, where biomolecules engage with the dielectric material, resulting in fluctuations in the drain current. A twin metal gate architecture with laterally split dielectrics is employed to eliminate short-channel effects. The biosensor has exceptional sensitivity, attaining a peak drain current sensitivity of 2.5 × 10 cm2 for biomolecules such as albumin (k = 7). The gadget proficiently identifies biomolecules with varying dielectric constants and charge distributions, enabling adaptable label-free detection of diverse targets. The study examines the influence of dielectric constant on critical metrics such as Energy Band Diagrams, Drain Current, Drain Sensitivity, and subthreshold swing (SS). The overlap between the source and pocket regions, along with the introduction of an auxiliary gate, optimizes the electrical characteristics. Simulation results show that the proposed InP/AlGaAs VTFET achieves a maximum sensitivity of 3.5 × 103, outperforming configurations without overlap (2 × 103), highlights the potential of proposed InP/AlGaAs VTFET for scalable, high-sensitivity, label-free biomolecule detection. © 2013 IEEE.

关键词： Junction gate field effect transistors

来源：评论

学校读者我要写书评

暂无评论

Analysis of Artificial Intelligence in Medical Sectors

Analysis of Artificial Intelligence in Medical Sectors

引用

2022 International Conference on Augmented Intelligence and Sustainable systems, ICAISS 2022

作者： Thilagavathi, J. Lavanya, K. Elango, S. Santhoshi, M. Muthumanickam, T. Ramachandran, G. Arjun College of Technology Dept of Artificial Intelligence and Data Science Coimbatore India Madanapalle Institute of Technology & Science Dept of CSE Andhra Pradesh Chittoor India CVR College of Engineering Department of Electronics and Communication Engineering Telangana India Department of Electronics and Communication Engineering Vinayaka Mission's Kirupananda Variyar Engineering College Vinayaka Mission's Research Foundation Deemed to Be University Salem India Salem India

ISBN: (纸本)9781665489621

Medical engineering research has recently advanced significantly. The ability to accurately record a significant amount of medical data has increased because to advancements in measuring device technology, which has caused medical data to rise rapidly. A significant amount of data has been encountered and it is crucial to use this enormous amount of data sensibly. By using an Artificial Intelligence (AI) based reasoning engine to scan medical data, it is possible to compile user-generated keywords and instantly suggest relevant content to users. The decision tree algorithm is emphasized as one of the main technologies to implement data mining in this research, and it also explores how data mining technology is used in clinical medical diagnosis mining and analysis. © 2022 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

SPEAR: Design and Implementation of an Advanced Virtual Assistant

SPEAR: Design and Implementation of an Advanced Virtual Assi...

引用

Sustainable Expert systems (ICSES), International Conference on

作者： Garima Jain Amita Shukla Nitesh Kumar Bairwa Anamika Chaudhary Ashish Patel Ankush Jain Department of Computer Science and Buisness Systems Noida Institute of Engineering and Technology Greater Noida India Department of Artificial Intelligence Noida Institute of Engineering and Technology Greater Noida India Department of Data Science Noida Institute of Engineering and Technology Greater Noida India Department of Artificial Intelligence and Machine Learning Dronacharya Group of Institutions Greater Noida India Department of Computer Science and Enginnering Netaji Subhash University of Technology Delhi India

ISBN: (数字)9798331540364

ISBN: (纸本)9798331540371

This research presents the development and evaluation of SPEAR, an advanced voice-activated personal desktop assistant designed to address challenges in existing virtual assistant technology, such as limited language support, low recognition accuracy, and inadequate task automation. Despite recent advancements in Natural Language Processing (NLP) and machine learning, implementation in current systems remains subpar. SPEAR achieves an 88% overall command execution success rate, with a speech recognition accuracy of 92% and an average response time of 1.8 seconds, demonstrating efficiency in real-time interactions. Developed using Python and machine learning libraries, SPEAR supports 15 voice commands across multiple platforms, excelling in note creation (95% success), web searching (94%), and information retrieval (92%). Its natural language understanding score of 0.86 and context retention rate of 75% highlight its conversational capabilities. While the assistant performs well in messaging functionality (85% success) and currently supports three languages, expanding its multilingual capabilities is essential for broader user engagement. Metrics indicate a satisfaction score of 8.2/10 and an average of 12 daily interactions per user, showcasing its practical utility. Additionally, the system's text-to-speech quality (8.5/10) and error recovery rate (82 %) affirm its robustness. These findings contribute valuable insights for future research, focusing on enhancing multilingual support, broadening task categories, and improving context retention, ultimately positioning SPEAR to rival established industry leaders by offering a comprehensive suite of services.

关键词： Accuracy Personal voice assistants Machine learning Information retrieval Natural language processing Real-time systems Robustness Text to speech Time factors Web search

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Model to Predict the Breast Cancer using Stacking and Bagging Model

A Hybrid Model to Predict the Breast Cancer using Stacking a...

引用

Mobile Networks and Wireless Communications (ICMNWC), IEEE International Conference on

作者： S. Yuvalatha S. Nithyapriya S. Prabhavathy R. Priyadharshini S. Savitha S. Kayathri Department of Computer Science and Business Systems Bannari Amman Institute of Technology Sathyamangalam India Department of Artificial Intelligence and Data Science Bannari Amman Institute of Technology Sathyamangalam India Department of Electronics and Communication Engineering Christ the King Engineering College Coimbatore India Department of Computer Science and Engineering Sri Ranganathar Institute of Engineering Coimbatore India Department of Computer and Science and Engineering PSR Engineering College Sivakasi India

Breast cancer is a malignant tumor that develops in the cells of the breast tissue. Breast cancer is one of the major causes of death for women globally. In the examination of medical data, breast cancer prediction is a difficult task. To make decisions and accurately distinguish between benign and malignant tumors, physicians and pathologists need certain automated technologies. In this paper, hybrid ensemble technique (Bagging and Stacking) is used to predict the breast tumors as benign and malignant tumors. In the proposed work, the subset of data is created from the initial Wisconsin (Diagnostic) data Set by bootstrapping technique. Each bootstrap dataset is used to train the weak learner. The weak learners are K-Nearest Neighbors (KNN) Random Forest (RF), Decision Tree (DT) and Support Vector Machine (SVM). The Logistic Regression (LR) is used as the Meta Learner. The Meta Learner uses the predictions of weak learners as its training data. The proposed hybrid ensemble model obtains an accuracy 98.7%, Precision 98.83%, Recall 98.54%, F1 Score 98.68% and 0.012% error

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Behavior Sequential Recommendation with Temporal Graph Transformer

arXiv

引用

arXiv 2022年

作者： Xia, Lianghao Huang, Chao Xu, Yong Pei, Jian The Department of Computer Science & Musketeers Foundation Institute of Data Science The University of Hong Kong Hong Kong Hong Kong The School of Computer Science and Technology South China University of Technology Guangzhou China School of Computing Science Simon Fraser University Canada

Modeling time-evolving preferences of users with their sequential item interactions, has attracted increasing attention in many online applications. Hence, sequential recommender systems have been developed to learn the dynamic user interests from the historical interactions for suggesting items. However, the interaction pattern encoding functions in most existing sequential recommender systems have focused on single type of user-item interactions. In many real-life online platforms, user-item interactive behaviors are often multi-typed (e.g., click, add-to-favorite, purchase) with complex cross-type behavior inter-dependencies. Learning from informative representations of users and items based on their multi-typed interaction data, is of great importance to accurately characterize the time-evolving user preference. In this work, we tackle the dynamic user-item relation learning with the awareness of multi-behavior interactive patterns. Towards this end, we propose a new Temporal Graph Transformer (TGT) recommendation framework to jointly capture dynamic short-term and long-range user-item interactive patterns, by exploring the evolving correlations across different types of behaviors. The new TGT method endows the sequential recommendation architecture to distill dedicated knowledge for type-specific behavior relational context and the implicit behavior dependencies. Experiments on the real-world datasets indicate that our method TGT consistently outperforms various state-of-the-art recommendation methods. Our model implementation codes are available at https://***/akaxlh/TGT. Copyright © 2022, The Authors. All rights reserved.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Wireless Sensor Network Routing Strategies with Machine Learning Protocols

Enhancing Wireless Sensor Network Routing Strategies with Ma...

引用

Networking and Communications (ICNWC), International Conference on

作者： Veeranjaneyulu K Lakshmi M Sri Venkateswara Swamy Sirisha K Nagarjuna N Anupkant S CVR College of Engineering Rangareddy Telangana India Data Science and Business Systems College of Engineering & Technology SRMIST Chennai India Vishnu Institute of Technology (A) Bhimavaram Andhra Pradesh India Department of CSE Siddharth Institute of Engineering & Technology Puttur A.P India Department of CSIT CVR College of Engineering Rangareddy Telangana India

ISBN: (数字)9798350365269

ISBN: (纸本)9798350365276

Woth the realm of Internet supportive Things (IoT), where numerous wireless components constantly communicate, a unique challenge arises. This challenge includes issues such as handling diverse devices, ensuring data broadcasting and managing scalability. To handle these issues, a new routing protocol has been proposed in this paper. This protocol is intelligent, energy-conscious, and employs a multi-objective approach, based on the distribution type Reinforcment based Learn -Driven (RL) mechanism integrated Meta-Learning termed as data synchronized -Machine learning (DS-ML). The core goal of proposed data-route mechanism, called DS-ML, will optimized power consumption on IoT connected networks, a critical issue given the defined power resources of wireless connected IoT Components. Additionally, mechanism focuses on adapting to network changes seamlessly by ensuring smooth adjustments to alterations and minimizing disruptions to enhances entire network Efficacy. The algorithm incorporates correlates issues in rewards designed in acceleration of the learn cycle. Through various simulation parameters, the DS-ML routing protocol demonstrated significant improvements in power efficacy and rapid adapt in unexpected network happenings. This was evidenced by enhancements in delivered ratio of data sets and reductions in data-sets delivery latency when compares in conventional data-routing Techniques. In general, proposed DS-ML system represents a solution for enhancing the performances and sustainability of IoT network infrastructure.

关键词： Wireless communication Metalearning Wireless sensor networks Energy consumption Scalability Routing Routing protocols

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：