检索结果-内蒙古大学图书馆

Ophthalmic Technologies XXXV 2025

作者： Gholami, Sina Jannat, Fatema-E Haghighi, Tania Thompson, Atalie Carina Ong, Sally Shin Yee Lim, Jennifer I. Leng, Theodore Tabkhivayghan, Hamed Alam, Minhaj Nur Department of Electrical and Computer Engineering University of North Carolina at Charlotte CharlotteNC United States Department of Ophthalmology Wake Forest School of Medicine Winston-SalemNC United States Department of Ophthalmology and Visual Science University of Illinois at Chicago ChicagoIL United States Byers Eye Institute at Stanford Stanford University School of Medicine StanfordCA United States

ISBN: (纸本)9781510683488

Early identification of ophthalmic disease can lead to timely interventions, potentially preventing or minimizing vision loss and improving patient outcomes. Proper classification of ophthalmic disease ensures that patients receive accurate diagnoses which is essential for effective treatment planning. This study introduces an innovative deep learning (DL) framework that uses recent advancements in diffusion models to classify various pathological retinal disease datasets. The performance is compared to traditional baseline methods using optical coherence tomography (OCT) images. Our framework comprises two networks: one for training a model for the reverse diffusion process and the other for semantic encoding to condition the denoising process and improve the outcomes of the first model. With these two networks, we pre-trained a semantic encoder that captures the most prominent features of OCT images. Then we compared the pre-trained semantic encoder with a baseline model on six different multi-class classification tasks. Our findings show the superiority of the pre-trained model and indicate the possibility of using the diffusion process as an unsupervised pre-training phase. © 2025 SPIE.

关键词： Optical coherence tomography Machine learning Diffusion Education and training Semantics Image processing Data modeling Classification systems Denoising Retinal diseases

来源：评论

学校读者我要写书评

暂无评论

Advancing Glaucoma Diagnosis Through Multi-Scale Feature Extraction and Cross-Attention Mechanisms in Optical Coherence Tomography Images

Engineering Reports

引用

engineering Reports 2025年第4期7卷

作者： Khajeha, Hamid Reza Fateh, Mansoor Abolghasemi, Vahid Fateh, Amir Reza Emamian, Mohammad Hassan Hashemi, Hassan Fotouhi, Akbar Faculty of Computer Engineering Shahroud University of Technology Shahrud Iran School of Computer Science and Electronic Engineering University of Essex Colchester United Kingdom Tehran Iran Ophthalmic Epidemiology Research Center Shahroud University of Medical Sciences Shahroud Iran Noor Ophthalmology Research Center Noor Eye Hospital Tehran Iran Department of Epidemiology and Biostatistics School of Public Health Tehran University of Medical Sciences Tehran Iran

Glaucoma is a major cause of irreversible vision loss, resulting from damage to the optic nerve. Hence, early diagnosis of this disease is crucial. This study utilizes optical coherence tomography (OCT) images from the "Shahroud Eye Cohort Study" dataset which has an unbalanced nature, to diagnose this disease. To address this imbalance, a novel approach is proposed, combining weighted bagging ensemble learning with deep learning models and data augmentation. Specifically, the glaucoma data is expanded sixfold using data augmentation techniques, and the normal data is stratified into five groups. Glaucoma samples were subsequently merged into each group, and independent training was performed. In addition to data balancing, the proposed method incorporates key architectural innovations, including multi-scale feature extraction, a cross-attention mechanism, and a Channel and Spatial Attention Module (CSAM), to improve feature extraction and focus on critical image regions. The suggested approach achieves an impressive accuracy of 98.90% with a 95% confidence interval of (96.76%, 100%) for glaucoma detection. In comparison to the earlier leading methods ConvNeXtLarge model, our method exhibits a 2.2% improvement in accuracy while using fewer parameters. These results have the potential to significantly aid ophthalmologists in early glaucoma detection, leading to more effective treatment interventions. © 2025 The Author(s). engineering Reports published by John Wiley & Sons Ltd.

关键词： deep neural network ensemble learning glaucoma Shahroud Eye Cohort Study

来源：评论

学校读者我要写书评

暂无评论

Channel and Spectrum Consumption Models for Urban Outdoor-to-Outdoor 28 GHz Wireless

arXiv

引用

arXiv 2025年

作者： Kohli, Manav Caicedo, Carlos E. Chen, Tingjun Tamim, Irfan Estigarribia, Angel D. Dai, Tianyi Kadota, Igor Chizhik, Dmitry Du, Jinfeng Feick, Rodolfo Valenzuela, Reinaldo A. Zussman, Gil Department of Electrical Engineering Columbia University New YorkNY10027 United States School of Information Sciences Syracuse University SyracuseNY13210 United States Department of Electrical and Computer Engineering Duke University DurhamNC27708 United States Department of Electrical and Computer Engineering Northwestern University EvanstonIL60208 United States Nokia Bell Labs Murray HillNJ07974 United States Department of Electronics Engineering Universidad Técnica Federico Santa María Valparaíso234000 Chile

Next generation wireless and mobile networks will utilize millimeter-wave (mmWave) communication to achieve significantly increased data rates. However, since mmWave radio signals experience high path loss, the operation of mmWave networks will require accurate channel models designed for specific deployment sites. In this paper, we focus on the deployment area of the PAWR COSMOS testbed in New York City and report extensive 28 GHz channel measurements. These include over 46 million power measurements collected from over 3,000 links on 24 sidewalks at 4 different sites and in different settings. Using these measurements, we study the effects of the setup and environments (e.g., transmitter height and seasonal effects). We then discuss the obtained path gain values and their fitted lines, and the resulting effective azimuth beamforming gain. Based on these results, we also study the link SNR values that can be supported on individual sidewalks and the corresponding theoretically achievable data rates. Finally, we develop a process to transform the measurements and generate Spectrum Consumption Models (SCMs) based on the IEEE 1900.5.2 standard. The generated SCMs facilitate the evaluation of spectrum sharing and interference management scenarios since they capture all the directional propagation effects reflected in the measurements and provide a way to easily share the main propagation characterization results derived from the measurements. We believe that the results can inform the COSMOS testbed deployment process and provide a benchmark for other deployment efforts in dense urban areas. © 2025, CC BY.

关键词： Testbeds

来源：评论

学校读者我要写书评

暂无评论

A Near-Optimal Category Information Sampling in RFID Systems

引用

IEEE Transactions on Mobile Computing 2025年

作者： Wang, Xiujun Liu, Zhi Zhou, Xiaokang Liao, Yong Hu, Han Zheng, Xiao Li, Jie Anhui University of Technology School of Computer Science Ma'anshan243032 China Anhui Engineering Research Center for Intelligent Applications and Security of Industrial Internet Ma'anshan243032 China University of Electro-Communications Graduate School of Informatics and Engineering Tokyo182- 8585 Japan Shiga University Faculty of Data Science Hikone522-8522 Japan RIKEN Center for Advanced Intelligence Project Tokyo103-0027 Japan University of Science and Technology of China School of Cyber Science and Technology Hefei China Beijing Institute of Technology School of Information and Electronics Beijing China School of Electronic Information and Electrical Engineering Shanghai200240 China

In many RFID-enabled applications, objects are classified into different categories, and the information associated with each object's category (called category information) is written into the attached tag, allowing the reader to access it later. The category information sampling in such RFID systems, which is to randomly choose (sample) a few tags from each category and collect their category information, is fundamental for providing real-time monitoring and analysis in RFID. However, to the best of our knowledge, two technical challenges, i.e., how to guarantee a minimized execution time and reduce collection failure caused by missing tags, remain unsolved for this problem. In this paper, we address these two limitations by considering how to use the shortest possible time to sample a different number of random tags from each category and collect their category information sequentially in small batches. In particular, we first obtain a lower bound on the execution time of any protocol that can solve this problem. Subsequently, we present a near-OPTimal Category information sampling protocol (OPT-C) that solves the problem with an execution time close to the lower bound. Finally, extensive simulation results demonstrate the superiority of OPT-C over existing protocols, while real-world experiments further validate its practicality. © 2002-2012 IEEE.

关键词： category information sampling execution time lower bound near-optimal protocol RFID systems

来源：评论

学校读者我要写书评

暂无评论

Way to Specialist: Closing Loop Between Specialized LLM and Evolving Domain Knowledge Graph 25

Way to Specialist: Closing Loop Between Specialized LLM and ...

引用

Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1

作者： Yutong Zhang Lixing Chen Shenghong Li Nan Cao Yang Shi Jiaxin Ding Zhe Qu Pan Zhou Yang Bai School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China College of Design and Innovation Tongji University Shanghai China John Hopcroft Center for Computer Science Shanghai Jiao Tong University Shanghai China School of Computer Science and Engineering Central South University Changsha Hunan China School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan Hubei China Department of Automation Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9798400712456

Large language models (LLMs) have demonstrated exceptional performance across a wide variety of domains. Nonetheless, generalist LLMs continue to fall short in reasoning tasks necessitating specialized knowledge, e.g., emotional sociology and medicine. Prior investigations into specialized LLMs focused on domain-specific training, which entails substantial efforts in domain data acquisition and model parameter fine-tuning. To address these challenges, this paper proposes the Way-to-Specialist (WTS) framework, which synergizes retrieval-augmented generation with knowledge graphs (KGs) to enhance the specialized capability of LLMs in the absence of specialized training. In distinction to existing paradigms that merely utilize external knowledge from general KGs or static domain KGs to prompt LLM for enhanced domain-specific reasoning, WTS proposes an innovative ''LLM↻KG'' paradigm, which achieves bidirectional enhancement between specialized LLM and domain knowledge graph (DKG). The proposed paradigm encompasses two closely coupled components: the DKG-Augmented LLM and the LLM-Assisted DKG Evolution. The former retrieves question-relevant domain knowledge from DKG and uses it to prompt LLM to enhance the reasoning capability for domain-specific tasks; the latter leverages LLM to generate new domain knowledge from processed tasks and use it to evolve DKG. WTS closes the loop between DKG-Augmented LLM and LLM-Assisted DKG Evolution, enabling continuous improvement in the domain specialization as it progressively answers and learns from domain-specific questions. We validate the performance of WTS on 7 datasets (e.g., TweetQA, ChatDoctor5k) spanning 6 domains, e.g., emotional sociology, medical, ect. The experimental results show that WTS surpasses the previous SOTA in 5 specialized domains, and achieves a maximum performance improvement of 11.3%.

关键词： domain knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Evaluation of machine learning-based regression techniques for prediction of diabetes levels fluctuations

引用

Heliyon 2025年第1期11卷 e41199页

作者： Alkalifah, Badriah Shaheen, Muhammad Tariq Alotibi, Johrah Alsubait, Tahani Alhakami, Hosam Department of Computer Science and Artificial Intelligence College of Computing Umm Al-Qura University Makkah Saudi Arabia School of Electrical Engineering and Computer Science NUST Islamabad Pakistan Department of Software Engineering College of Computing Umm Al-Qura University Makkah Saudi Arabia

Middle-Aged and Elderly people today face a variety of health problems as a result of their modern lifestyle, which includes increased work stress, less physical activity, and altered food habits. Because of Complications arising, diabetes has become one of the most frequent, severe, and fatal illnesses around the world. Therefore, inaccurate measurements of blood glucose levels can seriously damage vital organs. Several strategies for long-term glucose prediction have been proposed in the literature. Unfortunately, these methods require the patient to identify their daily activities, which can be error-prone, such as meal intake, insulin injection, and emotional aspects. This paper suggests using continuous glucose monitoring (CGM) of 14733 patients, with three assistance factors to predict blood glucose levels independently of other parameters, hence reducing the burden on the patients. To support this an Artificial Neural Network (ANN), Binary Decision Tree (BDT), Linear Regression (LR), Boosting Regression Tree Ensemble (BSTE), Linear Regression with Stochastic Gradient Descent (LRSGD), Stepwise (SW), Support Vector Machine (SVM), and Gaussian process regression (GPR) were investigated. The result indicated that The highest classification accuracy of (92.58%) has been achieved by BDT followed by BSTE (92.04%) and GPR (88.59%). The obtained average of root means square error (MSE) was 1.64, 1.67, 1.69, mg/dL for prediction horizon (PH) respectively to GPR, BSTE, and ANN. © 2024 The Author(s)

关键词： Continuous glucose monitoring (CGM) Diabetic Hyperglycemia Hypoglycemia Machine learning (ML) Regression

来源：评论

学校读者我要写书评

暂无评论

Harnessing the Power of AI With Deep Learning: Innovations and Implications

Harnessing the Power of AI With Deep Learning: Innovations a...

引用

Computational, Communication and Information Technology (ICCCIT), International Conference on

作者： Talluri Upender C. Sathiyamoorthy Udayakumar K D. Kirubakaran Purushothaman V Kiruba Thangam Raja Department of CSE CMR College of Engineering and Technology Medchal Hyderabad Telangana Department of Commerce Saveetha College of Liberal Arts and Sciences Saveetha Institute of Medical and Technical Sciences (SIMATS) Chennai Tamil Nadu India Department of CSE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Computer Science and Engineering R.M.K. Engineering College Chennai Tamil Nadu India Department of Electronics and Communication Engineering Chennai Institute of Technology Chennai Tamil Nadu India Department of Software and Systems Engineering School of Computer Science Engineering and Information Systems (SCORE) VIT University Vellore Tamil Nadu India

ISBN: (数字)9798331512965

ISBN: (纸本)9798331512972

The rapid advancements in artificial intelligence (AI) and deep learning have revolutionized various sectors, enabling unprecedented levels of innovation and efficiency. This paper delves into the transformative impact of deep learning across multiple domains, highlighting key innovations and their broader implications. By examining cutting-edge applications in healthcare, finance, autonomous systems, and natural language processing, the study elucidates how deep learning models, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), are pushing the boundaries of what's possible. Moreover, the paper explores the integration of deep learning with emerging technologies such as the Internet of Things (IoT), edge computing, and quantum computing, underscoring the synergistic potential of these combinations. The role of deep learning in predictive analytics and personalized solutions is discussed, showcasing its ability to enhance decision-making processes and improve user experiences. Furthermore, the paper discusses the ethical considerations, challenges, and future prospects associated with the widespread adoption of deep learning technologies. The insights provided aim to foster a deeper understanding of how harnessing AI with deep learning can drive progress while addressing critical societal and technological issues.

关键词： Deep learning Technological innovation Ethics Recurrent neural networks Autonomous systems Finance Medical services Safety Internet of Things Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Large Language Models for Bioinformatics

arXiv

引用

arXiv 2025年

作者： Ruan, Wei Lyu, Yanjun Zhang, Jing Cai, Jiazhang Shu, Peng Ge, Yang Lu, Yao Gao, Shang Wang, Yue Wang, Peilong Zhao, Lin Wang, Tao Liu, Yufang Fang, Luyang Liu, Ziyu Liu, Zhengliang Li, Yiwei Wu, Zihao Chen, Junhao Jiang, Hanqi Pan, Yi Yang, Zhenyuan Chen, Jingyuan Liang, Shizhe Zhang, Wei Ma, Terry Dou, Yuan Zhang, Jianli Gong, Xinyu Gan, Qi Zou, Yusong Chen, Zebang Qian, Yuanxin Yu, Shuo Lu, Jin Song, Kenan Wang, Xianqiao Sikora, Andrea Li, Gang Li, Xiang Li, Quanzheng Wang, Yingfeng Zhang, Lu Abate, Yohannes He, Lifang Zhong, Wenxuan Liu, Rongjie Huang, Chao Liu, Wei Shen, Ye Ma, Ping Zhu, Hongtu Yan, Yajun Zhu, Dajiang Liu, Tianming School of Computing University of Georgia GA United States Department of Computer Science and Engineering University of Texas ArlingtonTX United States Department of Statistics University of Georgia GA United States Department of Epidemiology and Biostatistics University of Georgia AthensGA United States Department of Biostatistics UNC Chapel HillNC United States Department of Radiation Oncology Mayo Clinic PhoenixAZ United States Institute of Plant Breeding Genetics & Genomics University of Georgia AthensGA United States School of Computer and Cyber Sciences Augusta University GA United States School of Computer Science Carnegie Mellon University PittsburghPA United States College of Engineering University of Georgia AthensGA United States Department of Biomedical Informatics University of Colorado CO United States Department of Radiology University of North Carolina Chapel HillNC United States Department of Radiology Massachusetts General Hospital Harvard Medical School MA United States Department of Computer Science and Engineering University of Tennessee ChattanoogaTN United States Department of Computer Science Indiana University IndianapolisIN United States Department of Physics and Astronomy University of Georgia AthensGA United States Department of Computer Science and Engineering Lehigh University PA United States

With the rapid advancements in large language model (LLM) technology and the emergence of bioinformatics-specific language models (BioLMs), there is a growing need for a comprehensive analysis of the current landscape, computational characteristics, and diverse applications. This survey aims to address this need by providing a thorough review of BioLMs, focusing on their evolution, classification, and distinguishing features, alongside a detailed examination of training methodologies, datasets, and evaluation frameworks. We explore the wide-ranging applications of BioLMs in critical areas such as disease diagnosis, drug discovery, and vaccine development, highlighting their impact and transformative potential in bioinformatics. We identify key challenges and limitations inherent in BioLMs, including data privacy and security concerns, interpretability issues, biases in training data and model outputs, and domain adaptation complexities. Finally, we highlight emerging trends and future directions, offering valuable insights to guide researchers and clinicians toward advancing BioLMs for increasingly sophisticated biological and clinical applications. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ESARSA-MRFO-FS: Optimizing Manta-ray Foraging Optimizer using Expected-SARSA reinforcement learning for features selection

引用

Knowledge-Based Systems 2025年 321卷

作者： AbdulAzeem, Yousry Magdy Balaha, Hossam Bamaqa, Amna Badawy, Mahmoud Elhosseini, Mostafa A. Zewail City of Science and Technology October Gardens 6th of October City Giza12578 Egypt Bioengineering Department J.B. Speed School of Engineering University of Louisville LouisvilleKY United States Computers and Control Systems Engineering Department Mansoura University Faculty of Engineering Mansoura35516 Egypt Department of Computer Science and Information Applied College Taibah University Madinah42353 Saudi Arabia Department of Information Systems College of Computer Science and Engineering Taibah University Yanbu46421 Saudi Arabia

Disease prediction with the help of computers has achieved significant progress in this area;however, it still requires a more accurate identification of each data feature. In the past few years, ML-based medical diagnoses have become increasingly dependent on the datasets rather than the algorithms. Consequently, the more features in a dataset, the more difficult the model training process will be. A feature selection (FS) strategy can be used to eliminate unwanted features before the training in order to improve the model performance. Due to the great increase in the number of features, FS causes a complex combinatorial problem, which is NP-hard. The primary goal of this research is to create a novel framework for improving the Manta-ray Foraging Optimizer (MRFO) algorithm's performance. By the method of exploration–exploitation toggle adjustments, this process becomes the most efficient one by using the Expected State–action-reward-state–action (ESARSA) reinforcement learning strategy. The study employed 12 datasets as well as two classifiers (K-Nearest-Neighbor and Decision-Tree), both with and without hyperparameter adjustment. The study compared the performances of three feature selection methods: no feature selection, the original MRFO algorithm, and the proposed ESARSAMRFO-FS algorithm. The results revealed that ESARSA-MRFO-FS is the most effective of the three algorithms with classifiers and optimization scenarios. Besides, experiments comparing MRFO and ESARSA-MRFO performance on 44 benchmarks are presented in the article. In five functions, ESARSA-MRFO outperforms MRFO. These results confirm that the proposed method is efficient for feature selection in medical diagnosis because of its accuracy and low processing costs. © 2025 Elsevier B.V.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

HeX: Encrypted Rich Queries with Forward and Backward Privacy Using Trusted Hardware

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Wu, Haotian Peng, Zhe Xiao, Jiang Xue, Lei Lin, Chenhao Chung, Sai-Ho The Hong Kong Polytechnic University Department of Industrial and Systems Engineering Hung Hom Hong Kong The Hong Kong Polytechnic University Department of Industrial and Systems Engineering Hong Kong Hong Kong Polytechnic University Shenzhen Research Institute Hong Kong Huazhong University of Science and Technology School of Computer Science and Technology China Sun Yat-sen University School of Cyber Science and Technology China Xi'an Jiaotong University Faculty of Electronic and Information Engineering China

Dynamic searchable symmetric encryption (DSSE) schemes empower data owners to outsource their encrypted data to clouds while retaining the ability to update or search on it. Despite a lot of efforts devoted in recent years, there are still several challenges that have not been well addressed. Firstly, the confidentiality of data might be compromised if forward privacy and backward privacy cannot be ensured. Secondly, only the traditional single keyword-file search has attracted tremendous attention, while other popular queries like Boolean queries and range queries are not fully investigated. Lastly, how to solve these problems on untrusted servers that may deviate from pre-defined protocols is also challenging. In this paper, aiming to tackle the above problems, we propose a novel DSSE scheme named HeX based on Trusted Execution Environment (TEE) that supports rich queries on untrusted servers while guaranteeing forward and backward privacy. We achieve strong forward and backward security by designing a deferred obfuscating read-write technique atop the bitmap index. We further extend the basic scheme to realize Boolean queries and range queries by reducing them to basic keyword queries. Strict theoretical analysis is conducted to prove the security of HeX, and extensive evaluations illustrate its efficiency and practicality. © 2004-2012 IEEE.

关键词： Differential privacy

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：