检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Krueger, Ryan K. Aviran, Sharon Mathews, David H. Zuber, Jeffrey Ward, Max School of Engineering and Applied Sciences Harvard University CambridgeMA02138 United States Department of Biomedical Engineering and Genome Center University of California Davis DavisCA95616 United States Department of Biochemistry and Biophysics and Center for RNA Biology University of the Rochester Medical Center RochesterNY14642 United States Department of Computer Science and Software Engineering The University of Western Australia PerthWA Australia

The Nearest Neighbor model is the de facto thermodynamic model of RNA secondary structure formation and is a cornerstone of RNA structure prediction and sequence design. The current functional form (Turner 2004) contains ≈ 13, 000 underlying thermodynamic parameters, and fitting these to both experimental and structural data is computationally challenging. Here, we leverage recent advances in differentiable folding, a method for directly computing gradients of the RNA folding algorithms, to devise an efficient, scalable, and flexible means of parameter optimization that uses known RNA structures and thermodynamic experiments. Our method yields a significantly improved parameter set that outperforms existing baselines on all metrics, including an increase in the average predicted probability of ground-truth sequence-structure pairs for a single RNA family by over 23 orders of magnitude. Our framework provides a path towards drastically improved RNA models, enabling the flexible incorporation of new experimental data, definition of novel loss terms, large training sets, and even treatment as a module in larger deep learning pipelines. We make available a new database, RNAometer, with experimentally-determined stabilities for small RNA model systems. Copyright © 2025, The Authors. All rights reserved.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Segment Any Crack: Deep Semantic Segmentation Adaptation for Crack Detection

arXiv

引用

arXiv 2025年

作者： Rostami, Ghodsiyeh Chen, Po-Han Hosseini, Mahdi S. Department of Building Civil and Environmental Engineering Concordia University MontrealH3G 1M8 Canada Department of Building Civil and Environmental Engineering Concordia UniversityMontreal H3G 1M8 Canada Department of Computer Science and Software Engineering Concordia University MontrealH3G 1M8 Canada

Image-based crack detection algorithms are increasingly in demand in infrastructure monitoring, as early detection of cracks is of paramount importance for timely maintenance planning. While deep learning has significantly advanced crack detection algorithms, existing models often require extensive labeled datasets and high computational costs for fine-tuning, limiting their adaptability across diverse conditions. This study introduces an efficient selective fine-tuning strategy, focusing on tuning normalization components, to enhance the adaptability of segmentation models for crack detection. The proposed method is applied to the Segment Anything Model (SAM) and five well-established segmentation models. Experimental results demonstrate that selective fine-tuning of only normalization parameters outperforms full fine-tuning and other common fine-tuning techniques in both performance and computational efficiency, while improving generalization. The proposed approach yields a SAM-based model, Segment Any Crack (SAC), achieving a 61.22% F1-score and 44.13% IoU on the OmniCrack30k benchmark dataset, along with the highest performance across three zero-shot datasets and the lowest standard deviation. The results highlight the effectiveness of the adaptation approach in improving segmentation accuracy while significantly reducing computational overhead. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Smart Water Taps Using IoT Sensors and Deep Reinforcement Learning for Personalized Consumption Control

Smart Water Taps Using IoT Sensors and Deep Reinforcement Le...

引用

International Conference on Energy, Power and Environment: Towards Sustainable Growth (ICEPE)

作者： Mageshkumar Naarayanasamy Varadarajan Viyyapu Lokeshwari Vinya R. Jenin Prabhu G. Swathi N. Mohankumar S. Velmurugan Lead Software Engineer Capital One Chennai Tamil Nadu India Assistant Professor Department of Computer Science and Engineering Vardhaman College of Engineering Ranga Reddy Telangana India Assistant Professor Department of Electrical and Electronics Engineering Vel Tech Multi Tech Dr. Rangarajan Dr. Sakundhala Engineering College Chennai Tamil Nadu India Assistant Professor Department of Computer Science and Engineering CMR Technical Campus Hyderabad Telangana India Professor Symbiosis Institute of Technology (SIT) Symbiosis International (Deemed University) Nagpur Maharashtra India Professor Department of Electronics and Communication Engineering T.J.S. Engineering College Chennai Tamil Nadu India

ISBN: (数字)9798350379297

ISBN: (纸本)9798350379303

This research introduces an innovative approach to water conservation and personalized consumption management by combining Internet of Things (IoT) sensors with Deep Reinforcement Learning (DRL) methods. The suggested approach aims to give people more control over their water use in response to water shortages and the need for sustainable resource management. It installs IoT sensors on taps to track water use in real time. A DRL framework is fed data that these sensors have collected. The DRL algorithm develops individual consumption profiles for each user by factoring in past water use, environmental conditions, and personal tastes. Using this unique profile, water efficiency may be improved instantly. Users may easily enter their water conservation choices, budgets, and the system's user interface. Adjusting the water's flow rate by the user profiles learned by the DRL actively regulates water use while keeping people happy. The results of the experiments reveal that our method effectively reduces both water use and waste. Integrating IoT sensors with DRL methods provides a flexible and scalable answer for smart water management that economically benefits the environment and consumers.

关键词： Water heating Water conservation User interfaces Deep reinforcement learning Real-time systems Sensor systems Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Applications of Knowledge Distillation in Remote Sensing: A Survey

arXiv

引用

arXiv 2024年

作者： Himeur, Yassine Aburaed, Nour Elharrouss, Omar Varlamis, Iraklis Atalla, Shadi Mansoor, Wathiq Al Ahmad, Hussain College of Engineering and Information Technology University of Dubai Dubai United Arab Emirates MBRSC Lab University of Dubai Dubai2713 United Arab Emirates Department of Computer Science and Software Engineering United Arab Emirates University United Arab Emirates Department of Informatics and Telematics Harokopio University of Athens AthensGR-17778 Greece

With the ever-growing complexity of models in the field of remote sensing (RS), there is an increasing demand for solutions that balance model accuracy with computational efficiency. Knowledge distillation (KD) has emerged as a powerful tool to meet this need, enabling the transfer of knowledge from large, complex models to smaller, more efficient ones without significant loss in performance. This review article provides an extensive examination of KD and its innovative applications in RS. KD, a technique developed to transfer knowledge from a complex, often cumbersome model (teacher) to a more compact and efficient model (student), has seen significant evolution and application across various domains. Initially, we introduce the fundamental concepts and historical progression of KD methods. The advantages of employing KD are highlighted, particularly in terms of model compression, enhanced computational efficiency, and improved performance, which are pivotal for practical deployments in RS scenarios. The article provides a comprehensive taxonomy of KD techniques, where each category is critically analyzed to demonstrate the breadth and depth of the alternative options, and illustrates specific case studies that showcase the practical implementation of KD methods in RS tasks, such as instance segmentation and object detection. Further, the review discusses the challenges and limitations of KD in RS, including practical constraints and prospective future directions, providing a comprehensive overview for researchers and practitioners in the field of RS. Through this organization, the paper not only elucidates the current state of research in KD but also sets the stage for future research opportunities, thereby contributing significantly to both academic research and real-world applications. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Stock Price Prediction Using LSTMSeq2Seq: A Deep Learning Approach with Advanced Feature engineering

Stock Price Prediction Using LSTMSeq2Seq: A Deep Learning Ap...

引用

International Conference on computer and Information Technology (ICCIT)

作者： Md. Kalim Amzad Chy Abdul Kadar Muhammad Masum Mohammed Shamsul Alam Md. Abul Kalam Azad Md Zia Uddin Dept. of AI Innovation Liberate Labs Texas USA Dept. of Software Engineering Daffodil International University Dhaka Bangladesh Dept. of Computer Science and Engineering International Islamic University Chittagong Chittagong Bangladesh Dept. of Business and Technology Management Islamic University of Technology Gazipur Bangladesh Software and Service Innovation Department SINTEF Digital Oslo Norway

ISBN: (数字)9798331519094

ISBN: (纸本)9798331519100

This paper explores stock price prediction in the context of the Bangladesh stock market using advanced deep learning methodologies, specifically the LSTMSeq2Seq model. Traditional analytical techniques often fail to capture the complex, non-linear patterns inherent in financial data. To address this limitation, our research leverages the strengths of the LSTM-Seq2Seq architecture, which is tailored to the unique dynamics of the Bangladesh market. A robust feature engineering process is employed, utilizing 67 diverse features, including market trends, stock-specific indicators, fundamental and technical variables, and key macroeconomic factors such as gold prices and foreign exchange reserves. The dataset encompasses historical stock market data from 2012 to 2022, and extensive data preprocessing is performed to handle inconsistencies. Hyperparameter optimization is conducted using grid search to ensure model performance. The LSTMSeq2Seq model is evaluated based on key metrics such as MAE, MAPE, MSE, and the R 2 score, demonstrating superior predictive capabilities compared to traditional methods. This research not only advances the application of deep learning in financial forecasting but also provides valuable insights into stock price prediction in emerging markets, addressing ethical concerns to mitigate risks like market manipulation.

关键词： Deep learning Measurement Sentiment analysis Computational modeling Time series analysis Predictive models Macroeconomics Stock markets Forecasting Long short term memory

来源：评论

学校读者我要写书评

暂无评论

GPT-Based Automated Induction: Vulnerability Detection in Medical software

引用

IEEE Journal of Biomedical and Health Informatics 2025年 PP卷 PP页

作者： Deng, Liangjun Lei, Hang Khan, Fazlullah Srivastava, Gautam Chen, Jingxue Haque, Mainul University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu610054 China University of Nottingham Ningbo China School of Computer Science and the Next-Generation Internet of Everything Laboratory Faculty of Science and Engineering Zhejiang Ningbo315104 China Lovely Professional University Division of Research and Development Phagwara India Chandigarh University University Centre of Research and Development Mohali India Brandon University Department of Math and Computer Science BrandonMBR7A 6A9 Canada China Medical University Research Centre for Interneural Computing Taichung40402 Taiwan Chitkara University Institute of Engineering and Technology Chitkara University Centre for Research Impact & Outcome Punjab Rajpura140401 India University of Nottingham Ningbo China Department of Mathematics Faculty of Science and Engineering Zhejiang Ningbo315104 China

Integrating Natural Language Processing (NLP) with Generative Pre-trained Transformer (GPT) models plays a pivotal role in enhancing the accuracy and efficiency of healthcare software, which is essential for patient safety and providing high-quality care. The precision of healthcare software is fundamental to protecting the well-being of the patient. In addition, it can ensure the delivery of superior care, maintain the integrity of healthcare systems, and promote trust and cost-effectiveness. It is necessary to emphasize the importance of software reliability in its development and deployment. Symbolic execution serves as a vital technology in automated vulnerability detection. However, symbolic execution often faces problems such as path explosion, which seriously affects efficiency. Although there have been several studies to reduce the number of computational paths in symbolic execution, this problem remains a major obstacle. Therefore, more efficient solutions are urgently needed to ensure the software security. This paper proposes a large-scale language model(LLM) induction method mitigating path explosion applied to symbolic execution engines. In contrast to traditional symbolic execution engines, which often result in timeout or out-of-memory detection, our approach achieves the task of detecting vulnerabilities in seconds. Furthermore, our proposal improves the scalability of symbolic execution, allowing more extensive and complex programs to be analyzed without significant increases in computational resources or time. This scalability is crucial to tackling modern software systems and improving the efficiency and effectiveness of automated defect verification in healthcare software. © 2025 IEEE. All rights reserved,

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Data Centric Blockchain Based Evaluation Approach to Analyze E-Commerce Reviews Using Machine and Deep Learning Techniques

Data Centric Blockchain Based Evaluation Approach to Analyze...

引用

International Conference on Wavelet Active Media Technology and Information Processing (ICWAMTIP)

作者： Edward Mensah Acheampong Shijie Zhou Yongjian Liao Peter Atandoh Daniel Addo Emmanuel Antwi-Boasiako Rose Nkrumah Esther Stacy E.B. Aggrey Michael Appiah-Twum School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China Department of Computer Science Ghana Institute of Management and Public Administration Ghana Department of Basic Education University of Cape Coast Ghana School of Resource and Environment University of Electronic Science and Technology of China Chengdu China

Machine and deep learning techniques are now essential for many different kinds of solutions in many areas, applications, and businesses. Analyzing e-commerce reviews using machine and deep learning techniques can motivate a company to make more wise decisions regarding the quality and services it offers. But issues can occur if there is insufficient high-quality data for the training, scalability, and upkeep of learning models. To address these important issues, we suggest a data-centric learning architecture that makes use of a blockchain and Interplanetary File System (IPFS)-based storage. Our architecture provides secure and cost-effective data storage and an incentive mechanism. Our experiment shows that as the dataset gets bigger, the Naïve Bayes (NB) and the Support Vector Machine (SVM) models get 2% more accurate, the Convolutional Neural Network (CNN) model gets 4% more accurate, and the Long Short-Term Memory (LSTM) model gets 3 % more accurate. The deep learning models exhibited higher accuracy rates than the machine learning models because hidden layers of deep learning possess the ability to extract intricate syntactic features from the review text.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Identification of Sounds Using Deep Learning with MFCC Features Extraction

Identification of Sounds Using Deep Learning with MFCC Featu...

引用

AITU: Digital Generation, IEEE

作者： Veeramanickam M.R.M Aniket Ingavale Vikas Khullar Sneha S Tirth Bishwajeet Pandey Harjit Pal Singh Department of Software Engineering Universidad Nacional Mayor de San Marcos (UNMSM) Lima Peru School of Engineering and Technology DES Pune University Pune India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Department of Computer Engineering Trinity College of Engineering and Research Pune India Department of IS&CS Astana IT University Astana Kazakhstan Department of Physics Faculty of Science and Technology The University of West Indies St Augustine Trinidad & Tobago

ISBN: (数字)9798350364378

ISBN: (纸本)9798350364385

Environmental sound classification is an essential aspect of identifying different classes of sounds using a machine learning approach. This work investigates the efficacy of convolutional neural networks for classifying short environmental sound clips. In this work, a deep 1D-CNN architecture with 2 layers of convolutional employing max-pooling, followed by two fully-connected layers are utilized. The model leverages segmented spectrograms with delta features as input. Evaluated with datasets encompassing environmental and urban recordings, our model surpasses baseline methods utilizing mel-frequency cepstral coefficients (MFCCs) and achieves competitive performance against traditional approaches.

关键词： Training Deep learning Computational modeling computer architecture Feature extraction Data augmentation Recording

来源：评论

学校读者我要写书评

暂无评论

Systems biology models to identify the influence of SARS-CoV-2 infections to the progression of human autoimmune diseases

引用

Informatics in Medicine Unlocked 2022年 32卷 101003页

作者： Al-Mustanjid, Md Mahmud, S. M. Hasan Akter, Farzana Rahman, Md Shazzadur Hossen, Md Sajid Rahman, Md Habibur Moni, Mohammad Ali Department of Software Engineering Faculty of Science and Information Technology Daffodil International University Dhaka 1207 Bangladesh Department of Computer Science American International University-Bangladesh Dhaka 1229 Bangladesh Department of Computer Science & Engineering Faculty of Science and Information Technology Daffodil International University Dhaka 1207 Bangladesh Department of Computer Science and Engineering Islamic University Kushtia 7003 Bangladesh Department of Computer Science and Engineering Pabna Science & Technology University Pabna 6600 Bangladesh

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has been circulating since 2019, and its global dominance is rising. Evidences suggest the respiratory illness SARS-CoV-2 has a sensitive affect on causing organ damage and other complications to the patients with autoimmune diseases (AD), posing a significant risk factor. The genetic interrelationships and molecular appearances between SARS-CoV-2 and AD are yet unknown. We carried out the transcriptomic analytical framework to delve into the SARS-CoV-2 impacts on AD progression. We analyzed both gene expression microarray and RNA-Seq datasets from SARS-CoV-2 and AD affected tissues. With neighborhood-based benchmarks and multilevel network topology, we obtained dysfunctional signaling and ontological pathways, gene disease (diseasesome) association network and protein-protein interaction network (PPIN), uncovered essential shared infection recurrence connectivities with biological insights underlying between SARS-CoV-2 and AD. We found a total of 77, 21, 9, 54 common DEGs for SARS-CoV-2 and inflammatory bowel disorder (IBD), SARS-CoV-2 and rheumatoid arthritis (RA), SARS-CoV-2 and systemic lupus erythematosus (SLE) and SARS-CoV-2 and type 1 diabetes (T1D). The enclosure of these common DEGs with bimolecular networks revealed 10 hub proteins (FYN, VEGFA, CTNNB1, KDR, STAT1, B2M, CD3G, ITGAV, TGFB3). Drugs such as amlodipine besylate, vorinostat, methylprednisolone, and disulfiram have been identified as a common ground between SARS-CoV-2 and AD from drug repurposing investigation which will stimulate the optimal selection of medications in the battle against this ongoing pandemic triggered by COVID-19. © 2022 The Authors

关键词： Autoimmune diseases COVID-19 DEGs Drug repurposing Hub gene Protein-protein interaction network (PPIN) SARS-CoV-2 Transcriptomic analysis

来源：评论

学校读者我要写书评

暂无评论

Detection of Ophthalmic Disorders Through Deep Feature Fusion

Detection of Ophthalmic Disorders Through Deep Feature Fusio...

引用

engineering & Computing Technologies (ICECT), International Conference on

作者： Muhammad Toheed Hussain Muhammad Faraz Sumair Aziz Khushbakht Iqtidar Muhammad Umar Khan Gabriel Axel Montes Department of Electronics Engineering University of Engg. & Tech. Taxila Taxila Pakistan Faculty of Science and Technology University of Canberra Canberra ACT Australia Dept. of Computer & Software Engineering National University of Sciences & Tech. Islamabad Pakistan University of Newcastle Callaghan NSW Australia

ISBN: (数字)9798350349719

ISBN: (纸本)9798350349726

Given the rising prevalence of ophthalmic disorders, this study aims to meet the urgent need for an automated technique capable of diagnosing and treating these conditions. Our approach combines deep learning and machine learning techniques to develop a diagnostic system that can detect and classify seven distinct ophthalmic disorders. Manual diagnosis of ophthalmic disorders is labor-intensive and slow, worsened by a shortage of medical experts. In this paper, we propose a medical diagnostic system that utilizes deep features extracted from a ResNet-50 CNN, which has been trained on retinal images enhanced through contrast-limited adaptive histogram equalization (CLAHE). These deep features serve as input for the machine learning model. To address the class imbalance problem, we employed ADASYN to generate synthetic features for all classes. An Ensemble subspace KNN classifier, trained on these deep features, achieved a remarkable mean accuracy of 99.18% compared to other classifiers evaluated in this study. The proposed technique has the potential to assist medical experts in achieving timely and accurate diagnoses of ophthalmic diseases.

关键词： Deep learning computers Histograms Accuracy Manuals Feature extraction Retina

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：