检索结果-内蒙古大学图书馆

3rd International Conference on Integrated Circuits and Communication Systems, ICICACS 2025

作者： Kumar, Gaurav Devayani, G. Saraswathi, C. Melba Kani, R. Dongre, Sandeep Mallick, M. S. Mohamed School of Computer Application Lovely Professional University Phagwara India M.Kumarasamy College of Engineering Department of Computer Science and Business Systems Karur India School of Management Studies Bannari Amman Institute of Technology Erode India Mar Ephraem college of Engineering and Technology Kanyakumari India Nagpur India Department of Computer Science Engineering Chennai India

ISBN: (纸本)9798331508456

Online retailers must monitor and respond to changing consumer trends to stay competitive. AI-driven customization's revolutionary impact on market trends is the focus of this study on online buying and customer behavior. As AI advances, e-commerce platforms will be able to customize user experiences. Preprocessing, feature extraction, and model training comprise the AI-driven personalization process. Customer data from online marketplaces is collected first. It manages missing values, balance the data, encode categorical variables, scale the features, and minimize the dimensions as part of our thorough data preprocessing to ensure fair and applicable results. To trained the algorithms with CNN and Convolutional LSTM Based on key criteria, the AI model beat LSTM and CNN. It provides personalized insights and recommendations with an average accuracy of 92.03%. Personalized experiences and product suggestions enabled by AI-powered personalization have transformed e-commerce. It's important to use smart algorithms to engage customers and examine large databases. This proposed approach to shows that AI can transform online shopping and improve customer experiences. © 2025 IEEE.

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

Location Privacy Preservation Crowdsensing With Federated Reinforcement Learning

引用

IEEE Transactions on Dependable and Secure Computing 2025年第3期22卷 1877-1894页

作者： You, Zhichao Dong, Xuewen Liu, Ximeng Gao, Sheng Wang, Yongzhi Shen, Yulong Xidian University School of Computer Science and Technology The Engineering Research Center of Blockchain Technology Application and Evaluation Ministry of Education Xi'an710071 China Shaanxi Key Laboratory of Blockchain and Secure Computing Xi'an710071 China Fuzhou University College of Computer and Data Science Fuzhou350025 China Central University of Finance and Economics School of Information Beijing102206 China California State Polytechnic University Pomona Department of Computer Information Systems PomonaCA91768 United States Xidian University School of Computer Science and Technology Xi'an710071 China Shaanxi Key Laboratory of Network and System Security Xi'an710071 China

Crowdsensing has become a popular method of sensing data collection while facing the problem of protecting participants' location privacy. Existing location-privacy crowdsensing mechanisms focus on static tasks and participants without considering sensing tasks' time requirements and participants' mobility, which cannot achieve satisfactory collected data quality and task completion in crowdsensing with dynamic tasks and participants. Inspired by this, we proposed a location-preservation crowdsensing mechanism, FedSense, considering dynamic tasks and participants based on federated learning (FL) and reinforcement learning (RL). In FedSense, through RL's outstanding decision-making ability, participants select sensing tasks to perform by well-trained RL models without uploading location information to servers for task allocation. We propose an independent tasks selection environment that defines actions, states, and rewards of RL to enable FedSense to achieve satisfactory task completion and data quality while preserving location privacy. Besides, FedSense applies an asynchronous FL aggregation algorithm that reduces participants' network stabilization and device computing ability requirements. Analysis proves that participants' location information does not leave the local device during the model training and task selection process, effectively avoiding privacy leakage. Simulation shows that compared with existing location-preservation crowdsensing mechanisms, FedSense achieves the highest task completion and sensing accuracy for dynamic tasks and participants. © 2024 IEEE.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

BioVLF-T: A Temporal Framework for Radiology Report Generation using Pre-Trained Vision Language Foundational Models

BioVLF-T: A Temporal Framework for Radiology Report Generati...

引用

Medical Imaging 2025: Clinical and Biomedical Imaging

作者： Kasturi, Akhil Vosoughi, Ali Hadjiyski, Nathan Wismüller, Axel Department of Electrical and Computer Engineering University of Rochester NY United States Department of Imaging Sciences University of Rochester NY United States Department of Computer Science University of Rochester NY United States Department of Biomedical Engineering University of Rochester NY United States Faculty of Medicine Institute of Clinical Radiology Ludwig Maximilian University Munich Germany

ISBN: (纸本)9781510685987

In this study, we propose BioVLF-T, a novel automatic radiology report generation framework built on a Bio-Vision Language Foundational Model (VLF) with a temporal framework. BioVLF-T enhances the contextual understanding of the vision-language model by leveraging historical patient data, incorporating previous chest X-rays and their corresponding radiology reports. We fine-tuned the BLIP-VQA, a vision-language foundational model, within this framework, integrating a CNN-based instructor model pre-trained on 14 pathological labels from CheXbert to accurately capture relevant pathologies. By sequentially integrating historical data, the model simulates a process akin to that of a radiologist, resulting in more precise and contextually relevant report generation. Our experimental results demonstrate significant performance enhancements, with the BioVLF-T framework showing a 120.47% improvement in BLEU scores and a 1069.50% increase in CIDEr scores over the conventional fine-tuning method. These improvements highlight the effectiveness of temporal data integration in radiology report generation. Additionally, we acknowledge the limitations of traditional metrics such as CIDEr in capturing the nuances of language and, in the future, will focus on scaling the model with larger datasets and exploring advanced evaluation methods, including LLM-based scores, to enhance prediction quality further. © 2025 SPIE.

关键词： Mammography

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Multi-scale Attention Cross-Fusion Network for Hyperspectral Image Classification 5

Self-Supervised Multi-scale Attention Cross-Fusion Network f...

引用

5th International Conference on Emerging Systems and Intelligent Computing, ESIC 2025

作者： Sahu, Soumya Ranjan Panda, Sucheta Veer Surendra Sai University of Technology Department of Computer Science and Engineering Burla Odisha Sambalpur768018 India

ISBN: (纸本)9798331522100

Hyperspectral image (HSI) classification has gained considerable attention due to its potential for precisely discriminating ground objects using detailed spectral and spatial features. This paper proposes a self-supervised multiscale attention-guided cross-fusion network for efficient HSI classification. This approach integrates advanced deep learning methodologies, emphasizing multiscale spatial-spectral attention and self-supervised learning mechanisms to capture complex relationships and enhance feature representation within HSIs effectively. The model's performance was rigorously evaluated on multiple datasets, including Indian Pines (IP) and Salinas (SA) dataset demonstrating significant improvements over benchmark models such as SSRNet, FCFS-SSL, and S3L. The proposed method achieved superior classification metrics, including higher Kappa, overall, and average accuracies, showcasing its capability to extract deep features and adapt to challenging data complexities. While the model outperformed traditional and semi-supervised methods, challenges such as computational complexity and hardware deployment constraints remain, motivating future exploration of lightweight transformer architectures. Overall, the proposed work offers a promising advancement for efficient, accurate, and scalable HSI classification. © 2025 IEEE.

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

The Novel DeepBoost Multi Output Regressor for Household Finance Intelligence 5

The Novel DeepBoost Multi Output Regressor for Household Fin...

引用

5th International Conference on Advanced Research in Computing, ICARC 2025

作者： Suwandaratna, S.H.S.V. Priyankara, G.O. Institute of Technology Department of Computer Science and Engineering Informatics No 10 Trelawney PI Colombo00400 Sri Lanka

ISBN: (纸本)9798331530983

This paper forecasts the microeconomic level household expenditures using a novel hybrid deep learning approach. In terms of research significance, household finance control has a major influence on the finance system within the economy. Accurate forecasting of household finances assists in maintaining positive financial behavior among individuals and the economy. The DeepBoost multi-output regressor proposed in this paper is based on the 1D CNN-ANN and the XGBoost. The proposed model in this paper is compared with the R2, MSE, and MAE since it's a regression problem. The experimental results reveal that the proposed DeepBoost multi-output regressor has the best application in forecasting the multiple expenditures of households by outperforming the ANN, 1D CNN-ANN, and Random Forest Regressor models. The proposed DeepBoost multi-output regressor evaluated the housing, food, transportation, healthcare, other necessities, childcare, and tax expenditures that had 0.94, 0.98, 0.83, 0.94, 0.97, 0.97, and 0.99 values for the R2, 9037.71, 2692.12, 9788, 15077.33, 1373.93, 13629.36, and 1904.52 values for the MSE, and 66.07, 34.05, 73.17, 87.05, 26.25, 78.74, and 29.47 MAE values than the ANN, RFR, and 1D CNN-ANN models. © 2025 IEEE.

关键词： Taxation

来源：评论

学校读者我要写书评

暂无评论

Opposition-based multi-objective ant colony optimization framework for sustainable retrofitting: time–cost–energy–risk trade-offs

引用

Asian Journal of Civil engineering 2025年第5期26卷 2223-2239页

作者： Pokkuluri, Kiran Sree Chauhan, Trupti Ravindra Macedo, Víctor Daniel Jiménez Manjunath, T.C. Bharadwaj, Manish Sethi, Krushna Chandra Department of Computer Science and Engineering Shri Vishnu Engineering College for Women Bhimavaram India Department of Design Manipal School of Architecture and Planning Manipal Academic of Higher Education Manipal Karnataka Udupi India Mechanical Engineering Faculty Michoacan University of Saint Nicholas of Hidalgo Morelia Mexico Department of Computer Science and Engineering Rajarajeswari College of Engineering Bengaluru India Department of Management Studies Atal Bihari Vajpayee Indian Institute of Information Technology and Management Gwalior India Civil Engineering Department Centurion University of Technology and Management Gajapati India

The increasing emphasis on sustainable retrofitting of buildings has brought attention to the need for optimizing trade-offs among critical objectives, such as time, cost, energy consumption, and risk. This study proposes an opposition-based multi-objective ant colony optimization (OB-MOACO) framework to address these challenges effectively. The framework incorporates opposition-based learning to enhance solution exploration and convergence in multi-objective optimization problems, specifically tailored for sustainable retrofitting projects. The study develops a time–cost–energy–risk trade-off (TCERT) model with four objectives: minimizing retrofitting time, cost, energy consumption, and risks. The model integrates constraints related to budget, project timelines, and energy efficiency to ensure feasibility and sustainability. A detailed case study of retrofitting a mixed-use building is presented, encompassing 11 aspects such as structural reinforcement, energy efficiency enhancement, and accessibility improvements. Results demonstrate the superiority of OB-MOACO over conventional methods like NSGA-III, MODE, and MOPSO in achieving Pareto-optimal solutions. Key performance metrics, including hypervolume (HV) and inverted generational distance (IGD), highlight the model's efficiency in balancing competing objectives. The study contributes to advancing sustainable retrofitting practices by providing an innovative, cost-effective, and energy-efficient decision-making framework. Implications for practitioners and policymakers are discussed, alongside recommendations for future research. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Multi-objective optimization Opposition-based ant colony optimization Pareto optimization Sustainable retrofitting Time–cost–energy–risk trade-off

来源：评论

学校读者我要写书评

暂无评论

Kontho: An AI-Driven Smart Glove for Enhanced Sign Language Communication 2nd

Kontho: An AI-Driven Smart Glove for Enhanced Sign Language...

引用

2nd International Conference on Applied Algorithms, ICAA 2025

作者： Dasgupta, Dyuti Datta, Soumyajit Pramanik, Sagnik Dey, Rohit Kumar Nandigrami, Jeet Ghosh, Debaditya Department of Artificial Intelligence and Machine Learning Heritage Institute of Technology Kolkata India Department of Computer Science and Engineering Heritage Institute of Technology Kolkata India

ISBN: (纸本)9783031845420

In India, over 63 million individuals are affected by hearing loss, yet less than 350 certified sign language interpreters are available, thus leading to communication barriers and significant social and economic exclusion. This paper introduces Kontho, an ergonomic, AI-driven, multi-sensor glove integrated with a mobile app for real-time sign language communication via American Sign Language (ASL). Utilizing flex sensors, accelerometers, gyroscopes and EMG sensors, Kontho captures gestures and muscle activity which is processed through a combination of ensemble models and Large Language Models (LLMs) to enhance communication by predicting and completing incomplete gestures. Evaluated on a dataset of 23 ASL gestures at over 3867 data points with an accuracy of 99.61%, Kontho offers a scalable solution to foster social inclusion and address the economic isolation of hearing and speech-impaired individuals, enabling their active participation in the society. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Signaling

来源：评论

学校读者我要写书评

暂无评论

Evaluating marginal likelihood approximations of dose–response relationship models in Bayesian benchmark dose methods for risk assessment

引用

Computational Toxicology 2025年 34卷

作者： Minewaki, Sota Ohigashi, Tomohiro Sozu, Takashi Department of Information and Computer Technology Tokyo University of Science of Engineering Japan Department of Information and Computer Technology Faculty of Engineering Tokyo University of Science Japan

Benchmark dose (BMD;a dose associated with a specified change in response) is used to determine the point of departure for the acceptable daily intake of substances for humans. Multiple dose–response relationship models are considered in the BMD method. The Bayesian model averaging (BMA) method is commonly used, where several models are averaged based on their posterior probabilities, which are determined by calculating the marginal likelihood (ML). Several ML approximation methods are employed in standard software packages, such as BBMD, ToxicR, and the EFSA platform for the BMD method, because the ML cannot be analytically calculated. Although ML values differ among approximation methods, resulting in BMD estimates, this phenomenon is neither widely recognized nor quantitatively evaluated. In this study, we evaluated the agreement of BMD estimates among five ML approximation methods in the BMA method. The five ML approximation methods are (1) maximum likelihood estimation (MLE)-based Schwarz criterion, (2) Markov chain Monte Carlo (MCMC)-based Schwarz criterion, (3) Laplace approximation, (4) density estimation, and (5) bridge sampling. We used eight dose–response relationship models and three prior distributions used in BBMD and ToxicR for 518 experimental datasets. The agreement among the approximation methods tended to be low in the non-informative prior distribution. Although the agreements tended to be high in the informative prior distribution, they were low in some approximation methods. Since the approximation method and the prior distribution affect the agreement, their selection should be carefully considered when implementing BMD methods. © 2025 Elsevier B.V.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Efficient Dual-Hop Routing in Underwater Optical Wireless Networks Using Honey Bee Optimization 4

Efficient Dual-Hop Routing in Underwater Optical Wireless Ne...

引用

4th International Conference on Power, Control and Computing Technologies, ICPC2T 2025

作者： Thakur, Sanat Kumar, Ankush Mahato, Dharmendra Prasad Department of Computer Science and Engineering National Institute of Technology Hamirpur Himachal Pradesh Hamirpur177 005 India

ISBN: (纸本)9798331530402

Underwater Optical Wireless Networks (UOWNs) offer a promising solution for high-speed data transmission, yet they face significant challenges due to the demanding aquatic environment, which affects signal propagation and data delivery reliability. To enhance UOWN performance, this research introduces an efficient distance-adaptive dual-hop routing method. The Honey Bee Optimization (HBO) algorithm is employed to dynamically select optimal relay nodes and transmission paths, aiming to increase data delivery success rates while minimizing total transmission distances. Simulation results, conducted under varied underwater conditions, demonstrate that the proposed method significantly improves network efficiency, reliability, and energy consumption compared to traditional routing algorithms. This approach effectively addresses key challenges, such as signal attenuation and limited communication range, in underwater environments. © 2025 IEEE.

关键词： Routing algorithms

来源：评论

学校读者我要写书评

暂无评论

Utilizing the Power of Residual and Attention Properties with Binary Focal Loss Optimization for Underwater Image Segmentation Using UNet Architecture 7th

Utilizing the Power of Residual and Attention Properties wit...

引用

7th International Conference on Communication, Device and Networking, ICCDN 2024

作者： George, Geomol Anusuya, S. Department of Electronics and Communication Engineering Saveetha School of Engineering SIMATS Tamil Nadu Chennai602105 India Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Tamil Nadu Chennai602105 India

ISBN: (纸本)9789819764648

Recent developments in deep-sea exploration, environmental surveillance, and ocean research, accurate segmentation of underwater images is essential. This study pursues this goal by exploring underwater image segmentation from a deep learning perspective. It specifically looks at how well the Attention Residual UNet architecture, a more sophisticated version of the U-Net, works with the focal loss technique to achieve accuracy in this crucial task. Using attention mechanisms and residual connections, the Attention Residual UNet architecture, based on the U-Net framework, can capture fine details while maintaining contextual coherence. Model loss and accuracy measures are considered as this study carefully assesses the architecture’s performance. Notably, the model exhibits outstanding accuracy, obtaining 97.23% and 92.76% accuracy on the training and validation sets, respectively. The Jaccard coefficient further demonstrates the model’s efficiency, which measures the intersection between predicted and actual segments and has coefficients for the model and validation sets of 74.31% and 66.51%, respectively. The Mean Intersection over Union (MIoU) statistic, which boasts a value 91.24%, validates the model’s superiority. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Underwater imaging

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：