检索结果-内蒙古大学图书馆

14th IEEE International Conference on Communication Systems and Network Technologies, CSNT 2025

作者： Priyadarshi, Rahul Rout, Jayant Kumar Vishwakarma, Anish Kumar Dhengre, Nikhil Ranjan, Rakesh Verma, Amit Faculty of Engineering and Technology ITER SOA Bhubaneswar India School of Computer Application KIIT Bhubaneswar India School of Computer Science UPES Uttarakhand Dehradun India Department of ECE IIIT Maharashtra Nagpur India

ISBN: (纸本)9798331531935

Wireless Sensor Networks (WSNs) require efficient node deployment strategies to optimize network longevity, energy consumption, and coverage. This paper introduces a novel approach for strategic node deployment in WSNs using Bayesian Optimization (BO). A BO-based framework that iteratively modifies node positions to maximize network performance metrics, such as energy efficiency and coverage ratio, while minimizing execution time is proposed. Through extensive simulations across diverse deployment scenarios, the proposed method is evaluated and demonstrates superior performance compared to both traditional and machine learning (ML)-based techniques. The results indicate significant improvements in coverage and energy efficiency, alongside competitive execution times. These findings highlight the potential of BO to enhance WSN deployment strategies, offering a scalable and adaptive solution for real-world applications. Future research will focus on integrating BO with other optimization techniques and extending the approach to dynamic environments and varied network configurations. © 2025 IEEE.

关键词： Bayesian Optimization Coverage Ratio Energy Efficiency Node Deployment Wireless Sensor Networks

来源：评论

学校读者我要写书评

暂无评论

Balancing data imbalance in biomedical datasets using a stacked augmentation approach with STDA, DAGAN, and pufferfish optimization to reveal AI's transformative impact

引用

International Journal of Information technology (Singapore) 2025年第1期17卷 455-480页

作者： Veedhi, Bhaskar Kumar Das, Kaberi Mishra, Debahuti Mishra, Sashikala Behera, Mandakini Priyadarshani Department of Computer Science and Engineering Siksha ‘O’ Anusandhan (Deemed to Be) University Odisha Bhubaneswar India Department of Computer Application Siksha ‘O’ Anusandhan (Deemed to Be) University Odisha Bhubaneswar India Department of Computer Science and Engineering Symbiosis Institute of Technology Symbiosis International (Deemed to Be) University Maharashtra Pune India School of Computer Engineering KIIT (Deemed to Be) University Odisha Bhubaneswar India

This study systematically assesses the effectiveness of data augmentation techniques, focusing particularly on the stacked approach, across a diverse range of biomedical datasets. Advanced data augmentation methods, including style transfer data augmentation (STDA) and data augmentation generative adversarial network (DAGAN), offer promising solutions in this context. STDA leverages style transfer techniques from computer vision to create varied and realistic synthetic samples while preserving semantic content, thereby enhancing dataset variability and improving model generalization. Conversely, DAGAN utilizes generative adversarial networks (GANs) to learn the underlying data distribution, resulting in the generation of high-quality synthetic samples. Subsequently, STDA and DAGAN techniques are applied to the selected data, followed by convolution and pooling operations on the augmented samples. The pooled samples are then stacked, and the Cosine similarity is calculated to measure the resemblance to the original dataset. Parameters of STDA and DAGAN are fine-tuned to maximize the Cosine similarity. Additionally, a metaheuristic optimization algorithm called Pufferfish optimization algorithm (POA) is employed to optimize decision variables—learning rate, number of hidden units (common for both STDA and DAGAN), number of attention heads for STDA, and latent space dimensionality of DAGAN. The classification performance of the proposed POA-stacked STDA-DAGAN data augmentation methodology, along with variants using genetic algorithm (GA) and particle swarm optimization (PSO), is compared with original datasets and SMOTE balanced datasets using various classifiers and the observed accuracies, sensitivity, specificity and F-score are ranging from 91.83% to 99.11%, 91.38% to100%, 92.50% to 100% and 92.95% to 98.32% respective for all ten biomedical datasets used in this research. Additionally, the class distribution graphs, learning curves, statistical validation, and exe

关键词： Biomedical data Data augmentation Data augmentation generative adversarial network (DAGAN) Pufferfish optimization algorithm (POA) Style transfer data augmentation (STDA)

来源：评论

学校读者我要写书评

暂无评论

Framework for classifying gait disorders and fall prevention

Framework for classifying gait disorders and fall prevention

引用

International Conference on computer, Electrical & Communication Engineering (ICCECE)

作者： Rupa Saha Koushik Karmakar Suparna Biswas Department of Computer Application Narula Institute of Technology Department of Computer Science and Technology Narula Institute of Technology Department of Computer Science & Engineering MAKAUT W B

ISBN: (数字)9798331513894

ISBN: (纸本)9798331513900

One of the crucial approaches that use tracking and analyzing human movement for the identification of functional disorders and illnesses of the human body is known as the gait analysis method. This method helps diagnose neurological and musculoskeletal conditions. It also tracks the effectiveness of rehabilitation. However, conventional techniques for analyzing gait frequently depend on costly items and methods like fixed lab apparatus, force plates, and motion capture devices. But new developments in wearable sensor technology and machine learning provide new methods that are cheaper, more affordable, portable, and easily accessible. It continuously tracks gait in real-world settings. In this work, the use of wearable sensors for gait analysis, which includes devices like magnetometers, gyroscopes, and accelerometers, is examined. They are integrated into gadgets like smartphones, insoles, and smartwatches and offer real-time kinematic data that machine learning algorithms can analyze. Some of the important gait parameters 1that are extracted from sensor data are stride length, cadence, and gait symmetry. Machine learning is used to process this data and use it for categorization and gait analysis. The suggested method improves patient monitoring outside of clinical settings. It supports individualized rehabilitation plans and also identifies early indicators of gait abnormalities. The use of the wearable sensor-based gait analysis may emerge as a game-changing medical tool. It offers constant, discrete monitoring and prompts intervention in gait-related disorders. This works explains it thoroughly. This report offers insights for upcoming researchers in the field by surveying the state of the art in wearable sensor-based gait analysis.

关键词： Legged locomotion Machine learning algorithms Accuracy Tracking Reviews Real-time systems Biomedical monitoring Gait recognition Wearable sensors Smart phones

来源：评论

学校读者我要写书评

暂无评论

A Novel Two-Stream Algorithm for Spatio-Temporal Fusion in Remote Sensing

引用

IEEE Geoscience and Remote Sensing Letters 2025年

作者： Wang, Shiying Zou, Xuechao Wang, Wentao Liu, Yao Zhang, Shun Cao, Tengfei Tao, Pin Qinghai University School of Computer Technology and Application Xining China Qinghai University Intelligent Computing and Application Laboratory of Qinghai Province China School of Computer Science & Technology Beijing China Tsinghua University Department of Computer Science and Technology Beijing China Ministry of Education Key Laboratory of Pervasive Computing China

The spatio-temporal fusion technology can effectively solve the problem of missing time series data. However, existing algorithms often struggle to accurately capture surface feature changes and fine details. To overcome these limitations, this paper introduces FemSTF, a flexible two-stream algorithm for remote sensing spatio-temporal fusion, which consists of three main stages: image sharpening, image fusion, and edge optimization. In the first stage, techniques such as interpolation, classification, and blending are employed to address missing pixel values caused by minimal input data. In the second stage, a two-stream strategy is introduced to enhance fusion accuracy, enabling the algorithm to capture regional detail changes with high sensitivity to surface variations. The third stage focuses on edge optimization, generating high-resolution predictive images under minimal input conditions (three images) while retaining rich texture and edge details. Notably, FemSTF achieves a performance comparable to that of methods requiring five input images. Experimental results demonstrate that FemSTF outperforms mainstream algorithms across multiple datasets. Ablation experiments confirm the effectiveness of the two-stream strategy, highlighting its role in enhancing remote sensing data processing accuracy. This study offers an efficient solution for spatio-temporal fusion, demonstrating great potential in the field. © 2004-2012 IEEE.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Automated Anomaly Detection in Medical Imaging Using Support Vector Machines 5th

Automated Anomaly Detection in Medical Imaging Using Support...

引用

5th International Conference on Data Science, Machine Learning and applications, ICDSMLA 2023

作者： Goyal, Manish Kumar Shahid, Mohammad Karthikeyan, M.P. Kumar, Ritesh Department of Computer Science & Application Vivekananda Global University Jaipur India Noida Institute of Engineering and Technology Uttar Pradesh Greater Noida India Karnataka Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India

ISBN: (纸本)9789819780426

Clinical imaging techniques such as X-ray, Magnetic Resonance Imaging (MRI), and laptop Tomography (CT) scanners are used to diagnose, compare, and deal with sufferers. Automatic Anomaly Detection is an automatic technique for identifying and diagnosing abnormalities in clinical imaging. It has been diagnosed that Support Vector Machines (SVM) can be effectively used to generate correct automatic anomaly detection for scientific imaging. SVM is an approach that uses supervised getting-to-know to create a choice boundary between classes, with the decision primarily based on the information to be had. The gain of SVM is that it plays an automatic function extracting from the medical imaging facts and uses those extracted capabilities for anomaly detection. It combines photograph segmentation and classification to classify the abnormal regions in an image. So one can enhance the accuracy of SVM;it's miles viable to use an expansion of kernel capabilities and unique parameter tuning. Moreover, introducing an automatic pipeline from training to deploying SVM reduces the efforts of manual feature extraction from photos. Consequently, aid Vector Machines is a feasible approach for automatic anomaly detection in scientific imaging. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Improving Medical Image Classification Through Transfer Learning and Meta Learning 5th

Improving Medical Image Classification Through Transfer Lear...

引用

5th International Conference on Data Science, Machine Learning and applications, ICDSMLA 2023

作者： Arora, Sonia Jebakumari, S. Adlin Singh, Vaishali Kharbas, Vikas Kumar Noida Institute of Engineering and Technology Uttar Pradesh Greater Noida India Karnataka Bangalore India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Department of Computer Science and Application Vivekananda Global University Jaipur India

ISBN: (纸本)9789819780426

This paper presents an observation of improving clinical picture classification via transfer getting to know and meta-studying. Switching getting-to-know and meta-learning methods are usually employed in medical imaging class tasks. Transfer studying objectives to switch information and illustration from a properly-trained version and mildew that expertise to higher healthy the problem at hand, while meta-gaining knowledge is a version of switch gaining knowledge of which targets to seize and adapt the generalizable expertise of a project domain, and to allow a progressed impact for the goal tasks. Inside the clinical imaging scenario, the two procedures can dig deeper into the several layers which might be involved in gaining deep knowledge of algorithms. The authors compare the effectiveness of the proposed strategies in five publicly available medical imaging datasets. Effects have shown that the proposed techniques notably advanced the usual type accuracy for a few datasets. Furthermore, it was found that the 2-step technique showed higher performance than the one-step technique. This study presents a higher understanding of the efficacy of transfer learning and meta-mastering techniques for clinical photo-type tasks. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Identifying Neuronal Damage and Plasticity by Analyzing Changes in Diffusion Tensor Imaging 5th

Identifying Neuronal Damage and Plasticity by Analyzing Chan...

引用

5th International Conference on Data Science, Machine Learning and applications, ICDSMLA 2023

作者： Chandra, Subhash Rengarajan, A. Sahoo, Girija Shankar Sharma, Sunil Noida Institute of Engineering and Technology Uttar Pradesh Greater Noida India Karnataka Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Department of Computer Science & Application Vivekananda Global University Jaipur India

ISBN: (纸本)9789819780426

This paper presents a unique method, which investigates the neuronal damage and plasticity, the use of changes in diffusion tensor imaging (DTI). Thru combining the information from DTI, collectively with cognitive and demographic records, this method identifies and assesses the adjustments inside the brain's white count number integrity. The findings suggest that the proposed approach is capable of signify the structural modifications in the white be counted, whilst additionally offering significant data about the diploma of neuronal harm and plasticity. This research consequently gives a significant device for in addition investigation into the diagnosis of certain neurological illnesses, especially in stroke and traumatic brain injury, wherein identifying modifications within the mind is critical for proper direction of remedy. In addition, the challenges related to the DTI statistics analysis is discussed, collectively with capability applications and future extensions. This paper presents a complete survey of ways Diffusion Tensor Imaging (DTI) may be applied to become aware of neural harm and plasticity. It explains how DTI can discover microstructural modifications in frightened tissue, making it a promising device for Neuro-imaging research. The paper compares the maximum popular indices used in analysis and model fitting the use of DTI to measure modifications, including fractional anisotropy and imply diffusivity. Subsequently, the paper examines destiny guidelines and potential packages of DTI within the clinical setting. In the end, the paper shows that DTI gives a valuable supply of perception into the neural machine, allowing researchers to discover, quantify, and better apprehend structural modifications to neurons. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Diffusion tensor imaging

来源：评论

学校读者我要写书评

暂无评论

Applying Transfer Learning to Medical Image Classification Tasks 5th

Applying Transfer Learning to Medical Image Classification T...

引用

5th International Conference on Data Science, Machine Learning and applications, ICDSMLA 2023

作者： Gupta, Manali Haripriya, V. Singh, Akhilendra Pratap Yadav, Surendra Noida Institute of Engineering and Technology Uttar Pradesh Greater Noida India Karnataka Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Department of Computer Science & Application Vivekananda Global University Jaipur India

ISBN: (纸本)9789819780426

Transfer studying is a machine learning approach that permits a model to leverage know-how from a previous challenge to boost studying in the following tasks. It's been used increasingly in medical photo classification obligations, allowing area-particular knowledge to be leveraged from current fashions. This method can enhance the overall performance of clinical photograph-type structures and reduce the amount of labeled information required to analyze a brand-new venture. In this paper, we assess the present-day kingdom of switches, getting to know the scientific photo category and the results for clinical picture evaluation. We discuss present switch studying techniques and their influences on the accuracy of medical photo category responsibilities and the challenges related to constructing generalizable fashions. Eventually, we take a look at existing datasets and implementations available for the clinical photo category and factor into promising destiny studies guidelines. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal Large Language Models 31

StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal L...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Yang, Li Xiao, Zhiding Huang, Wenxin Zhong, Xian Hubei Key Laboratory of Big Data Intelligent Analysis and Application School of Computer Science and Information Engineering Hubei University China Hubei Key Laboratory of Transportation Internet of Things School of Computer Science and Artificial Intelligence Wuhan University of Technology China

ISBN: (纸本)9798891761964

The rapid development of multi-modal large language models (MLLMs) has positioned visual storytelling as a crucial area in content creation. However, existing models often struggle to maintain temporal, spatial, and narrative coherence across image sequences and frequently lack the depth and engagement of human-authored stories. To address these challenges, we propose Story with Large Language and Vision Assistant (StoryLLaVA), a novel framework for enhancing visual storytelling. Our approach introduces a Topic-Driven Narrative Optimizer (TDNO) that improves both the training data and MLLM models by integrating image descriptions, topic generation, and GPT-4-based refinements. Furthermore, we employ a preference-based ranked story sampling method that aligns model outputs with human storytelling preferences through positive-negative pairing. These two phases of the framework differ in their training methods: the former uses supervised fine-tuning, while the latter incorporates reinforcement learning with positive and negative sample pairs. Experimental results demonstrate that StoryLLaVA outperforms current models in visual relevance, coherence, and fluency, with LLM-based evaluations confirming the generation of richer and more engaging narratives. The enhanced dataset and model are available at https://***/XxxZzD/StoryLLaVA. © 2025 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hybrid Model for Enhancing Fault Detection System in Nuclear Power Plant using Support Vector Machine and Multivariate State Estimation Techniques

Hybrid Model for Enhancing Fault Detection System in Nuclear...

引用

Trends in Material Science and Inventive Materials (ICTMIM), International Conference on

作者： Rahul Rajendhiran Ayyanathan N Department of Computer Application Hindustan Institute of Technology and Science Chennai Tamil Nadu

ISBN: (数字)9798331501488

ISBN: (纸本)9798331501495

Nuclear power plants (NPPs) are vital for sustainable energy production but require meticulous monitoring to ensure safety and operational stability. This study proposes a hybrid framework integrating Support Vector Machines (SVM) and Multivariate State Estimation (MSE) to enhance real-time fault detection and system reliability in NPPs. While SVMs effectively classify operational anomalies, challenges persist in optimizing kernel selection and managing high-dimensional sensor data. Our approach combines SVM’s predictive capabilities with MSE’s dynamic state estimation, enabling early detection of deviations and improved decision-making. By addressing limitations in real-time data processing and complex nuclear environments, this method supports predictive maintenance and reduces operational risks. The study reviews existing techniques and demonstrates how merging these tools advances monitoring accuracy, safety, and efficiency in NPPs. This paper explored critical gaps in the application of Support Vector Machines (SVM) for real-time monitoring in nuclear power plants (Nuclear Power Plants) and proposed a hybrid approach that combines SVM with the Multivariate State Estimation Technique (MSET).

关键词： Support vector machines Fault detection Real-time systems Hybrid power systems Safety Reliability State estimation Kernel Power generation Monitoring

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：