检索结果-内蒙古大学图书馆

24th IEEE International Conference on data Mining, ICDM 2024

作者： Liang, Fei-Yao Xi, Wu-Dong Xing, Xing-Xing Wan, Wei Wang, Chang-Dong Chen, Min Guizani, Mohsen School of Computer Science and Engineering Sun Yat-sen University Guangzhou China NetEase Games China UX Center NetEase Games Guangzhou China Guangdong Provincial Key Laboratory of Intellectual Property and Big Data Guangzhou China School of Computer Science and Engineering South China University of Technology Guangzhou China Pazhou Laboratory Guangzhou China Machine Learning Department Abu Dhabi United Arab Emirates

ISBN: (纸本)9798331506681

With the explosive growth of information, recommendation systems have emerged to alleviate the problem of information overload. In order to improve the performance of recommendation systems, many existing methods introduce Large Language Models to extract textual information from description text. However, Large Language Models are trained on large-scale generic textual data and may face a semantic gap for downstream recommendation tasks. To address the above issues, we propose Contrastive learning for Adapting Language Model to Sequential Recommendation (CLA-Rec). In CLA-Rec, we first extract text embeddings from description text using Large Language Models and align the text embeddings learned by Large Language Models with the collaborative information through contrastive learning to obtain high-quality item representations. Through semantic alignment, we bridge the semantic gap between Large Language Models and the recommendation task. To map textual information and collaborative information into user representations, we utilize a Transformer model to learn user representations and capture user preferences by combining the semantically aligned item representations. Extensive experiments on three public datasets demonstrate that our method outperforms state-of-the-art approaches on multiple evaluation metrics, illustrating the effectiveness of the CLA-Rec model in adapting Large Language Models to recommendation tasks. © 2024 IEEE.

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

RecCoder: Reformulating Sequential Recommendation as Large Language Model-Based Code Completion 24

RecCoder: Reformulating Sequential Recommendation as Large L...

引用

24th IEEE International Conference on data Mining, ICDM 2024

作者： Lai, Kai-Huang Xi, Wu-Dong Xing, Xing-Xing Wan, Wei Wang, Chang-Dong Chen, Min Guizani, Mohsen School of Computer Science and Engineering Sun Yat-sen University Guangzhou China NetEase Games China UX Center NetEase Games Guangzhou China Guangdong Provincial Key Laboratory of Intellectual Property and Big Data Guangzhou China School of Computer Science and Engineering South China University of Technology Guangzhou China Pazhou Laboratory Guangzhou China Machine Learning Department Abu Dhabi United Arab Emirates

ISBN: (纸本)9798331506681

In the evolving landscape of sequential recommendation systems, the application of Large Language Models (LLMs) is increasingly prominent. However, current attempts typically utilize general-purpose LLMs, which present a mismatch in capability and a large semantic gap relative to the specialized needs of recommendation tasks. To tackle these issues, we introduce RecCoder, an innovative model that reformulates sequential recommendation as a code completion task. This approach leverages the superior reasoning capability of code LLMs as a backbone, aligning well with the requirements of recommendation systems. To bridge the semantic gap, RecCoder creates extra tokens for each item and employs item content to initialize token embeddings. Furthermore, we have developed a suite of Semantic Adaptation Fine-tuning tasks, tailored to enhance the model's acquisition of both content and collaborative semantic information, thus aligning the model's intrinsic capabilities with the unique demands of recommendation tasks. Through extensive testing on three public datasets, RecCoder has shown remarkable improvements over existing models in terms of recommendation accuracy and efficiency. This success highlights the substantial yet previously underexplored potential of code LLMs in improving recommendation accuracy and efficiency, suggesting a promising new direction for future research in this area. The implementation code is accessible at https://***/AllminerLab/Code-for-RecCoder-master. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Predicting Agricultural Crop Damage Caused by Unexpected Rainfall Using Deep learning

Predicting Agricultural Crop Damage Caused by Unexpected Rai...

引用

Intelligent Systems for Cybersecurity (ISCS), International Conference on

作者： Bhushan Fulkar Pawan Patil Gaurav Srivastav Promod Mahale Department of Artificial Intelligence and Data science Faculty of Engineering and Technology Wardha Maharashtra India Artificial Intelligence and Data science Faculty of Engineering and Technology DMIHER(DU) Wardha Maharashtra India Department of Artificial Intelligence and Machine Learning Faculty of Engineering and Technology DMIHER(DU) Wardha Maharashtra India

ISBN: (数字)9798350375237

ISBN: (纸本)9798350375244

Efficient allocation of resources and timely agricultural interventions depend on the precise identification of crop loss at the field parcel level. Using recent data from 2018 to 2023, this study investigates the integration of deep learning techniques with real-time field photography to classify agricultural field parcels into those experiencing crop loss and those not. We build and assess deep learning models specifically for crop loss classification using a dataset from the Finnish Food Authority (FFA) that combines on-the-ground photos taken during field visits with comprehensive field parcel information. In this work, we use convolutional neural networks (CNNs) to examine the visual characteristics that we have extracted from field photos in order to identify the subtleties that may indicate crop health or possible loss. Our goal is to improve the model's generalization capabilities over a variety of crop types and agricultural landscapes by training it on a combination of field parcel data and corresponding photographs.

关键词： Deep learning Training Visualization Uncertainty Rain Crops Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Development of Punjabi Automatic Speech Recognition Application for Mobile Devices

Development of Punjabi Automatic Speech Recognition Applicat...

引用

International Conference on Computing Communication Control and Automation (ICCUBEA)

作者： Puneet Mittal Sukhwinder Sharma Department of Artificial Intelligence & Machine Learning Manipal University Jaipur Jaipur India Department of Data Science & Engineering Manipal University Jaipur Jaipur India

Speech recognition based mobile device applications are gaining popularity due to their ease of use, flexibility as well as ability to provide hands-free access to device features and functions for persons without hands or with disabilities like blindness. The increased accuracy of Automatic Speech Recognition (ASR) systems and support to multiple languages is further motivating the researchers to develop such applications. The development of an application for mobile device helps to validate the applicability of an ASR system in real world environment. An android based speech recognition application for calling and messaging features has been designed and developed in this paper. User can send message or call to any phone number or contact stored in the mobile phone using Punjabi speech. Punjabi based ASR system having pronunciation dictionary, acoustic model and language model is used to implement the underlying speech recognition for Punjabi speakers. Speech user interface has been designed using Android, while AndroidPocketSphinx has been used as speech decoder. The successfully running application has been tested for multiple male and female native Punjabi speakers, followed by thorough performance analysis. The results shown are quite optimistic with a very low combined error of 1.6% for all female speakers and 2.1% for all male speakers. The application gives 98.4% success rate or recognition accuracy for female speakers and 97.9% for male speakers for the underlying Punjabi based ASR system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Segment Together: A Versatile Paradigm for Semi-Supervised Medical Image Segmentation

引用

IEEE Transactions on Medical Imaging 2025年 PP卷 PP页

作者： Zeng, Qingjie Xie, Yutong Lu, Zilin Lu, Mengkang Wu, Yicheng Xia, Yong Northwestern Polytechnical University National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Xi’an710072 China The University of Adelaide Australian Institute for Machine Learning AdelaideSA5000 Australia Monash University Faculty of Information Technology Department of Data Science and AI Australia

The scarcity of annotations has become a significant obstacle in training powerful deep-learning models for medical image segmentation, limiting their clinical application. To overcome this, semi-supervised learning that leverages abundant unlabeled data is highly desirable to enhance model training. However, most existing works still focus on specific medical tasks and underestimate the potential of learning across diverse tasks and datasets. In this paper, we propose a Versatile Semi-supervised framework (VerSemi) to present a new perspective that integrates various SSL tasks into a unified model with an extensive label space, exploiting more unlabeled data for semi-supervised medical image segmentation. Specifically, we introduce a dynamic task-prompted design to segment various targets from different datasets. Next, this unified model is used to identify the foreground regions from all labeled data, capturing cross-dataset semantics. Particularly, we create a synthetic task with a CutMix strategy to augment foreground targets within the expanded label space. To effectively utilize unlabeled data, we introduce a consistency constraint that aligns aggregated predictions from various tasks with those from the synthetic task, further guiding the model to accurately segment foreground regions during training. We evaluated our VerSemi framework against seven established SSL methods on four public benchmarking datasets. Our results suggest that VerSemi consistently outperforms all competing methods, beating the second-best method with a 2.69% average Dice gain on four datasets and setting a new state of the art for semi-supervised medical image segmentation. Code is available at https://***/maxwell0027/VerSemi. © 1982-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

U-Star: AN Asymmetric U-Shaped Network Based on Element-Wise Multiplication to Segment Nuclei in H&E Stained Histological Images 22

U-Star: AN Asymmetric U-Shaped Network Based on Element-Wise...

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Yang, Guangzhengao Zhang, Li Zhao, Jie Chen, Zifan Li, Haoshen Dong, Bin Center for Data Science Peking University China Peking University National Engineering Laboratory for Big Data Analysis and Applications China Peking University Changsha Institute for Computing and Digital Economy China Beijing International Center for Mathematical Research Peking University China Center for Machine Learning Research Peking University China National Biomedical Imaging Center Peking University China

ISBN: (纸本)9798331520526

Nuclei segmentation in Hematoxylin and Eosin (H&E) stained images plays a crucial role in cancer diagnosis and pathological evaluation, enabling pathologists to identify abnormal cells and assess their morphology and distribution. While current automated nuclei segmentation methods predominantly employ convolutional neural networks and attention mechanisms, the potential of element-wise multiplication has been largely unexplored. This paper introduces U-Star, a novel asymmetric segmentation network based on the star block that leverages element-wise multiplication. U-Star adopts the classic encoder-decoder architecture and innovatively implements star-connection as an alternative to traditional skip-connections. In experiments on an H&E stained image dataset, U-Star achieved superior performance with a Dice coefficient of 0.8783, accuracy of 0.9089, and IoU of 0.7929, significantly outperforming baseline models. Extensive ablation studies validate the effectiveness of the star-connection and demonstrate the advantages of our proposed framework. Beyond advancing the application of element-wise multiplication techniques, U-Star shows promising potential for broader applications in medical image segmentation. © 2025 IEEE.

关键词： element-wise multiplication nuclei segmentation tokenized MLP

来源：评论

学校读者我要写书评

暂无评论

Vehicle Prediction for BUS Identification Output from our Route Testing Real Time Algorithm 5

Vehicle Prediction for BUS Identification Output from our Ro...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Misba, M. Ramya, R. Dickson, Joel Sharmila, L. Kavitha, J. Udayakumar, K. Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Artificial Intelligence and Machine Learning Tamil Nadu India St. Joseph's College of Engineering Department of Artificial Intelligence and Data Science Chennai India Bethlehem Institute of Engineering Tamil Nadu Karungal India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu India

ISBN: (纸本)9798331530013

Traffic generation in Indian cities is of a mixed nature, comprising over a dozen types of vehicles that can be broadly categorized into slow-moving and fast-moving vehicles. This study highlights the challenges associated with the inefficient operation of the existing bus system. GPS and mobile networks form integral components of the current system, enabling data storage and management using PostgreSQL. The system provides robust and reliable data to fulfill requests from other software applications. Operating on cloud platforms, it is compatible with all major web browsers. The proposed algorithm continuously tracks the real-time location of buses and their corresponding WMS (Web Map Service) location, alerting users through marker notifications. This paper also explores measures to evaluate the efficiency and effectiveness of bus services. Recognizing that an inadequate public transport system impedes economic growth and development, this study emphasizes the need to enhance the overall quality and accessibility of public transportation. The findings aim to improve the operational efficiency of bus services, contributing to a more effective and sustainable transport system. © 2024 IEEE.

关键词： Buses

来源：评论

学校读者我要写书评

暂无评论

Chest X-Ray Analysis Using machine learning for Pneumonia Detection

Chest X-Ray Analysis Using Machine Learning for Pneumonia De...

引用

data, Computation and Communication (ICDCC), International Conference on

作者： Thenmozhi MI Nithya Sree R S Mohammed Esa Khan J Akshaya R B Barath kumar L Department of Artificial Intelligence and Data Science Sri Eshwar College of Engineering Coimbatore Tamil Nadu India Department of CSE (Artificial Intelligence and Machine Learning) Sri Eshwar College of Engineering Coimbatore Tamil Nadu India

ISBN: (数字)9798331532956

ISBN: (纸本)9798331532963

A dangerous and potentially fatal respiratory infection is pneumonia., especially for young children and the elderly. With the shortage of radiologists, our automated approach can help fill the gap by providing a quick and reliable diagnosis. By leveraging advanced machine learning techniques, with the ultimate goal of improving patient outcomes by increasing the effectiveness and accuracy of pneumonia detection. Our study proposes an automated approach to detect pneumonia by applying advanced machine learning strategies to chest radiographs. The method is taking relevant information out of the photos and using a robust classification algorithm to distinguish between healthy images and images that show pneumonia. For image processing tasks, the Convolutional Neural Network (CNN) algorithm is selected due to its efficacy. A useful indicator for assessing pneumonia detection systems, the F1 score aids in determining how well machine learning models work. By indicating the model's capacity to precisely detect optimistic cases while reducing false positives, it offers a reasonable valuation of overall performance. The created model is a useful tool to assist healthcare workers in promptly identifying cases of pneumonia, since it demonstrates promising sensitivity and specificity. The findings of this study have implications for respiratory infection treatment that include accelerating diagnosis times, decreasing human error, and eventually increasing patient outcomes.

关键词： Pneumonia Accuracy Computational modeling machine learning Medical services data models Classification algorithms Convolutional neural networks Reliability X-ray imaging

来源：评论

学校读者我要写书评

暂无评论

Attention based 1-D CNN system for detection of Freezing of gait (FOG) in Parkinsons Patients

Attention based 1-D CNN system for detection of Freezing of ...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： D Pradeep Kumar B J Sowmya Ashvin Vincent Aravindh Pandiyan Department of Computer Science and Engineering Ramaiah Institute of Technology Bangalore India Department of Artificial Intelligence and Data Science Ramaiah Institute of Technology Bangalore India Machine Learning Engineer Bangalore India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

One common clinical symptom seen in Parkinson’s disease (PD) patients is freezing of gait (FOG). It manifests as an irregular gait, marked by abrupt, involuntary stopping of movement during gait episodes. FOG entails a major negative effect on PD patients’ quality of life. In this work, we analyze the movement data that is collected using the lower-back 3D accelerometer worn by the patients during FOG episodes. By employing machine learning methods to classify this data, we aim to accurately detect FOG trends. In particular, we focus on Deep learning-based techniques, specifically an attention-based 1D Convolutional Neural Network (1D-CNN), due to their capacity to extract intricate features from unprocessed sensor input. Our results indicate that the proposed model achieves AUC scores of 0.9032 with respect to the TDCSFOG dataset and 0.8682 for the DeFOG dataset, for a combined average AUC of 0.8857. Mean Average Precision (mAP) scores for TDCSFOG and DeFOG reach 0.8388 and 0.779, respectively, for an average of 0.8089, showing the ability of the model to predict FOG occurrences over time. These findings suggest techniques based on Deep learning enhance FOG detection, allowing clinicians to more effectively tailor treatments and care strategies for Parkinson’s patients, thus enhancing their ability to move and overall well-being.

关键词： Deep learning Accelerometers Three-dimensional displays Accuracy Predictive models Feature extraction Transformers Convolutional neural networks Forecasting Diseases

来源：评论

学校读者我要写书评

暂无评论

Mean Estimation in Banach Spaces Under Infinite Variance and Martingale Dependence

arXiv

引用

arXiv 2024年

作者： Whitehouse, Justin Chugg, Ben Martinez-Taboada, Diego Ramdas, Aaditya Management Science and Engineering Stanford University United States Machine Learning Department Carnegie Mellon University United States Department of Statistics and Data Science Carnegie Mellon University United States

We consider estimating the shared mean of a sequence of heavy-tailed random variables taking values in a Banach space. In particular, we revisit and extend a simple truncation-based mean estimator first proposed by Catoni and Giulini. While existing truncation-based approaches require a bound on the raw (non-central) second moment of observations, our results hold under a bound on either the central or non-central pth moment for some p ∈ (1, 2]. Our analysis thus handles distributions with infinite variance. The main contributions of the paper follow from exploiting connections between truncation-based mean estimation and the concentration of martingales in smooth Banach spaces. We prove two types of time-uniform bounds on the distance between the estimator and unknown mean: line-crossing inequalities, which can be optimized for a fixed sample size n, and iterated logarithm inequalities, which match the tightness of line-crossing inequalities at all points in time up to a doubly logarithmic factor in n. Our results do not depend on the dimension of the Banach space, hold under martingale dependence, and all constants in the inequalities are known and small. Copyright © 2024, The Authors. All rights reserved.

关键词： Banach spaces

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：