检索结果-内蒙古大学图书馆

Collaborative Advances in Software and COmputiNg (CASCON), International Conference on

作者： Mustafa Burak Topal Aysun Bozanta Ayse Basar Computer Engineering Bogazici University Istanbul Turkiye Management Information Systems Bogazici University Istanbul Turkiye Data Science Laboratory Toronto Metropolitan University Toronto Canada

ISBN: (数字)9798331504830

ISBN: (纸本)9798331515621

In this study, we explore the performance of large language models (LLMs) and provide insights into the strengths and weaknesses of these models in sentiment analysis. In addition, we explore the impact of various instruction methods and fine-tuning techniques on the models' performance and analyze how sensitive they are to different prompts. Although there are studies comparing LLMs on sentiment analysis tasks, there is a limited number of studies on fine-tuning strategies, instruction variety, and prompt sensitivity of LLMs for sentiment analysis. For this purpose, we used Llama2-7B, Lama3-8B, Mistral-7B, Gemma-7B, and Bloom-7B and compared them with BERT and Roberta. We evaluated fine-tuned and original chat versions with zero and few-shot experiments. We generated various instruction strategies and observed their effects on the performance of the models. We also compared Quantized Low-Rank Adapters (QLoRA) fine-tuning and full fine-tuning with all parameters. The fine-tuned versions performed better compared to the original chat versions on almost all tasks. The fine-tuned and chat versions of Llama3-8B and Mistral-7B outperformed others on these tasks, while the Llama2-7B-chat model often produced invalid responses. Our research indicates that QLoRA is a practical substitute for full fine-tuning, as it lessens computational demands without sacrificing performance. Fine-tuned models were less affected by variations in test prompts compared to chat models. This is likely because their specialized training allows them to better handle queries within their domain. In this exploratory study, we provide insights into the potential of LLMs in sentiment analysis tasks.

关键词： Training Sentiment analysis Analytical models Adaptation models Sensitivity Computational modeling Large language models Collaboration Software

来源：评论

学校读者我要写书评

暂无评论

Distributed solar generation forecasting using attention-based deep neural networks for cloud movement prediction

arXiv

引用

arXiv 2024年

作者： Perera, Maneesha De Hoog, Julian Bandara, Kasun Halgamuge, Saman Department of Mechanical Engineering School of Electrical Mechanical and Infrastructure Engineering The University of Melbourne Melbourne Australia School of Computing and Information Systems Melbourne Centre for Data Science The University of Melbourne Melbourne Australia

Accurate forecasts of distributed solar generation are necessary to reduce negative impacts resulting from the increased uptake of distributed solar photovoltaic (PV) systems. However, the high variability of solar generation over short time intervals (seconds to minutes) caused by cloud movement makes this forecasting task difficult. To address this, using cloud images, which capture the second-to-second changes in cloud cover affecting solar generation, has shown promise. Recently, deep neural networks with attention that focus on important regions of an image have been applied with success in many computer vision applications. However, their use for forecasting cloud movement has not yet been extensively explored. In this work, we propose an attention-based convolutional long short-term memory network to forecast cloud movement and apply an existing self-attention-based method previously proposed for video prediction to forecast cloud movement. We investigate and discuss the impact of cloud forecasts from attention-based methods towards forecasting distributed solar generation, compared to cloud forecasts from non-attention-based methods. We further provide insights into the different solar forecast performances that can be achieved for high and low altitude clouds. We find that for clouds at high altitudes, the cloud predictions obtained using attention-based methods result in solar forecast skill score improvements of 5.86% or more compared to non-attention-based methods. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adversarial Attacks on Featureless Deep Learning Malicious URLs Detection

引用

Computers, Materials & Continua 2021年第7期68卷 921-939页

作者： Bader Rasheed Adil Khan S.M.Ahsan Kazmi Rasheed Hussain Md.Jalil Piran Doug Young Suh Institute of Data Science and Articial Intelligence Innopolis UniversityInnopolis420500Russia Institute of Information Security and Cyberphysical Systems Innopolis UniversityInnopolis420500Russia Department of Computer Science and Engineering Sejong UniversitySeoulKorea Department of Electronics Engineering Kyung Hee UniversityYonginKorea

Detecting malicious Uniform Resource Locators(URLs)is crucially important to prevent attackers from committing *** researches have investigated the role of machine learning(ML)models to detect malicious *** using ML algorithms,rst,the features of URLs are extracted,and then different ML models are *** limitation of this approach is that it requires manual feature engineering and it does not consider the sequential patterns in the ***,deep learning(DL)models are used to solve these issues since they are able to perform featureless ***,DL models give better accuracy and generalization to newly designed URLs;however,the results of our study show that these models,such as any other DL models,can be susceptible to adversarial *** this paper,we examine the robustness of these models and demonstrate the importance of considering this susceptibility before applying such detection systems in real-world *** propose and demonstrate a black-box attack based on scoring functions with greedy search for the minimum number of perturbations leading to a *** attack is examined against different types of convolutional neural networks(CNN)-based URL classiers and it causes a tangible decrease in the accuracy with more than 56%reduction in the accuracy of the best classier(among the selected classiers for this work).Moreover,adversarial training shows promising results in reducing the inuence of the attack on the robustness of the model to less than 7%on average.

关键词： Malicious URLs detection deep learning adversarial attack web security

来源：评论

学校读者我要写书评

暂无评论

Improving Prediction Quality of Face Image Preference Using Combinatorial Fusion Algorithm 16th

Improving Prediction Quality of Face Image Preference Using...

引用

16th International Conference on Brain Informatics, BI 2023

作者： Zhang, Zihan Schweikert, Christina Shimojo, Shinsuke Hsu, D. Frank Laboratory of Informatics and Data Mining Department of Computer and Information Science Fordham University YorkNY10023 United States Division of Computer Science Mathematics and Science St. John’s University QueensNY11439 United States Division of Biology and Biological Engineering/Computation and Neural Systems California Institute of Technology PasadenaCA91125 United States

ISBN: (纸本)9783031430749

When two face images are shown to a subject, the subject’s preference choice is influenced by many factors. Although it is a challenging task, one way to detect a subject’s preference is to analyze the eye movement gaze cascade in the recorded video sequence together with a set of extracted attributes (features). Combinatorial fusion algorithm (CFA) is a new information fusion and machine learning paradigm for combining multiple scoring systems using rank-score characteristic (RSC) function and cognitive diversity (CD). In this paper, we apply CFA in the analysis of the eye movement gaze cascade sequence. In particular, we characterize each of the attributes and measure the diversity between two attributes using RSC function and CD respectively. The novelty of the combinatorial fusion approach is the new paradigm of incorporating both score function and rank function as well as using both score combination and rank combination. In addition, our results demonstrate that weighted rank combination has some advantage over weighted score combination when the weight is measured using diversity strength. Since diversity strength depends only on cognitive diversity between two attributes but not on any specific sequence in the eye movement gaze cascade, our result facilitates learning and modeling in an unsupervised manner. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： information fusion

来源：评论

学校读者我要写书评

暂无评论

MoundCount: A detection-based approach for automatic counting of planting microsites on UAV images

MoundCount: A detection-based approach for automatic countin...

引用

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Ahmed Zgaren Wassim Bouachir Nizar Bouguila Riad I. Hammoud Data Science Laboratory University of Québec (TÉLUQ) Institute for Information Systems Engineering Concordia University PlusAI Inc.

Planting by mounding is a commonly used forestry technique that improves soil quality and ensures optimal tree growth conditions. During planting operations, one of the main planning steps is to estimate the number of mechanically created mounds in each planting block. Traditional counting methods involve manual field surveys or human photo-interpretation of UAV images, which are generally subject to errors and time-consuming. In this work, we propose a new approach to count mounds on UAV orthomosaics. Our framework is designed to estimate the required number of seedlings for a given planting block, based on a visual detection approach and a global estimation module. Firstly, a deep local detection model is applied on local patches to recognize and count visible mounds. Then, an estimation model, based on global features is used to predict the final number of plant seedling required for a given plantation block. To evaluate the proposed framework in real-world conditions, we constructed a large UAV dataset, including 18 UAV orthomosaics, comprising 111,000 mounds. We have conducted extensive experiments in our dataset, including a comparison with the state-of-the-art counting methods, as well as an analysis of Human-Level Performance (HLP) in identifying and annotating mounds. The experimental results show that our model reaches the best performance in terms of MAE and MSE, by comparison to state-of-the-art automatic counting mehtods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Embracing Uncertainty: A Diffusion Generative Model of Spectrum Efficiency in 5G Networks 15

Embracing Uncertainty: A Diffusion Generative Model of Spect...

引用

15th IEEE International Conference on Wireless Communications and Signal Processing, WCSP 2023

作者： Wang, Hao Tang, Zhiwei Zhang, Shutao Shen, Chao Chang, Tsung-Hui Beijing Jiaotong University School of Electronic and Information Engineering Beijing China Shenzhen Research Institute of Big Data Shenzhen China The Chinese University of HongKong School of Science and Engineering Shenzhen China CUHKSZ-SRIBD-Huawei Joint Research Laboratory for Optimization of Future Network Systems Shenzhen China Pengcheng Laboratory Shenzhen China

ISBN: (纸本)9798350324662

Spectrum efficiency modeling is a crucial enabling technology for optimizing 5G networks. Neural networks have been employed to model the complex and nonlinear relationship between spectrum efficiency and other 5G network features, including reference signal received power (RSRP), modulation and coding scheme (MCS), and rank indicator (RI). However, the current neural network model can only produce deterministic predictions, disregarding the stochastic nature of wireless networks, which may lead to suboptimal network performance. To address this limitation and embrace the uncertainty, we propose a diffusion generative model that can learn the conditional distribution of spectrum efficiency given the information of RSRP, MCS, and RI, providing a more accurate representation of the inherent variability in wireless networks. Additionally, we introduce a novel neural network architecture that incorporates a U-Net structure with Multi-Layer Perceptron (MLP) as building blocks, facilitating efficient learning of the denoising function within the diffusion generative model. Simulation results demonstrate that the proposed diffusion generative model accurately learns the statistical distribution of spectrum efficiency. Moreover, the proposed diffusion generative model yields improved fitting performance based on real-world measurements and enables quantification of uncertainty in spectrum efficiency modeling, which is essential for better network optimization. © 2023 IEEE.

关键词： diffusion spectrum efficiency U-Net

来源：评论

学校读者我要写书评

暂无评论

Characteristics Exploration of Hospitals in Shanghai through Spatial Relationship Using Taxi data 7

Characteristics Exploration of Hospitals in Shanghai through...

引用

7th International Conference on Image, Vision and Computing, ICIVC 2022

作者： Zhou, Yixuan Zhang, Lei Xu, Qin Liu, Yixiao Fu, Wen Tongji University Department of Traffic Information and Control Engineering Shanghai China Tongji University Shanghai Research Institute for Intelligent Autonomous Systems Shanghai China City University of Macau Faculty of Data Science China

ISBN: (数字)9781665467346

ISBN: (纸本)9781665467346

With the increasing volume of spatiotemporal traffic data, many scholars used it to explore the characteristics of urban facilities. In this paper, a method of classifying the main tertiary hospitals in Shanghai using taxi data of online car-hailing was proposed. Rasterization of the researched area and extraction of OD (Origin-Destination) records were done, and an optimum buffer distance threshold was determined. By comparing the previous studies, we designed the clustering approach (based on K-Means algorithm) and set new inputs based on trips at different distances from a researched hospital. A reasonable result was achieved: 4 types of hospitals are obtained and a discussion was conducted. This research is valuable for identifying the function and orientation of hospitals, and can help government better understand the spatial relationship of hospitals. © 2022 IEEE.

关键词： Hospitals

来源：评论

学校读者我要写书评

暂无评论

A Novel Breast Cancer Detection and Classification Using Enhanced ANN Classification

A Novel Breast Cancer Detection and Classification Using Enh...

引用

IoT Based Control Networks and Intelligent systems (ICICNIS), International Conference on

作者： P. Mathiyalagan G. Kiruthiga A. Rasmi M. Vadivel K.V. Mahalakshmi T.S. Poornappriya Department of CSE Sri Ramakrishna Engineering College Coimbatore Dept of Artificial intelligence and Data science Karpagam College of Engineering Coimbatore Information Science and Engineering RR Institute of Technology Bangalore Department of Information Technology Excel Engineering College Namakkal TamilNadu CSE B V Raju Institute of Technology Telangana Data and Analytics Aspire Systems Pvt Ltd Bengaluru Karnataka

ISBN: (数字)9798331518097

ISBN: (纸本)9798331518103

The second most prevalent and leading cause of cancer death is breast cancer, which is the most common malignancy among women. Because the causes of breast cancer are not fully known, there is currently no reliable technique to prevent it. In recent years, breast cancer has become a widespread condition among women. Over the past several years, the issue of breast tumour categorization has become a significant issue. This article offers logical reasoning for the order in which to identify malignant lesions, a significant development in the mammography diagnosis of breast cancer. As a result, we concentrate on studying and analysing cancer imaging, with a particular emphasis on breast cancer. Mammography produces and processes pictures that are used in breast cancer detection. Sensitivity, specificity, and classification accuracy are the metrics used to assess the experimental findings. Results of an improved ANN classifier for differentiating between normal and abnormal cases in pictures from applied advanced mammography.

关键词： Image segmentation Sensitivity Mortality Predictive models Inspection Breast cancer Reliability Lesions Intelligent systems Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

OCET: One-Dimensional Convolution Embedding Transformer for Stock Trend Prediction 1

引用

17th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2022

作者： Yang, Peng Fu, Lang Zhang, Jian Li, Guiying Department of Statistics and Data Science Southern University of Science and Technology Shenzhen518055 China Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen518055 China Shenzhen Securities Information Co. Ltd. Shenzhen China

ISBN: (数字)9789819915491

ISBN: (纸本)9789819915484

Due to the strong data fitting ability of deep learning, the use of deep learning for quantitative trading has gradually sprung up in recent years. As a classical problem of quantitative trading, Stock Trend Prediction (STP) mainly predicts the movement of stock price in the future through the historical price information to better guide quantitative trading. In recent years, some deep learning work has made great progress in STP by effectively grasping long-term timing information. However, as a kind of real-time series data, short-term timing information is also very important, because stock trading is high-frequency and price fluctuates violently. And with the popularity of Transformer, there is a lack of an effective combination of feature extraction and Transformer in STP tasks. To make better use of short term information, we propose One-dimensional Convolution Embedding (OCE). Simultaneously, we introduce effective feature extraction with Transformer into STP problem to extract feature information and capture long-term timing information. By combining OCE and Transformer organically, we propose a noval STP prediction model, One-dimensional Convolution Embedding Transformer (OCET), to capture long-term and short-term time series information. Finally, OCET achieves a highest accuracy up to 0.927 in public benchmark FI-2010 When reasoning speed is twice that of SOTA models and a highest accuracy of 0.426 in HKGSAS-2020. Empirical results on these two datasets show that our OCET is significantly superior than other algorithms in STP tasks. Code are available at https://***/langgege-cqu/OCET. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Novel Explainable CNN Model for Screening COVID-19 on X-ray Images

引用

Computer systems science & engineering 2023年第8期46卷 1789-1809页

作者： Hicham Moujahid Bouchaib Cherradi Oussama El Gannour Wamda Nagmeldin Abdelzahir Abdelmaboud Mohammed Al-Sarem Lhoussain Bahatti Faisal Saeed Mohammed Hadwan EEIS Laboratory ENSET of MohammediaHassan II University of CasablancaMohammedia28820Morocco STIE Team CRMEF Casablanca-SettatThe Provincial Section of El JadidaEl Jadida24000Morocco Department of Information Systems College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia Department of Information Systems King Khalid UniversityMuhayel Aseer61913Saudi Arabia College of Computer Science and Engineering Taibah UniversityMedina42353Saudi Arabia Department of Computer Science University of Sheba RegionMarib14400Yemen DAAI Research Group Department of Computing and Data ScienceSchool of Computing and Digital TechnologyBirmingham City UniversityBirminghamB47XGUK Department of Information Technology College of ComputerQassim UniversityBuraydah 51452Saudi Arabia Department of Computer Science College of Applied SciencesTaiz UniversityTaiz6803Yemen

Due to the rapid propagation characteristic of the Coronavirus(COVID-19)disease,manual diagnostic methods cannot handle the large number of infected individuals to prevent the spread of ***,new automated diagnostic methods have been brought on board,particularly methods based on artificial intelligence using different medical data such as X-ray *** imaging,for example,produces several image types that can be processed and analyzed by machine and deep learning methods.X-ray imaging materials widely exist in most hospitals and health institutes since they are affordable compared to other imaging *** this paper,we propose a novel Convolutional Neural Network(CNN)model(COV2Net)that can detect COVID-19 virus by analyzing the X-ray images of suspected *** model is trained on a dataset containing thousands of X-ray images collected from different *** model was tested and evaluated on an independent *** order to approve the performance of the proposed model,three CNN models namely Mobile-Net,Residential Energy Services Network(Res-Net),and Visual Geometry Group 16(VGG-16)have been implemented using transfer learning *** experiment consists of a multi-label classification task based on X-ray images for normal patients,patients infected by COVID-19 virus and other patients infected with *** proposed model is empowered with Gradient-weighted Class Activation Mapping(Grad-CAM)and Grad-Cam++techniques for a visual explanation and methodology debugging *** finding results show that the proposed model COV2Net outperforms the state-of-the-art methods.

关键词： Artificial intelligence intelligent diagnostic systems decisionmaking COVID-19 convolutional neural network

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：