检索结果-内蒙古大学图书馆

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Bhimanpallewar, Ratnmala N. Jangid, Satish Kumar Yadav, Rakesh Kumar Arunkumar, D.T. Dehankar, Pooja Geetha, B. Vishwakarma Institute of Information Technology Department of Information Technology Pune India Vivekananda Global University Department of Electrical Engineering Jaipur India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Faculty of Engineering and Technology Department of Mechanical Engineering Karnataka Bangalore India School of Engineering Ajeenkya D. Y. Patil University Pune India Prince Shri Venkateshwara Padmavathy Engineering College Department of Science and Humanities Chennai128 India

ISBN: (纸本)9798350319125

Huge information evaluation, the use of synthetic Intelligence, is a manner of using AI structures to automate the system of extracting meaningful insights from massive sets of statistics. A combination of AI-driven algorithms and hardware may be used to quickly perceive styles in unlabeled information that could otherwise take vast quantities of time to extract. This paper presents a method and framework for Automating Big data Analysis using Artificial Intelligence (AI). With the increasing volume and complexity of big data, traditional manual analysis methods are becoming inefficient and often result in inaccurate or incomplete insights. To address this challenge, we propose a systematic approach that leverages AI techniques such as machine learning and natural language processing to automate the process of data analysis. Our framework includes measures for data preprocessing, feature selection, model building, and result interpretation, and adapts to different types and sources of big data. We demonstrate the effectiveness of our approach through experiments on real-world datasets and compare the results with manual analysis methods. The proposed automated approach not only improves the speed and accuracy of big data analysis, but also reduces the human effort and expertise required. This has the potential to greatly enhance decision-making processes in various industries and domains that deal with large amounts of data. These talents can be used to permit higher choice-making and create extra efficient, automatic approaches to conducting huge-scale data analysis. © 2023 ieee.

关键词： Permit Processing Quantities Similarly visualization

来源：评论

学校读者我要写书评

暂无评论

Relation-Aware Fine-Grained Reasoning Network for Textbook Question Answering

引用

ieee TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2023年第1期34卷 15-27页

作者： Ma, Jie Liu, Jun Wang, Yaxian Li, Junjun Liu, Tongliang Xi An Jiao Tong Univ Sch Comp Sci & Technol Natl Engn Lab Big Data Analyt Xian 710049 Peoples R China Xi An Jiao Tong Univ Sch Comp Sci & Technol Shaanxi Prov Key Lab Satellite & Terr Network Tec Xian 710049 Peoples R China Univ Sydney Sch Comp Sci Fac Engn Trustworthy Machine Learning Lab Darlington NSW 2008 Australia

Textbook question answering (TQA) is a task that one should answer non-diagram and diagram questions accurately, given a large context which consists of abundant diagrams and essays. Although lots of studies have made significant progress in the natural image question answering (QA), they are not applicable to comprehending diagrams and reasoning over the long multimodal context. To address the above issues, we propose a relation-aware fine-grained reasoning (RAFR) network that performs fine-grained reasoning over the nodes of relation-based diagram graphs. Our method uses semantic dependencies and relative positions between nodes in the diagram to construct relation graphs and applies graph attention networks to learn diagram representations. To extract and reason over the multimodal knowledge, we first extract the text that is the most relevant to questions, options, and the instructional diagram which is the most relevant to question diagrams at the word-sentence level and the node-diagram level, respectively. Then, we apply instructional-diagram-guided attention and question-guided attention to reason over the node of question diagrams, respectively. The experimental results show that our proposed method achieves the best performance on the TQA dataset compared with baselines. We also conduct extensive ablation studies to comprehensively analyze the proposed method.

关键词： Semantics Cognition Knowledge discovery Task analysis visualization Shape Frontal lobe Diagram understanding machine reading comprehension (MRC) multi-modality textbook question answering (TQA)

来源：评论

学校读者我要写书评

暂无评论

SCREADER: Prompting Large Language Models to Interpret scRNA-seq data 24

SCREADER: Prompting Large Language Models to Interpret scRNA...

引用

24th ieee International Conference on data Mining Workshops, ICDMW 2024

作者： Li, Cong Long, Qingqing Zhou, Yuanchun Xiao, Meng Institute of Zoology Chinese Academy of Sciences State Key Laboratory of Stem Cell and Reproductive Biology China University of Chinese Academy of Sciences China Chinese Academy of Sciences Computer Network Information Center China

ISBN: (纸本)9798331530631

Large language models (LLMs) have demonstrated remarkable advancements, primarily due to their capabilities in modeling the hidden relationships within text sequences. This innovation presents a unique opportunity in the field of life sciences, where vast collections of single-cell omics data from multiple species provide a foundation for training foundational models. However, the challenge lies in the disparity of data scales across different species, hindering the development of a comprehensive model for interpreting genetic data across diverse organisms. In this study, we propose an innovative hybrid approach that integrates the general knowledge capabilities of LLMs with domain-specific representation models for single-cell omics data interpretation. We begin by focusing on genes as the fundamental unit of representation. Gene representations are initialized using functional descriptions, leveraging the strengths of mature language models such as LLaMA-2. By inputting single-cell gene-level expression data with prompts, we effectively model cellular representations based on the differential expression levels of genes across various species and cell types. In the experiments, we constructed developmental cells from humans and mice, specifically targeting cells that are challenging to annotate. We evaluated our methodology through basic tasks such as cell annotation and visualization analysis. The results demonstrate the efficacy of our approach compared to other methods using LLMs, highlighting significant improvements in accuracy and interoperability. Our hybrid approach enhances the representation of single-cell data and offers a robust framework for future research in cross-species genetic analysis. 1 © 2024 ieee.

关键词： data Mining Large Language Model Prompt Learning Single Cell RNA data

来源：评论

学校读者我要写书评

暂无评论

Radiation Monitoring and Environmental Assessment in Precision Agriculture: Development of an Integrated IoT Device with Comprehensive data Analysis Capabilities 26

Radiation Monitoring and Environmental Assessment in Precisi...

引用

26th International Conference on Computer and Information Technology, ICCIT 2023

作者： Chakraborty, Anik Gupta, Rittik Das Roy, Drupada Kabir, Md. Zesanul Saiful Islam Bablu, Md. Gupta, Riva Das University of Dhaka Department of Nuclear Engineering Dhaka Bangladesh Khulna University Engineering and Technology Department of Electronics and Communication Engineering Khulna Bangladesh Bangladesh Agriculture University Department of Environmental Science Mymensingh Bangladesh Chittagong University Engineering and Technology Department of Electrical and Electronic Engineering Chittagong Bangladesh University of Chittagong Department of Economics Chittagong Bangladesh

ISBN: (纸本)9798350359015

This paper presents the development of an integrated IoT-based device tailored for precision agriculture, offering a holistic approach to background radiation monitoring and environmental assessment. The system comprises a carefully designed front end powered by Arduino and NodeMCU microcontrollers. It features an array of high-precision sensors including DHT-11 for temperature and humidity, optical dust sensor for particulate matter detection, and calibrated MQ sensors for CH4 and NH3 gas detection, alongside a Geiger radiation counter. The back end is seamlessly integrated with the Blynk application, offering real-time mobile monitoring, Thingspeak for comprehensive data visualization, and a secure Google spreadsheet for reliable data storage. A rigorous sensor validation process was conducted, demonstrating that this device's measurements align statistically with those of commercially available devices, validated through paired sample t-tests in SPSS software. The prototypic data analysis system also forms a crucial aspect of this research. Over six months, data was gathered from three strategically significant locations in Bangladesh. This analysis not only validates our device's efficacy but also provides a template for future users to effectively interpret their data. Additionally, comprehensive data analysis, including a graphical representation of all six parameters, provides a detailed insight into environmental conditions. The proposed IoT device not only demonstrates its effectiveness in precision agriculture but also showcases its adaptability for deployment across diverse geographical locations worldwide. © 2023 ieee.

关键词： data Analysis Environmental Assessment IoT Precision Agriculture Radiation Monitoring

来源：评论

学校读者我要写书评

暂无评论

Semantic Guided Latent Parts Embedding for Few-Shot Learning 23

Semantic Guided Latent Parts Embedding for Few-Shot Learning

引用

23rd ieee/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Yang, Fengyuan Wang, Ruiping Chen, Xilin Chinese Acad Sci Key Lab Intelligent Informat Proc Inst Comp Technol Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Beijing Acad Artificial Intelligence Beijing 100084 Peoples R China

ISBN: (纸本)9781665493468

The ability of few-shot learning (FSL) is a basic requirement of intelligent agent learning in the open visual world. However, existing deep learning systems rely too heavily on large numbers of training samples, making it hard to learn new categories efficiently from limited size of training data. Two key challenges of FSL are insufficient comprehension and imperfect modeling of the few-shot novel class. For insufficient visual comprehension, semantic knowledge which is information from other modalities can help replenish the understanding of novel classes. But even so, most works still suffer from the second challenge because the single global class prototype they adopted is extremely unstable and imperfect given the larger intra-class variation and harder inter-class discrimination in FSL scenario. Thus, we propose to represent each class by its several different parts with the help of class semantic knowledge. Since we can never pre-define parts for unknown novel classes, we embed them in a latent manner. Concretely, we train a generator that takes the class semantic knowledge as input and outputs several filters of class-specific semantic latent parts. By applying each part filter, our model can pay attention to corresponding local regions containing each part. At the inference stage, the classification is conducted by comparing the similarities between those parts. Experiments on several FSL benchmarks demonstrate the effectiveness of our proposed method and show its potential to go beyond class recognition to class understanding. Furthermore, we also find when semantic knowledge is more visualized and customized, it will be more helpful in the FSL task.

关键词： Training Deep learning visualization Semantics Training data Prototypes Generators

来源：评论

学校读者我要写书评

暂无评论

Automated Malaria Parasite Detection in Blood Smear Images with CNNs 1

Automated Malaria Parasite Detection in Blood Smear Images w...

引用

1st International Conference on Artificial Intelligence for Innovations in Healthcare Industries, ICAIIHI 2023

作者： Pandey, Saroj Kumar Dingankar, R. Shreyas Singh, Kamred Udham Rose, Anthony Singh, Teekam Gla University Department of Computer Engineering & Apllications UP Mathura India Pune India School of Computing Graphic Era Hill University Dehradun India Graphic Era Deemed to Be University Department of Computer Science and Engineering Dehradun India

ISBN: (纸本)9798350330915

This study uses Convolutional Neural Networks (CNNs) to construct an automated parasite identification method in blood smear pictures, addressing the urgent need for accurate and easy malaria diagnosis. We use secondary data collected from several datasets, utilizing an interpretive mindset, a deductive technique, as well as a descriptive research strategy. Technical considerations such as architecture selection, data preparation, and interpretability approaches are carefully taken into account when perfecting the CNN model. The model's effectiveness has been demonstrated by results showing excellent sensitivity (95%) and specificity (92%) in parasite identification. Techniques for visualization make regions of interest clearer, increasing confidence and transparency. Testing for generalizability shows consistent results across several datasets and demographic groupings. The CNN-based methodology performs better than traditional microscopy and quick diagnostic tests when compared to current approaches, especially in situations of low parasitemia. With implications for improvements in healthcare delivery in malaria-endemic areas, this research advances automated malaria diagnosis. © 2023 ieee.

关键词： Automated Diagnosis Convolutional Neural Networks Interpretivism Malaria Medical Imaging

来源：评论

学校读者我要写书评

暂无评论

Machine Learning based model to Detect Anomaly in the Water

Machine Learning based model to Detect Anomaly in the Water

引用

2023 International Conference on Computational Intelligence and Sustainable Engineering Solution, CISES 2023

作者： Kumar, Gaurav Pandey, Saroj Kumar Yadav, Dhirendra Prasad Singh, Kamred Udham Singh, Teekam Kumar, Ankit Gla University Department of Computer Engineering & Applications UP Mathura India School of Computing Graphic Era Hill University Dehradun India Graphic Era University Department of Computer Science and Engineering Dehradun India

ISBN: (纸本)9798350323917

The environmental impact of technology is only one area where the field is expanding rapidly without necessarily good results. [1] Water contamination is one such critical problem. Because water is essential to human survival, polluting it has serious consequences for civilization. [1] Knowing what harmful substances are in the water and being able to identify them is a crucial step toward reducing the damage they cause. While Image classification and sparse coding have been widely employed for water pollution identification [1,] they have unintended implications when applied to bacterial information detection. The current technologies used to identify contaminants in photos and water pipes, such as Convolutional neural networks (CNN), natural language processing (NLP), and the Internet of Things (IoT), are expensive and inefficient when compared to 3D microscopy data. It is a model that uses categorization and data visualization to estimate the total number of bacteria in a given environment. Accuracy scores may be seen in the model's studied graphs, decision tree, confusion matrix, and classification report. By the use of these data sets, the crucial factors for clean water were evaluated, and a model was built that can categorize the massive amounts of information, find meaningful patterns, and make reliable predictions. It has been determined which method yields the highest accuracy prediction (87%) by thoroughly analyzing the available models' accuracy scores. This study thus provides a valid evaluation of bacterial water vs unadulterated water. © 2023 ieee.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Amer: A New Attribute-Missing Network Embedding Approach

引用

ieee TRANSACTIONS ON CYBERNETICS 2023年第7期53卷 4306-4319页

作者： Jin, Di Wang, Rui Wang, Tao He, Dongxiao Ding, Weiping Huang, Yuxiao Wang, Longbiao Pedrycz, Witold Tianjin Univ Coll Intelligence & Comp Tianjin 300350 Peoples R China Nantong Univ Sch Informat Sci & Technol Nantong 226019 Peoples R China George Washington Univ Data Sci Washington DC 20037 USA Univ Alberta Dept Elect & Comp Engn Edmonton AB T6R 2V4 Canada King Abgudulaziz Univ Fac Engn Dept Elect & Comp Engn Jeddah 21589 Saudi Arabia Polish Acad Sci Syst Res Inst PL-01447 Warsaw Poland

Network embedding which aims to learn a low dimensional representation of nodes is a powerful technique for network analysis. While network embedding for networks with complete attributes has been widely investigated, in many real-world applications the attributes of partial nodes are unobserved (i.e., missing) due to privacy concern or resource limit. Very recently, several network embedding methods have been proposed for attribute-missing networks. They first complete the missing attributes and then use the complemented network to learn network embedding. The parameters of these two processes cannot be adjusted by each other, resulting in compromised results. To address this problem, we propose a unified model in which the process of completing missing attributes and the process of learning embedding are not separated but closely intertwined. Being specific, completing missing attributes is under the guidance of learning network representation via mutual information maximization, and the complemented attributes directly enter network representation module which will generate further feedback for completing missing attributes. We further impose attribute-structure relationship constraint for completing missing attributes by designing a new generative adversarial networks (GANs) model. To the best of our knowledge, this is the first unified model for attribute-missing network embedding. Empirical results on real-world datasets show the superiority of our new method over other state-of-the-art methods on four network analysis tasks, including node classification, node clustering, link prediction, and network visualization.

关键词： Task analysis Privacy Network topology Network analyzers Mutual information Generators Noise reduction Graph neural networks (GNNs) network embedding node attribute completion

来源：评论

学校读者我要写书评

暂无评论

Scene-Text Oriented Referring Expression Comprehension

引用

ieee TRANSACTIONS ON MULTIMEDIA 2023年 25卷 7208-7221页

作者： Bu, Yuqi Li, Liuwu Xie, Jiayuan Liu, Qiong Cai, Yi Huang, Qingbao Li, Qing South China Univ Technol Sch Software Engn Guangzhou 510006 Peoples R China Key Lab Big Data & Intelligent Robot SCUT MOE China Guangzhou 510006 Peoples R China Guangxi Univ Inst Artificial Intelligence Sch Elect Engn Nanning 530004 Guangxi Peoples R China Guangxi Key Lab Intelligent Control & Maintenance Nanning 530004 Peoples R China Hong Kong Polytech Univ Dept Comp Hong Kong 999077 Peoples R China

Referring expression comprehension (REC) aims to identify and locate a specific object in visual scenes referred to by a natural language expression. Existing studies of REC only focus on basic visual attributes and neglect scene text. Since scene text has the functions of object identification and disambiguation, it is naturally and frequently used to refer to objects. However, existing methods do not explicitly recognize text in images and fail to align scene text mentioned in expressions with the text shown in images, resulting in object localization errors. This article takes the first step toward addressing these limitations. First, we introduce a new task called scene-text oriented referring expression comprehension, which aims to align visual cues and textual semantics of scene text with referring expressions and visual contents. Second, we propose a scene text awareness network that can bridge the gap between texts from two modalities by grounding visual representations of expression-correlated scene texts. Specifically, we propose a correlated text extraction module to solve the problem of lacking semantic understanding, and a correlated region activation module to address the fixed alignment problem and absent alignment problem. These modules ensure that the proposed method focuses on local regions that are most relevant to scene text, thus mitigating the misalignment of scene text with irrelevant regions. Third, to conduct quantitative evaluations, we establish a new benchmark dataset called RefText. Experimental results demonstrate that the proposed method can effectively comprehend scene-text oriented referring expressions and achieves excellent performance.

关键词： visualization Task analysis Semantics Text recognition Pain Natural languages Image recognition Referring expression comprehension scene text representation multimodal alignment

来源：评论

学校读者我要写书评

暂无评论

RiskFix: Supporting Expert Validation of Predictive Timeseries Models in High-Intensity Settings

RiskFix: Supporting Expert Validation of Predictive Timeseri...

引用

25th Eurographics Conference on visualization, EuroVis 2023

作者： Morgenshtern, G. Verma, A. Tonekaboni, S. Greer, R. Bernard, J. Mazwi, M. Goldenberg, A. Chevalier, F. University of Zurich Institute of Informatics Switzerland University of Toronto Department of Computer Science Canada The Hospital for Sick Children Canada Vector Institute Canada Digital Society Initiative Zurich Switzerland

ISBN: (纸本)9783038682196

Many real-world machine learning workflows exist in longitudinal, interactive machine learning (ML) settings. This longitudinal nature is often due to incremental increasing of data, e.g., in clinical settings, where observations about patients evolve over their care period. Additionally, experts may become a bottleneck in the workflow, as their limited availability, combined with their role as human oracles, often leads to a lack of ground truth data. In such cases where ground truth data is small, the validation of interactive machine learning workflows relies on domain experts. Only those humans can assess the validity of a model prediction, especially in new situations that have been covered only weakly by available training data. Based on our experiences working with domain experts of a pediatric hospital’s intensive care unit, we derive requirements for the design of support interfaces for the validation of interactive ML workflows in fast-paced, high-intensity environments. We present RiskFix, a software package optimized for the validation workflow of domain experts of such contexts. RiskFix is adapted to the cognitive resources and needs of domain experts in validating and giving feedback to the model. Also, RiskFix supports data scientists in their model-building work, with appropriate data structuring for the re-calibration (and possible retraining) of ML models. © 2023 The Authors.

关键词： Intensive care units

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：