检索结果-内蒙古大学图书馆

Diffusion-Based Joint Temperature and Precipitation Emulation of Earth System Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Christensen, Katie Otto, Lyric Bassetti, Seth Tebaldi, Claudia Hutchinson, Brian Department of Computer Science Western Washington University BellinghamWA United States Computer Science Department Utah State University LoganUT United States Joint Global Change Research Institute Pacific Northwest National Laboratory College ParkMD United States AI and Data Analytics Division Pacific Northwest National Laboratory RichlandWA United States

Earth system models (ESMs) are the principal tools used in climate science to generate future climate projections under various atmospheric emissions scenarios on a global or regional scale. Generative deep learning approaches are suitable for emulating these tools due to their computational efficiency and ability, once trained, to generate realizations in a fraction of the time required by ESMs. We extend previous work that used a generative probabilistic diffusion model to emulate ESMs by targeting the joint emulation of multiple variables, temperature and precipitation, by a single diffusion model. Joint generation of multiple variables is critical to generate realistic samples of phenomena resulting from the interplay of multiple variables. The diffusion model emulator takes in the monthly mean-maps of temperature and precipitation and produces the daily values of each of these variables that exhibit statistical properties similar to those generated by ESMs. Our results show the outputs from our extended model closely resemble those from ESMs on various climate metrics including dry spells and hot streaks, and that the joint distribution of temperature and precipitation in our sample closely matches those of ESMs. Copyright © 2024, The Authors. All rights reserved.

关键词： Earth system models

Method and steps for diagnosing the possibility of corporate bankruptcy using massive news articles

学校读者我要写书评

暂无评论

IEIE Transactions on Smart Processing and Computing 2020年第1期9卷 13-21页

作者： Jin, Hoon Joo, Dong-Won Department of Computer Science and Engineering Kyonggi University Suwon Korea Republic of Big Data Analytics Team Xinapse Co. Ltd. Seoul Korea Republic of

Abstract: In the aftermath of the fourth industrial revolution, artificial intelligence and big data technology have been used in various fields in South Korea, and the techniques are being applied to, and are complemented by, various service fields in which they had not been introduced before. Especially in order to secure credit stability for companies borrowing from financial institutions, and to preemptively respond to risks, attempts to forecast the possibility of bankruptcy and adopt the forecasts into the actual business are actively conducted by major domestic banks by using online news articles and social networking site data. In this study, we suggest a specified step added to the established machine language analysis processes for opinion mining using massive amounts of text, and we provide an essential tool for it. Also, we designed an algorithm for diagnosing corporate bankruptcy, which has never been proposed in the related research area. Through deep exploratory data analysis and domain-specific data analysis, we implement a rule-based automatic tagger for labeling massive amounts of unlabeled news articles and have devised a novel prediction algorithm. As a result, we achieved 92% accuracy, with an area under the curve of 0.96 with respect to performance, and a hit ratio of 50% among the 26 candidates on a list predicted by financial data analysis. Thus, we recognize that the result of our study is sufficiently complementary to financial data analysis in performance and values, but several limitations remain, such as data coverage, reliability, and incompleteness due to linguistic characteristics. Copyrights © 2020.

关键词： Machine learning

CLAPSep: Leveraging Contrastive Pre-trained Model for Multi-Modal Query-Conditioned Target Sound Extraction

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ma, Hao Peng, Zhiyuan Li, Xu Shao, Mingjie Wu, Xixin Liu, Ju School of Information Science and Engineering Shandong University Qingdao China Department of Computer Science North Carolina State University NC United States ARC Lab Tencent PCG China Stanley Ho Big Data Decision Analytics Research Centre The Chinese University of Hong Kong Hong Kong

Universal sound separation (USS) aims to extract arbitrary types of sounds from real-world recordings. This can be achieved by language-queried target sound extraction (TSE), which typically consists of two components: a query network that converts user queries into conditional embeddings, and a separation network that extracts the target sound accordingly. Existing methods commonly train models from scratch. As a consequence, substantial data and computational resources are required to make the randomly initialized model comprehend sound events and perform separation accordingly. In this paper, we propose to integrate pre-trained models into TSE models to address the above issue. To be specific, we tailor and adapt the powerful contrastive language-audio pre-trained model (CLAP) for USS, denoted as CLAPSep. CLAPSep also accepts flexible user inputs, taking both positive and negative user prompts of uni- and/or multi-modalities for target sound extraction. These key features of CLAPSep can not only enhance the extraction performance but also improve the versatility of its application. We provide extensive experiments on 5 diverse datasets to demonstrate the superior performance and zero- and few-shot generalizability of our proposed CLAPSep with fast training convergence, surpassing previous methods by a significant margin. Full codes and some audio examples are released for reproduction and evaluation1 © 2024, CC BY.

关键词： Query languages

All in One: Multi-Task Prompting for Graph Neural Networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Sun, Xiangguo Cheng, Hong Li, Jia Liu, Bo Guan, Jihong Department of Systems Engineering and Engineering Management Shun Hing Institute of Advanced Engineering The Chinese University of Hong Kong Hong Kong Data Science and Analytics Thrust The Hong Kong University of Science and Technology Guangzhou China School of Computer Science and Engineering Southeast University Purple Mountain Laboratories China Department of Computer Science and Technology Tongji University China

Recently, "pre-training and fine-tuning" has been adopted as a standard workflow for many graph tasks since it can take general graph knowledge to relieve the lack of graph annotations from each application. However, graph tasks with node level, edge level, and graph level are far diversified, making the pre-training pretext often incompatible with these multiple tasks. This gap may even cause a "negative transfer" to the specific application, leading to poor results. Inspired by the prompt learning in natural language processing (NLP), which has presented significant effectiveness in leveraging prior knowledge for various NLP tasks, we study the prompting topic for graphs with the motivation of filling the gap between pre-trained models and various graph tasks. In this paper, we propose a novel multi-task prompting method for graph models. Specifically, we first unify the format of graph prompts and language prompts with the prompt token, token structure, and inserting pattern. In this way, the prompting idea from NLP can be seamlessly introduced to the graph area. Then, to further narrow the gap between various graph tasks and state-of-the-art pre-training strategies, we further study the task space of various graph applications and reformulate downstream problems to the graph-level task. Afterward, we introduce meta-learning to efficiently learn a better initialization for the multi-task prompt of graphs so that our prompting framework can be more reliable and general for different tasks. We conduct extensive experiments, results from which demonstrate the superiority of our method. Copyright © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

Safeguarding Privacy for Cloud Computing's Encrypted data Using Association Rule Mining Algorithm and FP Growth Algorithm

学校读者我要写书评

暂无评论

Safeguarding Privacy for Cloud Computing's Encrypted Data Us...

Delhi Section Conference (DELCON), IEEE

作者： D. MohanaPriya P. Anu N. Kalyani S. Rekha R. Praba S. Sasikala Department of Computer Science PSG College of Arts & Science Coimbatore Tamilnadu India School of Computing SASTRA Deemed to be University Thanjavur Tamilnadu India Department of Information Technology Dr. N. G. P. Arts and Science College Coimbatore Tamilnadu India Department of Data Analytics (PG) PSGR Krishnammal College for Women Coimbatore Tamilnadu India

ISBN: (数字)9798331518592

ISBN: (纸本)9798331518608

In an effort to support data privacy, safeguarding privacy guidelines for association mining techniques have recently been presented. Nevertheless, the algorithms are unable to conceal data frequency and have an extra expense when inserting fictitious objects or transactions. In this research, we present a connection constraint mining technique for cloud computing encrypted data that protects confidentiality. In order to accomplish the data mining operations using the two cloud servers, the strategy first uses propagated encryption, which impairs the cloud infrastructure’ encryption capabilities and shields the server from active attacks. Second, our approach uses combinations, coincidence masking, and cybernetic transactions in tandem to conceal the information while mining in order to safeguard the privacy of the association rule utilized in the extraction procedure. We use the FP growth algorithm for rule-mining for associations avoiding the need for extra fraudulent transactions. Therefore, the suggested technique can hide data frequency while ensuring query and data privacy. We show that, with regard to the time requirements of the Mining Association, the recommended strategy operates roughly three to five times better than the current algorithm.

关键词： data privacy Cloud computing Privacy Encryption Association rule learning Servers Cybernetics Guidelines

IoT-Enhanced Innovations in Drug Delivery Systems for Targeted Therapy in Autoimmune Disorders

学校读者我要写书评

暂无评论

IoT-Enhanced Innovations in Drug Delivery Systems for Target...

International Conference on Advanced Computing and Communication Systems (ICACCS)

作者： V Bhuvaneshwari R Sadaieswaran P Malathi N Legapriyadharshini T Thirumalaikumari S R Raja Department of Computer Science and Engineering Acharya College of Engineering Achariyapuram Puducherry India Department of Computer Applications Tagore College of arts and science Chennai Tamil Nadu India Department of Data Analytics Saveetha College of Liberal Arts and Sciences SIMATS Deemed to be University Chennai Tamil Nadu India Department of Computer Application Saveetha College of Liberal Arts and Sciences Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India Department of Computer Science Saveetha College of Liberal Arts and Sciences SIMATS Deemed to be University Chennai Tamil Nadu India

ISBN: (数字)9798350384369

ISBN: (纸本)9798350384376

The growing number of autoimmune diseases necessitates the needs novel drug delivery system alternatives to improve targeted therapy. The study deals with the immediate requirement for improvements by investigating the limitations of existing systems, highlighting their limitations in precision, patient adherence, and real-time monitoring. The proposed system combines Internet of Things (IoT) technology into medicine distribution, providing an extensive structure that makes use of smart devices, sensors, and networking solutions. The integration attempts to improve patient participation and treatment efficacy by ensuring tailored regimens. The study demonstrates promising discoveries in optimizing therapeutic interventions, cost-effectiveness, and data-driven insights through an in-depth evaluation of case studies and successful implementations. The proposed IoT-enhanced drug delivery system not only addresses the limitations of existing systems but also represents an evolution for healthcare professionals and pharmaceutical businesses. Patient privacy and data security are essential for ethical and regulatory reasons. The study's results and analysis highlight the proposed system's potential for overcoming limitations and enhancing targeted therapy for autoimmune disorders, setting the groundwork for a future in which IoT seamlessly interacts with drug delivery systems to transform patient care.

关键词： data privacy data security Transforms Drug delivery Sensor systems Real-time systems Autoimmune diseases Internet of Things Smart devices Intelligent sensors

Link Prediction with Contextualized Self-Supervision

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhang, Daokun Yin, Jie Yu, Philip S. The Department of Data Science & AI Faculty of Information Technology Monash University Australia The Discipline of Business Analytics The University of Sydney Australia Department of Computer Science University of Illinois Chicago United States

Link prediction aims to infer the link existence between pairs of nodes in networks/graphs. Despite their wide application, the success of traditional link prediction algorithms is hindered by three major challenges—link sparsity, node attribute noise and dynamic changes—that are faced by many real-world networks. To address these challenges, we propose a Contextualized Self-Supervised Learning (CSSL) framework that fully exploits structural context prediction for link prediction. The proposed CSSL framework learns a link encoder to infer the link existence probability from paired node embeddings, which are constructed via a transformation on node attributes. To generate informative node embeddings for link prediction, structural context prediction is leveraged as a self-supervised learning task to boost the link prediction performance. Two types of structural context are investigated, i.e., context nodes collected from random walks vs. context subgraphs. The CSSL framework can be trained in an end-to-end manner, with the learning of model parameters supervised by both the link prediction and self-supervised learning tasks. The proposed CSSL is a generic and flexible framework in the sense that it can handle both attributed and non-attributed networks, and operate under both transductive and inductive link prediction settings. Extensive experiments and ablation studies on seven real-world benchmark networks demonstrate the superior performance of the proposed self-supervision based link prediction algorithm over state-of-the-art baselines, on different types of networks under both transductive and inductive settings. The proposed CSSL also yields competitive performance in terms of its robustness to node attribute noise and scalability over large-scale networks. © 2022, CC BY-NC-ND.

关键词： Supervised learning

The effect of data Augmentation Using SMOTE: Diabetes Prediction by Machine Learning Techniques 23

学校读者我要写书评

暂无评论

The effect of Data Augmentation Using SMOTE: Diabetes Predic...

Proceedings of the 2023 6th Artificial Intelligence and Cloud Computing Conference

作者： A. Al-Qerem A. M Ali M. Alauthman M. Al Khaldy A. Aldweesh Computer Science Department Faculty of Information Technology Zarqa University Jordan Communications and Computer Engineering Department Faculty of Engineering Al-Ahliyya Amman University Jordan Department of Information Security Faculty of Information Technology University of Petra Jordan Business Inteligence & Data Analytics University of Petra Jordan College of Computing and Information Technology Shaqra University Saudi Arabia

ISBN: (纸本)9798400716225

Diabetes mellitus, a severe and enduring condition characterized by impaired glucose metabolism, poses a substantial threat to public health. Its pervasive impact continues to escalate globally, with a rising incidence that challenges preventive measures. Despite earnest efforts, individuals struggle to evade the clutches of diabetes, necessitating innovative approaches for disease management. Traditional methodologies in diabetes health monitoring exhibit limitations, prompting the exploration of advanced techniques. This study employs machine learning (ML) methods to delve into diabetes, aiming to enhance diagnostic accuracy. The primary objective is to develop a method capable of precise diabetes diagnoses with a heightened level of precision. The investigation incorporates machine learning algorithms, specifically Random Forest (RF), K Nearest Neighbor (KNN), and Logistic Regression. The inclusion of these algorithms seeks to streamline data processing ***, this study incorporates the Synthetic Minority Over-sampling Technique (SMOTE) as a data augmentation strategy. SMOTE addresses imbalances in the dataset, contributing to a more robust and representative sample. The research evaluates the effectiveness and accuracy of diabetes prediction using these algorithms both before and after SMOTE implementation. By considering the impact of SMOTE, the study aims to determine the optimal algorithm for assessing diabetes development. The comparative analysis sheds light on how SMOTE enhances the overall performance of machine learning models. This nuanced approach not only refines diabetes diagnostic protocols but also underscores the significance of addressing data imbalances in predictive modeling for enhanced precision in disease prediction.

关键词： Classification data augmentation Diabetes

Colon Cancer Tissue Classification Using ML

学校读者我要写书评

暂无评论

Colon Cancer Tissue Classification Using ML

International Conference on Information Systems and computer Networks (ISCON)

作者： Ashish Tripathi Kuldeep Kumar Anuradha Misra Brijesh Kumar Chaurasia Department of Computer Science and Engineering Amity School of Engineering & Technology Amity University Lucknow Lucknow Uttar Pradesh India Center for Data Analytics Bond Business School Bond University Gold Coast Queensland Australia Department of Computer Science and Engineering Pranveer Singh Institute of Technology Kanpur Uttar Pradesh India

In this paper, the classification of colon cancer tissues by means of machine learning approaches is evaluated. In today’s world, a revolutionary advancement has come in the classification and diagnosis of diseases in the medical and healthcare sectors. Deep learning classifiers and machine learning methods are now broadly applied to accurately diagnose a number of diseases. Cancer is one of the world’s most significant roots of death, appealing to the lives of one person out of every six. As per the national library of medicine, the third leading cause of death worldwide is colorectal cancer. Identifying an illness at a premature stage increases the chances of survival. Automated diagnosis and the classification of tissues from images can be completed much more quickly with the use of artificial intelligence. A publicly available IoT dataset CRC–VAL–HE–7K consisting of 7180 images, distributed among nine types of colorectal tissues: background, lymphocytes, adipose, mucus, colorectal adenocarcinoma epithelium, normal colon mucosa, debris, cancer-associated stroma, and, smooth muscle is used after preprocessing. Feature extraction is done by applying Differential-Box-Count on all blocks of images. The dataset is evaluated by these Machine Learning (ML) procedures: K-Nearest Neighbor, Support Vector Machine, Decision Tree, Random Forest, Extreme Gradient Boosting, and Gaussian Naive Bayes. Results show that the performance of Extreme Gradient Boosting is the best and most viable approach.

关键词： Deep learning Support vector machines Machine learning algorithms Transfer learning Feature extraction Boosting Colon