检索结果-内蒙古大学图书馆

Forecasting Thailand’s Precipitation with Cascading Model of CNN and GRU

学校读者我要写书评

暂无评论

Forecasting Thailand’s Precipitation with Cascading Model o...

International Conference on Information Technology and Electrical engineering (ICITEE)

作者： Fuenglada Manokij Kanoksri Sarinnapakorn Peerapon Vateekul Department of Computer Engineering Faculty of Engineering Chulalongkorn University Big Data Analytics and IoT Center (CUBIC) Chulalongkorn University Bangkok Thailand Hydro-Informatics Institute (Public Organization) Ministry of Higher Education Science Research and Innovation Bangkok Thailand

Precipitation prediction is necessary to use in water management, especially in Thailand, it can be applied for various ways, such as flood warning, agriculture planning, etc. There are many prior attempts to forecast rainfall from the rain-gauge station. Some deployed traditional machine learning approaches: ARIMA, k-NN, etc. Recently, deep learning approach has shown promising results in this task. However, the accuracy is still limited since the raining period throughout the year in Thailand is very scarce, so most rainfall amount is zero. In this paper, we propose to cascade two deep learning networks to tackle this problem: one is a classification model to classify whether it rains or not, and the other is a regression model to predict rainfall amount. Our network is a combination of CNN and GRU, where CNN aims to capture relationship between various sensors and GRU aims to capture time-series information. Furthermore, we also perform multi-step forecasting by applying a rolling mechanism that uses the predicted rainfall and involved features to predict the next 6 steps. The experiment was conducted on hourly rainfall dataset for 6 years (2013-2018) provided from the public government sector in Thailand. We use RMSE as performance metric to evaluate three periods of rainfall: Overall, Rain, and non-rain periods and the results show that our cascading model is the winner with only 4.53% in term of RMSE which is the average percentage of difference from over all regions.

关键词： Deep learning Rain Predictive models data models Sensors Forecasting Task analysis

PathoGraph: A Graph-Based Method for Standardized Representation of Pathology Knowledge

学校读者我要写书评

暂无评论

Scientific data 2025年第1期12卷 872页

作者： Peiliang Lou Yuxin Dong Caixia Ding Chunbao Wang Ruifeng Guo XiaoBo Pang Chen Wang Chen Li School of Computer Science and Technology Xi'an Jiaotong University Xi'an Shaanxi 710049 China. Division of Computational Biology Mayo Clinic Rochester MN USA. Department of Pathology Shaanxi Provincial Tumor Hospital Xi'an Jiaotong University 309 Yanta West Road Xi'an Shaanxi China. Department of Pathology The First Affiliated Hospital of Xi'an Jiaotong University 277 West Yanta Road Xi'an Shaanxi China. Division of Anatomic Pathology Department of Laboratory Medicine and Pathology Mayo Clinic Jacksonville Florida USA. Division of Computational Biology Mayo Clinic Rochester MN USA. wang.chen@mayo.edu. National Engineering Lab for Big Data Analytics Xi'an Jiaotong University Xi'an Shaanxi China. cli@***.

Pathology data, primarily consisting of slides and diagnostic reports, inherently contain knowledge that is pivotal for advancing data-driven biomedical research and clinical practice. However, the hidden and fragmented nature of this knowledge across various data modalities not only hinders its computational utilization, but also impedes the effective integration of AI technologies within the domain of pathology. To systematically organize pathology knowledge for its computational use, we propose PathoGraph, a knowledge representation method that describes pathology knowledge in a graph-based format. PathoGraph can represent: (1) pathological entities' types and morphological features; (2) the composition, spatial arrangements, and dynamic behaviors associated with pathological phenotypes; and (3) the differential diagnostic approaches used by pathologists. By applying PathoGraph to neoplastic diseases, we illustrate its ability to comprehensively and structurally capture multi-scale disease characteristics alongside pathologists' expertise. Furthermore, we validate its computational utility by demonstrating the feasibility of large-scale automated PathoGraph construction, showing performance improvements in downstream deep learning tasks, and presenting two illustrative use cases that highlight its clinical potential. We believe PathoGraph opens new avenues for AI-driven advances in the field of pathology.

关键词：

A ROBUST REPUTATION-BASED GROUP RANKING SYSTEM AND ITS RESISTANCE TO BRIBERY

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Saúde, João Ramos, Guilherme Boratto, Ludovico Caleiro, Carlos Department of Electrical and Computer Engineering Carnegie-Melon University Pittsburgh United States Department of Electrical and Computer Engineering Faculty of Engineering University of Porto Porto Portugal Data Science and Big Data Analytics EURECAT Barcelona Spain SQIG - Instituto de Telecomunicações Dept. of Mathematics Instituto Superior Técnico University of Lisbon Lisbon Portugal

The spread of online reviews and opinions and its growing influence on people’s behavior and decisions, boosted the interest to extract meaningful information from this data deluge. Hence, crowdsourced ratings of products and services gained a critical role in business and governments. Current state-of-the-art solutions rank the items with an average of the ratings expressed for an item, with a consequent lack of personalization for the users, and the exposure to attacks and spamming/spurious users. Using these ratings to group users with similar preferences might be useful to present users with items that reflect their preferences and overcome those vulnerabilities. In this paper, we propose a new reputation-based ranking system, utilizing multipartite rating subnetworks, which clusters users by their similarities using three measures, two of them based on Kolmogorov complexity. We also study its resistance to bribery and how to design optimal bribing strategies. Our system is novel in that it reflects the diversity of preferences by (possibly) assigning distinct rankings to the same item, for different groups of users. We prove the convergence and efficiency of the system. By testing it on synthetic and real data, we see that it copes better with spamming/spurious users, being more robust to attacks than state-of-the-art approaches. Also, by clustering users, the effect of bribery in the proposed multipartite ranking system is dimmed, comparing to the bipartite case. Copyright © 2020, The Authors. All rights reserved.

关键词： data mining

Early Fault Detection in Rolling Element Bearings Using Signal Processing Techniques

学校读者我要写书评

暂无评论

Early Fault Detection in Rolling Element Bearings Using Sign...

International Symposium on High Capacity Optical Networks and Enabling Technologies, HONET

作者： Ali Saeed M. Usman Akram Muazzam A. Khan M. Belal Afsar Department of Computer Science ICESCO Chair Big Data Analytics and Edge Computing Quaid-i-Azam University Islamabad Pakistan Department of Computer and Software Engineering National University of Sciences & Technology Islamabad Pakistan Faculty of Electrical Engineering and Information Technology Otto-von-Guericke University Maddeburg DE

ISBN: (数字)9798350378078

ISBN: (纸本)9798350378085

Many studies show that bearings are the most vulnerable components in low-voltage motors. While advanced bearing diagnostic systems exist, their cost can be a barrier for non-critical machinery due to the potential wait time to see a return on investment. This research explores the feasibility of using basic signal processing techniques on vibration data for bearing condition monitoring. The primary goal is to analyze benchmark data from the Case Western Reserve University (CWRU) dataset and establish a baseline performance for this data-driven approach. The results suggest that, with appropriate signal processing, it's possible to achieve early detection of bearing faults, leading to more efficient time-to-fault identification with higher detection accuracies ranging from 83 % to 100 % for each method.

关键词： Vibrations Fault diagnosis Low voltage Smart cities Rolling bearings Signal processing Motors Robots Monitoring Investment

Untargeted Adversarial Attack on Knowledge Graph Embeddings

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhao, Tianzhe Chen, Jiaoyan Ru, Yanchi Lin, Qika Geng, Yuxia Liu, Jun School of Computer Science and Technology Xi'an Jiaotong University Xi’an China Department of Computer Science The University of Manchester Manchester United Kingdom National University of Singapore Singapore School of Computer Science Hangzhou Dianzi University Hangzhou China National Engineering Lab for Big Data Analytics Xi'an Jiaotong University Xi’an China

Knowledge graph embedding (KGE) methods have achieved great success in handling various knowledge graph (KG) downstream tasks. However, KGE methods may learn biased representations on low-quality KGs that are prevalent in the real world. Some recent studies propose adversarial attacks to investigate the vulnerabilities of KGE methods, but their attackers are target-oriented with the KGE method and the target triples to predict are given in advance, which lacks practicability. In this work, we explore untargeted attacks with the aim of reducing the global performances of KGE methods over a set of unknown test triples and conducting systematic analyses on KGE robustness. Considering logic rules can effectively summarize the global structure of a KG, we develop rule-based attack strategies to enhance the attack efficiency. In particular, we consider adversarial deletion which learns rules, applying the rules to score triple importance and delete important triples, and adversarial addition which corrupts the learned rules and applies them for negative triples as perturbations. Extensive experiments on two datasets over three representative classes of KGE methods demonstrate the effectiveness of our proposed untargeted attacks in diminishing the link prediction results. And we also find that different KGE methods exhibit different robustness to untargeted attacks. For example, the robustness of methods engaged with graph neural networks and logic rules depends on the density of the graph. But rule-based methods like NCRL are easily affected by adversarial addition attacks to capture negative rules. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph embeddings

Improving Software Defined Network Controllers in a Multi-Vendor Environment

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Deneke, Bereketeab Berhanu Beyene, Asrat Mulatu Haile, Endalew Ayenew Department of Computer Science School of Graduate Studies St. Mary’s University Addis Ababa Ethiopia High Performance Computing & Big Data Analytics CoE Department of Electrical and Computer Engineering Addis Ababa Science and Technology University Addis Ababa Ethiopia Adama Science and Technology University School of Electrical Engineering and Computing Electrical Power and Control Engineering Adama Ethiopia

Software Defined Networking (SDN) is an emerging networking paradigm with the potential to foster innovation through programmable networks. SDNs are characterized by the separation of control and data planes where, in a logically centralized controller, it’s possible to make routing decisions on behalf of forwarding elements. For this, there are different protocols used like Open Flow, Forward and Control Element Separation (FORCES), Path Computation Element Protocol (PCEP), Network Configuration Protocol (NETCONF), and Interface to Routing System (IRS). Border Gateway Protocol (BGP) is one such protocol that can enable the network programmability promised by SDNs. The controllers used in BGP as control plane protocol leverages RESTCONF (RFC 8040) as management plane protocol to interact with physical routers, switches, and network service firewalls. Therefore, the aim of this work is to improve the performance of SDN controllers using BGP enabling a multi-vendor environment without requiring infrastructure upgrade showcasing how interoperability can be achieved. The proposed system is implemented using OpenDaylight controllers. The performance of the prototype is evaluated using Latency, Throughput, CPU consumption, and TTL (Time to Live). Based on the simulation results it is observed that the SDN controllers that use BGP show improvements in terms of Latency and Throughput. © 2023, The Authors. All rights reserved.

关键词： Controllers

BioIE: Biomedical Information Extraction with Multi-head Attention Enhanced Graph Convolutional Network

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wu, Jialun Liu, Yang Gao, Zeyu Gong, Tieliang Wang, Chunbao Li, Chen School of Computer Science and Technology Xi’an Jiaotong University Xi’an China National Engineering Lab for Big Data Analytics Xi’an Jiaotong University Xi’an China Department of Pathology the First Affiliated Hospital of Xi’an Jiaotong University Xi’an China

Constructing large-scaled medical knowledge graphs (MKGs) can significantly boost healthcare applications for medical surveillance, bring much attention from recent research. An essential step in constructing large-scale MKG is extracting information from medical reports. Recently, information extraction techniques have been proposed and show promising performance in biomedical information extraction. However, these methods only consider limited types of entity and relation due to the noisy biomedical text data with complex entity correlations. Thus, they fail to provide enough information for constructing MKGs and restrict the downstream applications. To address this issue, we propose Biomedical Information Extraction (BioIE), a hybrid neural network to extract relations from biomedical text and unstructured medical reports. Our model utilizes a multi-head attention enhanced graph convolutional network (GCN) to capture the complex relations and context information while resisting the noise from the data. We evaluate our model on two major biomedical relationship extraction tasks, chemical-disease relation (CDR) and chemical–protein interaction (CPI), and a cross-hospital pan-cancer pathology report corpus. The results show that our method achieves superior performance than baselines. Furthermore, we evaluate the applicability of our method under a transfer learning setting and show that BioIE achieves promising performance in processing medical text from different formats and writing styles. © 2021, CC BY.

关键词： Convolution

Enhancing Global Maritime Traffic Network Forecasting with Gravity-Inspired Deep Learning Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Song, Ruixin Spadon, Gabriel Pelot, Ronald Matwin, Stan Soares, Amilcar Department of Computer Science Memorial University of Newfoundland St. John’sNL Canada Institute for Big Data Analytics Dalhousie University HalifaxNS Canada Industrial Engineering Department Dalhousie University HalifaxNS Canada Institute of Computer Science Polish Academy of Sciences Warsaw Poland Department of Computer Science and Media Technology Linnaeus University Växjö Sweden

Aquatic non-indigenous species (NIS) pose significant threats to biodiversity, disrupting ecosystems and inflicting substantial economic damages across agriculture, forestry, and fisheries. Due to the fast growth of global trade and transportation networks, NIS has been introduced and spread unintentionally in new environments. This study develops a new physics-informed model to forecast maritime shipping traffic between port regions worldwide. The predicted information provided by these models, in turn, is used as input for risk assessment of NIS spread through transportation networks to evaluate the capability of our solution. Inspired by the gravity model for international trades, our model considers various factors that influence the likelihood and impact of vessel activities, such as shipping flux density, distance between ports, trade flow, and centrality measures of transportation hubs. Accordingly, this paper introduces transformers to gravity models to rebuild the short- and long-term dependencies that make the risk analysis feasible. Thus, we introduce a physics-inspired framework that achieves an 89% binary accuracy for existing and non-existing trajectories and an 84.8% accuracy for the number of vessels flowing between key port areas, representing more than 10% improvement over the traditional deep-gravity model. Along these lines, this research contributes to a better understanding of NIS risk assessment. It allows policymakers, conservationists, and stakeholders to prioritize management actions by identifying high-risk invasion pathways. Besides, our model is versatile and can include new data sources, making it suitable for assessing international vessel traffic flow in a changing global landscape. Copyright © 2024, The Authors. All rights reserved.

关键词： Risk assessment

Federated Learning-Based Intelligent Indoor Smoke and Fire Detection System for Smart Buildings

学校读者我要写书评

暂无评论

Federated Learning-Based Intelligent Indoor Smoke and Fire D...

2024 International Conference on Telecommunications and Intelligent Systems, ICTIS 2024

作者： Aymene Berkani, Mohamed Rafik Chouchane, Ammar Himeur, Yassine Abdennebi, Anes Sagiroglu, Seref Amira, Abbes Medea Algeria University Biskra University Center of Barika Laboratory of LI3C Amdoukal Road Barika05001 Algeria University of Dubai College of Engineering and Information Technology Dubai United Arab Emirates École de Technologie Supérieure Software and Information Technology Engineering Montréal Canada Analytics Security R&D Center Gazi University Artificial Intelligence and Big Data Ankara Turkey University of Sharjah Department of Computer Science Sharjah United Arab Emirates

ISBN: (纸本)9798331527396

Ensuring safety in smart buildings is crucial due to the increasing prevalence of smoke and fire hazards in modern environments. This paper introduces a novel privacy-preserving FL approach based on a CNN1D for smoke and fire detection in smart buildings. Our system integrates data from wearable environmental sensors to train a lightweight, edge-deployable DL-CNN1D model, ensuring data privacy while enabling collaborative learning across distributed clients using Federated Averaging (FedAvg) aggregation. Experiments conducted on a comprehensive air measurement dataset for smoke and fire detection demonstrate exceptional performance, with the global model achieving 99.97% accuracy, 99.96% precision, in smoke and fire recognition. Our model demonstrates a low communication cost of 0.4 MB, underscoring its efficiency for real-time applications. Our FL-based approach represents a significant step towards balancing the need for robust safety systems with growing privacy concerns in smart building environments. © 2024 IEEE.

关键词： Federated learning