检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Gong, Jibing Lin, Yuting Zhao, Yi Lin, Tianyu Fang, Xiaohan Feng, Xinchao Peng, Jiquan School of Information Science and Engineering Yanshan University Qinhuangdao066004 China The Key Laboratory for Computer Virtual Technology System Integration of Hebei Province Yanshan University Qinhuangdao066004 China

Knowledge Graphs have been practical tools to represent and integrate plentiful structural and semantic information in mainstream industrial scenarios. While promising, the heterogeneity and complexity of KGs pose a formidable obstacle, especially for graph representation learning. Most existing KG embedding models omit the dynamic high-order connectivity patterns, and heavily rely on the handcrafted patterns to handle the complex semantic relationships, thereby limiting their ability to adaptively capture nuanced and intricate relationships of knowledge graphs in different tasks. To fill this gap, we present ReHGD — a model designed for KGs that focuses on adaptively designing typed graphlets through a cooperative Multi-agent Reinforcement Learning algorithm. This approach can learn more discriminative graph representations tailored to specific downstream tasks. Specifically, ReHGD engages in the creation of typed graphlets through a two-stage process: it (1) establishes a reinforced chain design module to generate chains without predefined rules, and (2) employs a buffer-aware sampling technique to derive episodic chains from prior experiences. Subsequently, motifs are deduced by applying commute count and Hadamard product operations to the episodic chain-based subgraphs. Finally, ReHGD utilize chain and motif aggregations to learn graph representations. Experimental results on three real-world KGs show that ReHGD outperforms baselines on entity classification. © 2023, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Approximate state estimation with large-scale sensor networks under event-based sensor scheduling strategy

Approximate state estimation with large-scale sensor network...

引用

IEEE Conference on Decision and Control

作者： Xinhui Liu Meiqi Cheng Dawei Shi Ling Shi MIIT Key Laboratory of Servo Motion System Drive and Control School of Automation Beijing Institute of Technology Beijing China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Kowloon Hong Kong China

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

In this paper, we investigate the issues of real-time sensor scheduling and state estimator design within large-scale sensor network systems. Specifically, data redundancy sometimes occurs in large-scale sensor arrays due to the excessive proximity of sensing units in the spatial domain, leading to high similarity in their measurement data. Currently, it is difficult to account for such redundancy in sensor scheduling algorithms found in existing literature, where the optimal subset of sensors is generally selected by optimizing objective functions formulated from certain performance criteria. To tackle this problem, we introduce an event-based sensor scheduling strategy, the triggering condition of which is designed founded on the similarity of sensor data, so as to identify the most informative subset of sensors for state estimation. To evaluate the impact of the sensor scheduling protocol on system observability, we propose a new notion of $\mathscr{E}(\varepsilon)$-observability, based on which an observability criterion is derived. In addition, we have designed a set-valued state estimation algorithm, which takes into account the intricate measurement information structure inherent within the sensor selection mechanism. The performance enhancement of the proposed estimator is also investigated. Finally, numerical experiments are conducted to validate the effectiveness of the proposed estimation algorithm and to verify the performance improvement.

关键词： Protocols Event detection Scheduling algorithms Redundancy Approximation algorithms Real-time systems Sensors State estimation Observability Sensor arrays

来源：评论

学校读者我要写书评

暂无评论

Generative Positive-Unlabeled Classification for Hunting Small Open Reading Frames

Generative Positive-Unlabeled Classification for Hunting Sma...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Jie Chen Wenbin Liao Du Wen Jianqiang Li Fangzhong Wang College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Laboratory of Synthetic Microbiology School of Chemical Engineering & Technology Tianjin University China

The annotation of Open Reading Frames (ORFs) is a crucial step in gene annotation, as it precisely delineates the specific regions of expressed genes. However, small Open Reading Frames (smORFs), in comparison to ORFs, are shorter in length, exhibit lower expression abundance, and are more challenging to predict. Particularly in the presence of noise in prokaryotic data and limited availability of positive sample data, the difficulty of prediction is amplified. Therefore, it is necessary to study smORF prediction methods. However, current machine learning models use limited data for modeling and overlook the existence of undiscovered positive samples within the negative samples. Additionally, they do not incorporate prior knowledge that can be calibrated to enhance the 3-nt periodicity. This work utilizes a multimodal VAE for data dimensionality reduction and employs a GAN to generate latent vectors for data augmentation. It incorporates PU learning to leverage unknown samples and combines Riboseq data from experiments with and without antibiotic treatment. Additionally, an adversarial training mechanism is employed to enhance the model’s robustness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Study on Drones and Big Data for Supply Chain Optimization Using a Novel Approach

A Comprehensive Study on Drones and Big Data for Supply Chai...

引用

Advanced Computing and Emerging Technologies (ACET), International Conference on

作者： Dankan Gowda V D Palanikkumar Suganthi. N A.S. Malleswari Sanjog Thapa Rama Chaithanya Tanguturi Department of Electronics and Communication Engineering BMS Institute of Technology and Management Bangalore Karnataka Department of Computer Science and Engineering Dr NGP Institute of Technology Coimbatore Tamilnadu India Department of Electrical and Electronics Engineering Dayananda Sagar College of Engineering Bangalore Karnataka India Department of Computer Science & Engineering Aditya College of Engineering and Technology Surampalem Andhra Pradesh India Department of Information System and Analysis Lamar University Beaumont Texas USA School of Business Woxsen University Hyderabad India

ISBN: (数字)9798350367720

ISBN: (纸本)9798350367737

This research paper aims to provide qualitative and quantitative insights regarding the application of drones and big data techniques in the SCM field through a new scientific method. The proposed method exploits the opportunities of drones for real-time data capturing and big data technologies to enrich decision making in supply chain. The study is pertinent to modern tendencies in supply chain systems and proves the efficiency of the new method through the precise calculations and contrastive analysis. The following are some of the findings that suggest efficiency, cost decrease, and outstanding performance of the supply chain. The studies being offered in this research will prove beneficial for practitioners and researchers who endeavor to advance the concepts and practice of logistics and supply chain management.

关键词： Costs Supply chain management Supply chains Demand forecasting Big Data Real-time systems Security Reliability Drones Resilience

来源：评论

学校读者我要写书评

暂无评论

Classification And Prediction of Brain Tumors and its Types using Deep Learning

Classification And Prediction of Brain Tumors and its Types ...

引用

Computational Intelligence, Communication Technology and Networking (CICTN), International Conference on

作者： Madhvan Bajaj Priyanshu Rawat Aastha Bhatt Vikrant Sharma Ayushi Jain Navneet Kumar Computer Science and Engineering Graphic Era Hill University Dehradun India BSc Nursing College of Nursing CH (cc) Lucknow Uttar Pradesh School of Computer & System Sciences Jawaharlal Nehru University New Delhi India

Brain tumors are a major source of illness and mortality globally, with about 11,700 persons diagnosed with one each year. Brain tumor diagnosis and categorization are critical for proper treatment planning, which can increase patients' life expectancy. Due to the intricacy of brain tumors and their attributes, the traditional approach of manual assessment of brain MRI images might be error-prone. Automated classification approaches based on Machine Learning (ML) and Artificial Intelligence (AI) have been shown to be more accurate than manual categorization. Deep Learning techniques including Convolutional Neural Networks (CNNs), Artificial Neural Networks (ANNs), and Transfer Learning (TL) have shown promising results for the automatic categorization of brain MRI images in this context. These automated procedures can save time and lessen the possibility of misdiagnosis, but they should always be used in tandem with clinical experience. The suggested method has the potential to significantly improve the accuracy and efficiency of brain tumor identification and categorization for doctors and radiologists globally.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Method for Discovering Hidden Patterns of Cybersecurity Knowledge Based on Hierarchical Clustering∗ 6

A Method for Discovering Hidden Patterns of Cybersecurity Kn...

引用

6th IEEE International Conference on Data science in Cyberspace, DSC 2021

作者： Ding, Zhaoyun Cao, Deqi Liu, Lina Yu, Donghua Ma, Haoyang Wang, Fei National University Of Defense Technology Key Laboratory Of Information System Engineering Changsha China School Of Electronic And Information Engineering Soochow University Suzhou China Shaoxing University Department Of Computer Science And Engineering Shaoxing China

ISBN: (纸本)9781665418157

The construction of cybersecurity knowledge graphs improves the full-dimensional cognitive ability of cyber threats. However, most of the current research on the cybersecurity knowledge graphs focuses on the one-hop or multi-hop correlation queries of knowledge, while ignoring the hidden patterns in the knowledge graphs. Based on the knowledge graph stated in this paper[1], we propose a method for discovering hidden patterns of cybersecurity knowledge based on hierarchical clustering, using the hacker group features of security technologies in the knowledge graph, calculating the distance between the security technology knowledge in the knowledge graph based on the Phicoefficient, and mining cybersecurity technologies that are often used by hacker groups by employing the ward linkage method of hierarchical clustering. The experimental results show that three similar cybersecurity technologies, namely Peripheral Device Discovery, Data from Removable Media and Junk Data, all of which are aimed at stealing or attacking the externally-connected devices of computers, are used by most hacker groups. © 2021 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Advancing Survey on Multi-Tenant Cloud Environments: Challenges and Solutions

Advancing Survey on Multi-Tenant Cloud Environments: Challen...

引用

Intelligent systems for Cybersecurity (ISCS), International Conference on

作者： Bhawani Shanker Amina Tufail Chandradeep Bhatt Keshav Kaushik Ahthasham Sajid Inam Ullah Khan Department of Information Security Riphah Institute of System Engineering Islamabad Pakistan Department of CSE Graphic Era Hill University Uttarakhand India Graphic Era Deemed to be University Dehradun Uttarakhand India School of Computer Science University of Petroleum and Energy Studies Dehradun India Department of Computer Science SZABIST Islamabad Pakistan

ISBN: (数字)9798350375237

ISBN: (纸本)9798350375244

This research examines cloud forensic challenges and solutions using quantitative methodologies. Major challenges in cloud forensics, including data dispersion, loss of control, multi-tenancy, and integrity/authenticity, were identified. The effectiveness of cloud forensic tools was evaluated, with Tool 2 identified as the most effective. Factors A and B were found to influence tool adoption. Emerging trends in cloud forensics, such as advancements in cloud technologies and new security threats, were explored. The study provides valuable insights for practitioners and researchers, informing decision-making in addressing challenges, selecting tools, and considering future directions in cloud forensics.

关键词： Surveys Forensics Decision making Organizations Market research Intelligent systems computer security

来源：评论

学校读者我要写书评

暂无评论

Enhancing Acute Kidney Injury Prediction through Integration of Drug Features in Intensive Care Units

arXiv

引用

arXiv 2024年

作者： Manalu, Gabriel D.M. Christian, Mulomba Mukendi You, Songhee Choi, Hyebong Department of Computer Science and Electrical Engineering Handong Global University Korea Republic of Department of Advanced Convergence Handong Global University Korea Republic of School of Spatial Environment System Engineering Handong Global University Korea Republic of School of Global Entrepreneurship and ICT Handong Global University Korea Republic of

The relationship between acute kidney injury (AKI) prediction and nephrotoxic drugs, or drugs that adversely affect kidney function, is one that has yet to be explored in the critical care setting. One contributing factor to this gap in research is the limited investigation of drug modalities in the intensive care unit (ICU) context, due to the challenges of processing prescription data into the corresponding drug representations and a lack in the comprehensive understanding of these drug representations. This study addresses this gap by proposing a novel approach that leverages patient prescription data as a modality to improve existing models for AKI prediction. We base our research on Electronic Health Record (EHR) data, extracting the relevant patient prescription information and converting it into the selected drug representation for our research, the extended-connectivity fingerprint (ECFP). Furthermore, we adopt a unique multimodal approach, developing machine learning models and 1D Convolutional Neural Networks (CNN) applied to clinical drug representations, establishing a procedure which has not been used by any previous studies predicting AKI. The findings showcase a notable improvement in AKI prediction through the integration of drug embeddings and other patient cohort features. By using drug features represented as ECFP molecular fingerprints along with common cohort features such as demographics and lab test values, we achieved a considerable improvement in model performance for the AKI prediction task over the baseline model which does not include the drug representations as features, indicating that our distinct approach enhances existing baseline techniques and highlights the relevance of drug data in predicting AKI in the ICU setting. Copyright © 2024, The Authors. All rights reserved.

关键词： Intensive care units

来源：评论

学校读者我要写书评

暂无评论

Geo-Enhanced High-Order Feature Interaction Network for Cloud API QoS Prediction 19th

Geo-Enhanced High-Order Feature Interaction Network for Clou...

引用

19th CCF Conference on computer Supported Cooperative Work and Social Computing, ChineseCSCW 2024

作者： Ma, Xinhong Zeng, Yehong Qi, Mingyang Si, Yali Chen, Zhen School of Information Science and Engineering Yanshan University Qinhuangdao066004 China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan University Qinhuangdao066004 China Changshu Institute of Technology Jiangsu Changshu215500 China

ISBN: (纸本)9789819623754

In the era of open cloud, cloud API is an important component and key enabling technology to achieve efficient data transmission, artificial intelligence algorithm empowerment, and software development cost reduction and efficiency. With the proliferation of cloud API with similar functionality, quality of service (QoS) becomes essential for differentiating cloud API performance, and QoS-driven prediction for cloud API has emerged as a critical topic for high quality cloud API selection. However, existing methods often inadequately utilize contextual information in resource-constrained scenario, limiting the improvement of cloud API prediction performance. We in this paper propose a geo-enhanced high-order feature interaction network (GHFIN) for cloud API QoS prediction. Firstly, a correlation analysis was conducted on real-world QoS dataset to explore the relationship between QoS data and geospatial context. Then, we design a geo-enhanced strategy that effectively utilizes the hierarchical relationships of geospatial entities (country, province, city, and district) through an offline real-time coordinate conversion module. On this basis, a geo-enhanced cloud API QoS prediction network GHFIN was designed, which aims to learn the high-order feature interactions through layer-wise feature stacking. Experimental results on two real-world QoS datasets illustrate the effectiveness of GHFIN compared to the classic and state-of-the-art methods, and our extensive analysis shows how the geospatial context and high-order feature interaction positively impact the performance of cloud API QoS prediction. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Decision support system for handling intervention on toddlers stunting cases in Indonesia using the certainty factor method 10

Decision support system for handling intervention on toddler...

引用

10th International Seminar on New Paradigm and Innovation of Natural sciences and itsApplication, ISNPINSA 2020

作者： Sutoyo, I.W. Widodo, A.P. Rochim, A.F. Department of Information System Post Graduated School Diponegoro University Indonesia Department of Physics Faculty of Science and Mathematics Diponegoro University Indonesia Department of Computer Engineering Faculty Engineering Diponegoro University Indonesia

Stunting is a condition of failure to thrive in children under five caused by lack of nutritional intake for a long time and the occurrence of repeated infections. The causative factor is influenced by inadequate parenting, especially in the first 1,000 days of life. This study applies a decision support system with an expert system as an intervention for handling stunting by providing solutions using the Certainty Factor method. This expert system is implemented using the PHP programming language, and the use of expert systems will be easier when implemented into web-based applications. The test results are acceleration in reducing the number of stunting cases, thus providing the right percentage and solution in handling and increasing supervision of government efforts to combat stunting. Stunting intervention research can see the results of the percentage value of sensitive and specific interventions for pregnant women, nursing mothers, and adolescent girls. Testing uses black-box validation and accuracy. The validation results are in the form of 100%, which shows the system functionality can run well and according to the list of requirements. The accuracy result is 83% which shows that the expert system can function quite well according to the Certainty Factor method. © Published under licence by IOP Publishing Ltd.

关键词： Decision support systems

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：