检索结果-内蒙古大学图书馆

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： Weicong Chen Hao Qi Xiaoyi Lu Curtis Tatsuoka Department of Computer and Data Sciences Case Western Reserve University Cleveland USA Department of Computer Science and Engineering University of California Merced Merced USA Department of Medicine University of Pittsburgh Pittsburgh USA

The COVID-19 pandemic underscored the necessity for disease surveillance using group testing. Novel Bayesian methods using lattice models were proposed, which offer substantial improvements in group testing efficiency by precisely quantifying uncertainty in diagnoses, acknowledging varying individual risk and dilution effects, and guiding optimally convergent sequential pooled test selections using a Bayesian Halving Algorithm. Computationally, however, Bayesian group testing poses considerable challenges as computational complexity grows exponentially with sample size. This can lead to shortcomings in reaching a desirable scale without practical limitations. We propose a new framework for scaling Bayesian group testing based on Spark: SBGT. We show that SBGT is lightning fast and highly scalable. In particular, SBGT is up to 376x, 1733x, and 1523x faster than the state-of-the-art framework in manipulating lattice models, performing test selections, and conducting statistical analyses, respectively, while achieving up to 97.9% scaling efficiency up to 4096 CPU cores. More importantly, SBGT fulfills our mission towards reaching applicable scale for guiding pooling decisions in wide-scale disease surveillance, and other large scale group testing applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Behavioural Network Traffic Novelty Detection for the Internet of Things Infrastructures 1

引用

11th International Symposium on Parallel Architectures, Algorithms and Programming, PAAP 2020

作者： Hamad, Salma Abdalla Sheng, Quan Z. Tran, Dai Hoang Zhang, Wei Emma Nepal, Surya Department of Computing Faculty of Science and Engineering Macquarie University Sydney Australia School of Computer Science The University of Adelaide Adelaide Australia Data61 CSIRO Sydney Australia

ISBN: (数字)9789811600104

ISBN: (纸本)9789811600098

The Internet of Things (IoT) applied solutions are changing the way the world perceives technology. IoT devices are now being used in a wide range of applications to transfer or share relevant information, hence reducing human interventions. With such widespread IoT solutions, security becomes a significant concern. Many of the IoT devices are vulnerable due to several reasons, including in-secure implementations, poor life cycle management, and inappropriate configurations, leading to an increase in the risk of these devices getting exposed and attacked. However, the current security approaches for detecting compromised IoT devices are inefficient, especially for zero-day attacks. Since no one knows how a new attack would look like, it will be useful to monitor and detect anomalies using accurate detection techniques. This work probes the possibility of detecting IoT network traffic anomalies using novelty detection techniques;thus, it can detect compromised IoT devices. One of this work’s main contributions is developing an IoT anomaly detection system named Behavioural Novelty Detection for IoT Infrastructure (BND-IoT). BND-IoT trains a neural network with novel selected behavioural features extracted from benign traffic only and then uses the novelty techniques to detect any unusual traffic patterns. We show that the presented approach effectively detects anomalies within IoT devices’ network traffic with a robust average F1-score of 96.7% and a low false rejection rate of 7%. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Insurance Contract for High Renewable Energy Integration

Insurance Contract for High Renewable Energy Integration

引用

2022 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids, SmartGridComm 2022

作者： Zhao, Dongwei Wang, Hao Huang, Jianwei Lin, Xiaojun Mit Energy Initiative Massachusetts Institute of Technology United States Monash University Department of Data Science and Artificial Intelligence Australia School of Science and Engineering The Chinese University of HongKong Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society China Elmore Family School of Electrical and Computer Engineering Purdue University United States

ISBN: (数字)9781665432542

ISBN: (纸本)9781665432542

The increasing penetration of renewable energy poses significant challenges to power grid reliability. There have been increasing interests in utilizing financial tools, such as insurance, to help end-users hedge the potential risk of lost load due to renewable energy variability. With insurance, a user pays a premium fee to the utility, so that he will get compensated in case his demand is not fully satisfied. A proper insurance design needs to resolve the following two challenges: (i) users' reliability preference is private information;and (ii) the insurance design is tightly coupled with the renewable energy investment decision. To address these challenges, we adopt the contract theory to elicit users' private reliability preferences, and we study how the utility can jointly optimize the insurance contract and the planning of renewable energy. A key analytical challenge is that the joint optimization of the insurance design and the planning of renewables is non-convex. We resolve this difficulty by revealing important structural properties of the optimal solution, using the help of two benchmark problems: the no-insurance benchmark and the social-optimum benchmark. Compared with the no-insurance benchmark, we prove that the social cost and users' total energy cost are always no larger under the optimal contract. Simulation results show that the largest benefit of the insurance contract is achieved at a medium electricity-bill price together with a low type heterogeneity and a high renewable uncertainty. © 2022 IEEE.

关键词： Insurance

来源：评论

学校读者我要写书评

暂无评论

Ethical Considerations in Explainable AI: Balancing Transparency and User Privacy in English Language-based Virtual Assistants 5

Ethical Considerations in Explainable AI: Balancing Transpar...

引用

5th International Conference on Intelligent Communication Technologies and Virtual Mobile Networks, ICICV 2024

作者： Alijoyo, Franciskus Antonius Sandya Sneha Sri, S. Alapati, Purnachandra Rao Yuldashev, Dilyorjon Ponni Valavan, M. Center for Risk Management and Sustainability Indonesia School of Business and Information Technology Stmik Likmi Bandung Indonesia Krishna University Andhra Pradesh India Prasad v Potluri Siddhartha Institute of Technology Andhra Pradesh Vijayawada Kanuru India Turin Polytechnic University in Tashkent Automatic Control and Computer Engineering Department Tashkent Uzbekistan K.Ramakrishnan College of Engineering Trichy Department of Artificial Intelligence and Data Science Tamil Nadu India

ISBN: (纸本)9798350385649

English Language-Based Virtual Assistants (ELB-VAs) are AI-powered systems designed to comprehend and respond to user queries in the English language, exemplified by virtual assistants like Siri or Alexa. The need for balancing transparency and user privacy in ELB-VAs is paramount due to their pervasive integration into daily life. Ensuring transparency imbues user trust, while safeguarding privacy addresses ethical concerns associated with personal data. Existing methods involve clear privacy policies, user-controlled data sharing settings, and encryption. However, drawbacks include user confusion and potential biases. To address these limitations, this study proposes a novel approach. Methodologically, it integrates pre-processing techniques such as lowercasing and tokenization, coupled with a Natural Language Understanding model. This model undergoes intent and entity recognition training, enhancing accuracy, and incorporates privacy-aware response generation, ensuring informative yet privacy-conscious interactions. The implementation of the study's results is carried out using Python tools, showcasing improved metrics and response times. This approach contributes to a more transparent and privacy-respecting user experience, aligning with evolving ethical norms and setting the stage for advancements in ELB-VA technology. This comprehensive exploration bridges existing gaps, emphasizing the ethical imperative of user-centric and privacy-aware AI interactions in ELB- VAs. The proposed NLU model exhibits a substantial increase in accuracy compared to other methods, with an impressive accuracy value of 99.1%• On average, it outperforms the Random Forest and Decision Tree models by 15.7 percentage points, highlighting its superior predictive capabilities in the evaluated task. This comprehensive exploration aligns with evolving ethical norms and establishes a foundation for future advancements in ELB-VA technology. © 2024 IEEE.

关键词： Transparency

来源：评论

学校读者我要写书评

暂无评论

Empirical Evaluation of License Plate Recognition Using Tensorflow Framework

Empirical Evaluation of License Plate Recognition Using Tens...

引用

BIT Conference (BITCON), International

作者： S. Sowmyayani V. S. Harilakshmi J. Kavitha R. Roselinkiruba Department of Computer (SF) St. Mary’s College (Autonomous) (Affiliated to Manonmaniam Sundaranar University Tirunelveli) Thoothukudi Tamilnadu India Department of Artificial Intelligence and Data Science Holy Cross College (Autonomous) Nagercoil Tamilnadu India Department of Computer Science and Engineering VelTech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamilnadu India

ISBN: (数字)9798331518394

ISBN: (纸本)9798331518400

Due to the tremendous increase in vehicles, more attention is required to Intelligent Transport Systems (ITS). License Plate Recognition (LPR) is one such method in ITS. Although there are several researches on LPR, still the issues are partially solved. This is because license plate images suffer from low illumination, side view, etc. This paper developed a method to recognize license plates. It consists of license plate localization, segmentation and recognition. A Convolutional Neural Network (CNN) is designed for recognition. The proposed method is tested on the Chinese City Parking dataset (CCPD), Chinese License Plate dataset (CLPD), Application Oriented License Plate (AOLP) and PKUdata datasets. The performance of the proposed LPR method is evaluated using accuracy. It outperforms other recent methods by achieving an accuracy of 95%

关键词： Location awareness Image segmentation Accuracy Image recognition Codes Urban areas Lighting Convolutional neural networks License plate recognition

来源：评论

学校读者我要写书评

暂无评论

Continual Reinforcement Learning for Digital Twin Synchronization Optimization

引用

IEEE Transactions on Mobile Computing 2025年

作者： Tong, Haonan Chen, Mingzhe Zhao, Jun Hu, Ye Yang, Zhaohui Liu, Yuchen Yin, Changchuan Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System Architecture and Convergence Beijing Advanced Information Network Laboratory Beijing China College of Computing and Data Science Singapore University of Miami Department of Electrical and Computer Engineering Frost Institute for Data Science and Computing Coral Gables33146 United States University of Miami Department of Industrial and Systems Engineering Coral Gables33146 United States Zhejiang University College of Information Science and Electronic Engineering Hangzhou310027 China North Carolina State University Department of Computer Science RaleighNC27695 United States Beijing Key Laboratory of Network System Architecture and Convergence China Beijing University of Posts and Telecommunications Beijing Advanced Information Network Laboratory Beijing100876 China

This article investigates the adaptive resource allocation scheme for digital twin (DT) synchronization optimization over dynamic wireless networks. In our considered model, a base station (BS) continuously collects factory physical object state data from wireless devices to build a real-time virtual DT system for factory event analysis. Due to continuous data transmission, maintaining DT synchronization must use extensive wireless resources. To address this issue, a subset of devices is selected to transmit their sensing data, and resource block (RB) allocation is optimized. This problem is formulated as a constrained Markov process (CMDP) problem that minimizes the long-term mismatch between the physical and virtual systems. To solve this CMDP, we first transform the problem into a dual problem that refines RB constraint impacts on device scheduling strategies. We then propose a continual reinforcement learning (CRL) algorithm to solve the dual problem. The CRL algorithm learns a stable policy across historical experiences for quick adaptation to dynamics in physical states and network capacity. Simulation results show that the CRL can adapt quickly to network capacity changes and reduce normalized root mean square error (NRMSE) between physical and virtual states by up to 55.2%, using the same RB number as traditional methods. © 2025 IEEE. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

A Unified Framework for Preoperative Early Recurrence Prediction of Hepatocellular Carcinoma with Multi-phase CT Images 10th

A Unified Framework for Preoperative Early Recurrence Predic...

引用

10th KES International Conference on Innovation in Medicine and Healthcare, KES-InMed 2022

作者： Ouyang, Shuyi Xu, Yingying Wang, Weibin Li, Yinhao Wang, Fang Chen, Qingqing Lin, Lanfen Chen, Yen-Wei Hu, Hongjie College of Computer Science and Technology Zhejiang University Hangzhou310000 China Research Center for Healthcare Data Science Zhejiang Lab Hangzhou311121 China College of Information Science and Engineering Ritsumeikan University Shiga Kusatsu525-8577 Japan Department of Radiology Sir Run Run Shaw Hospital Zhejiang University Hangzhou310000 China

ISBN: (纸本)9789811934391

Early recurrence (ER) after surgery is one of the main causes of death in Hepatocellular Carcinoma (HCC). Making an effective prediction of the risk of ER is important in developing treatment strategies. The existing methods generally use radiomic features or simple deep learning features, which have insufficient feature representation capabilities. Here, we present a deep learning-based strategy for obtaining enriched multi-phase fusion features that can effectively represent feature information. We present an effective preoperative prediction model that uses multi-phase CT scans as input. Our proposed framework significantly utilizes and enhances multi-phase contextual information by effectively performing multi-phase feature fusion. We also present a novel backbone network with attention mechanisms called Inv-ResNet, that can extract more discriminative features from each CT phase using ResNet block and involution operator. Further, we design a Multi-Phase Feature Fusion Module that allows for global-Squeeze and phase-Excitation of important feature weights across all CT phases to selectively fuse features. In comparison to existing methods of preoperative prediction of ER of HCC, our method achieves 72.70% accuracy and a value of 0.7478 area under the ROC curve (AUC), which is the highest accuracy. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Secure Cloud Storage for IoT Healthcare Using BiGRU and BiLSTM Models

Blockchain-Based Secure Cloud Storage for IoT Healthcare Usi...

引用

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： Prachi Arihant Chougule Sarumathi S Ravi Kant Raj Kumar Gupta U. Pushpa Latha Anvesh Perada Department of Electrical Engineering DKTE Society's Tetile and Engineering Institute Ichalkaranji India Department of Computer Science and Engineering HKBK College of Engineering Bangalore India Department of Computer and Data Sciences YSAICDS Shoolini University Solan India Department of Physics Sardar Vallabhbhai Patel College Bhabua VKSU Ara India Department of English Malla Reddy Engineering College (Autonomous) Hyderabad India Department of Electrical and Computer Engineering Drexel University Philadelphia United States of America

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

Machine Learning (ML) algorithms have experienced a significant increase in popularity owing to the digitisation of analogue processes and other technological advancements, like the Internet of Things (IoT). Dependable datasets are crucial for the precise forecasting and resolution abilities of these algorithms, which are indispensable in healthcare, cloud computing, engineering, and finance. Conversely, training datasets are vulnerable to manipulation, thereby skewing the results. To address this issue, blockchain-based approaches have been proposed to enhance the reliability and security of cloud-stored E-Health data generated by the Internet of Things. To improve the accuracy and efficacy of healthcare prediction models, our study focusses on an advanced strategy that integrates feature selection with model training. Optimal input data is refined by feature selection employing entropy and correlation coefficient methodologies. The proposed model, employing BiGRU and BiLSTM, surpasses conventional CNNs and BiRNNs, with an average accuracy of 94.57%. When integrated with the Internet of Things (IoT), blockchain technology ensures the secure storage and transmission of electronic health records (EHRs). This strategy enhances predictive accuracy and safeguards sensitive health data in cloud infrastructures by amalgamating feature selection techniques with robust deep learning models.

关键词： Training Cloud computing Accuracy Bidirectional long short term memory Medical services Predictive models Feature extraction Internet of Things Security Secure storage

来源：评论

学校读者我要写书评

暂无评论

Hiding Scrambling Text Message in Speech Signal Based on Lightwight Hyperchaotic Map and Conditional Lsb Mechanisms

SSRN

引用

SSRN 2023年

作者： Al Sibahee, Mustafa A. Abduljaleel, Iman Qays Luo, Chengwen Zhang, Jin Huang, Yijing Abduljabbar, Zaid Ameen Ma, Junchao National Engineering Laboratory for Big Data System Computing Technology Shenzhen Technology University 518060 China Department of Computer Science College of Computer Science and Information Technology University of Basrah 61004 Iraq College of Computer Science and Software Engineering Shenzhen University 518060 China Department of Computer Science College of Education for Pure Sciences University of Basrah Basrah61004 Iraq Technical Computer Engineering Department Al-kunooze University College Basrah61001 Iraq Huazhong University of Science and Technology Shenzhen Institute Shenzhen518118 China College of Big Data and Internet Shenzhen Technology University Shenzhen518118 China

This study proposed a lightweight and secure audio steganography system for hiding text messages during transmission over the Internet to address the computational cost exaggeration, and Insufficient levels of security in earlier studies. The paper proposes a two-phase functioning mechanism. Text characters are transformed into ASCII code and then stored in a vector, which is then divided into three sub-vectors. The sub-vectors are scrambled using a two low complexity operation, namely a forwardbackward reading technique and an odd-even index. Two scrambling circuits can be performed: the first on tiny sub-vectors and another on the vector as a whole. In the hiding phase, the speech signal samples were divided into 256 blocks using only 200 values per block, and low complexity Quadratic and the Hénon maps to hide the speech signal in a random manner. This method utilizes the conditional LSB as low complexity algorithm to identify hidden bits and a special hyperchaotic map algorithm for randomly choosing locations. The proposed approach provides good security for a scrambled text message with high SNR and PSNR, small MSE error and PESQ, SSIM near one, BER close to zero, and MOS near five as well as the lowest computational hiding cost. © 2023, The Authors. All rights reserved.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

ML Based Phenotype Analysis Using Differential Gene Expression data in Schizophrenia

ML Based Phenotype Analysis Using Differential Gene Expressi...

引用

Smart Technologies in Computing, Electrical and Electronics (ICSTCEE), International Conference on

作者： Aadhithyan D Shabarirajan KJ Varun Maniappan Shivanesh B Divya S Praghaadeesh R Kalpana Raja I R Oviya Department of Computer Science and Engineering (Artificial Intelligence) Amrita Vishwa Vidyapeetham Chennai India Section for Biomedical Informatics and Data Science School of Medicine Yale University New Haven Connecticut USA

ISBN: (数字)9798350384628

ISBN: (纸本)9798350384635

In this paper, differential gene expression (DGE) data in schizophrenia is analysed using machine learning approaches with the objective of predicting cell phenotypes related to the condition. The dataset contains information on cis eQTNs, gene orientation, probe information, gene expression profiles, and SNP information. When first investigating well-known machine learning methods, a hybrid model combining Random Forests and XGBoost is suggested, however it only offers a little increase. Increases in predicted accuracy of more than 99.12% are made possible by the H2O AutoML package. The results demonstrate the capability of ML-based analysis to unravel the underlying biological mechanisms of schizophrenia and contribute to the design of individualised therapeutic approaches. The paper represents the capability of machine learning to comprehend the relationship between gene expression patterns and complicated illnesses like schizophrenia.

关键词： Water Training Accuracy Phenotypes Mental disorders Predictive models data models

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：