检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Staugaard, Benjamin Eichler Madsen, Simon Soele Ma, Zheng Yussof, Salman Jørgensen, Bo Nørregaard SDU Center for Energy Informatics Maersk Mc-Kinney Moller Institute University of Southern Denmark Odense Denmark Institute of Informatics and Computing in Energy Universiti Tenaga Nasional Kajang43000 Malaysia

In recent years, the building sector has experienced an increasing legislative pressure to reduce the energy consumption. This has created a global need for affordable building management systems (BMS) in areas such as lighting-, temperature-, air quality monitoring and control. BMS uses 2D and 3D building representations to visualize various aspects of building operations. Today the creation of these visual building representations relies on labor-intensive and costly computer-aided design (CAD) processes. Hence, to create affordable BMS there is an urgent need to develop methods for cost-effective automatic creation of visual building representations. This paper introduces an automatic, metadata-driven method for constructing building visualizations using metadata from existing smart building infrastructure. The method presented in this study utilizes a Velocity Verlet integration-based physics particle simulation that uses metadata to define the force dynamics within the simulation. This process generates an abstract point cloud representing the organization of BMS components into building zones. The developed system was tested in two buildings of respectively 2,560 m2 and 18,000 m2. The method successfully produced visual building representations based on the available metadata, demonstrating its feasibility and cost-effectiveness. © 2024, CC BY.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

Visualizing Model Behaviors for Clinic Users: Explaining A Clinical Prediction Model for 30-day Readmission after Inpatient Alcohol Dependence Treatment

Visualizing Model Behaviors for Clinic Users: Explaining A C...

引用

IEEE International Conference on Healthcare informatics (ICHI)

作者： Ou Stella Liang Christopher C. Yang Kate Gliske Jacqueline Braughton Quyen Ngo College of Computing and Informatics Drexel University Philadelphia U.S.A Butler Center for Research Hazelden Betty Ford Foundation Center City U.S.A

ISBN: (数字)9798350383737

ISBN: (纸本)9798350383744

Machine learning models for predicting alcohol use relapse lack adequate explanations. This study aims to utilize visualization techniques to (1) highlight a machine learning model's predictive reasoning and biases; and (2) to identify the risk factors associated with readmission following inpatient treatment for alcohol use disorder. Our visualizations show that first, the model was reliable in its negative predictions but had difficulty in correctly identifying positive instances with missing variable values; second, a history of multiple treatments may distinguish otherwise similar instances; and third, highly impactful risk factors for 30-day readmission included a history of multiple treatments and lower participation in treatment. The visualizations when considered together could help clinical users understand model biases.

关键词： Visualization Machine learning Mental health Medical services Predictive models Cognition History

来源：评论

学校读者我要写书评

暂无评论

Unprecedented Smart Algorithm for Uninterrupted SDN Services During DDoS Attack

引用

Computers, Materials & Continua 2022年第1期70卷 875-894页

作者： Muhammad Reazul Haque Saw Chin Tan Zulfadzli Yusoff Kashif Nisar Rizaludin Kaspin Iram Haider Sana Nisar J.P.C.Rodrigues Bhawani Shankar Chowdhry Muhammad AslamUqaili Satya Prasad Majumder Danda B.Rawat Richard Etengu Rajkumar Buyya Faculty of Computing&Informatics Multimedia UniversityPersiaranMultimediaCyberjaya63100SelangorMalaysia Faculty of Engineering Multimedia UniversityPersiaran MultimediaCyberjaya63100SelangorMalaysia Faculty of Computing and Informatics University Malaysia SabahJalan UMSKota Kinabalu Sabah88400Malaysia Telekom Malaysia Research&Development TM Innovation Centre63000CyberjayaSelangorMalaysia Federal University of Piauí(UFPI) TeresinaPIBrazil Instituto de Telecomunica珲es 6201-001Covilh?Portugal National Center of Robotics and Automation-Condition Monitoring Systems Lab MUETJamshoroPakistan Department of Electrical and Electronic Engineering BUETDhaka1205Bangladesh Department of Electrical Engineering and Computer Science Data Science and Cybersecurity CenterHoward UniversityWashingtonDCUSA Cloud Computing and Distributed Systems(CLOUDS)Laboratory School of Computing and Information SystemsThe University of MelbourneMelbourneVIC 3053Australia

In the design and planning of next-generation Internet of Things(IoT),telecommunication,and satellite communication systems,controller placement is crucial in software-defined networking(SDN).The programmability of the SDN controller is sophisticated for the centralized control system of the entire ***,it creates a significant loophole for the manifestation of a distributed denial of service(DDoS)attack ***,recently a Distributed Reflected Denial of Service(DRDoS)attack,an unusual DDoS attack,has been ***,minimal deliberation has given to this forthcoming single point of SDN infrastructure failure ***,recently the high frequencies of DDoS attacks have increased *** this paper,a smart algorithm for planning SDN smart backup controllers under DDoS attack scenarios has *** proposed smart algorithm can recommend single or multiple smart backup controllers in the event of DDoS *** obtained simulated results demonstrate that the validation of the proposed algorithm and the performance analysis achieved 99.99%accuracy in placing the smart backup controller under DDoS attacks within 0.125 to 46508.7 s in SDN.

关键词： SDN smart algorithm RTZLK-DAASCP DDoS attack DRDoS

来源：评论

学校读者我要写书评

暂无评论

Event Time Extraction from Japanese News Archives

Event Time Extraction from Japanese News Archives

引用

2022 IEEE International Conference on Big Data, Big Data 2022

作者： Peng, Siqi Yamamoto, Akihiro Mori, Shinsuke Sekino, Tatsuki Kyoto University Graduate School of Informatics Kyoto Japan Kyoto University Academic Center for Computing and Media Studies Kyoto Japan National Institutes for the Humanities International Research Center for Japanese Studies Kyoto Japan

ISBN: (纸本)9781665480451

This paper proposes an integrated method for extracting the time information of events from Japanese news archives. We first utilize a new pattern-based method named TRE/ERT combined with a neural-based model to extract all temporal expressions possibly related with an event. Then, we apply a simple but efficient clustering and narrowing process to summarize these temporal expressions into a small time frame for events lasting shorter than a day, or time frames for the beginning and the end days of the events for events spanning multiple days. We conducted two experiments where the results show that when working with one-day events, our system has a precision high up to 57% and the rate that the actual date of the event falls in our extracted time frame reaches 100% as long as the event name is found in the archive. The results also show that our system works with multiple-day events, but needs further improvements to get better results. © 2022 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Initial Development and Performance Evaluation of a Bengali Voice-Operated Virtual Assistant for Personal Computer Control 64

Initial Development and Performance Evaluation of a Bengali ...

引用

2023 IEEE 64th International Scientific Conference on Information Technology and Management Science of Riga Technical University, ITMS 2023

作者： Quiah, Raven Mark Akter, Soma Ahmed, Shad Rahman, Mohammad Masudur Alam, Sanzar Adnan Islam, Ashraful Center for Computational and Data Sciences Independent University Bangladesh Dhaka Bangladesh Independent University Bangladesh Department of Cse Dhaka Bangladesh School of Computing and Informatics University of Louisiana at Lafayette Louisiana United States Independent University Bangladesh Center for Computational and Data Sciences Department of Cse Dhaka Bangladesh

ISBN: (纸本)9798350370294

This paper presents the preliminary development and performance evaluation of a personal computer assistant designed for voice-operated interaction in Bengali. A bespoke phonetic grammar has been devised to map Bengali phonemes onto English representations, and an algorithm has been developed to mitigate the confusion of the machine in recognizing the same type of phonetics in the language, which helps to enhance the precision in comprehending Bengali commands. The system integrates the Microsoft speech synthesizer to articulate speech in Bengali, which facilitates the expansive human-computer interaction capabilities of the system, particularly for visually impaired individuals who face challenges in text-based computer interactions. The applications of this system extend among Bengali speakers and hold potential utility within rural regions of Bangladesh. The system also aims to replace the traditional mouse and keyboard for users with their own voice commands in their native language. Upon successful implementation of the system, it achieved 92.5% accuracy in the noise-free environment and 76.4% accuracy in the noisy environment with the help of 10 Bangladeshi individuals, including both males and females. © 2023 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Intent Classification from Online Forums for Phuket Medical Tourism 20

Intent Classification from Online Forums for Phuket Medical ...

引用

20th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2023

作者： Laosen, Nasith Laosen, Kanjana Ardharn, Jaturawit Phuket Rajabhat University Faculty of Science and Technology Phuket Thailand Prince of Songkla University Phuket Campus Andaman Intelligent Tourism and Service Informatics Center College of Computing Phuket Thailand Rangsit University Faculty of Radiological Technology Pathumthani Thailand

ISBN: (纸本)9798350310467

Social media makes healthcare and medical information readily available to medical tourists. The medical tourists use social media for searching and communicating about their intents. As the questions posted on social media are rapidly increased, the difficulty to read all questions by human is increased as well. Hospitals running medical tourism business also need to know the needs of medical tourists for improving services and providing the right products to them. The needs or intents of medical tourists can be found on questions that they ask. Therefore, the objective of this study is to collect and classify intents of medical tourists from the questions posted on online forums. In this study, we collect questions related to medical tourism from the TripAdvisor website. We use natural language processing (NLP) to pre-process the questions and classify them using two neural network models, i.e., a BiLSTM model and a BERT model. The experimental result shows that the BERT model provides better performance with 94.22% of accuracy. We also analyze the results and summarize shortcomings of the dataset and the models. © 2023 IEEE.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Systematic Analysis of Federated Learning Approaches for Intrusion Detection in the Internet of Things Environment

引用

IEEE Access 2025年 13卷 95410-95444页

作者： Nuha A. Hamad Khairul Azmi Abu Bakar Faizan Qamar Ahmed Mahdi Jubair Rajina R. Mohamed Mohamad Afendee Mohamed Center for Cyber Security Faculty of Information Science and Technology Universiti Kebangsaan Malaysia (UKM) Bangi Selangor Malaysia University Headquarter University of Anbar Anbar Iraq College of Computer Science and Information Technology University of Anbar Anbar Iraq College of Computing and Informatics Universiti Tenaga Nasional Kajang Malaysia Faculty of Informatics and Computing Universiti Sultan Zainal Abidin Kuala Terengganu Malaysia

The Internet of Things (IoT) has transformed various sectors by connecting devices, services, and applications, which boosts intelligence and operational efficiency. However, this growing connectivity has heightened concerns regarding data privacy and security, particularly for sensitive information. Intrusion detection systems (IDSs) have emerged as an effective strategy by incorporating machine learning (ML) methodologies to identify sophisticated cybersecurity threats. Traditional IDS solutions typically rely on centralized learning architectures, where data from edge nodes are transferred to central servers for analysis. This approach is effective but introduces major risks to the privacy of IoT data. Artificial intelligence (AI), specifically federated learning (FL), is a new frontier that offers an alternative option by enabling the direct implementation of distributed ML on IoT devices without requiring the sharing of raw data. FL supports decentralized and privacy-preserving learning, which makes it a critical instrument for enhancing the security of IoT ecosystems. Data security and privacy research in FL is increasingly becoming popular. However, the development of FL for IoT remains in its infancy and requires exploration in various areas. Moreover, current survey studies are limited and overlook the vital aspects of FL, particularly the diversity of datasets and the most recent methodologies employed in FL-enabled IDSs. This study conducts a systematic literature review that examines 43 studies published between 2020 and 2024. The focus revolves around recent advancements in applying AI to intrusion detection within IoT environments. This study comprehensively analyzes key ML models and datasets used to develop an IDS tailored for IoT systems. The review also explores emerging trends, challenges, and opportunities in implementing FL-based IDSs in IoT networks. The findings highlight the potential of FL to tackle pressing privacy and security challenges w

关键词： Internet of Things Security Privacy Data privacy Intrusion detection Taxonomy Systematic literature review Surveys Federated learning Computer architecture

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Learning Architectures for Histological Image Segmentation

Hybrid Deep Learning Architectures for Histological Image Se...

引用

International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

作者： Md Jahid Hasan Wan Siti Halimatul Munirah Wan Ahmad Mohammad Faizal Ahmad Fauzi Fazly Salleh Abas Faculty of Engineering Multimedia University Cyberjaya Malaysia Center for Visual Computing Faculty of Computing and Informatics Faculty of Engineering Multimedia University Cyberjaya Malaysia Faculty of Engineering and Technology Multimedia University Cyberjaya Malaysia

In histopathology image analysis, accurate segmentation of nuclei holds immense significance, particularly in the early detection and treatment of diseases like breast cancer. Nuclei segmentation is a fundamental but challenging task because of the intricate variations in nuclear shapes, sizes, densities, and overlapping instances. In this paper, we evaluate eight convolutional neural network (CNN) models, two of them existing models namely U-Net, SegNet, and six hybrid models by combining U-Net and SegNet modify decoder with ResNet, VGG and DenseNet (ResNet-UNet, ResNet-SegNet, VGG-UNet, VGG-SegNet, DenseNet-UNet, and DenseNet-SegNet. This experiment aims to identify the best deep-learning model for segmenting hematoxylin and eosin (H&E) stain images using a publicly available dataset called MoNuSeg. From the experimented work, we found that VGG-UNet outperforms other models with an F1 score of 0.8452 and IoU of 0.6929 respectively. This research will serve as a foundation for the future construction of more complex deep learning models with cascade or any combination of the models studied.

关键词：

来源：评论

学校读者我要写书评

暂无评论

User Schedule and Single-User RIS Allocation in QoS-Aware MmWave Vehicular Networks

User Schedule and Single-User RIS Allocation in QoS-Aware Mm...

引用

IEEE International Conference on Communications (ICC)

作者： Haowen Bai Ying Ju Jiawei Hu Haoyu Wang Qingqi Pei Mian Ahmad Jan Celimuge Wu School of Telecommunications Engineering Xidian University Xi'an China Center for Pervasive Communications and Computing University of California at Irvine CA USA College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Graduate School of Informatics and Engineering University of Electro-Communications Tokyo Japan

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

The combination of millimeter-wave (mmWave) and massive MIMO techniques can fulfill high data rate requirements for vehicular networks. However, due to the elevated path loss and severe blocking effects in mmWave propagation, the downlink data service of vehicles will seriously deteriorate. Fortunately, reconfigurable intelligent surface (RIS) can serve as a single-user relay to mitigate individual performance degradation without additional power consumption. In this paper, we propose a deep reinforcement learning (DRL)-based joint user schedule and RIS-User pairing scheme for the dynamic mmWave vehicular network to alleviate the blocking effects and maximize the total transmission data volume while ensuring the quality of service (QoS) for all target vehicles. In this scheme, each target vehicle has a distinct QoS constraint called minimum service data volume, which is a long-term and posterior optimization problem. Thus, QoS constraints are introduced in the reward design of the DRL algorithm, and the problem of high-dimensional action spaces is addressed by utilizing two nested Dueling Double-DQN (D-D3QN) networks. Simulation results demonstrate the superiority of our scheme in mmWave vehicular networks.

关键词： Schedules Simulation Quality of service Reconfigurable intelligent surfaces Dynamic scheduling Robustness Resource management

来源：评论

学校读者我要写书评

暂无评论

An analytical approach for optimization of computer network design considering the integration of the communication and power infrastructures

An analytical approach for optimization of computer network ...

引用

作者： Guimarães, Almir Maciel, Paulo Matias, Rivalino Silva, Bruno Nogueira, Bruno Institute of Computing Federal University of Alagoas Maceio Brazil Center of Informatics Federal University of Pernambuco Recife Brazil School of Computer Science Federal University of Uberlandia Uberlandia Brazil

Nowadays, computer networks are critical to the success of small and large businesses. They connect people, support applications and services, and provide access to the resources that keep the businesses running. Our work proposes analytical models and a methodology for supporting the optimization of the network infrastructure design, considering both technical and business oriented metrics, such as availability, reliability, and total cost. The integration of communication and power infrastructures is supported by this methodology. The dependability (availability/reliability) models were created using the Reliability Block Diagram and Stochastic Petri Net modeling mechanisms following a hierarchical approach. A case study considering the design of a real-world network infrastructure is presented to illustrate the proposed methodology. The results showed a significant reduction in the design complexity as well as an improvement in the relationship between technical and business aspects. © 2021 John Wiley & Sons, Ltd.

关键词： Stochastic 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：